| 1498 742 756 1501 29 29 29 29 29 29 29 29 1439 1439 1015 490 1472 8 1 1 1468 36 1441 453 1124 1407 1487 124 741 738 1043 511 1414 1485 71 71 74 4 7 64 71 71 74 74 7 3 1 1 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/read_write.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/slab.h> #include <linux/stat.h> #include <linux/sched/xacct.h> #include <linux/fcntl.h> #include <linux/file.h> #include <linux/uio.h> #include <linux/fsnotify.h> #include <linux/security.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/pagemap.h> #include <linux/splice.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/fs.h> #include <linux/filelock.h> #include "internal.h" #include <linux/uaccess.h> #include <asm/unistd.h> const struct file_operations generic_ro_fops = { .llseek = generic_file_llseek, .read_iter = generic_file_read_iter, .mmap_prepare = generic_file_readonly_mmap_prepare, .splice_read = filemap_splice_read, .setlease = generic_setlease, }; EXPORT_SYMBOL(generic_ro_fops); static inline bool unsigned_offsets(struct file *file) { return file->f_op->fop_flags & FOP_UNSIGNED_OFFSET; } /** * vfs_setpos_cookie - update the file offset for lseek and reset cookie * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * @cookie: cookie to reset * * Update the file offset to the value specified by @offset if the given * offset is valid and it is not equal to the current file offset and * reset the specified cookie to indicate that a seek happened. * * Return the specified offset on success and -EINVAL on invalid offset. */ static loff_t vfs_setpos_cookie(struct file *file, loff_t offset, loff_t maxsize, u64 *cookie) { if (offset < 0 && !unsigned_offsets(file)) return -EINVAL; if (offset > maxsize) return -EINVAL; if (offset != file->f_pos) { file->f_pos = offset; if (cookie) *cookie = 0; } return offset; } /** * vfs_setpos - update the file offset for lseek * @file: file structure in question * @offset: file offset to seek to * @maxsize: maximum file size * * This is a low-level filesystem helper for updating the file offset to * the value specified by @offset if the given offset is valid and it is * not equal to the current file offset. * * Return the specified offset on success and -EINVAL on invalid offset. */ loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize) { return vfs_setpos_cookie(file, offset, maxsize, NULL); } EXPORT_SYMBOL(vfs_setpos); /** * must_set_pos - check whether f_pos has to be updated * @file: file to seek on * @offset: offset to use * @whence: type of seek operation * @eof: end of file * * Check whether f_pos needs to be updated and update @offset according * to @whence. * * Return: 0 if f_pos doesn't need to be updated, 1 if f_pos has to be * updated, and negative error code on failure. */ static int must_set_pos(struct file *file, loff_t *offset, int whence, loff_t eof) { switch (whence) { case SEEK_END: *offset += eof; break; case SEEK_CUR: /* * Here we special-case the lseek(fd, 0, SEEK_CUR) * position-querying operation. Avoid rewriting the "same" * f_pos value back to the file because a concurrent read(), * write() or lseek() might have altered it */ if (*offset == 0) { *offset = file->f_pos; return 0; } break; case SEEK_DATA: /* * In the generic case the entire file is data, so as long as * offset isn't at the end of the file then the offset is data. */ if ((unsigned long long)*offset >= eof) return -ENXIO; break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so as long as * offset isn't i_size or larger, return i_size. */ if ((unsigned long long)*offset >= eof) return -ENXIO; *offset = eof; break; } return 1; } /** * generic_file_llseek_size - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @maxsize: max size of this file in file system * @eof: offset used for SEEK_END position * * This is a variant of generic_file_llseek that allows passing in a custom * maximum file size and a custom EOF position, for e.g. hashed directories * * Synchronization: * SEEK_SET and SEEK_END are unsynchronized (but atomic on 64bit platforms) * SEEK_CUR is synchronized against other SEEK_CURs, but not read/writes. * read/writes behave like SEEK_SET against seeks. */ loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof) { int ret; ret = must_set_pos(file, &offset, whence, eof); if (ret < 0) return ret; if (ret == 0) return offset; if (whence == SEEK_CUR) { /* * If the file requires locking via f_pos_lock we know * that mutual exclusion for SEEK_CUR on the same file * is guaranteed. If the file isn't locked, we take * f_lock to protect against f_pos races with other * SEEK_CURs. */ if (file_seek_cur_needs_f_lock(file)) { guard(spinlock)(&file->f_lock); return vfs_setpos(file, file->f_pos + offset, maxsize); } return vfs_setpos(file, file->f_pos + offset, maxsize); } return vfs_setpos(file, offset, maxsize); } EXPORT_SYMBOL(generic_file_llseek_size); /** * generic_llseek_cookie - versioned llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @cookie: cookie to update * * See generic_file_llseek for a general description and locking assumptions. * * In contrast to generic_file_llseek, this function also resets a * specified cookie to indicate a seek took place. */ loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, u64 *cookie) { struct inode *inode = file->f_mapping->host; loff_t maxsize = inode->i_sb->s_maxbytes; loff_t eof = i_size_read(inode); int ret; if (WARN_ON_ONCE(!cookie)) return -EINVAL; /* * Require that this is only used for directories that guarantee * synchronization between readdir and seek so that an update to * @cookie is correctly synchronized with concurrent readdir. */ if (WARN_ON_ONCE(!(file->f_mode & FMODE_ATOMIC_POS))) return -EINVAL; ret = must_set_pos(file, &offset, whence, eof); if (ret < 0) return ret; if (ret == 0) return offset; /* No need to hold f_lock because we know that f_pos_lock is held. */ if (whence == SEEK_CUR) return vfs_setpos_cookie(file, file->f_pos + offset, maxsize, cookie); return vfs_setpos_cookie(file, offset, maxsize, cookie); } EXPORT_SYMBOL(generic_llseek_cookie); /** * generic_file_llseek - generic llseek implementation for regular files * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is a generic implementation of ->llseek useable for all normal local * filesystems. It just updates the file offset to the value specified by * @offset and @whence. */ loff_t generic_file_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file->f_mapping->host; return generic_file_llseek_size(file, offset, whence, inode->i_sb->s_maxbytes, i_size_read(inode)); } EXPORT_SYMBOL(generic_file_llseek); /** * fixed_size_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: size of the file * */ loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: case SEEK_END: return generic_file_llseek_size(file, offset, whence, size, size); default: return -EINVAL; } } EXPORT_SYMBOL(fixed_size_llseek); /** * no_seek_end_llseek - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * */ loff_t no_seek_end_llseek(struct file *file, loff_t offset, int whence) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, OFFSET_MAX, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek); /** * no_seek_end_llseek_size - llseek implementation for fixed-sized devices * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * @size: maximal offset allowed * */ loff_t no_seek_end_llseek_size(struct file *file, loff_t offset, int whence, loff_t size) { switch (whence) { case SEEK_SET: case SEEK_CUR: return generic_file_llseek_size(file, offset, whence, size, 0); default: return -EINVAL; } } EXPORT_SYMBOL(no_seek_end_llseek_size); /** * noop_llseek - No Operation Performed llseek implementation * @file: file structure to seek on * @offset: file offset to seek to * @whence: type of seek * * This is an implementation of ->llseek useable for the rare special case when * userspace expects the seek to succeed but the (device) file is actually not * able to perform the seek. In this case you use noop_llseek() instead of * falling back to the default implementation of ->llseek. */ loff_t noop_llseek(struct file *file, loff_t offset, int whence) { return file->f_pos; } EXPORT_SYMBOL(noop_llseek); loff_t default_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); loff_t retval; retval = inode_lock_killable(inode); if (retval) return retval; switch (whence) { case SEEK_END: offset += i_size_read(inode); break; case SEEK_CUR: if (offset == 0) { retval = file->f_pos; goto out; } offset += file->f_pos; break; case SEEK_DATA: /* * In the generic case the entire file is data, so as * long as offset isn't at the end of the file then the * offset is data. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } break; case SEEK_HOLE: /* * There is a virtual hole at the end of the file, so * as long as offset isn't i_size or larger, return * i_size. */ if (offset >= inode->i_size) { retval = -ENXIO; goto out; } offset = inode->i_size; break; } retval = -EINVAL; if (offset >= 0 || unsigned_offsets(file)) { if (offset != file->f_pos) file->f_pos = offset; retval = offset; } out: inode_unlock(inode); return retval; } EXPORT_SYMBOL(default_llseek); loff_t vfs_llseek(struct file *file, loff_t offset, int whence) { if (!(file->f_mode & FMODE_LSEEK)) return -ESPIPE; return file->f_op->llseek(file, offset, whence); } EXPORT_SYMBOL(vfs_llseek); static off_t ksys_lseek(unsigned int fd, off_t offset, unsigned int whence) { off_t retval; CLASS(fd_pos, f)(fd); if (fd_empty(f)) return -EBADF; retval = -EINVAL; if (whence <= SEEK_MAX) { loff_t res = vfs_llseek(fd_file(f), offset, whence); retval = res; if (res != (loff_t)retval) retval = -EOVERFLOW; /* LFS: should only happen on 32 bit platforms */ } return retval; } SYSCALL_DEFINE3(lseek, unsigned int, fd, off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(lseek, unsigned int, fd, compat_off_t, offset, unsigned int, whence) { return ksys_lseek(fd, offset, whence); } #endif #if !defined(CONFIG_64BIT) || defined(CONFIG_COMPAT) || \ defined(__ARCH_WANT_SYS_LLSEEK) SYSCALL_DEFINE5(llseek, unsigned int, fd, unsigned long, offset_high, unsigned long, offset_low, loff_t __user *, result, unsigned int, whence) { int retval; CLASS(fd_pos, f)(fd); loff_t offset; if (fd_empty(f)) return -EBADF; if (whence > SEEK_MAX) return -EINVAL; offset = vfs_llseek(fd_file(f), ((loff_t) offset_high << 32) | offset_low, whence); retval = (int)offset; if (offset >= 0) { retval = -EFAULT; if (!copy_to_user(result, &offset, sizeof(offset))) retval = 0; } return retval; } #endif int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count) { int mask = read_write == READ ? MAY_READ : MAY_WRITE; int ret; if (unlikely((ssize_t) count < 0)) return -EINVAL; if (ppos) { loff_t pos = *ppos; if (unlikely(pos < 0)) { if (!unsigned_offsets(file)) return -EINVAL; if (count >= -pos) /* both values are in 0..LLONG_MAX */ return -EOVERFLOW; } else if (unlikely((loff_t) (pos + count) < 0)) { if (!unsigned_offsets(file)) return -EINVAL; } } ret = security_file_permission(file, mask); if (ret) return ret; return fsnotify_file_area_perm(file, mask, ppos, count); } EXPORT_SYMBOL(rw_verify_area); static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_DEST, buf, len); ret = filp->f_op->read_iter(&kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } static int warn_unsupported(struct file *file, const char *op) { pr_warn_ratelimited( "kernel %s not supported for file %pD4 (pid: %d comm: %.20s)\n", op, file, current->pid, current->comm); return -EINVAL; } ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct kiocb kiocb; struct iov_iter iter; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_READ))) return -EINVAL; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; /* * Also fail if ->read_iter and ->read are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->read_iter || file->f_op->read)) return warn_unsupported(file, "read"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; iov_iter_kvec(&iter, ITER_DEST, &iov, 1, iov.iov_len); ret = file->f_op->read_iter(&kiocb, &iter); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } ssize_t kernel_read(struct file *file, void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; return __kernel_read(file, buf, count, pos); } EXPORT_SYMBOL(kernel_read); ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(READ, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; if (file->f_op->read) ret = file->f_op->read(file, buf, count, pos); else if (file->f_op->read_iter) ret = new_sync_read(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_access(file); add_rchar(current, ret); } inc_syscr(current); return ret; } static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t len, loff_t *ppos) { struct kiocb kiocb; struct iov_iter iter; ssize_t ret; init_sync_kiocb(&kiocb, filp); kiocb.ki_pos = (ppos ? *ppos : 0); iov_iter_ubuf(&iter, ITER_SOURCE, (void __user *)buf, len); ret = filp->f_op->write_iter(&kiocb, &iter); BUG_ON(ret == -EIOCBQUEUED); if (ret > 0 && ppos) *ppos = kiocb.ki_pos; return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos) { struct kiocb kiocb; ssize_t ret; if (WARN_ON_ONCE(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; /* * Also fail if ->write_iter and ->write are both wired up as that * implies very convoluted semantics. */ if (unlikely(!file->f_op->write_iter || file->f_op->write)) return warn_unsupported(file, "write"); init_sync_kiocb(&kiocb, file); kiocb.ki_pos = pos ? *pos : 0; ret = file->f_op->write_iter(&kiocb, from); if (ret > 0) { if (pos) *pos = kiocb.ki_pos; fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); return ret; } /* caller is responsible for file_start_write/file_end_write */ ssize_t __kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { struct kvec iov = { .iov_base = (void *)buf, .iov_len = min_t(size_t, count, MAX_RW_COUNT), }; struct iov_iter iter; iov_iter_kvec(&iter, ITER_SOURCE, &iov, 1, iov.iov_len); return __kernel_write_iter(file, &iter, pos); } /* * This "EXPORT_SYMBOL_GPL()" is more of a "EXPORT_SYMBOL_DONTUSE()", * but autofs is one of the few internal kernel users that actually * wants this _and_ can be built as a module. So we need to export * this symbol for autofs, even though it really isn't appropriate * for any other kernel modules. */ EXPORT_SYMBOL_GPL(__kernel_write); ssize_t kernel_write(struct file *file, const void *buf, size_t count, loff_t *pos) { ssize_t ret; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; file_start_write(file); ret = __kernel_write(file, buf, count, pos); file_end_write(file); return ret; } EXPORT_SYMBOL(kernel_write); ssize_t vfs_write(struct file *file, const char __user *buf, size_t count, loff_t *pos) { ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (unlikely(!access_ok(buf, count))) return -EFAULT; ret = rw_verify_area(WRITE, file, pos, count); if (ret) return ret; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; file_start_write(file); if (file->f_op->write) ret = file->f_op->write(file, buf, count, pos); else if (file->f_op->write_iter) ret = new_sync_write(file, buf, count, pos); else ret = -EINVAL; if (ret > 0) { fsnotify_modify(file); add_wchar(current, ret); } inc_syscw(current); file_end_write(file); return ret; } /* file_ppos returns &file->f_pos or NULL if file is stream */ static inline loff_t *file_ppos(struct file *file) { return file->f_mode & FMODE_STREAM ? NULL : &file->f_pos; } ssize_t ksys_read(unsigned int fd, char __user *buf, size_t count) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_read(fd_file(f), buf, count, ppos); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } return ret; } SYSCALL_DEFINE3(read, unsigned int, fd, char __user *, buf, size_t, count) { return ksys_read(fd, buf, count); } ssize_t ksys_write(unsigned int fd, const char __user *buf, size_t count) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_write(fd_file(f), buf, count, ppos); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } return ret; } SYSCALL_DEFINE3(write, unsigned int, fd, const char __user *, buf, size_t, count) { return ksys_write(fd, buf, count); } ssize_t ksys_pread64(unsigned int fd, char __user *buf, size_t count, loff_t pos) { if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_mode & FMODE_PREAD) return vfs_read(fd_file(f), buf, count, &pos); return -ESPIPE; } SYSCALL_DEFINE4(pread64, unsigned int, fd, char __user *, buf, size_t, count, loff_t, pos) { return ksys_pread64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PREAD64) COMPAT_SYSCALL_DEFINE5(pread64, unsigned int, fd, char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pread64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif ssize_t ksys_pwrite64(unsigned int fd, const char __user *buf, size_t count, loff_t pos) { if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; if (fd_file(f)->f_mode & FMODE_PWRITE) return vfs_write(fd_file(f), buf, count, &pos); return -ESPIPE; } SYSCALL_DEFINE4(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, loff_t, pos) { return ksys_pwrite64(fd, buf, count, pos); } #if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_PWRITE64) COMPAT_SYSCALL_DEFINE5(pwrite64, unsigned int, fd, const char __user *, buf, size_t, count, compat_arg_u64_dual(pos)) { return ksys_pwrite64(fd, buf, count, compat_arg_u64_glue(pos)); } #endif static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { struct kiocb kiocb; ssize_t ret; init_sync_kiocb(&kiocb, filp); ret = kiocb_set_rw_flags(&kiocb, flags, type); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); if (type == READ) ret = filp->f_op->read_iter(&kiocb, iter); else ret = filp->f_op->write_iter(&kiocb, iter); BUG_ON(ret == -EIOCBQUEUED); if (ppos) *ppos = kiocb.ki_pos; return ret; } /* Do it by hand, with file-ops */ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter, loff_t *ppos, int type, rwf_t flags) { ssize_t ret = 0; if (flags & ~RWF_HIPRI) return -EOPNOTSUPP; while (iov_iter_count(iter)) { ssize_t nr; if (type == READ) { nr = filp->f_op->read(filp, iter_iov_addr(iter), iter_iov_len(iter), ppos); } else { nr = filp->f_op->write(filp, iter_iov_addr(iter), iter_iov_len(iter), ppos); } if (nr < 0) { if (!ret) ret = nr; break; } ret += nr; if (nr != iter_iov_len(iter)) break; iov_iter_advance(iter, nr); } return ret; } ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; ret = file->f_op->read_iter(iocb, iter); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_read); ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->read_iter) return -EINVAL; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, ppos, tot_len); if (ret < 0) return ret; ret = do_iter_readv_writev(file, iter, ppos, READ, flags); out: if (ret >= 0) fsnotify_access(file); return ret; } EXPORT_SYMBOL(vfs_iter_read); /* * Caller is responsible for calling kiocb_end_write() on completion * if async iocb was queued. */ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb, struct iov_iter *iter) { size_t tot_len; ssize_t ret = 0; if (!file->f_op->write_iter) return -EINVAL; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, &iocb->ki_pos, tot_len); if (ret < 0) return ret; kiocb_start_write(iocb); ret = file->f_op->write_iter(iocb, iter); if (ret != -EIOCBQUEUED) kiocb_end_write(iocb); if (ret > 0) fsnotify_modify(file); return ret; } EXPORT_SYMBOL(vfs_iocb_iter_write); ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, rwf_t flags) { size_t tot_len; ssize_t ret; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; if (!file->f_op->write_iter) return -EINVAL; tot_len = iov_iter_count(iter); if (!tot_len) return 0; ret = rw_verify_area(WRITE, file, ppos, tot_len); if (ret < 0) return ret; file_start_write(file); ret = do_iter_readv_writev(file, iter, ppos, WRITE, flags); if (ret > 0) fsnotify_modify(file); file_end_write(file); return ret; } EXPORT_SYMBOL(vfs_iter_write); static ssize_t vfs_readv(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_READ)) return -EBADF; if (!(file->f_mode & FMODE_CAN_READ)) return -EINVAL; ret = import_iovec(ITER_DEST, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) return ret; tot_len = iov_iter_count(&iter); if (!tot_len) goto out; ret = rw_verify_area(READ, file, pos, tot_len); if (ret < 0) goto out; if (file->f_op->read_iter) ret = do_iter_readv_writev(file, &iter, pos, READ, flags); else ret = do_loop_readv_writev(file, &iter, pos, READ, flags); out: if (ret >= 0) fsnotify_access(file); kfree(iov); return ret; } static ssize_t vfs_writev(struct file *file, const struct iovec __user *vec, unsigned long vlen, loff_t *pos, rwf_t flags) { struct iovec iovstack[UIO_FASTIOV]; struct iovec *iov = iovstack; struct iov_iter iter; size_t tot_len; ssize_t ret = 0; if (!(file->f_mode & FMODE_WRITE)) return -EBADF; if (!(file->f_mode & FMODE_CAN_WRITE)) return -EINVAL; ret = import_iovec(ITER_SOURCE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter); if (ret < 0) return ret; tot_len = iov_iter_count(&iter); if (!tot_len) goto out; ret = rw_verify_area(WRITE, file, pos, tot_len); if (ret < 0) goto out; file_start_write(file); if (file->f_op->write_iter) ret = do_iter_readv_writev(file, &iter, pos, WRITE, flags); else ret = do_loop_readv_writev(file, &iter, pos, WRITE, flags); if (ret > 0) fsnotify_modify(file); file_end_write(file); out: kfree(iov); return ret; } static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_readv(fd_file(f), vec, vlen, ppos, flags); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_writev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, rwf_t flags) { CLASS(fd_pos, f)(fd); ssize_t ret = -EBADF; if (!fd_empty(f)) { loff_t pos, *ppos = file_ppos(fd_file(f)); if (ppos) { pos = *ppos; ppos = &pos; } ret = vfs_writev(fd_file(f), vec, vlen, ppos, flags); if (ret >= 0 && ppos) fd_file(f)->f_pos = pos; } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } static inline loff_t pos_from_hilo(unsigned long high, unsigned long low) { #define HALF_LONG_BITS (BITS_PER_LONG / 2) return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low; } static ssize_t do_preadv(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (!fd_empty(f)) { ret = -ESPIPE; if (fd_file(f)->f_mode & FMODE_PREAD) ret = vfs_readv(fd_file(f), vec, vlen, &pos, flags); } if (ret > 0) add_rchar(current, ret); inc_syscr(current); return ret; } static ssize_t do_pwritev(unsigned long fd, const struct iovec __user *vec, unsigned long vlen, loff_t pos, rwf_t flags) { ssize_t ret = -EBADF; if (pos < 0) return -EINVAL; CLASS(fd, f)(fd); if (!fd_empty(f)) { ret = -ESPIPE; if (fd_file(f)->f_mode & FMODE_PWRITE) ret = vfs_writev(fd_file(f), vec, vlen, &pos, flags); } if (ret > 0) add_wchar(current, ret); inc_syscw(current); return ret; } SYSCALL_DEFINE3(readv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_readv(fd, vec, vlen, 0); } SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen) { return do_writev(fd, vec, vlen, 0); } SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_preadv(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(preadv2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h) { loff_t pos = pos_from_hilo(pos_h, pos_l); return do_pwritev(fd, vec, vlen, pos, 0); } SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h, rwf_t, flags) { loff_t pos = pos_from_hilo(pos_h, pos_l); if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } /* * Various compat syscalls. Note that they all pretend to take a native * iovec - import_iovec will properly treat those as compat_iovecs based on * in_compat_syscall(). */ #ifdef CONFIG_COMPAT #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64 COMPAT_SYSCALL_DEFINE4(preadv64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_preadv(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(preadv, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_preadv(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PREADV64V2 COMPAT_SYSCALL_DEFINE5(preadv64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(preadv2, compat_ulong_t, fd, const struct iovec __user *, vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_readv(fd, vec, vlen, flags); return do_preadv(fd, vec, vlen, pos, flags); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64 COMPAT_SYSCALL_DEFINE4(pwritev64, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos) { return do_pwritev(fd, vec, vlen, pos, 0); } #endif COMPAT_SYSCALL_DEFINE5(pwritev, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; return do_pwritev(fd, vec, vlen, pos, 0); } #ifdef __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 COMPAT_SYSCALL_DEFINE5(pwritev64v2, unsigned long, fd, const struct iovec __user *, vec, unsigned long, vlen, loff_t, pos, rwf_t, flags) { if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif COMPAT_SYSCALL_DEFINE6(pwritev2, compat_ulong_t, fd, const struct iovec __user *,vec, compat_ulong_t, vlen, u32, pos_low, u32, pos_high, rwf_t, flags) { loff_t pos = ((loff_t)pos_high << 32) | pos_low; if (pos == -1) return do_writev(fd, vec, vlen, flags); return do_pwritev(fd, vec, vlen, pos, flags); } #endif /* CONFIG_COMPAT */ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos, size_t count, loff_t max) { struct inode *in_inode, *out_inode; struct pipe_inode_info *opipe; loff_t pos; loff_t out_pos; ssize_t retval; int fl; /* * Get input file, and verify that it is ok.. */ CLASS(fd, in)(in_fd); if (fd_empty(in)) return -EBADF; if (!(fd_file(in)->f_mode & FMODE_READ)) return -EBADF; if (!ppos) { pos = fd_file(in)->f_pos; } else { pos = *ppos; if (!(fd_file(in)->f_mode & FMODE_PREAD)) return -ESPIPE; } retval = rw_verify_area(READ, fd_file(in), &pos, count); if (retval < 0) return retval; if (count > MAX_RW_COUNT) count = MAX_RW_COUNT; /* * Get output file, and verify that it is ok.. */ CLASS(fd, out)(out_fd); if (fd_empty(out)) return -EBADF; if (!(fd_file(out)->f_mode & FMODE_WRITE)) return -EBADF; in_inode = file_inode(fd_file(in)); out_inode = file_inode(fd_file(out)); out_pos = fd_file(out)->f_pos; if (!max) max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes); if (unlikely(pos + count > max)) { if (pos >= max) return -EOVERFLOW; count = max - pos; } fl = 0; #if 0 /* * We need to debate whether we can enable this or not. The * man page documents EAGAIN return for the output at least, * and the application is arguably buggy if it doesn't expect * EAGAIN on a non-blocking file descriptor. */ if (fd_file(in)->f_flags & O_NONBLOCK) fl = SPLICE_F_NONBLOCK; #endif opipe = get_pipe_info(fd_file(out), true); if (!opipe) { retval = rw_verify_area(WRITE, fd_file(out), &out_pos, count); if (retval < 0) return retval; retval = do_splice_direct(fd_file(in), &pos, fd_file(out), &out_pos, count, fl); } else { if (fd_file(out)->f_flags & O_NONBLOCK) fl |= SPLICE_F_NONBLOCK; retval = splice_file_to_pipe(fd_file(in), opipe, &pos, count, fl); } if (retval > 0) { add_rchar(current, retval); add_wchar(current, retval); fsnotify_access(fd_file(in)); fsnotify_modify(fd_file(out)); fd_file(out)->f_pos = out_pos; if (ppos) *ppos = pos; else fd_file(in)->f_pos = pos; } inc_syscr(current); inc_syscw(current); if (pos > max) retval = -EOVERFLOW; return retval; } SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, off_t __user *, offset, size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, loff_t __user *, offset, size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(sendfile, int, out_fd, int, in_fd, compat_off_t __user *, offset, compat_size_t, count) { loff_t pos; off_t off; ssize_t ret; if (offset) { if (unlikely(get_user(off, offset))) return -EFAULT; pos = off; ret = do_sendfile(out_fd, in_fd, &pos, count, MAX_NON_LFS); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd, compat_loff_t __user *, offset, compat_size_t, count) { loff_t pos; ssize_t ret; if (offset) { if (unlikely(copy_from_user(&pos, offset, sizeof(loff_t)))) return -EFAULT; ret = do_sendfile(out_fd, in_fd, &pos, count, 0); if (unlikely(put_user(pos, offset))) return -EFAULT; return ret; } return do_sendfile(out_fd, in_fd, NULL, count, 0); } #endif /* * Performs necessary checks before doing a file copy * * Can adjust amount of bytes to copy via @req_count argument. * Returns appropriate error code that caller should return or * zero in case the copy should be allowed. */ static int generic_copy_file_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t *req_count, unsigned int flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); uint64_t count = *req_count; loff_t size_in; int ret; ret = generic_file_rw_checks(file_in, file_out); if (ret) return ret; /* * We allow some filesystems to handle cross sb copy, but passing * a file of the wrong filesystem type to filesystem driver can result * in an attempt to dereference the wrong type of ->private_data, so * avoid doing that until we really have a good reason. * * nfs and cifs define several different file_system_type structures * and several different sets of file_operations, but they all end up * using the same ->copy_file_range() function pointer. */ if (flags & COPY_FILE_SPLICE) { /* cross sb splice is allowed */ } else if (file_out->f_op->copy_file_range) { if (file_in->f_op->copy_file_range != file_out->f_op->copy_file_range) return -EXDEV; } else if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb) { return -EXDEV; } /* Don't touch certain kinds of inodes */ if (IS_IMMUTABLE(inode_out)) return -EPERM; if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out)) return -ETXTBSY; /* Ensure offsets don't wrap. */ if (pos_in + count < pos_in || pos_out + count < pos_out) return -EOVERFLOW; /* Shorten the copy to EOF */ size_in = i_size_read(inode_in); if (pos_in >= size_in) count = 0; else count = min(count, size_in - (uint64_t)pos_in); ret = generic_write_check_limits(file_out, pos_out, &count); if (ret) return ret; /* Don't allow overlapped copying within the same file. */ if (inode_in == inode_out && pos_out + count > pos_in && pos_out < pos_in + count) return -EINVAL; *req_count = count; return 0; } /* * copy_file_range() differs from regular file read and write in that it * specifically allows return partial success. When it does so is up to * the copy_file_range method. */ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, size_t len, unsigned int flags) { ssize_t ret; bool splice = flags & COPY_FILE_SPLICE; bool samesb = file_inode(file_in)->i_sb == file_inode(file_out)->i_sb; if (flags & ~COPY_FILE_SPLICE) return -EINVAL; ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len, flags); if (unlikely(ret)) return ret; ret = rw_verify_area(READ, file_in, &pos_in, len); if (unlikely(ret)) return ret; ret = rw_verify_area(WRITE, file_out, &pos_out, len); if (unlikely(ret)) return ret; if (len == 0) return 0; /* * Make sure return value doesn't overflow in 32bit compat mode. Also * limit the size for all cases except when calling ->copy_file_range(). */ if (splice || !file_out->f_op->copy_file_range || in_compat_syscall()) len = min_t(size_t, MAX_RW_COUNT, len); file_start_write(file_out); /* * Cloning is supported by more file systems, so we implement copy on * same sb using clone, but for filesystems where both clone and copy * are supported (e.g. nfs,cifs), we only call the copy method. */ if (!splice && file_out->f_op->copy_file_range) { ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out, len, flags); } else if (!splice && file_in->f_op->remap_file_range && samesb) { ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, REMAP_FILE_CAN_SHORTEN); /* fallback to splice */ if (ret <= 0) splice = true; } else if (samesb) { /* Fallback to splice for same sb copy for backward compat */ splice = true; } file_end_write(file_out); if (!splice) goto done; /* * We can get here for same sb copy of filesystems that do not implement * ->copy_file_range() in case filesystem does not support clone or in * case filesystem supports clone but rejected the clone request (e.g. * because it was not block aligned). * * In both cases, fall back to kernel copy so we are able to maintain a * consistent story about which filesystems support copy_file_range() * and which filesystems do not, that will allow userspace tools to * make consistent desicions w.r.t using copy_file_range(). * * We also get here if caller (e.g. nfsd) requested COPY_FILE_SPLICE * for server-side-copy between any two sb. * * In any case, we call do_splice_direct() and not splice_file_range(), * without file_start_write() held, to avoid possible deadlocks related * to splicing from input file, while file_start_write() is held on * the output file on a different sb. */ ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out, len, 0); done: if (ret > 0) { fsnotify_access(file_in); add_rchar(current, ret); fsnotify_modify(file_out); add_wchar(current, ret); } inc_syscr(current); inc_syscw(current); return ret; } EXPORT_SYMBOL(vfs_copy_file_range); SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags) { loff_t pos_in; loff_t pos_out; ssize_t ret = -EBADF; CLASS(fd, f_in)(fd_in); if (fd_empty(f_in)) return -EBADF; CLASS(fd, f_out)(fd_out); if (fd_empty(f_out)) return -EBADF; if (off_in) { if (copy_from_user(&pos_in, off_in, sizeof(loff_t))) return -EFAULT; } else { pos_in = fd_file(f_in)->f_pos; } if (off_out) { if (copy_from_user(&pos_out, off_out, sizeof(loff_t))) return -EFAULT; } else { pos_out = fd_file(f_out)->f_pos; } if (flags != 0) return -EINVAL; ret = vfs_copy_file_range(fd_file(f_in), pos_in, fd_file(f_out), pos_out, len, flags); if (ret > 0) { pos_in += ret; pos_out += ret; if (off_in) { if (copy_to_user(off_in, &pos_in, sizeof(loff_t))) ret = -EFAULT; } else { fd_file(f_in)->f_pos = pos_in; } if (off_out) { if (copy_to_user(off_out, &pos_out, sizeof(loff_t))) ret = -EFAULT; } else { fd_file(f_out)->f_pos = pos_out; } } return ret; } /* * Don't operate on ranges the page cache doesn't support, and don't exceed the * LFS limits. If pos is under the limit it becomes a short access. If it * exceeds the limit we return -EFBIG. */ int generic_write_check_limits(struct file *file, loff_t pos, loff_t *count) { struct inode *inode = file->f_mapping->host; loff_t max_size = inode->i_sb->s_maxbytes; loff_t limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY) { if (pos >= limit) { send_sig(SIGXFSZ, current, 0); return -EFBIG; } *count = min(*count, limit - pos); } if (!(file->f_flags & O_LARGEFILE)) max_size = MAX_NON_LFS; if (unlikely(pos >= max_size)) return -EFBIG; *count = min(*count, max_size - pos); return 0; } EXPORT_SYMBOL_GPL(generic_write_check_limits); /* Like generic_write_checks(), but takes size of write instead of iter. */ int generic_write_checks_count(struct kiocb *iocb, loff_t *count) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; if (IS_SWAPFILE(inode)) return -ETXTBSY; if (!*count) return 0; if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); if ((iocb->ki_flags & IOCB_NOWAIT) && !((iocb->ki_flags & IOCB_DIRECT) || (file->f_op->fop_flags & FOP_BUFFER_WASYNC))) return -EINVAL; return generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, count); } EXPORT_SYMBOL(generic_write_checks_count); /* * Performs necessary checks before doing a write * * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { loff_t count = iov_iter_count(from); int ret; ret = generic_write_checks_count(iocb, &count); if (ret) return ret; iov_iter_truncate(from, count); return iov_iter_count(from); } EXPORT_SYMBOL(generic_write_checks); /* * Performs common checks before doing a file copy/clone * from @file_in to @file_out. */ int generic_file_rw_checks(struct file *file_in, struct file *file_out) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); /* Don't copy dirs, pipes, sockets... */ if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; if (!(file_in->f_mode & FMODE_READ) || !(file_out->f_mode & FMODE_WRITE) || (file_out->f_flags & O_APPEND)) return -EBADF; return 0; } int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter) { size_t len = iov_iter_count(iter); if (!iter_is_ubuf(iter)) return -EINVAL; if (!is_power_of_2(len)) return -EINVAL; if (!IS_ALIGNED(iocb->ki_pos, len)) return -EINVAL; if (!(iocb->ki_flags & IOCB_DIRECT)) return -EOPNOTSUPP; return 0; } EXPORT_SYMBOL_GPL(generic_atomic_write_valid); |
| 8 7 8 8 8 7 8 2 2 8 8 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/phy.h> #include <linux/phylib_stubs.h> #include "common.h" #include "netlink.h" struct linkstate_req_info { struct ethnl_req_info base; }; struct linkstate_reply_data { struct ethnl_reply_data base; int link; int sqi; int sqi_max; struct ethtool_link_ext_stats link_stats; bool link_ext_state_provided; struct ethtool_link_ext_state_info ethtool_link_ext_state_info; }; #define LINKSTATE_REPDATA(__reply_base) \ container_of(__reply_base, struct linkstate_reply_data, base) const struct nla_policy ethnl_linkstate_get_policy[] = { [ETHTOOL_A_LINKSTATE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static int linkstate_get_sqi(struct phy_device *phydev) { int ret; if (!phydev) return -EOPNOTSUPP; mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_sqi) ret = -EOPNOTSUPP; else if (!phydev->link) ret = -ENETDOWN; else ret = phydev->drv->get_sqi(phydev); mutex_unlock(&phydev->lock); return ret; } static int linkstate_get_sqi_max(struct phy_device *phydev) { int ret; if (!phydev) return -EOPNOTSUPP; mutex_lock(&phydev->lock); if (!phydev->drv || !phydev->drv->get_sqi_max) ret = -EOPNOTSUPP; else if (!phydev->link) ret = -ENETDOWN; else ret = phydev->drv->get_sqi_max(phydev); mutex_unlock(&phydev->lock); return ret; }; static bool linkstate_sqi_critical_error(int sqi) { return sqi < 0 && sqi != -EOPNOTSUPP && sqi != -ENETDOWN; } static bool linkstate_sqi_valid(struct linkstate_reply_data *data) { return data->sqi >= 0 && data->sqi_max >= 0 && data->sqi <= data->sqi_max; } static int linkstate_get_link_ext_state(struct net_device *dev, struct linkstate_reply_data *data) { int err; if (!dev->ethtool_ops->get_link_ext_state) return -EOPNOTSUPP; err = dev->ethtool_ops->get_link_ext_state(dev, &data->ethtool_link_ext_state_info); if (err) return err; data->link_ext_state_provided = true; return 0; } static int linkstate_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); struct net_device *dev = reply_base->dev; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_LINKSTATE_HEADER, info->extack); if (IS_ERR(phydev)) { ret = PTR_ERR(phydev); goto out; } ret = ethnl_ops_begin(dev); if (ret < 0) return ret; data->link = __ethtool_get_link(dev); ret = linkstate_get_sqi(phydev); if (linkstate_sqi_critical_error(ret)) goto out; data->sqi = ret; ret = linkstate_get_sqi_max(phydev); if (linkstate_sqi_critical_error(ret)) goto out; data->sqi_max = ret; if (dev->flags & IFF_UP) { ret = linkstate_get_link_ext_state(dev, data); if (ret < 0 && ret != -EOPNOTSUPP && ret != -ENODATA) goto out; } ethtool_stats_init((u64 *)&data->link_stats, sizeof(data->link_stats) / 8); if (req_base->flags & ETHTOOL_FLAG_STATS) { if (phydev) phy_ethtool_get_link_ext_stats(phydev, &data->link_stats); if (dev->ethtool_ops->get_link_ext_stats) dev->ethtool_ops->get_link_ext_stats(dev, &data->link_stats); } ret = 0; out: ethnl_ops_complete(dev); return ret; } static int linkstate_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); int len; len = nla_total_size(sizeof(u8)) /* LINKSTATE_LINK */ + 0; if (linkstate_sqi_valid(data)) { len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI */ len += nla_total_size(sizeof(u32)); /* LINKSTATE_SQI_MAX */ } if (data->link_ext_state_provided) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_STATE */ if (data->ethtool_link_ext_state_info.__link_ext_substate) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_SUBSTATE */ if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) len += nla_total_size(sizeof(u32)); return len; } static int linkstate_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { struct linkstate_reply_data *data = LINKSTATE_REPDATA(reply_base); if (data->link >= 0 && nla_put_u8(skb, ETHTOOL_A_LINKSTATE_LINK, !!data->link)) return -EMSGSIZE; if (linkstate_sqi_valid(data)) { if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI, data->sqi)) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_SQI_MAX, data->sqi_max)) return -EMSGSIZE; } if (data->link_ext_state_provided) { if (nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_STATE, data->ethtool_link_ext_state_info.link_ext_state)) return -EMSGSIZE; if (data->ethtool_link_ext_state_info.__link_ext_substate && nla_put_u8(skb, ETHTOOL_A_LINKSTATE_EXT_SUBSTATE, data->ethtool_link_ext_state_info.__link_ext_substate)) return -EMSGSIZE; } if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, data->link_stats.link_down_events)) return -EMSGSIZE; return 0; } const struct ethnl_request_ops ethnl_linkstate_request_ops = { .request_cmd = ETHTOOL_MSG_LINKSTATE_GET, .reply_cmd = ETHTOOL_MSG_LINKSTATE_GET_REPLY, .hdr_attr = ETHTOOL_A_LINKSTATE_HEADER, .req_info_size = sizeof(struct linkstate_req_info), .reply_data_size = sizeof(struct linkstate_reply_data), .prepare_data = linkstate_prepare_data, .reply_size = linkstate_reply_size, .fill_reply = linkstate_fill_reply, }; |
| 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_proto_udp.c: UDP load balancing support for IPVS * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Julian Anastasov <ja@ssi.bg> * * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> * Network name space (netns) aware. */ #define pr_fmt(fmt) "IPVS: " fmt #include <linux/in.h> #include <linux/ip.h> #include <linux/kernel.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/udp.h> #include <linux/indirect_call_wrapper.h> #include <net/ip_vs.h> #include <net/ip.h> #include <net/ip6_checksum.h> static int udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, unsigned int udphoff); static int udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, struct ip_vs_iphdr *iph) { struct ip_vs_service *svc; struct udphdr _udph, *uh; __be16 _ports[2], *ports = NULL; if (likely(!ip_vs_iph_icmp(iph))) { /* IPv6 fragments, only first fragment will hit this */ uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph); if (uh) ports = &uh->source; } else { ports = skb_header_pointer( skb, iph->len, sizeof(_ports), &_ports); } if (!ports) { *verdict = NF_DROP; return 0; } if (likely(!ip_vs_iph_inverse(iph))) svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->daddr, ports[1]); else svc = ip_vs_service_find(ipvs, af, skb->mark, iph->protocol, &iph->saddr, ports[0]); if (svc) { int ignored; if (ip_vs_todrop(ipvs)) { /* * It seems that we are very loaded. * We have to drop this packet :( */ *verdict = NF_DROP; return 0; } /* * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ *cpp = ip_vs_schedule(svc, skb, pd, &ignored, iph); if (!*cpp && ignored <= 0) { if (!ignored) *verdict = ip_vs_leave(svc, skb, pd, iph); else *verdict = NF_DROP; return 0; } } /* NF_ACCEPT */ return 1; } static inline void udp_fast_csum_update(int af, struct udphdr *uhdr, const union nf_inet_addr *oldip, const union nf_inet_addr *newip, __be16 oldport, __be16 newport) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) uhdr->check = csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, ip_vs_check_diff2(oldport, newport, ~csum_unfold(uhdr->check)))); else #endif uhdr->check = csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldport, newport, ~csum_unfold(uhdr->check)))); if (!uhdr->check) uhdr->check = CSUM_MANGLED_0; } static inline void udp_partial_csum_update(int af, struct udphdr *uhdr, const union nf_inet_addr *oldip, const union nf_inet_addr *newip, __be16 oldlen, __be16 newlen) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) uhdr->check = ~csum_fold(ip_vs_check_diff16(oldip->ip6, newip->ip6, ip_vs_check_diff2(oldlen, newlen, csum_unfold(uhdr->check)))); else #endif uhdr->check = ~csum_fold(ip_vs_check_diff4(oldip->ip, newip->ip, ip_vs_check_diff2(oldlen, newlen, csum_unfold(uhdr->check)))); } INDIRECT_CALLABLE_SCOPE int udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct udphdr *udph; unsigned int udphoff = iph->len; bool payload_csum = false; int oldlen; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) return 1; #endif oldlen = skb->len - udphoff; /* csum_check requires unshared skb */ if (skb_ensure_writable(skb, udphoff + sizeof(*udph))) return 0; if (unlikely(cp->app != NULL)) { int ret; /* Some checks before mangling */ if (!udp_csum_check(cp->af, skb, pp, udphoff)) return 0; /* * Call application helper if needed */ if (!(ret = ip_vs_app_pkt_out(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) oldlen = skb->len - udphoff; else payload_csum = true; } udph = (void *)skb_network_header(skb) + udphoff; udph->source = cp->vport; /* * Adjust UDP checksums */ if (skb->ip_summed == CHECKSUM_PARTIAL) { udp_partial_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr, htons(oldlen), htons(skb->len - udphoff)); } else if (!payload_csum && (udph->check != 0)) { /* Only port and addr are changed, do fast csum update */ udp_fast_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ udph->check = 0; skb->csum = skb_checksum(skb, udphoff, skb->len - udphoff, 0); #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) udph->check = csum_ipv6_magic(&cp->vaddr.in6, &cp->caddr.in6, skb->len - udphoff, cp->protocol, skb->csum); else #endif udph->check = csum_tcpudp_magic(cp->vaddr.ip, cp->caddr.ip, skb->len - udphoff, cp->protocol, skb->csum); if (udph->check == 0) udph->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n", pp->name, udph->check, (char*)&(udph->check) - (char*)udph); } return 1; } static int udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { struct udphdr *udph; unsigned int udphoff = iph->len; bool payload_csum = false; int oldlen; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6 && iph->fragoffs) return 1; #endif oldlen = skb->len - udphoff; /* csum_check requires unshared skb */ if (skb_ensure_writable(skb, udphoff + sizeof(*udph))) return 0; if (unlikely(cp->app != NULL)) { int ret; /* Some checks before mangling */ if (!udp_csum_check(cp->af, skb, pp, udphoff)) return 0; /* * Attempt ip_vs_app call. * It will fix ip_vs_conn */ if (!(ret = ip_vs_app_pkt_in(cp, skb, iph))) return 0; /* ret=2: csum update is needed after payload mangling */ if (ret == 1) oldlen = skb->len - udphoff; else payload_csum = true; } udph = (void *)skb_network_header(skb) + udphoff; udph->dest = cp->dport; /* * Adjust UDP checksums */ if (skb->ip_summed == CHECKSUM_PARTIAL) { udp_partial_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr, htons(oldlen), htons(skb->len - udphoff)); } else if (!payload_csum && (udph->check != 0)) { /* Only port and addr are changed, do fast csum update */ udp_fast_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ udph->check = 0; skb->csum = skb_checksum(skb, udphoff, skb->len - udphoff, 0); #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) udph->check = csum_ipv6_magic(&cp->caddr.in6, &cp->daddr.in6, skb->len - udphoff, cp->protocol, skb->csum); else #endif udph->check = csum_tcpudp_magic(cp->caddr.ip, cp->daddr.ip, skb->len - udphoff, cp->protocol, skb->csum); if (udph->check == 0) udph->check = CSUM_MANGLED_0; skb->ip_summed = CHECKSUM_UNNECESSARY; } return 1; } static int udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, unsigned int udphoff) { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, udphoff, sizeof(_udph), &_udph); if (uh == NULL) return 0; if (uh->check != 0) { switch (skb->ip_summed) { case CHECKSUM_NONE: skb->csum = skb_checksum(skb, udphoff, skb->len - udphoff, 0); fallthrough; case CHECKSUM_COMPLETE: #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { if (csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len - udphoff, IPPROTO_UDP, skb->csum)) { IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } } else #endif if (csum_tcpudp_magic(ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, skb->len - udphoff, ip_hdr(skb)->protocol, skb->csum)) { IP_VS_DBG_RL_PKT(0, af, pp, skb, 0, "Failed checksum for"); return 0; } break; default: /* No need to checksum. */ break; } } return 1; } static inline __u16 udp_app_hashkey(__be16 port) { return (((__force u16)port >> UDP_APP_TAB_BITS) ^ (__force u16)port) & UDP_APP_TAB_MASK; } static int udp_register_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); hash = udp_app_hashkey(port); list_for_each_entry(i, &ipvs->udp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } list_add_rcu(&inc->p_list, &ipvs->udp_apps[hash]); atomic_inc(&pd->appcnt); out: return ret; } static void udp_unregister_app(struct netns_ipvs *ipvs, struct ip_vs_app *inc) { struct ip_vs_proto_data *pd = ip_vs_proto_data_get(ipvs, IPPROTO_UDP); atomic_dec(&pd->appcnt); list_del_rcu(&inc->p_list); } static int udp_app_conn_bind(struct ip_vs_conn *cp) { struct netns_ipvs *ipvs = cp->ipvs; int hash; struct ip_vs_app *inc; int result = 0; /* Default binding: bind app only for NAT */ if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) return 0; /* Lookup application incarnations and bind the right one */ hash = udp_app_hashkey(cp->vport); list_for_each_entry_rcu(inc, &ipvs->udp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->" "%s:%u to app %s on port %u\n", __func__, IP_VS_DBG_ADDR(cp->af, &cp->caddr), ntohs(cp->cport), IP_VS_DBG_ADDR(cp->af, &cp->vaddr), ntohs(cp->vport), inc->name, ntohs(inc->port)); cp->app = inc; if (inc->init_conn) result = inc->init_conn(inc, cp); break; } } return result; } static const int udp_timeouts[IP_VS_UDP_S_LAST+1] = { [IP_VS_UDP_S_NORMAL] = 5*60*HZ, [IP_VS_UDP_S_LAST] = 2*HZ, }; static const char *const udp_state_name_table[IP_VS_UDP_S_LAST+1] = { [IP_VS_UDP_S_NORMAL] = "UDP", [IP_VS_UDP_S_LAST] = "BUG!", }; static const char * udp_state_name(int state) { if (state >= IP_VS_UDP_S_LAST) return "ERR!"; return udp_state_name_table[state] ? udp_state_name_table[state] : "?"; } static void udp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, struct ip_vs_proto_data *pd) { if (unlikely(!pd)) { pr_err("UDP no ns data\n"); return; } cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL]; if (direction == IP_VS_DIR_OUTPUT) ip_vs_control_assure_ct(cp); } static int __udp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { ip_vs_init_hash_table(ipvs->udp_apps, UDP_APP_TAB_SIZE); pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts, sizeof(udp_timeouts)); if (!pd->timeout_table) return -ENOMEM; return 0; } static void __udp_exit(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { kfree(pd->timeout_table); } struct ip_vs_protocol ip_vs_protocol_udp = { .name = "UDP", .protocol = IPPROTO_UDP, .num_states = IP_VS_UDP_S_LAST, .dont_defrag = 0, .init = NULL, .exit = NULL, .init_netns = __udp_init, .exit_netns = __udp_exit, .conn_schedule = udp_conn_schedule, .conn_in_get = ip_vs_conn_in_get_proto, .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = udp_snat_handler, .dnat_handler = udp_dnat_handler, .state_transition = udp_state_transition, .state_name = udp_state_name, .register_app = udp_register_app, .unregister_app = udp_unregister_app, .app_conn_bind = udp_app_conn_bind, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = NULL, }; |
| 5 2 7 5 5 5 5 23 3 8 59 150 220 2 215 66 38 41 38 3 38 93 99 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 8006 8007 8008 8009 8010 8011 8012 8013 8014 8015 8016 8017 8018 8019 8020 8021 8022 8023 8024 8025 8026 8027 8028 8029 8030 8031 8032 8033 8034 8035 8036 8037 8038 8039 8040 8041 8042 8043 8044 8045 8046 8047 8048 8049 8050 8051 8052 8053 8054 8055 8056 8057 8058 8059 8060 8061 8062 8063 8064 8065 8066 8067 8068 8069 8070 8071 8072 8073 8074 8075 8076 8077 8078 8079 8080 8081 8082 8083 8084 8085 8086 8087 8088 8089 8090 8091 8092 8093 8094 8095 8096 8097 8098 8099 8100 8101 8102 8103 8104 8105 8106 8107 8108 8109 8110 8111 8112 8113 8114 8115 8116 8117 8118 8119 8120 8121 8122 8123 8124 8125 8126 8127 8128 8129 8130 8131 8132 8133 8134 8135 8136 8137 8138 8139 8140 8141 8142 8143 8144 8145 8146 8147 8148 8149 8150 8151 8152 8153 8154 8155 8156 8157 8158 8159 8160 8161 8162 8163 8164 8165 8166 8167 8168 8169 8170 8171 8172 8173 8174 8175 8176 8177 8178 8179 8180 8181 8182 8183 8184 8185 8186 8187 8188 8189 8190 8191 8192 8193 8194 8195 8196 8197 8198 8199 8200 8201 8202 8203 8204 8205 8206 8207 8208 8209 8210 8211 8212 8213 8214 8215 8216 8217 8218 8219 8220 8221 8222 8223 8224 8225 8226 8227 8228 8229 8230 8231 8232 8233 8234 8235 8236 8237 8238 8239 8240 8241 8242 8243 8244 8245 8246 8247 8248 8249 8250 8251 8252 8253 8254 8255 8256 8257 8258 8259 8260 8261 8262 8263 8264 8265 8266 8267 8268 8269 8270 8271 8272 8273 8274 8275 8276 8277 8278 8279 8280 8281 8282 8283 8284 8285 8286 8287 8288 8289 8290 8291 8292 8293 8294 8295 8296 8297 8298 8299 8300 8301 8302 8303 8304 8305 8306 8307 8308 8309 8310 8311 8312 8313 8314 8315 8316 8317 8318 8319 8320 8321 8322 8323 8324 8325 8326 8327 8328 8329 8330 8331 8332 8333 8334 8335 8336 8337 8338 8339 8340 8341 8342 8343 8344 8345 8346 8347 8348 8349 8350 8351 8352 8353 8354 8355 8356 8357 8358 8359 8360 8361 8362 8363 8364 8365 8366 8367 8368 8369 8370 8371 8372 8373 8374 8375 8376 8377 8378 8379 8380 8381 8382 8383 8384 8385 8386 8387 8388 8389 8390 8391 8392 8393 8394 8395 8396 8397 8398 8399 8400 8401 8402 8403 8404 8405 8406 8407 8408 8409 8410 8411 8412 8413 8414 8415 8416 8417 8418 8419 8420 8421 8422 8423 8424 8425 8426 8427 8428 8429 8430 8431 8432 8433 8434 8435 8436 8437 8438 8439 8440 8441 8442 8443 8444 8445 8446 8447 8448 8449 8450 8451 8452 8453 8454 8455 8456 8457 8458 8459 8460 8461 8462 8463 8464 8465 8466 8467 8468 8469 8470 8471 8472 8473 8474 8475 8476 8477 8478 8479 8480 8481 8482 8483 8484 8485 8486 8487 8488 8489 8490 8491 8492 8493 8494 8495 8496 8497 8498 8499 8500 8501 8502 8503 8504 8505 8506 8507 8508 8509 8510 8511 8512 8513 8514 8515 8516 8517 8518 8519 8520 8521 8522 8523 8524 8525 8526 8527 8528 8529 8530 8531 8532 8533 8534 8535 8536 8537 8538 8539 8540 8541 8542 8543 8544 8545 8546 8547 8548 8549 8550 8551 8552 8553 8554 8555 8556 8557 8558 8559 8560 8561 8562 8563 8564 8565 8566 8567 8568 8569 8570 8571 8572 8573 8574 8575 8576 8577 8578 8579 8580 8581 8582 8583 8584 8585 8586 8587 8588 8589 8590 8591 8592 8593 8594 8595 8596 8597 8598 8599 8600 8601 8602 8603 8604 8605 8606 8607 8608 8609 8610 8611 8612 8613 8614 8615 8616 8617 8618 8619 8620 8621 8622 8623 8624 8625 8626 8627 8628 8629 8630 8631 8632 8633 8634 8635 8636 8637 8638 8639 8640 8641 8642 8643 8644 8645 8646 8647 8648 8649 8650 8651 8652 8653 8654 8655 8656 8657 8658 8659 8660 8661 8662 8663 8664 8665 8666 8667 8668 8669 8670 8671 8672 8673 8674 8675 8676 8677 8678 8679 8680 8681 8682 8683 8684 8685 8686 8687 8688 8689 8690 8691 8692 8693 8694 8695 8696 8697 8698 8699 8700 8701 8702 8703 8704 8705 8706 8707 8708 8709 8710 8711 8712 8713 8714 8715 8716 8717 8718 8719 8720 8721 8722 8723 8724 8725 8726 8727 8728 8729 8730 8731 8732 8733 8734 8735 8736 8737 8738 8739 8740 8741 8742 8743 8744 8745 8746 8747 8748 8749 8750 8751 8752 8753 8754 8755 8756 8757 8758 8759 8760 8761 8762 8763 8764 8765 8766 8767 8768 8769 8770 8771 8772 8773 8774 8775 8776 8777 8778 8779 8780 8781 8782 8783 8784 8785 8786 8787 8788 8789 8790 8791 8792 8793 8794 8795 8796 8797 8798 8799 8800 8801 8802 8803 8804 8805 8806 8807 8808 8809 8810 8811 8812 8813 8814 8815 8816 8817 8818 8819 8820 8821 8822 8823 8824 8825 8826 8827 8828 8829 8830 8831 8832 8833 8834 8835 8836 8837 8838 8839 8840 8841 8842 8843 8844 8845 8846 8847 8848 8849 8850 8851 8852 8853 8854 8855 8856 8857 8858 8859 8860 8861 8862 8863 8864 8865 8866 8867 8868 8869 8870 8871 8872 8873 8874 8875 8876 8877 8878 8879 8880 8881 8882 8883 8884 8885 8886 8887 8888 8889 8890 8891 8892 8893 8894 8895 8896 8897 8898 8899 8900 8901 8902 8903 8904 8905 8906 8907 8908 8909 8910 8911 8912 8913 8914 8915 8916 8917 8918 8919 8920 8921 8922 8923 8924 8925 8926 8927 8928 8929 8930 8931 8932 8933 8934 8935 8936 8937 8938 8939 8940 8941 8942 8943 8944 8945 8946 8947 8948 8949 8950 8951 8952 8953 8954 8955 8956 8957 8958 8959 8960 8961 8962 8963 8964 8965 8966 8967 8968 8969 8970 8971 8972 8973 8974 8975 8976 8977 8978 8979 8980 8981 8982 8983 8984 8985 8986 8987 8988 8989 8990 8991 8992 8993 8994 8995 8996 8997 8998 8999 9000 9001 9002 9003 9004 9005 9006 9007 9008 9009 9010 9011 9012 9013 9014 9015 9016 9017 9018 9019 9020 9021 9022 9023 9024 9025 9026 9027 9028 9029 9030 9031 9032 9033 9034 9035 9036 9037 9038 9039 9040 9041 9042 9043 9044 9045 9046 9047 9048 9049 9050 9051 9052 9053 9054 9055 9056 9057 9058 9059 9060 9061 9062 9063 9064 9065 9066 9067 9068 9069 9070 9071 9072 9073 9074 9075 9076 9077 9078 9079 9080 9081 9082 9083 9084 9085 9086 9087 9088 9089 9090 9091 9092 9093 9094 9095 9096 9097 9098 9099 9100 9101 9102 9103 9104 9105 9106 9107 9108 9109 9110 9111 9112 9113 9114 9115 9116 9117 9118 9119 9120 9121 9122 9123 9124 9125 9126 9127 9128 9129 9130 9131 9132 9133 9134 9135 9136 9137 9138 9139 9140 9141 9142 9143 9144 9145 9146 9147 9148 9149 9150 9151 9152 9153 9154 9155 9156 9157 9158 9159 9160 9161 9162 9163 9164 9165 9166 9167 9168 9169 9170 9171 9172 9173 9174 9175 9176 9177 9178 9179 9180 9181 9182 9183 9184 9185 9186 9187 9188 9189 9190 9191 9192 9193 9194 9195 9196 9197 9198 9199 9200 9201 9202 9203 9204 9205 9206 9207 9208 9209 9210 9211 9212 9213 9214 9215 9216 9217 9218 9219 9220 9221 9222 9223 9224 9225 9226 9227 9228 9229 9230 9231 9232 9233 9234 9235 9236 9237 9238 9239 9240 9241 9242 9243 9244 9245 9246 9247 9248 9249 9250 9251 9252 9253 9254 9255 9256 9257 9258 9259 9260 9261 9262 9263 9264 9265 9266 9267 9268 9269 9270 9271 9272 9273 9274 9275 9276 9277 9278 9279 9280 9281 9282 9283 9284 9285 9286 9287 9288 9289 9290 9291 9292 9293 9294 9295 9296 9297 9298 9299 9300 9301 9302 9303 9304 9305 9306 9307 9308 9309 9310 9311 9312 9313 9314 9315 9316 9317 9318 9319 9320 9321 9322 9323 9324 9325 9326 9327 9328 9329 9330 9331 9332 9333 9334 9335 9336 9337 9338 9339 9340 9341 9342 9343 9344 9345 9346 9347 9348 9349 9350 9351 9352 9353 9354 9355 9356 9357 9358 9359 9360 9361 9362 9363 9364 9365 9366 9367 9368 9369 9370 9371 9372 9373 9374 9375 9376 9377 9378 9379 9380 9381 9382 9383 9384 9385 9386 9387 9388 9389 9390 9391 9392 9393 9394 9395 9396 9397 9398 9399 9400 9401 9402 9403 9404 9405 9406 9407 9408 9409 9410 9411 9412 9413 9414 9415 9416 9417 9418 9419 9420 9421 9422 9423 9424 9425 9426 9427 9428 9429 9430 9431 9432 9433 9434 9435 9436 9437 9438 9439 9440 9441 9442 9443 9444 9445 9446 9447 9448 9449 9450 9451 9452 9453 9454 9455 9456 9457 9458 9459 9460 9461 9462 9463 9464 9465 9466 9467 9468 9469 9470 9471 9472 9473 9474 9475 9476 9477 9478 9479 9480 9481 9482 9483 9484 9485 9486 9487 9488 9489 9490 9491 9492 9493 9494 9495 9496 9497 9498 9499 9500 9501 9502 9503 9504 9505 9506 9507 9508 9509 9510 9511 9512 9513 9514 9515 9516 9517 9518 9519 9520 9521 9522 9523 9524 9525 9526 9527 9528 9529 9530 9531 9532 9533 9534 9535 9536 9537 9538 9539 9540 9541 9542 9543 9544 9545 9546 9547 9548 9549 9550 9551 9552 9553 9554 9555 9556 9557 9558 9559 9560 9561 9562 9563 9564 9565 9566 9567 9568 9569 9570 9571 9572 9573 9574 9575 9576 9577 9578 9579 9580 9581 9582 9583 9584 9585 9586 9587 9588 9589 9590 9591 9592 9593 9594 9595 9596 9597 9598 9599 9600 9601 9602 9603 9604 9605 9606 9607 9608 9609 9610 9611 9612 9613 9614 9615 9616 9617 9618 9619 9620 9621 9622 9623 9624 9625 9626 9627 9628 9629 9630 9631 9632 9633 9634 9635 9636 9637 9638 9639 9640 9641 9642 9643 9644 9645 9646 9647 9648 9649 9650 9651 9652 9653 9654 9655 9656 9657 9658 9659 9660 9661 9662 9663 9664 9665 9666 9667 9668 9669 9670 9671 9672 9673 9674 9675 9676 9677 9678 9679 9680 9681 9682 9683 9684 9685 9686 9687 9688 9689 9690 9691 9692 9693 9694 9695 9696 9697 9698 9699 9700 9701 9702 9703 9704 9705 9706 9707 9708 9709 9710 9711 9712 9713 9714 9715 9716 9717 9718 9719 9720 9721 9722 9723 9724 9725 9726 9727 9728 9729 9730 9731 9732 9733 9734 9735 9736 9737 9738 9739 9740 9741 9742 9743 9744 9745 9746 9747 9748 9749 9750 9751 9752 9753 9754 9755 9756 9757 9758 9759 9760 9761 9762 9763 9764 9765 9766 9767 9768 9769 9770 9771 9772 9773 9774 9775 9776 9777 9778 9779 9780 9781 9782 9783 9784 9785 9786 9787 9788 9789 9790 9791 9792 9793 9794 9795 9796 9797 9798 9799 9800 9801 9802 9803 9804 9805 9806 9807 9808 9809 9810 9811 9812 9813 9814 9815 9816 9817 9818 9819 9820 9821 9822 9823 9824 9825 9826 9827 9828 9829 9830 9831 9832 9833 9834 9835 9836 9837 9838 9839 9840 9841 9842 9843 9844 9845 9846 9847 9848 9849 9850 9851 9852 9853 9854 9855 9856 9857 9858 9859 9860 9861 9862 9863 9864 9865 9866 9867 9868 9869 9870 9871 9872 9873 9874 9875 9876 9877 9878 9879 9880 9881 9882 9883 9884 9885 9886 9887 9888 9889 9890 9891 9892 9893 9894 9895 9896 9897 9898 9899 9900 9901 9902 9903 9904 9905 9906 9907 9908 9909 9910 9911 9912 9913 9914 9915 9916 9917 9918 9919 9920 9921 9922 9923 9924 9925 9926 9927 9928 9929 9930 9931 9932 9933 9934 9935 9936 9937 9938 9939 9940 9941 9942 9943 9944 9945 9946 9947 9948 9949 9950 9951 9952 9953 9954 9955 9956 9957 9958 9959 9960 9961 9962 9963 9964 9965 9966 9967 9968 9969 9970 9971 9972 9973 9974 9975 9976 9977 9978 9979 9980 9981 9982 9983 9984 9985 9986 9987 9988 9989 9990 9991 9992 9993 9994 9995 9996 9997 9998 9999 10000 10001 10002 10003 10004 10005 10006 10007 10008 10009 10010 10011 10012 10013 10014 10015 10016 10017 10018 10019 10020 10021 10022 10023 10024 10025 10026 10027 10028 10029 10030 10031 10032 10033 10034 10035 10036 10037 10038 10039 10040 10041 10042 10043 10044 10045 10046 10047 10048 10049 10050 10051 10052 10053 10054 10055 10056 10057 10058 10059 10060 10061 10062 10063 10064 10065 10066 10067 10068 10069 10070 10071 10072 10073 10074 10075 10076 10077 10078 10079 10080 10081 10082 10083 10084 10085 10086 10087 10088 10089 10090 10091 10092 10093 10094 10095 10096 10097 10098 10099 10100 10101 10102 10103 10104 10105 10106 10107 10108 10109 10110 10111 10112 10113 10114 10115 10116 10117 10118 10119 10120 10121 10122 10123 10124 10125 10126 10127 10128 10129 10130 10131 10132 10133 10134 10135 10136 10137 10138 10139 10140 10141 10142 10143 10144 10145 10146 10147 10148 10149 10150 10151 10152 10153 10154 10155 10156 10157 10158 10159 10160 10161 10162 10163 10164 10165 10166 10167 10168 10169 10170 10171 10172 10173 10174 10175 10176 10177 10178 10179 10180 10181 10182 10183 10184 10185 10186 10187 10188 10189 10190 10191 10192 10193 10194 10195 10196 10197 10198 10199 10200 10201 10202 10203 10204 10205 10206 10207 10208 10209 10210 10211 10212 10213 10214 10215 10216 10217 10218 10219 10220 10221 10222 10223 10224 10225 10226 10227 10228 10229 10230 10231 10232 10233 10234 10235 10236 10237 10238 10239 10240 10241 10242 10243 10244 10245 10246 10247 10248 10249 10250 10251 10252 10253 10254 10255 10256 10257 10258 10259 10260 10261 10262 10263 10264 10265 10266 10267 10268 10269 10270 10271 10272 10273 10274 10275 10276 10277 10278 10279 10280 10281 10282 10283 10284 10285 10286 10287 10288 10289 10290 10291 10292 10293 10294 10295 10296 10297 10298 10299 10300 10301 10302 10303 10304 10305 10306 10307 10308 10309 10310 10311 10312 10313 10314 10315 10316 10317 10318 10319 10320 10321 10322 10323 10324 10325 10326 10327 10328 10329 10330 10331 10332 10333 10334 10335 10336 10337 10338 10339 10340 10341 10342 10343 10344 10345 10346 10347 10348 10349 10350 10351 10352 10353 10354 10355 10356 10357 10358 10359 10360 10361 10362 10363 10364 10365 10366 10367 10368 10369 10370 10371 10372 10373 10374 10375 10376 10377 10378 10379 10380 10381 10382 10383 10384 10385 10386 10387 10388 10389 10390 10391 10392 10393 10394 10395 10396 10397 10398 10399 10400 10401 10402 10403 10404 10405 10406 10407 10408 10409 10410 10411 10412 10413 10414 10415 10416 10417 10418 10419 10420 10421 10422 10423 10424 10425 10426 10427 10428 10429 10430 10431 10432 10433 10434 10435 10436 10437 10438 10439 10440 10441 10442 10443 10444 10445 10446 10447 10448 10449 10450 10451 10452 10453 10454 10455 10456 10457 10458 10459 10460 10461 10462 10463 10464 10465 10466 10467 10468 10469 10470 10471 10472 10473 10474 10475 10476 10477 10478 10479 10480 10481 10482 10483 10484 10485 10486 10487 10488 10489 10490 10491 10492 10493 10494 10495 10496 10497 10498 10499 10500 10501 10502 10503 10504 10505 10506 10507 10508 10509 10510 10511 10512 10513 10514 10515 10516 10517 10518 10519 10520 10521 10522 10523 10524 10525 10526 10527 10528 10529 10530 10531 10532 10533 10534 10535 10536 10537 10538 10539 10540 10541 10542 10543 10544 10545 10546 10547 10548 10549 10550 10551 10552 10553 10554 10555 10556 10557 10558 10559 10560 10561 10562 10563 10564 10565 10566 10567 10568 10569 10570 10571 10572 10573 10574 10575 10576 10577 10578 10579 10580 10581 10582 10583 10584 10585 10586 10587 10588 10589 10590 10591 10592 10593 10594 10595 10596 10597 10598 10599 10600 10601 10602 10603 10604 10605 10606 10607 10608 10609 10610 10611 10612 10613 10614 10615 10616 10617 10618 10619 10620 10621 10622 10623 10624 10625 10626 10627 10628 10629 10630 10631 10632 10633 10634 10635 10636 10637 10638 10639 10640 10641 10642 10643 10644 10645 10646 10647 10648 10649 10650 10651 10652 10653 10654 10655 10656 10657 10658 10659 10660 10661 10662 10663 10664 10665 10666 10667 10668 10669 10670 10671 10672 10673 10674 10675 10676 10677 10678 10679 10680 10681 10682 10683 10684 10685 10686 10687 10688 10689 10690 10691 10692 10693 10694 10695 10696 10697 10698 10699 10700 10701 10702 10703 10704 10705 10706 10707 10708 10709 10710 10711 10712 10713 10714 10715 10716 10717 10718 10719 10720 10721 10722 10723 10724 10725 10726 10727 10728 10729 10730 10731 10732 10733 10734 10735 10736 10737 10738 10739 10740 10741 10742 10743 10744 10745 10746 10747 10748 10749 10750 10751 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __NET_CFG80211_H #define __NET_CFG80211_H /* * 802.11 device and configuration interface * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2015-2017 Intel Deutschland GmbH * Copyright (C) 2018-2026 Intel Corporation */ #include <linux/ethtool.h> #include <uapi/linux/rfkill.h> #include <linux/netdevice.h> #include <linux/debugfs.h> #include <linux/list.h> #include <linux/bug.h> #include <linux/netlink.h> #include <linux/skbuff.h> #include <linux/nl80211.h> #include <linux/if_ether.h> #include <linux/ieee80211.h> #include <linux/net.h> #include <linux/rfkill.h> #include <net/regulatory.h> /** * DOC: Introduction * * cfg80211 is the configuration API for 802.11 devices in Linux. It bridges * userspace and drivers, and offers some utility functionality associated * with 802.11. cfg80211 must, directly or indirectly via mac80211, be used * by all modern wireless drivers in Linux, so that they offer a consistent * API through nl80211. For backward compatibility, cfg80211 also offers * wireless extensions to userspace, but hides them from drivers completely. * * Additionally, cfg80211 contains code to help enforce regulatory spectrum * use restrictions. */ /** * DOC: Device registration * * In order for a driver to use cfg80211, it must register the hardware device * with cfg80211. This happens through a number of hardware capability structs * described below. * * The fundamental structure for each device is the 'wiphy', of which each * instance describes a physical wireless device connected to the system. Each * such wiphy can have zero, one, or many virtual interfaces associated with * it, which need to be identified as such by pointing the network interface's * @ieee80211_ptr pointer to a &struct wireless_dev which further describes * the wireless part of the interface. Normally this struct is embedded in the * network interface's private data area. Drivers can optionally allow creating * or destroying virtual interfaces on the fly, but without at least one or the * ability to create some the wireless device isn't useful. * * Each wiphy structure contains device capability information, and also has * a pointer to the various operations the driver offers. The definitions and * structures here describe these capabilities in detail. */ struct wiphy; /* * wireless hardware capability structures */ /** * enum ieee80211_channel_flags - channel flags * * Channel flags set by the regulatory control code. * * @IEEE80211_CHAN_DISABLED: This channel is disabled. * @IEEE80211_CHAN_NO_IR: do not initiate radiation, this includes * sending probe requests or beaconing. * @IEEE80211_CHAN_PSD: Power spectral density (in dBm) is set for this * channel. * @IEEE80211_CHAN_RADAR: Radar detection is required on this channel. * @IEEE80211_CHAN_NO_HT40PLUS: extension channel above this channel * is not permitted. * @IEEE80211_CHAN_NO_HT40MINUS: extension channel below this channel * is not permitted. * @IEEE80211_CHAN_NO_OFDM: OFDM is not allowed on this channel. * @IEEE80211_CHAN_NO_80MHZ: If the driver supports 80 MHz on the band, * this flag indicates that an 80 MHz channel cannot use this * channel as the control or any of the secondary channels. * This may be due to the driver or due to regulatory bandwidth * restrictions. * @IEEE80211_CHAN_NO_160MHZ: If the driver supports 160 MHz on the band, * this flag indicates that an 160 MHz channel cannot use this * channel as the control or any of the secondary channels. * This may be due to the driver or due to regulatory bandwidth * restrictions. * @IEEE80211_CHAN_INDOOR_ONLY: see %NL80211_FREQUENCY_ATTR_INDOOR_ONLY * @IEEE80211_CHAN_IR_CONCURRENT: see %NL80211_FREQUENCY_ATTR_IR_CONCURRENT * @IEEE80211_CHAN_NO_20MHZ: 20 MHz bandwidth is not permitted * on this channel. * @IEEE80211_CHAN_NO_10MHZ: 10 MHz bandwidth is not permitted * on this channel. * @IEEE80211_CHAN_NO_HE: HE operation is not permitted on this channel. * @IEEE80211_CHAN_NO_320MHZ: If the driver supports 320 MHz on the band, * this flag indicates that a 320 MHz channel cannot use this * channel as the control or any of the secondary channels. * This may be due to the driver or due to regulatory bandwidth * restrictions. * @IEEE80211_CHAN_NO_EHT: EHT operation is not permitted on this channel. * @IEEE80211_CHAN_DFS_CONCURRENT: See %NL80211_RRF_DFS_CONCURRENT * @IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT: Client connection with VLP AP * not permitted using this channel * @IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT: Client connection with AFC AP * not permitted using this channel * @IEEE80211_CHAN_CAN_MONITOR: This channel can be used for monitor * mode even in the presence of other (regulatory) restrictions, * even if it is otherwise disabled. * @IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP: Allow using this channel for AP operation * with very low power (VLP), even if otherwise set to NO_IR. * @IEEE80211_CHAN_ALLOW_20MHZ_ACTIVITY: Allow activity on a 20 MHz channel, * even if otherwise set to NO_IR. * @IEEE80211_CHAN_S1G_NO_PRIMARY: Prevents the channel for use as an S1G * primary channel. Does not prevent the wider operating channel * described by the chandef from being used. In order for a 2MHz primary * to be used, both 1MHz subchannels shall not contain this flag. * @IEEE80211_CHAN_NO_4MHZ: 4 MHz bandwidth is not permitted on this channel. * @IEEE80211_CHAN_NO_8MHZ: 8 MHz bandwidth is not permitted on this channel. * @IEEE80211_CHAN_NO_16MHZ: 16 MHz bandwidth is not permitted on this channel. * @IEEE80211_CHAN_NO_UHR: UHR operation is not permitted on this channel. */ enum ieee80211_channel_flags { IEEE80211_CHAN_DISABLED = BIT(0), IEEE80211_CHAN_NO_IR = BIT(1), IEEE80211_CHAN_PSD = BIT(2), IEEE80211_CHAN_RADAR = BIT(3), IEEE80211_CHAN_NO_HT40PLUS = BIT(4), IEEE80211_CHAN_NO_HT40MINUS = BIT(5), IEEE80211_CHAN_NO_OFDM = BIT(6), IEEE80211_CHAN_NO_80MHZ = BIT(7), IEEE80211_CHAN_NO_160MHZ = BIT(8), IEEE80211_CHAN_INDOOR_ONLY = BIT(9), IEEE80211_CHAN_IR_CONCURRENT = BIT(10), IEEE80211_CHAN_NO_20MHZ = BIT(11), IEEE80211_CHAN_NO_10MHZ = BIT(12), IEEE80211_CHAN_NO_HE = BIT(13), /* can use free bits here */ IEEE80211_CHAN_NO_UHR = BIT(18), IEEE80211_CHAN_NO_320MHZ = BIT(19), IEEE80211_CHAN_NO_EHT = BIT(20), IEEE80211_CHAN_DFS_CONCURRENT = BIT(21), IEEE80211_CHAN_NO_6GHZ_VLP_CLIENT = BIT(22), IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT = BIT(23), IEEE80211_CHAN_CAN_MONITOR = BIT(24), IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP = BIT(25), IEEE80211_CHAN_ALLOW_20MHZ_ACTIVITY = BIT(26), IEEE80211_CHAN_S1G_NO_PRIMARY = BIT(27), IEEE80211_CHAN_NO_4MHZ = BIT(28), IEEE80211_CHAN_NO_8MHZ = BIT(29), IEEE80211_CHAN_NO_16MHZ = BIT(30), }; #define IEEE80211_CHAN_NO_HT40 \ (IEEE80211_CHAN_NO_HT40PLUS | IEEE80211_CHAN_NO_HT40MINUS) #define IEEE80211_DFS_MIN_CAC_TIME_MS 60000 #define IEEE80211_DFS_MIN_NOP_TIME_MS (30 * 60 * 1000) /** * struct ieee80211_channel - channel definition * * This structure describes a single channel for use * with cfg80211. * * @center_freq: center frequency in MHz * @freq_offset: offset from @center_freq, in KHz * @hw_value: hardware-specific value for the channel * @flags: channel flags from &enum ieee80211_channel_flags. * @orig_flags: channel flags at registration time, used by regulatory * code to support devices with additional restrictions * @band: band this channel belongs to. * @max_antenna_gain: maximum antenna gain in dBi * @max_power: maximum transmission power (in dBm) * @max_reg_power: maximum regulatory transmission power (in dBm) * @beacon_found: helper to regulatory code to indicate when a beacon * has been found on this channel. Use regulatory_hint_found_beacon() * to enable this, this is useful only on 5 GHz band. * @orig_mag: internal use * @orig_mpwr: internal use * @dfs_state: current state of this channel. Only relevant if radar is required * on this channel. * @dfs_state_entered: timestamp (jiffies) when the dfs state was entered. * @dfs_cac_ms: DFS CAC time in milliseconds, this is valid for DFS channels. * @cac_start_time: timestamp (CLOCK_BOOTTIME, nanoseconds) when CAC was * started on this channel. Zero when CAC is not in progress. * @psd: power spectral density (in dBm) */ struct ieee80211_channel { enum nl80211_band band; u32 center_freq; u16 freq_offset; u16 hw_value; u32 flags; int max_antenna_gain; int max_power; int max_reg_power; bool beacon_found; u32 orig_flags; int orig_mag, orig_mpwr; enum nl80211_dfs_state dfs_state; unsigned long dfs_state_entered; unsigned int dfs_cac_ms; u64 cac_start_time; s8 psd; }; /** * enum ieee80211_rate_flags - rate flags * * Hardware/specification flags for rates. These are structured * in a way that allows using the same bitrate structure for * different bands/PHY modes. * * @IEEE80211_RATE_SHORT_PREAMBLE: Hardware can send with short * preamble on this bitrate; only relevant in 2.4GHz band and * with CCK rates. * @IEEE80211_RATE_MANDATORY_A: This bitrate is a mandatory rate * when used with 802.11a (on the 5 GHz band); filled by the * core code when registering the wiphy. * @IEEE80211_RATE_MANDATORY_B: This bitrate is a mandatory rate * when used with 802.11b (on the 2.4 GHz band); filled by the * core code when registering the wiphy. * @IEEE80211_RATE_MANDATORY_G: This bitrate is a mandatory rate * when used with 802.11g (on the 2.4 GHz band); filled by the * core code when registering the wiphy. * @IEEE80211_RATE_ERP_G: This is an ERP rate in 802.11g mode. * @IEEE80211_RATE_SUPPORTS_5MHZ: Rate can be used in 5 MHz mode * @IEEE80211_RATE_SUPPORTS_10MHZ: Rate can be used in 10 MHz mode */ enum ieee80211_rate_flags { IEEE80211_RATE_SHORT_PREAMBLE = BIT(0), IEEE80211_RATE_MANDATORY_A = BIT(1), IEEE80211_RATE_MANDATORY_B = BIT(2), IEEE80211_RATE_MANDATORY_G = BIT(3), IEEE80211_RATE_ERP_G = BIT(4), IEEE80211_RATE_SUPPORTS_5MHZ = BIT(5), IEEE80211_RATE_SUPPORTS_10MHZ = BIT(6), }; /** * enum ieee80211_bss_type - BSS type filter * * @IEEE80211_BSS_TYPE_ESS: Infrastructure BSS * @IEEE80211_BSS_TYPE_PBSS: Personal BSS * @IEEE80211_BSS_TYPE_IBSS: Independent BSS * @IEEE80211_BSS_TYPE_MBSS: Mesh BSS * @IEEE80211_BSS_TYPE_ANY: Wildcard value for matching any BSS type */ enum ieee80211_bss_type { IEEE80211_BSS_TYPE_ESS, IEEE80211_BSS_TYPE_PBSS, IEEE80211_BSS_TYPE_IBSS, IEEE80211_BSS_TYPE_MBSS, IEEE80211_BSS_TYPE_ANY }; /** * enum ieee80211_privacy - BSS privacy filter * * @IEEE80211_PRIVACY_ON: privacy bit set * @IEEE80211_PRIVACY_OFF: privacy bit clear * @IEEE80211_PRIVACY_ANY: Wildcard value for matching any privacy setting */ enum ieee80211_privacy { IEEE80211_PRIVACY_ON, IEEE80211_PRIVACY_OFF, IEEE80211_PRIVACY_ANY }; #define IEEE80211_PRIVACY(x) \ ((x) ? IEEE80211_PRIVACY_ON : IEEE80211_PRIVACY_OFF) /** * struct ieee80211_rate - bitrate definition * * This structure describes a bitrate that an 802.11 PHY can * operate with. The two values @hw_value and @hw_value_short * are only for driver use when pointers to this structure are * passed around. * * @flags: rate-specific flags from &enum ieee80211_rate_flags * @bitrate: bitrate in units of 100 Kbps * @hw_value: driver/hardware value for this rate * @hw_value_short: driver/hardware value for this rate when * short preamble is used */ struct ieee80211_rate { u32 flags; u16 bitrate; u16 hw_value, hw_value_short; }; /** * struct ieee80211_he_obss_pd - AP settings for spatial reuse * * @enable: is the feature enabled. * @sr_ctrl: The SR Control field of SRP element. * @non_srg_max_offset: non-SRG maximum tx power offset * @min_offset: minimal tx power offset an associated station shall use * @max_offset: maximum tx power offset an associated station shall use * @bss_color_bitmap: bitmap that indicates the BSS color values used by * members of the SRG * @partial_bssid_bitmap: bitmap that indicates the partial BSSID values * used by members of the SRG */ struct ieee80211_he_obss_pd { bool enable; u8 sr_ctrl; u8 non_srg_max_offset; u8 min_offset; u8 max_offset; u8 bss_color_bitmap[8]; u8 partial_bssid_bitmap[8]; }; /** * struct cfg80211_he_bss_color - AP settings for BSS coloring * * @color: the current color. * @enabled: HE BSS color is used * @partial: define the AID equation. */ struct cfg80211_he_bss_color { u8 color; bool enabled; bool partial; }; /** * struct ieee80211_sta_ht_cap - STA's HT capabilities * * This structure describes most essential parameters needed * to describe 802.11n HT capabilities for an STA. * * @ht_supported: is HT supported by the STA * @cap: HT capabilities map as described in 802.11n spec * @ampdu_factor: Maximum A-MPDU length factor * @ampdu_density: Minimum A-MPDU spacing * @mcs: Supported MCS rates */ struct ieee80211_sta_ht_cap { u16 cap; /* use IEEE80211_HT_CAP_ */ bool ht_supported; u8 ampdu_factor; u8 ampdu_density; struct ieee80211_mcs_info mcs; }; /** * struct ieee80211_sta_vht_cap - STA's VHT capabilities * * This structure describes most essential parameters needed * to describe 802.11ac VHT capabilities for an STA. * * @vht_supported: is VHT supported by the STA * @cap: VHT capabilities map as described in 802.11ac spec * @vht_mcs: Supported VHT MCS rates */ struct ieee80211_sta_vht_cap { bool vht_supported; u32 cap; /* use IEEE80211_VHT_CAP_ */ struct ieee80211_vht_mcs_info vht_mcs; }; #define IEEE80211_HE_PPE_THRES_MAX_LEN 25 /** * struct ieee80211_sta_he_cap - STA's HE capabilities * * This structure describes most essential parameters needed * to describe 802.11ax HE capabilities for a STA. * * @has_he: true iff HE data is valid. * @he_cap_elem: Fixed portion of the HE capabilities element. * @he_mcs_nss_supp: The supported NSS/MCS combinations. * @ppe_thres: Holds the PPE Thresholds data. */ struct ieee80211_sta_he_cap { bool has_he; struct ieee80211_he_cap_elem he_cap_elem; struct ieee80211_he_mcs_nss_supp he_mcs_nss_supp; u8 ppe_thres[IEEE80211_HE_PPE_THRES_MAX_LEN]; }; /** * struct ieee80211_eht_mcs_nss_supp - EHT max supported NSS per MCS * * See P802.11be_D1.3 Table 9-401k - "Subfields of the Supported EHT-MCS * and NSS Set field" * * @only_20mhz: MCS/NSS support for 20 MHz-only STA. * @bw: MCS/NSS support for 80, 160 and 320 MHz * @bw._80: MCS/NSS support for BW <= 80 MHz * @bw._160: MCS/NSS support for BW = 160 MHz * @bw._320: MCS/NSS support for BW = 320 MHz */ struct ieee80211_eht_mcs_nss_supp { union { struct ieee80211_eht_mcs_nss_supp_20mhz_only only_20mhz; struct { struct ieee80211_eht_mcs_nss_supp_bw _80; struct ieee80211_eht_mcs_nss_supp_bw _160; struct ieee80211_eht_mcs_nss_supp_bw _320; } __packed bw; } __packed; } __packed; #define IEEE80211_EHT_PPE_THRES_MAX_LEN 32 /** * struct ieee80211_sta_eht_cap - STA's EHT capabilities * * This structure describes most essential parameters needed * to describe 802.11be EHT capabilities for a STA. * * @has_eht: true iff EHT data is valid. * @eht_cap_elem: Fixed portion of the eht capabilities element. * @eht_mcs_nss_supp: The supported NSS/MCS combinations. * @eht_ppe_thres: Holds the PPE Thresholds data. */ struct ieee80211_sta_eht_cap { bool has_eht; struct ieee80211_eht_cap_elem_fixed eht_cap_elem; struct ieee80211_eht_mcs_nss_supp eht_mcs_nss_supp; u8 eht_ppe_thres[IEEE80211_EHT_PPE_THRES_MAX_LEN]; }; /** * struct ieee80211_sta_uhr_cap - STA's UHR capabilities * @has_uhr: true iff UHR is supported and data is valid * @mac: fixed MAC capabilities * @phy: fixed PHY capabilities */ struct ieee80211_sta_uhr_cap { bool has_uhr; struct ieee80211_uhr_cap_mac mac; struct ieee80211_uhr_cap_phy phy; }; /* sparse defines __CHECKER__; see Documentation/dev-tools/sparse.rst */ #ifdef __CHECKER__ /* * This is used to mark the sband->iftype_data pointer which is supposed * to be an array with special access semantics (per iftype), but a lot * of code got it wrong in the past, so with this marking sparse will be * noisy when the pointer is used directly. */ # define __iftd __attribute__((noderef, address_space(__iftype_data))) #else # define __iftd #endif /* __CHECKER__ */ /** * struct ieee80211_sband_iftype_data - sband data per interface type * * This structure encapsulates sband data that is relevant for the * interface types defined in @types_mask. Each type in the * @types_mask must be unique across all instances of iftype_data. * * @types_mask: interface types mask * @he_cap: holds the HE capabilities * @he_6ghz_capa: HE 6 GHz capabilities, must be filled in for a * 6 GHz band channel (and 0 may be valid value). * @eht_cap: STA's EHT capabilities * @uhr_cap: STA's UHR capabilities * @vendor_elems: vendor element(s) to advertise * @vendor_elems.data: vendor element(s) data * @vendor_elems.len: vendor element(s) length */ struct ieee80211_sband_iftype_data { u16 types_mask; struct ieee80211_sta_he_cap he_cap; struct ieee80211_he_6ghz_capa he_6ghz_capa; struct ieee80211_sta_eht_cap eht_cap; struct ieee80211_sta_uhr_cap uhr_cap; struct { const u8 *data; unsigned int len; } vendor_elems; }; /** * enum ieee80211_edmg_bw_config - allowed channel bandwidth configurations * * @IEEE80211_EDMG_BW_CONFIG_4: 2.16GHz * @IEEE80211_EDMG_BW_CONFIG_5: 2.16GHz and 4.32GHz * @IEEE80211_EDMG_BW_CONFIG_6: 2.16GHz, 4.32GHz and 6.48GHz * @IEEE80211_EDMG_BW_CONFIG_7: 2.16GHz, 4.32GHz, 6.48GHz and 8.64GHz * @IEEE80211_EDMG_BW_CONFIG_8: 2.16GHz and 2.16GHz + 2.16GHz * @IEEE80211_EDMG_BW_CONFIG_9: 2.16GHz, 4.32GHz and 2.16GHz + 2.16GHz * @IEEE80211_EDMG_BW_CONFIG_10: 2.16GHz, 4.32GHz, 6.48GHz and 2.16GHz+2.16GHz * @IEEE80211_EDMG_BW_CONFIG_11: 2.16GHz, 4.32GHz, 6.48GHz, 8.64GHz and * 2.16GHz+2.16GHz * @IEEE80211_EDMG_BW_CONFIG_12: 2.16GHz, 2.16GHz + 2.16GHz and * 4.32GHz + 4.32GHz * @IEEE80211_EDMG_BW_CONFIG_13: 2.16GHz, 4.32GHz, 2.16GHz + 2.16GHz and * 4.32GHz + 4.32GHz * @IEEE80211_EDMG_BW_CONFIG_14: 2.16GHz, 4.32GHz, 6.48GHz, 2.16GHz + 2.16GHz * and 4.32GHz + 4.32GHz * @IEEE80211_EDMG_BW_CONFIG_15: 2.16GHz, 4.32GHz, 6.48GHz, 8.64GHz, * 2.16GHz + 2.16GHz and 4.32GHz + 4.32GHz */ enum ieee80211_edmg_bw_config { IEEE80211_EDMG_BW_CONFIG_4 = 4, IEEE80211_EDMG_BW_CONFIG_5 = 5, IEEE80211_EDMG_BW_CONFIG_6 = 6, IEEE80211_EDMG_BW_CONFIG_7 = 7, IEEE80211_EDMG_BW_CONFIG_8 = 8, IEEE80211_EDMG_BW_CONFIG_9 = 9, IEEE80211_EDMG_BW_CONFIG_10 = 10, IEEE80211_EDMG_BW_CONFIG_11 = 11, IEEE80211_EDMG_BW_CONFIG_12 = 12, IEEE80211_EDMG_BW_CONFIG_13 = 13, IEEE80211_EDMG_BW_CONFIG_14 = 14, IEEE80211_EDMG_BW_CONFIG_15 = 15, }; /** * struct ieee80211_edmg - EDMG configuration * * This structure describes most essential parameters needed * to describe 802.11ay EDMG configuration * * @channels: bitmap that indicates the 2.16 GHz channel(s) * that are allowed to be used for transmissions. * Bit 0 indicates channel 1, bit 1 indicates channel 2, etc. * Set to 0 indicate EDMG not supported. * @bw_config: Channel BW Configuration subfield encodes * the allowed channel bandwidth configurations */ struct ieee80211_edmg { u8 channels; enum ieee80211_edmg_bw_config bw_config; }; /** * struct ieee80211_sta_s1g_cap - STA's S1G capabilities * * This structure describes most essential parameters needed * to describe 802.11ah S1G capabilities for a STA. * * @s1g: is STA an S1G STA * @cap: S1G capabilities information * @nss_mcs: Supported NSS MCS set */ struct ieee80211_sta_s1g_cap { bool s1g; u8 cap[10]; /* use S1G_CAPAB_ */ u8 nss_mcs[5]; }; /** * struct ieee80211_supported_band - frequency band definition * * This structure describes a frequency band a wiphy * is able to operate in. * * @channels: Array of channels the hardware can operate with * in this band. * @band: the band this structure represents * @n_channels: Number of channels in @channels * @bitrates: Array of bitrates the hardware can operate with * in this band. Must be sorted to give a valid "supported * rates" IE, i.e. CCK rates first, then OFDM. * @n_bitrates: Number of bitrates in @bitrates * @ht_cap: HT capabilities in this band * @vht_cap: VHT capabilities in this band * @s1g_cap: S1G capabilities in this band * @edmg_cap: EDMG capabilities in this band * @s1g_cap: S1G capabilities in this band (S1G band only, of course) * @n_iftype_data: number of iftype data entries * @iftype_data: interface type data entries. Note that the bits in * @types_mask inside this structure cannot overlap (i.e. only * one occurrence of each type is allowed across all instances of * iftype_data). */ struct ieee80211_supported_band { struct ieee80211_channel *channels; struct ieee80211_rate *bitrates; enum nl80211_band band; int n_channels; int n_bitrates; struct ieee80211_sta_ht_cap ht_cap; struct ieee80211_sta_vht_cap vht_cap; struct ieee80211_sta_s1g_cap s1g_cap; struct ieee80211_edmg edmg_cap; u16 n_iftype_data; const struct ieee80211_sband_iftype_data __iftd *iftype_data; }; /** * _ieee80211_set_sband_iftype_data - set sband iftype data array * @sband: the sband to initialize * @iftd: the iftype data array pointer * @n_iftd: the length of the iftype data array * * Set the sband iftype data array; use this where the length cannot * be derived from the ARRAY_SIZE() of the argument, but prefer * ieee80211_set_sband_iftype_data() where it can be used. */ static inline void _ieee80211_set_sband_iftype_data(struct ieee80211_supported_band *sband, const struct ieee80211_sband_iftype_data *iftd, u16 n_iftd) { sband->iftype_data = (const void __iftd __force *)iftd; sband->n_iftype_data = n_iftd; } /** * ieee80211_set_sband_iftype_data - set sband iftype data array * @sband: the sband to initialize * @iftd: the iftype data array */ #define ieee80211_set_sband_iftype_data(sband, iftd) \ _ieee80211_set_sband_iftype_data(sband, iftd, ARRAY_SIZE(iftd)) /** * for_each_sband_iftype_data - iterate sband iftype data entries * @sband: the sband whose iftype_data array to iterate * @i: iterator counter * @iftd: iftype data pointer to set */ #define for_each_sband_iftype_data(sband, i, iftd) \ for (i = 0, iftd = (const void __force *)&(sband)->iftype_data[i]; \ i < (sband)->n_iftype_data; \ i++, iftd = (const void __force *)&(sband)->iftype_data[i]) /** * ieee80211_get_sband_iftype_data - return sband data for a given iftype * @sband: the sband to search for the STA on * @iftype: enum nl80211_iftype * * Return: pointer to struct ieee80211_sband_iftype_data, or NULL is none found */ static inline const struct ieee80211_sband_iftype_data * ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband, u8 iftype) { const struct ieee80211_sband_iftype_data *data; int i; if (WARN_ON(iftype >= NUM_NL80211_IFTYPES)) return NULL; if (iftype == NL80211_IFTYPE_AP_VLAN) iftype = NL80211_IFTYPE_AP; for_each_sband_iftype_data(sband, i, data) { if (data->types_mask & BIT(iftype)) return data; } return NULL; } /** * ieee80211_get_he_iftype_cap - return HE capabilities for an sband's iftype * @sband: the sband to search for the iftype on * @iftype: enum nl80211_iftype * * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found */ static inline const struct ieee80211_sta_he_cap * ieee80211_get_he_iftype_cap(const struct ieee80211_supported_band *sband, u8 iftype) { const struct ieee80211_sband_iftype_data *data = ieee80211_get_sband_iftype_data(sband, iftype); if (data && data->he_cap.has_he) return &data->he_cap; return NULL; } /** * ieee80211_get_he_6ghz_capa - return HE 6 GHz capabilities * @sband: the sband to search for the STA on * @iftype: the iftype to search for * * Return: the 6GHz capabilities */ static inline __le16 ieee80211_get_he_6ghz_capa(const struct ieee80211_supported_band *sband, enum nl80211_iftype iftype) { const struct ieee80211_sband_iftype_data *data = ieee80211_get_sband_iftype_data(sband, iftype); if (WARN_ON(!data || !data->he_cap.has_he)) return 0; return data->he_6ghz_capa.capa; } /** * ieee80211_get_eht_iftype_cap - return EHT capabilities for an sband's iftype * @sband: the sband to search for the iftype on * @iftype: enum nl80211_iftype * * Return: pointer to the struct ieee80211_sta_eht_cap, or NULL is none found */ static inline const struct ieee80211_sta_eht_cap * ieee80211_get_eht_iftype_cap(const struct ieee80211_supported_band *sband, enum nl80211_iftype iftype) { const struct ieee80211_sband_iftype_data *data = ieee80211_get_sband_iftype_data(sband, iftype); if (data && data->eht_cap.has_eht) return &data->eht_cap; return NULL; } /** * ieee80211_get_uhr_iftype_cap - return UHR capabilities for an sband's iftype * @sband: the sband to search for the iftype on * @iftype: enum nl80211_iftype * * Return: pointer to the struct ieee80211_sta_uhr_cap, or NULL is none found */ static inline const struct ieee80211_sta_uhr_cap * ieee80211_get_uhr_iftype_cap(const struct ieee80211_supported_band *sband, enum nl80211_iftype iftype) { const struct ieee80211_sband_iftype_data *data = ieee80211_get_sband_iftype_data(sband, iftype); if (data && data->uhr_cap.has_uhr) return &data->uhr_cap; return NULL; } /** * wiphy_read_of_freq_limits - read frequency limits from device tree * * @wiphy: the wireless device to get extra limits for * * Some devices may have extra limitations specified in DT. This may be useful * for chipsets that normally support more bands but are limited due to board * design (e.g. by antennas or external power amplifier). * * This function reads info from DT and uses it to *modify* channels (disable * unavailable ones). It's usually a *bad* idea to use it in drivers with * shared channel data as DT limitations are device specific. You should make * sure to call it only if channels in wiphy are copied and can be modified * without affecting other devices. * * As this function access device node it has to be called after set_wiphy_dev. * It also modifies channels so they have to be set first. * If using this helper, call it before wiphy_register(). */ #ifdef CONFIG_OF void wiphy_read_of_freq_limits(struct wiphy *wiphy); #else /* CONFIG_OF */ static inline void wiphy_read_of_freq_limits(struct wiphy *wiphy) { } #endif /* !CONFIG_OF */ /* * Wireless hardware/device configuration structures and methods */ /** * DOC: Actions and configuration * * Each wireless device and each virtual interface offer a set of configuration * operations and other actions that are invoked by userspace. Each of these * actions is described in the operations structure, and the parameters these * operations use are described separately. * * Additionally, some operations are asynchronous and expect to get status * information via some functions that drivers need to call. * * Scanning and BSS list handling with its associated functionality is described * in a separate chapter. */ #define VHT_MUMIMO_GROUPS_DATA_LEN (WLAN_MEMBERSHIP_LEN +\ WLAN_USER_POSITION_LEN) /** * struct vif_params - describes virtual interface parameters * @flags: monitor interface flags, unchanged if 0, otherwise * %MONITOR_FLAG_CHANGED will be set * @use_4addr: use 4-address frames * @macaddr: address to use for this virtual interface. * If this parameter is set to zero address the driver may * determine the address as needed. * This feature is only fully supported by drivers that enable the * %NL80211_FEATURE_MAC_ON_CREATE flag. Others may support creating ** only p2p devices with specified MAC. * @vht_mumimo_groups: MU-MIMO groupID, used for monitoring MU-MIMO packets * belonging to that MU-MIMO groupID; %NULL if not changed * @vht_mumimo_follow_addr: MU-MIMO follow address, used for monitoring * MU-MIMO packets going to the specified station; %NULL if not changed */ struct vif_params { u32 flags; int use_4addr; u8 macaddr[ETH_ALEN]; const u8 *vht_mumimo_groups; const u8 *vht_mumimo_follow_addr; }; /** * struct key_params - key information * * Information about a key * * @key: key material * @key_len: length of key material * @cipher: cipher suite selector * @seq: sequence counter (IV/PN), must be in little endian, * length given by @seq_len. * @seq_len: length of @seq. * @vlan_id: vlan_id for VLAN group key (if nonzero) * @mode: key install mode (RX_TX, NO_TX or SET_TX) */ struct key_params { const u8 *key; const u8 *seq; int key_len; int seq_len; u16 vlan_id; u32 cipher; enum nl80211_key_mode mode; }; /** * struct cfg80211_chan_def - channel definition * @chan: the (control) channel * @width: channel width * @center_freq1: center frequency of first segment * @center_freq2: center frequency of second segment * (only with 80+80 MHz) * @edmg: define the EDMG channels configuration. * If edmg is requested (i.e. the .channels member is non-zero), * chan will define the primary channel and all other * parameters are ignored. * @freq1_offset: offset from @center_freq1, in KHz * @punctured: mask of the punctured 20 MHz subchannels, with * bits turned on being disabled (punctured); numbered * from lower to higher frequency (like in the spec) * @s1g_primary_2mhz: Indicates if the control channel pointed to * by 'chan' exists as a 1MHz primary subchannel within an * S1G 2MHz primary channel. */ struct cfg80211_chan_def { struct ieee80211_channel *chan; enum nl80211_chan_width width; u32 center_freq1; u32 center_freq2; struct ieee80211_edmg edmg; u16 freq1_offset; u16 punctured; bool s1g_primary_2mhz; }; /* * cfg80211_bitrate_mask - masks for bitrate control */ struct cfg80211_bitrate_mask { struct { u32 legacy; u8 ht_mcs[IEEE80211_HT_MCS_MASK_LEN]; u16 vht_mcs[NL80211_VHT_NSS_MAX]; u16 he_mcs[NL80211_HE_NSS_MAX]; u16 eht_mcs[NL80211_EHT_NSS_MAX]; enum nl80211_txrate_gi gi; enum nl80211_he_gi he_gi; enum nl80211_eht_gi eht_gi; enum nl80211_he_ltf he_ltf; enum nl80211_eht_ltf eht_ltf; } control[NUM_NL80211_BANDS]; }; /** * struct cfg80211_tid_cfg - TID specific configuration * @config_override: Flag to notify driver to reset TID configuration * of the peer. * @tids: bitmap of TIDs to modify * @mask: bitmap of attributes indicating which parameter changed, * similar to &nl80211_tid_config_supp. * @noack: noack configuration value for the TID * @retry_long: retry count value * @retry_short: retry count value * @ampdu: Enable/Disable MPDU aggregation * @rtscts: Enable/Disable RTS/CTS * @amsdu: Enable/Disable MSDU aggregation * @txrate_type: Tx bitrate mask type * @txrate_mask: Tx bitrate to be applied for the TID */ struct cfg80211_tid_cfg { bool config_override; u8 tids; u64 mask; enum nl80211_tid_config noack; u8 retry_long, retry_short; enum nl80211_tid_config ampdu; enum nl80211_tid_config rtscts; enum nl80211_tid_config amsdu; enum nl80211_tx_rate_setting txrate_type; struct cfg80211_bitrate_mask txrate_mask; }; /** * struct cfg80211_tid_config - TID configuration * @peer: Station's MAC address * @n_tid_conf: Number of TID specific configurations to be applied * @tid_conf: Configuration change info */ struct cfg80211_tid_config { const u8 *peer; u32 n_tid_conf; struct cfg80211_tid_cfg tid_conf[] __counted_by(n_tid_conf); }; /** * struct cfg80211_fils_aad - FILS AAD data * @macaddr: STA MAC address * @kek: FILS KEK * @kek_len: FILS KEK length * @snonce: STA Nonce * @anonce: AP Nonce */ struct cfg80211_fils_aad { const u8 *macaddr; const u8 *kek; u8 kek_len; const u8 *snonce; const u8 *anonce; }; /** * struct cfg80211_set_hw_timestamp - enable/disable HW timestamping * @macaddr: peer MAC address. NULL to enable/disable HW timestamping for all * addresses. * @enable: if set, enable HW timestamping for the specified MAC address. * Otherwise disable HW timestamping for the specified MAC address. */ struct cfg80211_set_hw_timestamp { const u8 *macaddr; bool enable; }; /** * cfg80211_get_chandef_type - return old channel type from chandef * @chandef: the channel definition * * Return: The old channel type (NOHT, HT20, HT40+/-) from a given * chandef, which must have a bandwidth allowing this conversion. */ static inline enum nl80211_channel_type cfg80211_get_chandef_type(const struct cfg80211_chan_def *chandef) { switch (chandef->width) { case NL80211_CHAN_WIDTH_20_NOHT: return NL80211_CHAN_NO_HT; case NL80211_CHAN_WIDTH_20: return NL80211_CHAN_HT20; case NL80211_CHAN_WIDTH_40: if (chandef->center_freq1 > chandef->chan->center_freq) return NL80211_CHAN_HT40PLUS; return NL80211_CHAN_HT40MINUS; default: WARN_ON(1); return NL80211_CHAN_NO_HT; } } /** * cfg80211_chandef_create - create channel definition using channel type * @chandef: the channel definition struct to fill * @channel: the control channel * @chantype: the channel type * * Given a channel type, create a channel definition. */ void cfg80211_chandef_create(struct cfg80211_chan_def *chandef, struct ieee80211_channel *channel, enum nl80211_channel_type chantype); /** * cfg80211_chandef_identical - check if two channel definitions are identical * @chandef1: first channel definition * @chandef2: second channel definition * * Return: %true if the channels defined by the channel definitions are * identical, %false otherwise. */ static inline bool cfg80211_chandef_identical(const struct cfg80211_chan_def *chandef1, const struct cfg80211_chan_def *chandef2) { return (chandef1->chan == chandef2->chan && chandef1->width == chandef2->width && chandef1->center_freq1 == chandef2->center_freq1 && chandef1->freq1_offset == chandef2->freq1_offset && chandef1->center_freq2 == chandef2->center_freq2 && chandef1->punctured == chandef2->punctured && chandef1->s1g_primary_2mhz == chandef2->s1g_primary_2mhz); } /** * cfg80211_chandef_is_edmg - check if chandef represents an EDMG channel * * @chandef: the channel definition * * Return: %true if EDMG defined, %false otherwise. */ static inline bool cfg80211_chandef_is_edmg(const struct cfg80211_chan_def *chandef) { return chandef->edmg.channels || chandef->edmg.bw_config; } /** * cfg80211_chandef_is_s1g - check if chandef represents an S1G channel * @chandef: the channel definition * * Return: %true if S1G. */ static inline bool cfg80211_chandef_is_s1g(const struct cfg80211_chan_def *chandef) { return chandef->chan->band == NL80211_BAND_S1GHZ; } /** * cfg80211_chandef_compatible - check if two channel definitions are compatible * @chandef1: first channel definition * @chandef2: second channel definition * * Return: %NULL if the given channel definitions are incompatible, * chandef1 or chandef2 otherwise. */ const struct cfg80211_chan_def * cfg80211_chandef_compatible(const struct cfg80211_chan_def *chandef1, const struct cfg80211_chan_def *chandef2); /** * nl80211_chan_width_to_mhz - get the channel width in MHz * @chan_width: the channel width from &enum nl80211_chan_width * * Return: channel width in MHz if the chan_width from &enum nl80211_chan_width * is valid. -1 otherwise. */ int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width); /** * cfg80211_chandef_get_width - return chandef width in MHz * @c: chandef to return bandwidth for * Return: channel width in MHz for the given chandef; note that it returns * 80 for 80+80 configurations */ static inline int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c) { return nl80211_chan_width_to_mhz(c->width); } /** * cfg80211_chandef_valid - check if a channel definition is valid * @chandef: the channel definition to check * Return: %true if the channel definition is valid. %false otherwise. */ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef); /** * cfg80211_chandef_usable - check if secondary channels can be used * @wiphy: the wiphy to validate against * @chandef: the channel definition to check * @prohibited_flags: the regulatory channel flags that must not be set * Return: %true if secondary channels are usable. %false otherwise. */ bool cfg80211_chandef_usable(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef, u32 prohibited_flags); /** * cfg80211_chandef_dfs_required - checks if radar detection is required * @wiphy: the wiphy to validate against * @chandef: the channel definition to check * @iftype: the interface type as specified in &enum nl80211_iftype * Returns: * 1 if radar detection is required, 0 if it is not, < 0 on error */ int cfg80211_chandef_dfs_required(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef, enum nl80211_iftype iftype); /** * cfg80211_chandef_dfs_usable - checks if chandef is DFS usable and we * can/need start CAC on such channel * @wiphy: the wiphy to validate against * @chandef: the channel definition to check * * Return: true if all channels available and at least * one channel requires CAC (NL80211_DFS_USABLE) */ bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef); /** * cfg80211_chandef_dfs_cac_time - get the DFS CAC time (in ms) for given * channel definition * @wiphy: the wiphy to validate against * @chandef: the channel definition to check * * Returns: DFS CAC time (in ms) which applies for this channel definition */ unsigned int cfg80211_chandef_dfs_cac_time(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef); /** * cfg80211_chandef_primary - calculate primary 40/80/160 MHz freq * @chandef: chandef to calculate for * @primary_chan_width: primary channel width to calculate center for * @punctured: punctured sub-channel bitmap, will be recalculated * according to the new bandwidth, can be %NULL * * Returns: the primary 40/80/160 MHz channel center frequency, or -1 * for errors, updating the punctured bitmap */ int cfg80211_chandef_primary(const struct cfg80211_chan_def *chandef, enum nl80211_chan_width primary_chan_width, u16 *punctured); /** * nl80211_send_chandef - sends the channel definition. * @msg: the msg to send channel definition * @chandef: the channel definition to check * * Returns: 0 if sent the channel definition to msg, < 0 on error **/ int nl80211_send_chandef(struct sk_buff *msg, const struct cfg80211_chan_def *chandef); /** * ieee80211_chandef_max_power - maximum transmission power for the chandef * * In some regulations, the transmit power may depend on the configured channel * bandwidth which may be defined as dBm/MHz. This function returns the actual * max_power for non-standard (20 MHz) channels. * * @chandef: channel definition for the channel * * Returns: maximum allowed transmission power in dBm for the chandef */ static inline int ieee80211_chandef_max_power(struct cfg80211_chan_def *chandef) { switch (chandef->width) { case NL80211_CHAN_WIDTH_5: return min(chandef->chan->max_reg_power - 6, chandef->chan->max_power); case NL80211_CHAN_WIDTH_10: return min(chandef->chan->max_reg_power - 3, chandef->chan->max_power); default: break; } return chandef->chan->max_power; } /** * cfg80211_any_usable_channels - check for usable channels * @wiphy: the wiphy to check for * @band_mask: which bands to check on * @prohibited_flags: which channels to not consider usable, * %IEEE80211_CHAN_DISABLED is always taken into account * * Return: %true if usable channels found, %false otherwise */ bool cfg80211_any_usable_channels(struct wiphy *wiphy, unsigned long band_mask, u32 prohibited_flags); /** * enum survey_info_flags - survey information flags * * @SURVEY_INFO_NOISE_DBM: noise (in dBm) was filled in * @SURVEY_INFO_IN_USE: channel is currently being used * @SURVEY_INFO_TIME: active time (in ms) was filled in * @SURVEY_INFO_TIME_BUSY: busy time was filled in * @SURVEY_INFO_TIME_EXT_BUSY: extension channel busy time was filled in * @SURVEY_INFO_TIME_RX: receive time was filled in * @SURVEY_INFO_TIME_TX: transmit time was filled in * @SURVEY_INFO_TIME_SCAN: scan time was filled in * @SURVEY_INFO_TIME_BSS_RX: local BSS receive time was filled in * * Used by the driver to indicate which info in &struct survey_info * it has filled in during the get_survey(). */ enum survey_info_flags { SURVEY_INFO_NOISE_DBM = BIT(0), SURVEY_INFO_IN_USE = BIT(1), SURVEY_INFO_TIME = BIT(2), SURVEY_INFO_TIME_BUSY = BIT(3), SURVEY_INFO_TIME_EXT_BUSY = BIT(4), SURVEY_INFO_TIME_RX = BIT(5), SURVEY_INFO_TIME_TX = BIT(6), SURVEY_INFO_TIME_SCAN = BIT(7), SURVEY_INFO_TIME_BSS_RX = BIT(8), }; /** * struct survey_info - channel survey response * * @channel: the channel this survey record reports, may be %NULL for a single * record to report global statistics * @filled: bitflag of flags from &enum survey_info_flags * @noise: channel noise in dBm. This and all following fields are * optional * @time: amount of time in ms the radio was turn on (on the channel) * @time_busy: amount of time the primary channel was sensed busy * @time_ext_busy: amount of time the extension channel was sensed busy * @time_rx: amount of time the radio spent receiving data * @time_tx: amount of time the radio spent transmitting data * @time_scan: amount of time the radio spent for scanning * @time_bss_rx: amount of time the radio spent receiving data on a local BSS * * Used by dump_survey() to report back per-channel survey information. * * This structure can later be expanded with things like * channel duty cycle etc. */ struct survey_info { struct ieee80211_channel *channel; u64 time; u64 time_busy; u64 time_ext_busy; u64 time_rx; u64 time_tx; u64 time_scan; u64 time_bss_rx; u32 filled; s8 noise; }; #define CFG80211_MAX_NUM_AKM_SUITES 10 /** * struct cfg80211_crypto_settings - Crypto settings * @wpa_versions: indicates which, if any, WPA versions are enabled * (from enum nl80211_wpa_versions) * @cipher_group: group key cipher suite (or 0 if unset) * @n_ciphers_pairwise: number of AP supported unicast ciphers * @ciphers_pairwise: unicast key cipher suites * @n_akm_suites: number of AKM suites * @akm_suites: AKM suites * @control_port: Whether user space controls IEEE 802.1X port, i.e., * sets/clears %NL80211_STA_FLAG_AUTHORIZED. If true, the driver is * required to assume that the port is unauthorized until authorized by * user space. Otherwise, port is marked authorized by default. * @control_port_ethertype: the control port protocol that should be * allowed through even on unauthorized ports * @control_port_no_encrypt: TRUE to prevent encryption of control port * protocol frames. * @control_port_over_nl80211: TRUE if userspace expects to exchange control * port frames over NL80211 instead of the network interface. * @control_port_no_preauth: disables pre-auth rx over the nl80211 control * port for mac80211 * @psk: PSK (for devices supporting 4-way-handshake offload) * @sae_pwd: password for SAE authentication (for devices supporting SAE * offload) * @sae_pwd_len: length of SAE password (for devices supporting SAE offload) * @sae_pwe: The mechanisms allowed for SAE PWE derivation: * * NL80211_SAE_PWE_UNSPECIFIED * Not-specified, used to indicate userspace did not specify any * preference. The driver should follow its internal policy in * such a scenario. * * NL80211_SAE_PWE_HUNT_AND_PECK * Allow hunting-and-pecking loop only * * NL80211_SAE_PWE_HASH_TO_ELEMENT * Allow hash-to-element only * * NL80211_SAE_PWE_BOTH * Allow either hunting-and-pecking loop or hash-to-element */ struct cfg80211_crypto_settings { u32 wpa_versions; u32 cipher_group; int n_ciphers_pairwise; u32 ciphers_pairwise[NL80211_MAX_NR_CIPHER_SUITES]; int n_akm_suites; u32 akm_suites[CFG80211_MAX_NUM_AKM_SUITES]; bool control_port; __be16 control_port_ethertype; bool control_port_no_encrypt; bool control_port_over_nl80211; bool control_port_no_preauth; const u8 *psk; const u8 *sae_pwd; u8 sae_pwd_len; enum nl80211_sae_pwe_mechanism sae_pwe; }; /** * struct cfg80211_mbssid_config - AP settings for multi bssid * * @tx_wdev: pointer to the transmitted interface in the MBSSID set * @tx_link_id: link ID of the transmitted profile in an MLD. * @index: index of this AP in the multi bssid group. * @ema: set to true if the beacons should be sent out in EMA mode. */ struct cfg80211_mbssid_config { struct wireless_dev *tx_wdev; u8 tx_link_id; u8 index; bool ema; }; /** * struct cfg80211_mbssid_elems - Multiple BSSID elements * * @cnt: Number of elements in array %elems. * * @elem: Array of multiple BSSID element(s) to be added into Beacon frames. * @elem.data: Data for multiple BSSID elements. * @elem.len: Length of data. */ struct cfg80211_mbssid_elems { u8 cnt; struct { const u8 *data; size_t len; } elem[] __counted_by(cnt); }; /** * struct cfg80211_rnr_elems - Reduced neighbor report (RNR) elements * * @cnt: Number of elements in array %elems. * * @elem: Array of RNR element(s) to be added into Beacon frames. * @elem.data: Data for RNR elements. * @elem.len: Length of data. */ struct cfg80211_rnr_elems { u8 cnt; struct { const u8 *data; size_t len; } elem[] __counted_by(cnt); }; /** * struct cfg80211_beacon_data - beacon data * @link_id: the link ID for the AP MLD link sending this beacon * @head: head portion of beacon (before TIM IE) * or %NULL if not changed * @tail: tail portion of beacon (after TIM IE) * or %NULL if not changed * @head_len: length of @head * @tail_len: length of @tail * @beacon_ies: extra information element(s) to add into Beacon frames or %NULL * @beacon_ies_len: length of beacon_ies in octets * @proberesp_ies: extra information element(s) to add into Probe Response * frames or %NULL * @proberesp_ies_len: length of proberesp_ies in octets * @assocresp_ies: extra information element(s) to add into (Re)Association * Response frames or %NULL * @assocresp_ies_len: length of assocresp_ies in octets * @probe_resp_len: length of probe response template (@probe_resp) * @probe_resp: probe response template (AP mode only) * @mbssid_ies: multiple BSSID elements * @rnr_ies: reduced neighbor report elements * @ftm_responder: enable FTM responder functionality; -1 for no change * (which also implies no change in LCI/civic location data) * @lci: Measurement Report element content, starting with Measurement Token * (measurement type 8) * @civicloc: Measurement Report element content, starting with Measurement * Token (measurement type 11) * @lci_len: LCI data length * @civicloc_len: Civic location data length * @he_bss_color: BSS Color settings * @he_bss_color_valid: indicates whether bss color * attribute is present in beacon data or not. */ struct cfg80211_beacon_data { unsigned int link_id; const u8 *head, *tail; const u8 *beacon_ies; const u8 *proberesp_ies; const u8 *assocresp_ies; const u8 *probe_resp; const u8 *lci; const u8 *civicloc; struct cfg80211_mbssid_elems *mbssid_ies; struct cfg80211_rnr_elems *rnr_ies; s8 ftm_responder; size_t head_len, tail_len; size_t beacon_ies_len; size_t proberesp_ies_len; size_t assocresp_ies_len; size_t probe_resp_len; size_t lci_len; size_t civicloc_len; struct cfg80211_he_bss_color he_bss_color; bool he_bss_color_valid; }; struct mac_address { u8 addr[ETH_ALEN]; }; /** * struct cfg80211_acl_data - Access control list data * * @acl_policy: ACL policy to be applied on the station's * entry specified by mac_addr * @n_acl_entries: Number of MAC address entries passed * @mac_addrs: List of MAC addresses of stations to be used for ACL */ struct cfg80211_acl_data { enum nl80211_acl_policy acl_policy; int n_acl_entries; /* Keep it last */ struct mac_address mac_addrs[] __counted_by(n_acl_entries); }; /** * struct cfg80211_fils_discovery - FILS discovery parameters from * IEEE Std 802.11ai-2016, Annex C.3 MIB detail. * * @update: Set to true if the feature configuration should be updated. * @min_interval: Minimum packet interval in TUs (0 - 10000) * @max_interval: Maximum packet interval in TUs (0 - 10000) * @tmpl_len: Template length * @tmpl: Template data for FILS discovery frame including the action * frame headers. */ struct cfg80211_fils_discovery { bool update; u32 min_interval; u32 max_interval; size_t tmpl_len; const u8 *tmpl; }; /** * struct cfg80211_unsol_bcast_probe_resp - Unsolicited broadcast probe * response parameters in 6GHz. * * @update: Set to true if the feature configuration should be updated. * @interval: Packet interval in TUs. Maximum allowed is 20 TU, as mentioned * in IEEE P802.11ax/D6.0 26.17.2.3.2 - AP behavior for fast passive * scanning * @tmpl_len: Template length * @tmpl: Template data for probe response */ struct cfg80211_unsol_bcast_probe_resp { bool update; u32 interval; size_t tmpl_len; const u8 *tmpl; }; /** * struct cfg80211_s1g_short_beacon - S1G short beacon data. * * @update: Set to true if the feature configuration should be updated. * @short_head: Short beacon head. * @short_tail: Short beacon tail. * @short_head_len: Short beacon head len. * @short_tail_len: Short beacon tail len. */ struct cfg80211_s1g_short_beacon { bool update; const u8 *short_head; const u8 *short_tail; size_t short_head_len; size_t short_tail_len; }; /** * struct cfg80211_ap_settings - AP configuration * * Used to configure an AP interface. * * @chandef: defines the channel to use * @beacon: beacon data * @beacon_interval: beacon interval * @dtim_period: DTIM period * @ssid: SSID to be used in the BSS (note: may be %NULL if not provided from * user space) * @ssid_len: length of @ssid * @hidden_ssid: whether to hide the SSID in Beacon/Probe Response frames * @crypto: crypto settings * @privacy: the BSS uses privacy * @auth_type: Authentication type (algorithm) * @inactivity_timeout: time in seconds to determine station's inactivity. * @p2p_ctwindow: P2P CT Window * @p2p_opp_ps: P2P opportunistic PS * @acl: ACL configuration used by the drivers which has support for * MAC address based access control * @pbss: If set, start as a PCP instead of AP. Relevant for DMG * networks. * @beacon_rate: bitrate to be used for beacons * @ht_cap: HT capabilities (or %NULL if HT isn't enabled) * @vht_cap: VHT capabilities (or %NULL if VHT isn't enabled) * @he_cap: HE capabilities (or %NULL if HE isn't enabled) * @eht_cap: EHT capabilities (or %NULL if EHT isn't enabled) * @eht_oper: EHT operation IE (or %NULL if EHT isn't enabled) * @uhr_oper: UHR operation (or %NULL if UHR isn't enabled) * @ht_required: stations must support HT * @vht_required: stations must support VHT * @twt_responder: Enable Target Wait Time * @he_required: stations must support HE * @sae_h2e_required: stations must support direct H2E technique in SAE * @flags: flags, as defined in &enum nl80211_ap_settings_flags * @he_obss_pd: OBSS Packet Detection settings * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters * @mbssid_config: AP settings for multiple bssid * @s1g_long_beacon_period: S1G long beacon period * @s1g_short_beacon: S1G short beacon data */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; struct cfg80211_beacon_data beacon; int beacon_interval, dtim_period; const u8 *ssid; size_t ssid_len; enum nl80211_hidden_ssid hidden_ssid; struct cfg80211_crypto_settings crypto; bool privacy; enum nl80211_auth_type auth_type; int inactivity_timeout; u8 p2p_ctwindow; bool p2p_opp_ps; const struct cfg80211_acl_data *acl; bool pbss; struct cfg80211_bitrate_mask beacon_rate; const struct ieee80211_ht_cap *ht_cap; const struct ieee80211_vht_cap *vht_cap; const struct ieee80211_he_cap_elem *he_cap; const struct ieee80211_he_operation *he_oper; const struct ieee80211_eht_cap_elem *eht_cap; const struct ieee80211_eht_operation *eht_oper; const struct ieee80211_uhr_operation *uhr_oper; bool ht_required, vht_required, he_required, sae_h2e_required; bool twt_responder; u32 flags; struct ieee80211_he_obss_pd he_obss_pd; struct cfg80211_fils_discovery fils_discovery; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; struct cfg80211_mbssid_config mbssid_config; u8 s1g_long_beacon_period; struct cfg80211_s1g_short_beacon s1g_short_beacon; }; /** * struct cfg80211_ap_update - AP configuration update * * Subset of &struct cfg80211_ap_settings, for updating a running AP. * * @beacon: beacon data * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters * @s1g_short_beacon: S1G short beacon data */ struct cfg80211_ap_update { struct cfg80211_beacon_data beacon; struct cfg80211_fils_discovery fils_discovery; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; struct cfg80211_s1g_short_beacon s1g_short_beacon; }; /** * struct cfg80211_csa_settings - channel switch settings * * Used for channel switch * * @chandef: defines the channel to use after the switch * @beacon_csa: beacon data while performing the switch * @counter_offsets_beacon: offsets of the counters within the beacon (tail) * @counter_offsets_presp: offsets of the counters within the probe response * @n_counter_offsets_beacon: number of csa counters the beacon (tail) * @n_counter_offsets_presp: number of csa counters in the probe response * @beacon_after: beacon data to be used on the new channel * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters * @radar_required: whether radar detection is required on the new channel * @block_tx: whether transmissions should be blocked while changing * @count: number of beacons until switch * @link_id: defines the link on which channel switch is expected during * MLO. 0 in case of non-MLO. */ struct cfg80211_csa_settings { struct cfg80211_chan_def chandef; struct cfg80211_beacon_data beacon_csa; const u16 *counter_offsets_beacon; const u16 *counter_offsets_presp; unsigned int n_counter_offsets_beacon; unsigned int n_counter_offsets_presp; struct cfg80211_beacon_data beacon_after; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; bool radar_required; bool block_tx; u8 count; u8 link_id; }; /** * struct cfg80211_color_change_settings - color change settings * * Used for bss color change * * @beacon_color_change: beacon data while performing the color countdown * @counter_offset_beacon: offsets of the counters within the beacon (tail) * @counter_offset_presp: offsets of the counters within the probe response * @beacon_next: beacon data to be used after the color change * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters * @count: number of beacons until the color change * @color: the color used after the change * @link_id: defines the link on which color change is expected during MLO. * 0 in case of non-MLO. */ struct cfg80211_color_change_settings { struct cfg80211_beacon_data beacon_color_change; u16 counter_offset_beacon; u16 counter_offset_presp; struct cfg80211_beacon_data beacon_next; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; u8 count; u8 color; u8 link_id; }; /** * struct iface_combination_params - input parameters for interface combinations * * Used to pass interface combination parameters * * @radio_idx: wiphy radio index or -1 for global * @num_different_channels: the number of different channels we want * to use for verification * @radar_detect: a bitmap where each bit corresponds to a channel * width where radar detection is needed, as in the definition of * &struct ieee80211_iface_combination.@radar_detect_widths * @iftype_num: array with the number of interfaces of each interface * type. The index is the interface type as specified in &enum * nl80211_iftype. * @new_beacon_int: set this to the beacon interval of a new interface * that's not operating yet, if such is to be checked as part of * the verification */ struct iface_combination_params { int radio_idx; int num_different_channels; u8 radar_detect; int iftype_num[NUM_NL80211_IFTYPES]; u32 new_beacon_int; }; /** * enum station_parameters_apply_mask - station parameter values to apply * @STATION_PARAM_APPLY_UAPSD: apply new uAPSD parameters (uapsd_queues, max_sp) * @STATION_PARAM_APPLY_CAPABILITY: apply new capability * @STATION_PARAM_APPLY_PLINK_STATE: apply new plink state * * Not all station parameters have in-band "no change" signalling, * for those that don't these flags will are used. */ enum station_parameters_apply_mask { STATION_PARAM_APPLY_UAPSD = BIT(0), STATION_PARAM_APPLY_CAPABILITY = BIT(1), STATION_PARAM_APPLY_PLINK_STATE = BIT(2), }; /** * struct sta_txpwr - station txpower configuration * * Used to configure txpower for station. * * @power: tx power (in dBm) to be used for sending data traffic. If tx power * is not provided, the default per-interface tx power setting will be * overriding. Driver should be picking up the lowest tx power, either tx * power per-interface or per-station. * @type: In particular if TPC %type is NL80211_TX_POWER_LIMITED then tx power * will be less than or equal to specified from userspace, whereas if TPC * %type is NL80211_TX_POWER_AUTOMATIC then it indicates default tx power. * NL80211_TX_POWER_FIXED is not a valid configuration option for * per peer TPC. */ struct sta_txpwr { s16 power; enum nl80211_tx_power_setting type; }; /** * struct link_station_parameters - link station parameters * * Used to change and create a new link station. * * @mld_mac: MAC address of the station * @link_id: the link id (-1 for non-MLD station) * @link_mac: MAC address of the link * @supported_rates: supported rates in IEEE 802.11 format * (or NULL for no change) * @supported_rates_len: number of supported rates * @ht_capa: HT capabilities of station * @vht_capa: VHT capabilities of station * @opmode_notif: operating mode field from Operating Mode Notification * @opmode_notif_used: information if operating mode field is used * @he_capa: HE capabilities of station * @he_capa_len: the length of the HE capabilities * @txpwr: transmit power for an associated station * @txpwr_set: txpwr field is set * @he_6ghz_capa: HE 6 GHz Band capabilities of station * @eht_capa: EHT capabilities of station * @eht_capa_len: the length of the EHT capabilities * @s1g_capa: S1G capabilities of station * @uhr_capa: UHR capabilities of the station * @uhr_capa_len: the length of the UHR capabilities */ struct link_station_parameters { const u8 *mld_mac; int link_id; const u8 *link_mac; const u8 *supported_rates; u8 supported_rates_len; const struct ieee80211_ht_cap *ht_capa; const struct ieee80211_vht_cap *vht_capa; u8 opmode_notif; bool opmode_notif_used; const struct ieee80211_he_cap_elem *he_capa; u8 he_capa_len; struct sta_txpwr txpwr; bool txpwr_set; const struct ieee80211_he_6ghz_capa *he_6ghz_capa; const struct ieee80211_eht_cap_elem *eht_capa; u8 eht_capa_len; const struct ieee80211_s1g_cap *s1g_capa; const struct ieee80211_uhr_cap *uhr_capa; u8 uhr_capa_len; }; /** * struct link_station_del_parameters - link station deletion parameters * * Used to delete a link station entry (or all stations). * * @mld_mac: MAC address of the station * @link_id: the link id */ struct link_station_del_parameters { const u8 *mld_mac; u32 link_id; }; /** * struct cfg80211_ttlm_params: TID to link mapping parameters * * Used for setting a TID to link mapping. * * @dlink: Downlink TID to link mapping, as defined in section 9.4.2.314 * (TID-To-Link Mapping element) in Draft P802.11be_D4.0. * @ulink: Uplink TID to link mapping, as defined in section 9.4.2.314 * (TID-To-Link Mapping element) in Draft P802.11be_D4.0. */ struct cfg80211_ttlm_params { u16 dlink[8]; u16 ulink[8]; }; /** * struct station_parameters - station parameters * * Used to change and create a new station. * * @vlan: vlan interface station should belong to * @sta_flags_mask: station flags that changed * (bitmask of BIT(%NL80211_STA_FLAG_...)) * @sta_flags_set: station flags values * (bitmask of BIT(%NL80211_STA_FLAG_...)) * @listen_interval: listen interval or -1 for no change * @aid: AID or zero for no change * @vlan_id: VLAN ID for station (if nonzero) * @peer_aid: mesh peer AID or zero for no change * @plink_action: plink action to take * @plink_state: set the peer link state for a station * @uapsd_queues: bitmap of queues configured for uapsd. same format * as the AC bitmap in the QoS info field * @max_sp: max Service Period. same format as the MAX_SP in the * QoS info field (but already shifted down) * @sta_modify_mask: bitmap indicating which parameters changed * (for those that don't have a natural "no change" value), * see &enum station_parameters_apply_mask * @local_pm: local link-specific mesh power save mode (no change when set * to unknown) * @capability: station capability * @ext_capab: extended capabilities of the station * @ext_capab_len: number of extended capabilities * @supported_channels: supported channels in IEEE 802.11 format * @supported_channels_len: number of supported channels * @supported_oper_classes: supported oper classes in IEEE 802.11 format * @supported_oper_classes_len: number of supported operating classes * @support_p2p_ps: information if station supports P2P PS mechanism * @airtime_weight: airtime scheduler weight for this station * @eml_cap_present: Specifies if EML capabilities field (@eml_cap) is * present/updated * @eml_cap: EML capabilities of this station * @link_sta_params: link related params. * @epp_peer: EPP peer indication * @nmi_mac: MAC address of the NMI station of the NAN peer */ struct station_parameters { struct net_device *vlan; u32 sta_flags_mask, sta_flags_set; u32 sta_modify_mask; int listen_interval; u16 aid; u16 vlan_id; u16 peer_aid; u8 plink_action; u8 plink_state; u8 uapsd_queues; u8 max_sp; enum nl80211_mesh_power_mode local_pm; u16 capability; const u8 *ext_capab; u8 ext_capab_len; const u8 *supported_channels; u8 supported_channels_len; const u8 *supported_oper_classes; u8 supported_oper_classes_len; int support_p2p_ps; u16 airtime_weight; bool eml_cap_present; u16 eml_cap; struct link_station_parameters link_sta_params; bool epp_peer; const u8 *nmi_mac; }; /** * struct station_del_parameters - station deletion parameters * * Used to delete a station entry (or all stations). * * @mac: MAC address of the station to remove or NULL to remove all stations * @subtype: Management frame subtype to use for indicating removal * (10 = Disassociation, 12 = Deauthentication) * @reason_code: Reason code for the Disassociation/Deauthentication frame * @link_id: Link ID indicating a link that stations to be flushed must be * using; valid only for MLO, but can also be -1 for MLO to really * remove all stations. */ struct station_del_parameters { const u8 *mac; u8 subtype; u16 reason_code; int link_id; }; /** * enum cfg80211_station_type - the type of station being modified * @CFG80211_STA_AP_CLIENT: client of an AP interface * @CFG80211_STA_AP_CLIENT_UNASSOC: client of an AP interface that is still * unassociated (update properties for this type of client is permitted) * @CFG80211_STA_AP_MLME_CLIENT: client of an AP interface that has * the AP MLME in the device * @CFG80211_STA_AP_STA: AP station on managed interface * @CFG80211_STA_IBSS: IBSS station * @CFG80211_STA_TDLS_PEER_SETUP: TDLS peer on managed interface (dummy entry * while TDLS setup is in progress, it moves out of this state when * being marked authorized; use this only if TDLS with external setup is * supported/used) * @CFG80211_STA_TDLS_PEER_ACTIVE: TDLS peer on managed interface (active * entry that is operating, has been marked authorized by userspace) * @CFG80211_STA_MESH_PEER_KERNEL: peer on mesh interface (kernel managed) * @CFG80211_STA_MESH_PEER_USER: peer on mesh interface (user managed) * @CFG80211_STA_NAN_MGMT: NAN management interface station * @CFG80211_STA_NAN_DATA: NAN data path station */ enum cfg80211_station_type { CFG80211_STA_AP_CLIENT, CFG80211_STA_AP_CLIENT_UNASSOC, CFG80211_STA_AP_MLME_CLIENT, CFG80211_STA_AP_STA, CFG80211_STA_IBSS, CFG80211_STA_TDLS_PEER_SETUP, CFG80211_STA_TDLS_PEER_ACTIVE, CFG80211_STA_MESH_PEER_KERNEL, CFG80211_STA_MESH_PEER_USER, CFG80211_STA_NAN_MGMT, CFG80211_STA_NAN_DATA, }; /** * cfg80211_check_station_change - validate parameter changes * @wiphy: the wiphy this operates on * @params: the new parameters for a station * @statype: the type of station being modified * * Utility function for the @change_station driver method. Call this function * with the appropriate station type looking up the station (and checking that * it exists). It will verify whether the station change is acceptable. * * Return: 0 if the change is acceptable, otherwise an error code. Note that * it may modify the parameters for backward compatibility reasons, so don't * use them before calling this. */ int cfg80211_check_station_change(struct wiphy *wiphy, struct station_parameters *params, enum cfg80211_station_type statype); /** * enum rate_info_flags - bitrate info flags * * Used by the driver to indicate the specific rate transmission * type for 802.11n transmissions. * * @RATE_INFO_FLAGS_MCS: mcs field filled with HT MCS * @RATE_INFO_FLAGS_VHT_MCS: mcs field filled with VHT MCS * @RATE_INFO_FLAGS_SHORT_GI: 400ns guard interval * @RATE_INFO_FLAGS_DMG: 60GHz MCS * @RATE_INFO_FLAGS_HE_MCS: HE MCS information * @RATE_INFO_FLAGS_EDMG: 60GHz MCS in EDMG mode * @RATE_INFO_FLAGS_EXTENDED_SC_DMG: 60GHz extended SC MCS * @RATE_INFO_FLAGS_EHT_MCS: EHT MCS information * @RATE_INFO_FLAGS_S1G_MCS: MCS field filled with S1G MCS * @RATE_INFO_FLAGS_UHR_MCS: UHR MCS information * @RATE_INFO_FLAGS_UHR_ELR_MCS: UHR ELR MCS was used * (set together with @RATE_INFO_FLAGS_UHR_MCS) * @RATE_INFO_FLAGS_UHR_IM: UHR Interference Mitigation * was used */ enum rate_info_flags { RATE_INFO_FLAGS_MCS = BIT(0), RATE_INFO_FLAGS_VHT_MCS = BIT(1), RATE_INFO_FLAGS_SHORT_GI = BIT(2), RATE_INFO_FLAGS_DMG = BIT(3), RATE_INFO_FLAGS_HE_MCS = BIT(4), RATE_INFO_FLAGS_EDMG = BIT(5), RATE_INFO_FLAGS_EXTENDED_SC_DMG = BIT(6), RATE_INFO_FLAGS_EHT_MCS = BIT(7), RATE_INFO_FLAGS_S1G_MCS = BIT(8), RATE_INFO_FLAGS_UHR_MCS = BIT(9), RATE_INFO_FLAGS_UHR_ELR_MCS = BIT(10), RATE_INFO_FLAGS_UHR_IM = BIT(11), }; /** * enum rate_info_bw - rate bandwidth information * * Used by the driver to indicate the rate bandwidth. * * @RATE_INFO_BW_5: 5 MHz bandwidth * @RATE_INFO_BW_10: 10 MHz bandwidth * @RATE_INFO_BW_20: 20 MHz bandwidth * @RATE_INFO_BW_40: 40 MHz bandwidth * @RATE_INFO_BW_80: 80 MHz bandwidth * @RATE_INFO_BW_160: 160 MHz bandwidth * @RATE_INFO_BW_HE_RU: bandwidth determined by HE RU allocation * @RATE_INFO_BW_320: 320 MHz bandwidth * @RATE_INFO_BW_EHT_RU: bandwidth determined by EHT/UHR RU allocation * @RATE_INFO_BW_1: 1 MHz bandwidth * @RATE_INFO_BW_2: 2 MHz bandwidth * @RATE_INFO_BW_4: 4 MHz bandwidth * @RATE_INFO_BW_8: 8 MHz bandwidth * @RATE_INFO_BW_16: 16 MHz bandwidth */ enum rate_info_bw { RATE_INFO_BW_20 = 0, RATE_INFO_BW_5, RATE_INFO_BW_10, RATE_INFO_BW_40, RATE_INFO_BW_80, RATE_INFO_BW_160, RATE_INFO_BW_HE_RU, RATE_INFO_BW_320, RATE_INFO_BW_EHT_RU, RATE_INFO_BW_1, RATE_INFO_BW_2, RATE_INFO_BW_4, RATE_INFO_BW_8, RATE_INFO_BW_16, }; /** * struct rate_info - bitrate information * * Information about a receiving or transmitting bitrate * * @flags: bitflag of flags from &enum rate_info_flags * @legacy: bitrate in 100kbit/s for 802.11abg * @mcs: mcs index if struct describes an HT/VHT/HE/EHT/S1G/UHR rate * @nss: number of streams (VHT & HE only) * @bw: bandwidth (from &enum rate_info_bw) * @he_gi: HE guard interval (from &enum nl80211_he_gi) * @he_dcm: HE DCM value * @he_ru_alloc: HE RU allocation (from &enum nl80211_he_ru_alloc, * only valid if bw is %RATE_INFO_BW_HE_RU) * @n_bonded_ch: In case of EDMG the number of bonded channels (1-4) * @eht_gi: EHT guard interval (from &enum nl80211_eht_gi) * @eht_ru_alloc: EHT RU allocation (from &enum nl80211_eht_ru_alloc, * only valid if bw is %RATE_INFO_BW_EHT_RU) */ struct rate_info { u16 flags; u16 legacy; u8 mcs; u8 nss; u8 bw; u8 he_gi; u8 he_dcm; u8 he_ru_alloc; u8 n_bonded_ch; u8 eht_gi; u8 eht_ru_alloc; }; /** * enum bss_param_flags - bitrate info flags * * Used by the driver to indicate the specific rate transmission * type for 802.11n transmissions. * * @BSS_PARAM_FLAGS_CTS_PROT: whether CTS protection is enabled * @BSS_PARAM_FLAGS_SHORT_PREAMBLE: whether short preamble is enabled * @BSS_PARAM_FLAGS_SHORT_SLOT_TIME: whether short slot time is enabled */ enum bss_param_flags { BSS_PARAM_FLAGS_CTS_PROT = BIT(0), BSS_PARAM_FLAGS_SHORT_PREAMBLE = BIT(1), BSS_PARAM_FLAGS_SHORT_SLOT_TIME = BIT(2), }; /** * struct sta_bss_parameters - BSS parameters for the attached station * * Information about the currently associated BSS * * @flags: bitflag of flags from &enum bss_param_flags * @dtim_period: DTIM period for the BSS * @beacon_interval: beacon interval */ struct sta_bss_parameters { u8 flags; u8 dtim_period; u16 beacon_interval; }; /** * struct cfg80211_txq_stats - TXQ statistics for this TID * @filled: bitmap of flags using the bits of &enum nl80211_txq_stats to * indicate the relevant values in this struct are filled * @backlog_bytes: total number of bytes currently backlogged * @backlog_packets: total number of packets currently backlogged * @flows: number of new flows seen * @drops: total number of packets dropped * @ecn_marks: total number of packets marked with ECN CE * @overlimit: number of drops due to queue space overflow * @overmemory: number of drops due to memory limit overflow * @collisions: number of hash collisions * @tx_bytes: total number of bytes dequeued * @tx_packets: total number of packets dequeued * @max_flows: maximum number of flows supported */ struct cfg80211_txq_stats { u32 filled; u32 backlog_bytes; u32 backlog_packets; u32 flows; u32 drops; u32 ecn_marks; u32 overlimit; u32 overmemory; u32 collisions; u32 tx_bytes; u32 tx_packets; u32 max_flows; }; /** * struct cfg80211_tid_stats - per-TID statistics * @filled: bitmap of flags using the bits of &enum nl80211_tid_stats to * indicate the relevant values in this struct are filled * @rx_msdu: number of received MSDUs * @tx_msdu: number of (attempted) transmitted MSDUs * @tx_msdu_retries: number of retries (not counting the first) for * transmitted MSDUs * @tx_msdu_failed: number of failed transmitted MSDUs * @txq_stats: TXQ statistics */ struct cfg80211_tid_stats { u32 filled; u64 rx_msdu; u64 tx_msdu; u64 tx_msdu_retries; u64 tx_msdu_failed; struct cfg80211_txq_stats txq_stats; }; #define IEEE80211_MAX_CHAINS 4 /** * struct link_station_info - link station information * * Link station information filled by driver for get_station() and * dump_station(). * @filled: bit flag of flags using the bits of &enum nl80211_sta_info to * indicate the relevant values in this struct for them * @connected_time: time(in secs) since a link of station is last connected * @inactive_time: time since last activity for link station(tx/rx) * in milliseconds * @assoc_at: bootime (ns) of the last association of link of station * @rx_bytes: bytes (size of MPDUs) received from this link of station * @tx_bytes: bytes (size of MPDUs) transmitted to this link of station * @signal: The signal strength, type depends on the wiphy's signal_type. * For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_. * @signal_avg: Average signal strength, type depends on the wiphy's * signal_type. For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_ * @chains: bitmask for filled values in @chain_signal, @chain_signal_avg * @chain_signal: per-chain signal strength of last received packet in dBm * @chain_signal_avg: per-chain signal strength average in dBm * @txrate: current unicast bitrate from this link of station * @rxrate: current unicast bitrate to this link of station * @rx_packets: packets (MSDUs & MMPDUs) received from this link of station * @tx_packets: packets (MSDUs & MMPDUs) transmitted to this link of station * @tx_retries: cumulative retry counts (MPDUs) for this link of station * @tx_failed: number of failed transmissions (MPDUs) (retries exceeded, no ACK) * @rx_dropped_misc: Dropped for un-specified reason. * @bss_param: current BSS parameters * @beacon_loss_count: Number of times beacon loss event has triggered. * @expected_throughput: expected throughput in kbps (including 802.11 headers) * towards this station. * @rx_beacon: number of beacons received from this peer * @rx_beacon_signal_avg: signal strength average (in dBm) for beacons received * from this peer * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer * @tx_duration: aggregate PPDU duration(usecs) for all the frames to a peer * @airtime_weight: current airtime scheduling weight * @pertid: per-TID statistics, see &struct cfg80211_tid_stats, using the last * (IEEE80211_NUM_TIDS) index for MSDUs not encapsulated in QoS-MPDUs. * Note that this doesn't use the @filled bit, but is used if non-NULL. * @ack_signal: signal strength (in dBm) of the last ACK frame. * @avg_ack_signal: average rssi value of ack packet for the no of msdu's has * been sent. * @rx_mpdu_count: number of MPDUs received from this station * @fcs_err_count: number of packets (MPDUs) received from this station with * an FCS error. This counter should be incremented only when TA of the * received packet with an FCS error matches the peer MAC address. * @addr: For MLO STA connection, filled with address of the link of station. */ struct link_station_info { u64 filled; u32 connected_time; u32 inactive_time; u64 assoc_at; u64 rx_bytes; u64 tx_bytes; s8 signal; s8 signal_avg; u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; s8 chain_signal_avg[IEEE80211_MAX_CHAINS]; struct rate_info txrate; struct rate_info rxrate; u32 rx_packets; u32 tx_packets; u32 tx_retries; u32 tx_failed; u32 rx_dropped_misc; struct sta_bss_parameters bss_param; u32 beacon_loss_count; u32 expected_throughput; u64 tx_duration; u64 rx_duration; u64 rx_beacon; u8 rx_beacon_signal_avg; u16 airtime_weight; s8 ack_signal; s8 avg_ack_signal; struct cfg80211_tid_stats *pertid; u32 rx_mpdu_count; u32 fcs_err_count; u8 addr[ETH_ALEN] __aligned(2); }; /** * struct station_info - station information * * Station information filled by driver for get_station() and dump_station. * * @filled: bitflag of flags using the bits of &enum nl80211_sta_info to * indicate the relevant values in this struct for them * @connected_time: time(in secs) since a station is last connected * @inactive_time: time since last station activity (tx/rx) in milliseconds * @assoc_at: bootime (ns) of the last association * @rx_bytes: bytes (size of MPDUs) received from this station * @tx_bytes: bytes (size of MPDUs) transmitted to this station * @signal: The signal strength, type depends on the wiphy's signal_type. * For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_. * @signal_avg: Average signal strength, type depends on the wiphy's signal_type. * For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_. * @chains: bitmask for filled values in @chain_signal, @chain_signal_avg * @chain_signal: per-chain signal strength of last received packet in dBm * @chain_signal_avg: per-chain signal strength average in dBm * @txrate: current unicast bitrate from this station * @rxrate: current unicast bitrate to this station * @rx_packets: packets (MSDUs & MMPDUs) received from this station * @tx_packets: packets (MSDUs & MMPDUs) transmitted to this station * @tx_retries: cumulative retry counts (MPDUs) * @tx_failed: number of failed transmissions (MPDUs) (retries exceeded, no ACK) * @rx_dropped_misc: Dropped for un-specified reason. * @bss_param: current BSS parameters * @generation: generation number for nl80211 dumps. * This number should increase every time the list of stations * changes, i.e. when a station is added or removed, so that * userspace can tell whether it got a consistent snapshot. * @beacon_loss_count: Number of times beacon loss event has triggered. * @assoc_req_ies: IEs from (Re)Association Request. * This is used only when in AP mode with drivers that do not use * user space MLME/SME implementation. The information is provided for * the cfg80211_new_sta() calls to notify user space of the IEs. * @assoc_req_ies_len: Length of assoc_req_ies buffer in octets. * @sta_flags: station flags mask & values * @t_offset: Time offset of the station relative to this host. * @llid: mesh local link id * @plid: mesh peer link id * @plink_state: mesh peer link state * @connected_to_gate: true if mesh STA has a path to mesh gate * @connected_to_as: true if mesh STA has a path to authentication server * @airtime_link_metric: mesh airtime link metric. * @local_pm: local mesh STA power save mode * @peer_pm: peer mesh STA power save mode * @nonpeer_pm: non-peer mesh STA power save mode * @expected_throughput: expected throughput in kbps (including 802.11 headers) * towards this station. * @rx_beacon: number of beacons received from this peer * @rx_beacon_signal_avg: signal strength average (in dBm) for beacons received * from this peer * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer * @tx_duration: aggregate PPDU duration(usecs) for all the frames to a peer * @airtime_weight: current airtime scheduling weight * @pertid: per-TID statistics, see &struct cfg80211_tid_stats, using the last * (IEEE80211_NUM_TIDS) index for MSDUs not encapsulated in QoS-MPDUs. * Note that this doesn't use the @filled bit, but is used if non-NULL. * @ack_signal: signal strength (in dBm) of the last ACK frame. * @avg_ack_signal: average rssi value of ack packet for the no of msdu's has * been sent. * @rx_mpdu_count: number of MPDUs received from this station * @fcs_err_count: number of packets (MPDUs) received from this station with * an FCS error. This counter should be incremented only when TA of the * received packet with an FCS error matches the peer MAC address. * @mlo_params_valid: Indicates @assoc_link_id and @mld_addr fields are filled * by driver. Drivers use this only in cfg80211_new_sta() calls when AP * MLD's MLME/SME is offload to driver. Drivers won't fill this * information in cfg80211_del_sta_sinfo(), get_station() and * dump_station() callbacks. * @assoc_link_id: Indicates MLO link ID of the AP, with which the station * completed (re)association. This information filled for both MLO * and non-MLO STA connections when the AP affiliated with an MLD. * @mld_addr: For MLO STA connection, filled with MLD address of the station. * For non-MLO STA connection, filled with all zeros. * @assoc_resp_ies: IEs from (Re)Association Response. * This is used only when in AP mode with drivers that do not use user * space MLME/SME implementation. The information is provided only for the * cfg80211_new_sta() calls to notify user space of the IEs. Drivers won't * fill this information in cfg80211_del_sta_sinfo(), get_station() and * dump_station() callbacks. User space needs this information to determine * the accepted and rejected affiliated links of the connected station. * @assoc_resp_ies_len: Length of @assoc_resp_ies buffer in octets. * @valid_links: bitmap of valid links, or 0 for non-MLO. Drivers fill this * information in cfg80211_new_sta(), cfg80211_del_sta_sinfo(), * get_station() and dump_station() callbacks. * @links: reference to Link sta entries for MLO STA, all link specific * information is accessed through links[link_id]. */ struct station_info { u64 filled; u32 connected_time; u32 inactive_time; u64 assoc_at; u64 rx_bytes; u64 tx_bytes; s8 signal; s8 signal_avg; u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; s8 chain_signal_avg[IEEE80211_MAX_CHAINS]; struct rate_info txrate; struct rate_info rxrate; u32 rx_packets; u32 tx_packets; u32 tx_retries; u32 tx_failed; u32 rx_dropped_misc; struct sta_bss_parameters bss_param; struct nl80211_sta_flag_update sta_flags; int generation; u32 beacon_loss_count; const u8 *assoc_req_ies; size_t assoc_req_ies_len; s64 t_offset; u16 llid; u16 plid; u8 plink_state; u8 connected_to_gate; u8 connected_to_as; u32 airtime_link_metric; enum nl80211_mesh_power_mode local_pm; enum nl80211_mesh_power_mode peer_pm; enum nl80211_mesh_power_mode nonpeer_pm; u32 expected_throughput; u16 airtime_weight; s8 ack_signal; s8 avg_ack_signal; struct cfg80211_tid_stats *pertid; u64 tx_duration; u64 rx_duration; u64 rx_beacon; u8 rx_beacon_signal_avg; u32 rx_mpdu_count; u32 fcs_err_count; bool mlo_params_valid; u8 assoc_link_id; u8 mld_addr[ETH_ALEN] __aligned(2); const u8 *assoc_resp_ies; size_t assoc_resp_ies_len; u16 valid_links; struct link_station_info *links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** * struct cfg80211_sar_sub_specs - sub specs limit * @power: power limitation in 0.25dbm * @freq_range_index: index the power limitation applies to */ struct cfg80211_sar_sub_specs { s32 power; u32 freq_range_index; }; /** * struct cfg80211_sar_specs - sar limit specs * @type: it's set with power in 0.25dbm or other types * @num_sub_specs: number of sar sub specs * @sub_specs: memory to hold the sar sub specs */ struct cfg80211_sar_specs { enum nl80211_sar_type type; u32 num_sub_specs; struct cfg80211_sar_sub_specs sub_specs[] __counted_by(num_sub_specs); }; /** * struct cfg80211_sar_freq_ranges - sar frequency ranges * @start_freq: start range edge frequency * @end_freq: end range edge frequency */ struct cfg80211_sar_freq_ranges { u32 start_freq; u32 end_freq; }; /** * struct cfg80211_sar_capa - sar limit capability * @type: it's set via power in 0.25dbm or other types * @num_freq_ranges: number of frequency ranges * @freq_ranges: memory to hold the freq ranges. * * Note: WLAN driver may append new ranges or split an existing * range to small ones and then append them. */ struct cfg80211_sar_capa { enum nl80211_sar_type type; u32 num_freq_ranges; const struct cfg80211_sar_freq_ranges *freq_ranges; }; #if IS_ENABLED(CONFIG_CFG80211) /** * cfg80211_get_station - retrieve information about a given station * @dev: the device where the station is supposed to be connected to * @mac_addr: the mac address of the station of interest * @sinfo: pointer to the structure to fill with the information * * Return: 0 on success and sinfo is filled with the available information * otherwise returns a negative error code and the content of sinfo has to be * considered undefined. */ int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, struct station_info *sinfo); #else static inline int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, struct station_info *sinfo) { return -ENOENT; } #endif /** * enum monitor_flags - monitor flags * * Monitor interface configuration flags. Note that these must be the bits * according to the nl80211 flags. * * @MONITOR_FLAG_CHANGED: set if the flags were changed * @MONITOR_FLAG_FCSFAIL: pass frames with bad FCS * @MONITOR_FLAG_PLCPFAIL: pass frames with bad PLCP * @MONITOR_FLAG_CONTROL: pass control frames * @MONITOR_FLAG_OTHER_BSS: disable BSSID filtering * @MONITOR_FLAG_COOK_FRAMES: deprecated, will unconditionally be refused * @MONITOR_FLAG_ACTIVE: active monitor, ACKs frames on its MAC address * @MONITOR_FLAG_SKIP_TX: do not pass locally transmitted frames */ enum monitor_flags { MONITOR_FLAG_CHANGED = BIT(__NL80211_MNTR_FLAG_INVALID), MONITOR_FLAG_FCSFAIL = BIT(NL80211_MNTR_FLAG_FCSFAIL), MONITOR_FLAG_PLCPFAIL = BIT(NL80211_MNTR_FLAG_PLCPFAIL), MONITOR_FLAG_CONTROL = BIT(NL80211_MNTR_FLAG_CONTROL), MONITOR_FLAG_OTHER_BSS = BIT(NL80211_MNTR_FLAG_OTHER_BSS), MONITOR_FLAG_COOK_FRAMES = BIT(NL80211_MNTR_FLAG_COOK_FRAMES), MONITOR_FLAG_ACTIVE = BIT(NL80211_MNTR_FLAG_ACTIVE), MONITOR_FLAG_SKIP_TX = BIT(NL80211_MNTR_FLAG_SKIP_TX), }; /** * enum mpath_info_flags - mesh path information flags * * Used by the driver to indicate which info in &struct mpath_info it has filled * in during get_station() or dump_station(). * * @MPATH_INFO_FRAME_QLEN: @frame_qlen filled * @MPATH_INFO_SN: @sn filled * @MPATH_INFO_METRIC: @metric filled * @MPATH_INFO_EXPTIME: @exptime filled * @MPATH_INFO_DISCOVERY_TIMEOUT: @discovery_timeout filled * @MPATH_INFO_DISCOVERY_RETRIES: @discovery_retries filled * @MPATH_INFO_FLAGS: @flags filled * @MPATH_INFO_HOP_COUNT: @hop_count filled * @MPATH_INFO_PATH_CHANGE: @path_change_count filled */ enum mpath_info_flags { MPATH_INFO_FRAME_QLEN = BIT(0), MPATH_INFO_SN = BIT(1), MPATH_INFO_METRIC = BIT(2), MPATH_INFO_EXPTIME = BIT(3), MPATH_INFO_DISCOVERY_TIMEOUT = BIT(4), MPATH_INFO_DISCOVERY_RETRIES = BIT(5), MPATH_INFO_FLAGS = BIT(6), MPATH_INFO_HOP_COUNT = BIT(7), MPATH_INFO_PATH_CHANGE = BIT(8), }; /** * struct mpath_info - mesh path information * * Mesh path information filled by driver for get_mpath() and dump_mpath(). * * @filled: bitfield of flags from &enum mpath_info_flags * @frame_qlen: number of queued frames for this destination * @sn: target sequence number * @metric: metric (cost) of this mesh path * @exptime: expiration time for the mesh path from now, in msecs * @flags: mesh path flags from &enum mesh_path_flags * @discovery_timeout: total mesh path discovery timeout, in msecs * @discovery_retries: mesh path discovery retries * @generation: generation number for nl80211 dumps. * This number should increase every time the list of mesh paths * changes, i.e. when a station is added or removed, so that * userspace can tell whether it got a consistent snapshot. * @hop_count: hops to destination * @path_change_count: total number of path changes to destination */ struct mpath_info { u32 filled; u32 frame_qlen; u32 sn; u32 metric; u32 exptime; u32 discovery_timeout; u8 discovery_retries; u8 flags; u8 hop_count; u32 path_change_count; int generation; }; /** * enum wiphy_bss_param_flags - bit positions for supported bss parameters. * * @WIPHY_BSS_PARAM_CTS_PROT: support changing CTS protection. * @WIPHY_BSS_PARAM_SHORT_PREAMBLE: support changing short preamble usage. * @WIPHY_BSS_PARAM_SHORT_SLOT_TIME: support changing short slot time usage. * @WIPHY_BSS_PARAM_BASIC_RATES: support reconfiguring basic rates. * @WIPHY_BSS_PARAM_AP_ISOLATE: support changing AP isolation. * @WIPHY_BSS_PARAM_HT_OPMODE: support changing HT operating mode. * @WIPHY_BSS_PARAM_P2P_CTWINDOW: support reconfiguring ctwindow. * @WIPHY_BSS_PARAM_P2P_OPPPS: support changing P2P opportunistic power-save. */ enum wiphy_bss_param_flags { WIPHY_BSS_PARAM_CTS_PROT = BIT(0), WIPHY_BSS_PARAM_SHORT_PREAMBLE = BIT(1), WIPHY_BSS_PARAM_SHORT_SLOT_TIME = BIT(2), WIPHY_BSS_PARAM_BASIC_RATES = BIT(3), WIPHY_BSS_PARAM_AP_ISOLATE = BIT(4), WIPHY_BSS_PARAM_HT_OPMODE = BIT(5), WIPHY_BSS_PARAM_P2P_CTWINDOW = BIT(6), WIPHY_BSS_PARAM_P2P_OPPPS = BIT(7), }; /** * struct bss_parameters - BSS parameters * * Used to change BSS parameters (mainly for AP mode). * * @link_id: link_id or -1 for non-MLD * @use_cts_prot: Whether to use CTS protection * (0 = no, 1 = yes, -1 = do not change) * @use_short_preamble: Whether the use of short preambles is allowed * (0 = no, 1 = yes, -1 = do not change) * @use_short_slot_time: Whether the use of short slot time is allowed * (0 = no, 1 = yes, -1 = do not change) * @basic_rates: basic rates in IEEE 802.11 format * (or NULL for no change) * @basic_rates_len: number of basic rates * @ap_isolate: do not forward packets between connected stations * (0 = no, 1 = yes, -1 = do not change) * @ht_opmode: HT Operation mode * (u16 = opmode, -1 = do not change) * @p2p_ctwindow: P2P CT Window (-1 = no change) * @p2p_opp_ps: P2P opportunistic PS (-1 = no change) */ struct bss_parameters { int link_id; int use_cts_prot; int use_short_preamble; int use_short_slot_time; const u8 *basic_rates; u8 basic_rates_len; int ap_isolate; int ht_opmode; s8 p2p_ctwindow, p2p_opp_ps; }; /** * struct mesh_config - 802.11s mesh configuration * * These parameters can be changed while the mesh is active. * * @dot11MeshRetryTimeout: the initial retry timeout in millisecond units used * by the Mesh Peering Open message * @dot11MeshConfirmTimeout: the initial retry timeout in millisecond units * used by the Mesh Peering Open message * @dot11MeshHoldingTimeout: the confirm timeout in millisecond units used by * the mesh peering management to close a mesh peering * @dot11MeshMaxPeerLinks: the maximum number of peer links allowed on this * mesh interface * @dot11MeshMaxRetries: the maximum number of peer link open retries that can * be sent to establish a new peer link instance in a mesh * @dot11MeshTTL: the value of TTL field set at a source mesh STA * @element_ttl: the value of TTL field set at a mesh STA for path selection * elements * @auto_open_plinks: whether we should automatically open peer links when we * detect compatible mesh peers * @dot11MeshNbrOffsetMaxNeighbor: the maximum number of neighbors to * synchronize to for 11s default synchronization method * @dot11MeshHWMPmaxPREQretries: the number of action frames containing a PREQ * that an originator mesh STA can send to a particular path target * @path_refresh_time: how frequently to refresh mesh paths in milliseconds * @min_discovery_timeout: the minimum length of time to wait until giving up on * a path discovery in milliseconds * @dot11MeshHWMPactivePathTimeout: the time (in TUs) for which mesh STAs * receiving a PREQ shall consider the forwarding information from the * root to be valid. (TU = time unit) * @dot11MeshHWMPpreqMinInterval: the minimum interval of time (in TUs) during * which a mesh STA can send only one action frame containing a PREQ * element * @dot11MeshHWMPperrMinInterval: the minimum interval of time (in TUs) during * which a mesh STA can send only one Action frame containing a PERR * element * @dot11MeshHWMPnetDiameterTraversalTime: the interval of time (in TUs) that * it takes for an HWMP information element to propagate across the mesh * @dot11MeshHWMPRootMode: the configuration of a mesh STA as root mesh STA * @dot11MeshHWMPRannInterval: the interval of time (in TUs) between root * announcements are transmitted * @dot11MeshGateAnnouncementProtocol: whether to advertise that this mesh * station has access to a broader network beyond the MBSS. (This is * missnamed in draft 12.0: dot11MeshGateAnnouncementProtocol set to true * only means that the station will announce others it's a mesh gate, but * not necessarily using the gate announcement protocol. Still keeping the * same nomenclature to be in sync with the spec) * @dot11MeshForwarding: whether the Mesh STA is forwarding or non-forwarding * entity (default is TRUE - forwarding entity) * @rssi_threshold: the threshold for average signal strength of candidate * station to establish a peer link * @ht_opmode: mesh HT protection mode * * @dot11MeshHWMPactivePathToRootTimeout: The time (in TUs) for which mesh STAs * receiving a proactive PREQ shall consider the forwarding information to * the root mesh STA to be valid. * * @dot11MeshHWMProotInterval: The interval of time (in TUs) between proactive * PREQs are transmitted. * @dot11MeshHWMPconfirmationInterval: The minimum interval of time (in TUs) * during which a mesh STA can send only one Action frame containing * a PREQ element for root path confirmation. * @power_mode: The default mesh power save mode which will be the initial * setting for new peer links. * @dot11MeshAwakeWindowDuration: The duration in TUs the STA will remain awake * after transmitting its beacon. * @plink_timeout: If no tx activity is seen from a STA we've established * peering with for longer than this time (in seconds), then remove it * from the STA's list of peers. Default is 30 minutes. * @dot11MeshConnectedToAuthServer: if set to true then this mesh STA * will advertise that it is connected to a authentication server * in the mesh formation field. * @dot11MeshConnectedToMeshGate: if set to true, advertise that this STA is * connected to a mesh gate in mesh formation info. If false, the * value in mesh formation is determined by the presence of root paths * in the mesh path table * @dot11MeshNolearn: Try to avoid multi-hop path discovery (e.g. PREQ/PREP * for HWMP) if the destination is a direct neighbor. Note that this might * not be the optimal decision as a multi-hop route might be better. So * if using this setting you will likely also want to disable * dot11MeshForwarding and use another mesh routing protocol on top. */ struct mesh_config { u16 dot11MeshRetryTimeout; u16 dot11MeshConfirmTimeout; u16 dot11MeshHoldingTimeout; u16 dot11MeshMaxPeerLinks; u8 dot11MeshMaxRetries; u8 dot11MeshTTL; u8 element_ttl; bool auto_open_plinks; u32 dot11MeshNbrOffsetMaxNeighbor; u8 dot11MeshHWMPmaxPREQretries; u32 path_refresh_time; u16 min_discovery_timeout; u32 dot11MeshHWMPactivePathTimeout; u16 dot11MeshHWMPpreqMinInterval; u16 dot11MeshHWMPperrMinInterval; u16 dot11MeshHWMPnetDiameterTraversalTime; u8 dot11MeshHWMPRootMode; bool dot11MeshConnectedToMeshGate; bool dot11MeshConnectedToAuthServer; u16 dot11MeshHWMPRannInterval; bool dot11MeshGateAnnouncementProtocol; bool dot11MeshForwarding; s32 rssi_threshold; u16 ht_opmode; u32 dot11MeshHWMPactivePathToRootTimeout; u16 dot11MeshHWMProotInterval; u16 dot11MeshHWMPconfirmationInterval; enum nl80211_mesh_power_mode power_mode; u16 dot11MeshAwakeWindowDuration; u32 plink_timeout; bool dot11MeshNolearn; }; /** * struct mesh_setup - 802.11s mesh setup configuration * @chandef: defines the channel to use * @mesh_id: the mesh ID * @mesh_id_len: length of the mesh ID, at least 1 and at most 32 bytes * @sync_method: which synchronization method to use * @path_sel_proto: which path selection protocol to use * @path_metric: which metric to use * @auth_id: which authentication method this mesh is using * @ie: vendor information elements (optional) * @ie_len: length of vendor information elements * @is_authenticated: this mesh requires authentication * @is_secure: this mesh uses security * @user_mpm: userspace handles all MPM functions * @dtim_period: DTIM period to use * @beacon_interval: beacon interval to use * @mcast_rate: multicast rate for Mesh Node [6Mbps is the default for 802.11a] * @basic_rates: basic rates to use when creating the mesh * @beacon_rate: bitrate to be used for beacons * @userspace_handles_dfs: whether user space controls DFS operation, i.e. * changes the channel when a radar is detected. This is required * to operate on DFS channels. * @control_port_over_nl80211: TRUE if userspace expects to exchange control * port frames over NL80211 instead of the network interface. * * These parameters are fixed when the mesh is created. */ struct mesh_setup { struct cfg80211_chan_def chandef; const u8 *mesh_id; u8 mesh_id_len; u8 sync_method; u8 path_sel_proto; u8 path_metric; u8 auth_id; const u8 *ie; u8 ie_len; bool is_authenticated; bool is_secure; bool user_mpm; u8 dtim_period; u16 beacon_interval; int mcast_rate[NUM_NL80211_BANDS]; u32 basic_rates; struct cfg80211_bitrate_mask beacon_rate; bool userspace_handles_dfs; bool control_port_over_nl80211; }; /** * struct ocb_setup - 802.11p OCB mode setup configuration * @chandef: defines the channel to use * * These parameters are fixed when connecting to the network */ struct ocb_setup { struct cfg80211_chan_def chandef; }; /** * struct ieee80211_txq_params - TX queue parameters * @ac: AC identifier * @txop: Maximum burst time in units of 32 usecs, 0 meaning disabled * @cwmin: Minimum contention window [a value of the form 2^n-1 in the range * 1..32767] * @cwmax: Maximum contention window [a value of the form 2^n-1 in the range * 1..32767] * @aifs: Arbitration interframe space [0..255] * @link_id: link_id or -1 for non-MLD */ struct ieee80211_txq_params { enum nl80211_ac ac; u16 txop; u16 cwmin; u16 cwmax; u8 aifs; int link_id; }; /** * DOC: Scanning and BSS list handling * * The scanning process itself is fairly simple, but cfg80211 offers quite * a bit of helper functionality. To start a scan, the scan operation will * be invoked with a scan definition. This scan definition contains the * channels to scan, and the SSIDs to send probe requests for (including the * wildcard, if desired). A passive scan is indicated by having no SSIDs to * probe. Additionally, a scan request may contain extra information elements * that should be added to the probe request. The IEs are guaranteed to be * well-formed, and will not exceed the maximum length the driver advertised * in the wiphy structure. * * When scanning finds a BSS, cfg80211 needs to be notified of that, because * it is responsible for maintaining the BSS list; the driver should not * maintain a list itself. For this notification, various functions exist. * * Since drivers do not maintain a BSS list, there are also a number of * functions to search for a BSS and obtain information about it from the * BSS structure cfg80211 maintains. The BSS list is also made available * to userspace. */ /** * struct cfg80211_ssid - SSID description * @ssid: the SSID * @ssid_len: length of the ssid */ struct cfg80211_ssid { u8 ssid[IEEE80211_MAX_SSID_LEN]; u8 ssid_len; }; /** * struct cfg80211_scan_info - information about completed scan * @scan_start_tsf: scan start time in terms of the TSF of the BSS that the * wireless device that requested the scan is connected to. If this * information is not available, this field is left zero. * @tsf_bssid: the BSSID according to which %scan_start_tsf is set. * @aborted: set to true if the scan was aborted for any reason, * userspace will be notified of that */ struct cfg80211_scan_info { u64 scan_start_tsf; u8 tsf_bssid[ETH_ALEN] __aligned(2); bool aborted; }; /** * struct cfg80211_scan_6ghz_params - relevant for 6 GHz only * * @short_ssid: short ssid to scan for * @bssid: bssid to scan for * @channel_idx: idx of the channel in the channel array in the scan request * which the above info is relevant to * @unsolicited_probe: the AP transmits unsolicited probe response every 20 TU * @short_ssid_valid: @short_ssid is valid and can be used * @psc_no_listen: when set, and the channel is a PSC channel, no need to wait * 20 TUs before starting to send probe requests. * @psd_20: The AP's 20 MHz PSD value. */ struct cfg80211_scan_6ghz_params { u32 short_ssid; u32 channel_idx; u8 bssid[ETH_ALEN]; bool unsolicited_probe; bool short_ssid_valid; bool psc_no_listen; s8 psd_20; }; /** * struct cfg80211_scan_request - scan request description * * @ssids: SSIDs to scan for (active scan only) * @n_ssids: number of SSIDs * @channels: channels to scan on. * @n_channels: total number of channels to scan * @ie: optional information element(s) to add into Probe Request or %NULL * @ie_len: length of ie in octets * @duration: how long to listen on each channel, in TUs. If * %duration_mandatory is not set, this is the maximum dwell time and * the actual dwell time may be shorter. * @duration_mandatory: if set, the scan duration must be as specified by the * %duration field. * @flags: control flags from &enum nl80211_scan_flags * @rates: bitmap of rates to advertise for each band * @wiphy: the wiphy this was for * @scan_start: time (in jiffies) when the scan started * @wdev: the wireless device to scan for * @no_cck: used to send probe requests at non CCK rate in 2GHz band * @mac_addr: MAC address used with randomisation * @mac_addr_mask: MAC address mask used with randomisation, bits that * are 0 in the mask should be randomised, bits that are 1 should * be taken from the @mac_addr * @scan_6ghz: relevant for split scan request only, * true if this is a 6 GHz scan request * @first_part: %true if this is the first part of a split scan request or a * scan that was not split. May be %true for a @scan_6ghz scan if no other * channels were requested * @n_6ghz_params: number of 6 GHz params * @scan_6ghz_params: 6 GHz params * @bssid: BSSID to scan for (most commonly, the wildcard BSSID) * @tsf_report_link_id: for MLO, indicates the link ID of the BSS that should be * used for TSF reporting. Can be set to -1 to indicate no preference. */ struct cfg80211_scan_request { struct cfg80211_ssid *ssids; int n_ssids; u32 n_channels; const u8 *ie; size_t ie_len; u16 duration; bool duration_mandatory; u32 flags; u32 rates[NUM_NL80211_BANDS]; struct wireless_dev *wdev; u8 mac_addr[ETH_ALEN] __aligned(2); u8 mac_addr_mask[ETH_ALEN] __aligned(2); u8 bssid[ETH_ALEN] __aligned(2); struct wiphy *wiphy; unsigned long scan_start; bool no_cck; bool scan_6ghz; bool first_part; u32 n_6ghz_params; struct cfg80211_scan_6ghz_params *scan_6ghz_params; s8 tsf_report_link_id; /* keep last */ struct ieee80211_channel *channels[]; }; static inline void get_random_mask_addr(u8 *buf, const u8 *addr, const u8 *mask) { int i; get_random_bytes(buf, ETH_ALEN); for (i = 0; i < ETH_ALEN; i++) { buf[i] &= ~mask[i]; buf[i] |= addr[i] & mask[i]; } } /** * struct cfg80211_match_set - sets of attributes to match * * @ssid: SSID to be matched; may be zero-length in case of BSSID match * or no match (RSSI only) * @bssid: BSSID to be matched; may be all-zero BSSID in case of SSID match * or no match (RSSI only) * @rssi_thold: don't report scan results below this threshold (in s32 dBm) */ struct cfg80211_match_set { struct cfg80211_ssid ssid; u8 bssid[ETH_ALEN]; s32 rssi_thold; }; /** * struct cfg80211_sched_scan_plan - scan plan for scheduled scan * * @interval: interval between scheduled scan iterations. In seconds. * @iterations: number of scan iterations in this scan plan. Zero means * infinite loop. * The last scan plan will always have this parameter set to zero, * all other scan plans will have a finite number of iterations. */ struct cfg80211_sched_scan_plan { u32 interval; u32 iterations; }; /** * struct cfg80211_bss_select_adjust - BSS selection with RSSI adjustment. * * @band: band of BSS which should match for RSSI level adjustment. * @delta: value of RSSI level adjustment. */ struct cfg80211_bss_select_adjust { enum nl80211_band band; s8 delta; }; /** * struct cfg80211_sched_scan_request - scheduled scan request description * * @reqid: identifies this request. * @ssids: SSIDs to scan for (passed in the probe_reqs in active scans) * @n_ssids: number of SSIDs * @n_channels: total number of channels to scan * @ie: optional information element(s) to add into Probe Request or %NULL * @ie_len: length of ie in octets * @flags: control flags from &enum nl80211_scan_flags * @match_sets: sets of parameters to be matched for a scan result * entry to be considered valid and to be passed to the host * (others are filtered out). * If omitted, all results are passed. * @n_match_sets: number of match sets * @report_results: indicates that results were reported for this request * @wiphy: the wiphy this was for * @dev: the interface * @scan_start: start time of the scheduled scan * @channels: channels to scan * @min_rssi_thold: for drivers only supporting a single threshold, this * contains the minimum over all matchsets * @mac_addr: MAC address used with randomisation * @mac_addr_mask: MAC address mask used with randomisation, bits that * are 0 in the mask should be randomised, bits that are 1 should * be taken from the @mac_addr * @scan_plans: scan plans to be executed in this scheduled scan. Lowest * index must be executed first. * @n_scan_plans: number of scan plans, at least 1. * @rcu_head: RCU callback used to free the struct * @owner_nlportid: netlink portid of owner (if this should is a request * owned by a particular socket) * @nl_owner_dead: netlink owner socket was closed - this request be freed * @list: for keeping list of requests. * @delay: delay in seconds to use before starting the first scan * cycle. The driver may ignore this parameter and start * immediately (or at any other time), if this feature is not * supported. * @relative_rssi_set: Indicates whether @relative_rssi is set or not. * @relative_rssi: Relative RSSI threshold in dB to restrict scan result * reporting in connected state to cases where a matching BSS is determined * to have better or slightly worse RSSI than the current connected BSS. * The relative RSSI threshold values are ignored in disconnected state. * @rssi_adjust: delta dB of RSSI preference to be given to the BSSs that belong * to the specified band while deciding whether a better BSS is reported * using @relative_rssi. If delta is a negative number, the BSSs that * belong to the specified band will be penalized by delta dB in relative * comparisons. */ struct cfg80211_sched_scan_request { u64 reqid; struct cfg80211_ssid *ssids; int n_ssids; u32 n_channels; const u8 *ie; size_t ie_len; u32 flags; struct cfg80211_match_set *match_sets; int n_match_sets; s32 min_rssi_thold; u32 delay; struct cfg80211_sched_scan_plan *scan_plans; int n_scan_plans; u8 mac_addr[ETH_ALEN] __aligned(2); u8 mac_addr_mask[ETH_ALEN] __aligned(2); bool relative_rssi_set; s8 relative_rssi; struct cfg80211_bss_select_adjust rssi_adjust; /* internal */ struct wiphy *wiphy; struct net_device *dev; unsigned long scan_start; bool report_results; struct rcu_head rcu_head; u32 owner_nlportid; bool nl_owner_dead; struct list_head list; /* keep last */ struct ieee80211_channel *channels[] __counted_by(n_channels); }; /** * enum cfg80211_signal_type - signal type * * @CFG80211_SIGNAL_TYPE_NONE: no signal strength information available * @CFG80211_SIGNAL_TYPE_MBM: signal strength in mBm (100*dBm) * @CFG80211_SIGNAL_TYPE_UNSPEC: signal strength, increasing from 0 through 100 */ enum cfg80211_signal_type { CFG80211_SIGNAL_TYPE_NONE, CFG80211_SIGNAL_TYPE_MBM, CFG80211_SIGNAL_TYPE_UNSPEC, }; /** * struct cfg80211_inform_bss - BSS inform data * @chan: channel the frame was received on * @signal: signal strength value, according to the wiphy's * signal type * @boottime_ns: timestamp (CLOCK_BOOTTIME) when the information was * received; should match the time when the frame was actually * received by the device (not just by the host, in case it was * buffered on the device) and be accurate to about 10ms. * If the frame isn't buffered, just passing the return value of * ktime_get_boottime_ns() is likely appropriate. * @parent_tsf: the time at the start of reception of the first octet of the * timestamp field of the frame. The time is the TSF of the BSS specified * by %parent_bssid. * @parent_bssid: the BSS according to which %parent_tsf is set. This is set to * the BSS that requested the scan in which the beacon/probe was received. * @chains: bitmask for filled values in @chain_signal. * @chain_signal: per-chain signal strength of last received BSS in dBm. * @restrict_use: restrict usage, if not set, assume @use_for is * %NL80211_BSS_USE_FOR_NORMAL. * @use_for: bitmap of possible usage for this BSS, see * &enum nl80211_bss_use_for * @cannot_use_reasons: the reasons (bitmap) for not being able to connect, * if @restrict_use is set and @use_for is zero (empty); may be 0 for * unspecified reasons; see &enum nl80211_bss_cannot_use_reasons * @drv_data: Data to be passed through to @inform_bss */ struct cfg80211_inform_bss { struct ieee80211_channel *chan; s32 signal; u64 boottime_ns; u64 parent_tsf; u8 parent_bssid[ETH_ALEN] __aligned(2); u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; u8 restrict_use:1, use_for:7; u8 cannot_use_reasons; void *drv_data; }; /** * struct cfg80211_bss_ies - BSS entry IE data * @tsf: TSF contained in the frame that carried these IEs * @rcu_head: internal use, for freeing * @len: length of the IEs * @from_beacon: these IEs are known to come from a beacon * @data: IE data */ struct cfg80211_bss_ies { u64 tsf; struct rcu_head rcu_head; int len; bool from_beacon; u8 data[]; }; /** * struct cfg80211_bss - BSS description * * This structure describes a BSS (which may also be a mesh network) * for use in scan results and similar. * * @channel: channel this BSS is on * @bssid: BSSID of the BSS * @beacon_interval: the beacon interval as from the frame * @capability: the capability field in host byte order * @ies: the information elements (Note that there is no guarantee that these * are well-formed!); this is a pointer to either the beacon_ies or * proberesp_ies depending on whether Probe Response frame has been * received. It is always non-%NULL. * @beacon_ies: the information elements from the last Beacon frame * (implementation note: if @hidden_beacon_bss is set this struct doesn't * own the beacon_ies, but they're just pointers to the ones from the * @hidden_beacon_bss struct) * @proberesp_ies: the information elements from the last Probe Response frame * @proberesp_ecsa_stuck: ECSA element is stuck in the Probe Response frame, * cannot rely on it having valid data * @hidden_beacon_bss: in case this BSS struct represents a probe response from * a BSS that hides the SSID in its beacon, this points to the BSS struct * that holds the beacon data. @beacon_ies is still valid, of course, and * points to the same data as hidden_beacon_bss->beacon_ies in that case. * @transmitted_bss: pointer to the transmitted BSS, if this is a * non-transmitted one (multi-BSSID support) * @nontrans_list: list of non-transmitted BSS, if this is a transmitted one * (multi-BSSID support) * @signal: signal strength value (type depends on the wiphy's signal_type) * @ts_boottime: timestamp of the last BSS update in nanoseconds since boot * @chains: bitmask for filled values in @chain_signal. * @chain_signal: per-chain signal strength of last received BSS in dBm. * @bssid_index: index in the multiple BSS set * @max_bssid_indicator: max number of members in the BSS set * @use_for: bitmap of possible usage for this BSS, see * &enum nl80211_bss_use_for * @cannot_use_reasons: the reasons (bitmap) for not being able to connect, * if @restrict_use is set and @use_for is zero (empty); may be 0 for * unspecified reasons; see &enum nl80211_bss_cannot_use_reasons * @priv: private area for driver use, has at least wiphy->bss_priv_size bytes */ struct cfg80211_bss { struct ieee80211_channel *channel; const struct cfg80211_bss_ies __rcu *ies; const struct cfg80211_bss_ies __rcu *beacon_ies; const struct cfg80211_bss_ies __rcu *proberesp_ies; struct cfg80211_bss *hidden_beacon_bss; struct cfg80211_bss *transmitted_bss; struct list_head nontrans_list; s32 signal; u64 ts_boottime; u16 beacon_interval; u16 capability; u8 bssid[ETH_ALEN]; u8 chains; s8 chain_signal[IEEE80211_MAX_CHAINS]; u8 proberesp_ecsa_stuck:1; u8 bssid_index; u8 max_bssid_indicator; u8 use_for; u8 cannot_use_reasons; u8 priv[] __aligned(sizeof(void *)); }; /** * ieee80211_bss_get_elem - find element with given ID * @bss: the bss to search * @id: the element ID * * Note that the return value is an RCU-protected pointer, so * rcu_read_lock() must be held when calling this function. * Return: %NULL if not found. */ const struct element *ieee80211_bss_get_elem(struct cfg80211_bss *bss, u8 id); /** * ieee80211_bss_get_ie - find IE with given ID * @bss: the bss to search * @id: the element ID * * Note that the return value is an RCU-protected pointer, so * rcu_read_lock() must be held when calling this function. * Return: %NULL if not found. */ static inline const u8 *ieee80211_bss_get_ie(struct cfg80211_bss *bss, u8 id) { return (const void *)ieee80211_bss_get_elem(bss, id); } /** * struct cfg80211_auth_request - Authentication request data * * This structure provides information needed to complete IEEE 802.11 * authentication. * * @bss: The BSS to authenticate with, the callee must obtain a reference * to it if it needs to keep it. * @supported_selectors: List of selectors that should be assumed to be * supported by the station. * SAE_H2E must be assumed supported if set to %NULL. * @supported_selectors_len: Length of supported_selectors in octets. * @auth_type: Authentication type (algorithm) * @ie: Extra IEs to add to Authentication frame or %NULL * @ie_len: Length of ie buffer in octets * @key_len: length of WEP key for shared key authentication * @key_idx: index of WEP key for shared key authentication * @key: WEP key for shared key authentication * @auth_data: Fields and elements in Authentication frames. This contains * the authentication frame body (non-IE and IE data), excluding the * Authentication algorithm number, i.e., starting at the Authentication * transaction sequence number field. * @auth_data_len: Length of auth_data buffer in octets * @link_id: if >= 0, indicates authentication should be done as an MLD, * the interface address is included as the MLD address and the * necessary link (with the given link_id) will be created (and * given an MLD address) by the driver * @ap_mld_addr: AP MLD address in case of authentication request with * an AP MLD, valid iff @link_id >= 0 */ struct cfg80211_auth_request { struct cfg80211_bss *bss; const u8 *ie; size_t ie_len; const u8 *supported_selectors; u8 supported_selectors_len; enum nl80211_auth_type auth_type; const u8 *key; u8 key_len; s8 key_idx; const u8 *auth_data; size_t auth_data_len; s8 link_id; const u8 *ap_mld_addr; }; /** * struct cfg80211_assoc_link - per-link information for MLO association * @bss: the BSS pointer, see also &struct cfg80211_assoc_request::bss; * if this is %NULL for a link, that link is not requested * @elems: extra elements for the per-STA profile for this link * @elems_len: length of the elements * @error: per-link error code, must be <= 0. If there is an error, then the * operation as a whole must fail. */ struct cfg80211_assoc_link { struct cfg80211_bss *bss; const u8 *elems; size_t elems_len; int error; }; /** * struct cfg80211_ml_reconf_req - MLO link reconfiguration request * @add_links: data for links to add, see &struct cfg80211_assoc_link * @rem_links: bitmap of links to remove * @ext_mld_capa_ops: extended MLD capabilities and operations set by * userspace for the ML reconfiguration action frame */ struct cfg80211_ml_reconf_req { struct cfg80211_assoc_link add_links[IEEE80211_MLD_MAX_NUM_LINKS]; u16 rem_links; u16 ext_mld_capa_ops; }; /** * enum cfg80211_assoc_req_flags - Over-ride default behaviour in association. * * @ASSOC_REQ_DISABLE_HT: Disable HT (802.11n) * @ASSOC_REQ_DISABLE_VHT: Disable VHT * @ASSOC_REQ_USE_RRM: Declare RRM capability in this association * @CONNECT_REQ_EXTERNAL_AUTH_SUPPORT: User space indicates external * authentication capability. Drivers can offload authentication to * userspace if this flag is set. Only applicable for cfg80211_connect() * request (connect callback). * @ASSOC_REQ_DISABLE_HE: Disable HE * @ASSOC_REQ_DISABLE_EHT: Disable EHT * @CONNECT_REQ_MLO_SUPPORT: Userspace indicates support for handling MLD links. * Drivers shall disable MLO features for the current association if this * flag is not set. * @ASSOC_REQ_SPP_AMSDU: SPP A-MSDUs will be used on this connection (if any) * @ASSOC_REQ_DISABLE_UHR: Disable UHR */ enum cfg80211_assoc_req_flags { ASSOC_REQ_DISABLE_HT = BIT(0), ASSOC_REQ_DISABLE_VHT = BIT(1), ASSOC_REQ_USE_RRM = BIT(2), CONNECT_REQ_EXTERNAL_AUTH_SUPPORT = BIT(3), ASSOC_REQ_DISABLE_HE = BIT(4), ASSOC_REQ_DISABLE_EHT = BIT(5), CONNECT_REQ_MLO_SUPPORT = BIT(6), ASSOC_REQ_SPP_AMSDU = BIT(7), ASSOC_REQ_DISABLE_UHR = BIT(8), }; /** * struct cfg80211_assoc_request - (Re)Association request data * * This structure provides information needed to complete IEEE 802.11 * (re)association. * @bss: The BSS to associate with. If the call is successful the driver is * given a reference that it must give back to cfg80211_send_rx_assoc() * or to cfg80211_assoc_timeout(). To ensure proper refcounting, new * association requests while already associating must be rejected. * This also applies to the @links.bss parameter, which is used instead * of this one (it is %NULL) for MLO associations. * @ie: Extra IEs to add to (Re)Association Request frame or %NULL * @ie_len: Length of ie buffer in octets * @use_mfp: Use management frame protection (IEEE 802.11w) in this association * @crypto: crypto settings * @prev_bssid: previous BSSID, if not %NULL use reassociate frame. This is used * to indicate a request to reassociate within the ESS instead of a request * do the initial association with the ESS. When included, this is set to * the BSSID of the current association, i.e., to the value that is * included in the Current AP address field of the Reassociation Request * frame. * @flags: See &enum cfg80211_assoc_req_flags * @supported_selectors: supported BSS selectors in IEEE 802.11 format * (or %NULL for no change). * If %NULL, then support for SAE_H2E should be assumed. * @supported_selectors_len: number of supported BSS selectors * @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask * will be used in ht_capa. Un-supported values will be ignored. * @ht_capa_mask: The bits of ht_capa which are to be used. * @vht_capa: VHT capability override * @vht_capa_mask: VHT capability mask indicating which fields to use * @fils_kek: FILS KEK for protecting (Re)Association Request/Response frame or * %NULL if FILS is not used. * @fils_kek_len: Length of fils_kek in octets * @fils_nonces: FILS nonces (part of AAD) for protecting (Re)Association * Request/Response frame or %NULL if FILS is not used. This field starts * with 16 octets of STA Nonce followed by 16 octets of AP Nonce. * @s1g_capa: S1G capability override * @s1g_capa_mask: S1G capability override mask * @links: per-link information for MLO connections * @link_id: >= 0 for MLO connections, where links are given, and indicates * the link on which the association request should be sent * @ap_mld_addr: AP MLD address in case of MLO association request, * valid iff @link_id >= 0 * @ext_mld_capa_ops: extended MLD capabilities and operations set by * userspace for the association */ struct cfg80211_assoc_request { struct cfg80211_bss *bss; const u8 *ie, *prev_bssid; size_t ie_len; struct cfg80211_crypto_settings crypto; bool use_mfp; u32 flags; const u8 *supported_selectors; u8 supported_selectors_len; struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; struct ieee80211_vht_cap vht_capa, vht_capa_mask; const u8 *fils_kek; size_t fils_kek_len; const u8 *fils_nonces; struct ieee80211_s1g_cap s1g_capa, s1g_capa_mask; struct cfg80211_assoc_link links[IEEE80211_MLD_MAX_NUM_LINKS]; const u8 *ap_mld_addr; s8 link_id; u16 ext_mld_capa_ops; }; /** * struct cfg80211_deauth_request - Deauthentication request data * * This structure provides information needed to complete IEEE 802.11 * deauthentication. * * @bssid: the BSSID or AP MLD address to deauthenticate from * @ie: Extra IEs to add to Deauthentication frame or %NULL * @ie_len: Length of ie buffer in octets * @reason_code: The reason code for the deauthentication * @local_state_change: if set, change local state only and * do not set a deauth frame */ struct cfg80211_deauth_request { const u8 *bssid; const u8 *ie; size_t ie_len; u16 reason_code; bool local_state_change; }; /** * struct cfg80211_disassoc_request - Disassociation request data * * This structure provides information needed to complete IEEE 802.11 * disassociation. * * @ap_addr: the BSSID or AP MLD address to disassociate from * @ie: Extra IEs to add to Disassociation frame or %NULL * @ie_len: Length of ie buffer in octets * @reason_code: The reason code for the disassociation * @local_state_change: This is a request for a local state only, i.e., no * Disassociation frame is to be transmitted. */ struct cfg80211_disassoc_request { const u8 *ap_addr; const u8 *ie; size_t ie_len; u16 reason_code; bool local_state_change; }; /** * struct cfg80211_ibss_params - IBSS parameters * * This structure defines the IBSS parameters for the join_ibss() * method. * * @ssid: The SSID, will always be non-null. * @ssid_len: The length of the SSID, will always be non-zero. * @bssid: Fixed BSSID requested, maybe be %NULL, if set do not * search for IBSSs with a different BSSID. * @chandef: defines the channel to use if no other IBSS to join can be found * @channel_fixed: The channel should be fixed -- do not search for * IBSSs to join on other channels. * @ie: information element(s) to include in the beacon * @ie_len: length of that * @beacon_interval: beacon interval to use * @privacy: this is a protected network, keys will be configured * after joining * @control_port: whether user space controls IEEE 802.1X port, i.e., * sets/clears %NL80211_STA_FLAG_AUTHORIZED. If true, the driver is * required to assume that the port is unauthorized until authorized by * user space. Otherwise, port is marked authorized by default. * @control_port_over_nl80211: TRUE if userspace expects to exchange control * port frames over NL80211 instead of the network interface. * @userspace_handles_dfs: whether user space controls DFS operation, i.e. * changes the channel when a radar is detected. This is required * to operate on DFS channels. * @basic_rates: bitmap of basic rates to use when creating the IBSS * @mcast_rate: per-band multicast rate index + 1 (0: disabled) * @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask * will be used in ht_capa. Un-supported values will be ignored. * @ht_capa_mask: The bits of ht_capa which are to be used. * @wep_keys: static WEP keys, if not NULL points to an array of * CFG80211_MAX_WEP_KEYS WEP keys * @wep_tx_key: key index (0..3) of the default TX static WEP key */ struct cfg80211_ibss_params { const u8 *ssid; const u8 *bssid; struct cfg80211_chan_def chandef; const u8 *ie; u8 ssid_len, ie_len; u16 beacon_interval; u32 basic_rates; bool channel_fixed; bool privacy; bool control_port; bool control_port_over_nl80211; bool userspace_handles_dfs; int mcast_rate[NUM_NL80211_BANDS]; struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; struct key_params *wep_keys; int wep_tx_key; }; /** * struct cfg80211_bss_selection - connection parameters for BSS selection. * * @behaviour: requested BSS selection behaviour. * @param: parameters for requestion behaviour. * @param.band_pref: preferred band for %NL80211_BSS_SELECT_ATTR_BAND_PREF. * @param.adjust: parameters for %NL80211_BSS_SELECT_ATTR_RSSI_ADJUST. */ struct cfg80211_bss_selection { enum nl80211_bss_select_attr behaviour; union { enum nl80211_band band_pref; struct cfg80211_bss_select_adjust adjust; } param; }; /** * struct cfg80211_connect_params - Connection parameters * * This structure provides information needed to complete IEEE 802.11 * authentication and association. * * @channel: The channel to use or %NULL if not specified (auto-select based * on scan results) * @channel_hint: The channel of the recommended BSS for initial connection or * %NULL if not specified * @bssid: The AP BSSID or %NULL if not specified (auto-select based on scan * results) * @bssid_hint: The recommended AP BSSID for initial connection to the BSS or * %NULL if not specified. Unlike the @bssid parameter, the driver is * allowed to ignore this @bssid_hint if it has knowledge of a better BSS * to use. * @ssid: SSID * @ssid_len: Length of ssid in octets * @auth_type: Authentication type (algorithm) * @ie: IEs for association request * @ie_len: Length of assoc_ie in octets * @privacy: indicates whether privacy-enabled APs should be used * @mfp: indicate whether management frame protection is used * @crypto: crypto settings * @key_len: length of WEP key for shared key authentication * @key_idx: index of WEP key for shared key authentication * @key: WEP key for shared key authentication * @flags: See &enum cfg80211_assoc_req_flags * @bg_scan_period: Background scan period in seconds * or -1 to indicate that default value is to be used. * @ht_capa: HT Capabilities over-rides. Values set in ht_capa_mask * will be used in ht_capa. Un-supported values will be ignored. * @ht_capa_mask: The bits of ht_capa which are to be used. * @vht_capa: VHT Capability overrides * @vht_capa_mask: The bits of vht_capa which are to be used. * @pbss: if set, connect to a PCP instead of AP. Valid for DMG * networks. * @bss_select: criteria to be used for BSS selection. * @prev_bssid: previous BSSID, if not %NULL use reassociate frame. This is used * to indicate a request to reassociate within the ESS instead of a request * do the initial association with the ESS. When included, this is set to * the BSSID of the current association, i.e., to the value that is * included in the Current AP address field of the Reassociation Request * frame. * @fils_erp_username: EAP re-authentication protocol (ERP) username part of the * NAI or %NULL if not specified. This is used to construct FILS wrapped * data IE. * @fils_erp_username_len: Length of @fils_erp_username in octets. * @fils_erp_realm: EAP re-authentication protocol (ERP) realm part of NAI or * %NULL if not specified. This specifies the domain name of ER server and * is used to construct FILS wrapped data IE. * @fils_erp_realm_len: Length of @fils_erp_realm in octets. * @fils_erp_next_seq_num: The next sequence number to use in the FILS ERP * messages. This is also used to construct FILS wrapped data IE. * @fils_erp_rrk: ERP re-authentication Root Key (rRK) used to derive additional * keys in FILS or %NULL if not specified. * @fils_erp_rrk_len: Length of @fils_erp_rrk in octets. * @want_1x: indicates user-space supports and wants to use 802.1X driver * offload of 4-way handshake. * @edmg: define the EDMG channels. * This may specify multiple channels and bonding options for the driver * to choose from, based on BSS configuration. */ struct cfg80211_connect_params { struct ieee80211_channel *channel; struct ieee80211_channel *channel_hint; const u8 *bssid; const u8 *bssid_hint; const u8 *ssid; size_t ssid_len; enum nl80211_auth_type auth_type; const u8 *ie; size_t ie_len; bool privacy; enum nl80211_mfp mfp; struct cfg80211_crypto_settings crypto; const u8 *key; u8 key_len, key_idx; u32 flags; int bg_scan_period; struct ieee80211_ht_cap ht_capa; struct ieee80211_ht_cap ht_capa_mask; struct ieee80211_vht_cap vht_capa; struct ieee80211_vht_cap vht_capa_mask; bool pbss; struct cfg80211_bss_selection bss_select; const u8 *prev_bssid; const u8 *fils_erp_username; size_t fils_erp_username_len; const u8 *fils_erp_realm; size_t fils_erp_realm_len; u16 fils_erp_next_seq_num; const u8 *fils_erp_rrk; size_t fils_erp_rrk_len; bool want_1x; struct ieee80211_edmg edmg; }; /** * enum cfg80211_connect_params_changed - Connection parameters being updated * * This enum provides information of all connect parameters that * have to be updated as part of update_connect_params() call. * * @UPDATE_ASSOC_IES: Indicates whether association request IEs are updated * @UPDATE_FILS_ERP_INFO: Indicates that FILS connection parameters (realm, * username, erp sequence number and rrk) are updated * @UPDATE_AUTH_TYPE: Indicates that authentication type is updated */ enum cfg80211_connect_params_changed { UPDATE_ASSOC_IES = BIT(0), UPDATE_FILS_ERP_INFO = BIT(1), UPDATE_AUTH_TYPE = BIT(2), }; /** * enum wiphy_params_flags - set_wiphy_params bitfield values * @WIPHY_PARAM_RETRY_SHORT: wiphy->retry_short has changed * @WIPHY_PARAM_RETRY_LONG: wiphy->retry_long has changed * @WIPHY_PARAM_FRAG_THRESHOLD: wiphy->frag_threshold has changed * @WIPHY_PARAM_RTS_THRESHOLD: wiphy->rts_threshold has changed * @WIPHY_PARAM_COVERAGE_CLASS: coverage class changed * @WIPHY_PARAM_DYN_ACK: dynack has been enabled * @WIPHY_PARAM_TXQ_LIMIT: TXQ packet limit has been changed * @WIPHY_PARAM_TXQ_MEMORY_LIMIT: TXQ memory limit has been changed * @WIPHY_PARAM_TXQ_QUANTUM: TXQ scheduler quantum */ enum wiphy_params_flags { WIPHY_PARAM_RETRY_SHORT = BIT(0), WIPHY_PARAM_RETRY_LONG = BIT(1), WIPHY_PARAM_FRAG_THRESHOLD = BIT(2), WIPHY_PARAM_RTS_THRESHOLD = BIT(3), WIPHY_PARAM_COVERAGE_CLASS = BIT(4), WIPHY_PARAM_DYN_ACK = BIT(5), WIPHY_PARAM_TXQ_LIMIT = BIT(6), WIPHY_PARAM_TXQ_MEMORY_LIMIT = BIT(7), WIPHY_PARAM_TXQ_QUANTUM = BIT(8), }; #define IEEE80211_DEFAULT_AIRTIME_WEIGHT 256 /* The per TXQ device queue limit in airtime */ #define IEEE80211_DEFAULT_AQL_TXQ_LIMIT_L 5000 #define IEEE80211_DEFAULT_AQL_TXQ_LIMIT_H 12000 /* The per interface airtime threshold to switch to lower queue limit */ #define IEEE80211_AQL_THRESHOLD 24000 /** * struct cfg80211_pmksa - PMK Security Association * * This structure is passed to the set/del_pmksa() method for PMKSA * caching. * * @bssid: The AP's BSSID (may be %NULL). * @pmkid: The identifier to refer a PMKSA. * @pmk: The PMK for the PMKSA identified by @pmkid. This is used for key * derivation by a FILS STA. Otherwise, %NULL. * @pmk_len: Length of the @pmk. The length of @pmk can differ depending on * the hash algorithm used to generate this. * @ssid: SSID to specify the ESS within which a PMKSA is valid when using FILS * cache identifier (may be %NULL). * @ssid_len: Length of the @ssid in octets. * @cache_id: 2-octet cache identifier advertized by a FILS AP identifying the * scope of PMKSA. This is valid only if @ssid_len is non-zero (may be * %NULL). * @pmk_lifetime: Maximum lifetime for PMKSA in seconds * (dot11RSNAConfigPMKLifetime) or 0 if not specified. * The configured PMKSA must not be used for PMKSA caching after * expiration and any keys derived from this PMK become invalid on * expiration, i.e., the current association must be dropped if the PMK * used for it expires. * @pmk_reauth_threshold: Threshold time for reauthentication (percentage of * PMK lifetime, dot11RSNAConfigPMKReauthThreshold) or 0 if not specified. * Drivers are expected to trigger a full authentication instead of using * this PMKSA for caching when reassociating to a new BSS after this * threshold to generate a new PMK before the current one expires. */ struct cfg80211_pmksa { const u8 *bssid; const u8 *pmkid; const u8 *pmk; size_t pmk_len; const u8 *ssid; size_t ssid_len; const u8 *cache_id; u32 pmk_lifetime; u8 pmk_reauth_threshold; }; /** * struct cfg80211_pkt_pattern - packet pattern * @mask: bitmask where to match pattern and where to ignore bytes, * one bit per byte, in same format as nl80211 * @pattern: bytes to match where bitmask is 1 * @pattern_len: length of pattern (in bytes) * @pkt_offset: packet offset (in bytes) * * Internal note: @mask and @pattern are allocated in one chunk of * memory, free @mask only! */ struct cfg80211_pkt_pattern { const u8 *mask, *pattern; int pattern_len; int pkt_offset; }; /** * struct cfg80211_wowlan_tcp - TCP connection parameters * * @sock: (internal) socket for source port allocation * @src: source IP address * @dst: destination IP address * @dst_mac: destination MAC address * @src_port: source port * @dst_port: destination port * @payload_len: data payload length * @payload: data payload buffer * @payload_seq: payload sequence stamping configuration * @data_interval: interval at which to send data packets * @wake_len: wakeup payload match length * @wake_data: wakeup payload match data * @wake_mask: wakeup payload match mask * @tokens_size: length of the tokens buffer * @payload_tok: payload token usage configuration */ struct cfg80211_wowlan_tcp { struct socket *sock; __be32 src, dst; u16 src_port, dst_port; u8 dst_mac[ETH_ALEN]; int payload_len; const u8 *payload; struct nl80211_wowlan_tcp_data_seq payload_seq; u32 data_interval; u32 wake_len; const u8 *wake_data, *wake_mask; u32 tokens_size; /* must be last, variable member */ struct nl80211_wowlan_tcp_data_token payload_tok; }; /** * struct cfg80211_wowlan - Wake on Wireless-LAN support info * * This structure defines the enabled WoWLAN triggers for the device. * @any: wake up on any activity -- special trigger if device continues * operating as normal during suspend * @disconnect: wake up if getting disconnected * @magic_pkt: wake up on receiving magic packet * @patterns: wake up on receiving packet matching a pattern * @n_patterns: number of patterns * @gtk_rekey_failure: wake up on GTK rekey failure * @eap_identity_req: wake up on EAP identity request packet * @four_way_handshake: wake up on 4-way handshake * @rfkill_release: wake up when rfkill is released * @tcp: TCP connection establishment/wakeup parameters, see nl80211.h. * NULL if not configured. * @nd_config: configuration for the scan to be used for net detect wake. */ struct cfg80211_wowlan { bool any, disconnect, magic_pkt, gtk_rekey_failure, eap_identity_req, four_way_handshake, rfkill_release; struct cfg80211_pkt_pattern *patterns; struct cfg80211_wowlan_tcp *tcp; int n_patterns; struct cfg80211_sched_scan_request *nd_config; }; /** * struct cfg80211_coalesce_rules - Coalesce rule parameters * * This structure defines coalesce rule for the device. * @delay: maximum coalescing delay in msecs. * @condition: condition for packet coalescence. * see &enum nl80211_coalesce_condition. * @patterns: array of packet patterns * @n_patterns: number of patterns */ struct cfg80211_coalesce_rules { int delay; enum nl80211_coalesce_condition condition; struct cfg80211_pkt_pattern *patterns; int n_patterns; }; /** * struct cfg80211_coalesce - Packet coalescing settings * * This structure defines coalescing settings. * @rules: array of coalesce rules * @n_rules: number of rules */ struct cfg80211_coalesce { int n_rules; struct cfg80211_coalesce_rules rules[] __counted_by(n_rules); }; /** * struct cfg80211_wowlan_nd_match - information about the match * * @ssid: SSID of the match that triggered the wake up * @n_channels: Number of channels where the match occurred. This * value may be zero if the driver can't report the channels. * @channels: center frequencies of the channels where a match * occurred (in MHz) */ struct cfg80211_wowlan_nd_match { struct cfg80211_ssid ssid; int n_channels; u32 channels[] __counted_by(n_channels); }; /** * struct cfg80211_wowlan_nd_info - net detect wake up information * * @n_matches: Number of match information instances provided in * @matches. This value may be zero if the driver can't provide * match information. * @matches: Array of pointers to matches containing information about * the matches that triggered the wake up. */ struct cfg80211_wowlan_nd_info { int n_matches; struct cfg80211_wowlan_nd_match *matches[] __counted_by(n_matches); }; /** * struct cfg80211_wowlan_wakeup - wakeup report * @disconnect: woke up by getting disconnected * @magic_pkt: woke up by receiving magic packet * @gtk_rekey_failure: woke up by GTK rekey failure * @eap_identity_req: woke up by EAP identity request packet * @four_way_handshake: woke up by 4-way handshake * @rfkill_release: woke up by rfkill being released * @pattern_idx: pattern that caused wakeup, -1 if not due to pattern * @packet_present_len: copied wakeup packet data * @packet_len: original wakeup packet length * @packet: The packet causing the wakeup, if any. * @packet_80211: For pattern match, magic packet and other data * frame triggers an 802.3 frame should be reported, for * disconnect due to deauth 802.11 frame. This indicates which * it is. * @tcp_match: TCP wakeup packet received * @tcp_connlost: TCP connection lost or failed to establish * @tcp_nomoretokens: TCP data ran out of tokens * @net_detect: if not %NULL, woke up because of net detect * @unprot_deauth_disassoc: woke up due to unprotected deauth or * disassoc frame (in MFP). */ struct cfg80211_wowlan_wakeup { bool disconnect, magic_pkt, gtk_rekey_failure, eap_identity_req, four_way_handshake, rfkill_release, packet_80211, tcp_match, tcp_connlost, tcp_nomoretokens, unprot_deauth_disassoc; s32 pattern_idx; u32 packet_present_len, packet_len; const void *packet; struct cfg80211_wowlan_nd_info *net_detect; }; /** * struct cfg80211_gtk_rekey_data - rekey data * @kek: key encryption key (@kek_len bytes) * @kck: key confirmation key (@kck_len bytes) * @replay_ctr: replay counter (NL80211_REPLAY_CTR_LEN bytes) * @kek_len: length of kek * @kck_len: length of kck * @akm: akm (oui, id) */ struct cfg80211_gtk_rekey_data { const u8 *kek, *kck, *replay_ctr; u32 akm; u8 kek_len, kck_len; }; /** * struct cfg80211_update_ft_ies_params - FT IE Information * * This structure provides information needed to update the fast transition IE * * @md: The Mobility Domain ID, 2 Octet value * @ie: Fast Transition IEs * @ie_len: Length of ft_ie in octets */ struct cfg80211_update_ft_ies_params { u16 md; const u8 *ie; size_t ie_len; }; /** * struct cfg80211_mgmt_tx_params - mgmt tx parameters * * This structure provides information needed to transmit a mgmt frame * * @chan: channel to use * @offchan: indicates whether off channel operation is required * @wait: duration for ROC * @buf: buffer to transmit * @len: buffer length * @no_cck: don't use cck rates for this frame * @dont_wait_for_ack: tells the low level not to wait for an ack * @n_csa_offsets: length of csa_offsets array * @csa_offsets: array of all the csa offsets in the frame * @link_id: for MLO, the link ID to transmit on, -1 if not given; note * that the link ID isn't validated (much), it's in range but the * link might not exist (or be used by the receiver STA) */ struct cfg80211_mgmt_tx_params { struct ieee80211_channel *chan; bool offchan; unsigned int wait; const u8 *buf; size_t len; bool no_cck; bool dont_wait_for_ack; int n_csa_offsets; const u16 *csa_offsets; int link_id; }; /** * struct cfg80211_dscp_exception - DSCP exception * * @dscp: DSCP value that does not adhere to the user priority range definition * @up: user priority value to which the corresponding DSCP value belongs */ struct cfg80211_dscp_exception { u8 dscp; u8 up; }; /** * struct cfg80211_dscp_range - DSCP range definition for user priority * * @low: lowest DSCP value of this user priority range, inclusive * @high: highest DSCP value of this user priority range, inclusive */ struct cfg80211_dscp_range { u8 low; u8 high; }; /* QoS Map Set element length defined in IEEE Std 802.11-2012, 8.4.2.97 */ #define IEEE80211_QOS_MAP_MAX_EX 21 #define IEEE80211_QOS_MAP_LEN_MIN 16 #define IEEE80211_QOS_MAP_LEN_MAX \ (IEEE80211_QOS_MAP_LEN_MIN + 2 * IEEE80211_QOS_MAP_MAX_EX) /** * struct cfg80211_qos_map - QoS Map Information * * This struct defines the Interworking QoS map setting for DSCP values * * @num_des: number of DSCP exceptions (0..21) * @dscp_exception: optionally up to maximum of 21 DSCP exceptions from * the user priority DSCP range definition * @up: DSCP range definition for a particular user priority */ struct cfg80211_qos_map { u8 num_des; struct cfg80211_dscp_exception dscp_exception[IEEE80211_QOS_MAP_MAX_EX]; struct cfg80211_dscp_range up[8]; }; /** * DOC: Neighbor Awareness Networking (NAN) * * NAN uses two interface types: * * - %NL80211_IFTYPE_NAN: a non-netdev interface. This has two roles: (1) holds * the configuration of all NAN activities (DE parameters, synchronisation * parameters, local schedule, etc.), and (2) uses as the NAN Management * Interface (NMI), which is used for NAN management communication. * * - %NL80211_IFTYPE_NAN_DATA: The NAN Data Interface (NDI), used for data * communication with NAN peers. * * An NDI interface can only be started (IFF_UP) if the NMI one is running and * NAN is started. Before NAN is stopped, all associated NDI interfaces * must be stopped first. * * The local schedule specifies which channels the device is available on and * when. Must be cancelled before NAN is stopped. * * NAN Stations * ~~~~~~~~~~~~ * * There are two types of stations corresponding to the two interface types: * * - NMI station: Represents the NAN peer. Peer-specific data such as the peer's * schedule and the HT, VHT and HE capabilities belongs to the NMI station. * Also used for Tx/Rx of NAN management frames to/from the peer. * Added on the %NL80211_IFTYPE_NAN interface. * * - NDI station: Used for Tx/Rx of data frames (and non-NAN management frames) * for a specific NDP established with the NAN peer. Added on the * %NL80211_IFTYPE_NAN_DATA interface. * * A peer may reuse its NMI address as the NDI address. In that case, two * separate stations should be added even though they share the same MAC * address. * * HT, VHT and HE capabilities should not changes after it was set. It is the * driver's responsibility to check that. * * An NDI station can only be added if the corresponding NMI station has already * been configured with HT (and possibly VHT and HE) capabilities. It is the * driver's responsibility to check that. * * All NDI stations must be removed before corresponding NMI station is removed. * Therefore, removing a NMI station implies that the associated NDI station(s) * (if any) will be removed first. * * NAN Dependencies * ~~~~~~~~~~~~~~~~ * * The following diagram shows the dependencies between NAN components. * An arrow from A to B means A must be started/added before B, and B must be * stopped/removed before A: * * +-------------+ * | NMI iface |---(local schedule) * +------+------+ * / \ * v v * +-----------+ +-------------+ * | NDI iface | | NMI sta |---(peer schedule) * +-----+-----+ +------+------+ * \ / * v v * +----------+ * | NDI sta | * +----------+ */ /** * struct cfg80211_nan_band_config - NAN band specific configuration * * @chan: Pointer to the IEEE 802.11 channel structure. The channel to be used * for NAN operations on this band. For 2.4 GHz band, this is always * channel 6. For 5 GHz band, the channel is either 44 or 149, according * to the regulatory constraints. If chan pointer is NULL the entire band * configuration entry is considered invalid and should not be used. * @rssi_close: RSSI close threshold used for NAN state transition algorithm * as described in chapters 3.3.6 and 3.3.7 "NAN Device Role and State * Transition" of Wi-Fi Aware Specification v4.0. If not * specified (set to 0), default device value is used. The value should * be greater than -60 dBm. * @rssi_middle: RSSI middle threshold used for NAN state transition algorithm. * as described in chapters 3.3.6 and 3.3.7 "NAN Device Role and State * Transition" of Wi-Fi Aware Specification v4.0. If not * specified (set to 0), default device value is used. The value should be * greater than -75 dBm and less than rssi_close. * @awake_dw_interval: Committed DW interval. Valid values range: 0-5. 0 * indicates no wakeup for DW and can't be used on 2.4GHz band, otherwise * 2^(n-1). * @disable_scan: If true, the device will not scan this band for cluster * merge. Disabling scan on 2.4 GHz band is not allowed. */ struct cfg80211_nan_band_config { struct ieee80211_channel *chan; s8 rssi_close; s8 rssi_middle; u8 awake_dw_interval; bool disable_scan; }; /** * struct cfg80211_nan_conf - NAN configuration * * This struct defines NAN configuration parameters * * @master_pref: master preference (1 - 255) * @bands: operating bands, a bitmap of &enum nl80211_band values. * For instance, for NL80211_BAND_2GHZ, bit 0 would be set * (i.e. BIT(NL80211_BAND_2GHZ)). * @cluster_id: cluster ID used for NAN synchronization. This is a MAC address * that can take a value from 50-6F-9A-01-00-00 to 50-6F-9A-01-FF-FF. * @scan_period: period (in seconds) between NAN scans. * @scan_dwell_time: dwell time (in milliseconds) for NAN scans. * @discovery_beacon_interval: interval (in TUs) for discovery beacons. * @enable_dw_notification: flag to enable/disable discovery window * notifications. * @band_cfgs: array of band specific configurations, indexed by * &enum nl80211_band values. * @extra_nan_attrs: pointer to additional NAN attributes. * @extra_nan_attrs_len: length of the additional NAN attributes. * @vendor_elems: pointer to vendor-specific elements. * @vendor_elems_len: length of the vendor-specific elements. */ struct cfg80211_nan_conf { u8 master_pref; u8 bands; u8 cluster_id[ETH_ALEN] __aligned(2); u16 scan_period; u16 scan_dwell_time; u8 discovery_beacon_interval; bool enable_dw_notification; struct cfg80211_nan_band_config band_cfgs[NUM_NL80211_BANDS]; const u8 *extra_nan_attrs; u16 extra_nan_attrs_len; const u8 *vendor_elems; u16 vendor_elems_len; }; #define CFG80211_NAN_SCHED_NUM_TIME_SLOTS 32 /** * struct cfg80211_nan_channel - NAN channel configuration * * This struct defines a NAN channel configuration * * @chandef: the channel definition * @channel_entry: pointer to the Channel Entry blob as defined in Wi-Fi Aware * (TM) 4.0 specification Table 100 (Channel Entry format for the NAN * Availability attribute). * @rx_nss: number of spatial streams supported on this channel */ struct cfg80211_nan_channel { struct cfg80211_chan_def chandef; const u8 *channel_entry; u8 rx_nss; }; /** * struct cfg80211_nan_local_sched - NAN local schedule * * This struct defines NAN local schedule parameters * * @schedule: a mapping of time slots to chandef indexes in %nan_channels. * An unscheduled slot will be set to %NL80211_NAN_SCHED_NOT_AVAIL_SLOT. * @n_channels: number of channel definitions in %nan_channels. * @nan_avail_blob: pointer to NAN Availability attribute blob. * See %NL80211_ATTR_NAN_AVAIL_BLOB for more details. * @nan_avail_blob_len: length of the @nan_avail_blob in bytes. * @deferred: if true, the command containing this schedule configuration is a * request from the device to perform an announced schedule update. This * means that it needs to send the updated NAN availability to the peers, * and do the actual switch on the right time (i.e. at the end of the slot * after the slot in which the updated NAN Availability was sent). * See %NL80211_ATTR_NAN_SCHED_DEFERRED for more details. * If false, the schedule is applied immediately. * @nan_channels: array of NAN channel definitions that can be scheduled. */ struct cfg80211_nan_local_sched { u8 schedule[CFG80211_NAN_SCHED_NUM_TIME_SLOTS]; u8 n_channels; const u8 *nan_avail_blob; u16 nan_avail_blob_len; bool deferred; struct cfg80211_nan_channel nan_channels[] __counted_by(n_channels); }; /** * struct cfg80211_nan_peer_map - NAN peer schedule map * * This struct defines a single NAN peer schedule map * * @map_id: map ID of this schedule map * @schedule: a mapping of time slots to chandef indexes in the schedule's * @nan_channels. Each slot lasts 16TUs. An unscheduled slot will be * set to %NL80211_NAN_SCHED_NOT_AVAIL_SLOT. */ struct cfg80211_nan_peer_map { u8 map_id; u8 schedule[CFG80211_NAN_SCHED_NUM_TIME_SLOTS]; }; #define CFG80211_NAN_MAX_PEER_MAPS 2 #define CFG80211_NAN_INVALID_MAP_ID 0xff /** * struct cfg80211_nan_peer_sched - NAN peer schedule * * This struct defines NAN peer schedule parameters for a peer. * * @peer_addr: MAC address of the peer (NMI address) * @seq_id: sequence ID of the peer schedule. * @committed_dw: committed DW as published by the peer. * See %NL80211_ATTR_NAN_COMMITTED_DW * @max_chan_switch: maximum channel switch time in microseconds as published * by the peer. See %NL80211_ATTR_NAN_MAX_CHAN_SWITCH_TIME. * @init_ulw: initial ULWs as published by the peer. * @ulw_size: number of bytes in @init_ulw. * @n_channels: number of channel definitions in @nan_channels. * @nan_channels: array of NAN channel definitions for this schedule. * @maps: array of peer schedule maps. Unused entries have * map_id = %CFG80211_NAN_INVALID_MAP_ID. */ struct cfg80211_nan_peer_sched { const u8 *peer_addr; u8 seq_id; u16 committed_dw; u16 max_chan_switch; const u8 *init_ulw; u16 ulw_size; u8 n_channels; struct cfg80211_nan_channel *nan_channels; struct cfg80211_nan_peer_map maps[CFG80211_NAN_MAX_PEER_MAPS]; }; /** * enum cfg80211_nan_conf_changes - indicates changed fields in NAN * configuration * * @CFG80211_NAN_CONF_CHANGED_PREF: master preference * @CFG80211_NAN_CONF_CHANGED_BANDS: operating bands * @CFG80211_NAN_CONF_CHANGED_CONFIG: changed additional configuration. * When this flag is set, it indicates that some additional attribute(s) * (other then master_pref and bands) have been changed. In this case, * all the unchanged attributes will be properly configured to their * previous values. The driver doesn't need to store any * previous configuration besides master_pref and bands. */ enum cfg80211_nan_conf_changes { CFG80211_NAN_CONF_CHANGED_PREF = BIT(0), CFG80211_NAN_CONF_CHANGED_BANDS = BIT(1), CFG80211_NAN_CONF_CHANGED_CONFIG = BIT(2), }; /** * struct cfg80211_nan_func_filter - a NAN function Rx / Tx filter * * @filter: the content of the filter * @len: the length of the filter */ struct cfg80211_nan_func_filter { const u8 *filter; u8 len; }; /** * struct cfg80211_nan_func - a NAN function * * @type: &enum nl80211_nan_function_type * @service_id: the service ID of the function * @publish_type: &nl80211_nan_publish_type * @close_range: if true, the range should be limited. Threshold is * implementation specific. * @publish_bcast: if true, the solicited publish should be broadcasted * @subscribe_active: if true, the subscribe is active * @followup_id: the instance ID for follow up * @followup_reqid: the requester instance ID for follow up * @followup_dest: MAC address of the recipient of the follow up * @ttl: time to live counter in DW. * @serv_spec_info: Service Specific Info * @serv_spec_info_len: Service Specific Info length * @srf_include: if true, SRF is inclusive * @srf_bf: Bloom Filter * @srf_bf_len: Bloom Filter length * @srf_bf_idx: Bloom Filter index * @srf_macs: SRF MAC addresses * @srf_num_macs: number of MAC addresses in SRF * @rx_filters: rx filters that are matched with corresponding peer's tx_filter * @tx_filters: filters that should be transmitted in the SDF. * @num_rx_filters: length of &rx_filters. * @num_tx_filters: length of &tx_filters. * @instance_id: driver allocated id of the function. * @cookie: unique NAN function identifier. */ struct cfg80211_nan_func { enum nl80211_nan_function_type type; u8 service_id[NL80211_NAN_FUNC_SERVICE_ID_LEN]; u8 publish_type; bool close_range; bool publish_bcast; bool subscribe_active; u8 followup_id; u8 followup_reqid; struct mac_address followup_dest; u32 ttl; const u8 *serv_spec_info; u8 serv_spec_info_len; bool srf_include; const u8 *srf_bf; u8 srf_bf_len; u8 srf_bf_idx; struct mac_address *srf_macs; int srf_num_macs; struct cfg80211_nan_func_filter *rx_filters; struct cfg80211_nan_func_filter *tx_filters; u8 num_tx_filters; u8 num_rx_filters; u8 instance_id; u64 cookie; }; /** * struct cfg80211_pmk_conf - PMK configuration * * @aa: authenticator address * @pmk_len: PMK length in bytes. * @pmk: the PMK material * @pmk_r0_name: PMK-R0 Name. NULL if not applicable (i.e., the PMK * is not PMK-R0). When pmk_r0_name is not NULL, the pmk field * holds PMK-R0. */ struct cfg80211_pmk_conf { const u8 *aa; u8 pmk_len; const u8 *pmk; const u8 *pmk_r0_name; }; /** * struct cfg80211_external_auth_params - Trigger External authentication. * * Commonly used across the external auth request and event interfaces. * * @action: action type / trigger for external authentication. Only significant * for the authentication request event interface (driver to user space). * @bssid: BSSID of the peer with which the authentication has * to happen. Used by both the authentication request event and * authentication response command interface. * @ssid: SSID of the AP. Used by both the authentication request event and * authentication response command interface. * @key_mgmt_suite: AKM suite of the respective authentication. Used by the * authentication request event interface. * @status: status code, %WLAN_STATUS_SUCCESS for successful authentication, * use %WLAN_STATUS_UNSPECIFIED_FAILURE if user space cannot give you * the real status code for failures. Used only for the authentication * response command interface (user space to driver). * @pmkid: The identifier to refer a PMKSA. * @mld_addr: MLD address of the peer. Used by the authentication request event * interface. Driver indicates this to enable MLO during the authentication * offload to user space. Driver shall look at %NL80211_ATTR_MLO_SUPPORT * flag capability in NL80211_CMD_CONNECT to know whether the user space * supports enabling MLO during the authentication offload. * User space should use the address of the interface (on which the * authentication request event reported) as self MLD address. User space * and driver should use MLD addresses in RA, TA and BSSID fields of * authentication frames sent or received via cfg80211. The driver * translates the MLD addresses to/from link addresses based on the link * chosen for the authentication. */ struct cfg80211_external_auth_params { enum nl80211_external_auth_action action; u8 bssid[ETH_ALEN] __aligned(2); struct cfg80211_ssid ssid; unsigned int key_mgmt_suite; u16 status; const u8 *pmkid; u8 mld_addr[ETH_ALEN] __aligned(2); }; /** * struct cfg80211_ftm_responder_stats - FTM responder statistics * * @filled: bitflag of flags using the bits of &enum nl80211_ftm_stats to * indicate the relevant values in this struct for them * @success_num: number of FTM sessions in which all frames were successfully * answered * @partial_num: number of FTM sessions in which part of frames were * successfully answered * @failed_num: number of failed FTM sessions * @asap_num: number of ASAP FTM sessions * @non_asap_num: number of non-ASAP FTM sessions * @total_duration_ms: total sessions durations - gives an indication * of how much time the responder was busy * @unknown_triggers_num: number of unknown FTM triggers - triggers from * initiators that didn't finish successfully the negotiation phase with * the responder * @reschedule_requests_num: number of FTM reschedule requests - initiator asks * for a new scheduling although it already has scheduled FTM slot * @out_of_window_triggers_num: total FTM triggers out of scheduled window */ struct cfg80211_ftm_responder_stats { u32 filled; u32 success_num; u32 partial_num; u32 failed_num; u32 asap_num; u32 non_asap_num; u64 total_duration_ms; u32 unknown_triggers_num; u32 reschedule_requests_num; u32 out_of_window_triggers_num; }; /** * struct cfg80211_pmsr_ftm_result - FTM result * @failure_reason: if this measurement failed (PMSR status is * %NL80211_PMSR_STATUS_FAILURE), this gives a more precise * reason than just "failure" * @burst_index: if reporting partial results, this is the index * in [0 .. num_bursts-1] of the burst that's being reported * @num_ftmr_attempts: number of FTM request frames transmitted * @num_ftmr_successes: number of FTM request frames acked * @busy_retry_time: if failure_reason is %NL80211_PMSR_FTM_FAILURE_PEER_BUSY, * fill this to indicate in how many seconds a retry is deemed possible * by the responder * @num_bursts_exp: actual number of bursts exponent negotiated * @burst_duration: actual burst duration negotiated * @ftms_per_burst: actual FTMs per burst negotiated * @burst_period: actual burst period negotiated in units of 100ms * @lci_len: length of LCI information (if present) * @civicloc_len: length of civic location information (if present) * @lci: LCI data (may be %NULL) * @civicloc: civic location data (may be %NULL) * @rssi_avg: average RSSI over FTM action frames reported * @rssi_spread: spread of the RSSI over FTM action frames reported * @tx_rate: bitrate for transmitted FTM action frame response * @rx_rate: bitrate of received FTM action frame * @rtt_avg: average of RTTs measured (must have either this or @dist_avg) * @rtt_variance: variance of RTTs measured (note that standard deviation is * the square root of the variance) * @rtt_spread: spread of the RTTs measured * @dist_avg: average of distances (mm) measured * (must have either this or @rtt_avg) * @dist_variance: variance of distances measured (see also @rtt_variance) * @dist_spread: spread of distances measured (see also @rtt_spread) * @num_ftmr_attempts_valid: @num_ftmr_attempts is valid * @num_ftmr_successes_valid: @num_ftmr_successes is valid * @rssi_avg_valid: @rssi_avg is valid * @rssi_spread_valid: @rssi_spread is valid * @tx_rate_valid: @tx_rate is valid * @rx_rate_valid: @rx_rate is valid * @rtt_avg_valid: @rtt_avg is valid * @rtt_variance_valid: @rtt_variance is valid * @rtt_spread_valid: @rtt_spread is valid * @dist_avg_valid: @dist_avg is valid * @dist_variance_valid: @dist_variance is valid * @dist_spread_valid: @dist_spread is valid */ struct cfg80211_pmsr_ftm_result { const u8 *lci; const u8 *civicloc; unsigned int lci_len; unsigned int civicloc_len; enum nl80211_peer_measurement_ftm_failure_reasons failure_reason; u32 num_ftmr_attempts, num_ftmr_successes; s16 burst_index; u8 busy_retry_time; u8 num_bursts_exp; u8 burst_duration; u8 ftms_per_burst; u16 burst_period; s32 rssi_avg; s32 rssi_spread; struct rate_info tx_rate, rx_rate; s64 rtt_avg; s64 rtt_variance; s64 rtt_spread; s64 dist_avg; s64 dist_variance; s64 dist_spread; u16 num_ftmr_attempts_valid:1, num_ftmr_successes_valid:1, rssi_avg_valid:1, rssi_spread_valid:1, tx_rate_valid:1, rx_rate_valid:1, rtt_avg_valid:1, rtt_variance_valid:1, rtt_spread_valid:1, dist_avg_valid:1, dist_variance_valid:1, dist_spread_valid:1; }; /** * struct cfg80211_pmsr_result - peer measurement result * @addr: address of the peer * @host_time: host time (use ktime_get_boottime() adjust to the time when the * measurement was made) * @ap_tsf: AP's TSF at measurement time * @status: status of the measurement * @final: if reporting partial results, mark this as the last one; if not * reporting partial results always set this flag * @ap_tsf_valid: indicates the @ap_tsf value is valid * @type: type of the measurement reported, note that we only support reporting * one type at a time, but you can report multiple results separately and * they're all aggregated for userspace. * @ftm: FTM result */ struct cfg80211_pmsr_result { u64 host_time, ap_tsf; enum nl80211_peer_measurement_status status; u8 addr[ETH_ALEN]; u8 final:1, ap_tsf_valid:1; enum nl80211_peer_measurement_type type; union { struct cfg80211_pmsr_ftm_result ftm; }; }; /** * struct cfg80211_pmsr_ftm_request_peer - FTM request data * @requested: indicates FTM is requested * @preamble: frame preamble to use * @burst_period: burst period to use * @asap: indicates to use ASAP mode * @num_bursts_exp: number of bursts exponent * @burst_duration: burst duration. If @trigger_based or @non_trigger_based is * set, this is the burst duration in milliseconds, and zero means the * device should pick an appropriate value based on @ftms_per_burst. * @ftms_per_burst: number of FTMs per burst * @ftmr_retries: number of retries for FTM request * @request_lci: request LCI information * @request_civicloc: request civic location information * @trigger_based: use trigger based ranging for the measurement * If neither @trigger_based nor @non_trigger_based is set, * EDCA based ranging will be used. * @non_trigger_based: use non trigger based ranging for the measurement * If neither @trigger_based nor @non_trigger_based is set, * EDCA based ranging will be used. * @lmr_feedback: negotiate for I2R LMR feedback. Only valid if either * @trigger_based or @non_trigger_based is set. * @rsta: Operate as the RSTA in the measurement. Only valid if @lmr_feedback * and either @trigger_based or @non_trigger_based is set. * @bss_color: the bss color of the responder. Optional. Set to zero to * indicate the driver should set the BSS color. Only valid if * @non_trigger_based or @trigger_based is set. * * See also nl80211 for the respective attribute documentation. */ struct cfg80211_pmsr_ftm_request_peer { enum nl80211_preamble preamble; u16 burst_period; u8 requested:1, asap:1, request_lci:1, request_civicloc:1, trigger_based:1, non_trigger_based:1, lmr_feedback:1, rsta:1; u8 num_bursts_exp; u8 burst_duration; u8 ftms_per_burst; u8 ftmr_retries; u8 bss_color; }; /** * struct cfg80211_pmsr_request_peer - peer data for a peer measurement request * @addr: MAC address * @chandef: channel to use * @report_ap_tsf: report the associated AP's TSF * @ftm: FTM data, see &struct cfg80211_pmsr_ftm_request_peer */ struct cfg80211_pmsr_request_peer { u8 addr[ETH_ALEN]; struct cfg80211_chan_def chandef; u8 report_ap_tsf:1; struct cfg80211_pmsr_ftm_request_peer ftm; }; /** * struct cfg80211_pmsr_request - peer measurement request * @cookie: cookie, set by cfg80211 * @nl_portid: netlink portid - used by cfg80211 * @drv_data: driver data for this request, if required for aborting, * not otherwise freed or anything by cfg80211 * @mac_addr: MAC address used for (randomised) request * @mac_addr_mask: MAC address mask used for randomisation, bits that * are 0 in the mask should be randomised, bits that are 1 should * be taken from the @mac_addr * @list: used by cfg80211 to hold on to the request * @timeout: timeout (in milliseconds) for the whole operation, if * zero it means there's no timeout * @n_peers: number of peers to do measurements with * @peers: per-peer measurement request data */ struct cfg80211_pmsr_request { u64 cookie; void *drv_data; u32 n_peers; u32 nl_portid; u32 timeout; u8 mac_addr[ETH_ALEN] __aligned(2); u8 mac_addr_mask[ETH_ALEN] __aligned(2); struct list_head list; struct cfg80211_pmsr_request_peer peers[] __counted_by(n_peers); }; /** * struct cfg80211_update_owe_info - OWE Information * * This structure provides information needed for the drivers to offload OWE * (Opportunistic Wireless Encryption) processing to the user space. * * Commonly used across update_owe_info request and event interfaces. * * @peer: MAC address of the peer device for which the OWE processing * has to be done. * @status: status code, %WLAN_STATUS_SUCCESS for successful OWE info * processing, use %WLAN_STATUS_UNSPECIFIED_FAILURE if user space * cannot give you the real status code for failures. Used only for * OWE update request command interface (user space to driver). * @ie: IEs obtained from the peer or constructed by the user space. These are * the IEs of the remote peer in the event from the host driver and * the constructed IEs by the user space in the request interface. * @ie_len: Length of IEs in octets. * @assoc_link_id: MLO link ID of the AP, with which (re)association requested * by peer. This will be filled by driver for both MLO and non-MLO station * connections when the AP affiliated with an MLD. For non-MLD AP mode, it * will be -1. Used only with OWE update event (driver to user space). * @peer_mld_addr: For MLO connection, MLD address of the peer. For non-MLO * connection, it will be all zeros. This is applicable only when * @assoc_link_id is not -1, i.e., the AP affiliated with an MLD. Used only * with OWE update event (driver to user space). */ struct cfg80211_update_owe_info { u8 peer[ETH_ALEN] __aligned(2); u16 status; const u8 *ie; size_t ie_len; int assoc_link_id; u8 peer_mld_addr[ETH_ALEN] __aligned(2); }; /** * struct mgmt_frame_regs - management frame registrations data * @global_stypes: bitmap of management frame subtypes registered * for the entire device * @interface_stypes: bitmap of management frame subtypes registered * for the given interface * @global_mcast_stypes: mcast RX is needed globally for these subtypes * @interface_mcast_stypes: mcast RX is needed on this interface * for these subtypes */ struct mgmt_frame_regs { u32 global_stypes, interface_stypes; u32 global_mcast_stypes, interface_mcast_stypes; }; /** * struct cfg80211_ops - backend description for wireless configuration * * This struct is registered by fullmac card drivers and/or wireless stacks * in order to handle configuration requests on their interfaces. * * All callbacks except where otherwise noted should return 0 * on success or a negative error code. * * All operations are invoked with the wiphy mutex held. The RTNL may be * held in addition (due to wireless extensions) but this cannot be relied * upon except in cases where documented below. Note that due to ordering, * the RTNL also cannot be acquired in any handlers. * * @suspend: wiphy device needs to be suspended. The variable @wow will * be %NULL or contain the enabled Wake-on-Wireless triggers that are * configured for the device. * @resume: wiphy device needs to be resumed * @set_wakeup: Called when WoWLAN is enabled/disabled, use this callback * to call device_set_wakeup_enable() to enable/disable wakeup from * the device. * * @add_virtual_intf: create a new virtual interface with the given name, * must set the struct wireless_dev's iftype. Beware: You must create * the new netdev in the wiphy's network namespace! Returns the struct * wireless_dev, or an ERR_PTR. For P2P device wdevs, the driver must * also set the address member in the wdev. * This additionally holds the RTNL to be able to do netdev changes. * * @del_virtual_intf: remove the virtual interface * This additionally holds the RTNL to be able to do netdev changes. * * @change_virtual_intf: change type/configuration of virtual interface, * keep the struct wireless_dev's iftype updated. * This additionally holds the RTNL to be able to do netdev changes. * * @add_intf_link: Add a new MLO link to the given interface. Note that * the wdev->link[] data structure has been updated, so the new link * address is available. * @del_intf_link: Remove an MLO link from the given interface. * * @add_key: add a key with the given parameters. @mac_addr will be %NULL * when adding a group key. @link_id will be -1 for non-MLO connection. * For MLO connection, @link_id will be >= 0 for group key and -1 for * pairwise key, @mac_addr will be peer's MLD address for MLO pairwise key. * * @get_key: get information about the key with the given parameters. * @mac_addr will be %NULL when requesting information for a group * key. All pointers given to the @callback function need not be valid * after it returns. This function should return an error if it is * not possible to retrieve the key, -ENOENT if it doesn't exist. * @link_id will be -1 for non-MLO connection. For MLO connection, * @link_id will be >= 0 for group key and -1 for pairwise key, @mac_addr * will be peer's MLD address for MLO pairwise key. * * @del_key: remove a key given the @mac_addr (%NULL for a group key) * and @key_index, return -ENOENT if the key doesn't exist. @link_id will * be -1 for non-MLO connection. For MLO connection, @link_id will be >= 0 * for group key and -1 for pairwise key, @mac_addr will be peer's MLD * address for MLO pairwise key. * * @set_default_key: set the default key on an interface. @link_id will be >= 0 * for MLO connection and -1 for non-MLO connection. * * @set_default_mgmt_key: set the default management frame key on an interface. * @link_id will be >= 0 for MLO connection and -1 for non-MLO connection. * * @set_default_beacon_key: set the default Beacon frame key on an interface. * @link_id will be >= 0 for MLO connection and -1 for non-MLO connection. * * @set_rekey_data: give the data necessary for GTK rekeying to the driver * * @start_ap: Start acting in AP mode defined by the parameters. * @change_beacon: Change the beacon parameters for an access point mode * interface. This should reject the call when AP mode wasn't started. * @stop_ap: Stop being an AP, including stopping beaconing. * * @add_station: Add a new station. * @del_station: Remove a station * @change_station: Modify a given station. Note that flags changes are not much * validated in cfg80211, in particular the auth/assoc/authorized flags * might come to the driver in invalid combinations -- make sure to check * them, also against the existing state! Drivers must call * cfg80211_check_station_change() to validate the information. * @get_station: get station information for the station identified by @mac * @dump_station: dump station callback -- resume dump at index @idx * * @add_mpath: add a fixed mesh path * @del_mpath: delete a given mesh path * @change_mpath: change a given mesh path * @get_mpath: get a mesh path for the given parameters * @dump_mpath: dump mesh path callback -- resume dump at index @idx * @get_mpp: get a mesh proxy path for the given parameters * @dump_mpp: dump mesh proxy path callback -- resume dump at index @idx * @join_mesh: join the mesh network with the specified parameters * (invoked with the wireless_dev mutex held) * @leave_mesh: leave the current mesh network * (invoked with the wireless_dev mutex held) * * @get_mesh_config: Get the current mesh configuration * * @update_mesh_config: Update mesh parameters on a running mesh. * The mask is a bitfield which tells us which parameters to * set, and which to leave alone. * * @change_bss: Modify parameters for a given BSS. * * @inform_bss: Called by cfg80211 while being informed about new BSS data * for every BSS found within the reported data or frame. This is called * from within the cfg8011 inform_bss handlers while holding the bss_lock. * The data parameter is passed through from drv_data inside * struct cfg80211_inform_bss. * The new IE data for the BSS is explicitly passed. * * @set_txq_params: Set TX queue parameters * * @libertas_set_mesh_channel: Only for backward compatibility for libertas, * as it doesn't implement join_mesh and needs to set the channel to * join the mesh instead. * * @set_monitor_channel: Set the monitor mode channel for the device. If other * interfaces are active this callback should reject the configuration. * If no interfaces are active or the device is down, the channel should * be stored for when a monitor interface becomes active. * * @scan: Request to do a scan. If returning zero, the scan request is given * the driver, and will be valid until passed to cfg80211_scan_done(). * For scan results, call cfg80211_inform_bss(); you can call this outside * the scan/scan_done bracket too. * @abort_scan: Tell the driver to abort an ongoing scan. The driver shall * indicate the status of the scan through cfg80211_scan_done(). * * @auth: Request to authenticate with the specified peer * (invoked with the wireless_dev mutex held) * @assoc: Request to (re)associate with the specified peer * (invoked with the wireless_dev mutex held) * @deauth: Request to deauthenticate from the specified peer * (invoked with the wireless_dev mutex held) * @disassoc: Request to disassociate from the specified peer * (invoked with the wireless_dev mutex held) * * @connect: Connect to the ESS with the specified parameters. When connected, * call cfg80211_connect_result()/cfg80211_connect_bss() with status code * %WLAN_STATUS_SUCCESS. If the connection fails for some reason, call * cfg80211_connect_result()/cfg80211_connect_bss() with the status code * from the AP or cfg80211_connect_timeout() if no frame with status code * was received. * The driver is allowed to roam to other BSSes within the ESS when the * other BSS matches the connect parameters. When such roaming is initiated * by the driver, the driver is expected to verify that the target matches * the configured security parameters and to use Reassociation Request * frame instead of Association Request frame. * The connect function can also be used to request the driver to perform a * specific roam when connected to an ESS. In that case, the prev_bssid * parameter is set to the BSSID of the currently associated BSS as an * indication of requesting reassociation. * In both the driver-initiated and new connect() call initiated roaming * cases, the result of roaming is indicated with a call to * cfg80211_roamed(). (invoked with the wireless_dev mutex held) * @update_connect_params: Update the connect parameters while connected to a * BSS. The updated parameters can be used by driver/firmware for * subsequent BSS selection (roaming) decisions and to form the * Authentication/(Re)Association Request frames. This call does not * request an immediate disassociation or reassociation with the current * BSS, i.e., this impacts only subsequent (re)associations. The bits in * changed are defined in &enum cfg80211_connect_params_changed. * (invoked with the wireless_dev mutex held) * @disconnect: Disconnect from the BSS/ESS or stop connection attempts if * connection is in progress. Once done, call cfg80211_disconnected() in * case connection was already established (invoked with the * wireless_dev mutex held), otherwise call cfg80211_connect_timeout(). * * @join_ibss: Join the specified IBSS (or create if necessary). Once done, call * cfg80211_ibss_joined(), also call that function when changing BSSID due * to a merge. * (invoked with the wireless_dev mutex held) * @leave_ibss: Leave the IBSS. * (invoked with the wireless_dev mutex held) * * @set_mcast_rate: Set the specified multicast rate (only if vif is in ADHOC or * MESH mode) * * @set_wiphy_params: Notify that wiphy parameters have changed; * @changed bitfield (see &enum wiphy_params_flags) describes which values * have changed. The actual parameter values are available in * struct wiphy. If returning an error, no value should be changed. * * @set_tx_power: set the transmit power according to the parameters, * the power passed is in mBm, to get dBm use MBM_TO_DBM(). The * wdev may be %NULL if power was set for the wiphy, and will * always be %NULL unless the driver supports per-vif TX power * (as advertised by the nl80211 feature flag.) * @get_tx_power: store the current TX power into the dbm variable; * return 0 if successful * * @rfkill_poll: polls the hw rfkill line, use cfg80211 reporting * functions to adjust rfkill hw state * * @dump_survey: get site survey information. * * @remain_on_channel: Request the driver to remain awake on the specified * channel for the specified duration to complete an off-channel * operation (e.g., public action frame exchange). When the driver is * ready on the requested channel, it must indicate this with an event * notification by calling cfg80211_ready_on_channel(). * @cancel_remain_on_channel: Cancel an on-going remain-on-channel operation. * This allows the operation to be terminated prior to timeout based on * the duration value. * @mgmt_tx: Transmit a management frame. * @mgmt_tx_cancel_wait: Cancel the wait time from transmitting a management * frame on another channel * * @testmode_cmd: run a test mode command; @wdev may be %NULL * @testmode_dump: Implement a test mode dump. The cb->args[2] and up may be * used by the function, but 0 and 1 must not be touched. Additionally, * return error codes other than -ENOBUFS and -ENOENT will terminate the * dump and return to userspace with an error, so be careful. If any data * was passed in from userspace then the data/len arguments will be present * and point to the data contained in %NL80211_ATTR_TESTDATA. * * @set_bitrate_mask: set the bitrate mask configuration * * @set_pmksa: Cache a PMKID for a BSSID. This is mostly useful for fullmac * devices running firmwares capable of generating the (re) association * RSN IE. It allows for faster roaming between WPA2 BSSIDs. * @del_pmksa: Delete a cached PMKID. * @flush_pmksa: Flush all cached PMKIDs. * @set_power_mgmt: Configure WLAN power management. A timeout value of -1 * allows the driver to adjust the dynamic ps timeout value. * @set_cqm_rssi_config: Configure connection quality monitor RSSI threshold. * After configuration, the driver should (soon) send an event indicating * the current level is above/below the configured threshold; this may * need some care when the configuration is changed (without first being * disabled.) * @set_cqm_rssi_range_config: Configure two RSSI thresholds in the * connection quality monitor. An event is to be sent only when the * signal level is found to be outside the two values. The driver should * set %NL80211_EXT_FEATURE_CQM_RSSI_LIST if this method is implemented. * If it is provided then there's no point providing @set_cqm_rssi_config. * @set_cqm_txe_config: Configure connection quality monitor TX error * thresholds. * @sched_scan_start: Tell the driver to start a scheduled scan. * @sched_scan_stop: Tell the driver to stop an ongoing scheduled scan with * given request id. This call must stop the scheduled scan and be ready * for starting a new one before it returns, i.e. @sched_scan_start may be * called immediately after that again and should not fail in that case. * The driver should not call cfg80211_sched_scan_stopped() for a requested * stop (when this method returns 0). * * @update_mgmt_frame_registrations: Notify the driver that management frame * registrations were updated. The callback is allowed to sleep. * * @set_antenna: Set antenna configuration (tx_ant, rx_ant) on the device. * Parameters are bitmaps of allowed antennas to use for TX/RX. Drivers may * reject TX/RX mask combinations they cannot support by returning -EINVAL * (also see nl80211.h @NL80211_ATTR_WIPHY_ANTENNA_TX). * * @get_antenna: Get current antenna configuration from device (tx_ant, rx_ant). * * @tdls_mgmt: Transmit a TDLS management frame. * @tdls_oper: Perform a high-level TDLS operation (e.g. TDLS link setup). * * @probe_client: probe an associated client, must return a cookie that it * later passes to cfg80211_probe_status(). * * @set_noack_map: Set the NoAck Map for the TIDs. * * @get_channel: Get the current operating channel for the virtual interface. * For monitor interfaces, it should return %NULL unless there's a single * current monitoring channel. * * @start_p2p_device: Start the given P2P device. * @stop_p2p_device: Stop the given P2P device. * * @set_mac_acl: Sets MAC address control list in AP and P2P GO mode. * Parameters include ACL policy, an array of MAC address of stations * and the number of MAC addresses. If there is already a list in driver * this new list replaces the existing one. Driver has to clear its ACL * when number of MAC addresses entries is passed as 0. Drivers which * advertise the support for MAC based ACL have to implement this callback. * * @start_radar_detection: Start radar detection in the driver. * * @end_cac: End running CAC, probably because a related CAC * was finished on another phy. * * @update_ft_ies: Provide updated Fast BSS Transition information to the * driver. If the SME is in the driver/firmware, this information can be * used in building Authentication and Reassociation Request frames. * * @crit_proto_start: Indicates a critical protocol needs more link reliability * for a given duration (milliseconds). The protocol is provided so the * driver can take the most appropriate actions. * @crit_proto_stop: Indicates critical protocol no longer needs increased link * reliability. This operation can not fail. * @set_coalesce: Set coalesce parameters. * * @channel_switch: initiate channel-switch procedure (with CSA). Driver is * responsible for veryfing if the switch is possible. Since this is * inherently tricky driver may decide to disconnect an interface later * with cfg80211_stop_iface(). This doesn't mean driver can accept * everything. It should do it's best to verify requests and reject them * as soon as possible. * * @set_qos_map: Set QoS mapping information to the driver * * @set_ap_chanwidth: Set the AP (including P2P GO) mode channel width for the * given interface This is used e.g. for dynamic HT 20/40 MHz channel width * changes during the lifetime of the BSS. * * @add_tx_ts: validate (if admitted_time is 0) or add a TX TS to the device * with the given parameters; action frame exchange has been handled by * userspace so this just has to modify the TX path to take the TS into * account. * If the admitted time is 0 just validate the parameters to make sure * the session can be created at all; it is valid to just always return * success for that but that may result in inefficient behaviour (handshake * with the peer followed by immediate teardown when the addition is later * rejected) * @del_tx_ts: remove an existing TX TS * * @join_ocb: join the OCB network with the specified parameters * (invoked with the wireless_dev mutex held) * @leave_ocb: leave the current OCB network * (invoked with the wireless_dev mutex held) * * @tdls_channel_switch: Start channel-switching with a TDLS peer. The driver * is responsible for continually initiating channel-switching operations * and returning to the base channel for communication with the AP. * @tdls_cancel_channel_switch: Stop channel-switching with a TDLS peer. Both * peers must be on the base channel when the call completes. * @start_nan: Start the NAN interface. * @stop_nan: Stop the NAN interface. * @add_nan_func: Add a NAN function. Returns negative value on failure. * On success @nan_func ownership is transferred to the driver and * it may access it outside of the scope of this function. The driver * should free the @nan_func when no longer needed by calling * cfg80211_free_nan_func(). * On success the driver should assign an instance_id in the * provided @nan_func. * @del_nan_func: Delete a NAN function. * @nan_change_conf: changes NAN configuration. The changed parameters must * be specified in @changes (using &enum cfg80211_nan_conf_changes); * All other parameters must be ignored. * @nan_set_local_sched: configure the local schedule for NAN. The schedule * consists of an array of %cfg80211_nan_channel and the schedule itself, * in which each entry maps each time slot to the channel on which the * radio should operate on. If the chandef of a NAN channel is not * changed, the channel entry must also remain unchanged. It is the * driver's responsibility to verify this. * @nan_set_peer_sched: configure the peer schedule for NAN. The schedule * consists of an array of %cfg80211_nan_channel and the schedule itself, * in which each entry maps each time slot to a channel on which the * radio should operate on. In addition, it contains more peer's schedule * information such as committed DW, etc. When updating an existing peer * schedule, the full new schedule is provided - partial updates are not * supported, and the new schedule completely replaces the previous one. * * @set_multicast_to_unicast: configure multicast to unicast conversion for BSS * * @get_txq_stats: Get TXQ stats for interface or phy. If wdev is %NULL, this * function should return phy stats, and interface stats otherwise. * * @set_pmk: configure the PMK to be used for offloaded 802.1X 4-Way handshake. * If not deleted through @del_pmk the PMK remains valid until disconnect * upon which the driver should clear it. * (invoked with the wireless_dev mutex held) * @del_pmk: delete the previously configured PMK for the given authenticator. * (invoked with the wireless_dev mutex held) * * @external_auth: indicates result of offloaded authentication processing from * user space * * @tx_control_port: TX a control port frame (EAPoL). The noencrypt parameter * tells the driver that the frame should not be encrypted. * * @get_ftm_responder_stats: Retrieve FTM responder statistics, if available. * Statistics should be cumulative, currently no way to reset is provided. * @start_pmsr: start peer measurement (e.g. FTM) * @abort_pmsr: abort peer measurement * * @update_owe_info: Provide updated OWE info to driver. Driver implementing SME * but offloading OWE processing to the user space will get the updated * DH IE through this interface. * * @probe_mesh_link: Probe direct Mesh peer's link quality by sending data frame * and overrule HWMP path selection algorithm. * @set_tid_config: TID specific configuration, this can be peer or BSS specific * This callback may sleep. * @reset_tid_config: Reset TID specific configuration for the peer, for the * given TIDs. This callback may sleep. * * @set_sar_specs: Update the SAR (TX power) settings. * * @color_change: Initiate a color change. * * @set_fils_aad: Set FILS AAD data to the AP driver so that the driver can use * those to decrypt (Re)Association Request and encrypt (Re)Association * Response frame. * * @set_radar_background: Configure dedicated offchannel chain available for * radar/CAC detection on some hw. This chain can't be used to transmit * or receive frames and it is bounded to a running wdev. * Background radar/CAC detection allows to avoid the CAC downtime * switching to a different channel during CAC detection on the selected * radar channel. * The caller is expected to set chandef pointer to NULL in order to * disable background CAC/radar detection. * @add_link_station: Add a link to a station. * @mod_link_station: Modify a link of a station. * @del_link_station: Remove a link of a station. * * @set_hw_timestamp: Enable/disable HW timestamping of TM/FTM frames. * @set_ttlm: set the TID to link mapping. * @set_epcs: Enable/Disable EPCS for station mode. * @get_radio_mask: get bitmask of radios in use. * (invoked with the wiphy mutex held) * @assoc_ml_reconf: Request a non-AP MLO connection to perform ML * reconfiguration, i.e., add and/or remove links to/from the * association using ML reconfiguration action frames. Successfully added * links will be added to the set of valid links. Successfully removed * links will be removed from the set of valid links. The driver must * indicate removed links by calling cfg80211_links_removed() and added * links by calling cfg80211_mlo_reconf_add_done(). When calling * cfg80211_mlo_reconf_add_done() the bss pointer must be given for each * link for which MLO reconfiguration 'add' operation was requested. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); int (*resume)(struct wiphy *wiphy); void (*set_wakeup)(struct wiphy *wiphy, bool enabled); struct wireless_dev * (*add_virtual_intf)(struct wiphy *wiphy, const char *name, unsigned char name_assign_type, enum nl80211_iftype type, struct vif_params *params); int (*del_virtual_intf)(struct wiphy *wiphy, struct wireless_dev *wdev); int (*change_virtual_intf)(struct wiphy *wiphy, struct net_device *dev, enum nl80211_iftype type, struct vif_params *params); int (*add_intf_link)(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id); void (*del_intf_link)(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id); int (*add_key)(struct wiphy *wiphy, struct wireless_dev *wdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr, struct key_params *params); int (*get_key)(struct wiphy *wiphy, struct wireless_dev *wdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr, void *cookie, void (*callback)(void *cookie, struct key_params*)); int (*del_key)(struct wiphy *wiphy, struct wireless_dev *wdev, int link_id, u8 key_index, bool pairwise, const u8 *mac_addr); int (*set_default_key)(struct wiphy *wiphy, struct net_device *netdev, int link_id, u8 key_index, bool unicast, bool multicast); int (*set_default_mgmt_key)(struct wiphy *wiphy, struct wireless_dev *wdev, int link_id, u8 key_index); int (*set_default_beacon_key)(struct wiphy *wiphy, struct wireless_dev *wdev, int link_id, u8 key_index); int (*start_ap)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_settings *settings); int (*change_beacon)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_update *info); int (*stop_ap)(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id); int (*add_station)(struct wiphy *wiphy, struct wireless_dev *wdev, const u8 *mac, struct station_parameters *params); int (*del_station)(struct wiphy *wiphy, struct wireless_dev *wdev, struct station_del_parameters *params); int (*change_station)(struct wiphy *wiphy, struct wireless_dev *wdev, const u8 *mac, struct station_parameters *params); int (*get_station)(struct wiphy *wiphy, struct wireless_dev *wdev, const u8 *mac, struct station_info *sinfo); int (*dump_station)(struct wiphy *wiphy, struct wireless_dev *wdev, int idx, u8 *mac, struct station_info *sinfo); int (*add_mpath)(struct wiphy *wiphy, struct net_device *dev, const u8 *dst, const u8 *next_hop); int (*del_mpath)(struct wiphy *wiphy, struct net_device *dev, const u8 *dst); int (*change_mpath)(struct wiphy *wiphy, struct net_device *dev, const u8 *dst, const u8 *next_hop); int (*get_mpath)(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *next_hop, struct mpath_info *pinfo); int (*dump_mpath)(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *next_hop, struct mpath_info *pinfo); int (*get_mpp)(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *mpp, struct mpath_info *pinfo); int (*dump_mpp)(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *mpp, struct mpath_info *pinfo); int (*get_mesh_config)(struct wiphy *wiphy, struct net_device *dev, struct mesh_config *conf); int (*update_mesh_config)(struct wiphy *wiphy, struct net_device *dev, u32 mask, const struct mesh_config *nconf); int (*join_mesh)(struct wiphy *wiphy, struct net_device *dev, const struct mesh_config *conf, const struct mesh_setup *setup); int (*leave_mesh)(struct wiphy *wiphy, struct net_device *dev); int (*join_ocb)(struct wiphy *wiphy, struct net_device *dev, struct ocb_setup *setup); int (*leave_ocb)(struct wiphy *wiphy, struct net_device *dev); int (*change_bss)(struct wiphy *wiphy, struct net_device *dev, struct bss_parameters *params); void (*inform_bss)(struct wiphy *wiphy, struct cfg80211_bss *bss, const struct cfg80211_bss_ies *ies, void *data); int (*set_txq_params)(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_txq_params *params); int (*libertas_set_mesh_channel)(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_channel *chan); int (*set_monitor_channel)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef); int (*scan)(struct wiphy *wiphy, struct cfg80211_scan_request *request); void (*abort_scan)(struct wiphy *wiphy, struct wireless_dev *wdev); int (*auth)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_auth_request *req); int (*assoc)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_assoc_request *req); int (*deauth)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_deauth_request *req); int (*disassoc)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_disassoc_request *req); int (*connect)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_connect_params *sme); int (*update_connect_params)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_connect_params *sme, u32 changed); int (*disconnect)(struct wiphy *wiphy, struct net_device *dev, u16 reason_code); int (*join_ibss)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ibss_params *params); int (*leave_ibss)(struct wiphy *wiphy, struct net_device *dev); int (*set_mcast_rate)(struct wiphy *wiphy, struct net_device *dev, int rate[NUM_NL80211_BANDS]); int (*set_wiphy_params)(struct wiphy *wiphy, int radio_idx, u32 changed); int (*set_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev, int radio_idx, enum nl80211_tx_power_setting type, int mbm); int (*get_tx_power)(struct wiphy *wiphy, struct wireless_dev *wdev, int radio_idx, unsigned int link_id, int *dbm); void (*rfkill_poll)(struct wiphy *wiphy); #ifdef CONFIG_NL80211_TESTMODE int (*testmode_cmd)(struct wiphy *wiphy, struct wireless_dev *wdev, void *data, int len); int (*testmode_dump)(struct wiphy *wiphy, struct sk_buff *skb, struct netlink_callback *cb, void *data, int len); #endif int (*set_bitrate_mask)(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id, const u8 *peer, const struct cfg80211_bitrate_mask *mask); int (*dump_survey)(struct wiphy *wiphy, struct net_device *netdev, int idx, struct survey_info *info); int (*set_pmksa)(struct wiphy *wiphy, struct net_device *netdev, struct cfg80211_pmksa *pmksa); int (*del_pmksa)(struct wiphy *wiphy, struct net_device *netdev, struct cfg80211_pmksa *pmksa); int (*flush_pmksa)(struct wiphy *wiphy, struct net_device *netdev); int (*remain_on_channel)(struct wiphy *wiphy, struct wireless_dev *wdev, struct ieee80211_channel *chan, unsigned int duration, u64 *cookie); int (*cancel_remain_on_channel)(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie); int (*mgmt_tx)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_mgmt_tx_params *params, u64 *cookie); int (*mgmt_tx_cancel_wait)(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie); int (*set_power_mgmt)(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout); int (*set_cqm_rssi_config)(struct wiphy *wiphy, struct net_device *dev, s32 rssi_thold, u32 rssi_hyst); int (*set_cqm_rssi_range_config)(struct wiphy *wiphy, struct net_device *dev, s32 rssi_low, s32 rssi_high); int (*set_cqm_txe_config)(struct wiphy *wiphy, struct net_device *dev, u32 rate, u32 pkts, u32 intvl); void (*update_mgmt_frame_registrations)(struct wiphy *wiphy, struct wireless_dev *wdev, struct mgmt_frame_regs *upd); int (*set_antenna)(struct wiphy *wiphy, int radio_idx, u32 tx_ant, u32 rx_ant); int (*get_antenna)(struct wiphy *wiphy, int radio_idx, u32 *tx_ant, u32 *rx_ant); int (*sched_scan_start)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_sched_scan_request *request); int (*sched_scan_stop)(struct wiphy *wiphy, struct net_device *dev, u64 reqid); int (*set_rekey_data)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_gtk_rekey_data *data); int (*tdls_mgmt)(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, int link_id, u8 action_code, u8 dialog_token, u16 status_code, u32 peer_capability, bool initiator, const u8 *buf, size_t len); int (*tdls_oper)(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, enum nl80211_tdls_operation oper); int (*probe_client)(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, u64 *cookie); int (*set_noack_map)(struct wiphy *wiphy, struct net_device *dev, u16 noack_map); int (*get_channel)(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id, struct cfg80211_chan_def *chandef); int (*start_p2p_device)(struct wiphy *wiphy, struct wireless_dev *wdev); void (*stop_p2p_device)(struct wiphy *wiphy, struct wireless_dev *wdev); int (*set_mac_acl)(struct wiphy *wiphy, struct net_device *dev, const struct cfg80211_acl_data *params); int (*start_radar_detection)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef, u32 cac_time_ms, int link_id); void (*end_cac)(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id); int (*update_ft_ies)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_update_ft_ies_params *ftie); int (*crit_proto_start)(struct wiphy *wiphy, struct wireless_dev *wdev, enum nl80211_crit_proto_id protocol, u16 duration); void (*crit_proto_stop)(struct wiphy *wiphy, struct wireless_dev *wdev); int (*set_coalesce)(struct wiphy *wiphy, struct cfg80211_coalesce *coalesce); int (*channel_switch)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params); int (*set_qos_map)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_qos_map *qos_map); int (*set_ap_chanwidth)(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id, struct cfg80211_chan_def *chandef); int (*add_tx_ts)(struct wiphy *wiphy, struct net_device *dev, u8 tsid, const u8 *peer, u8 user_prio, u16 admitted_time); int (*del_tx_ts)(struct wiphy *wiphy, struct net_device *dev, u8 tsid, const u8 *peer); int (*tdls_channel_switch)(struct wiphy *wiphy, struct net_device *dev, const u8 *addr, u8 oper_class, struct cfg80211_chan_def *chandef); void (*tdls_cancel_channel_switch)(struct wiphy *wiphy, struct net_device *dev, const u8 *addr); int (*start_nan)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf); void (*stop_nan)(struct wiphy *wiphy, struct wireless_dev *wdev); int (*add_nan_func)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_func *nan_func); void (*del_nan_func)(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie); int (*nan_change_conf)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf, u32 changes); int (*nan_set_local_sched)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_local_sched *sched); int (*nan_set_peer_sched)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_peer_sched *sched); int (*set_multicast_to_unicast)(struct wiphy *wiphy, struct net_device *dev, const bool enabled); int (*get_txq_stats)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_txq_stats *txqstats); int (*set_pmk)(struct wiphy *wiphy, struct net_device *dev, const struct cfg80211_pmk_conf *conf); int (*del_pmk)(struct wiphy *wiphy, struct net_device *dev, const u8 *aa); int (*external_auth)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_external_auth_params *params); int (*tx_control_port)(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len, const u8 *dest, const __be16 proto, const bool noencrypt, int link_id, u64 *cookie); int (*get_ftm_responder_stats)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ftm_responder_stats *ftm_stats); int (*start_pmsr)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_pmsr_request *request); void (*abort_pmsr)(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_pmsr_request *request); int (*update_owe_info)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_update_owe_info *owe_info); int (*probe_mesh_link)(struct wiphy *wiphy, struct net_device *dev, const u8 *buf, size_t len); int (*set_tid_config)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_tid_config *tid_conf); int (*reset_tid_config)(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, u8 tids); int (*set_sar_specs)(struct wiphy *wiphy, struct cfg80211_sar_specs *sar); int (*color_change)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_color_change_settings *params); int (*set_fils_aad)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_fils_aad *fils_aad); int (*set_radar_background)(struct wiphy *wiphy, struct cfg80211_chan_def *chandef); int (*add_link_station)(struct wiphy *wiphy, struct net_device *dev, struct link_station_parameters *params); int (*mod_link_station)(struct wiphy *wiphy, struct net_device *dev, struct link_station_parameters *params); int (*del_link_station)(struct wiphy *wiphy, struct net_device *dev, struct link_station_del_parameters *params); int (*set_hw_timestamp)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_set_hw_timestamp *hwts); int (*set_ttlm)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ttlm_params *params); u32 (*get_radio_mask)(struct wiphy *wiphy, struct net_device *dev); int (*assoc_ml_reconf)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ml_reconf_req *req); int (*set_epcs)(struct wiphy *wiphy, struct net_device *dev, bool val); }; /* * wireless hardware and networking interfaces structures * and registration/helper functions */ /** * enum wiphy_flags - wiphy capability flags * * @WIPHY_FLAG_SPLIT_SCAN_6GHZ: if set to true, the scan request will be split * into two, first for legacy bands and second for 6 GHz. * @WIPHY_FLAG_NETNS_OK: if not set, do not allow changing the netns of this * wiphy at all * @WIPHY_FLAG_PS_ON_BY_DEFAULT: if set to true, powersave will be enabled * by default -- this flag will be set depending on the kernel's default * on wiphy_new(), but can be changed by the driver if it has a good * reason to override the default * @WIPHY_FLAG_4ADDR_AP: supports 4addr mode even on AP (with a single station * on a VLAN interface). This flag also serves an extra purpose of * supporting 4ADDR AP mode on devices which do not support AP/VLAN iftype. * @WIPHY_FLAG_4ADDR_STATION: supports 4addr mode even as a station * @WIPHY_FLAG_CONTROL_PORT_PROTOCOL: This device supports setting the * control port protocol ethertype. The device also honours the * control_port_no_encrypt flag. * @WIPHY_FLAG_IBSS_RSN: The device supports IBSS RSN. * @WIPHY_FLAG_MESH_AUTH: The device supports mesh authentication by routing * auth frames to userspace. See @NL80211_MESH_SETUP_USERSPACE_AUTH. * @WIPHY_FLAG_SUPPORTS_FW_ROAM: The device supports roaming feature in the * firmware. * @WIPHY_FLAG_AP_UAPSD: The device supports uapsd on AP. * @WIPHY_FLAG_SUPPORTS_TDLS: The device supports TDLS (802.11z) operation. * @WIPHY_FLAG_TDLS_EXTERNAL_SETUP: The device does not handle TDLS (802.11z) * link setup/discovery operations internally. Setup, discovery and * teardown packets should be sent through the @NL80211_CMD_TDLS_MGMT * command. When this flag is not set, @NL80211_CMD_TDLS_OPER should be * used for asking the driver/firmware to perform a TDLS operation. * @WIPHY_FLAG_HAVE_AP_SME: device integrates AP SME * @WIPHY_FLAG_REPORTS_OBSS: the device will report beacons from other BSSes * when there are virtual interfaces in AP mode by calling * cfg80211_report_obss_beacon(). * @WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD: When operating as an AP, the device * responds to probe-requests in hardware. * @WIPHY_FLAG_OFFCHAN_TX: Device supports direct off-channel TX. * @WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL: Device supports remain-on-channel call. * @WIPHY_FLAG_SUPPORTS_5_10_MHZ: Device supports 5 MHz and 10 MHz channels. * @WIPHY_FLAG_HAS_CHANNEL_SWITCH: Device supports channel switch in * beaconing mode (AP, IBSS, Mesh, ...). * @WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK: The device supports bigger kek and kck keys * @WIPHY_FLAG_SUPPORTS_MLO: This is a temporary flag gating the MLO APIs, * in order to not have them reachable in normal drivers, until we have * complete feature/interface combinations/etc. advertisement. No driver * should set this flag for now. * @WIPHY_FLAG_SUPPORTS_EXT_KCK_32: The device supports 32-byte KCK keys. * @WIPHY_FLAG_NOTIFY_REGDOM_BY_DRIVER: The device could handle reg notify for * NL80211_REGDOM_SET_BY_DRIVER. * @WIPHY_FLAG_CHANNEL_CHANGE_ON_BEACON: reg_call_notifier() is called if driver * set this flag to update channels on beacon hints. * @WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY: support connection to non-primary link * of an NSTR mobile AP MLD. * @WIPHY_FLAG_DISABLE_WEXT: disable wireless extensions for this device */ enum wiphy_flags { WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK = BIT(0), WIPHY_FLAG_SUPPORTS_MLO = BIT(1), WIPHY_FLAG_SPLIT_SCAN_6GHZ = BIT(2), WIPHY_FLAG_NETNS_OK = BIT(3), WIPHY_FLAG_PS_ON_BY_DEFAULT = BIT(4), WIPHY_FLAG_4ADDR_AP = BIT(5), WIPHY_FLAG_4ADDR_STATION = BIT(6), WIPHY_FLAG_CONTROL_PORT_PROTOCOL = BIT(7), WIPHY_FLAG_IBSS_RSN = BIT(8), WIPHY_FLAG_DISABLE_WEXT = BIT(9), WIPHY_FLAG_MESH_AUTH = BIT(10), WIPHY_FLAG_SUPPORTS_EXT_KCK_32 = BIT(11), WIPHY_FLAG_SUPPORTS_NSTR_NONPRIMARY = BIT(12), WIPHY_FLAG_SUPPORTS_FW_ROAM = BIT(13), WIPHY_FLAG_AP_UAPSD = BIT(14), WIPHY_FLAG_SUPPORTS_TDLS = BIT(15), WIPHY_FLAG_TDLS_EXTERNAL_SETUP = BIT(16), WIPHY_FLAG_HAVE_AP_SME = BIT(17), WIPHY_FLAG_REPORTS_OBSS = BIT(18), WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD = BIT(19), WIPHY_FLAG_OFFCHAN_TX = BIT(20), WIPHY_FLAG_HAS_REMAIN_ON_CHANNEL = BIT(21), WIPHY_FLAG_SUPPORTS_5_10_MHZ = BIT(22), WIPHY_FLAG_HAS_CHANNEL_SWITCH = BIT(23), WIPHY_FLAG_NOTIFY_REGDOM_BY_DRIVER = BIT(24), WIPHY_FLAG_CHANNEL_CHANGE_ON_BEACON = BIT(25), }; /** * struct ieee80211_iface_limit - limit on certain interface types * @max: maximum number of interfaces of these types * @types: interface types (bits) */ struct ieee80211_iface_limit { u16 max; u16 types; }; /** * struct ieee80211_iface_combination - possible interface combination * * With this structure the driver can describe which interface * combinations it supports concurrently. When set in a struct wiphy_radio, * the combinations refer to combinations of interfaces currently active on * that radio. * * Examples: * * 1. Allow #STA <= 1, #AP <= 1, matching BI, channels = 1, 2 total: * * .. code-block:: c * * struct ieee80211_iface_limit limits1[] = { * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), }, * { .max = 1, .types = BIT(NL80211_IFTYPE_AP), }, * }; * struct ieee80211_iface_combination combination1 = { * .limits = limits1, * .n_limits = ARRAY_SIZE(limits1), * .max_interfaces = 2, * .beacon_int_infra_match = true, * }; * * * 2. Allow #{AP, P2P-GO} <= 8, channels = 1, 8 total: * * .. code-block:: c * * struct ieee80211_iface_limit limits2[] = { * { .max = 8, .types = BIT(NL80211_IFTYPE_AP) | * BIT(NL80211_IFTYPE_P2P_GO), }, * }; * struct ieee80211_iface_combination combination2 = { * .limits = limits2, * .n_limits = ARRAY_SIZE(limits2), * .max_interfaces = 8, * .num_different_channels = 1, * }; * * * 3. Allow #STA <= 1, #{P2P-client,P2P-GO} <= 3 on two channels, 4 total. * * This allows for an infrastructure connection and three P2P connections. * * .. code-block:: c * * struct ieee80211_iface_limit limits3[] = { * { .max = 1, .types = BIT(NL80211_IFTYPE_STATION), }, * { .max = 3, .types = BIT(NL80211_IFTYPE_P2P_GO) | * BIT(NL80211_IFTYPE_P2P_CLIENT), }, * }; * struct ieee80211_iface_combination combination3 = { * .limits = limits3, * .n_limits = ARRAY_SIZE(limits3), * .max_interfaces = 4, * .num_different_channels = 2, * }; * */ struct ieee80211_iface_combination { /** * @limits: * limits for the given interface types */ const struct ieee80211_iface_limit *limits; /** * @num_different_channels: * can use up to this many different channels */ u32 num_different_channels; /** * @max_interfaces: * maximum number of interfaces in total allowed in this group */ u16 max_interfaces; /** * @n_limits: * number of limitations */ u8 n_limits; /** * @beacon_int_infra_match: * In this combination, the beacon intervals between infrastructure * and AP types must match. This is required only in special cases. */ bool beacon_int_infra_match; /** * @radar_detect_widths: * bitmap of channel widths supported for radar detection */ u8 radar_detect_widths; /** * @radar_detect_regions: * bitmap of regions supported for radar detection */ u8 radar_detect_regions; /** * @beacon_int_min_gcd: * This interface combination supports different beacon intervals. * * = 0 * all beacon intervals for different interface must be same. * > 0 * any beacon interval for the interface part of this combination AND * GCD of all beacon intervals from beaconing interfaces of this * combination must be greater or equal to this value. */ u32 beacon_int_min_gcd; }; struct ieee80211_txrx_stypes { u16 tx, rx; }; /** * enum wiphy_wowlan_support_flags - WoWLAN support flags * @WIPHY_WOWLAN_ANY: supports wakeup for the special "any" * trigger that keeps the device operating as-is and * wakes up the host on any activity, for example a * received packet that passed filtering; note that the * packet should be preserved in that case * @WIPHY_WOWLAN_MAGIC_PKT: supports wakeup on magic packet * (see nl80211.h) * @WIPHY_WOWLAN_DISCONNECT: supports wakeup on disconnect * @WIPHY_WOWLAN_SUPPORTS_GTK_REKEY: supports GTK rekeying while asleep * @WIPHY_WOWLAN_GTK_REKEY_FAILURE: supports wakeup on GTK rekey failure * @WIPHY_WOWLAN_EAP_IDENTITY_REQ: supports wakeup on EAP identity request * @WIPHY_WOWLAN_4WAY_HANDSHAKE: supports wakeup on 4-way handshake failure * @WIPHY_WOWLAN_RFKILL_RELEASE: supports wakeup on RF-kill release * @WIPHY_WOWLAN_NET_DETECT: supports wakeup on network detection */ enum wiphy_wowlan_support_flags { WIPHY_WOWLAN_ANY = BIT(0), WIPHY_WOWLAN_MAGIC_PKT = BIT(1), WIPHY_WOWLAN_DISCONNECT = BIT(2), WIPHY_WOWLAN_SUPPORTS_GTK_REKEY = BIT(3), WIPHY_WOWLAN_GTK_REKEY_FAILURE = BIT(4), WIPHY_WOWLAN_EAP_IDENTITY_REQ = BIT(5), WIPHY_WOWLAN_4WAY_HANDSHAKE = BIT(6), WIPHY_WOWLAN_RFKILL_RELEASE = BIT(7), WIPHY_WOWLAN_NET_DETECT = BIT(8), }; struct wiphy_wowlan_tcp_support { const struct nl80211_wowlan_tcp_data_token_feature *tok; u32 data_payload_max; u32 data_interval_max; u32 wake_payload_max; bool seq; }; /** * struct wiphy_wowlan_support - WoWLAN support data * @flags: see &enum wiphy_wowlan_support_flags * @n_patterns: number of supported wakeup patterns * (see nl80211.h for the pattern definition) * @pattern_max_len: maximum length of each pattern * @pattern_min_len: minimum length of each pattern * @max_pkt_offset: maximum Rx packet offset * @max_nd_match_sets: maximum number of matchsets for net-detect, * similar, but not necessarily identical, to max_match_sets for * scheduled scans. * See &struct cfg80211_sched_scan_request.@match_sets for more * details. * @tcp: TCP wakeup support information */ struct wiphy_wowlan_support { u32 flags; int n_patterns; int pattern_max_len; int pattern_min_len; int max_pkt_offset; int max_nd_match_sets; const struct wiphy_wowlan_tcp_support *tcp; }; /** * struct wiphy_coalesce_support - coalesce support data * @n_rules: maximum number of coalesce rules * @max_delay: maximum supported coalescing delay in msecs * @n_patterns: number of supported patterns in a rule * (see nl80211.h for the pattern definition) * @pattern_max_len: maximum length of each pattern * @pattern_min_len: minimum length of each pattern * @max_pkt_offset: maximum Rx packet offset */ struct wiphy_coalesce_support { int n_rules; int max_delay; int n_patterns; int pattern_max_len; int pattern_min_len; int max_pkt_offset; }; /** * enum wiphy_vendor_command_flags - validation flags for vendor commands * @WIPHY_VENDOR_CMD_NEED_WDEV: vendor command requires wdev * @WIPHY_VENDOR_CMD_NEED_NETDEV: vendor command requires netdev * @WIPHY_VENDOR_CMD_NEED_RUNNING: interface/wdev must be up & running * (must be combined with %_WDEV or %_NETDEV) */ enum wiphy_vendor_command_flags { WIPHY_VENDOR_CMD_NEED_WDEV = BIT(0), WIPHY_VENDOR_CMD_NEED_NETDEV = BIT(1), WIPHY_VENDOR_CMD_NEED_RUNNING = BIT(2), }; /** * enum wiphy_opmode_flag - Station's ht/vht operation mode information flags * * @STA_OPMODE_MAX_BW_CHANGED: Max Bandwidth changed * @STA_OPMODE_SMPS_MODE_CHANGED: SMPS mode changed * @STA_OPMODE_N_SS_CHANGED: max N_SS (number of spatial streams) changed * */ enum wiphy_opmode_flag { STA_OPMODE_MAX_BW_CHANGED = BIT(0), STA_OPMODE_SMPS_MODE_CHANGED = BIT(1), STA_OPMODE_N_SS_CHANGED = BIT(2), }; /** * struct sta_opmode_info - Station's ht/vht operation mode information * @changed: contains value from &enum wiphy_opmode_flag * @smps_mode: New SMPS mode value from &enum nl80211_smps_mode of a station * @bw: new max bandwidth value from &enum nl80211_chan_width of a station * @rx_nss: new rx_nss value of a station */ struct sta_opmode_info { u32 changed; enum nl80211_smps_mode smps_mode; enum nl80211_chan_width bw; u8 rx_nss; }; #define VENDOR_CMD_RAW_DATA ((const struct nla_policy *)(long)(-ENODATA)) /** * struct wiphy_vendor_command - vendor command definition * @info: vendor command identifying information, as used in nl80211 * @flags: flags, see &enum wiphy_vendor_command_flags * @doit: callback for the operation, note that wdev is %NULL if the * flags didn't ask for a wdev and non-%NULL otherwise; the data * pointer may be %NULL if userspace provided no data at all * @dumpit: dump callback, for transferring bigger/multiple items. The * @storage points to cb->args[5], ie. is preserved over the multiple * dumpit calls. * @policy: policy pointer for attributes within %NL80211_ATTR_VENDOR_DATA. * Set this to %VENDOR_CMD_RAW_DATA if no policy can be given and the * attribute is just raw data (e.g. a firmware command). * @maxattr: highest attribute number in policy * It's recommended to not have the same sub command with both @doit and * @dumpit, so that userspace can assume certain ones are get and others * are used with dump requests. */ struct wiphy_vendor_command { struct nl80211_vendor_cmd_info info; u32 flags; int (*doit)(struct wiphy *wiphy, struct wireless_dev *wdev, const void *data, int data_len); int (*dumpit)(struct wiphy *wiphy, struct wireless_dev *wdev, struct sk_buff *skb, const void *data, int data_len, unsigned long *storage); const struct nla_policy *policy; unsigned int maxattr; }; /** * struct wiphy_iftype_ext_capab - extended capabilities per interface type * @iftype: interface type * @extended_capabilities: extended capabilities supported by the driver, * additional capabilities might be supported by userspace; these are the * 802.11 extended capabilities ("Extended Capabilities element") and are * in the same format as in the information element. See IEEE Std * 802.11-2012 8.4.2.29 for the defined fields. * @extended_capabilities_mask: mask of the valid values * @extended_capabilities_len: length of the extended capabilities * @eml_capabilities: EML capabilities (for MLO) * @mld_capa_and_ops: MLD capabilities and operations (for MLO) */ struct wiphy_iftype_ext_capab { enum nl80211_iftype iftype; const u8 *extended_capabilities; const u8 *extended_capabilities_mask; u8 extended_capabilities_len; u16 eml_capabilities; u16 mld_capa_and_ops; }; /** * cfg80211_get_iftype_ext_capa - lookup interface type extended capability * @wiphy: the wiphy to look up from * @type: the interface type to look up * * Return: The extended capability for the given interface @type, may be %NULL */ const struct wiphy_iftype_ext_capab * cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type); /** * struct cfg80211_pmsr_capabilities - cfg80211 peer measurement capabilities * @max_peers: maximum number of peers in a single measurement * @report_ap_tsf: can report assoc AP's TSF for radio resource measurement * @randomize_mac_addr: can randomize MAC address for measurement * @ftm: FTM measurement data * @ftm.supported: FTM measurement is supported * @ftm.asap: ASAP-mode is supported * @ftm.non_asap: non-ASAP-mode is supported * @ftm.request_lci: can request LCI data * @ftm.request_civicloc: can request civic location data * @ftm.preambles: bitmap of preambles supported (&enum nl80211_preamble) * @ftm.bandwidths: bitmap of bandwidths supported (&enum nl80211_chan_width) * @ftm.max_bursts_exponent: maximum burst exponent supported * (set to -1 if not limited; note that setting this will necessarily * forbid using the value 15 to let the responder pick) * @ftm.max_ftms_per_burst: maximum FTMs per burst supported (set to 0 if * not limited) * @ftm.trigger_based: trigger based ranging measurement is supported * @ftm.non_trigger_based: non trigger based ranging measurement is supported * @ftm.support_6ghz: supports ranging in 6 GHz band * @ftm.max_tx_ltf_rep: maximum number of TX LTF repetitions supported (0 means * only one LTF, no repetitions) * @ftm.max_rx_ltf_rep: maximum number of RX LTF repetitions supported (0 means * only one LTF, no repetitions) * @ftm.max_tx_sts: maximum number of TX STS supported (zero based) * @ftm.max_rx_sts: maximum number of RX STS supported (zero based) * @ftm.max_total_ltf_tx: maximum total number of LTFs that can be transmitted * (0 means unknown) * @ftm.max_total_ltf_rx: maximum total number of LTFs that can be received * (0 means unknown) * @ftm.support_rsta: supports operating as RSTA in PMSR FTM request */ struct cfg80211_pmsr_capabilities { unsigned int max_peers; u8 report_ap_tsf:1, randomize_mac_addr:1; struct { u32 preambles; u32 bandwidths; s8 max_bursts_exponent; u8 max_ftms_per_burst; u8 supported:1, asap:1, non_asap:1, request_lci:1, request_civicloc:1, trigger_based:1, non_trigger_based:1, support_6ghz:1; u8 max_tx_ltf_rep; u8 max_rx_ltf_rep; u8 max_tx_sts; u8 max_rx_sts; u8 max_total_ltf_tx; u8 max_total_ltf_rx; u8 support_rsta:1; } ftm; }; /** * struct wiphy_iftype_akm_suites - This structure encapsulates supported akm * suites for interface types defined in @iftypes_mask. Each type in the * @iftypes_mask must be unique across all instances of iftype_akm_suites. * * @iftypes_mask: bitmask of interfaces types * @akm_suites: points to an array of supported akm suites * @n_akm_suites: number of supported AKM suites */ struct wiphy_iftype_akm_suites { u16 iftypes_mask; const u32 *akm_suites; int n_akm_suites; }; /** * struct wiphy_radio_cfg - physical radio config of a wiphy * This structure describes the configurations of a physical radio in a * wiphy. It is used to denote per-radio attributes belonging to a wiphy. * * @rts_threshold: RTS threshold (dot11RTSThreshold); * -1 (default) = RTS/CTS disabled * @radio_debugfsdir: Pointer to debugfs directory containing the radio- * specific parameters. * NULL (default) = Debugfs directory not created */ struct wiphy_radio_cfg { u32 rts_threshold; struct dentry *radio_debugfsdir; }; /** * struct wiphy_radio_freq_range - wiphy frequency range * @start_freq: start range edge frequency (kHz) * @end_freq: end range edge frequency (kHz) */ struct wiphy_radio_freq_range { u32 start_freq; u32 end_freq; }; /** * struct wiphy_radio - physical radio of a wiphy * This structure describes a physical radio belonging to a wiphy. * It is used to describe concurrent-channel capabilities. Only one channel * can be active on the radio described by struct wiphy_radio. * * @freq_range: frequency range that the radio can operate on. * @n_freq_range: number of elements in @freq_range * * @iface_combinations: Valid interface combinations array, should not * list single interface types. * @n_iface_combinations: number of entries in @iface_combinations array. * * @antenna_mask: bitmask of antennas connected to this radio. */ struct wiphy_radio { const struct wiphy_radio_freq_range *freq_range; int n_freq_range; const struct ieee80211_iface_combination *iface_combinations; int n_iface_combinations; u32 antenna_mask; }; /** * enum wiphy_nan_flags - NAN capabilities * * @WIPHY_NAN_FLAGS_CONFIGURABLE_SYNC: Device supports NAN configurable * synchronization. * @WIPHY_NAN_FLAGS_USERSPACE_DE: Device doesn't support DE offload. */ enum wiphy_nan_flags { WIPHY_NAN_FLAGS_CONFIGURABLE_SYNC = BIT(0), WIPHY_NAN_FLAGS_USERSPACE_DE = BIT(1), }; /** * struct wiphy_nan_capa - NAN capabilities * * This structure describes the NAN capabilities of a wiphy. * * @flags: NAN capabilities flags, see &enum wiphy_nan_flags * @op_mode: NAN operation mode, as defined in Wi-Fi Aware (TM) specification * Table 81. * @n_antennas: number of antennas supported by the device for Tx/Rx. Lower * nibble indicates the number of TX antennas and upper nibble indicates the * number of RX antennas. Value 0 indicates the information is not * available. * @max_channel_switch_time: maximum channel switch time in milliseconds. * @dev_capabilities: NAN device capabilities as defined in Wi-Fi Aware (TM) * specification Table 79 (Capabilities field). * @phy: Band-agnostic capabilities for NAN data interfaces. Since NAN * operates on multiple channels simultaneously, these capabilities apply * across all bands. Valid only if NL80211_IFTYPE_NAN_DATA is supported. * @phy.ht: HT capabilities (mandatory for NAN data) * @phy.vht: VHT capabilities (optional) * @phy.he: HE capabilities (optional) */ struct wiphy_nan_capa { u32 flags; u8 op_mode; u8 n_antennas; u16 max_channel_switch_time; u8 dev_capabilities; struct { struct ieee80211_sta_ht_cap ht; struct ieee80211_sta_vht_cap vht; struct ieee80211_sta_he_cap he; } phy; }; #define CFG80211_HW_TIMESTAMP_ALL_PEERS 0xffff /** * struct wiphy - wireless hardware description * @mtx: mutex for the data (structures) of this device * @reg_notifier: the driver's regulatory notification callback, * note that if your driver uses wiphy_apply_custom_regulatory() * the reg_notifier's request can be passed as NULL * @regd: the driver's regulatory domain, if one was requested via * the regulatory_hint() API. This can be used by the driver * on the reg_notifier() if it chooses to ignore future * regulatory domain changes caused by other drivers. * @signal_type: signal type reported in &struct cfg80211_bss. * @cipher_suites: supported cipher suites * @n_cipher_suites: number of supported cipher suites * @akm_suites: supported AKM suites. These are the default AKMs supported if * the supported AKMs not advertized for a specific interface type in * iftype_akm_suites. * @n_akm_suites: number of supported AKM suites * @iftype_akm_suites: array of supported akm suites info per interface type. * Note that the bits in @iftypes_mask inside this structure cannot * overlap (i.e. only one occurrence of each type is allowed across all * instances of iftype_akm_suites). * @num_iftype_akm_suites: number of interface types for which supported akm * suites are specified separately. * @retry_short: Retry limit for short frames (dot11ShortRetryLimit) * @retry_long: Retry limit for long frames (dot11LongRetryLimit) * @frag_threshold: Fragmentation threshold (dot11FragmentationThreshold); * -1 = fragmentation disabled, only odd values >= 256 used * @rts_threshold: RTS threshold (dot11RTSThreshold); -1 = RTS/CTS disabled * @_net: the network namespace this wiphy currently lives in * @perm_addr: permanent MAC address of this device * @addr_mask: If the device supports multiple MAC addresses by masking, * set this to a mask with variable bits set to 1, e.g. if the last * four bits are variable then set it to 00-00-00-00-00-0f. The actual * variable bits shall be determined by the interfaces added, with * interfaces not matching the mask being rejected to be brought up. * @n_addresses: number of addresses in @addresses. * @addresses: If the device has more than one address, set this pointer * to a list of addresses (6 bytes each). The first one will be used * by default for perm_addr. In this case, the mask should be set to * all-zeroes. In this case it is assumed that the device can handle * the same number of arbitrary MAC addresses. * @registered: protects ->resume and ->suspend sysfs callbacks against * unregister hardware * @debugfsdir: debugfs directory used for this wiphy (ieee80211/<wiphyname>). * It will be renamed automatically on wiphy renames * @dev: (virtual) struct device for this wiphy. The item in * /sys/class/ieee80211/ points to this. You need use set_wiphy_dev() * (see below). * @wext: wireless extension handlers * @priv: driver private data (sized according to wiphy_new() parameter) * @interface_modes: bitmask of interfaces types valid for this wiphy, * must be set by driver * @iface_combinations: Valid interface combinations array, should not * list single interface types. * @n_iface_combinations: number of entries in @iface_combinations array. * @software_iftypes: bitmask of software interface types, these are not * subject to any restrictions since they are purely managed in SW. * @flags: wiphy flags, see &enum wiphy_flags * @regulatory_flags: wiphy regulatory flags, see * &enum ieee80211_regulatory_flags * @features: features advertised to nl80211, see &enum nl80211_feature_flags. * @ext_features: extended features advertised to nl80211, see * &enum nl80211_ext_feature_index. * @bss_priv_size: each BSS struct has private data allocated with it, * this variable determines its size * @max_scan_ssids: maximum number of SSIDs the device can scan for in * any given scan * @max_sched_scan_reqs: maximum number of scheduled scan requests that * the device can run concurrently. * @max_sched_scan_ssids: maximum number of SSIDs the device can scan * for in any given scheduled scan * @max_match_sets: maximum number of match sets the device can handle * when performing a scheduled scan, 0 if filtering is not * supported. * @max_scan_ie_len: maximum length of user-controlled IEs device can * add to probe request frames transmitted during a scan, must not * include fixed IEs like supported rates * @max_sched_scan_ie_len: same as max_scan_ie_len, but for scheduled * scans * @max_sched_scan_plans: maximum number of scan plans (scan interval and number * of iterations) for scheduled scan supported by the device. * @max_sched_scan_plan_interval: maximum interval (in seconds) for a * single scan plan supported by the device. * @max_sched_scan_plan_iterations: maximum number of iterations for a single * scan plan supported by the device. * @coverage_class: current coverage class * @fw_version: firmware version for ethtool reporting * @hw_version: hardware version for ethtool reporting * @max_num_pmkids: maximum number of PMKIDs supported by device * @privid: a pointer that drivers can use to identify if an arbitrary * wiphy is theirs, e.g. in global notifiers * @bands: information about bands/channels supported by this device * * @mgmt_stypes: bitmasks of frame subtypes that can be subscribed to or * transmitted through nl80211, points to an array indexed by interface * type * * @available_antennas_tx: bitmap of antennas which are available to be * configured as TX antennas. Antenna configuration commands will be * rejected unless this or @available_antennas_rx is set. * * @available_antennas_rx: bitmap of antennas which are available to be * configured as RX antennas. Antenna configuration commands will be * rejected unless this or @available_antennas_tx is set. * * @probe_resp_offload: * Bitmap of supported protocols for probe response offloading. * See &enum nl80211_probe_resp_offload_support_attr. Only valid * when the wiphy flag @WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD is set. * * @max_remain_on_channel_duration: Maximum time a remain-on-channel operation * may request, if implemented. * * @wowlan: WoWLAN support information * @wowlan_config: current WoWLAN configuration; this should usually not be * used since access to it is necessarily racy, use the parameter passed * to the suspend() operation instead. * * @ap_sme_capa: AP SME capabilities, flags from &enum nl80211_ap_sme_features. * @ht_capa_mod_mask: Specify what ht_cap values can be over-ridden. * If null, then none can be over-ridden. * @vht_capa_mod_mask: Specify what VHT capabilities can be over-ridden. * If null, then none can be over-ridden. * * @wdev_list: the list of associated (virtual) interfaces; this list must * not be modified by the driver, but can be read with RTNL/RCU protection. * * @max_acl_mac_addrs: Maximum number of MAC addresses that the device * supports for ACL. * * @extended_capabilities: extended capabilities supported by the driver, * additional capabilities might be supported by userspace; these are * the 802.11 extended capabilities ("Extended Capabilities element") * and are in the same format as in the information element. See * 802.11-2012 8.4.2.29 for the defined fields. These are the default * extended capabilities to be used if the capabilities are not specified * for a specific interface type in iftype_ext_capab. * @extended_capabilities_mask: mask of the valid values * @extended_capabilities_len: length of the extended capabilities * @iftype_ext_capab: array of extended capabilities per interface type * @num_iftype_ext_capab: number of interface types for which extended * capabilities are specified separately. * @coalesce: packet coalescing support information * * @vendor_commands: array of vendor commands supported by the hardware * @n_vendor_commands: number of vendor commands * @vendor_events: array of vendor events supported by the hardware * @n_vendor_events: number of vendor events * * @max_ap_assoc_sta: maximum number of associated stations supported in AP mode * (including P2P GO) or 0 to indicate no such limit is advertised. The * driver is allowed to advertise a theoretical limit that it can reach in * some cases, but may not always reach. * * @max_num_csa_counters: Number of supported csa_counters in beacons * and probe responses. This value should be set if the driver * wishes to limit the number of csa counters. Default (0) means * infinite. * @bss_param_support: bitmask indicating which bss_parameters as defined in * &struct bss_parameters the driver can actually handle in the * .change_bss() callback. The bit positions are defined in &enum * wiphy_bss_param_flags. * * @bss_select_support: bitmask indicating the BSS selection criteria supported * by the driver in the .connect() callback. The bit position maps to the * attribute indices defined in &enum nl80211_bss_select_attr. * * @nan_supported_bands: bands supported by the device in NAN mode, a * bitmap of &enum nl80211_band values. For instance, for * NL80211_BAND_2GHZ, bit 0 would be set * (i.e. BIT(NL80211_BAND_2GHZ)). * @nan_capa: NAN capabilities * * @txq_limit: configuration of internal TX queue frame limit * @txq_memory_limit: configuration internal TX queue memory limit * @txq_quantum: configuration of internal TX queue scheduler quantum * * @tx_queue_len: allow setting transmit queue len for drivers not using * wake_tx_queue * * @support_mbssid: can HW support association with nontransmitted AP * @support_only_he_mbssid: don't parse MBSSID elements if it is not * HE AP, in order to avoid compatibility issues. * @support_mbssid must be set for this to have any effect. * * @pmsr_capa: peer measurement capabilities * * @tid_config_support: describes the per-TID config support that the * device has * @tid_config_support.vif: bitmap of attributes (configurations) * supported by the driver for each vif * @tid_config_support.peer: bitmap of attributes (configurations) * supported by the driver for each peer * @tid_config_support.max_retry: maximum supported retry count for * long/short retry configuration * * @max_data_retry_count: maximum supported per TID retry count for * configuration through the %NL80211_TID_CONFIG_ATTR_RETRY_SHORT and * %NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes * @sar_capa: SAR control capabilities * @rfkill: a pointer to the rfkill structure * * @mbssid_max_interfaces: maximum number of interfaces supported by the driver * in a multiple BSSID set. This field must be set to a non-zero value * by the driver to advertise MBSSID support. * @ema_max_profile_periodicity: maximum profile periodicity supported by * the driver. Setting this field to a non-zero value indicates that the * driver supports enhanced multi-BSSID advertisements (EMA AP). * @max_num_akm_suites: maximum number of AKM suites allowed for * configuration through %NL80211_CMD_CONNECT, %NL80211_CMD_ASSOCIATE and * %NL80211_CMD_START_AP. Set to NL80211_MAX_NR_AKM_SUITES if not set by * driver. If set by driver minimum allowed value is * NL80211_MAX_NR_AKM_SUITES in order to avoid compatibility issues with * legacy userspace and maximum allowed value is * CFG80211_MAX_NUM_AKM_SUITES. * * @hw_timestamp_max_peers: maximum number of peers that the driver supports * enabling HW timestamping for concurrently. Setting this field to a * non-zero value indicates that the driver supports HW timestamping. * A value of %CFG80211_HW_TIMESTAMP_ALL_PEERS indicates the driver * supports enabling HW timestamping for all peers (i.e. no need to * specify a mac address). * * @radio_cfg: configuration of radios belonging to a muli-radio wiphy. This * struct contains a list of all radio specific attributes and should be * used only for multi-radio wiphy. * * @radio: radios belonging to this wiphy * @n_radio: number of radios */ struct wiphy { struct mutex mtx; /* assign these fields before you register the wiphy */ u8 perm_addr[ETH_ALEN]; u8 addr_mask[ETH_ALEN]; struct mac_address *addresses; const struct ieee80211_txrx_stypes *mgmt_stypes; const struct ieee80211_iface_combination *iface_combinations; int n_iface_combinations; u16 software_iftypes; u16 n_addresses; /* Supported interface modes, OR together BIT(NL80211_IFTYPE_...) */ u16 interface_modes; u16 max_acl_mac_addrs; u32 flags, regulatory_flags, features; u8 ext_features[DIV_ROUND_UP(NUM_NL80211_EXT_FEATURES, 8)]; u32 ap_sme_capa; enum cfg80211_signal_type signal_type; int bss_priv_size; u8 max_scan_ssids; u8 max_sched_scan_reqs; u8 max_sched_scan_ssids; u8 max_match_sets; u16 max_scan_ie_len; u16 max_sched_scan_ie_len; u32 max_sched_scan_plans; u32 max_sched_scan_plan_interval; u32 max_sched_scan_plan_iterations; int n_cipher_suites; const u32 *cipher_suites; int n_akm_suites; const u32 *akm_suites; const struct wiphy_iftype_akm_suites *iftype_akm_suites; unsigned int num_iftype_akm_suites; u8 retry_short; u8 retry_long; u32 frag_threshold; u32 rts_threshold; u8 coverage_class; char fw_version[ETHTOOL_FWVERS_LEN]; u32 hw_version; #ifdef CONFIG_PM const struct wiphy_wowlan_support *wowlan; struct cfg80211_wowlan *wowlan_config; #endif u16 max_remain_on_channel_duration; u8 max_num_pmkids; u32 available_antennas_tx; u32 available_antennas_rx; u32 probe_resp_offload; const u8 *extended_capabilities, *extended_capabilities_mask; u8 extended_capabilities_len; const struct wiphy_iftype_ext_capab *iftype_ext_capab; unsigned int num_iftype_ext_capab; const void *privid; struct ieee80211_supported_band *bands[NUM_NL80211_BANDS]; void (*reg_notifier)(struct wiphy *wiphy, struct regulatory_request *request); struct wiphy_radio_cfg *radio_cfg; /* fields below are read-only, assigned by cfg80211 */ const struct ieee80211_regdomain __rcu *regd; struct device dev; bool registered; struct dentry *debugfsdir; const struct ieee80211_ht_cap *ht_capa_mod_mask; const struct ieee80211_vht_cap *vht_capa_mod_mask; struct list_head wdev_list; possible_net_t _net; #ifdef CONFIG_CFG80211_WEXT const struct iw_handler_def *wext; #endif const struct wiphy_coalesce_support *coalesce; const struct wiphy_vendor_command *vendor_commands; const struct nl80211_vendor_cmd_info *vendor_events; int n_vendor_commands, n_vendor_events; u16 max_ap_assoc_sta; u8 max_num_csa_counters; u32 bss_param_support; u32 bss_select_support; u8 nan_supported_bands; struct wiphy_nan_capa nan_capa; u32 txq_limit; u32 txq_memory_limit; u32 txq_quantum; unsigned long tx_queue_len; u8 support_mbssid:1, support_only_he_mbssid:1; const struct cfg80211_pmsr_capabilities *pmsr_capa; struct { u64 peer, vif; u8 max_retry; } tid_config_support; u8 max_data_retry_count; const struct cfg80211_sar_capa *sar_capa; struct rfkill *rfkill; u8 mbssid_max_interfaces; u8 ema_max_profile_periodicity; u16 max_num_akm_suites; u16 hw_timestamp_max_peers; int n_radio; const struct wiphy_radio *radio; char priv[] __aligned(NETDEV_ALIGN); }; static inline struct net *wiphy_net(struct wiphy *wiphy) { return read_pnet(&wiphy->_net); } static inline void wiphy_net_set(struct wiphy *wiphy, struct net *net) { write_pnet(&wiphy->_net, net); } /** * wiphy_priv - return priv from wiphy * * @wiphy: the wiphy whose priv pointer to return * Return: The priv of @wiphy. */ static inline void *wiphy_priv(struct wiphy *wiphy) { BUG_ON(!wiphy); return &wiphy->priv; } /** * priv_to_wiphy - return the wiphy containing the priv * * @priv: a pointer previously returned by wiphy_priv * Return: The wiphy of @priv. */ static inline struct wiphy *priv_to_wiphy(void *priv) { BUG_ON(!priv); return container_of(priv, struct wiphy, priv); } /** * set_wiphy_dev - set device pointer for wiphy * * @wiphy: The wiphy whose device to bind * @dev: The device to parent it to */ static inline void set_wiphy_dev(struct wiphy *wiphy, struct device *dev) { wiphy->dev.parent = dev; } /** * wiphy_dev - get wiphy dev pointer * * @wiphy: The wiphy whose device struct to look up * Return: The dev of @wiphy. */ static inline struct device *wiphy_dev(struct wiphy *wiphy) { return wiphy->dev.parent; } /** * wiphy_name - get wiphy name * * @wiphy: The wiphy whose name to return * Return: The name of @wiphy. */ static inline const char *wiphy_name(const struct wiphy *wiphy) { return dev_name(&wiphy->dev); } /** * wiphy_new_nm - create a new wiphy for use with cfg80211 * * @ops: The configuration operations for this device * @sizeof_priv: The size of the private area to allocate * @requested_name: Request a particular name. * NULL is valid value, and means use the default phy%d naming. * * Create a new wiphy and associate the given operations with it. * @sizeof_priv bytes are allocated for private use. * * Return: A pointer to the new wiphy. This pointer must be * assigned to each netdev's ieee80211_ptr for proper operation. */ struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv, const char *requested_name); /** * wiphy_new - create a new wiphy for use with cfg80211 * * @ops: The configuration operations for this device * @sizeof_priv: The size of the private area to allocate * * Create a new wiphy and associate the given operations with it. * @sizeof_priv bytes are allocated for private use. * * Return: A pointer to the new wiphy. This pointer must be * assigned to each netdev's ieee80211_ptr for proper operation. */ static inline struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) { return wiphy_new_nm(ops, sizeof_priv, NULL); } /** * wiphy_register - register a wiphy with cfg80211 * * @wiphy: The wiphy to register. * * Return: A non-negative wiphy index or a negative error code. */ int wiphy_register(struct wiphy *wiphy); /* this is a define for better error reporting (file/line) */ #define lockdep_assert_wiphy(wiphy) lockdep_assert_held(&(wiphy)->mtx) /** * rcu_dereference_wiphy - rcu_dereference with debug checking * @wiphy: the wiphy to check the locking on * @p: The pointer to read, prior to dereferencing * * Do an rcu_dereference(p), but check caller either holds rcu_read_lock() * or RTNL. Note: Please prefer wiphy_dereference() or rcu_dereference(). */ #define rcu_dereference_wiphy(wiphy, p) \ rcu_dereference_check(p, lockdep_is_held(&wiphy->mtx)) /** * wiphy_dereference - fetch RCU pointer when updates are prevented by wiphy mtx * @wiphy: the wiphy to check the locking on * @p: The pointer to read, prior to dereferencing * * Return: the value of the specified RCU-protected pointer, but omit the * READ_ONCE(), because caller holds the wiphy mutex used for updates. */ #define wiphy_dereference(wiphy, p) \ rcu_dereference_protected(p, lockdep_is_held(&wiphy->mtx)) /** * get_wiphy_regdom - get custom regdomain for the given wiphy * @wiphy: the wiphy to get the regdomain from * * Context: Requires any of RTNL, wiphy mutex or RCU protection. * * Return: pointer to the regulatory domain associated with the wiphy */ const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy); /** * wiphy_unregister - deregister a wiphy from cfg80211 * * @wiphy: The wiphy to unregister. * * After this call, no more requests can be made with this priv * pointer, but the call may sleep to wait for an outstanding * request that is being handled. */ void wiphy_unregister(struct wiphy *wiphy); /** * wiphy_free - free wiphy * * @wiphy: The wiphy to free */ void wiphy_free(struct wiphy *wiphy); /* internal structs */ struct cfg80211_conn; struct cfg80211_internal_bss; struct cfg80211_cached_keys; struct cfg80211_cqm_config; /** * wiphy_lock - lock the wiphy * @wiphy: the wiphy to lock * * This is needed around registering and unregistering netdevs that * aren't created through cfg80211 calls, since that requires locking * in cfg80211 when the notifiers is called, but that cannot * differentiate which way it's called. * * It can also be used by drivers for their own purposes. * * When cfg80211 ops are called, the wiphy is already locked. * * Note that this makes sure that no workers that have been queued * with wiphy_queue_work() are running. */ static inline void wiphy_lock(struct wiphy *wiphy) __acquires(&wiphy->mtx) { mutex_lock(&wiphy->mtx); __acquire(&wiphy->mtx); } /** * wiphy_unlock - unlock the wiphy again * @wiphy: the wiphy to unlock */ static inline void wiphy_unlock(struct wiphy *wiphy) __releases(&wiphy->mtx) { __release(&wiphy->mtx); mutex_unlock(&wiphy->mtx); } DEFINE_GUARD(wiphy, struct wiphy *, mutex_lock(&_T->mtx), mutex_unlock(&_T->mtx)) struct wiphy_work; typedef void (*wiphy_work_func_t)(struct wiphy *, struct wiphy_work *); struct wiphy_work { struct list_head entry; wiphy_work_func_t func; }; static inline void wiphy_work_init(struct wiphy_work *work, wiphy_work_func_t func) { INIT_LIST_HEAD(&work->entry); work->func = func; } /** * wiphy_work_queue - queue work for the wiphy * @wiphy: the wiphy to queue for * @work: the work item * * This is useful for work that must be done asynchronously, and work * queued here has the special property that the wiphy mutex will be * held as if wiphy_lock() was called, and that it cannot be running * after wiphy_lock() was called. Therefore, wiphy_cancel_work() can * use just cancel_work() instead of cancel_work_sync(), it requires * being in a section protected by wiphy_lock(). */ void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work); /** * wiphy_work_cancel - cancel previously queued work * @wiphy: the wiphy, for debug purposes * @work: the work to cancel * * Cancel the work *without* waiting for it, this assumes being * called under the wiphy mutex acquired by wiphy_lock(). */ void wiphy_work_cancel(struct wiphy *wiphy, struct wiphy_work *work); /** * wiphy_work_flush - flush previously queued work * @wiphy: the wiphy, for debug purposes * @work: the work to flush, this can be %NULL to flush all work * * Flush the work (i.e. run it if pending). This must be called * under the wiphy mutex acquired by wiphy_lock(). */ void wiphy_work_flush(struct wiphy *wiphy, struct wiphy_work *work); struct wiphy_delayed_work { struct wiphy_work work; struct wiphy *wiphy; struct timer_list timer; }; void wiphy_delayed_work_timer(struct timer_list *t); static inline void wiphy_delayed_work_init(struct wiphy_delayed_work *dwork, wiphy_work_func_t func) { timer_setup(&dwork->timer, wiphy_delayed_work_timer, 0); wiphy_work_init(&dwork->work, func); } /** * wiphy_delayed_work_queue - queue delayed work for the wiphy * @wiphy: the wiphy to queue for * @dwork: the delayable worker * @delay: number of jiffies to wait before queueing * * This is useful for work that must be done asynchronously, and work * queued here has the special property that the wiphy mutex will be * held as if wiphy_lock() was called, and that it cannot be running * after wiphy_lock() was called. Therefore, wiphy_cancel_work() can * use just cancel_work() instead of cancel_work_sync(), it requires * being in a section protected by wiphy_lock(). * * Note that these are scheduled with a timer where the accuracy * becomes less the longer in the future the scheduled timer is. Use * wiphy_hrtimer_work_queue() if the timer must be not be late by more * than approximately 10 percent. */ void wiphy_delayed_work_queue(struct wiphy *wiphy, struct wiphy_delayed_work *dwork, unsigned long delay); /** * wiphy_delayed_work_cancel - cancel previously queued delayed work * @wiphy: the wiphy, for debug purposes * @dwork: the delayed work to cancel * * Cancel the work *without* waiting for it, this assumes being * called under the wiphy mutex acquired by wiphy_lock(). */ void wiphy_delayed_work_cancel(struct wiphy *wiphy, struct wiphy_delayed_work *dwork); /** * wiphy_delayed_work_flush - flush previously queued delayed work * @wiphy: the wiphy, for debug purposes * @dwork: the delayed work to flush * * Flush the work (i.e. run it if pending). This must be called * under the wiphy mutex acquired by wiphy_lock(). */ void wiphy_delayed_work_flush(struct wiphy *wiphy, struct wiphy_delayed_work *dwork); /** * wiphy_delayed_work_pending - Find out whether a wiphy delayable * work item is currently pending. * * @wiphy: the wiphy, for debug purposes * @dwork: the delayed work in question * * Return: true if timer is pending, false otherwise * * How wiphy_delayed_work_queue() works is by setting a timer which * when it expires calls wiphy_work_queue() to queue the wiphy work. * Because wiphy_delayed_work_queue() uses mod_timer(), if it is * called twice and the second call happens before the first call * deadline, the work will rescheduled for the second deadline and * won't run before that. * * wiphy_delayed_work_pending() can be used to detect if calling * wiphy_work_delayed_work_queue() would start a new work schedule * or delayed a previous one. As seen below it cannot be used to * detect precisely if the work has finished to execute nor if it * is currently executing. * * CPU0 CPU1 * wiphy_delayed_work_queue(wk) * mod_timer(wk->timer) * wiphy_delayed_work_pending(wk) -> true * * [...] * expire_timers(wk->timer) * detach_timer(wk->timer) * wiphy_delayed_work_pending(wk) -> false * wk->timer->function() | * wiphy_work_queue(wk) | delayed work pending * list_add_tail() | returns false but * queue_work(cfg80211_wiphy_work) | wk->func() has not * | been run yet * [...] | * cfg80211_wiphy_work() | * wk->func() V * */ bool wiphy_delayed_work_pending(struct wiphy *wiphy, struct wiphy_delayed_work *dwork); struct wiphy_hrtimer_work { struct wiphy_work work; struct wiphy *wiphy; struct hrtimer timer; }; enum hrtimer_restart wiphy_hrtimer_work_timer(struct hrtimer *t); static inline void wiphy_hrtimer_work_init(struct wiphy_hrtimer_work *hrwork, wiphy_work_func_t func) { hrtimer_setup(&hrwork->timer, wiphy_hrtimer_work_timer, CLOCK_BOOTTIME, HRTIMER_MODE_REL); wiphy_work_init(&hrwork->work, func); } /** * wiphy_hrtimer_work_queue - queue hrtimer work for the wiphy * @wiphy: the wiphy to queue for * @hrwork: the high resolution timer worker * @delay: the delay given as a ktime_t * * Please refer to wiphy_delayed_work_queue(). The difference is that * the hrtimer work uses a high resolution timer for scheduling. This * may be needed if timeouts might be scheduled further in the future * and the accuracy of the normal timer is not sufficient. * * Expect a delay of a few milliseconds as the timer is scheduled * with some slack and some more time may pass between queueing the * work and its start. */ void wiphy_hrtimer_work_queue(struct wiphy *wiphy, struct wiphy_hrtimer_work *hrwork, ktime_t delay); /** * wiphy_hrtimer_work_cancel - cancel previously queued hrtimer work * @wiphy: the wiphy, for debug purposes * @hrtimer: the hrtimer work to cancel * * Cancel the work *without* waiting for it, this assumes being * called under the wiphy mutex acquired by wiphy_lock(). */ void wiphy_hrtimer_work_cancel(struct wiphy *wiphy, struct wiphy_hrtimer_work *hrtimer); /** * wiphy_hrtimer_work_flush - flush previously queued hrtimer work * @wiphy: the wiphy, for debug purposes * @hrwork: the hrtimer work to flush * * Flush the work (i.e. run it if pending). This must be called * under the wiphy mutex acquired by wiphy_lock(). */ void wiphy_hrtimer_work_flush(struct wiphy *wiphy, struct wiphy_hrtimer_work *hrwork); /** * wiphy_hrtimer_work_pending - Find out whether a wiphy hrtimer * work item is currently pending. * * @wiphy: the wiphy, for debug purposes * @hrwork: the hrtimer work in question * * Return: true if timer is pending, false otherwise * * Please refer to the wiphy_delayed_work_pending() documentation as * this is the equivalent function for hrtimer based delayed work * items. */ bool wiphy_hrtimer_work_pending(struct wiphy *wiphy, struct wiphy_hrtimer_work *hrwork); /** * enum ieee80211_ap_reg_power - regulatory power for an Access Point * * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode * @IEEE80211_REG_LPI_AP: Indoor Access Point * @IEEE80211_REG_SP_AP: Standard power Access Point * @IEEE80211_REG_VLP_AP: Very low power Access Point */ enum ieee80211_ap_reg_power { IEEE80211_REG_UNSET_AP, IEEE80211_REG_LPI_AP, IEEE80211_REG_SP_AP, IEEE80211_REG_VLP_AP, }; /** * struct wireless_dev - wireless device state * * For netdevs, this structure must be allocated by the driver * that uses the ieee80211_ptr field in struct net_device (this * is intentional so it can be allocated along with the netdev.) * It need not be registered then as netdev registration will * be intercepted by cfg80211 to see the new wireless device, * however, drivers must lock the wiphy before registering or * unregistering netdevs if they pre-create any netdevs (in ops * called from cfg80211, the wiphy is already locked.) * * For non-netdev uses, it must also be allocated by the driver * in response to the cfg80211 callbacks that require it, as * there's no netdev registration in that case it may not be * allocated outside of callback operations that return it. * * @wiphy: pointer to hardware description * @iftype: interface type * @registered: is this wdev already registered with cfg80211 * @registering: indicates we're doing registration under wiphy lock * for the notifier * @list: (private) Used to collect the interfaces * @netdev: (private) Used to reference back to the netdev, may be %NULL * @identifier: (private) Identifier used in nl80211 to identify this * wireless device if it has no netdev * @u: union containing data specific to @iftype * @connected: indicates if connected or not (STA mode) * @wext: (private) Used by the internal wireless extensions compat code * @wext.ibss: (private) IBSS data part of wext handling * @wext.connect: (private) connection handling data * @wext.keys: (private) (WEP) key data * @wext.ie: (private) extra elements for association * @wext.ie_len: (private) length of extra elements * @wext.bssid: (private) selected network BSSID * @wext.ssid: (private) selected network SSID * @wext.default_key: (private) selected default key index * @wext.default_mgmt_key: (private) selected default management key index * @wext.prev_bssid: (private) previous BSSID for reassociation * @wext.prev_bssid_valid: (private) previous BSSID validity * @use_4addr: indicates 4addr mode is used on this interface, must be * set by driver (if supported) on add_interface BEFORE registering the * netdev and may otherwise be used by driver read-only, will be update * by cfg80211 on change_interface * @mgmt_registrations: list of registrations for management frames * @mgmt_registrations_need_update: mgmt registrations were updated, * need to propagate the update to the driver * @address: The address for this device, valid only if @netdev is %NULL * @is_running: true if this is a non-netdev device that has been started, e.g. * the P2P Device. * @ps: powersave mode is enabled * @ps_timeout: dynamic powersave timeout * @unexpected_nlportid: (private) netlink port ID of application * registered for unexpected frames (AP mode or NAN_DATA mode) * @conn: (private) cfg80211 software SME connection state machine data * @connect_keys: (private) keys to set after connection is established * @conn_bss_type: connecting/connected BSS type * @conn_owner_nlportid: (private) connection owner socket port ID * @disconnect_wk: (private) auto-disconnect work * @disconnect_bssid: (private) the BSSID to use for auto-disconnect * @event_list: (private) list for internal event processing * @event_lock: (private) lock for event list * @owner_nlportid: (private) owner socket port ID * @nl_owner_dead: (private) owner socket went away * @cqm_rssi_work: (private) CQM RSSI reporting work * @cqm_config: (private) nl80211 RSSI monitor state * @pmsr_list: (private) peer measurement requests * @pmsr_lock: (private) peer measurements requests/results lock * @pmsr_free_wk: (private) peer measurements cleanup work * @unprot_beacon_reported: (private) timestamp of last * unprotected beacon report * @links: array of %IEEE80211_MLD_MAX_NUM_LINKS elements containing @addr * @ap and @client for each link * @links.cac_started: true if DFS channel availability check has been * started * @links.cac_start_time: timestamp (jiffies) when the dfs state was * entered. * @links.cac_time_ms: CAC time in ms * @valid_links: bitmap describing what elements of @links are valid * @radio_mask: Bitmask of radios that this interface is allowed to operate on. */ struct wireless_dev { struct wiphy *wiphy; enum nl80211_iftype iftype; /* the remainder of this struct should be private to cfg80211 */ struct list_head list; struct net_device *netdev; u32 identifier; struct list_head mgmt_registrations; u8 mgmt_registrations_need_update:1; bool use_4addr, is_running, registered, registering; u8 address[ETH_ALEN] __aligned(sizeof(u16)); /* currently used for IBSS and SME - might be rearranged later */ struct cfg80211_conn *conn; struct cfg80211_cached_keys *connect_keys; enum ieee80211_bss_type conn_bss_type; u32 conn_owner_nlportid; struct work_struct disconnect_wk; u8 disconnect_bssid[ETH_ALEN]; struct list_head event_list; spinlock_t event_lock; u8 connected:1; bool ps; int ps_timeout; u32 unexpected_nlportid; u32 owner_nlportid; bool nl_owner_dead; #ifdef CONFIG_CFG80211_WEXT /* wext data */ struct { struct cfg80211_ibss_params ibss; struct cfg80211_connect_params connect; struct cfg80211_cached_keys *keys; const u8 *ie; size_t ie_len; u8 bssid[ETH_ALEN]; u8 prev_bssid[ETH_ALEN]; u8 ssid[IEEE80211_MAX_SSID_LEN]; s8 default_key, default_mgmt_key; bool prev_bssid_valid; } wext; #endif struct wiphy_work cqm_rssi_work; struct cfg80211_cqm_config __rcu *cqm_config; struct list_head pmsr_list; spinlock_t pmsr_lock; struct work_struct pmsr_free_wk; unsigned long unprot_beacon_reported; union { struct { u8 connected_addr[ETH_ALEN] __aligned(2); u8 ssid[IEEE80211_MAX_SSID_LEN]; u8 ssid_len; } client; struct { int beacon_interval; struct cfg80211_chan_def preset_chandef; struct cfg80211_chan_def chandef; u8 id[IEEE80211_MAX_MESH_ID_LEN]; u8 id_len, id_up_len; } mesh; struct { struct cfg80211_chan_def preset_chandef; u8 ssid[IEEE80211_MAX_SSID_LEN]; u8 ssid_len; } ap; struct { struct cfg80211_internal_bss *current_bss; struct cfg80211_chan_def chandef; int beacon_interval; u8 ssid[IEEE80211_MAX_SSID_LEN]; u8 ssid_len; } ibss; struct { struct cfg80211_chan_def chandef; } ocb; struct { u8 cluster_id[ETH_ALEN] __aligned(2); u8 n_channels; struct cfg80211_chan_def *chandefs; bool sched_update_pending; } nan; } u; struct { u8 addr[ETH_ALEN] __aligned(2); union { struct { unsigned int beacon_interval; struct cfg80211_chan_def chandef; } ap; struct { struct cfg80211_internal_bss *current_bss; } client; }; bool cac_started; unsigned long cac_start_time; unsigned int cac_time_ms; } links[IEEE80211_MLD_MAX_NUM_LINKS]; u16 valid_links; u32 radio_mask; }; static inline const u8 *wdev_address(struct wireless_dev *wdev) { if (wdev->netdev) return wdev->netdev->dev_addr; return wdev->address; } static inline bool wdev_running(struct wireless_dev *wdev) { if (wdev->netdev) return netif_running(wdev->netdev); return wdev->is_running; } /** * wdev_priv - return wiphy priv from wireless_dev * * @wdev: The wireless device whose wiphy's priv pointer to return * Return: The wiphy priv of @wdev. */ static inline void *wdev_priv(struct wireless_dev *wdev) { BUG_ON(!wdev); return wiphy_priv(wdev->wiphy); } /** * wdev_chandef - return chandef pointer from wireless_dev * @wdev: the wdev * @link_id: the link ID for MLO * * Return: The chandef depending on the mode, or %NULL. */ struct cfg80211_chan_def *wdev_chandef(struct wireless_dev *wdev, unsigned int link_id); static inline void WARN_INVALID_LINK_ID(struct wireless_dev *wdev, unsigned int link_id) { WARN_ON(link_id && !wdev->valid_links); WARN_ON(wdev->valid_links && !(wdev->valid_links & BIT(link_id))); } #define for_each_valid_link(link_info, link_id) \ for (link_id = 0; \ link_id < ((link_info)->valid_links ? \ ARRAY_SIZE((link_info)->links) : 1); \ link_id++) \ if (!(link_info)->valid_links || \ ((link_info)->valid_links & BIT(link_id))) /** * DOC: Utility functions * * cfg80211 offers a number of utility functions that can be useful. */ /** * ieee80211_channel_equal - compare two struct ieee80211_channel * * @a: 1st struct ieee80211_channel * @b: 2nd struct ieee80211_channel * Return: true if center frequency of @a == @b */ static inline bool ieee80211_channel_equal(struct ieee80211_channel *a, struct ieee80211_channel *b) { return (a->center_freq == b->center_freq && a->freq_offset == b->freq_offset); } /** * ieee80211_channel_to_khz - convert ieee80211_channel to frequency in KHz * @chan: struct ieee80211_channel to convert * Return: The corresponding frequency (in KHz) */ static inline u32 ieee80211_channel_to_khz(const struct ieee80211_channel *chan) { return MHZ_TO_KHZ(chan->center_freq) + chan->freq_offset; } /** * ieee80211_channel_to_freq_khz - convert channel number to frequency * @chan: channel number * @band: band, necessary due to channel number overlap * Return: The corresponding frequency (in KHz), or 0 if the conversion failed. */ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band); /** * ieee80211_channel_to_frequency - convert channel number to frequency * @chan: channel number * @band: band, necessary due to channel number overlap * Return: The corresponding frequency (in MHz), or 0 if the conversion failed. */ static inline int ieee80211_channel_to_frequency(int chan, enum nl80211_band band) { return KHZ_TO_MHZ(ieee80211_channel_to_freq_khz(chan, band)); } /** * ieee80211_freq_khz_to_channel - convert frequency to channel number * @freq: center frequency in KHz * Return: The corresponding channel, or 0 if the conversion failed. */ int ieee80211_freq_khz_to_channel(u32 freq); /** * ieee80211_frequency_to_channel - convert frequency to channel number * @freq: center frequency in MHz * Return: The corresponding channel, or 0 if the conversion failed. */ static inline int ieee80211_frequency_to_channel(int freq) { return ieee80211_freq_khz_to_channel(MHZ_TO_KHZ(freq)); } /** * ieee80211_get_channel_khz - get channel struct from wiphy for specified * frequency * @wiphy: the struct wiphy to get the channel for * @freq: the center frequency (in KHz) of the channel * Return: The channel struct from @wiphy at @freq. */ struct ieee80211_channel * ieee80211_get_channel_khz(struct wiphy *wiphy, u32 freq); /** * ieee80211_get_channel - get channel struct from wiphy for specified frequency * * @wiphy: the struct wiphy to get the channel for * @freq: the center frequency (in MHz) of the channel * Return: The channel struct from @wiphy at @freq. */ static inline struct ieee80211_channel * ieee80211_get_channel(struct wiphy *wiphy, int freq) { return ieee80211_get_channel_khz(wiphy, MHZ_TO_KHZ(freq)); } /** * cfg80211_channel_is_psc - Check if the channel is a 6 GHz PSC * @chan: control channel to check * * The Preferred Scanning Channels (PSC) are defined in * Draft IEEE P802.11ax/D5.0, 26.17.2.3.3 * * Return: %true if channel is a PSC, %false otherwise */ static inline bool cfg80211_channel_is_psc(struct ieee80211_channel *chan) { if (chan->band != NL80211_BAND_6GHZ) return false; return ieee80211_frequency_to_channel(chan->center_freq) % 16 == 5; } /** * ieee80211_radio_freq_range_valid - Check if the radio supports the * specified frequency range * * @radio: wiphy radio * @freq: the frequency (in KHz) to be queried * @width: the bandwidth (in KHz) to be queried * * Return: whether or not the given frequency range is valid for the given radio */ bool ieee80211_radio_freq_range_valid(const struct wiphy_radio *radio, u32 freq, u32 width); /** * cfg80211_radio_chandef_valid - Check if the radio supports the chandef * * @radio: wiphy radio * @chandef: chandef for current channel * * Return: whether or not the given chandef is valid for the given radio */ bool cfg80211_radio_chandef_valid(const struct wiphy_radio *radio, const struct cfg80211_chan_def *chandef); /** * cfg80211_wdev_channel_allowed - Check if the wdev may use the channel * * @wdev: the wireless device * @chan: channel to check * * Return: whether or not the wdev may use the channel */ bool cfg80211_wdev_channel_allowed(struct wireless_dev *wdev, struct ieee80211_channel *chan); /** * ieee80211_get_response_rate - get basic rate for a given rate * * @sband: the band to look for rates in * @basic_rates: bitmap of basic rates * @bitrate: the bitrate for which to find the basic rate * * Return: The basic rate corresponding to a given bitrate, that * is the next lower bitrate contained in the basic rate map, * which is, for this function, given as a bitmap of indices of * rates in the band's bitrate table. */ const struct ieee80211_rate * ieee80211_get_response_rate(struct ieee80211_supported_band *sband, u32 basic_rates, int bitrate); /** * ieee80211_mandatory_rates - get mandatory rates for a given band * @sband: the band to look for rates in * * Return: a bitmap of the mandatory rates for the given band, bits * are set according to the rate position in the bitrates array. */ u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband); /* * Radiotap parsing functions -- for controlled injection support * * Implemented in net/wireless/radiotap.c * Documentation in Documentation/networking/radiotap-headers.rst */ struct radiotap_align_size { uint8_t align:4, size:4; }; struct ieee80211_radiotap_namespace { const struct radiotap_align_size *align_size; int n_bits; uint32_t oui; uint8_t subns; }; struct ieee80211_radiotap_vendor_namespaces { const struct ieee80211_radiotap_namespace *ns; int n_ns; }; /** * struct ieee80211_radiotap_iterator - tracks walk thru present radiotap args * @this_arg_index: index of current arg, valid after each successful call * to ieee80211_radiotap_iterator_next() * @this_arg: pointer to current radiotap arg; it is valid after each * call to ieee80211_radiotap_iterator_next() but also after * ieee80211_radiotap_iterator_init() where it will point to * the beginning of the actual data portion * @this_arg_size: length of the current arg, for convenience * @current_namespace: pointer to the current namespace definition * (or internally %NULL if the current namespace is unknown) * @is_radiotap_ns: indicates whether the current namespace is the default * radiotap namespace or not * * @_rtheader: pointer to the radiotap header we are walking through * @_max_length: length of radiotap header in cpu byte ordering * @_arg_index: next argument index * @_arg: next argument pointer * @_next_bitmap: internal pointer to next present u32 * @_bitmap_shifter: internal shifter for curr u32 bitmap, b0 set == arg present * @_vns: vendor namespace definitions * @_next_ns_data: beginning of the next namespace's data * @_reset_on_ext: internal; reset the arg index to 0 when going to the * next bitmap word * * Describes the radiotap parser state. Fields prefixed with an underscore * must not be used by users of the parser, only by the parser internally. */ struct ieee80211_radiotap_iterator { struct ieee80211_radiotap_header *_rtheader; const struct ieee80211_radiotap_vendor_namespaces *_vns; const struct ieee80211_radiotap_namespace *current_namespace; unsigned char *_arg, *_next_ns_data; __le32 *_next_bitmap; unsigned char *this_arg; int this_arg_index; int this_arg_size; int is_radiotap_ns; int _max_length; int _arg_index; uint32_t _bitmap_shifter; int _reset_on_ext; }; int ieee80211_radiotap_iterator_init(struct ieee80211_radiotap_iterator *iterator, struct ieee80211_radiotap_header *radiotap_header, int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns); int ieee80211_radiotap_iterator_next(struct ieee80211_radiotap_iterator *iterator); extern const unsigned char rfc1042_header[6]; extern const unsigned char bridge_tunnel_header[6]; /** * ieee80211_get_hdrlen_from_skb - get header length from data * * @skb: the frame * * Given an skb with a raw 802.11 header at the data pointer this function * returns the 802.11 header length. * * Return: The 802.11 header length in bytes (not including encryption * headers). Or 0 if the data in the sk_buff is too short to contain a valid * 802.11 header. */ unsigned int ieee80211_get_hdrlen_from_skb(const struct sk_buff *skb); /** * ieee80211_hdrlen - get header length in bytes from frame control * @fc: frame control field in little-endian format * Return: The header length in bytes. */ unsigned int __attribute_const__ ieee80211_hdrlen(__le16 fc); /** * ieee80211_get_mesh_hdrlen - get mesh extension header length * @meshhdr: the mesh extension header, only the flags field * (first byte) will be accessed * Return: The length of the extension header, which is always at * least 6 bytes and at most 18 if address 5 and 6 are present. */ unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr); /** * DOC: Data path helpers * * In addition to generic utilities, cfg80211 also offers * functions that help implement the data path for devices * that do not do the 802.11/802.3 conversion on the device. */ /** * ieee80211_data_to_8023_exthdr - convert an 802.11 data frame to 802.3 * @skb: the 802.11 data frame * @ehdr: pointer to a &struct ethhdr that will get the header, instead * of it being pushed into the SKB * @addr: the device MAC address * @iftype: the virtual interface type * @data_offset: offset of payload after the 802.11 header * @is_amsdu: true if the 802.11 header is A-MSDU * Return: 0 on success. Non-zero on error. */ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr, const u8 *addr, enum nl80211_iftype iftype, u8 data_offset, bool is_amsdu); /** * ieee80211_data_to_8023 - convert an 802.11 data frame to 802.3 * @skb: the 802.11 data frame * @addr: the device MAC address * @iftype: the virtual interface type * Return: 0 on success. Non-zero on error. */ static inline int ieee80211_data_to_8023(struct sk_buff *skb, const u8 *addr, enum nl80211_iftype iftype) { return ieee80211_data_to_8023_exthdr(skb, NULL, addr, iftype, 0, false); } /** * ieee80211_is_valid_amsdu - check if subframe lengths of an A-MSDU are valid * * This is used to detect non-standard A-MSDU frames, e.g. the ones generated * by ath10k and ath11k, where the subframe length includes the length of the * mesh control field. * * @skb: The input A-MSDU frame without any headers. * @mesh_hdr: the type of mesh header to test * 0: non-mesh A-MSDU length field * 1: big-endian mesh A-MSDU length field * 2: little-endian mesh A-MSDU length field * Returns: true if subframe header lengths are valid for the @mesh_hdr mode */ bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr); /** * ieee80211_amsdu_to_8023s - decode an IEEE 802.11n A-MSDU frame * * Decode an IEEE 802.11 A-MSDU and convert it to a list of 802.3 frames. * The @list will be empty if the decode fails. The @skb must be fully * header-less before being passed in here; it is freed in this function. * * @skb: The input A-MSDU frame without any headers. * @list: The output list of 802.3 frames. It must be allocated and * initialized by the caller. * @addr: The device MAC address. * @iftype: The device interface type. * @extra_headroom: The hardware extra headroom for SKBs in the @list. * @check_da: DA to check in the inner ethernet header, or NULL * @check_sa: SA to check in the inner ethernet header, or NULL * @mesh_control: see mesh_hdr in ieee80211_is_valid_amsdu */ void ieee80211_amsdu_to_8023s(struct sk_buff *skb, struct sk_buff_head *list, const u8 *addr, enum nl80211_iftype iftype, const unsigned int extra_headroom, const u8 *check_da, const u8 *check_sa, u8 mesh_control); /** * ieee80211_get_8023_tunnel_proto - get RFC1042 or bridge tunnel encap protocol * * Check for RFC1042 or bridge tunnel header and fetch the encapsulated * protocol. * * @hdr: pointer to the MSDU payload * @proto: destination pointer to store the protocol * Return: true if encapsulation was found */ bool ieee80211_get_8023_tunnel_proto(const void *hdr, __be16 *proto); /** * ieee80211_strip_8023_mesh_hdr - strip mesh header from converted 802.3 frames * * Strip the mesh header, which was left in by ieee80211_data_to_8023 as part * of the MSDU data. Also move any source/destination addresses from the mesh * header to the ethernet header (if present). * * @skb: The 802.3 frame with embedded mesh header * * Return: 0 on success. Non-zero on error. */ int ieee80211_strip_8023_mesh_hdr(struct sk_buff *skb); /** * cfg80211_classify8021d - determine the 802.1p/1d tag for a data frame * @skb: the data frame * @qos_map: Interworking QoS mapping or %NULL if not in use * Return: The 802.1p/1d tag. */ unsigned int cfg80211_classify8021d(struct sk_buff *skb, struct cfg80211_qos_map *qos_map); /** * cfg80211_find_elem_match - match information element and byte array in data * * @eid: element ID * @ies: data consisting of IEs * @len: length of data * @match: byte array to match * @match_len: number of bytes in the match array * @match_offset: offset in the IE data where the byte array should match. * Note the difference to cfg80211_find_ie_match() which considers * the offset to start from the element ID byte, but here we take * the data portion instead. * * Return: %NULL if the element ID could not be found or if * the element is invalid (claims to be longer than the given * data) or if the byte array doesn't match; otherwise return the * requested element struct. * * Note: There are no checks on the element length other than * having to fit into the given data and being large enough for the * byte array to match. */ const struct element * cfg80211_find_elem_match(u8 eid, const u8 *ies, unsigned int len, const u8 *match, unsigned int match_len, unsigned int match_offset); /** * cfg80211_find_ie_match - match information element and byte array in data * * @eid: element ID * @ies: data consisting of IEs * @len: length of data * @match: byte array to match * @match_len: number of bytes in the match array * @match_offset: offset in the IE where the byte array should match. * If match_len is zero, this must also be set to zero. * Otherwise this must be set to 2 or more, because the first * byte is the element id, which is already compared to eid, and * the second byte is the IE length. * * Return: %NULL if the element ID could not be found or if * the element is invalid (claims to be longer than the given * data) or if the byte array doesn't match, or a pointer to the first * byte of the requested element, that is the byte containing the * element ID. * * Note: There are no checks on the element length other than * having to fit into the given data and being large enough for the * byte array to match. */ static inline const u8 * cfg80211_find_ie_match(u8 eid, const u8 *ies, unsigned int len, const u8 *match, unsigned int match_len, unsigned int match_offset) { /* match_offset can't be smaller than 2, unless match_len is * zero, in which case match_offset must be zero as well. */ if (WARN_ON((match_len && match_offset < 2) || (!match_len && match_offset))) return NULL; return (const void *)cfg80211_find_elem_match(eid, ies, len, match, match_len, match_offset ? match_offset - 2 : 0); } /** * cfg80211_find_elem - find information element in data * * @eid: element ID * @ies: data consisting of IEs * @len: length of data * * Return: %NULL if the element ID could not be found or if * the element is invalid (claims to be longer than the given * data) or if the byte array doesn't match; otherwise return the * requested element struct. * * Note: There are no checks on the element length other than * having to fit into the given data. */ static inline const struct element * cfg80211_find_elem(u8 eid, const u8 *ies, int len) { return cfg80211_find_elem_match(eid, ies, len, NULL, 0, 0); } /** * cfg80211_find_ie - find information element in data * * @eid: element ID * @ies: data consisting of IEs * @len: length of data * * Return: %NULL if the element ID could not be found or if * the element is invalid (claims to be longer than the given * data), or a pointer to the first byte of the requested * element, that is the byte containing the element ID. * * Note: There are no checks on the element length other than * having to fit into the given data. */ static inline const u8 *cfg80211_find_ie(u8 eid, const u8 *ies, int len) { return cfg80211_find_ie_match(eid, ies, len, NULL, 0, 0); } /** * cfg80211_find_ext_elem - find information element with EID Extension in data * * @ext_eid: element ID Extension * @ies: data consisting of IEs * @len: length of data * * Return: %NULL if the extended element could not be found or if * the element is invalid (claims to be longer than the given * data) or if the byte array doesn't match; otherwise return the * requested element struct. * * Note: There are no checks on the element length other than * having to fit into the given data. */ static inline const struct element * cfg80211_find_ext_elem(u8 ext_eid, const u8 *ies, int len) { return cfg80211_find_elem_match(WLAN_EID_EXTENSION, ies, len, &ext_eid, 1, 0); } /** * cfg80211_find_ext_ie - find information element with EID Extension in data * * @ext_eid: element ID Extension * @ies: data consisting of IEs * @len: length of data * * Return: %NULL if the extended element ID could not be found or if * the element is invalid (claims to be longer than the given * data), or a pointer to the first byte of the requested * element, that is the byte containing the element ID. * * Note: There are no checks on the element length other than * having to fit into the given data. */ static inline const u8 *cfg80211_find_ext_ie(u8 ext_eid, const u8 *ies, int len) { return cfg80211_find_ie_match(WLAN_EID_EXTENSION, ies, len, &ext_eid, 1, 2); } /** * cfg80211_find_vendor_elem - find vendor specific information element in data * * @oui: vendor OUI * @oui_type: vendor-specific OUI type (must be < 0xff), negative means any * @ies: data consisting of IEs * @len: length of data * * Return: %NULL if the vendor specific element ID could not be found or if the * element is invalid (claims to be longer than the given data); otherwise * return the element structure for the requested element. * * Note: There are no checks on the element length other than having to fit into * the given data. */ const struct element *cfg80211_find_vendor_elem(unsigned int oui, int oui_type, const u8 *ies, unsigned int len); /** * cfg80211_find_vendor_ie - find vendor specific information element in data * * @oui: vendor OUI * @oui_type: vendor-specific OUI type (must be < 0xff), negative means any * @ies: data consisting of IEs * @len: length of data * * Return: %NULL if the vendor specific element ID could not be found or if the * element is invalid (claims to be longer than the given data), or a pointer to * the first byte of the requested element, that is the byte containing the * element ID. * * Note: There are no checks on the element length other than having to fit into * the given data. */ static inline const u8 * cfg80211_find_vendor_ie(unsigned int oui, int oui_type, const u8 *ies, unsigned int len) { return (const void *)cfg80211_find_vendor_elem(oui, oui_type, ies, len); } /** * enum cfg80211_rnr_iter_ret - reduced neighbor report iteration state * @RNR_ITER_CONTINUE: continue iterating with the next entry * @RNR_ITER_BREAK: break iteration and return success * @RNR_ITER_ERROR: break iteration and return error */ enum cfg80211_rnr_iter_ret { RNR_ITER_CONTINUE, RNR_ITER_BREAK, RNR_ITER_ERROR, }; /** * cfg80211_iter_rnr - iterate reduced neighbor report entries * @elems: the frame elements to iterate RNR elements and then * their entries in * @elems_len: length of the elements * @iter: iteration function, see also &enum cfg80211_rnr_iter_ret * for the return value * @iter_data: additional data passed to the iteration function * Return: %true on success (after successfully iterating all entries * or if the iteration function returned %RNR_ITER_BREAK), * %false on error (iteration function returned %RNR_ITER_ERROR * or elements were malformed.) */ bool cfg80211_iter_rnr(const u8 *elems, size_t elems_len, enum cfg80211_rnr_iter_ret (*iter)(void *data, u8 type, const struct ieee80211_neighbor_ap_info *info, const u8 *tbtt_info, u8 tbtt_info_len), void *iter_data); /** * cfg80211_defragment_element - Defrag the given element data into a buffer * * @elem: the element to defragment * @ies: elements where @elem is contained * @ieslen: length of @ies * @data: buffer to store element data, or %NULL to just determine size * @data_len: length of @data, or 0 * @frag_id: the element ID of fragments * * Return: length of @data, or -EINVAL on error * * Copy out all data from an element that may be fragmented into @data, while * skipping all headers. * * The function uses memmove() internally. It is acceptable to defragment an * element in-place. */ ssize_t cfg80211_defragment_element(const struct element *elem, const u8 *ies, size_t ieslen, u8 *data, size_t data_len, u8 frag_id); /** * cfg80211_send_layer2_update - send layer 2 update frame * * @dev: network device * @addr: STA MAC address * * Wireless drivers can use this function to update forwarding tables in bridge * devices upon STA association. */ void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr); /** * DOC: Regulatory enforcement infrastructure * * TODO */ /** * regulatory_hint - driver hint to the wireless core a regulatory domain * @wiphy: the wireless device giving the hint (used only for reporting * conflicts) * @alpha2: the ISO/IEC 3166 alpha2 the driver claims its regulatory domain * should be in. If @rd is set this should be NULL. Note that if you * set this to NULL you should still set rd->alpha2 to some accepted * alpha2. * * Wireless drivers can use this function to hint to the wireless core * what it believes should be the current regulatory domain by * giving it an ISO/IEC 3166 alpha2 country code it knows its regulatory * domain should be in or by providing a completely build regulatory domain. * If the driver provides an ISO/IEC 3166 alpha2 userspace will be queried * for a regulatory domain structure for the respective country. * * The wiphy must have been registered to cfg80211 prior to this call. * For cfg80211 drivers this means you must first use wiphy_register(), * for mac80211 drivers you must first use ieee80211_register_hw(). * * Drivers should check the return value, its possible you can get * an -ENOMEM. * * Return: 0 on success. -ENOMEM. */ int regulatory_hint(struct wiphy *wiphy, const char *alpha2); /** * regulatory_set_wiphy_regd - set regdom info for self managed drivers * @wiphy: the wireless device we want to process the regulatory domain on * @rd: the regulatory domain information to use for this wiphy * * Set the regulatory domain information for self-managed wiphys, only they * may use this function. See %REGULATORY_WIPHY_SELF_MANAGED for more * information. * * Return: 0 on success. -EINVAL, -EPERM */ int regulatory_set_wiphy_regd(struct wiphy *wiphy, struct ieee80211_regdomain *rd); /** * regulatory_set_wiphy_regd_sync - set regdom for self-managed drivers * @wiphy: the wireless device we want to process the regulatory domain on * @rd: the regulatory domain information to use for this wiphy * * This functions requires the RTNL and the wiphy mutex to be held and * applies the new regdomain synchronously to this wiphy. For more details * see regulatory_set_wiphy_regd(). * * Return: 0 on success. -EINVAL, -EPERM */ int regulatory_set_wiphy_regd_sync(struct wiphy *wiphy, struct ieee80211_regdomain *rd); /** * wiphy_apply_custom_regulatory - apply a custom driver regulatory domain * @wiphy: the wireless device we want to process the regulatory domain on * @regd: the custom regulatory domain to use for this wiphy * * Drivers can sometimes have custom regulatory domains which do not apply * to a specific country. Drivers can use this to apply such custom regulatory * domains. This routine must be called prior to wiphy registration. The * custom regulatory domain will be trusted completely and as such previous * default channel settings will be disregarded. If no rule is found for a * channel on the regulatory domain the channel will be disabled. * Drivers using this for a wiphy should also set the wiphy flag * REGULATORY_CUSTOM_REG or cfg80211 will set it for the wiphy * that called this helper. */ void wiphy_apply_custom_regulatory(struct wiphy *wiphy, const struct ieee80211_regdomain *regd); /** * freq_reg_info - get regulatory information for the given frequency * @wiphy: the wiphy for which we want to process this rule for * @center_freq: Frequency in KHz for which we want regulatory information for * * Use this function to get the regulatory rule for a specific frequency on * a given wireless device. If the device has a specific regulatory domain * it wants to follow we respect that unless a country IE has been received * and processed already. * * Return: A valid pointer, or, when an error occurs, for example if no rule * can be found, the return value is encoded using ERR_PTR(). Use IS_ERR() to * check and PTR_ERR() to obtain the numeric return value. The numeric return * value will be -ERANGE if we determine the given center_freq does not even * have a regulatory rule for a frequency range in the center_freq's band. * See freq_in_rule_band() for our current definition of a band -- this is * purely subjective and right now it's 802.11 specific. */ const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy, u32 center_freq); /** * reg_initiator_name - map regulatory request initiator enum to name * @initiator: the regulatory request initiator * * You can use this to map the regulatory request initiator enum to a * proper string representation. * * Return: pointer to string representation of the initiator */ const char *reg_initiator_name(enum nl80211_reg_initiator initiator); /** * regulatory_pre_cac_allowed - check if pre-CAC allowed in the current regdom * @wiphy: wiphy for which pre-CAC capability is checked. * * Pre-CAC is allowed only in some regdomains (notable ETSI). * * Return: %true if allowed, %false otherwise */ bool regulatory_pre_cac_allowed(struct wiphy *wiphy); /** * DOC: Internal regulatory db functions * */ /** * reg_query_regdb_wmm - Query internal regulatory db for wmm rule * Regulatory self-managed driver can use it to proactively * * @alpha2: the ISO/IEC 3166 alpha2 wmm rule to be queried. * @freq: the frequency (in MHz) to be queried. * @rule: pointer to store the wmm rule from the regulatory db. * * Self-managed wireless drivers can use this function to query * the internal regulatory database to check whether the given * ISO/IEC 3166 alpha2 country and freq have wmm rule limitations. * * Drivers should check the return value, its possible you can get * an -ENODATA. * * Return: 0 on success. -ENODATA. */ int reg_query_regdb_wmm(char *alpha2, int freq, struct ieee80211_reg_rule *rule); /* * callbacks for asynchronous cfg80211 methods, notification * functions and BSS handling helpers */ /** * cfg80211_scan_done - notify that scan finished * * @request: the corresponding scan request * @info: information about the completed scan */ void cfg80211_scan_done(struct cfg80211_scan_request *request, struct cfg80211_scan_info *info); /** * cfg80211_sched_scan_results - notify that new scan results are available * * @wiphy: the wiphy which got scheduled scan results * @reqid: identifier for the related scheduled scan request */ void cfg80211_sched_scan_results(struct wiphy *wiphy, u64 reqid); /** * cfg80211_sched_scan_stopped - notify that the scheduled scan has stopped * * @wiphy: the wiphy on which the scheduled scan stopped * @reqid: identifier for the related scheduled scan request * * The driver can call this function to inform cfg80211 that the * scheduled scan had to be stopped, for whatever reason. The driver * is then called back via the sched_scan_stop operation when done. */ void cfg80211_sched_scan_stopped(struct wiphy *wiphy, u64 reqid); /** * cfg80211_sched_scan_stopped_locked - notify that the scheduled scan has stopped * * @wiphy: the wiphy on which the scheduled scan stopped * @reqid: identifier for the related scheduled scan request * * The driver can call this function to inform cfg80211 that the * scheduled scan had to be stopped, for whatever reason. The driver * is then called back via the sched_scan_stop operation when done. * This function should be called with the wiphy mutex held. */ void cfg80211_sched_scan_stopped_locked(struct wiphy *wiphy, u64 reqid); /** * cfg80211_inform_bss_frame_data - inform cfg80211 of a received BSS frame * @wiphy: the wiphy reporting the BSS * @data: the BSS metadata * @mgmt: the management frame (probe response or beacon) * @len: length of the management frame * @gfp: context flags * * This informs cfg80211 that BSS information was found and * the BSS should be updated/added. * * Return: A referenced struct, must be released with cfg80211_put_bss()! * Or %NULL on error. */ struct cfg80211_bss * __must_check cfg80211_inform_bss_frame_data(struct wiphy *wiphy, struct cfg80211_inform_bss *data, struct ieee80211_mgmt *mgmt, size_t len, gfp_t gfp); static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_frame(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, struct ieee80211_mgmt *mgmt, size_t len, s32 signal, gfp_t gfp) { struct cfg80211_inform_bss data = { .chan = rx_channel, .signal = signal, }; return cfg80211_inform_bss_frame_data(wiphy, &data, mgmt, len, gfp); } /** * cfg80211_gen_new_bssid - generate a nontransmitted BSSID for multi-BSSID * @bssid: transmitter BSSID * @max_bssid: max BSSID indicator, taken from Multiple BSSID element * @mbssid_index: BSSID index, taken from Multiple BSSID index element * @new_bssid: calculated nontransmitted BSSID */ static inline void cfg80211_gen_new_bssid(const u8 *bssid, u8 max_bssid, u8 mbssid_index, u8 *new_bssid) { u64 bssid_u64 = ether_addr_to_u64(bssid); u64 mask = GENMASK_ULL(max_bssid - 1, 0); u64 new_bssid_u64; new_bssid_u64 = bssid_u64 & ~mask; new_bssid_u64 |= ((bssid_u64 & mask) + mbssid_index) & mask; u64_to_ether_addr(new_bssid_u64, new_bssid); } /** * cfg80211_is_element_inherited - returns if element ID should be inherited * @element: element to check * @non_inherit_element: non inheritance element * * Return: %true if should be inherited, %false otherwise */ bool cfg80211_is_element_inherited(const struct element *element, const struct element *non_inherit_element); /** * cfg80211_merge_profile - merges a MBSSID profile if it is split between IEs * @ie: ies * @ielen: length of IEs * @mbssid_elem: current MBSSID element * @sub_elem: current MBSSID subelement (profile) * @merged_ie: location of the merged profile * @max_copy_len: max merged profile length * * Return: the number of bytes merged */ size_t cfg80211_merge_profile(const u8 *ie, size_t ielen, const struct element *mbssid_elem, const struct element *sub_elem, u8 *merged_ie, size_t max_copy_len); /** * enum cfg80211_bss_frame_type - frame type that the BSS data came from * @CFG80211_BSS_FTYPE_UNKNOWN: driver doesn't know whether the data is * from a beacon or probe response * @CFG80211_BSS_FTYPE_BEACON: data comes from a beacon * @CFG80211_BSS_FTYPE_PRESP: data comes from a probe response * @CFG80211_BSS_FTYPE_S1G_BEACON: data comes from an S1G beacon */ enum cfg80211_bss_frame_type { CFG80211_BSS_FTYPE_UNKNOWN, CFG80211_BSS_FTYPE_BEACON, CFG80211_BSS_FTYPE_PRESP, CFG80211_BSS_FTYPE_S1G_BEACON, }; /** * cfg80211_get_ies_channel_number - returns the channel number from ies * @ie: IEs * @ielen: length of IEs * @band: enum nl80211_band of the channel * * Return: the channel number, or -1 if none could be determined. */ int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, enum nl80211_band band); /** * cfg80211_ssid_eq - compare two SSIDs * @a: first SSID * @b: second SSID * * Return: %true if SSIDs are equal, %false otherwise. */ static inline bool cfg80211_ssid_eq(struct cfg80211_ssid *a, struct cfg80211_ssid *b) { if (WARN_ON(!a || !b)) return false; if (a->ssid_len != b->ssid_len) return false; return memcmp(a->ssid, b->ssid, a->ssid_len) ? false : true; } /** * cfg80211_inform_bss_data - inform cfg80211 of a new BSS * * @wiphy: the wiphy reporting the BSS * @data: the BSS metadata * @ftype: frame type (if known) * @bssid: the BSSID of the BSS * @tsf: the TSF sent by the peer in the beacon/probe response (or 0) * @capability: the capability field sent by the peer * @beacon_interval: the beacon interval announced by the peer * @ie: additional IEs sent by the peer * @ielen: length of the additional IEs * @gfp: context flags * * This informs cfg80211 that BSS information was found and * the BSS should be updated/added. * * Return: A referenced struct, must be released with cfg80211_put_bss()! * Or %NULL on error. */ struct cfg80211_bss * __must_check cfg80211_inform_bss_data(struct wiphy *wiphy, struct cfg80211_inform_bss *data, enum cfg80211_bss_frame_type ftype, const u8 *bssid, u64 tsf, u16 capability, u16 beacon_interval, const u8 *ie, size_t ielen, gfp_t gfp); static inline struct cfg80211_bss * __must_check cfg80211_inform_bss(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, enum cfg80211_bss_frame_type ftype, const u8 *bssid, u64 tsf, u16 capability, u16 beacon_interval, const u8 *ie, size_t ielen, s32 signal, gfp_t gfp) { struct cfg80211_inform_bss data = { .chan = rx_channel, .signal = signal, }; return cfg80211_inform_bss_data(wiphy, &data, ftype, bssid, tsf, capability, beacon_interval, ie, ielen, gfp); } /** * __cfg80211_get_bss - get a BSS reference * @wiphy: the wiphy this BSS struct belongs to * @channel: the channel to search on (or %NULL) * @bssid: the desired BSSID (or %NULL) * @ssid: the desired SSID (or %NULL) * @ssid_len: length of the SSID (or 0) * @bss_type: type of BSS, see &enum ieee80211_bss_type * @privacy: privacy filter, see &enum ieee80211_privacy * @use_for: indicates which use is intended * * Return: Reference-counted BSS on success. %NULL on error. */ struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, const u8 *bssid, const u8 *ssid, size_t ssid_len, enum ieee80211_bss_type bss_type, enum ieee80211_privacy privacy, u32 use_for); /** * cfg80211_get_bss - get a BSS reference * @wiphy: the wiphy this BSS struct belongs to * @channel: the channel to search on (or %NULL) * @bssid: the desired BSSID (or %NULL) * @ssid: the desired SSID (or %NULL) * @ssid_len: length of the SSID (or 0) * @bss_type: type of BSS, see &enum ieee80211_bss_type * @privacy: privacy filter, see &enum ieee80211_privacy * * This version implies regular usage, %NL80211_BSS_USE_FOR_NORMAL. * * Return: Reference-counted BSS on success. %NULL on error. */ static inline struct cfg80211_bss * cfg80211_get_bss(struct wiphy *wiphy, struct ieee80211_channel *channel, const u8 *bssid, const u8 *ssid, size_t ssid_len, enum ieee80211_bss_type bss_type, enum ieee80211_privacy privacy) { return __cfg80211_get_bss(wiphy, channel, bssid, ssid, ssid_len, bss_type, privacy, NL80211_BSS_USE_FOR_NORMAL); } static inline struct cfg80211_bss * cfg80211_get_ibss(struct wiphy *wiphy, struct ieee80211_channel *channel, const u8 *ssid, size_t ssid_len) { return cfg80211_get_bss(wiphy, channel, NULL, ssid, ssid_len, IEEE80211_BSS_TYPE_IBSS, IEEE80211_PRIVACY_ANY); } /** * cfg80211_ref_bss - reference BSS struct * @wiphy: the wiphy this BSS struct belongs to * @bss: the BSS struct to reference * * Increments the refcount of the given BSS struct. */ void cfg80211_ref_bss(struct wiphy *wiphy, struct cfg80211_bss *bss); /** * cfg80211_put_bss - unref BSS struct * @wiphy: the wiphy this BSS struct belongs to * @bss: the BSS struct * * Decrements the refcount of the given BSS struct. */ void cfg80211_put_bss(struct wiphy *wiphy, struct cfg80211_bss *bss); /** * cfg80211_unlink_bss - unlink BSS from internal data structures * @wiphy: the wiphy * @bss: the bss to remove * * This function removes the given BSS from the internal data structures * thereby making it no longer show up in scan results etc. Use this * function when you detect a BSS is gone. Normally BSSes will also time * out, so it is not necessary to use this function at all. */ void cfg80211_unlink_bss(struct wiphy *wiphy, struct cfg80211_bss *bss); /** * cfg80211_bss_iter - iterate all BSS entries * * This function iterates over the BSS entries associated with the given wiphy * and calls the callback for the iterated BSS. The iterator function is not * allowed to call functions that might modify the internal state of the BSS DB. * * @wiphy: the wiphy * @chandef: if given, the iterator function will be called only if the channel * of the currently iterated BSS is a subset of the given channel. * @iter: the iterator function to call * @iter_data: an argument to the iterator function */ void cfg80211_bss_iter(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, void (*iter)(struct wiphy *wiphy, struct cfg80211_bss *bss, void *data), void *iter_data); /** * cfg80211_rx_mlme_mgmt - notification of processed MLME management frame * @dev: network device * @buf: authentication frame (header + body) * @len: length of the frame data * * This function is called whenever an authentication, disassociation or * deauthentication frame has been received and processed in station mode. * After being asked to authenticate via cfg80211_ops::auth() the driver must * call either this function or cfg80211_auth_timeout(). * After being asked to associate via cfg80211_ops::assoc() the driver must * call either this function or cfg80211_auth_timeout(). * While connected, the driver must calls this for received and processed * disassociation and deauthentication frames. If the frame couldn't be used * because it was unprotected, the driver must call the function * cfg80211_rx_unprot_mlme_mgmt() instead. * * This function may sleep. The caller must hold the corresponding wdev's mutex. */ void cfg80211_rx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len); /** * cfg80211_auth_timeout - notification of timed out authentication * @dev: network device * @addr: The MAC address of the device with which the authentication timed out * * This function may sleep. The caller must hold the corresponding wdev's * mutex. */ void cfg80211_auth_timeout(struct net_device *dev, const u8 *addr); /** * struct cfg80211_rx_assoc_resp_data - association response data * @buf: (Re)Association Response frame (header + body) * @len: length of the frame data * @uapsd_queues: bitmap of queues configured for uapsd. Same format * as the AC bitmap in the QoS info field * @req_ies: information elements from the (Re)Association Request frame * @req_ies_len: length of req_ies data * @ap_mld_addr: AP MLD address (in case of MLO) * @links: per-link information indexed by link ID, use links[0] for * non-MLO connections * @links.bss: the BSS that association was requested with, ownership of the * pointer moves to cfg80211 in the call to cfg80211_rx_assoc_resp() * @links.status: Set this (along with a BSS pointer) for links that * were rejected by the AP. */ struct cfg80211_rx_assoc_resp_data { const u8 *buf; size_t len; const u8 *req_ies; size_t req_ies_len; int uapsd_queues; const u8 *ap_mld_addr; struct { u8 addr[ETH_ALEN] __aligned(2); struct cfg80211_bss *bss; u16 status; } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** * cfg80211_rx_assoc_resp - notification of processed association response * @dev: network device * @data: association response data, &struct cfg80211_rx_assoc_resp_data * * After being asked to associate via cfg80211_ops::assoc() the driver must * call either this function or cfg80211_auth_timeout(). * * This function may sleep. The caller must hold the corresponding wdev's mutex. */ void cfg80211_rx_assoc_resp(struct net_device *dev, const struct cfg80211_rx_assoc_resp_data *data); /** * struct cfg80211_assoc_failure - association failure data * @ap_mld_addr: AP MLD address, or %NULL * @bss: list of BSSes, must use entry 0 for non-MLO connections * (@ap_mld_addr is %NULL) * @timeout: indicates the association failed due to timeout, otherwise * the association was abandoned for a reason reported through some * other API (e.g. deauth RX) */ struct cfg80211_assoc_failure { const u8 *ap_mld_addr; struct cfg80211_bss *bss[IEEE80211_MLD_MAX_NUM_LINKS]; bool timeout; }; /** * cfg80211_assoc_failure - notification of association failure * @dev: network device * @data: data describing the association failure * * This function may sleep. The caller must hold the corresponding wdev's mutex. */ void cfg80211_assoc_failure(struct net_device *dev, struct cfg80211_assoc_failure *data); /** * cfg80211_tx_mlme_mgmt - notification of transmitted deauth/disassoc frame * @dev: network device * @buf: 802.11 frame (header + body) * @len: length of the frame data * @reconnect: immediate reconnect is desired (include the nl80211 attribute) * * This function is called whenever deauthentication has been processed in * station mode. This includes both received deauthentication frames and * locally generated ones. This function may sleep. The caller must hold the * corresponding wdev's mutex. */ void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len, bool reconnect); /** * cfg80211_rx_unprot_mlme_mgmt - notification of unprotected mlme mgmt frame * @dev: network device * @buf: received management frame (header + body) * @len: length of the frame data * * This function is called whenever a received deauthentication or dissassoc * frame has been dropped in station mode because of MFP being used but the * frame was not protected. This is also used to notify reception of a Beacon * frame that was dropped because it did not include a valid MME MIC while * beacon protection was enabled (BIGTK configured in station mode). * * This function may sleep. */ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len); /** * cfg80211_michael_mic_failure - notification of Michael MIC failure (TKIP) * @dev: network device * @addr: The source MAC address of the frame * @key_type: The key type that the received frame used * @key_id: Key identifier (0..3). Can be -1 if missing. * @tsc: The TSC value of the frame that generated the MIC failure (6 octets) * @gfp: allocation flags * * This function is called whenever the local MAC detects a MIC failure in a * received frame. This matches with MLME-MICHAELMICFAILURE.indication() * primitive. */ void cfg80211_michael_mic_failure(struct net_device *dev, const u8 *addr, enum nl80211_key_type key_type, int key_id, const u8 *tsc, gfp_t gfp); /** * cfg80211_ibss_joined - notify cfg80211 that device joined an IBSS * * @dev: network device * @bssid: the BSSID of the IBSS joined * @channel: the channel of the IBSS joined * @gfp: allocation flags * * This function notifies cfg80211 that the device joined an IBSS or * switched to a different BSSID. Before this function can be called, * either a beacon has to have been received from the IBSS, or one of * the cfg80211_inform_bss{,_frame} functions must have been called * with the locally generated beacon -- this guarantees that there is * always a scan result for this IBSS. cfg80211 will handle the rest. */ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, struct ieee80211_channel *channel, gfp_t gfp); /** * cfg80211_notify_new_peer_candidate - notify cfg80211 of a new mesh peer * candidate * * @dev: network device * @macaddr: the MAC address of the new candidate * @ie: information elements advertised by the peer candidate * @ie_len: length of the information elements buffer * @sig_dbm: signal level in dBm * @gfp: allocation flags * * This function notifies cfg80211 that the mesh peer candidate has been * detected, most likely via a beacon or, less likely, via a probe response. * cfg80211 then sends a notification to userspace. */ void cfg80211_notify_new_peer_candidate(struct net_device *dev, const u8 *macaddr, const u8 *ie, u8 ie_len, int sig_dbm, gfp_t gfp); /** * DOC: RFkill integration * * RFkill integration in cfg80211 is almost invisible to drivers, * as cfg80211 automatically registers an rfkill instance for each * wireless device it knows about. Soft kill is also translated * into disconnecting and turning all interfaces off. Drivers are * expected to turn off the device when all interfaces are down. * * However, devices may have a hard RFkill line, in which case they * also need to interact with the rfkill subsystem, via cfg80211. * They can do this with a few helper functions documented here. */ /** * wiphy_rfkill_set_hw_state_reason - notify cfg80211 about hw block state * @wiphy: the wiphy * @blocked: block status * @reason: one of reasons in &enum rfkill_hard_block_reasons */ void wiphy_rfkill_set_hw_state_reason(struct wiphy *wiphy, bool blocked, enum rfkill_hard_block_reasons reason); static inline void wiphy_rfkill_set_hw_state(struct wiphy *wiphy, bool blocked) { wiphy_rfkill_set_hw_state_reason(wiphy, blocked, RFKILL_HARD_BLOCK_SIGNAL); } /** * wiphy_rfkill_start_polling - start polling rfkill * @wiphy: the wiphy */ void wiphy_rfkill_start_polling(struct wiphy *wiphy); /** * wiphy_rfkill_stop_polling - stop polling rfkill * @wiphy: the wiphy */ static inline void wiphy_rfkill_stop_polling(struct wiphy *wiphy) { rfkill_pause_polling(wiphy->rfkill); } /** * DOC: Vendor commands * * Occasionally, there are special protocol or firmware features that * can't be implemented very openly. For this and similar cases, the * vendor command functionality allows implementing the features with * (typically closed-source) userspace and firmware, using nl80211 as * the configuration mechanism. * * A driver supporting vendor commands must register them as an array * in struct wiphy, with handlers for each one. Each command has an * OUI and sub command ID to identify it. * * Note that this feature should not be (ab)used to implement protocol * features that could openly be shared across drivers. In particular, * it must never be required to use vendor commands to implement any * "normal" functionality that higher-level userspace like connection * managers etc. need. */ struct sk_buff *__cfg80211_alloc_reply_skb(struct wiphy *wiphy, enum nl80211_commands cmd, enum nl80211_attrs attr, int approxlen); struct sk_buff *__cfg80211_alloc_event_skb(struct wiphy *wiphy, struct wireless_dev *wdev, enum nl80211_commands cmd, enum nl80211_attrs attr, unsigned int portid, int vendor_event_idx, int approxlen, gfp_t gfp); void __cfg80211_send_event_skb(struct sk_buff *skb, gfp_t gfp); /** * cfg80211_vendor_cmd_alloc_reply_skb - allocate vendor command reply * @wiphy: the wiphy * @approxlen: an upper bound of the length of the data that will * be put into the skb * * This function allocates and pre-fills an skb for a reply to * a vendor command. Since it is intended for a reply, calling * it outside of a vendor command's doit() operation is invalid. * * The returned skb is pre-filled with some identifying data in * a way that any data that is put into the skb (with skb_put(), * nla_put() or similar) will end up being within the * %NL80211_ATTR_VENDOR_DATA attribute, so all that needs to be done * with the skb is adding data for the corresponding userspace tool * which can then read that data out of the vendor data attribute. * You must not modify the skb in any other way. * * When done, call cfg80211_vendor_cmd_reply() with the skb and return * its error code as the result of the doit() operation. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * cfg80211_vendor_cmd_alloc_reply_skb(struct wiphy *wiphy, int approxlen) { return __cfg80211_alloc_reply_skb(wiphy, NL80211_CMD_VENDOR, NL80211_ATTR_VENDOR_DATA, approxlen); } /** * cfg80211_vendor_cmd_reply - send the reply skb * @skb: The skb, must have been allocated with * cfg80211_vendor_cmd_alloc_reply_skb() * * Since calling this function will usually be the last thing * before returning from the vendor command doit() you should * return the error code. Note that this function consumes the * skb regardless of the return value. * * Return: An error code or 0 on success. */ int cfg80211_vendor_cmd_reply(struct sk_buff *skb); /** * cfg80211_vendor_cmd_get_sender - get the current sender netlink ID * @wiphy: the wiphy * * Return: the current netlink port ID in a vendor command handler. * * Context: May only be called from a vendor command handler */ unsigned int cfg80211_vendor_cmd_get_sender(struct wiphy *wiphy); /** * cfg80211_vendor_event_alloc - allocate vendor-specific event skb * @wiphy: the wiphy * @wdev: the wireless device * @event_idx: index of the vendor event in the wiphy's vendor_events * @approxlen: an upper bound of the length of the data that will * be put into the skb * @gfp: allocation flags * * This function allocates and pre-fills an skb for an event on the * vendor-specific multicast group. * * If wdev != NULL, both the ifindex and identifier of the specified * wireless device are added to the event message before the vendor data * attribute. * * When done filling the skb, call cfg80211_vendor_event() with the * skb to send the event. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * cfg80211_vendor_event_alloc(struct wiphy *wiphy, struct wireless_dev *wdev, int approxlen, int event_idx, gfp_t gfp) { return __cfg80211_alloc_event_skb(wiphy, wdev, NL80211_CMD_VENDOR, NL80211_ATTR_VENDOR_DATA, 0, event_idx, approxlen, gfp); } /** * cfg80211_vendor_event_alloc_ucast - alloc unicast vendor-specific event skb * @wiphy: the wiphy * @wdev: the wireless device * @event_idx: index of the vendor event in the wiphy's vendor_events * @portid: port ID of the receiver * @approxlen: an upper bound of the length of the data that will * be put into the skb * @gfp: allocation flags * * This function allocates and pre-fills an skb for an event to send to * a specific (userland) socket. This socket would previously have been * obtained by cfg80211_vendor_cmd_get_sender(), and the caller MUST take * care to register a netlink notifier to see when the socket closes. * * If wdev != NULL, both the ifindex and identifier of the specified * wireless device are added to the event message before the vendor data * attribute. * * When done filling the skb, call cfg80211_vendor_event() with the * skb to send the event. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * cfg80211_vendor_event_alloc_ucast(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int portid, int approxlen, int event_idx, gfp_t gfp) { return __cfg80211_alloc_event_skb(wiphy, wdev, NL80211_CMD_VENDOR, NL80211_ATTR_VENDOR_DATA, portid, event_idx, approxlen, gfp); } /** * cfg80211_vendor_event - send the event * @skb: The skb, must have been allocated with cfg80211_vendor_event_alloc() * @gfp: allocation flags * * This function sends the given @skb, which must have been allocated * by cfg80211_vendor_event_alloc(), as an event. It always consumes it. */ static inline void cfg80211_vendor_event(struct sk_buff *skb, gfp_t gfp) { __cfg80211_send_event_skb(skb, gfp); } #ifdef CONFIG_NL80211_TESTMODE /** * DOC: Test mode * * Test mode is a set of utility functions to allow drivers to * interact with driver-specific tools to aid, for instance, * factory programming. * * This chapter describes how drivers interact with it. For more * information see the nl80211 book's chapter on it. */ /** * cfg80211_testmode_alloc_reply_skb - allocate testmode reply * @wiphy: the wiphy * @approxlen: an upper bound of the length of the data that will * be put into the skb * * This function allocates and pre-fills an skb for a reply to * the testmode command. Since it is intended for a reply, calling * it outside of the @testmode_cmd operation is invalid. * * The returned skb is pre-filled with the wiphy index and set up in * a way that any data that is put into the skb (with skb_put(), * nla_put() or similar) will end up being within the * %NL80211_ATTR_TESTDATA attribute, so all that needs to be done * with the skb is adding data for the corresponding userspace tool * which can then read that data out of the testdata attribute. You * must not modify the skb in any other way. * * When done, call cfg80211_testmode_reply() with the skb and return * its error code as the result of the @testmode_cmd operation. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * cfg80211_testmode_alloc_reply_skb(struct wiphy *wiphy, int approxlen) { return __cfg80211_alloc_reply_skb(wiphy, NL80211_CMD_TESTMODE, NL80211_ATTR_TESTDATA, approxlen); } /** * cfg80211_testmode_reply - send the reply skb * @skb: The skb, must have been allocated with * cfg80211_testmode_alloc_reply_skb() * * Since calling this function will usually be the last thing * before returning from the @testmode_cmd you should return * the error code. Note that this function consumes the skb * regardless of the return value. * * Return: An error code or 0 on success. */ static inline int cfg80211_testmode_reply(struct sk_buff *skb) { return cfg80211_vendor_cmd_reply(skb); } /** * cfg80211_testmode_alloc_event_skb - allocate testmode event * @wiphy: the wiphy * @approxlen: an upper bound of the length of the data that will * be put into the skb * @gfp: allocation flags * * This function allocates and pre-fills an skb for an event on the * testmode multicast group. * * The returned skb is set up in the same way as with * cfg80211_testmode_alloc_reply_skb() but prepared for an event. As * there, you should simply add data to it that will then end up in the * %NL80211_ATTR_TESTDATA attribute. Again, you must not modify the skb * in any other way. * * When done filling the skb, call cfg80211_testmode_event() with the * skb to send the event. * * Return: An allocated and pre-filled skb. %NULL if any errors happen. */ static inline struct sk_buff * cfg80211_testmode_alloc_event_skb(struct wiphy *wiphy, int approxlen, gfp_t gfp) { return __cfg80211_alloc_event_skb(wiphy, NULL, NL80211_CMD_TESTMODE, NL80211_ATTR_TESTDATA, 0, -1, approxlen, gfp); } /** * cfg80211_testmode_event - send the event * @skb: The skb, must have been allocated with * cfg80211_testmode_alloc_event_skb() * @gfp: allocation flags * * This function sends the given @skb, which must have been allocated * by cfg80211_testmode_alloc_event_skb(), as an event. It always * consumes it. */ static inline void cfg80211_testmode_event(struct sk_buff *skb, gfp_t gfp) { __cfg80211_send_event_skb(skb, gfp); } #define CFG80211_TESTMODE_CMD(cmd) .testmode_cmd = (cmd), #define CFG80211_TESTMODE_DUMP(cmd) .testmode_dump = (cmd), #else #define CFG80211_TESTMODE_CMD(cmd) #define CFG80211_TESTMODE_DUMP(cmd) #endif /** * struct cfg80211_fils_resp_params - FILS connection response params * @kek: KEK derived from a successful FILS connection (may be %NULL) * @kek_len: Length of @fils_kek in octets * @update_erp_next_seq_num: Boolean value to specify whether the value in * @erp_next_seq_num is valid. * @erp_next_seq_num: The next sequence number to use in ERP message in * FILS Authentication. This value should be specified irrespective of the * status for a FILS connection. * @pmk: A new PMK if derived from a successful FILS connection (may be %NULL). * @pmk_len: Length of @pmk in octets * @pmkid: A new PMKID if derived from a successful FILS connection or the PMKID * used for this FILS connection (may be %NULL). */ struct cfg80211_fils_resp_params { const u8 *kek; size_t kek_len; bool update_erp_next_seq_num; u16 erp_next_seq_num; const u8 *pmk; size_t pmk_len; const u8 *pmkid; }; /** * struct cfg80211_connect_resp_params - Connection response params * @status: Status code, %WLAN_STATUS_SUCCESS for successful connection, use * %WLAN_STATUS_UNSPECIFIED_FAILURE if your device cannot give you * the real status code for failures. If this call is used to report a * failure due to a timeout (e.g., not receiving an Authentication frame * from the AP) instead of an explicit rejection by the AP, -1 is used to * indicate that this is a failure, but without a status code. * @timeout_reason is used to report the reason for the timeout in that * case. * @req_ie: Association request IEs (may be %NULL) * @req_ie_len: Association request IEs length * @resp_ie: Association response IEs (may be %NULL) * @resp_ie_len: Association response IEs length * @fils: FILS connection response parameters. * @timeout_reason: Reason for connection timeout. This is used when the * connection fails due to a timeout instead of an explicit rejection from * the AP. %NL80211_TIMEOUT_UNSPECIFIED is used when the timeout reason is * not known. This value is used only if @status < 0 to indicate that the * failure is due to a timeout and not due to explicit rejection by the AP. * This value is ignored in other cases (@status >= 0). * @valid_links: For MLO connection, BIT mask of the valid link ids. Otherwise * zero. * @ap_mld_addr: For MLO connection, MLD address of the AP. Otherwise %NULL. * @links : For MLO connection, contains link info for the valid links indicated * using @valid_links. For non-MLO connection, links[0] contains the * connected AP info. * @links.addr: For MLO connection, MAC address of the STA link. Otherwise * %NULL. * @links.bssid: For MLO connection, MAC address of the AP link. For non-MLO * connection, links[0].bssid points to the BSSID of the AP (may be %NULL). * @links.bss: For MLO connection, entry of bss to which STA link is connected. * For non-MLO connection, links[0].bss points to entry of bss to which STA * is connected. It can be obtained through cfg80211_get_bss() (may be * %NULL). It is recommended to store the bss from the connect_request and * hold a reference to it and return through this param to avoid a warning * if the bss is expired during the connection, esp. for those drivers * implementing connect op. Only one parameter among @bssid and @bss needs * to be specified. * @links.status: per-link status code, to report a status code that's not * %WLAN_STATUS_SUCCESS for a given link, it must also be in the * @valid_links bitmap and may have a BSS pointer (which is then released) */ struct cfg80211_connect_resp_params { int status; const u8 *req_ie; size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; struct cfg80211_fils_resp_params fils; enum nl80211_timeout_reason timeout_reason; const u8 *ap_mld_addr; u16 valid_links; struct { const u8 *addr; const u8 *bssid; struct cfg80211_bss *bss; u16 status; } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** * cfg80211_connect_done - notify cfg80211 of connection result * * @dev: network device * @params: connection response parameters * @gfp: allocation flags * * It should be called by the underlying driver once execution of the connection * request from connect() has been completed. This is similar to * cfg80211_connect_bss(), but takes a structure pointer for connection response * parameters. Only one of the functions among cfg80211_connect_bss(), * cfg80211_connect_result(), cfg80211_connect_timeout(), * and cfg80211_connect_done() should be called. */ void cfg80211_connect_done(struct net_device *dev, struct cfg80211_connect_resp_params *params, gfp_t gfp); /** * cfg80211_connect_bss - notify cfg80211 of connection result * * @dev: network device * @bssid: the BSSID of the AP * @bss: Entry of bss to which STA got connected to, can be obtained through * cfg80211_get_bss() (may be %NULL). But it is recommended to store the * bss from the connect_request and hold a reference to it and return * through this param to avoid a warning if the bss is expired during the * connection, esp. for those drivers implementing connect op. * Only one parameter among @bssid and @bss needs to be specified. * @req_ie: association request IEs (maybe be %NULL) * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) * @resp_ie_len: assoc response IEs length * @status: status code, %WLAN_STATUS_SUCCESS for successful connection, use * %WLAN_STATUS_UNSPECIFIED_FAILURE if your device cannot give you * the real status code for failures. If this call is used to report a * failure due to a timeout (e.g., not receiving an Authentication frame * from the AP) instead of an explicit rejection by the AP, -1 is used to * indicate that this is a failure, but without a status code. * @timeout_reason is used to report the reason for the timeout in that * case. * @gfp: allocation flags * @timeout_reason: reason for connection timeout. This is used when the * connection fails due to a timeout instead of an explicit rejection from * the AP. %NL80211_TIMEOUT_UNSPECIFIED is used when the timeout reason is * not known. This value is used only if @status < 0 to indicate that the * failure is due to a timeout and not due to explicit rejection by the AP. * This value is ignored in other cases (@status >= 0). * * It should be called by the underlying driver once execution of the connection * request from connect() has been completed. This is similar to * cfg80211_connect_result(), but with the option of identifying the exact bss * entry for the connection. Only one of the functions among * cfg80211_connect_bss(), cfg80211_connect_result(), * cfg80211_connect_timeout(), and cfg80211_connect_done() should be called. */ static inline void cfg80211_connect_bss(struct net_device *dev, const u8 *bssid, struct cfg80211_bss *bss, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, size_t resp_ie_len, int status, gfp_t gfp, enum nl80211_timeout_reason timeout_reason) { struct cfg80211_connect_resp_params params; memset(¶ms, 0, sizeof(params)); params.status = status; params.links[0].bssid = bssid; params.links[0].bss = bss; params.req_ie = req_ie; params.req_ie_len = req_ie_len; params.resp_ie = resp_ie; params.resp_ie_len = resp_ie_len; params.timeout_reason = timeout_reason; cfg80211_connect_done(dev, ¶ms, gfp); } /** * cfg80211_connect_result - notify cfg80211 of connection result * * @dev: network device * @bssid: the BSSID of the AP * @req_ie: association request IEs (maybe be %NULL) * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) * @resp_ie_len: assoc response IEs length * @status: status code, %WLAN_STATUS_SUCCESS for successful connection, use * %WLAN_STATUS_UNSPECIFIED_FAILURE if your device cannot give you * the real status code for failures. * @gfp: allocation flags * * It should be called by the underlying driver once execution of the connection * request from connect() has been completed. This is similar to * cfg80211_connect_bss() which allows the exact bss entry to be specified. Only * one of the functions among cfg80211_connect_bss(), cfg80211_connect_result(), * cfg80211_connect_timeout(), and cfg80211_connect_done() should be called. */ static inline void cfg80211_connect_result(struct net_device *dev, const u8 *bssid, const u8 *req_ie, size_t req_ie_len, const u8 *resp_ie, size_t resp_ie_len, u16 status, gfp_t gfp) { cfg80211_connect_bss(dev, bssid, NULL, req_ie, req_ie_len, resp_ie, resp_ie_len, status, gfp, NL80211_TIMEOUT_UNSPECIFIED); } /** * cfg80211_connect_timeout - notify cfg80211 of connection timeout * * @dev: network device * @bssid: the BSSID of the AP * @req_ie: association request IEs (maybe be %NULL) * @req_ie_len: association request IEs length * @gfp: allocation flags * @timeout_reason: reason for connection timeout. * * It should be called by the underlying driver whenever connect() has failed * in a sequence where no explicit authentication/association rejection was * received from the AP. This could happen, e.g., due to not being able to send * out the Authentication or Association Request frame or timing out while * waiting for the response. Only one of the functions among * cfg80211_connect_bss(), cfg80211_connect_result(), * cfg80211_connect_timeout(), and cfg80211_connect_done() should be called. */ static inline void cfg80211_connect_timeout(struct net_device *dev, const u8 *bssid, const u8 *req_ie, size_t req_ie_len, gfp_t gfp, enum nl80211_timeout_reason timeout_reason) { cfg80211_connect_bss(dev, bssid, NULL, req_ie, req_ie_len, NULL, 0, -1, gfp, timeout_reason); } /** * struct cfg80211_roam_info - driver initiated roaming information * * @req_ie: association request IEs (maybe be %NULL) * @req_ie_len: association request IEs length * @resp_ie: association response IEs (may be %NULL) * @resp_ie_len: assoc response IEs length * @fils: FILS related roaming information. * @valid_links: For MLO roaming, BIT mask of the new valid links is set. * Otherwise zero. * @ap_mld_addr: For MLO roaming, MLD address of the new AP. Otherwise %NULL. * @links : For MLO roaming, contains new link info for the valid links set in * @valid_links. For non-MLO roaming, links[0] contains the new AP info. * @links.addr: For MLO roaming, MAC address of the STA link. Otherwise %NULL. * @links.bssid: For MLO roaming, MAC address of the new AP link. For non-MLO * roaming, links[0].bssid points to the BSSID of the new AP. May be * %NULL if %links.bss is set. * @links.channel: the channel of the new AP. * @links.bss: For MLO roaming, entry of new bss to which STA link got * roamed. For non-MLO roaming, links[0].bss points to entry of bss to * which STA got roamed (may be %NULL if %links.bssid is set) */ struct cfg80211_roam_info { const u8 *req_ie; size_t req_ie_len; const u8 *resp_ie; size_t resp_ie_len; struct cfg80211_fils_resp_params fils; const u8 *ap_mld_addr; u16 valid_links; struct { const u8 *addr; const u8 *bssid; struct ieee80211_channel *channel; struct cfg80211_bss *bss; } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** * cfg80211_roamed - notify cfg80211 of roaming * * @dev: network device * @info: information about the new BSS. struct &cfg80211_roam_info. * @gfp: allocation flags * * This function may be called with the driver passing either the BSSID of the * new AP or passing the bss entry to avoid a race in timeout of the bss entry. * It should be called by the underlying driver whenever it roamed from one AP * to another while connected. Drivers which have roaming implemented in * firmware should pass the bss entry to avoid a race in bss entry timeout where * the bss entry of the new AP is seen in the driver, but gets timed out by the * time it is accessed in __cfg80211_roamed() due to delay in scheduling * rdev->event_work. In case of any failures, the reference is released * either in cfg80211_roamed() or in __cfg80211_romed(), Otherwise, it will be * released while disconnecting from the current bss. */ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, gfp_t gfp); /** * cfg80211_port_authorized - notify cfg80211 of successful security association * * @dev: network device * @peer_addr: BSSID of the AP/P2P GO in case of STA/GC or STA/GC MAC address * in case of AP/P2P GO * @td_bitmap: transition disable policy * @td_bitmap_len: Length of transition disable policy * @gfp: allocation flags * * This function should be called by a driver that supports 4 way handshake * offload after a security association was successfully established (i.e., * the 4 way handshake was completed successfully). The call to this function * should be preceded with a call to cfg80211_connect_result(), * cfg80211_connect_done(), cfg80211_connect_bss() or cfg80211_roamed() to * indicate the 802.11 association. * This function can also be called by AP/P2P GO driver that supports * authentication offload. In this case the peer_mac passed is that of * associated STA/GC. */ void cfg80211_port_authorized(struct net_device *dev, const u8 *peer_addr, const u8* td_bitmap, u8 td_bitmap_len, gfp_t gfp); /** * cfg80211_disconnected - notify cfg80211 that connection was dropped * * @dev: network device * @ie: information elements of the deauth/disassoc frame (may be %NULL) * @ie_len: length of IEs * @reason: reason code for the disconnection, set it to 0 if unknown * @locally_generated: disconnection was requested locally * @gfp: allocation flags * * After it calls this function, the driver should enter an idle state * and not try to connect to any AP any more. */ void cfg80211_disconnected(struct net_device *dev, u16 reason, const u8 *ie, size_t ie_len, bool locally_generated, gfp_t gfp); /** * cfg80211_ready_on_channel - notification of remain_on_channel start * @wdev: wireless device * @cookie: the request cookie * @chan: The current channel (from remain_on_channel request) * @duration: Duration in milliseconds that the driver intents to remain on the * channel * @gfp: allocation flags */ void cfg80211_ready_on_channel(struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, unsigned int duration, gfp_t gfp); /** * cfg80211_remain_on_channel_expired - remain_on_channel duration expired * @wdev: wireless device * @cookie: the request cookie * @chan: The current channel (from remain_on_channel request) * @gfp: allocation flags */ void cfg80211_remain_on_channel_expired(struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, gfp_t gfp); /** * cfg80211_tx_mgmt_expired - tx_mgmt duration expired * @wdev: wireless device * @cookie: the requested cookie * @chan: The current channel (from tx_mgmt request) * @gfp: allocation flags */ void cfg80211_tx_mgmt_expired(struct wireless_dev *wdev, u64 cookie, struct ieee80211_channel *chan, gfp_t gfp); /** * cfg80211_sinfo_alloc_tid_stats - allocate per-tid statistics. * * @sinfo: the station information * @gfp: allocation flags * * Return: 0 on success. Non-zero on error. */ int cfg80211_sinfo_alloc_tid_stats(struct station_info *sinfo, gfp_t gfp); /** * cfg80211_link_sinfo_alloc_tid_stats - allocate per-tid statistics. * * @link_sinfo: the link station information * @gfp: allocation flags * * Return: 0 on success. Non-zero on error. */ int cfg80211_link_sinfo_alloc_tid_stats(struct link_station_info *link_sinfo, gfp_t gfp); /** * cfg80211_sinfo_release_content - release contents of station info * @sinfo: the station information * * Releases any potentially allocated sub-information of the station * information, but not the struct itself (since it's typically on * the stack.) */ static inline void cfg80211_sinfo_release_content(struct station_info *sinfo) { kfree(sinfo->pertid); for (int link_id = 0; link_id < ARRAY_SIZE(sinfo->links); link_id++) { if (sinfo->links[link_id]) { kfree(sinfo->links[link_id]->pertid); kfree(sinfo->links[link_id]); } } } /** * cfg80211_new_sta - notify userspace about station * * @wdev: the wireless device * @mac_addr: the station's address * @sinfo: the station information * @gfp: allocation flags */ void cfg80211_new_sta(struct wireless_dev *wdev, const u8 *mac_addr, struct station_info *sinfo, gfp_t gfp); /** * cfg80211_del_sta_sinfo - notify userspace about deletion of a station * @wdev: the wireless device * @mac_addr: the station's address. For MLD station, MLD address is used. * @sinfo: the station information/statistics * @gfp: allocation flags */ void cfg80211_del_sta_sinfo(struct wireless_dev *wdev, const u8 *mac_addr, struct station_info *sinfo, gfp_t gfp); /** * cfg80211_del_sta - notify userspace about deletion of a station * * @wdev: the wireless device * @mac_addr: the station's address. For MLD station, MLD address is used. * @gfp: allocation flags */ static inline void cfg80211_del_sta(struct wireless_dev *wdev, const u8 *mac_addr, gfp_t gfp) { cfg80211_del_sta_sinfo(wdev, mac_addr, NULL, gfp); } /** * cfg80211_conn_failed - connection request failed notification * * @dev: the netdev * @mac_addr: the station's address * @reason: the reason for connection failure * @gfp: allocation flags * * Whenever a station tries to connect to an AP and if the station * could not connect to the AP as the AP has rejected the connection * for some reasons, this function is called. * * The reason for connection failure can be any of the value from * nl80211_connect_failed_reason enum */ void cfg80211_conn_failed(struct net_device *dev, const u8 *mac_addr, enum nl80211_connect_failed_reason reason, gfp_t gfp); /** * struct cfg80211_rx_info - received management frame info * * @freq: Frequency on which the frame was received in kHz * @sig_dbm: signal strength in dBm, or 0 if unknown * @have_link_id: indicates the frame was received on a link of * an MLD, i.e. the @link_id field is valid * @link_id: the ID of the link the frame was received on * @buf: Management frame (header + body) * @len: length of the frame data * @flags: flags, as defined in &enum nl80211_rxmgmt_flags * @rx_tstamp: Hardware timestamp of frame RX in nanoseconds * @ack_tstamp: Hardware timestamp of ack TX in nanoseconds */ struct cfg80211_rx_info { int freq; int sig_dbm; bool have_link_id; u8 link_id; const u8 *buf; size_t len; u32 flags; u64 rx_tstamp; u64 ack_tstamp; }; /** * cfg80211_rx_mgmt_ext - management frame notification with extended info * @wdev: wireless device receiving the frame * @info: RX info as defined in struct cfg80211_rx_info * * This function is called whenever an Action frame is received for a station * mode interface, but is not processed in kernel. * * Return: %true if a user space application has registered for this frame. * For action frames, that makes it responsible for rejecting unrecognized * action frames; %false otherwise, in which case for action frames the * driver is responsible for rejecting the frame. */ bool cfg80211_rx_mgmt_ext(struct wireless_dev *wdev, struct cfg80211_rx_info *info); /** * cfg80211_rx_mgmt_khz - notification of received, unprocessed management frame * @wdev: wireless device receiving the frame * @freq: Frequency on which the frame was received in KHz * @sig_dbm: signal strength in dBm, or 0 if unknown * @buf: Management frame (header + body) * @len: length of the frame data * @flags: flags, as defined in enum nl80211_rxmgmt_flags * * This function is called whenever an Action frame is received for a station * mode interface, but is not processed in kernel. * * Return: %true if a user space application has registered for this frame. * For action frames, that makes it responsible for rejecting unrecognized * action frames; %false otherwise, in which case for action frames the * driver is responsible for rejecting the frame. */ static inline bool cfg80211_rx_mgmt_khz(struct wireless_dev *wdev, int freq, int sig_dbm, const u8 *buf, size_t len, u32 flags) { struct cfg80211_rx_info info = { .freq = freq, .sig_dbm = sig_dbm, .buf = buf, .len = len, .flags = flags }; return cfg80211_rx_mgmt_ext(wdev, &info); } /** * cfg80211_rx_mgmt - notification of received, unprocessed management frame * @wdev: wireless device receiving the frame * @freq: Frequency on which the frame was received in MHz * @sig_dbm: signal strength in dBm, or 0 if unknown * @buf: Management frame (header + body) * @len: length of the frame data * @flags: flags, as defined in enum nl80211_rxmgmt_flags * * This function is called whenever an Action frame is received for a station * mode interface, but is not processed in kernel. * * Return: %true if a user space application has registered for this frame. * For action frames, that makes it responsible for rejecting unrecognized * action frames; %false otherwise, in which case for action frames the * driver is responsible for rejecting the frame. */ static inline bool cfg80211_rx_mgmt(struct wireless_dev *wdev, int freq, int sig_dbm, const u8 *buf, size_t len, u32 flags) { struct cfg80211_rx_info info = { .freq = MHZ_TO_KHZ(freq), .sig_dbm = sig_dbm, .buf = buf, .len = len, .flags = flags }; return cfg80211_rx_mgmt_ext(wdev, &info); } /** * struct cfg80211_tx_status - TX status for management frame information * * @cookie: Cookie returned by cfg80211_ops::mgmt_tx() * @tx_tstamp: hardware TX timestamp in nanoseconds * @ack_tstamp: hardware ack RX timestamp in nanoseconds * @buf: Management frame (header + body) * @len: length of the frame data * @ack: Whether frame was acknowledged */ struct cfg80211_tx_status { u64 cookie; u64 tx_tstamp; u64 ack_tstamp; const u8 *buf; size_t len; bool ack; }; /** * cfg80211_mgmt_tx_status_ext - TX status notification with extended info * @wdev: wireless device receiving the frame * @status: TX status data * @gfp: context flags * * This function is called whenever a management frame was requested to be * transmitted with cfg80211_ops::mgmt_tx() to report the TX status of the * transmission attempt with extended info. */ void cfg80211_mgmt_tx_status_ext(struct wireless_dev *wdev, struct cfg80211_tx_status *status, gfp_t gfp); /** * cfg80211_mgmt_tx_status - notification of TX status for management frame * @wdev: wireless device receiving the frame * @cookie: Cookie returned by cfg80211_ops::mgmt_tx() * @buf: Management frame (header + body) * @len: length of the frame data * @ack: Whether frame was acknowledged * @gfp: context flags * * This function is called whenever a management frame was requested to be * transmitted with cfg80211_ops::mgmt_tx() to report the TX status of the * transmission attempt. */ static inline void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, const u8 *buf, size_t len, bool ack, gfp_t gfp) { struct cfg80211_tx_status status = { .cookie = cookie, .buf = buf, .len = len, .ack = ack }; cfg80211_mgmt_tx_status_ext(wdev, &status, gfp); } /** * cfg80211_control_port_tx_status - notification of TX status for control * port frames * @wdev: wireless device receiving the frame * @cookie: Cookie returned by cfg80211_ops::tx_control_port() * @buf: Data frame (header + body) * @len: length of the frame data * @ack: Whether frame was acknowledged * @gfp: context flags * * This function is called whenever a control port frame was requested to be * transmitted with cfg80211_ops::tx_control_port() to report the TX status of * the transmission attempt. */ void cfg80211_control_port_tx_status(struct wireless_dev *wdev, u64 cookie, const u8 *buf, size_t len, bool ack, gfp_t gfp); /** * cfg80211_rx_control_port - notification about a received control port frame * @dev: The device the frame matched to * @skb: The skbuf with the control port frame. It is assumed that the skbuf * is 802.3 formatted (with 802.3 header). The skb can be non-linear. * This function does not take ownership of the skb, so the caller is * responsible for any cleanup. The caller must also ensure that * skb->protocol is set appropriately. * @unencrypted: Whether the frame was received unencrypted * @link_id: the link the frame was received on, -1 if not applicable or unknown * * This function is used to inform userspace about a received control port * frame. It should only be used if userspace indicated it wants to receive * control port frames over nl80211. * * The frame is the data portion of the 802.3 or 802.11 data frame with all * network layer headers removed (e.g. the raw EAPoL frame). * * Return: %true if the frame was passed to userspace */ bool cfg80211_rx_control_port(struct net_device *dev, struct sk_buff *skb, bool unencrypted, int link_id); /** * cfg80211_cqm_rssi_notify - connection quality monitoring rssi event * @dev: network device * @rssi_event: the triggered RSSI event * @rssi_level: new RSSI level value or 0 if not available * @gfp: context flags * * This function is called when a configured connection quality monitoring * rssi threshold reached event occurs. */ void cfg80211_cqm_rssi_notify(struct net_device *dev, enum nl80211_cqm_rssi_threshold_event rssi_event, s32 rssi_level, gfp_t gfp); /** * cfg80211_cqm_pktloss_notify - notify userspace about packetloss to peer * @dev: network device * @peer: peer's MAC address * @num_packets: how many packets were lost -- should be a fixed threshold * but probably no less than maybe 50, or maybe a throughput dependent * threshold (to account for temporary interference) * @gfp: context flags */ void cfg80211_cqm_pktloss_notify(struct net_device *dev, const u8 *peer, u32 num_packets, gfp_t gfp); /** * cfg80211_cqm_txe_notify - TX error rate event * @dev: network device * @peer: peer's MAC address * @num_packets: how many packets were lost * @rate: % of packets which failed transmission * @intvl: interval (in s) over which the TX failure threshold was breached. * @gfp: context flags * * Notify userspace when configured % TX failures over number of packets in a * given interval is exceeded. */ void cfg80211_cqm_txe_notify(struct net_device *dev, const u8 *peer, u32 num_packets, u32 rate, u32 intvl, gfp_t gfp); /** * cfg80211_cqm_beacon_loss_notify - beacon loss event * @dev: network device * @gfp: context flags * * Notify userspace about beacon loss from the connected AP. */ void cfg80211_cqm_beacon_loss_notify(struct net_device *dev, gfp_t gfp); /** * __cfg80211_radar_event - radar detection event * @wiphy: the wiphy * @chandef: chandef for the current channel * @offchan: the radar has been detected on the offchannel chain * @gfp: context flags * * This function is called when a radar is detected on the current chanenl. */ void __cfg80211_radar_event(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, bool offchan, gfp_t gfp); static inline void cfg80211_radar_event(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, gfp_t gfp) { __cfg80211_radar_event(wiphy, chandef, false, gfp); } static inline void cfg80211_background_radar_event(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, gfp_t gfp) { __cfg80211_radar_event(wiphy, chandef, true, gfp); } /** * cfg80211_sta_opmode_change_notify - STA's ht/vht operation mode change event * @dev: network device * @mac: MAC address of a station which opmode got modified * @sta_opmode: station's current opmode value * @gfp: context flags * * Driver should call this function when station's opmode modified via action * frame. */ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, struct sta_opmode_info *sta_opmode, gfp_t gfp); /** * cfg80211_cac_event - Channel availability check (CAC) event * @netdev: network device * @chandef: chandef for the current channel * @event: type of event * @gfp: context flags * @link_id: valid link_id for MLO operation or 0 otherwise. * * This function is called when a Channel availability check (CAC) is finished * or aborted. This must be called to notify the completion of a CAC process, * also by full-MAC drivers. */ void cfg80211_cac_event(struct net_device *netdev, const struct cfg80211_chan_def *chandef, enum nl80211_radar_event event, gfp_t gfp, unsigned int link_id); /** * cfg80211_background_cac_abort - Channel Availability Check offchan abort event * @wiphy: the wiphy * * This function is called by the driver when a Channel Availability Check * (CAC) is aborted by a offchannel dedicated chain. */ void cfg80211_background_cac_abort(struct wiphy *wiphy); /** * cfg80211_gtk_rekey_notify - notify userspace about driver rekeying * @dev: network device * @bssid: BSSID of AP (to avoid races) * @replay_ctr: new replay counter * @gfp: allocation flags */ void cfg80211_gtk_rekey_notify(struct net_device *dev, const u8 *bssid, const u8 *replay_ctr, gfp_t gfp); /** * cfg80211_pmksa_candidate_notify - notify about PMKSA caching candidate * @dev: network device * @index: candidate index (the smaller the index, the higher the priority) * @bssid: BSSID of AP * @preauth: Whether AP advertises support for RSN pre-authentication * @gfp: allocation flags */ void cfg80211_pmksa_candidate_notify(struct net_device *dev, int index, const u8 *bssid, bool preauth, gfp_t gfp); /** * cfg80211_rx_spurious_frame - inform userspace about a spurious frame * @dev: The device the frame matched to * @link_id: the link the frame was received on, -1 if not applicable or unknown * @addr: the transmitter address * @gfp: context flags * * This function is used in AP mode to inform userspace that a spurious * class 3 frame was received, to be able to deauth the sender. * It is also used in NAN_DATA mode to report frames from unknown peers * (A2 not assigned to any active NDP), per Wi-Fi Aware (TM) 4.0 specification 6.2.5. * Return: %true if the frame was passed to userspace (or this failed * for a reason other than not having a subscription.) */ bool cfg80211_rx_spurious_frame(struct net_device *dev, const u8 *addr, int link_id, gfp_t gfp); /** * cfg80211_rx_unexpected_4addr_frame - inform about unexpected WDS frame * @dev: The device the frame matched to * @addr: the transmitter address * @link_id: the link the frame was received on, -1 if not applicable or unknown * @gfp: context flags * * This function is used in AP mode (only!) to inform userspace that * an associated station sent a 4addr frame but that wasn't expected. * It is allowed and desirable to send this event only once for each * station to avoid event flooding. * Return: %true if the frame was passed to userspace (or this failed * for a reason other than not having a subscription.) */ bool cfg80211_rx_unexpected_4addr_frame(struct net_device *dev, const u8 *addr, int link_id, gfp_t gfp); /** * cfg80211_probe_status - notify userspace about probe status * @dev: the device the probe was sent on * @addr: the address of the peer * @cookie: the cookie filled in @probe_client previously * @acked: indicates whether probe was acked or not * @ack_signal: signal strength (in dBm) of the ACK frame. * @is_valid_ack_signal: indicates the ack_signal is valid or not. * @gfp: allocation flags */ void cfg80211_probe_status(struct net_device *dev, const u8 *addr, u64 cookie, bool acked, s32 ack_signal, bool is_valid_ack_signal, gfp_t gfp); /** * cfg80211_report_obss_beacon_khz - report beacon from other APs * @wiphy: The wiphy that received the beacon * @frame: the frame * @len: length of the frame * @freq: frequency the frame was received on in KHz * @sig_dbm: signal strength in dBm, or 0 if unknown * * Use this function to report to userspace when a beacon was * received. It is not useful to call this when there is no * netdev that is in AP/GO mode. */ void cfg80211_report_obss_beacon_khz(struct wiphy *wiphy, const u8 *frame, size_t len, int freq, int sig_dbm); /** * cfg80211_report_obss_beacon - report beacon from other APs * @wiphy: The wiphy that received the beacon * @frame: the frame * @len: length of the frame * @freq: frequency the frame was received on * @sig_dbm: signal strength in dBm, or 0 if unknown * * Use this function to report to userspace when a beacon was * received. It is not useful to call this when there is no * netdev that is in AP/GO mode. */ static inline void cfg80211_report_obss_beacon(struct wiphy *wiphy, const u8 *frame, size_t len, int freq, int sig_dbm) { cfg80211_report_obss_beacon_khz(wiphy, frame, len, MHZ_TO_KHZ(freq), sig_dbm); } /** * struct cfg80211_beaconing_check_config - beacon check configuration * @iftype: the interface type to check for * @relax: allow IR-relaxation conditions to apply (e.g. another * interface connected already on the same channel) * NOTE: If this is set, wiphy mutex must be held. * @reg_power: &enum ieee80211_ap_reg_power value indicating the * advertised/used 6 GHz regulatory power setting */ struct cfg80211_beaconing_check_config { enum nl80211_iftype iftype; enum ieee80211_ap_reg_power reg_power; bool relax; }; /** * cfg80211_reg_check_beaconing - check if beaconing is allowed * @wiphy: the wiphy * @chandef: the channel definition * @cfg: additional parameters for the checking * * Return: %true if there is no secondary channel or the secondary channel(s) * can be used for beaconing (i.e. is not a radar channel etc.) */ bool cfg80211_reg_check_beaconing(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, struct cfg80211_beaconing_check_config *cfg); /** * cfg80211_reg_can_beacon - check if beaconing is allowed * @wiphy: the wiphy * @chandef: the channel definition * @iftype: interface type * * Return: %true if there is no secondary channel or the secondary channel(s) * can be used for beaconing (i.e. is not a radar channel etc.) */ static inline bool cfg80211_reg_can_beacon(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_iftype iftype) { struct cfg80211_beaconing_check_config config = { .iftype = iftype, }; return cfg80211_reg_check_beaconing(wiphy, chandef, &config); } /** * cfg80211_reg_can_beacon_relax - check if beaconing is allowed with relaxation * @wiphy: the wiphy * @chandef: the channel definition * @iftype: interface type * * Return: %true if there is no secondary channel or the secondary channel(s) * can be used for beaconing (i.e. is not a radar channel etc.). This version * also checks if IR-relaxation conditions apply, to allow beaconing under * more permissive conditions. * * Context: Requires the wiphy mutex to be held. */ static inline bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_iftype iftype) { struct cfg80211_beaconing_check_config config = { .iftype = iftype, .relax = true, }; return cfg80211_reg_check_beaconing(wiphy, chandef, &config); } /** * cfg80211_ch_switch_notify - update wdev channel and notify userspace * @dev: the device which switched channels * @chandef: the new channel definition * @link_id: the link ID for MLO, must be 0 for non-MLO * * Caller must hold wiphy mutex, therefore must only be called from sleepable * driver context! */ void cfg80211_ch_switch_notify(struct net_device *dev, struct cfg80211_chan_def *chandef, unsigned int link_id); /** * cfg80211_ch_switch_started_notify - notify channel switch start * @dev: the device on which the channel switch started * @chandef: the future channel definition * @link_id: the link ID for MLO, must be 0 for non-MLO * @count: the number of TBTTs until the channel switch happens * @quiet: whether or not immediate quiet was requested by the AP * * Inform the userspace about the channel switch that has just * started, so that it can take appropriate actions (eg. starting * channel switch on other vifs), if necessary. */ void cfg80211_ch_switch_started_notify(struct net_device *dev, struct cfg80211_chan_def *chandef, unsigned int link_id, u8 count, bool quiet); /** * ieee80211_operating_class_to_band - convert operating class to band * * @operating_class: the operating class to convert * @band: band pointer to fill * * Return: %true if the conversion was successful, %false otherwise. */ bool ieee80211_operating_class_to_band(u8 operating_class, enum nl80211_band *band); /** * ieee80211_operating_class_to_chandef - convert operating class to chandef * * @operating_class: the operating class to convert * @chan: the ieee80211_channel to convert * @chandef: a pointer to the resulting chandef * * Return: %true if the conversion was successful, %false otherwise. */ bool ieee80211_operating_class_to_chandef(u8 operating_class, struct ieee80211_channel *chan, struct cfg80211_chan_def *chandef); /** * ieee80211_chandef_to_operating_class - convert chandef to operation class * * @chandef: the chandef to convert * @op_class: a pointer to the resulting operating class * * Return: %true if the conversion was successful, %false otherwise. */ bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class); /** * ieee80211_chandef_to_khz - convert chandef to frequency in KHz * * @chandef: the chandef to convert * * Return: the center frequency of chandef (1st segment) in KHz. */ static inline u32 ieee80211_chandef_to_khz(const struct cfg80211_chan_def *chandef) { return MHZ_TO_KHZ(chandef->center_freq1) + chandef->freq1_offset; } /** * cfg80211_tdls_oper_request - request userspace to perform TDLS operation * @dev: the device on which the operation is requested * @peer: the MAC address of the peer device * @oper: the requested TDLS operation (NL80211_TDLS_SETUP or * NL80211_TDLS_TEARDOWN) * @reason_code: the reason code for teardown request * @gfp: allocation flags * * This function is used to request userspace to perform TDLS operation that * requires knowledge of keys, i.e., link setup or teardown when the AP * connection uses encryption. This is optional mechanism for the driver to use * if it can automatically determine when a TDLS link could be useful (e.g., * based on traffic and signal strength for a peer). */ void cfg80211_tdls_oper_request(struct net_device *dev, const u8 *peer, enum nl80211_tdls_operation oper, u16 reason_code, gfp_t gfp); /** * cfg80211_calculate_bitrate - calculate actual bitrate (in 100Kbps units) * @rate: given rate_info to calculate bitrate from * * Return: calculated bitrate */ u32 cfg80211_calculate_bitrate(struct rate_info *rate); /** * cfg80211_unregister_wdev - remove the given wdev * @wdev: struct wireless_dev to remove * * This function removes the device so it can no longer be used. It is necessary * to call this function even when cfg80211 requests the removal of the device * by calling the del_virtual_intf() callback. The function must also be called * when the driver wishes to unregister the wdev, e.g. when the hardware device * is unbound from the driver. * * Context: Requires the RTNL and wiphy mutex to be held. */ void cfg80211_unregister_wdev(struct wireless_dev *wdev); /** * cfg80211_register_netdevice - register the given netdev * @dev: the netdev to register * * Note: In contexts coming from cfg80211 callbacks, you must call this rather * than register_netdevice(), unregister_netdev() is impossible as the RTNL is * held. Otherwise, both register_netdevice() and register_netdev() are usable * instead as well. * * Context: Requires the RTNL and wiphy mutex to be held. * * Return: 0 on success. Non-zero on error. */ int cfg80211_register_netdevice(struct net_device *dev); /** * cfg80211_unregister_netdevice - unregister the given netdev * @dev: the netdev to register * * Note: In contexts coming from cfg80211 callbacks, you must call this rather * than unregister_netdevice(), unregister_netdev() is impossible as the RTNL * is held. Otherwise, both unregister_netdevice() and unregister_netdev() are * usable instead as well. * * Context: Requires the RTNL and wiphy mutex to be held. */ static inline void cfg80211_unregister_netdevice(struct net_device *dev) { #if IS_ENABLED(CONFIG_CFG80211) cfg80211_unregister_wdev(dev->ieee80211_ptr); #endif } /** * struct cfg80211_ft_event_params - FT Information Elements * @ies: FT IEs * @ies_len: length of the FT IE in bytes * @target_ap: target AP's MAC address * @ric_ies: RIC IE * @ric_ies_len: length of the RIC IE in bytes */ struct cfg80211_ft_event_params { const u8 *ies; size_t ies_len; const u8 *target_ap; const u8 *ric_ies; size_t ric_ies_len; }; /** * cfg80211_ft_event - notify userspace about FT IE and RIC IE * @netdev: network device * @ft_event: IE information */ void cfg80211_ft_event(struct net_device *netdev, struct cfg80211_ft_event_params *ft_event); /** * cfg80211_get_p2p_attr - find and copy a P2P attribute from IE buffer * @ies: the input IE buffer * @len: the input length * @attr: the attribute ID to find * @buf: output buffer, can be %NULL if the data isn't needed, e.g. * if the function is only called to get the needed buffer size * @bufsize: size of the output buffer * * The function finds a given P2P attribute in the (vendor) IEs and * copies its contents to the given buffer. * * Return: A negative error code (-%EILSEQ or -%ENOENT) if the data is * malformed or the attribute can't be found (respectively), or the * length of the found attribute (which can be zero). */ int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, enum ieee80211_p2p_attr_id attr, u8 *buf, unsigned int bufsize); /** * ieee80211_ie_split_ric - split an IE buffer according to ordering (with RIC) * @ies: the IE buffer * @ielen: the length of the IE buffer * @ids: an array with element IDs that are allowed before * the split. A WLAN_EID_EXTENSION value means that the next * EID in the list is a sub-element of the EXTENSION IE. * @n_ids: the size of the element ID array * @after_ric: array IE types that come after the RIC element * @n_after_ric: size of the @after_ric array * @offset: offset where to start splitting in the buffer * * This function splits an IE buffer by updating the @offset * variable to point to the location where the buffer should be * split. * * It assumes that the given IE buffer is well-formed, this * has to be guaranteed by the caller! * * It also assumes that the IEs in the buffer are ordered * correctly, if not the result of using this function will not * be ordered correctly either, i.e. it does no reordering. * * Return: The offset where the next part of the buffer starts, which * may be @ielen if the entire (remainder) of the buffer should be * used. */ size_t ieee80211_ie_split_ric(const u8 *ies, size_t ielen, const u8 *ids, int n_ids, const u8 *after_ric, int n_after_ric, size_t offset); /** * ieee80211_ie_split - split an IE buffer according to ordering * @ies: the IE buffer * @ielen: the length of the IE buffer * @ids: an array with element IDs that are allowed before * the split. A WLAN_EID_EXTENSION value means that the next * EID in the list is a sub-element of the EXTENSION IE. * @n_ids: the size of the element ID array * @offset: offset where to start splitting in the buffer * * This function splits an IE buffer by updating the @offset * variable to point to the location where the buffer should be * split. * * It assumes that the given IE buffer is well-formed, this * has to be guaranteed by the caller! * * It also assumes that the IEs in the buffer are ordered * correctly, if not the result of using this function will not * be ordered correctly either, i.e. it does no reordering. * * Return: The offset where the next part of the buffer starts, which * may be @ielen if the entire (remainder) of the buffer should be * used. */ static inline size_t ieee80211_ie_split(const u8 *ies, size_t ielen, const u8 *ids, int n_ids, size_t offset) { return ieee80211_ie_split_ric(ies, ielen, ids, n_ids, NULL, 0, offset); } /** * ieee80211_fragment_element - fragment the last element in skb * @skb: The skbuf that the element was added to * @len_pos: Pointer to length of the element to fragment * @frag_id: The element ID to use for fragments * * This function fragments all data after @len_pos, adding fragmentation * elements with the given ID as appropriate. The SKB will grow in size * accordingly. */ void ieee80211_fragment_element(struct sk_buff *skb, u8 *len_pos, u8 frag_id); /** * cfg80211_report_wowlan_wakeup - report wakeup from WoWLAN * @wdev: the wireless device reporting the wakeup * @wakeup: the wakeup report * @gfp: allocation flags * * This function reports that the given device woke up. If it * caused the wakeup, report the reason(s), otherwise you may * pass %NULL as the @wakeup parameter to advertise that something * else caused the wakeup. */ void cfg80211_report_wowlan_wakeup(struct wireless_dev *wdev, struct cfg80211_wowlan_wakeup *wakeup, gfp_t gfp); /** * cfg80211_crit_proto_stopped() - indicate critical protocol stopped by driver. * * @wdev: the wireless device for which critical protocol is stopped. * @gfp: allocation flags * * This function can be called by the driver to indicate it has reverted * operation back to normal. One reason could be that the duration given * by .crit_proto_start() has expired. */ void cfg80211_crit_proto_stopped(struct wireless_dev *wdev, gfp_t gfp); /** * ieee80211_get_num_supported_channels - get number of channels device has * @wiphy: the wiphy * * Return: the number of channels supported by the device. */ unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy); /** * cfg80211_check_combinations - check interface combinations * * @wiphy: the wiphy * @params: the interface combinations parameter * * This function can be called by the driver to check whether a * combination of interfaces and their types are allowed according to * the interface combinations. * * Return: 0 if combinations are allowed. Non-zero on error. */ int cfg80211_check_combinations(struct wiphy *wiphy, struct iface_combination_params *params); /** * cfg80211_iter_combinations - iterate over matching combinations * * @wiphy: the wiphy * @params: the interface combinations parameter * @iter: function to call for each matching combination * @data: pointer to pass to iter function * * This function can be called by the driver to check what possible * combinations it fits in at a given moment, e.g. for channel switching * purposes. * * Return: 0 on success. Non-zero on error. */ int cfg80211_iter_combinations(struct wiphy *wiphy, struct iface_combination_params *params, void (*iter)(const struct ieee80211_iface_combination *c, void *data), void *data); /** * cfg80211_get_radio_idx_by_chan - get the radio index by the channel * * @wiphy: the wiphy * @chan: channel for which the supported radio index is required * * Return: radio index on success or -EINVAL otherwise */ int cfg80211_get_radio_idx_by_chan(struct wiphy *wiphy, const struct ieee80211_channel *chan); /** * cfg80211_stop_link - stop AP/P2P_GO link if link_id is non-negative or stops * all links on the interface. * * @wiphy: the wiphy * @wdev: wireless device * @link_id: valid link ID in case of MLO AP/P2P_GO Operation or else -1 * @gfp: context flags * * If link_id is set during MLO operation, stops only the specified AP/P2P_GO * link and if link_id is set to -1 or last link is stopped, the entire * interface is stopped as if AP was stopped, IBSS/mesh left, STA disconnected. */ void cfg80211_stop_link(struct wiphy *wiphy, struct wireless_dev *wdev, int link_id, gfp_t gfp); /** * cfg80211_stop_iface - trigger interface disconnection * * @wiphy: the wiphy * @wdev: wireless device * @gfp: context flags * * Trigger interface to be stopped as if AP was stopped, IBSS/mesh left, STA * disconnected. * * Note: This doesn't need any locks and is asynchronous. */ static inline void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev, gfp_t gfp) { cfg80211_stop_link(wiphy, wdev, -1, gfp); } /** * cfg80211_shutdown_all_interfaces - shut down all interfaces for a wiphy * @wiphy: the wiphy to shut down * * This function shuts down all interfaces belonging to this wiphy by * calling dev_close() (and treating non-netdev interfaces as needed). * It shouldn't really be used unless there are some fatal device errors * that really can't be recovered in any other way. * * Callers must hold the RTNL and be able to deal with callbacks into * the driver while the function is running. */ void cfg80211_shutdown_all_interfaces(struct wiphy *wiphy); /** * wiphy_ext_feature_set - set the extended feature flag * * @wiphy: the wiphy to modify. * @ftidx: extended feature bit index. * * The extended features are flagged in multiple bytes (see * &struct wiphy.@ext_features) */ static inline void wiphy_ext_feature_set(struct wiphy *wiphy, enum nl80211_ext_feature_index ftidx) { u8 *ft_byte; ft_byte = &wiphy->ext_features[ftidx / 8]; *ft_byte |= BIT(ftidx % 8); } /** * wiphy_ext_feature_isset - check the extended feature flag * * @wiphy: the wiphy to modify. * @ftidx: extended feature bit index. * * The extended features are flagged in multiple bytes (see * &struct wiphy.@ext_features) * * Return: %true if extended feature flag is set, %false otherwise */ static inline bool wiphy_ext_feature_isset(struct wiphy *wiphy, enum nl80211_ext_feature_index ftidx) { u8 ft_byte; ft_byte = wiphy->ext_features[ftidx / 8]; return (ft_byte & BIT(ftidx % 8)) != 0; } /** * cfg80211_free_nan_func - free NAN function * @f: NAN function that should be freed * * Frees all the NAN function and all it's allocated members. */ void cfg80211_free_nan_func(struct cfg80211_nan_func *f); /** * struct cfg80211_nan_match_params - NAN match parameters * @type: the type of the function that triggered a match. If it is * %NL80211_NAN_FUNC_SUBSCRIBE it means that we replied to a subscriber. * If it is %NL80211_NAN_FUNC_PUBLISH, it means that we got a discovery * result. * If it is %NL80211_NAN_FUNC_FOLLOW_UP, we received a follow up. * @inst_id: the local instance id * @peer_inst_id: the instance id of the peer's function * @addr: the MAC address of the peer * @info_len: the length of the &info * @info: the Service Specific Info from the peer (if any) * @cookie: unique identifier of the corresponding function */ struct cfg80211_nan_match_params { enum nl80211_nan_function_type type; u8 inst_id; u8 peer_inst_id; const u8 *addr; u8 info_len; const u8 *info; u64 cookie; }; /** * cfg80211_nan_match - report a match for a NAN function. * @wdev: the wireless device reporting the match * @match: match notification parameters * @gfp: allocation flags * * This function reports that the a NAN function had a match. This * can be a subscribe that had a match or a solicited publish that * was sent. It can also be a follow up that was received. */ void cfg80211_nan_match(struct wireless_dev *wdev, struct cfg80211_nan_match_params *match, gfp_t gfp); /** * cfg80211_nan_func_terminated - notify about NAN function termination. * * @wdev: the wireless device reporting the match * @inst_id: the local instance id * @reason: termination reason (one of the NL80211_NAN_FUNC_TERM_REASON_*) * @cookie: unique NAN function identifier * @gfp: allocation flags * * This function reports that the a NAN function is terminated. */ void cfg80211_nan_func_terminated(struct wireless_dev *wdev, u8 inst_id, enum nl80211_nan_func_term_reason reason, u64 cookie, gfp_t gfp); /** * cfg80211_nan_sched_update_done - notify deferred schedule update completion * @wdev: the wireless device reporting the event * @success: whether or not the schedule update was successful * @gfp: allocation flags * * This function notifies user space that a deferred local NAN schedule update * (requested with %NL80211_ATTR_NAN_SCHED_DEFERRED) has been completed. */ void cfg80211_nan_sched_update_done(struct wireless_dev *wdev, bool success, gfp_t gfp); /* ethtool helper */ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info); /** * cfg80211_external_auth_request - userspace request for authentication * @netdev: network device * @params: External authentication parameters * @gfp: allocation flags * Returns: 0 on success, < 0 on error */ int cfg80211_external_auth_request(struct net_device *netdev, struct cfg80211_external_auth_params *params, gfp_t gfp); /** * cfg80211_pmsr_report - report peer measurement result data * @wdev: the wireless device reporting the measurement * @req: the original measurement request * @result: the result data * @gfp: allocation flags */ void cfg80211_pmsr_report(struct wireless_dev *wdev, struct cfg80211_pmsr_request *req, struct cfg80211_pmsr_result *result, gfp_t gfp); /** * cfg80211_pmsr_complete - report peer measurement completed * @wdev: the wireless device reporting the measurement * @req: the original measurement request * @gfp: allocation flags * * Report that the entire measurement completed, after this * the request pointer will no longer be valid. */ void cfg80211_pmsr_complete(struct wireless_dev *wdev, struct cfg80211_pmsr_request *req, gfp_t gfp); /** * cfg80211_iftype_allowed - check whether the interface can be allowed * @wiphy: the wiphy * @iftype: interface type * @is_4addr: use_4addr flag, must be '0' when check_swif is '1' * @check_swif: check iftype against software interfaces * * Check whether the interface is allowed to operate; additionally, this API * can be used to check iftype against the software interfaces when * check_swif is '1'. * * Return: %true if allowed, %false otherwise */ bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, bool is_4addr, u8 check_swif); /** * cfg80211_assoc_comeback - notification of association that was * temporarily rejected with a comeback * @netdev: network device * @ap_addr: AP (MLD) address that rejected the association * @timeout: timeout interval value TUs. * * this function may sleep. the caller must hold the corresponding wdev's mutex. */ void cfg80211_assoc_comeback(struct net_device *netdev, const u8 *ap_addr, u32 timeout); /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ #define wiphy_printk(level, wiphy, format, args...) \ dev_printk(level, &(wiphy)->dev, format, ##args) #define wiphy_emerg(wiphy, format, args...) \ dev_emerg(&(wiphy)->dev, format, ##args) #define wiphy_alert(wiphy, format, args...) \ dev_alert(&(wiphy)->dev, format, ##args) #define wiphy_crit(wiphy, format, args...) \ dev_crit(&(wiphy)->dev, format, ##args) #define wiphy_err(wiphy, format, args...) \ dev_err(&(wiphy)->dev, format, ##args) #define wiphy_warn(wiphy, format, args...) \ dev_warn(&(wiphy)->dev, format, ##args) #define wiphy_notice(wiphy, format, args...) \ dev_notice(&(wiphy)->dev, format, ##args) #define wiphy_info(wiphy, format, args...) \ dev_info(&(wiphy)->dev, format, ##args) #define wiphy_info_once(wiphy, format, args...) \ dev_info_once(&(wiphy)->dev, format, ##args) #define wiphy_err_ratelimited(wiphy, format, args...) \ dev_err_ratelimited(&(wiphy)->dev, format, ##args) #define wiphy_warn_ratelimited(wiphy, format, args...) \ dev_warn_ratelimited(&(wiphy)->dev, format, ##args) #define wiphy_debug(wiphy, format, args...) \ wiphy_printk(KERN_DEBUG, wiphy, format, ##args) #define wiphy_dbg(wiphy, format, args...) \ dev_dbg(&(wiphy)->dev, format, ##args) #if defined(VERBOSE_DEBUG) #define wiphy_vdbg wiphy_dbg #else #define wiphy_vdbg(wiphy, format, args...) \ ({ \ if (0) \ wiphy_printk(KERN_DEBUG, wiphy, format, ##args); \ 0; \ }) #endif /* * wiphy_WARN() acts like wiphy_printk(), but with the key difference * of using a WARN/WARN_ON to get the message out, including the * file/line information and a backtrace. */ #define wiphy_WARN(wiphy, format, args...) \ WARN(1, "wiphy: %s\n" format, wiphy_name(wiphy), ##args); /** * cfg80211_update_owe_info_event - Notify the peer's OWE info to user space * @netdev: network device * @owe_info: peer's owe info * @gfp: allocation flags */ void cfg80211_update_owe_info_event(struct net_device *netdev, struct cfg80211_update_owe_info *owe_info, gfp_t gfp); /** * cfg80211_bss_flush - resets all the scan entries * @wiphy: the wiphy */ void cfg80211_bss_flush(struct wiphy *wiphy); /** * cfg80211_bss_color_notify - notify about bss color event * @dev: network device * @cmd: the actual event we want to notify * @count: the number of TBTTs until the color change happens * @color_bitmap: representations of the colors that the local BSS is aware of * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Return: 0 on success. Non-zero on error. */ int cfg80211_bss_color_notify(struct net_device *dev, enum nl80211_commands cmd, u8 count, u64 color_bitmap, u8 link_id); /** * cfg80211_obss_color_collision_notify - notify about bss color collision * @dev: network device * @color_bitmap: representations of the colors that the local BSS is aware of * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Return: 0 on success. Non-zero on error. */ static inline int cfg80211_obss_color_collision_notify(struct net_device *dev, u64 color_bitmap, u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_OBSS_COLOR_COLLISION, 0, color_bitmap, link_id); } /** * cfg80211_color_change_started_notify - notify color change start * @dev: the device on which the color is switched * @count: the number of TBTTs until the color change happens * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Inform the userspace about the color change that has started. * * Return: 0 on success. Non-zero on error. */ static inline int cfg80211_color_change_started_notify(struct net_device *dev, u8 count, u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_COLOR_CHANGE_STARTED, count, 0, link_id); } /** * cfg80211_color_change_aborted_notify - notify color change abort * @dev: the device on which the color is switched * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Inform the userspace about the color change that has aborted. * * Return: 0 on success. Non-zero on error. */ static inline int cfg80211_color_change_aborted_notify(struct net_device *dev, u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_COLOR_CHANGE_ABORTED, 0, 0, link_id); } /** * cfg80211_color_change_notify - notify color change completion * @dev: the device on which the color was switched * @link_id: valid link_id in case of MLO or 0 for non-MLO. * * Inform the userspace about the color change that has completed. * * Return: 0 on success. Non-zero on error. */ static inline int cfg80211_color_change_notify(struct net_device *dev, u8 link_id) { return cfg80211_bss_color_notify(dev, NL80211_CMD_COLOR_CHANGE_COMPLETED, 0, 0, link_id); } /** * cfg80211_6ghz_power_type - determine AP regulatory power type * @control: control flags * @client_flags: &enum ieee80211_channel_flags for station mode to enable * SP to LPI fallback, zero otherwise. * * Return: regulatory power type from &enum ieee80211_ap_reg_power */ static inline enum ieee80211_ap_reg_power cfg80211_6ghz_power_type(u8 control, u32 client_flags) { switch (u8_get_bits(control, IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { case IEEE80211_6GHZ_CTRL_REG_LPI_AP: case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: case IEEE80211_6GHZ_CTRL_REG_AP_ROLE_NOT_RELEVANT: case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD: return IEEE80211_REG_LPI_AP; case IEEE80211_6GHZ_CTRL_REG_SP_AP: return IEEE80211_REG_SP_AP; case IEEE80211_6GHZ_CTRL_REG_VLP_AP: return IEEE80211_REG_VLP_AP; case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP: if (client_flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT) return IEEE80211_REG_LPI_AP; return IEEE80211_REG_SP_AP; default: return IEEE80211_REG_UNSET_AP; } } /** * cfg80211_links_removed - Notify about removed STA MLD setup links. * @dev: network device. * @link_mask: BIT mask of removed STA MLD setup link IDs. * * Inform cfg80211 and the userspace about removed STA MLD setup links due to * AP MLD removing the corresponding affiliated APs with Multi-Link * reconfiguration. Note that it's not valid to remove all links, in this * case disconnect instead. * Also note that the wdev mutex must be held. */ void cfg80211_links_removed(struct net_device *dev, u16 link_mask); /** * struct cfg80211_mlo_reconf_done_data - MLO reconfiguration data * @buf: MLO Reconfiguration Response frame (header + body) * @len: length of the frame data * @driver_initiated: Indicates whether the add links request is initiated by * driver. This is set to true when the link reconfiguration request * initiated by driver due to AP link recommendation requests * (Ex: BTM (BSS Transition Management) request) handling offloaded to * driver. * @added_links: BIT mask of links successfully added to the association * @links: per-link information indexed by link ID * @links.bss: the BSS that MLO reconfiguration was requested for, ownership of * the pointer moves to cfg80211 in the call to * cfg80211_mlo_reconf_add_done(). * * The BSS pointer must be set for each link for which 'add' operation was * requested in the assoc_ml_reconf callback. */ struct cfg80211_mlo_reconf_done_data { const u8 *buf; size_t len; bool driver_initiated; u16 added_links; struct { struct cfg80211_bss *bss; u8 *addr; } links[IEEE80211_MLD_MAX_NUM_LINKS]; }; /** * cfg80211_mlo_reconf_add_done - Notify about MLO reconfiguration result * @dev: network device. * @data: MLO reconfiguration done data, &struct cfg80211_mlo_reconf_done_data * * Inform cfg80211 and the userspace that processing of ML reconfiguration * request to add links to the association is done. */ void cfg80211_mlo_reconf_add_done(struct net_device *dev, struct cfg80211_mlo_reconf_done_data *data); /** * cfg80211_schedule_channels_check - schedule regulatory check if needed * @wdev: the wireless device to check * * In case the device supports NO_IR or DFS relaxations, schedule regulatory * channels check, as previous concurrent operation conditions may not * hold anymore. */ void cfg80211_schedule_channels_check(struct wireless_dev *wdev); /** * cfg80211_epcs_changed - Notify about a change in EPCS state * @netdev: the wireless device whose EPCS state changed * @enabled: set to true if EPCS was enabled, otherwise set to false. */ void cfg80211_epcs_changed(struct net_device *netdev, bool enabled); /** * cfg80211_next_nan_dw_notif - Notify about the next NAN Discovery Window (DW) * @wdev: Pointer to the wireless device structure * @chan: DW channel (6, 44 or 149) * @gfp: Memory allocation flags */ void cfg80211_next_nan_dw_notif(struct wireless_dev *wdev, struct ieee80211_channel *chan, gfp_t gfp); /** * cfg80211_nan_cluster_joined - Notify about NAN cluster join * @wdev: Pointer to the wireless device structure * @cluster_id: Cluster ID of the NAN cluster that was joined or started * @new_cluster: Indicates if this is a new cluster or an existing one * @gfp: Memory allocation flags * * This function is used to notify user space when a NAN cluster has been * joined, providing the cluster ID and a flag whether it is a new cluster. */ void cfg80211_nan_cluster_joined(struct wireless_dev *wdev, const u8 *cluster_id, bool new_cluster, gfp_t gfp); /** * cfg80211_nan_ulw_update - Notify user space about ULW update * @wdev: Pointer to the wireless device structure * @ulw: Pointer to the ULW blob data * @ulw_len: Length of the ULW blob in bytes * @gfp: Memory allocation flags * * This function is used by drivers to notify user space when the device's * ULW (Unaligned Schedule) blob has been updated. User space can use this * blob to attach to frames sent to peers. */ void cfg80211_nan_ulw_update(struct wireless_dev *wdev, const u8 *ulw, size_t ulw_len, gfp_t gfp); /** * cfg80211_nan_channel_evac - Notify user space about NAN channel evacuation * @wdev: Pointer to the wireless device structure * @chandef: Pointer to the channel definition of the NAN channel that was * evacuated * @gfp: Memory allocation flags * * This function is used by drivers to notify user space when a NAN * channel has been evacuated (i.e. ULWed) due to channel resource conflicts * with other interfaces. * This can happen when another interface sharing the channel resource with NAN * needs to move to a different channel (e.g. due to channel switch or link * switch). User space may reconfigure the local schedule to exclude the * evacuated channel. */ void cfg80211_nan_channel_evac(struct wireless_dev *wdev, const struct cfg80211_chan_def *chandef, gfp_t gfp); #ifdef CONFIG_CFG80211_DEBUGFS /** * wiphy_locked_debugfs_read - do a locked read in debugfs * @wiphy: the wiphy to use * @file: the file being read * @buf: the buffer to fill and then read from * @bufsize: size of the buffer * @userbuf: the user buffer to copy to * @count: read count * @ppos: read position * @handler: the read handler to call (under wiphy lock) * @data: additional data to pass to the read handler * * Return: the number of characters read, or a negative errno */ ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file, char *buf, size_t bufsize, char __user *userbuf, size_t count, loff_t *ppos, ssize_t (*handler)(struct wiphy *wiphy, struct file *file, char *buf, size_t bufsize, void *data), void *data); /** * wiphy_locked_debugfs_write - do a locked write in debugfs * @wiphy: the wiphy to use * @file: the file being written to * @buf: the buffer to copy the user data to * @bufsize: size of the buffer * @userbuf: the user buffer to copy from * @count: read count * @handler: the write handler to call (under wiphy lock) * @data: additional data to pass to the write handler * * Return: the number of characters written, or a negative errno */ ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy, struct file *file, char *buf, size_t bufsize, const char __user *userbuf, size_t count, ssize_t (*handler)(struct wiphy *wiphy, struct file *file, char *buf, size_t count, void *data), void *data); #endif /** * cfg80211_s1g_get_start_freq_khz - get S1G chandef start frequency * @chandef: the chandef to use * * Return: the chandefs starting frequency in KHz */ static inline u32 cfg80211_s1g_get_start_freq_khz(const struct cfg80211_chan_def *chandef) { u32 bw_mhz = cfg80211_chandef_get_width(chandef); u32 center_khz = MHZ_TO_KHZ(chandef->center_freq1) + chandef->freq1_offset; return center_khz - bw_mhz * 500 + 500; } /** * cfg80211_s1g_get_end_freq_khz - get S1G chandef end frequency * @chandef: the chandef to use * * Return: the chandefs ending frequency in KHz */ static inline u32 cfg80211_s1g_get_end_freq_khz(const struct cfg80211_chan_def *chandef) { u32 bw_mhz = cfg80211_chandef_get_width(chandef); u32 center_khz = MHZ_TO_KHZ(chandef->center_freq1) + chandef->freq1_offset; return center_khz + bw_mhz * 500 - 500; } /** * cfg80211_s1g_get_primary_sibling - retrieve the sibling 1MHz subchannel * for an S1G chandef using a 2MHz primary channel. * @wiphy: wiphy the channel belongs to * @chandef: the chandef to use * * When chandef::s1g_primary_2mhz is set to true, we are operating on a 2MHz * primary channel. The 1MHz subchannel designated by the primary channel * location exists within chandef::chan, whilst the 'sibling' is denoted as * being the other 1MHz subchannel that make up the 2MHz primary channel. * * Returns: the sibling 1MHz &struct ieee80211_channel, or %NULL on failure. */ static inline struct ieee80211_channel * cfg80211_s1g_get_primary_sibling(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef) { int width_mhz = cfg80211_chandef_get_width(chandef); u32 pri_1mhz_khz, sibling_1mhz_khz, op_low_1mhz_khz, pri_index; if (!chandef->s1g_primary_2mhz || width_mhz < 2) return NULL; pri_1mhz_khz = ieee80211_channel_to_khz(chandef->chan); op_low_1mhz_khz = cfg80211_s1g_get_start_freq_khz(chandef); /* * Compute the index of the primary 1 MHz subchannel within the * operating channel, relative to the lowest 1 MHz center frequency. * Flip the least significant bit to select the even/odd sibling, * then translate that index back into a channel frequency. */ pri_index = (pri_1mhz_khz - op_low_1mhz_khz) / 1000; sibling_1mhz_khz = op_low_1mhz_khz + ((pri_index ^ 1) * 1000); return ieee80211_get_channel_khz(wiphy, sibling_1mhz_khz); } /** * cfg80211_incumbent_signal_notify - Notify userspace of incumbent signal detection * @wiphy: the wiphy to use * @chandef: channel definition in which the interference was detected * @signal_interference_bitmap: bitmap indicating interference across 20 MHz segments * @gfp: allocation context for message creation and multicast; pass GFP_ATOMIC * if called from atomic context (e.g. firmware event handler), otherwise * GFP_KERNEL * * Use this function to notify userspace when an incumbent signal is detected on * the operating channel in the 6 GHz band. The notification includes the * current channel definition and a bitmap representing interference across * the operating bandwidth. Each bit in the bitmap corresponds to a 20 MHz * segment, with the lowest bit representing the lowest frequency segment. * Punctured sub-channels are included in the bitmap structure but are always * set to zero since interference detection is not performed on them. */ void cfg80211_incumbent_signal_notify(struct wiphy *wiphy, const struct cfg80211_chan_def *chandef, u32 signal_interference_bitmap, gfp_t gfp); #endif /* __NET_CFG80211_H */ |
| 1567 1022 1505 58 506 26 26 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_TASK_H #define _LINUX_SCHED_TASK_H /* * Interface between the scheduler and various task lifetime (fork()/exit()) * functionality: */ #include <linux/rcupdate.h> #include <linux/refcount.h> #include <linux/sched.h> #include <linux/uaccess.h> struct task_struct; struct rusage; union thread_union; struct css_set; /* All the bits taken by the old clone syscall. */ #define CLONE_LEGACY_FLAGS 0xffffffffULL struct kernel_clone_args { u64 flags; int __user *pidfd; int __user *child_tid; int __user *parent_tid; const char *name; int exit_signal; u32 kthread:1; u32 io_thread:1; u32 user_worker:1; u32 no_files:1; unsigned long stack; unsigned long stack_size; unsigned long tls; pid_t *set_tid; /* Number of elements in *set_tid */ size_t set_tid_size; int cgroup; int idle; int (*fn)(void *); void *fn_arg; struct cgroup *cgrp; struct css_set *cset; unsigned int kill_seq; }; /* * This serializes "schedule()" and also protects * the run-queue from deletions/modifications (but * _adding_ to the beginning of the run-queue has * a separate lock). */ extern rwlock_t tasklist_lock; extern spinlock_t mmlist_lock; extern union thread_union init_thread_union; extern struct task_struct init_task; extern int lockdep_tasklist_lock_is_held(void); extern asmlinkage void schedule_tail(struct task_struct *prev); extern void init_idle(struct task_struct *idle, int cpu); extern int sched_fork(u64 clone_flags, struct task_struct *p); extern int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs); extern void sched_cancel_fork(struct task_struct *p); extern void sched_post_fork(struct task_struct *p); extern void sched_dead(struct task_struct *p); void __noreturn do_task_dead(void); void __noreturn make_task_dead(int signr); extern void mm_cache_init(void); extern void proc_caches_init(void); extern void fork_init(void); extern void release_task(struct task_struct * p); extern int copy_thread(struct task_struct *, const struct kernel_clone_args *); extern void flush_thread(void); #ifdef CONFIG_HAVE_EXIT_THREAD extern void exit_thread(struct task_struct *tsk); #else static inline void exit_thread(struct task_struct *tsk) { } #endif extern __noreturn void do_group_exit(int); extern void exit_files(struct task_struct *); extern void exit_itimers(struct task_struct *); extern pid_t kernel_clone(struct kernel_clone_args *kargs); struct task_struct *copy_process(struct pid *pid, int trace, int node, struct kernel_clone_args *args); struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node); struct task_struct *fork_idle(int); extern pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, unsigned long flags); extern pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags); extern long kernel_wait4(pid_t, int __user *, int, struct rusage *); int kernel_wait(pid_t pid, int *stat); extern void free_task(struct task_struct *tsk); /* sched_exec is called by processes performing an exec */ extern void sched_exec(void); static inline struct task_struct *get_task_struct(struct task_struct *t) { refcount_inc(&t->usage); return t; } static inline struct task_struct *tryget_task_struct(struct task_struct *t) { return refcount_inc_not_zero(&t->usage) ? t : NULL; } extern void __put_task_struct(struct task_struct *t); extern void __put_task_struct_rcu_cb(struct rcu_head *rhp); static inline void put_task_struct(struct task_struct *t) { if (!refcount_dec_and_test(&t->usage)) return; /* * Under PREEMPT_RT, we can't call __put_task_struct * in atomic context because it will indirectly * acquire sleeping locks. The same is true if the * current process has a mutex enqueued (blocked on * a PI chain). * * In !RT, it is always safe to call __put_task_struct(). * Though, in order to simplify the code, resort to the * deferred call too. * * call_rcu() will schedule __put_task_struct_rcu_cb() * to be called in process context. * * __put_task_struct() is called when * refcount_dec_and_test(&t->usage) succeeds. * * This means that it can't "conflict" with * put_task_struct_rcu_user() which abuses ->rcu the same * way; rcu_users has a reference so task->usage can't be * zero after rcu_users 1 -> 0 transition. * * delayed_free_task() also uses ->rcu, but it is only called * when it fails to fork a process. Therefore, there is no * way it can conflict with __put_task_struct(). */ call_rcu(&t->rcu, __put_task_struct_rcu_cb); } DEFINE_FREE(put_task, struct task_struct *, if (_T) put_task_struct(_T)) static inline void put_task_struct_many(struct task_struct *t, int nr) { if (refcount_sub_and_test(nr, &t->usage)) __put_task_struct(t); } void put_task_struct_rcu_user(struct task_struct *task); /* Free all architecture-specific resources held by a thread. */ void release_thread(struct task_struct *dead_task); #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT extern int arch_task_struct_size __read_mostly; #else # define arch_task_struct_size (sizeof(struct task_struct)) #endif #ifndef CONFIG_HAVE_ARCH_THREAD_STRUCT_WHITELIST /* * If an architecture has not declared a thread_struct whitelist we * must assume something there may need to be copied to userspace. */ static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { *offset = 0; /* Handle dynamically sized thread_struct. */ *size = arch_task_struct_size - offsetof(struct task_struct, thread); } #endif #ifdef CONFIG_VMAP_STACK static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return t->stack_vm_area; } #else static inline struct vm_struct *task_stack_vm_area(const struct task_struct *t) { return NULL; } #endif /* * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests inside of read_lock(&tasklist_lock). It must not be nested with * write_lock_irq(&tasklist_lock), neither inside nor outside. */ static inline void task_lock(struct task_struct *p) __acquires(&p->alloc_lock) { spin_lock(&p->alloc_lock); } static inline void task_unlock(struct task_struct *p) __releases(&p->alloc_lock) { spin_unlock(&p->alloc_lock); } DEFINE_LOCK_GUARD_1(task_lock, struct task_struct, task_lock(_T->lock), task_unlock(_T->lock)) DECLARE_LOCK_GUARD_1_ATTRS(task_lock, __acquires(&_T->alloc_lock), __releases(&(*(struct task_struct **)_T)->alloc_lock)) #define class_task_lock_constructor(_T) WITH_LOCK_GUARD_1_ATTRS(task_lock, _T) #endif /* _LINUX_SCHED_TASK_H */ |
| 506 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 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 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM task #if !defined(_TRACE_TASK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TASK_H #include <linux/tracepoint.h> TRACE_EVENT(task_newtask, TP_PROTO(struct task_struct *task, u64 clone_flags), TP_ARGS(task, clone_flags), TP_STRUCT__entry( __field( pid_t, pid) __array( char, comm, TASK_COMM_LEN) __field( u64, clone_flags) __field( short, oom_score_adj) ), TP_fast_assign( __entry->pid = task->pid; memcpy(__entry->comm, task->comm, TASK_COMM_LEN); __entry->clone_flags = clone_flags; __entry->oom_score_adj = task->signal->oom_score_adj; ), TP_printk("pid=%d comm=%s clone_flags=%llx oom_score_adj=%hd", __entry->pid, __entry->comm, __entry->clone_flags, __entry->oom_score_adj) ); TRACE_EVENT(task_rename, TP_PROTO(struct task_struct *task, const char *comm), TP_ARGS(task, comm), TP_STRUCT__entry( __field( pid_t, pid) __array( char, oldcomm, TASK_COMM_LEN) __array( char, newcomm, TASK_COMM_LEN) __field( short, oom_score_adj) ), TP_fast_assign( __entry->pid = task->pid; memcpy(entry->oldcomm, task->comm, TASK_COMM_LEN); strscpy(entry->newcomm, comm, TASK_COMM_LEN); __entry->oom_score_adj = task->signal->oom_score_adj; ), TP_printk("pid=%d oldcomm=%s newcomm=%s oom_score_adj=%hd", __entry->pid, __entry->oldcomm, __entry->newcomm, __entry->oom_score_adj) ); /** * task_prctl_unknown - called on unknown prctl() option * @option: option passed * @arg2: arg2 passed * @arg3: arg3 passed * @arg4: arg4 passed * @arg5: arg5 passed * * Called on an unknown prctl() option. */ TRACE_EVENT(task_prctl_unknown, TP_PROTO(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5), TP_ARGS(option, arg2, arg3, arg4, arg5), TP_STRUCT__entry( __field( int, option) __field( unsigned long, arg2) __field( unsigned long, arg3) __field( unsigned long, arg4) __field( unsigned long, arg5) ), TP_fast_assign( __entry->option = option; __entry->arg2 = arg2; __entry->arg3 = arg3; __entry->arg4 = arg4; __entry->arg5 = arg5; ), TP_printk("option=%d arg2=%ld arg3=%ld arg4=%ld arg5=%ld", __entry->option, __entry->arg2, __entry->arg3, __entry->arg4, __entry->arg5) ); #endif /* This part must be outside protection */ #include <trace/define_trace.h> |
| 5 5 11 1235 1236 9 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/etherdevice.h> #include <linux/if_macvlan.h> #include <linux/if_tap.h> #include <linux/if_vlan.h> #include <linux/interrupt.h> #include <linux/nsproxy.h> #include <linux/compat.h> #include <linux/if_tun.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/sched/signal.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/cdev.h> #include <linux/idr.h> #include <linux/fs.h> #include <linux/uio.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> #include <linux/virtio_net.h> #include <linux/skb_array.h> struct macvtap_dev { struct macvlan_dev vlan; struct tap_dev tap; }; /* * Variables for dealing with macvtaps device numbers. */ static dev_t macvtap_major; static const struct ns_common *macvtap_net_namespace(const struct device *d) { const struct net_device *dev = to_net_dev(d->parent); return to_ns_common(dev_net(dev)); } static struct class macvtap_class = { .name = "macvtap", .ns_type = &net_ns_type_operations, .namespace = macvtap_net_namespace, }; static struct cdev macvtap_cdev; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ NETIF_F_TSO6) static void macvtap_count_tx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; this_cpu_inc(vlan->pcpu_stats->tx_dropped); } static void macvtap_count_rx_dropped(struct tap_dev *tap) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; macvlan_count_rx(vlan, 0, 0, 0); } static void macvtap_update_features(struct tap_dev *tap, netdev_features_t features) { struct macvtap_dev *vlantap = container_of(tap, struct macvtap_dev, tap); struct macvlan_dev *vlan = &vlantap->vlan; vlan->set_features = features; netdev_update_features(vlan->dev); } static int macvtap_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct macvtap_dev *vlantap = netdev_priv(dev); int err; INIT_LIST_HEAD(&vlantap->tap.queue_list); /* Since macvlan supports all offloads by default, make * tap support all offloads also. */ vlantap->tap.tap_features = TUN_OFFLOADS; /* Register callbacks for rx/tx drops accounting and updating * net_device features */ vlantap->tap.count_tx_dropped = macvtap_count_tx_dropped; vlantap->tap.count_rx_dropped = macvtap_count_rx_dropped; vlantap->tap.update_features = macvtap_update_features; err = netdev_rx_handler_register(dev, tap_handle_frame, &vlantap->tap); if (err) return err; /* Don't put anything that may fail after macvlan_common_newlink * because we can't undo what it does. */ err = macvlan_common_newlink(dev, params, extack); if (err) { netdev_rx_handler_unregister(dev); return err; } vlantap->tap.dev = vlantap->vlan.dev; return 0; } static void macvtap_dellink(struct net_device *dev, struct list_head *head) { struct macvtap_dev *vlantap = netdev_priv(dev); netdev_rx_handler_unregister(dev); tap_del_queues(&vlantap->tap); macvlan_dellink(dev, head); } static void macvtap_setup(struct net_device *dev) { macvlan_common_setup(dev); dev->tx_queue_len = TUN_READQ_SIZE; } static struct net *macvtap_link_net(const struct net_device *dev) { return dev_net(macvlan_dev_real_dev(dev)); } static struct rtnl_link_ops macvtap_link_ops __read_mostly = { .kind = "macvtap", .setup = macvtap_setup, .newlink = macvtap_newlink, .dellink = macvtap_dellink, .get_link_net = macvtap_link_net, .priv_size = sizeof(struct macvtap_dev), }; static int macvtap_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct macvtap_dev *vlantap; struct device *classdev; dev_t devt; int err; char tap_name[IFNAMSIZ]; if (dev->rtnl_link_ops != &macvtap_link_ops) return NOTIFY_DONE; snprintf(tap_name, IFNAMSIZ, "tap%d", dev->ifindex); vlantap = netdev_priv(dev); switch (event) { case NETDEV_REGISTER: /* Create the device node here after the network device has * been registered but before register_netdevice has * finished running. */ err = tap_get_minor(macvtap_major, &vlantap->tap); if (err) return notifier_from_errno(err); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); classdev = device_create(&macvtap_class, &dev->dev, devt, dev, "%s", tap_name); if (IS_ERR(classdev)) { tap_free_minor(macvtap_major, &vlantap->tap); return notifier_from_errno(PTR_ERR(classdev)); } err = sysfs_create_link(&dev->dev.kobj, &classdev->kobj, tap_name); if (err) return notifier_from_errno(err); break; case NETDEV_UNREGISTER: /* vlan->minor == 0 if NETDEV_REGISTER above failed */ if (vlantap->tap.minor == 0) break; sysfs_remove_link(&dev->dev.kobj, tap_name); devt = MKDEV(MAJOR(macvtap_major), vlantap->tap.minor); device_destroy(&macvtap_class, devt); tap_free_minor(macvtap_major, &vlantap->tap); break; case NETDEV_CHANGE_TX_QUEUE_LEN: if (tap_queue_resize(&vlantap->tap)) return NOTIFY_BAD; break; } return NOTIFY_DONE; } static struct notifier_block macvtap_notifier_block __read_mostly = { .notifier_call = macvtap_device_event, }; static int __init macvtap_init(void) { int err; err = tap_create_cdev(&macvtap_cdev, &macvtap_major, "macvtap", THIS_MODULE); if (err) goto out1; err = class_register(&macvtap_class); if (err) goto out2; err = register_netdevice_notifier(&macvtap_notifier_block); if (err) goto out3; err = macvlan_link_register(&macvtap_link_ops); if (err) goto out4; return 0; out4: unregister_netdevice_notifier(&macvtap_notifier_block); out3: class_unregister(&macvtap_class); out2: tap_destroy_cdev(macvtap_major, &macvtap_cdev); out1: return err; } module_init(macvtap_init); static void __exit macvtap_exit(void) { rtnl_link_unregister(&macvtap_link_ops); unregister_netdevice_notifier(&macvtap_notifier_block); class_unregister(&macvtap_class); tap_destroy_cdev(macvtap_major, &macvtap_cdev); } module_exit(macvtap_exit); MODULE_ALIAS_RTNL_LINK("macvtap"); MODULE_DESCRIPTION("MAC-VLAN based tap driver"); MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>"); MODULE_LICENSE("GPL"); |
| 21 13 8 7 1 1 1 8 8 8 8 1 8 8 8 8 8 8 8 7 6 6 8 8 1 7 6 7 7 6 5 8 1 8 7 8 8 7 7 7 8 8 8 8 8 8 8 8 8 8 8 21 508 137 494 76 494 507 507 74 75 75 74 1231 587 742 115 18 90 136 508 517 216 106 267 321 322 200 441 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 | /* * Copyright (c) 2015, Mellanox Technologies inc. All rights reserved. * * This software is available to you under a choice of one of two * licenses. You may choose to be licensed under the terms of the GNU * General Public License (GPL) Version 2, available from the file * COPYING in the main directory of this source tree, or the * OpenIB.org BSD license below: * * Redistribution and use in source and binary forms, with or * without modification, are permitted provided that the following * conditions are met: * * - Redistributions of source code must retain the above * copyright notice, this list of conditions and the following * disclaimer. * * - Redistributions in binary form must reproduce the above * copyright notice, this list of conditions and the following * disclaimer in the documentation and/or other materials * provided with the distribution. * * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE * SOFTWARE. */ #include "core_priv.h" #include <linux/in.h> #include <linux/in6.h> /* For in6_dev_get/in6_dev_put */ #include <net/addrconf.h> #include <net/bonding.h> #include <rdma/ib_cache.h> #include <rdma/ib_addr.h> static struct workqueue_struct *gid_cache_wq; enum gid_op_type { GID_DEL = 0, GID_ADD }; struct update_gid_event_work { struct work_struct work; union ib_gid gid; struct ib_gid_attr gid_attr; enum gid_op_type gid_op; }; #define ROCE_NETDEV_CALLBACK_SZ 3 struct netdev_event_work_cmd { roce_netdev_callback cb; roce_netdev_filter filter; struct net_device *ndev; struct net_device *filter_ndev; }; struct netdev_event_work { struct work_struct work; struct netdev_event_work_cmd cmds[ROCE_NETDEV_CALLBACK_SZ]; }; static const struct { bool (*is_supported)(const struct ib_device *device, u32 port_num); enum ib_gid_type gid_type; } PORT_CAP_TO_GID_TYPE[] = { {rdma_protocol_roce_eth_encap, IB_GID_TYPE_ROCE}, {rdma_protocol_roce_udp_encap, IB_GID_TYPE_ROCE_UDP_ENCAP}, }; #define CAP_TO_GID_TABLE_SIZE ARRAY_SIZE(PORT_CAP_TO_GID_TYPE) unsigned long roce_gid_type_mask_support(struct ib_device *ib_dev, u32 port) { int i; unsigned int ret_flags = 0; if (!rdma_protocol_roce(ib_dev, port)) return 1UL << IB_GID_TYPE_IB; for (i = 0; i < CAP_TO_GID_TABLE_SIZE; i++) if (PORT_CAP_TO_GID_TYPE[i].is_supported(ib_dev, port)) ret_flags |= 1UL << PORT_CAP_TO_GID_TYPE[i].gid_type; return ret_flags; } EXPORT_SYMBOL(roce_gid_type_mask_support); static void update_gid(enum gid_op_type gid_op, struct ib_device *ib_dev, u32 port, union ib_gid *gid, struct ib_gid_attr *gid_attr) { int i; unsigned long gid_type_mask = roce_gid_type_mask_support(ib_dev, port); for (i = 0; i < IB_GID_TYPE_SIZE; i++) { if ((1UL << i) & gid_type_mask) { gid_attr->gid_type = i; switch (gid_op) { case GID_ADD: ib_cache_gid_add(ib_dev, port, gid, gid_attr); break; case GID_DEL: ib_cache_gid_del(ib_dev, port, gid, gid_attr); break; } } } } enum bonding_slave_state { BONDING_SLAVE_STATE_ACTIVE = 1UL << 0, BONDING_SLAVE_STATE_INACTIVE = 1UL << 1, /* No primary slave or the device isn't a slave in bonding */ BONDING_SLAVE_STATE_NA = 1UL << 2, }; static enum bonding_slave_state is_eth_active_slave_of_bonding_rcu(struct net_device *dev, struct net_device *upper) { if (upper && netif_is_bond_master(upper)) { struct net_device *pdev = bond_option_active_slave_get_rcu(netdev_priv(upper)); if (pdev) return dev == pdev ? BONDING_SLAVE_STATE_ACTIVE : BONDING_SLAVE_STATE_INACTIVE; } return BONDING_SLAVE_STATE_NA; } #define REQUIRED_BOND_STATES (BONDING_SLAVE_STATE_ACTIVE | \ BONDING_SLAVE_STATE_NA) static bool is_eth_port_of_netdev_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *real_dev; bool res; if (!rdma_ndev) return false; rcu_read_lock(); real_dev = rdma_vlan_dev_real_dev(cookie); if (!real_dev) real_dev = cookie; res = ((rdma_is_upper_dev_rcu(rdma_ndev, cookie) && (is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) & REQUIRED_BOND_STATES)) || real_dev == rdma_ndev); rcu_read_unlock(); return res; } static bool is_eth_port_inactive_slave_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *master_dev; bool res; if (!rdma_ndev) return false; rcu_read_lock(); master_dev = netdev_master_upper_dev_get_rcu(rdma_ndev); res = is_eth_active_slave_of_bonding_rcu(rdma_ndev, master_dev) == BONDING_SLAVE_STATE_INACTIVE; rcu_read_unlock(); return res; } /** * is_ndev_for_default_gid_filter - Check if a given netdevice * can be considered for default GIDs or not. * @ib_dev: IB device to check * @port: Port to consider for adding default GID * @rdma_ndev: rdma netdevice pointer * @cookie: Netdevice to consider to form a default GID * * is_ndev_for_default_gid_filter() returns true if a given netdevice can be * considered for deriving default RoCE GID, returns false otherwise. */ static bool is_ndev_for_default_gid_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; bool res; if (!rdma_ndev) return false; rcu_read_lock(); /* * When rdma netdevice is used in bonding, bonding master netdevice * should be considered for default GIDs. Therefore, ignore slave rdma * netdevices when bonding is considered. * Additionally when event(cookie) netdevice is bond master device, * make sure that it the upper netdevice of rdma netdevice. */ res = ((cookie_ndev == rdma_ndev && !netif_is_bond_slave(rdma_ndev)) || (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev))); rcu_read_unlock(); return res; } static bool pass_all_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { return true; } static bool upper_device_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { bool res; if (!rdma_ndev) return false; if (rdma_ndev == cookie) return true; rcu_read_lock(); res = rdma_is_upper_dev_rcu(rdma_ndev, cookie); rcu_read_unlock(); return res; } /** * is_upper_ndev_bond_master_filter - Check if a given netdevice * is bond master device of netdevice of the RDMA device of port. * @ib_dev: IB device to check * @port: Port to consider for adding default GID * @rdma_ndev: Pointer to rdma netdevice * @cookie: Netdevice to consider to form a default GID * * is_upper_ndev_bond_master_filter() returns true if a cookie_netdev * is bond master device and rdma_ndev is its lower netdevice. It might * not have been established as slave device yet. */ static bool is_upper_ndev_bond_master_filter(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; bool match = false; if (!rdma_ndev) return false; rcu_read_lock(); if (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev)) match = true; rcu_read_unlock(); return match; } static void update_gid_ip(enum gid_op_type gid_op, struct ib_device *ib_dev, u32 port, struct net_device *ndev, struct sockaddr *addr) { union ib_gid gid; struct ib_gid_attr gid_attr; rdma_ip2gid(addr, &gid); memset(&gid_attr, 0, sizeof(gid_attr)); gid_attr.ndev = ndev; update_gid(gid_op, ib_dev, port, &gid, &gid_attr); } static void bond_delete_netdev_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, struct net_device *event_ndev) { struct net_device *real_dev = rdma_vlan_dev_real_dev(event_ndev); unsigned long gid_type_mask; if (!rdma_ndev) return; if (!real_dev) real_dev = event_ndev; rcu_read_lock(); if (((rdma_ndev != event_ndev && !rdma_is_upper_dev_rcu(rdma_ndev, event_ndev)) || is_eth_active_slave_of_bonding_rcu(rdma_ndev, real_dev) == BONDING_SLAVE_STATE_INACTIVE)) { rcu_read_unlock(); return; } rcu_read_unlock(); gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, rdma_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_DELETE); } static void enum_netdev_ipv4_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { const struct in_ifaddr *ifa; struct in_device *in_dev; struct sin_list { struct list_head list; struct sockaddr_in ip; }; struct sin_list *sin_iter; struct sin_list *sin_temp; LIST_HEAD(sin_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; rcu_read_lock(); in_dev = __in_dev_get_rcu(ndev); if (!in_dev) { rcu_read_unlock(); return; } in_dev_for_each_ifa_rcu(ifa, in_dev) { struct sin_list *entry = kzalloc_obj(*entry, GFP_ATOMIC); if (!entry) continue; entry->ip.sin_family = AF_INET; entry->ip.sin_addr.s_addr = ifa->ifa_address; list_add_tail(&entry->list, &sin_list); } rcu_read_unlock(); list_for_each_entry_safe(sin_iter, sin_temp, &sin_list, list) { update_gid_ip(GID_ADD, ib_dev, port, ndev, (struct sockaddr *)&sin_iter->ip); list_del(&sin_iter->list); kfree(sin_iter); } } static void enum_netdev_ipv6_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { struct inet6_ifaddr *ifp; struct inet6_dev *in6_dev; struct sin6_list { struct list_head list; struct sockaddr_in6 sin6; }; struct sin6_list *sin6_iter; struct sin6_list *sin6_temp; struct ib_gid_attr gid_attr = {.ndev = ndev}; LIST_HEAD(sin6_list); if (ndev->reg_state >= NETREG_UNREGISTERING) return; in6_dev = in6_dev_get(ndev); if (!in6_dev) return; read_lock_bh(&in6_dev->lock); list_for_each_entry(ifp, &in6_dev->addr_list, if_list) { struct sin6_list *entry = kzalloc_obj(*entry, GFP_ATOMIC); if (!entry) continue; entry->sin6.sin6_family = AF_INET6; entry->sin6.sin6_addr = ifp->addr; list_add_tail(&entry->list, &sin6_list); } read_unlock_bh(&in6_dev->lock); in6_dev_put(in6_dev); list_for_each_entry_safe(sin6_iter, sin6_temp, &sin6_list, list) { union ib_gid gid; rdma_ip2gid((struct sockaddr *)&sin6_iter->sin6, &gid); update_gid(GID_ADD, ib_dev, port, &gid, &gid_attr); list_del(&sin6_iter->list); kfree(sin6_iter); } } static void _add_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { enum_netdev_ipv4_ips(ib_dev, port, ndev); if (IS_ENABLED(CONFIG_IPV6)) enum_netdev_ipv6_ips(ib_dev, port, ndev); } static void add_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { _add_netdev_ips(ib_dev, port, cookie); } static void del_netdev_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { ib_cache_gid_del_all_netdev_gids(ib_dev, port, cookie); } /** * del_default_gids - Delete default GIDs of the event/cookie netdevice * @ib_dev: RDMA device pointer * @port: Port of the RDMA device whose GID table to consider * @rdma_ndev: Unused rdma netdevice * @cookie: Pointer to event netdevice * * del_default_gids() deletes the default GIDs of the event/cookie netdevice. */ static void del_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *cookie_ndev = cookie; unsigned long gid_type_mask; gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, cookie_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_DELETE); } static void add_default_gids(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *event_ndev = cookie; unsigned long gid_type_mask; gid_type_mask = roce_gid_type_mask_support(ib_dev, port); ib_cache_gid_set_default_gid(ib_dev, port, event_ndev, gid_type_mask, IB_CACHE_GID_DEFAULT_MODE_SET); } static void enum_all_gids_of_dev_cb(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net *net; struct net_device *ndev; /* Lock the rtnl to make sure the netdevs does not move under * our feet */ rtnl_lock(); down_read(&net_rwsem); for_each_net(net) for_each_netdev(net, ndev) { /* * Filter and add default GIDs of the primary netdevice * when not in bonding mode, or add default GIDs * of bond master device, when in bonding mode. */ if (is_ndev_for_default_gid_filter(ib_dev, port, rdma_ndev, ndev)) add_default_gids(ib_dev, port, rdma_ndev, ndev); if (is_eth_port_of_netdev_filter(ib_dev, port, rdma_ndev, ndev)) _add_netdev_ips(ib_dev, port, ndev); } up_read(&net_rwsem); rtnl_unlock(); } /** * rdma_roce_rescan_device - Rescan all of the network devices in the system * and add their gids, as needed, to the relevant RoCE devices. * * @ib_dev: the rdma device */ void rdma_roce_rescan_device(struct ib_device *ib_dev) { ib_enum_roce_netdev(ib_dev, pass_all_filter, NULL, enum_all_gids_of_dev_cb, NULL); } EXPORT_SYMBOL(rdma_roce_rescan_device); /** * rdma_roce_rescan_port - Rescan all of the network devices in the system * and add their gids if relevant to the port of the RoCE device. * * @ib_dev: IB device * @port: Port number */ void rdma_roce_rescan_port(struct ib_device *ib_dev, u32 port) { struct net_device *ndev = NULL; if (rdma_protocol_roce(ib_dev, port)) { ndev = ib_device_get_netdev(ib_dev, port); if (!ndev) return; enum_all_gids_of_dev_cb(ib_dev, port, ndev, ndev); dev_put(ndev); } } EXPORT_SYMBOL(rdma_roce_rescan_port); static void callback_for_addr_gid_device_scan(struct ib_device *device, u32 port, struct net_device *rdma_ndev, void *cookie) { struct update_gid_event_work *parsed = cookie; return update_gid(parsed->gid_op, device, port, &parsed->gid, &parsed->gid_attr); } struct upper_list { struct list_head list; struct net_device *upper; }; static int netdev_upper_walk(struct net_device *upper, struct netdev_nested_priv *priv) { struct upper_list *entry = kmalloc_obj(*entry, GFP_ATOMIC); struct list_head *upper_list = (struct list_head *)priv->data; if (!entry) return 0; list_add_tail(&entry->list, upper_list); dev_hold(upper); entry->upper = upper; return 0; } static void handle_netdev_upper(struct ib_device *ib_dev, u32 port, void *cookie, void (*handle_netdev)(struct ib_device *ib_dev, u32 port, struct net_device *ndev)) { struct net_device *ndev = cookie; struct netdev_nested_priv priv; struct upper_list *upper_iter; struct upper_list *upper_temp; LIST_HEAD(upper_list); priv.data = &upper_list; rcu_read_lock(); netdev_walk_all_upper_dev_rcu(ndev, netdev_upper_walk, &priv); rcu_read_unlock(); handle_netdev(ib_dev, port, ndev); list_for_each_entry_safe(upper_iter, upper_temp, &upper_list, list) { handle_netdev(ib_dev, port, upper_iter->upper); dev_put(upper_iter->upper); list_del(&upper_iter->list); kfree(upper_iter); } } void roce_del_all_netdev_gids(struct ib_device *ib_dev, u32 port, struct net_device *ndev) { ib_cache_gid_del_all_netdev_gids(ib_dev, port, ndev); } EXPORT_SYMBOL(roce_del_all_netdev_gids); static void del_netdev_upper_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { handle_netdev_upper(ib_dev, port, cookie, roce_del_all_netdev_gids); } static void add_netdev_upper_ips(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { handle_netdev_upper(ib_dev, port, cookie, _add_netdev_ips); } static void del_netdev_default_ips_join(struct ib_device *ib_dev, u32 port, struct net_device *rdma_ndev, void *cookie) { struct net_device *master_ndev; rcu_read_lock(); master_ndev = netdev_master_upper_dev_get_rcu(rdma_ndev); dev_hold(master_ndev); rcu_read_unlock(); if (master_ndev) { bond_delete_netdev_default_gids(ib_dev, port, rdma_ndev, master_ndev); dev_put(master_ndev); } } /* The following functions operate on all IB devices. netdevice_event and * addr_event execute ib_enum_all_roce_netdevs through a work. * ib_enum_all_roce_netdevs iterates through all IB devices. */ static void netdevice_event_work_handler(struct work_struct *_work) { struct netdev_event_work *work = container_of(_work, struct netdev_event_work, work); unsigned int i; for (i = 0; i < ARRAY_SIZE(work->cmds) && work->cmds[i].cb; i++) { ib_enum_all_roce_netdevs(work->cmds[i].filter, work->cmds[i].filter_ndev, work->cmds[i].cb, work->cmds[i].ndev); dev_put(work->cmds[i].ndev); dev_put(work->cmds[i].filter_ndev); } kfree(work); } static int netdevice_queue_work(struct netdev_event_work_cmd *cmds, struct net_device *ndev) { unsigned int i; struct netdev_event_work *ndev_work = kmalloc_obj(*ndev_work); if (!ndev_work) return NOTIFY_DONE; memcpy(ndev_work->cmds, cmds, sizeof(ndev_work->cmds)); for (i = 0; i < ARRAY_SIZE(ndev_work->cmds) && ndev_work->cmds[i].cb; i++) { if (!ndev_work->cmds[i].ndev) ndev_work->cmds[i].ndev = ndev; if (!ndev_work->cmds[i].filter_ndev) ndev_work->cmds[i].filter_ndev = ndev; dev_hold(ndev_work->cmds[i].ndev); dev_hold(ndev_work->cmds[i].filter_ndev); } INIT_WORK(&ndev_work->work, netdevice_event_work_handler); queue_work(gid_cache_wq, &ndev_work->work); return NOTIFY_DONE; } static const struct netdev_event_work_cmd add_cmd = { .cb = add_netdev_ips, .filter = is_eth_port_of_netdev_filter }; static const struct netdev_event_work_cmd add_cmd_upper_ips = { .cb = add_netdev_upper_ips, .filter = is_eth_port_of_netdev_filter }; static void ndev_event_unlink(struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { static const struct netdev_event_work_cmd upper_ips_del_cmd = { .cb = del_netdev_upper_ips, .filter = upper_device_filter }; cmds[0] = upper_ips_del_cmd; cmds[0].ndev = changeupper_info->upper_dev; cmds[1] = add_cmd; } static const struct netdev_event_work_cmd bonding_default_add_cmd = { .cb = add_default_gids, .filter = is_upper_ndev_bond_master_filter }; static void ndev_event_link(struct net_device *event_ndev, struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { static const struct netdev_event_work_cmd bonding_default_del_cmd = { .cb = del_default_gids, .filter = is_upper_ndev_bond_master_filter }; /* * When a lower netdev is linked to its upper bonding * netdev, delete lower slave netdev's default GIDs. */ cmds[0] = bonding_default_del_cmd; cmds[0].ndev = event_ndev; cmds[0].filter_ndev = changeupper_info->upper_dev; /* Now add bonding upper device default GIDs */ cmds[1] = bonding_default_add_cmd; cmds[1].ndev = changeupper_info->upper_dev; cmds[1].filter_ndev = changeupper_info->upper_dev; /* Now add bonding upper device IP based GIDs */ cmds[2] = add_cmd_upper_ips; cmds[2].ndev = changeupper_info->upper_dev; cmds[2].filter_ndev = changeupper_info->upper_dev; } static void netdevice_event_changeupper(struct net_device *event_ndev, struct netdev_notifier_changeupper_info *changeupper_info, struct netdev_event_work_cmd *cmds) { if (changeupper_info->linking) ndev_event_link(event_ndev, changeupper_info, cmds); else ndev_event_unlink(changeupper_info, cmds); } static const struct netdev_event_work_cmd add_default_gid_cmd = { .cb = add_default_gids, .filter = is_ndev_for_default_gid_filter, }; static int netdevice_event(struct notifier_block *this, unsigned long event, void *ptr) { static const struct netdev_event_work_cmd del_cmd = { .cb = del_netdev_ips, .filter = pass_all_filter}; static const struct netdev_event_work_cmd bonding_default_del_cmd_join = { .cb = del_netdev_default_ips_join, .filter = is_eth_port_inactive_slave_filter }; static const struct netdev_event_work_cmd netdev_del_cmd = { .cb = del_netdev_ips, .filter = is_eth_port_of_netdev_filter }; static const struct netdev_event_work_cmd bonding_event_ips_del_cmd = { .cb = del_netdev_upper_ips, .filter = upper_device_filter}; struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct netdev_event_work_cmd cmds[ROCE_NETDEV_CALLBACK_SZ] = { {NULL} }; if (ndev->type != ARPHRD_ETHER) return NOTIFY_DONE; switch (event) { case NETDEV_REGISTER: case NETDEV_UP: cmds[0] = bonding_default_del_cmd_join; cmds[1] = add_default_gid_cmd; cmds[2] = add_cmd; break; case NETDEV_UNREGISTER: if (ndev->reg_state < NETREG_UNREGISTERED) cmds[0] = del_cmd; else return NOTIFY_DONE; break; case NETDEV_CHANGEADDR: cmds[0] = netdev_del_cmd; if (ndev->reg_state == NETREG_REGISTERED) { cmds[1] = add_default_gid_cmd; cmds[2] = add_cmd; } break; case NETDEV_CHANGEUPPER: netdevice_event_changeupper(ndev, container_of(ptr, struct netdev_notifier_changeupper_info, info), cmds); break; case NETDEV_BONDING_FAILOVER: cmds[0] = bonding_event_ips_del_cmd; /* Add default GIDs of the bond device */ cmds[1] = bonding_default_add_cmd; /* Add IP based GIDs of the bond device */ cmds[2] = add_cmd_upper_ips; break; default: return NOTIFY_DONE; } return netdevice_queue_work(cmds, ndev); } static void update_gid_event_work_handler(struct work_struct *_work) { struct update_gid_event_work *work = container_of(_work, struct update_gid_event_work, work); ib_enum_all_roce_netdevs(is_eth_port_of_netdev_filter, work->gid_attr.ndev, callback_for_addr_gid_device_scan, work); dev_put(work->gid_attr.ndev); kfree(work); } static int addr_event(struct notifier_block *this, unsigned long event, struct sockaddr *sa, struct net_device *ndev) { struct update_gid_event_work *work; enum gid_op_type gid_op; if (ndev->type != ARPHRD_ETHER) return NOTIFY_DONE; switch (event) { case NETDEV_UP: gid_op = GID_ADD; break; case NETDEV_DOWN: gid_op = GID_DEL; break; default: return NOTIFY_DONE; } work = kmalloc_obj(*work, GFP_ATOMIC); if (!work) return NOTIFY_DONE; INIT_WORK(&work->work, update_gid_event_work_handler); rdma_ip2gid(sa, &work->gid); work->gid_op = gid_op; memset(&work->gid_attr, 0, sizeof(work->gid_attr)); dev_hold(ndev); work->gid_attr.ndev = ndev; queue_work(gid_cache_wq, &work->work); return NOTIFY_DONE; } static int inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct sockaddr_in in; struct net_device *ndev; struct in_ifaddr *ifa = ptr; in.sin_family = AF_INET; in.sin_addr.s_addr = ifa->ifa_address; ndev = ifa->ifa_dev->dev; return addr_event(this, event, (struct sockaddr *)&in, ndev); } static int inet6addr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct sockaddr_in6 in6; struct net_device *ndev; struct inet6_ifaddr *ifa6 = ptr; in6.sin6_family = AF_INET6; in6.sin6_addr = ifa6->addr; ndev = ifa6->idev->dev; return addr_event(this, event, (struct sockaddr *)&in6, ndev); } static struct notifier_block nb_netdevice = { .notifier_call = netdevice_event }; static struct notifier_block nb_inetaddr = { .notifier_call = inetaddr_event }; static struct notifier_block nb_inet6addr = { .notifier_call = inet6addr_event }; int __init roce_gid_mgmt_init(void) { gid_cache_wq = alloc_ordered_workqueue("gid-cache-wq", 0); if (!gid_cache_wq) return -ENOMEM; register_inetaddr_notifier(&nb_inetaddr); if (IS_ENABLED(CONFIG_IPV6)) register_inet6addr_notifier(&nb_inet6addr); /* We relay on the netdevice notifier to enumerate all * existing devices in the system. Register to this notifier * last to make sure we will not miss any IP add/del * callbacks. */ register_netdevice_notifier(&nb_netdevice); return 0; } void __exit roce_gid_mgmt_cleanup(void) { if (IS_ENABLED(CONFIG_IPV6)) unregister_inet6addr_notifier(&nb_inet6addr); unregister_inetaddr_notifier(&nb_inetaddr); unregister_netdevice_notifier(&nb_netdevice); /* Ensure all gid deletion tasks complete before we go down, * to avoid any reference to free'd memory. By the time * ib-core is removed, all physical devices have been removed, * so no issue with remaining hardware contexts. */ destroy_workqueue(gid_cache_wq); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/bitfield.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/xarray.h> #include <net/net_namespace.h> #include <net/psp.h> #include <net/udp.h> #include "psp.h" #include "psp-nl-gen.h" DEFINE_XARRAY_ALLOC1(psp_devs); struct mutex psp_devs_lock; /** * DOC: PSP locking * * psp_devs_lock protects the psp_devs xarray. * Ordering is take the psp_devs_lock and then the instance lock. * Each instance is protected by RCU, and has a refcount. * When driver unregisters the instance gets flushed, but struct sticks around. */ /** * psp_dev_check_access() - check if user in a given net ns can access PSP dev * @psd: PSP device structure user is trying to access * @net: net namespace user is in * * Return: 0 if PSP device should be visible in @net, errno otherwise. */ int psp_dev_check_access(struct psp_dev *psd, struct net *net) { if (dev_net(psd->main_netdev) == net) return 0; return -ENOENT; } /** * psp_dev_create() - create and register PSP device * @netdev: main netdevice * @psd_ops: driver callbacks * @psd_caps: device capabilities * @priv_ptr: back-pointer to driver private data * * Return: pointer to allocated PSP device, or ERR_PTR. */ struct psp_dev * psp_dev_create(struct net_device *netdev, struct psp_dev_ops *psd_ops, struct psp_dev_caps *psd_caps, void *priv_ptr) { struct psp_dev *psd; static u32 last_id; int err; if (WARN_ON(!psd_caps->versions || !psd_ops->set_config || !psd_ops->key_rotate || !psd_ops->rx_spi_alloc || !psd_ops->tx_key_add || !psd_ops->tx_key_del || !psd_ops->get_stats)) return ERR_PTR(-EINVAL); psd = kzalloc_obj(*psd); if (!psd) return ERR_PTR(-ENOMEM); psd->main_netdev = netdev; psd->ops = psd_ops; psd->caps = psd_caps; psd->drv_priv = priv_ptr; mutex_init(&psd->lock); INIT_LIST_HEAD(&psd->active_assocs); INIT_LIST_HEAD(&psd->prev_assocs); INIT_LIST_HEAD(&psd->stale_assocs); refcount_set(&psd->refcnt, 1); mutex_lock(&psp_devs_lock); err = xa_alloc_cyclic(&psp_devs, &psd->id, psd, xa_limit_16b, &last_id, GFP_KERNEL); if (err) { mutex_unlock(&psp_devs_lock); kfree(psd); return ERR_PTR(err); } mutex_lock(&psd->lock); mutex_unlock(&psp_devs_lock); psp_nl_notify_dev(psd, PSP_CMD_DEV_ADD_NTF); rcu_assign_pointer(netdev->psp_dev, psd); mutex_unlock(&psd->lock); return psd; } EXPORT_SYMBOL(psp_dev_create); void psp_dev_free(struct psp_dev *psd) { mutex_lock(&psp_devs_lock); xa_erase(&psp_devs, psd->id); mutex_unlock(&psp_devs_lock); mutex_destroy(&psd->lock); kfree_rcu(psd, rcu); } /** * psp_dev_unregister() - unregister PSP device * @psd: PSP device structure */ void psp_dev_unregister(struct psp_dev *psd) { struct psp_assoc *pas, *next; mutex_lock(&psp_devs_lock); mutex_lock(&psd->lock); psp_nl_notify_dev(psd, PSP_CMD_DEV_DEL_NTF); /* Wait until psp_dev_free() to call xa_erase() to prevent a * different psd from being added to the xarray with this id, while * there are still references to this psd being held. */ xa_store(&psp_devs, psd->id, NULL, GFP_KERNEL); mutex_unlock(&psp_devs_lock); list_splice_init(&psd->active_assocs, &psd->prev_assocs); list_splice_init(&psd->prev_assocs, &psd->stale_assocs); list_for_each_entry_safe(pas, next, &psd->stale_assocs, assocs_list) psp_dev_tx_key_del(psd, pas); rcu_assign_pointer(psd->main_netdev->psp_dev, NULL); psd->ops = NULL; psd->drv_priv = NULL; mutex_unlock(&psd->lock); psp_dev_put(psd); } EXPORT_SYMBOL(psp_dev_unregister); unsigned int psp_key_size(u32 version) { switch (version) { case PSP_VERSION_HDR0_AES_GCM_128: case PSP_VERSION_HDR0_AES_GMAC_128: return 16; case PSP_VERSION_HDR0_AES_GCM_256: case PSP_VERSION_HDR0_AES_GMAC_256: return 32; default: return 0; } } EXPORT_SYMBOL(psp_key_size); static void psp_write_headers(struct net *net, struct sk_buff *skb, __be32 spi, u8 ver, unsigned int udp_len, __be16 sport) { struct udphdr *uh = udp_hdr(skb); struct psphdr *psph = (struct psphdr *)(uh + 1); const struct sock *sk = skb->sk; uh->dest = htons(PSP_DEFAULT_UDP_PORT); /* A bit of theory: Selection of the source port. * * We need some entropy, so that multiple flows use different * source ports for better RSS spreading at the receiver. * * We also need that all packets belonging to one TCP flow * use the same source port through their duration, * so that all these packets land in the same receive queue. * * udp_flow_src_port() is using sk_txhash, inherited from * skb_set_hash_from_sk() call in __tcp_transmit_skb(). * This field is subject to reshuffling, thanks to * sk_rethink_txhash() calls in various TCP functions. * * Instead, use sk->sk_hash which is constant through * the whole flow duration. */ if (likely(sk)) { u32 hash = sk->sk_hash; int min, max; /* These operations are cheap, no need to cache the result * in another socket field. */ inet_get_local_port_range(net, &min, &max); /* Since this is being sent on the wire obfuscate hash a bit * to minimize possibility that any useful information to an * attacker is leaked. Only upper 16 bits are relevant in the * computation for 16 bit port value because we use a * reciprocal divide. */ hash ^= hash << 16; uh->source = htons(reciprocal_scale(hash, max - min + 1) + min); } else { uh->source = udp_flow_src_port(net, skb, 0, 0, false); } uh->check = 0; uh->len = htons(udp_len); psph->nexthdr = IPPROTO_TCP; psph->hdrlen = PSP_HDRLEN_NOOPT; psph->crypt_offset = 0; psph->verfl = FIELD_PREP(PSPHDR_VERFL_VERSION, ver) | FIELD_PREP(PSPHDR_VERFL_ONE, 1); psph->spi = spi; memset(&psph->iv, 0, sizeof(psph->iv)); } /* Encapsulate a TCP packet with PSP by adding the UDP+PSP headers and filling * them in. */ bool psp_dev_encapsulate(struct net *net, struct sk_buff *skb, __be32 spi, u8 ver, __be16 sport) { u32 network_len = skb_network_header_len(skb); u32 ethr_len = skb_mac_header_len(skb); u32 bufflen = ethr_len + network_len; if (skb_cow_head(skb, PSP_ENCAP_HLEN)) return false; skb_push(skb, PSP_ENCAP_HLEN); skb->mac_header -= PSP_ENCAP_HLEN; skb->network_header -= PSP_ENCAP_HLEN; skb->transport_header -= PSP_ENCAP_HLEN; memmove(skb->data, skb->data + PSP_ENCAP_HLEN, bufflen); if (skb->protocol == htons(ETH_P_IP)) { ip_hdr(skb)->protocol = IPPROTO_UDP; be16_add_cpu(&ip_hdr(skb)->tot_len, PSP_ENCAP_HLEN); ip_hdr(skb)->check = 0; ip_hdr(skb)->check = ip_fast_csum((u8 *)ip_hdr(skb), ip_hdr(skb)->ihl); } else if (skb->protocol == htons(ETH_P_IPV6)) { ipv6_hdr(skb)->nexthdr = IPPROTO_UDP; be16_add_cpu(&ipv6_hdr(skb)->payload_len, PSP_ENCAP_HLEN); } else { return false; } skb_set_inner_ipproto(skb, IPPROTO_TCP); skb_set_inner_transport_header(skb, skb_transport_offset(skb) + PSP_ENCAP_HLEN); skb->encapsulation = 1; psp_write_headers(net, skb, spi, ver, skb->len - skb_transport_offset(skb), sport); return true; } EXPORT_SYMBOL(psp_dev_encapsulate); /* Receive handler for PSP packets. * * Accepts only already-authenticated packets. The full PSP header is * stripped according to psph->hdrlen; any optional fields it advertises * (virtualization cookies, etc.) are ignored and discarded along with the * rest of the header. The caller should ensure that skb->data is pointing * to the mac header, and that skb->mac_len is set. This function does not * currently adjust skb->csum (CHECKSUM_COMPLETE is not supported). */ int psp_dev_rcv(struct sk_buff *skb, u16 dev_id, u8 generation, bool strip_icv) { int l2_hlen = 0, l3_hlen, encap, psp_hlen; struct psp_skb_ext *pse; struct psphdr *psph; struct ethhdr *eth; struct udphdr *uh; __be16 proto; bool is_udp; eth = (struct ethhdr *)skb->data; proto = __vlan_get_protocol(skb, eth->h_proto, &l2_hlen); if (proto == htons(ETH_P_IP)) l3_hlen = sizeof(struct iphdr); else if (proto == htons(ETH_P_IPV6)) l3_hlen = sizeof(struct ipv6hdr); else return -EINVAL; if (unlikely(!pskb_may_pull(skb, l2_hlen + l3_hlen + PSP_ENCAP_HLEN))) return -EINVAL; if (proto == htons(ETH_P_IP)) { struct iphdr *iph = (struct iphdr *)(skb->data + l2_hlen); is_udp = iph->protocol == IPPROTO_UDP; l3_hlen = iph->ihl * 4; if (l3_hlen != sizeof(struct iphdr) && !pskb_may_pull(skb, l2_hlen + l3_hlen + PSP_ENCAP_HLEN)) return -EINVAL; } else { struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + l2_hlen); is_udp = ipv6h->nexthdr == IPPROTO_UDP; } if (unlikely(!is_udp)) return -EINVAL; uh = (struct udphdr *)(skb->data + l2_hlen + l3_hlen); if (unlikely(uh->dest != htons(PSP_DEFAULT_UDP_PORT))) return -EINVAL; psph = (struct psphdr *)(skb->data + l2_hlen + l3_hlen + sizeof(struct udphdr)); /* Strip the full PSP header per psph->hdrlen; VC/options are pulled * into the linear region only so they can be discarded with the * rest of the header. */ psp_hlen = (psph->hdrlen + 1) * 8; if (unlikely(psp_hlen < sizeof(struct psphdr))) return -EINVAL; if (psp_hlen > sizeof(struct psphdr) && !pskb_may_pull(skb, l2_hlen + l3_hlen + sizeof(struct udphdr) + psp_hlen)) return -EINVAL; psph = (struct psphdr *)(skb->data + l2_hlen + l3_hlen + sizeof(struct udphdr)); pse = skb_ext_add(skb, SKB_EXT_PSP); if (!pse) return -EINVAL; pse->spi = psph->spi; pse->dev_id = dev_id; pse->generation = generation; pse->version = FIELD_GET(PSPHDR_VERFL_VERSION, psph->verfl); encap = sizeof(struct udphdr) + psp_hlen; encap += strip_icv ? PSP_TRL_SIZE : 0; if (proto == htons(ETH_P_IP)) { struct iphdr *iph = (struct iphdr *)(skb->data + l2_hlen); iph->protocol = psph->nexthdr; iph->tot_len = htons(ntohs(iph->tot_len) - encap); iph->check = 0; iph->check = ip_fast_csum((u8 *)iph, iph->ihl); } else { struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + l2_hlen); ipv6h->nexthdr = psph->nexthdr; ipv6h->payload_len = htons(ntohs(ipv6h->payload_len) - encap); } memmove(skb->data + sizeof(struct udphdr) + psp_hlen, skb->data, l2_hlen + l3_hlen); skb_pull(skb, sizeof(struct udphdr) + psp_hlen); if (strip_icv) pskb_trim(skb, skb->len - PSP_TRL_SIZE); return 0; } EXPORT_SYMBOL(psp_dev_rcv); static int __init psp_init(void) { mutex_init(&psp_devs_lock); return genl_register_family(&psp_nl_family); } subsys_initcall(psp_init); |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 2020 Linaro Limited * * Author: Daniel Lezcano <daniel.lezcano@linaro.org> * * Generic netlink for thermal management framework */ #include <linux/module.h> #include <linux/notifier.h> #include <linux/kernel.h> #include <net/sock.h> #include <net/genetlink.h> #include <uapi/linux/thermal.h> #include "thermal_core.h" static const struct genl_multicast_group thermal_genl_mcgrps[] = { [THERMAL_GENL_SAMPLING_GROUP] = { .name = THERMAL_GENL_SAMPLING_GROUP_NAME, }, [THERMAL_GENL_EVENT_GROUP] = { .name = THERMAL_GENL_EVENT_GROUP_NAME, }, }; static const struct nla_policy thermal_genl_policy[THERMAL_GENL_ATTR_MAX + 1] = { /* Thermal zone */ [THERMAL_GENL_ATTR_TZ] = { .type = NLA_NESTED }, [THERMAL_GENL_ATTR_TZ_ID] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_TZ_TEMP] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_TZ_TRIP] = { .type = NLA_NESTED }, [THERMAL_GENL_ATTR_TZ_TRIP_ID] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_TZ_TRIP_TEMP] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_TZ_TRIP_TYPE] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_TZ_TRIP_HYST] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_TZ_MODE] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_TZ_CDEV_WEIGHT] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_TZ_NAME] = { .type = NLA_STRING, .len = THERMAL_NAME_LENGTH }, /* Governor(s) */ [THERMAL_GENL_ATTR_TZ_GOV] = { .type = NLA_NESTED }, [THERMAL_GENL_ATTR_TZ_GOV_NAME] = { .type = NLA_STRING, .len = THERMAL_NAME_LENGTH }, /* Cooling devices */ [THERMAL_GENL_ATTR_CDEV] = { .type = NLA_NESTED }, [THERMAL_GENL_ATTR_CDEV_ID] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_CDEV_CUR_STATE] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_CDEV_MAX_STATE] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_CDEV_NAME] = { .type = NLA_STRING, .len = THERMAL_NAME_LENGTH }, /* CPU capabilities */ [THERMAL_GENL_ATTR_CPU_CAPABILITY] = { .type = NLA_NESTED }, [THERMAL_GENL_ATTR_CPU_CAPABILITY_ID] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_CPU_CAPABILITY_PERFORMANCE] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_CPU_CAPABILITY_EFFICIENCY] = { .type = NLA_U32 }, /* Thresholds */ [THERMAL_GENL_ATTR_THRESHOLD] = { .type = NLA_NESTED }, [THERMAL_GENL_ATTR_THRESHOLD_TEMP] = { .type = NLA_U32 }, [THERMAL_GENL_ATTR_THRESHOLD_DIRECTION] = { .type = NLA_U32 }, }; struct param { struct nlattr **attrs; struct sk_buff *msg; const char *name; int tz_id; int cdev_id; int trip_id; int trip_temp; int trip_type; int trip_hyst; int temp; int prev_temp; int direction; int cdev_state; int cdev_max_state; struct thermal_genl_cpu_caps *cpu_capabilities; int cpu_capabilities_count; }; typedef int (*cb_t)(struct param *); static struct genl_family thermal_genl_family; static BLOCKING_NOTIFIER_HEAD(thermal_genl_chain); static int thermal_group_has_listeners(enum thermal_genl_multicast_groups group) { return genl_has_listeners(&thermal_genl_family, &init_net, group); } /************************** Sampling encoding *******************************/ int thermal_genl_sampling_temp(int id, int temp) { struct sk_buff *skb; void *hdr; if (!thermal_group_has_listeners(THERMAL_GENL_SAMPLING_GROUP)) return 0; skb = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOMEM; hdr = genlmsg_put(skb, 0, 0, &thermal_genl_family, 0, THERMAL_GENL_SAMPLING_TEMP); if (!hdr) goto out_free; if (nla_put_u32(skb, THERMAL_GENL_ATTR_TZ_ID, id)) goto out_cancel; if (nla_put_u32(skb, THERMAL_GENL_ATTR_TZ_TEMP, temp)) goto out_cancel; genlmsg_end(skb, hdr); genlmsg_multicast(&thermal_genl_family, skb, 0, THERMAL_GENL_SAMPLING_GROUP, GFP_KERNEL); return 0; out_cancel: genlmsg_cancel(skb, hdr); out_free: nlmsg_free(skb); return -EMSGSIZE; } /**************************** Event encoding *********************************/ static int thermal_genl_event_tz_create(struct param *p) { if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) || nla_put_string(p->msg, THERMAL_GENL_ATTR_TZ_NAME, p->name)) return -EMSGSIZE; return 0; } static int thermal_genl_event_tz(struct param *p) { if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id)) return -EMSGSIZE; return 0; } static int thermal_genl_event_tz_trip_up(struct param *p) { if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, p->trip_id) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TEMP, p->temp)) return -EMSGSIZE; return 0; } static int thermal_genl_event_tz_trip_change(struct param *p) { if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, p->trip_id) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_TYPE, p->trip_type) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_TEMP, p->trip_temp) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TRIP_HYST, p->trip_hyst)) return -EMSGSIZE; return 0; } static int thermal_genl_event_cdev_add(struct param *p) { if (nla_put_string(p->msg, THERMAL_GENL_ATTR_CDEV_NAME, p->name) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_CDEV_ID, p->cdev_id) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_CDEV_MAX_STATE, p->cdev_max_state)) return -EMSGSIZE; return 0; } static int thermal_genl_event_cdev_delete(struct param *p) { if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_CDEV_ID, p->cdev_id)) return -EMSGSIZE; return 0; } static int thermal_genl_event_cdev_state_update(struct param *p) { if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_CDEV_ID, p->cdev_id) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_CDEV_CUR_STATE, p->cdev_state)) return -EMSGSIZE; return 0; } static int thermal_genl_event_gov_change(struct param *p) { if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) || nla_put_string(p->msg, THERMAL_GENL_ATTR_GOV_NAME, p->name)) return -EMSGSIZE; return 0; } static int thermal_genl_event_cpu_capability_change(struct param *p) { struct thermal_genl_cpu_caps *cpu_cap = p->cpu_capabilities; struct sk_buff *msg = p->msg; struct nlattr *start_cap; int i; start_cap = nla_nest_start(msg, THERMAL_GENL_ATTR_CPU_CAPABILITY); if (!start_cap) return -EMSGSIZE; for (i = 0; i < p->cpu_capabilities_count; ++i) { if (nla_put_u32(msg, THERMAL_GENL_ATTR_CPU_CAPABILITY_ID, cpu_cap->cpu)) goto out_cancel_nest; if (nla_put_u32(msg, THERMAL_GENL_ATTR_CPU_CAPABILITY_PERFORMANCE, cpu_cap->performance)) goto out_cancel_nest; if (nla_put_u32(msg, THERMAL_GENL_ATTR_CPU_CAPABILITY_EFFICIENCY, cpu_cap->efficiency)) goto out_cancel_nest; ++cpu_cap; } nla_nest_end(msg, start_cap); return 0; out_cancel_nest: nla_nest_cancel(msg, start_cap); return -EMSGSIZE; } static int thermal_genl_event_threshold_add(struct param *p) { if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_THRESHOLD_TEMP, p->temp) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_THRESHOLD_DIRECTION, p->direction)) return -EMSGSIZE; return 0; } static int thermal_genl_event_threshold_flush(struct param *p) { if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id)) return -EMSGSIZE; return 0; } static int thermal_genl_event_threshold_up(struct param *p) { if (nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_ID, p->tz_id) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_PREV_TEMP, p->prev_temp) || nla_put_u32(p->msg, THERMAL_GENL_ATTR_TZ_TEMP, p->temp)) return -EMSGSIZE; return 0; } int thermal_genl_event_tz_delete(struct param *p) __attribute__((alias("thermal_genl_event_tz"))); int thermal_genl_event_tz_enable(struct param *p) __attribute__((alias("thermal_genl_event_tz"))); int thermal_genl_event_tz_disable(struct param *p) __attribute__((alias("thermal_genl_event_tz"))); int thermal_genl_event_tz_trip_down(struct param *p) __attribute__((alias("thermal_genl_event_tz_trip_up"))); int thermal_genl_event_threshold_delete(struct param *p) __attribute__((alias("thermal_genl_event_threshold_add"))); int thermal_genl_event_threshold_down(struct param *p) __attribute__((alias("thermal_genl_event_threshold_up"))); static cb_t event_cb[] = { [THERMAL_GENL_EVENT_TZ_CREATE] = thermal_genl_event_tz_create, [THERMAL_GENL_EVENT_TZ_DELETE] = thermal_genl_event_tz_delete, [THERMAL_GENL_EVENT_TZ_ENABLE] = thermal_genl_event_tz_enable, [THERMAL_GENL_EVENT_TZ_DISABLE] = thermal_genl_event_tz_disable, [THERMAL_GENL_EVENT_TZ_TRIP_UP] = thermal_genl_event_tz_trip_up, [THERMAL_GENL_EVENT_TZ_TRIP_DOWN] = thermal_genl_event_tz_trip_down, [THERMAL_GENL_EVENT_TZ_TRIP_CHANGE] = thermal_genl_event_tz_trip_change, [THERMAL_GENL_EVENT_CDEV_ADD] = thermal_genl_event_cdev_add, [THERMAL_GENL_EVENT_CDEV_DELETE] = thermal_genl_event_cdev_delete, [THERMAL_GENL_EVENT_CDEV_STATE_UPDATE] = thermal_genl_event_cdev_state_update, [THERMAL_GENL_EVENT_TZ_GOV_CHANGE] = thermal_genl_event_gov_change, [THERMAL_GENL_EVENT_CPU_CAPABILITY_CHANGE] = thermal_genl_event_cpu_capability_change, [THERMAL_GENL_EVENT_THRESHOLD_ADD] = thermal_genl_event_threshold_add, [THERMAL_GENL_EVENT_THRESHOLD_DELETE] = thermal_genl_event_threshold_delete, [THERMAL_GENL_EVENT_THRESHOLD_FLUSH] = thermal_genl_event_threshold_flush, [THERMAL_GENL_EVENT_THRESHOLD_DOWN] = thermal_genl_event_threshold_down, [THERMAL_GENL_EVENT_THRESHOLD_UP] = thermal_genl_event_threshold_up, }; /* * Generic netlink event encoding */ static int thermal_genl_send_event(enum thermal_genl_event event, struct param *p) { struct sk_buff *msg; int ret = -EMSGSIZE; void *hdr; if (!thermal_group_has_listeners(THERMAL_GENL_EVENT_GROUP)) return 0; msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!msg) return -ENOMEM; p->msg = msg; hdr = genlmsg_put(msg, 0, 0, &thermal_genl_family, 0, event); if (!hdr) goto out_free_msg; ret = event_cb[event](p); if (ret) goto out_cancel_msg; genlmsg_end(msg, hdr); genlmsg_multicast(&thermal_genl_family, msg, 0, THERMAL_GENL_EVENT_GROUP, GFP_KERNEL); return 0; out_cancel_msg: genlmsg_cancel(msg, hdr); out_free_msg: nlmsg_free(msg); return ret; } int thermal_notify_tz_create(const struct thermal_zone_device *tz) { struct param p = { .tz_id = tz->id, .name = tz->type }; return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_CREATE, &p); } int thermal_notify_tz_delete(const struct thermal_zone_device *tz) { struct param p = { .tz_id = tz->id }; return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_DELETE, &p); } int thermal_notify_tz_enable(const struct thermal_zone_device *tz) { struct param p = { .tz_id = tz->id }; return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_ENABLE, &p); } int thermal_notify_tz_disable(const struct thermal_zone_device *tz) { struct param p = { .tz_id = tz->id }; return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_DISABLE, &p); } int thermal_notify_tz_trip_down(const struct thermal_zone_device *tz, const struct thermal_trip *trip) { struct param p = { .tz_id = tz->id, .trip_id = thermal_zone_trip_id(tz, trip), .temp = tz->temperature }; return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_DOWN, &p); } int thermal_notify_tz_trip_up(const struct thermal_zone_device *tz, const struct thermal_trip *trip) { struct param p = { .tz_id = tz->id, .trip_id = thermal_zone_trip_id(tz, trip), .temp = tz->temperature }; return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_UP, &p); } int thermal_notify_tz_trip_change(const struct thermal_zone_device *tz, const struct thermal_trip *trip) { struct param p = { .tz_id = tz->id, .trip_id = thermal_zone_trip_id(tz, trip), .trip_type = trip->type, .trip_temp = trip->temperature, .trip_hyst = trip->hysteresis }; return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_TRIP_CHANGE, &p); } int thermal_notify_cdev_state_update(const struct thermal_cooling_device *cdev, int state) { struct param p = { .cdev_id = cdev->id, .cdev_state = state }; return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_STATE_UPDATE, &p); } int thermal_notify_cdev_add(const struct thermal_cooling_device *cdev) { struct param p = { .cdev_id = cdev->id, .name = cdev->type, .cdev_max_state = cdev->max_state }; return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_ADD, &p); } int thermal_notify_cdev_delete(const struct thermal_cooling_device *cdev) { struct param p = { .cdev_id = cdev->id }; return thermal_genl_send_event(THERMAL_GENL_EVENT_CDEV_DELETE, &p); } int thermal_notify_tz_gov_change(const struct thermal_zone_device *tz, const char *name) { struct param p = { .tz_id = tz->id, .name = name }; return thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_GOV_CHANGE, &p); } int thermal_genl_cpu_capability_event(int count, struct thermal_genl_cpu_caps *caps) { struct param p = { .cpu_capabilities_count = count, .cpu_capabilities = caps }; return thermal_genl_send_event(THERMAL_GENL_EVENT_CPU_CAPABILITY_CHANGE, &p); } EXPORT_SYMBOL_GPL(thermal_genl_cpu_capability_event); int thermal_notify_threshold_add(const struct thermal_zone_device *tz, int temperature, int direction) { struct param p = { .tz_id = tz->id, .temp = temperature, .direction = direction }; return thermal_genl_send_event(THERMAL_GENL_EVENT_THRESHOLD_ADD, &p); } int thermal_notify_threshold_delete(const struct thermal_zone_device *tz, int temperature, int direction) { struct param p = { .tz_id = tz->id, .temp = temperature, .direction = direction }; return thermal_genl_send_event(THERMAL_GENL_EVENT_THRESHOLD_DELETE, &p); } int thermal_notify_threshold_flush(const struct thermal_zone_device *tz) { struct param p = { .tz_id = tz->id }; return thermal_genl_send_event(THERMAL_GENL_EVENT_THRESHOLD_FLUSH, &p); } int thermal_notify_threshold_down(const struct thermal_zone_device *tz) { struct param p = { .tz_id = tz->id, .temp = tz->temperature, .prev_temp = tz->last_temperature }; return thermal_genl_send_event(THERMAL_GENL_EVENT_THRESHOLD_DOWN, &p); } int thermal_notify_threshold_up(const struct thermal_zone_device *tz) { struct param p = { .tz_id = tz->id, .temp = tz->temperature, .prev_temp = tz->last_temperature }; return thermal_genl_send_event(THERMAL_GENL_EVENT_THRESHOLD_UP, &p); } /*************************** Command encoding ********************************/ static int __thermal_genl_cmd_tz_get_id(struct thermal_zone_device *tz, void *data) { struct sk_buff *msg = data; if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_ID, tz->id) || nla_put_string(msg, THERMAL_GENL_ATTR_TZ_NAME, tz->type)) return -EMSGSIZE; return 0; } static int thermal_genl_cmd_tz_get_id(struct param *p) { struct sk_buff *msg = p->msg; struct nlattr *start_tz; int ret; start_tz = nla_nest_start(msg, THERMAL_GENL_ATTR_TZ); if (!start_tz) return -EMSGSIZE; ret = for_each_thermal_zone(__thermal_genl_cmd_tz_get_id, msg); if (ret) goto out_cancel_nest; nla_nest_end(msg, start_tz); return 0; out_cancel_nest: nla_nest_cancel(msg, start_tz); return ret; } static int thermal_genl_cmd_tz_get_trip(struct param *p) { struct sk_buff *msg = p->msg; const struct thermal_trip_desc *td; struct nlattr *start_trip; int id; if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID]) return -EINVAL; id = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_TZ_ID]); CLASS(thermal_zone_get_by_id, tz)(id); if (!tz) return -EINVAL; start_trip = nla_nest_start(msg, THERMAL_GENL_ATTR_TZ_TRIP); if (!start_trip) return -EMSGSIZE; guard(thermal_zone)(tz); for_each_trip_desc(tz, td) { const struct thermal_trip *trip = &td->trip; if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_ID, thermal_zone_trip_id(tz, trip)) || nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_TYPE, trip->type) || nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_TEMP, trip->temperature) || nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TRIP_HYST, trip->hysteresis)) return -EMSGSIZE; } nla_nest_end(msg, start_trip); return 0; } static int thermal_genl_cmd_tz_get_temp(struct param *p) { struct sk_buff *msg = p->msg; int temp, ret, id; if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID]) return -EINVAL; id = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_TZ_ID]); CLASS(thermal_zone_get_by_id, tz)(id); if (!tz) return -EINVAL; ret = thermal_zone_get_temp(tz, &temp); if (ret) return ret; if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_ID, id) || nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_TEMP, temp)) return -EMSGSIZE; return 0; } static int thermal_genl_cmd_tz_get_gov(struct param *p) { struct sk_buff *msg = p->msg; int id; if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID]) return -EINVAL; id = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_TZ_ID]); CLASS(thermal_zone_get_by_id, tz)(id); if (!tz) return -EINVAL; guard(thermal_zone)(tz); if (nla_put_u32(msg, THERMAL_GENL_ATTR_TZ_ID, id) || nla_put_string(msg, THERMAL_GENL_ATTR_TZ_GOV_NAME, tz->governor->name)) return -EMSGSIZE; return 0; } static int __thermal_genl_cmd_cdev_get(struct thermal_cooling_device *cdev, void *data) { struct sk_buff *msg = data; if (nla_put_u32(msg, THERMAL_GENL_ATTR_CDEV_ID, cdev->id)) return -EMSGSIZE; if (nla_put_string(msg, THERMAL_GENL_ATTR_CDEV_NAME, cdev->type)) return -EMSGSIZE; return 0; } static int thermal_genl_cmd_cdev_get(struct param *p) { struct sk_buff *msg = p->msg; struct nlattr *start_cdev; int ret; start_cdev = nla_nest_start(msg, THERMAL_GENL_ATTR_CDEV); if (!start_cdev) return -EMSGSIZE; ret = for_each_thermal_cooling_device(__thermal_genl_cmd_cdev_get, msg); if (ret) goto out_cancel_nest; nla_nest_end(msg, start_cdev); return 0; out_cancel_nest: nla_nest_cancel(msg, start_cdev); return ret; } static int __thermal_genl_cmd_threshold_get(struct user_threshold *threshold, void *arg) { struct sk_buff *msg = arg; if (nla_put_u32(msg, THERMAL_GENL_ATTR_THRESHOLD_TEMP, threshold->temperature) || nla_put_u32(msg, THERMAL_GENL_ATTR_THRESHOLD_DIRECTION, threshold->direction)) return -1; return 0; } static int thermal_genl_cmd_threshold_get(struct param *p) { struct sk_buff *msg = p->msg; struct nlattr *start_trip; int id, ret; if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID]) return -EINVAL; id = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_TZ_ID]); CLASS(thermal_zone_get_by_id, tz)(id); if (!tz) return -EINVAL; start_trip = nla_nest_start(msg, THERMAL_GENL_ATTR_THRESHOLD); if (!start_trip) return -EMSGSIZE; ret = thermal_thresholds_for_each(tz, __thermal_genl_cmd_threshold_get, msg); if (ret) return -EMSGSIZE; nla_nest_end(msg, start_trip); return 0; } static int thermal_genl_cmd_threshold_add(struct param *p) { int id, temp, direction; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID] || !p->attrs[THERMAL_GENL_ATTR_THRESHOLD_TEMP] || !p->attrs[THERMAL_GENL_ATTR_THRESHOLD_DIRECTION]) return -EINVAL; id = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_TZ_ID]); temp = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_THRESHOLD_TEMP]); direction = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_THRESHOLD_DIRECTION]); CLASS(thermal_zone_get_by_id, tz)(id); if (!tz) return -EINVAL; guard(thermal_zone)(tz); return thermal_thresholds_add(tz, temp, direction); } static int thermal_genl_cmd_threshold_delete(struct param *p) { int id, temp, direction; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID] || !p->attrs[THERMAL_GENL_ATTR_THRESHOLD_TEMP] || !p->attrs[THERMAL_GENL_ATTR_THRESHOLD_DIRECTION]) return -EINVAL; id = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_TZ_ID]); temp = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_THRESHOLD_TEMP]); direction = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_THRESHOLD_DIRECTION]); CLASS(thermal_zone_get_by_id, tz)(id); if (!tz) return -EINVAL; guard(thermal_zone)(tz); return thermal_thresholds_delete(tz, temp, direction); } static int thermal_genl_cmd_threshold_flush(struct param *p) { int id; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!p->attrs[THERMAL_GENL_ATTR_TZ_ID]) return -EINVAL; id = nla_get_u32(p->attrs[THERMAL_GENL_ATTR_TZ_ID]); CLASS(thermal_zone_get_by_id, tz)(id); if (!tz) return -EINVAL; guard(thermal_zone)(tz); thermal_thresholds_flush(tz); return 0; } static cb_t cmd_cb[] = { [THERMAL_GENL_CMD_TZ_GET_ID] = thermal_genl_cmd_tz_get_id, [THERMAL_GENL_CMD_TZ_GET_TRIP] = thermal_genl_cmd_tz_get_trip, [THERMAL_GENL_CMD_TZ_GET_TEMP] = thermal_genl_cmd_tz_get_temp, [THERMAL_GENL_CMD_TZ_GET_GOV] = thermal_genl_cmd_tz_get_gov, [THERMAL_GENL_CMD_CDEV_GET] = thermal_genl_cmd_cdev_get, [THERMAL_GENL_CMD_THRESHOLD_GET] = thermal_genl_cmd_threshold_get, [THERMAL_GENL_CMD_THRESHOLD_ADD] = thermal_genl_cmd_threshold_add, [THERMAL_GENL_CMD_THRESHOLD_DELETE] = thermal_genl_cmd_threshold_delete, [THERMAL_GENL_CMD_THRESHOLD_FLUSH] = thermal_genl_cmd_threshold_flush, }; static int thermal_genl_cmd_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct param p = { .msg = skb }; const struct genl_dumpit_info *info = genl_dumpit_info(cb); int cmd = info->op.cmd; int ret; void *hdr; hdr = genlmsg_put(skb, 0, 0, &thermal_genl_family, 0, cmd); if (!hdr) return -EMSGSIZE; ret = cmd_cb[cmd](&p); if (ret) goto out_cancel_msg; genlmsg_end(skb, hdr); return 0; out_cancel_msg: genlmsg_cancel(skb, hdr); return ret; } static int thermal_genl_cmd_doit(struct sk_buff *skb, struct genl_info *info) { struct param p = { .attrs = info->attrs }; struct sk_buff *msg; void *hdr; int cmd = info->genlhdr->cmd; int ret = -EMSGSIZE; msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); if (!msg) return -ENOMEM; p.msg = msg; hdr = genlmsg_put_reply(msg, info, &thermal_genl_family, 0, cmd); if (!hdr) goto out_free_msg; ret = cmd_cb[cmd](&p); if (ret) goto out_cancel_msg; genlmsg_end(msg, hdr); return genlmsg_reply(msg, info); out_cancel_msg: genlmsg_cancel(msg, hdr); out_free_msg: nlmsg_free(msg); return ret; } static int thermal_genl_bind(int mcgrp) { struct thermal_genl_notify n = { .mcgrp = mcgrp }; if (WARN_ON_ONCE(mcgrp > THERMAL_GENL_MAX_GROUP)) return -EINVAL; blocking_notifier_call_chain(&thermal_genl_chain, THERMAL_NOTIFY_BIND, &n); return 0; } static void thermal_genl_unbind(int mcgrp) { struct thermal_genl_notify n = { .mcgrp = mcgrp }; if (WARN_ON_ONCE(mcgrp > THERMAL_GENL_MAX_GROUP)) return; blocking_notifier_call_chain(&thermal_genl_chain, THERMAL_NOTIFY_UNBIND, &n); } static const struct genl_small_ops thermal_genl_ops[] = { { .cmd = THERMAL_GENL_CMD_TZ_GET_ID, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = thermal_genl_cmd_dumpit, }, { .cmd = THERMAL_GENL_CMD_TZ_GET_TRIP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = thermal_genl_cmd_doit, }, { .cmd = THERMAL_GENL_CMD_TZ_GET_TEMP, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = thermal_genl_cmd_doit, }, { .cmd = THERMAL_GENL_CMD_TZ_GET_GOV, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = thermal_genl_cmd_doit, }, { .cmd = THERMAL_GENL_CMD_CDEV_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .dumpit = thermal_genl_cmd_dumpit, }, { .cmd = THERMAL_GENL_CMD_THRESHOLD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = thermal_genl_cmd_doit, }, { .cmd = THERMAL_GENL_CMD_THRESHOLD_ADD, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = thermal_genl_cmd_doit, }, { .cmd = THERMAL_GENL_CMD_THRESHOLD_DELETE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = thermal_genl_cmd_doit, }, { .cmd = THERMAL_GENL_CMD_THRESHOLD_FLUSH, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = thermal_genl_cmd_doit, }, }; static struct genl_family thermal_genl_family __ro_after_init = { .hdrsize = 0, .name = THERMAL_GENL_FAMILY_NAME, .version = THERMAL_GENL_VERSION, .maxattr = THERMAL_GENL_ATTR_MAX, .policy = thermal_genl_policy, .bind = thermal_genl_bind, .unbind = thermal_genl_unbind, .small_ops = thermal_genl_ops, .n_small_ops = ARRAY_SIZE(thermal_genl_ops), .resv_start_op = __THERMAL_GENL_CMD_MAX, .mcgrps = thermal_genl_mcgrps, .n_mcgrps = ARRAY_SIZE(thermal_genl_mcgrps), }; int thermal_genl_register_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&thermal_genl_chain, nb); } int thermal_genl_unregister_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&thermal_genl_chain, nb); } int __init thermal_netlink_init(void) { return genl_register_family(&thermal_genl_family); } void __init thermal_netlink_exit(void) { genl_unregister_family(&thermal_genl_family); } |
| 31 31 40 40 12 12 12 12 12 12 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 | // SPDX-License-Identifier: GPL-2.0 /* Linux multicast routing support * Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation */ #include <linux/rhashtable.h> #include <linux/mroute_base.h> /* Sets everything common except 'dev', since that is done under locking */ void vif_device_init(struct vif_device *v, struct net_device *dev, unsigned long rate_limit, unsigned char threshold, unsigned short flags, unsigned short get_iflink_mask) { RCU_INIT_POINTER(v->dev, NULL); v->bytes_in = 0; v->bytes_out = 0; v->pkt_in = 0; v->pkt_out = 0; v->rate_limit = rate_limit; v->flags = flags; v->threshold = threshold; if (v->flags & get_iflink_mask) v->link = dev_get_iflink(dev); else v->link = dev->ifindex; } static void __mr_free_table(struct work_struct *work) { struct mr_table *mrt = container_of(to_rcu_work(work), struct mr_table, work); rhltable_destroy(&mrt->mfc_hash); kfree(mrt); } void mr_table_free(struct mr_table *mrt) { queue_rcu_work(system_unbound_wq, &mrt->work); } struct mr_table * mr_table_alloc(struct net *net, u32 id, struct mr_table_ops *ops, void (*expire_func)(struct timer_list *t), void (*table_set)(struct mr_table *mrt, struct net *net)) { struct mr_table *mrt; int err; mrt = kzalloc_obj(*mrt); if (!mrt) return ERR_PTR(-ENOMEM); mrt->id = id; write_pnet(&mrt->net, net); mrt->ops = *ops; err = rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params); if (err) { kfree(mrt); return ERR_PTR(err); } INIT_RCU_WORK(&mrt->work, __mr_free_table); INIT_LIST_HEAD(&mrt->mfc_cache_list); INIT_LIST_HEAD(&mrt->mfc_unres_queue); timer_setup(&mrt->ipmr_expire_timer, expire_func, 0); mrt->mroute_reg_vif_num = -1; table_set(mrt, net); return mrt; } void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent) { struct rhlist_head *tmp, *list; struct mr_mfc *c; list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params); rhl_for_each_entry_rcu(c, tmp, list, mnode) if (parent == -1 || parent == c->mfc_parent) return c; return NULL; } void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi) { struct rhlist_head *tmp, *list; struct mr_mfc *c; list = rhltable_lookup(&mrt->mfc_hash, mrt->ops.cmparg_any, *mrt->ops.rht_params); rhl_for_each_entry_rcu(c, tmp, list, mnode) if (c->mfc_un.res.ttls[vifi] < 255) return c; return NULL; } void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg) { struct rhlist_head *tmp, *list; struct mr_mfc *c, *proxy; list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params); rhl_for_each_entry_rcu(c, tmp, list, mnode) { if (c->mfc_un.res.ttls[vifi] < 255) return c; /* It's ok if the vifi is part of the static tree */ proxy = mr_mfc_find_any_parent(mrt, c->mfc_parent); if (proxy && proxy->mfc_un.res.ttls[vifi] < 255) return c; } return mr_mfc_find_any_parent(mrt, vifi); } #ifdef CONFIG_PROC_FS void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos) { struct mr_table *mrt = iter->mrt; for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) { if (!VIF_EXISTS(mrt, iter->ct)) continue; if (pos-- == 0) return &mrt->vif_table[iter->ct]; } return NULL; } void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct mr_vif_iter *iter = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt = iter->mrt; ++*pos; if (v == SEQ_START_TOKEN) return mr_vif_seq_idx(net, iter, 0); while (++iter->ct < mrt->maxvif) { if (!VIF_EXISTS(mrt, iter->ct)) continue; return &mrt->vif_table[iter->ct]; } return NULL; } void *mr_mfc_seq_idx(struct net *net, struct mr_mfc_iter *it, loff_t pos) { struct mr_table *mrt = it->mrt; struct mr_mfc *mfc; rcu_read_lock(); it->cache = &mrt->mfc_cache_list; list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) if (pos-- == 0) return mfc; rcu_read_unlock(); spin_lock_bh(it->lock); it->cache = &mrt->mfc_unres_queue; list_for_each_entry(mfc, it->cache, list) if (pos-- == 0) return mfc; spin_unlock_bh(it->lock); it->cache = NULL; return NULL; } void *mr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct mr_mfc_iter *it = seq->private; struct net *net = seq_file_net(seq); struct mr_table *mrt = it->mrt; struct mr_mfc *c = v; ++*pos; if (v == SEQ_START_TOKEN) return mr_mfc_seq_idx(net, seq->private, 0); if (c->list.next != it->cache) return list_entry(c->list.next, struct mr_mfc, list); if (it->cache == &mrt->mfc_unres_queue) goto end_of_list; /* exhausted cache_array, show unresolved */ rcu_read_unlock(); it->cache = &mrt->mfc_unres_queue; spin_lock_bh(it->lock); if (!list_empty(it->cache)) return list_first_entry(it->cache, struct mr_mfc, list); end_of_list: spin_unlock_bh(it->lock); it->cache = NULL; return NULL; } #endif int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, struct mr_mfc *c, struct rtmsg *rtm) { struct net_device *vif_dev; struct rta_mfc_stats mfcs; struct nlattr *mp_attr; struct rtnexthop *nhp; unsigned long lastuse; int ct; /* If cache is unresolved, don't try to parse IIF and OIF */ if (c->mfc_parent >= MAXVIFS) { rtm->rtm_flags |= RTNH_F_UNRESOLVED; return -ENOENT; } rcu_read_lock(); vif_dev = rcu_dereference(mrt->vif_table[c->mfc_parent].dev); if (vif_dev && nla_put_u32(skb, RTA_IIF, READ_ONCE(vif_dev->ifindex)) < 0) { rcu_read_unlock(); return -EMSGSIZE; } rcu_read_unlock(); if (c->mfc_flags & MFC_OFFLOAD) rtm->rtm_flags |= RTNH_F_OFFLOAD; mp_attr = nla_nest_start_noflag(skb, RTA_MULTIPATH); if (!mp_attr) return -EMSGSIZE; rcu_read_lock(); for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { struct vif_device *vif = &mrt->vif_table[ct]; vif_dev = rcu_dereference(vif->dev); if (vif_dev && c->mfc_un.res.ttls[ct] < 255) { nhp = nla_reserve_nohdr(skb, sizeof(*nhp)); if (!nhp) { rcu_read_unlock(); nla_nest_cancel(skb, mp_attr); return -EMSGSIZE; } nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; nhp->rtnh_ifindex = READ_ONCE(vif_dev->ifindex); nhp->rtnh_len = sizeof(*nhp); } } rcu_read_unlock(); nla_nest_end(skb, mp_attr); lastuse = READ_ONCE(c->mfc_un.res.lastuse); lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0; mfcs.mfcs_packets = atomic_long_read(&c->mfc_un.res.pkt); mfcs.mfcs_bytes = atomic_long_read(&c->mfc_un.res.bytes); mfcs.mfcs_wrong_if = atomic_long_read(&c->mfc_un.res.wrong_if); if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) || nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse), RTA_PAD)) return -EMSGSIZE; rtm->rtm_type = RTN_MULTICAST; return 1; } static bool mr_mfc_uses_dev(const struct mr_table *mrt, const struct mr_mfc *c, const struct net_device *dev) { int ct; for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { const struct net_device *vif_dev; const struct vif_device *vif; vif = &mrt->vif_table[ct]; vif_dev = rcu_access_pointer(vif->dev); if (vif_dev && c->mfc_un.res.ttls[ct] < 255 && vif_dev == dev) return true; } return false; } int mr_table_dump(struct mr_table *mrt, struct sk_buff *skb, struct netlink_callback *cb, int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter) { unsigned int e = 0, s_e = cb->args[1]; unsigned int flags = NLM_F_MULTI; struct mr_mfc *mfc; int err; if (filter->filter_set) flags |= NLM_F_DUMP_FILTERED; list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list, lockdep_rtnl_is_held()) { if (e < s_e) goto next_entry; if (filter->dev && !mr_mfc_uses_dev(mrt, mfc, filter->dev)) goto next_entry; err = fill(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags); if (err < 0) goto out; next_entry: e++; } spin_lock_bh(lock); list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) { if (e < s_e) goto next_entry2; err = fill(mrt, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, mfc, RTM_NEWROUTE, flags); if (err < 0) { spin_unlock_bh(lock); goto out; } next_entry2: e++; } spin_unlock_bh(lock); err = 0; out: cb->args[1] = e; return err; } int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb, struct mr_table *(*iter)(struct net *net, struct mr_table *mrt), int (*fill)(struct mr_table *mrt, struct sk_buff *skb, u32 portid, u32 seq, struct mr_mfc *c, int cmd, int flags), spinlock_t *lock, struct fib_dump_filter *filter) { unsigned int t = 0, s_t = cb->args[0]; struct net *net = sock_net(skb->sk); struct mr_table *mrt; int err; /* multicast does not track protocol or have route type other * than RTN_MULTICAST */ if (filter->filter_set) { if (filter->protocol || filter->flags || (filter->rt_type && filter->rt_type != RTN_MULTICAST)) return skb->len; } rcu_read_lock(); for (mrt = iter(net, NULL); mrt; mrt = iter(net, mrt)) { if (t < s_t) goto next_table; err = mr_table_dump(mrt, skb, cb, fill, lock, filter); if (err < 0) break; cb->args[1] = 0; next_table: t++; } rcu_read_unlock(); cb->args[0] = t; return skb->len; } int mr_dump(struct net *net, struct notifier_block *nb, unsigned short family, int (*rules_dump)(struct net *net, struct notifier_block *nb, struct netlink_ext_ack *extack), struct mr_table *(*mr_iter)(struct net *net, struct mr_table *mrt), struct netlink_ext_ack *extack) { struct mr_table *mrt; int err; err = rules_dump(net, nb, extack); if (err) return err; for (mrt = mr_iter(net, NULL); mrt; mrt = mr_iter(net, mrt)) { struct vif_device *v = &mrt->vif_table[0]; struct net_device *vif_dev; struct mr_mfc *mfc; int vifi; /* Notifiy on table VIF entries */ rcu_read_lock(); for (vifi = 0; vifi < mrt->maxvif; vifi++, v++) { vif_dev = rcu_dereference(v->dev); if (!vif_dev) continue; err = mr_call_vif_notifier(nb, family, FIB_EVENT_VIF_ADD, v, vif_dev, vifi, mrt->id, extack); if (err) break; } rcu_read_unlock(); if (err) return err; /* Notify on table MFC entries */ list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) { err = mr_call_mfc_notifier(nb, family, FIB_EVENT_ENTRY_ADD, mfc, mrt->id, extack); if (err) return err; } } return 0; } |
| 632 44 44 217 372 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 | #undef TRACE_SYSTEM #define TRACE_SYSTEM neigh #if !defined(_TRACE_NEIGH_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NEIGH_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #include <net/neighbour.h> #define neigh_state_str(state) \ __print_symbolic(state, \ { NUD_INCOMPLETE, "incomplete" }, \ { NUD_REACHABLE, "reachable" }, \ { NUD_STALE, "stale" }, \ { NUD_DELAY, "delay" }, \ { NUD_PROBE, "probe" }, \ { NUD_FAILED, "failed" }, \ { NUD_NOARP, "noarp" }, \ { NUD_PERMANENT, "permanent"}) TRACE_EVENT(neigh_create, TP_PROTO(struct neigh_table *tbl, struct net_device *dev, const void *pkey, const struct neighbour *n, bool exempt_from_gc), TP_ARGS(tbl, dev, pkey, n, exempt_from_gc), TP_STRUCT__entry( __field(u32, family) __string(dev, dev ? dev->name : "NULL") __field(int, entries) __field(u8, created) __field(u8, gc_exempt) __array(u8, primary_key4, 4) __array(u8, primary_key6, 16) ), TP_fast_assign( __be32 *p32; __entry->family = tbl->family; __assign_str(dev); __entry->entries = atomic_read(&tbl->gc_entries); __entry->created = n != NULL; __entry->gc_exempt = exempt_from_gc; p32 = (__be32 *)__entry->primary_key4; if (tbl->family == AF_INET) *p32 = *(__be32 *)pkey; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (tbl->family == AF_INET6) { struct in6_addr *pin6; pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)pkey; } #endif ), TP_printk("family %d dev %s entries %d primary_key4 %pI4 primary_key6 %pI6c created %d gc_exempt %d", __entry->family, __get_str(dev), __entry->entries, __entry->primary_key4, __entry->primary_key6, __entry->created, __entry->gc_exempt) ); TRACE_EVENT(neigh_update, TP_PROTO(struct neighbour *n, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid), TP_ARGS(n, lladdr, new, flags, nlmsg_pid), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __array(u8, new_lladdr, MAX_ADDR_LEN) __field(u8, new_state) __field(u32, update_flags) __field(u32, pid) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->updated; __entry->used = n->used; if (lladdr) memcpy(__entry->new_lladdr, lladdr, lladdr_len); __entry->new_state = new; __entry->update_flags = flags; __entry->pid = nlmsg_pid; ), TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " "confirmed %lu updated %lu used %lu new_lladdr %s " "new_state %s update_flags %02x pid %d", __entry->family, __get_str(dev), __print_hex_str(__entry->lladdr, __entry->lladdr_len), __entry->flags, neigh_state_str(__entry->nud_state), __entry->type, __entry->dead, __entry->refcnt, __entry->primary_key4, __entry->primary_key6, __entry->confirmed, __entry->updated, __entry->used, __print_hex_str(__entry->new_lladdr, __entry->lladdr_len), neigh_state_str(__entry->new_state), __entry->update_flags, __entry->pid) ); DECLARE_EVENT_CLASS(neigh__update, TP_PROTO(struct neighbour *n, int err), TP_ARGS(n, err), TP_STRUCT__entry( __field(u32, family) __string(dev, (n->dev ? n->dev->name : "NULL")) __array(u8, lladdr, MAX_ADDR_LEN) __field(u8, lladdr_len) __field(u8, flags) __field(u8, nud_state) __field(u8, type) __field(u8, dead) __field(int, refcnt) __array(__u8, primary_key4, 4) __array(__u8, primary_key6, 16) __field(unsigned long, confirmed) __field(unsigned long, updated) __field(unsigned long, used) __field(u32, err) ), TP_fast_assign( int lladdr_len = (n->dev ? n->dev->addr_len : MAX_ADDR_LEN); struct in6_addr *pin6; __be32 *p32; __entry->family = n->tbl->family; __assign_str(dev); __entry->lladdr_len = lladdr_len; memcpy(__entry->lladdr, n->ha, lladdr_len); __entry->flags = n->flags; __entry->nud_state = n->nud_state; __entry->type = n->type; __entry->dead = n->dead; __entry->refcnt = refcount_read(&n->refcnt); pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (n->tbl->family == AF_INET) *p32 = *(__be32 *)n->primary_key; else *p32 = 0; #if IS_ENABLED(CONFIG_IPV6) if (n->tbl->family == AF_INET6) { pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)n->primary_key; } else #endif { ipv6_addr_set_v4mapped(*p32, pin6); } __entry->confirmed = n->confirmed; __entry->updated = n->updated; __entry->used = n->used; __entry->err = err; ), TP_printk("family %d dev %s lladdr %s flags %02x nud_state %s type %02x " "dead %d refcnt %d primary_key4 %pI4 primary_key6 %pI6c " "confirmed %lu updated %lu used %lu err %d", __entry->family, __get_str(dev), __print_hex_str(__entry->lladdr, __entry->lladdr_len), __entry->flags, neigh_state_str(__entry->nud_state), __entry->type, __entry->dead, __entry->refcnt, __entry->primary_key4, __entry->primary_key6, __entry->confirmed, __entry->updated, __entry->used, __entry->err) ); DEFINE_EVENT(neigh__update, neigh_update_done, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_timer_handler, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_event_send_done, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_event_send_dead, TP_PROTO(struct neighbour *neigh, int err), TP_ARGS(neigh, err) ); DEFINE_EVENT(neigh__update, neigh_cleanup_and_release, TP_PROTO(struct neighbour *neigh, int rc), TP_ARGS(neigh, rc) ); #endif /* _TRACE_NEIGH_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 10 9 16 1 1 2 1 11 10 10 10 10 10 9 10 10 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 | // 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_ids.h> #include <linux/bpf_local_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/rcupdate.h> #include <linux/rcupdate_trace.h> #include <linux/rcupdate_wait.h> #define BPF_LOCAL_STORAGE_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_CLONE) static struct bpf_local_storage_map_bucket * select_bucket(struct bpf_local_storage_map *smap, struct bpf_local_storage *local_storage) { return &smap->buckets[hash_ptr(local_storage, smap->bucket_log)]; } static int mem_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct bpf_map *map = &smap->map; if (!map->ops->map_local_storage_charge) return 0; return map->ops->map_local_storage_charge(smap, owner, size); } static void mem_uncharge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct bpf_map *map = &smap->map; if (map->ops->map_local_storage_uncharge) map->ops->map_local_storage_uncharge(smap, owner, size); } static struct bpf_local_storage __rcu ** owner_storage(struct bpf_local_storage_map *smap, void *owner) { struct bpf_map *map = &smap->map; return map->ops->map_owner_storage_ptr(owner); } static bool selem_linked_to_storage_lockless(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed_lockless(&selem->snode); } static bool selem_linked_to_storage(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->snode); } static bool selem_linked_to_map(const struct bpf_local_storage_elem *selem) { return !hlist_unhashed(&selem->map_node); } struct bpf_local_storage_elem * bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value, bool swap_uptrs) { struct bpf_local_storage_elem *selem; if (mem_charge(smap, owner, smap->elem_size)) return NULL; selem = bpf_map_kmalloc_nolock(&smap->map, smap->elem_size, __GFP_ZERO, NUMA_NO_NODE); if (selem) { RCU_INIT_POINTER(SDATA(selem)->smap, smap); atomic_set(&selem->state, 0); if (value) { /* No need to call check_and_init_map_value as memory is zero init */ copy_map_value(&smap->map, SDATA(selem)->data, value); if (swap_uptrs) bpf_obj_swap_uptrs(smap->map.record, SDATA(selem)->data, value); } return selem; } mem_uncharge(smap, owner, smap->elem_size); return NULL; } static void bpf_local_storage_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage *local_storage; /* * RCU Tasks Trace grace period implies RCU grace period, do * kfree() directly. */ local_storage = container_of(rcu, struct bpf_local_storage, rcu); kfree(local_storage); } static void bpf_local_storage_free(struct bpf_local_storage *local_storage, bool reuse_now) { if (!local_storage) return; if (reuse_now) { kfree_rcu(local_storage, rcu); return; } call_rcu_tasks_trace(&local_storage->rcu, bpf_local_storage_free_trace_rcu); } static void bpf_selem_free_trace_rcu(struct rcu_head *rcu) { struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; selem = container_of(rcu, struct bpf_local_storage_elem, rcu); /* The bpf_local_storage_map_free will wait for rcu_barrier */ smap = rcu_dereference_check(SDATA(selem)->smap, 1); if (smap) bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); /* * RCU Tasks Trace grace period implies RCU grace period, do * kfree() directly. */ kfree(selem); } void bpf_selem_free(struct bpf_local_storage_elem *selem, bool reuse_now) { struct bpf_local_storage_map *smap; smap = rcu_dereference_check(SDATA(selem)->smap, 1); if (reuse_now) { if (smap) bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); kfree_rcu(selem, rcu); return; } call_rcu_tasks_trace(&selem->rcu, bpf_selem_free_trace_rcu); } static void bpf_selem_free_list(struct hlist_head *list, bool reuse_now) { struct bpf_local_storage_elem *selem; struct hlist_node *n; /* The "_safe" iteration is needed. * The loop is not removing the selem from the list * but bpf_selem_free will use the selem->rcu_head * which is union-ized with the selem->free_node. */ hlist_for_each_entry_safe(selem, n, list, free_node) bpf_selem_free(selem, reuse_now); } static void bpf_selem_unlink_storage_nolock_misc(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map *smap, struct bpf_local_storage *local_storage, bool free_local_storage, bool pin_owner) { void *owner = local_storage->owner; u32 uncharge = smap->elem_size; if (rcu_access_pointer(local_storage->cache[smap->cache_idx]) == SDATA(selem)) RCU_INIT_POINTER(local_storage->cache[smap->cache_idx], NULL); if (pin_owner && !refcount_inc_not_zero(&local_storage->owner_refcnt)) return; uncharge += free_local_storage ? sizeof(*local_storage) : 0; mem_uncharge(smap, local_storage->owner, uncharge); local_storage->mem_charge -= uncharge; if (free_local_storage) { local_storage->owner = NULL; /* After this RCU_INIT, owner may be freed and cannot be used */ RCU_INIT_POINTER(*owner_storage(smap, owner), NULL); } if (pin_owner) refcount_dec(&local_storage->owner_refcnt); } /* local_storage->lock must be held and selem->local_storage == local_storage. * The caller must ensure selem->smap is still valid to be * dereferenced for its smap->elem_size and smap->cache_idx. */ static bool bpf_selem_unlink_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem, struct hlist_head *free_selem_list) { struct bpf_local_storage_map *smap; bool free_local_storage; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); free_local_storage = hlist_is_singular_node(&selem->snode, &local_storage->list); bpf_selem_unlink_storage_nolock_misc(selem, smap, local_storage, free_local_storage, false); hlist_del_init_rcu(&selem->snode); hlist_add_head(&selem->free_node, free_selem_list); return free_local_storage; } void bpf_selem_link_storage_nolock(struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map *smap; smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); local_storage->mem_charge += smap->elem_size; RCU_INIT_POINTER(selem->local_storage, local_storage); hlist_add_head_rcu(&selem->snode, &local_storage->list); } static int bpf_selem_unlink_map(struct bpf_local_storage_elem *selem) { struct bpf_local_storage *local_storage; struct bpf_local_storage_map *smap; struct bpf_local_storage_map_bucket *b; unsigned long flags; int err; local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); b = select_bucket(smap, local_storage); err = raw_res_spin_lock_irqsave(&b->lock, flags); if (err) return err; hlist_del_init_rcu(&selem->map_node); raw_res_spin_unlock_irqrestore(&b->lock, flags); return 0; } static void bpf_selem_unlink_map_nolock(struct bpf_local_storage_elem *selem) { hlist_del_init_rcu(&selem->map_node); } int bpf_selem_link_map(struct bpf_local_storage_map *smap, struct bpf_local_storage *local_storage, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_map_bucket *b; unsigned long flags; int err; b = select_bucket(smap, local_storage); err = raw_res_spin_lock_irqsave(&b->lock, flags); if (err) return err; hlist_add_head_rcu(&selem->map_node, &b->list); raw_res_spin_unlock_irqrestore(&b->lock, flags); return 0; } static void bpf_selem_link_map_nolock(struct bpf_local_storage_map_bucket *b, struct bpf_local_storage_elem *selem) { hlist_add_head_rcu(&selem->map_node, &b->list); } /* * Unlink an selem from map and local storage with lock held. * This is the common path used by local storages to delete an selem. */ int bpf_selem_unlink(struct bpf_local_storage_elem *selem) { struct bpf_local_storage *local_storage; bool free_local_storage = false; HLIST_HEAD(selem_free_list); unsigned long flags; int err; if (in_nmi()) return -EOPNOTSUPP; if (unlikely(!selem_linked_to_storage_lockless(selem))) /* selem has already been unlinked from sk */ return 0; local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); err = raw_res_spin_lock_irqsave(&local_storage->lock, flags); if (err) return err; if (likely(selem_linked_to_storage(selem))) { /* Always unlink from map before unlinking from local_storage * because selem will be freed after successfully unlinked from * the local_storage. */ err = bpf_selem_unlink_map(selem); if (err) goto out; free_local_storage = bpf_selem_unlink_storage_nolock( local_storage, selem, &selem_free_list); } out: raw_res_spin_unlock_irqrestore(&local_storage->lock, flags); bpf_selem_free_list(&selem_free_list, false); if (free_local_storage) bpf_local_storage_free(local_storage, false); return err; } /* * Unlink an selem from map and local storage with lockless fallback if callers * are racing or rqspinlock returns error. It should only be called by * bpf_local_storage_destroy() or bpf_local_storage_map_free(). */ static void bpf_selem_unlink_nofail(struct bpf_local_storage_elem *selem, struct bpf_local_storage_map_bucket *b) { bool in_map_free = !!b, free_storage = false; struct bpf_local_storage *local_storage; struct bpf_local_storage_map *smap; unsigned long flags; int err, unlink = 0; local_storage = rcu_dereference_check(selem->local_storage, bpf_rcu_lock_held()); smap = rcu_dereference_check(SDATA(selem)->smap, bpf_rcu_lock_held()); if (smap) { b = b ? : select_bucket(smap, local_storage); err = raw_res_spin_lock_irqsave(&b->lock, flags); if (!err) { /* * Call bpf_obj_free_fields() under b->lock to make sure it is done * exactly once for an selem. Safe to free special fields immediately * as no BPF program should be referencing the selem. */ if (likely(selem_linked_to_map(selem))) { hlist_del_init_rcu(&selem->map_node); bpf_obj_free_fields(smap->map.record, SDATA(selem)->data); unlink++; } raw_res_spin_unlock_irqrestore(&b->lock, flags); } /* * Highly unlikely scenario: resource leak * * When map_free(selem1), destroy(selem1) and destroy(selem2) are racing * and both selem belong to the same bucket, if destroy(selem2) acquired * b->lock and block for too long, neither map_free(selem1) and * destroy(selem1) will be able to free the special field associated * with selem1 as raw_res_spin_lock_irqsave() returns -ETIMEDOUT. */ WARN_ON_ONCE(err && in_map_free); if (!err || in_map_free) RCU_INIT_POINTER(SDATA(selem)->smap, NULL); } if (local_storage) { err = raw_res_spin_lock_irqsave(&local_storage->lock, flags); if (!err) { if (likely(selem_linked_to_storage(selem))) { free_storage = hlist_is_singular_node(&selem->snode, &local_storage->list); /* * Okay to skip clearing owner_storage and storage->owner in * destroy() since the owner is going away. No user or bpf * programs should be able to reference it. */ if (smap && in_map_free) bpf_selem_unlink_storage_nolock_misc( selem, smap, local_storage, free_storage, true); hlist_del_init_rcu(&selem->snode); unlink++; } raw_res_spin_unlock_irqrestore(&local_storage->lock, flags); } /* * Highly unlikely scenario: memory leak * * When destroy() fails to acqurire local_storage->lock and initializes * selem->local_storage to NULL before any racing map_free() sees the same * selem, no one will free the local storage. */ WARN_ON_ONCE(err && !in_map_free); if (!err || !in_map_free) RCU_INIT_POINTER(selem->local_storage, NULL); } if (unlink != 2) atomic_or(in_map_free ? SELEM_MAP_UNLINKED : SELEM_STORAGE_UNLINKED, &selem->state); /* * Normally, an selem can be unlinked under local_storage->lock and b->lock, and * then freed after an RCU grace period. However, if destroy() and map_free() are * racing or rqspinlock returns errors in unlikely situations (unlink != 2), free * the selem only after both map_free() and destroy() see the selem. */ if (unlink == 2 || atomic_cmpxchg(&selem->state, SELEM_UNLINKED, SELEM_TOFREE) == SELEM_UNLINKED) bpf_selem_free(selem, true); if (free_storage) bpf_local_storage_free(local_storage, true); } void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { unsigned long flags; int err; /* spinlock is needed to avoid racing with the * parallel delete. Otherwise, publishing an already * deleted sdata to the cache will become a use-after-free * problem in the next bpf_local_storage_lookup(). */ err = raw_res_spin_lock_irqsave(&local_storage->lock, flags); if (err) return; if (selem_linked_to_storage(selem)) rcu_assign_pointer(local_storage->cache[smap->cache_idx], SDATA(selem)); raw_res_spin_unlock_irqrestore(&local_storage->lock, flags); } static int check_flags(const struct bpf_local_storage_data *old_sdata, u64 map_flags) { if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) /* elem already exists */ return -EEXIST; if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) /* elem doesn't exist, cannot update it */ return -ENOENT; return 0; } int bpf_local_storage_alloc(void *owner, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *first_selem) { struct bpf_local_storage *prev_storage, *storage; struct bpf_local_storage **owner_storage_ptr; struct bpf_local_storage_map_bucket *b; unsigned long flags; int err; err = mem_charge(smap, owner, sizeof(*storage)); if (err) return err; storage = bpf_map_kmalloc_nolock(&smap->map, sizeof(*storage), __GFP_ZERO, NUMA_NO_NODE); if (!storage) { err = -ENOMEM; goto uncharge; } INIT_HLIST_HEAD(&storage->list); raw_res_spin_lock_init(&storage->lock); storage->owner = owner; storage->mem_charge = sizeof(*storage); refcount_set(&storage->owner_refcnt, 1); bpf_selem_link_storage_nolock(storage, first_selem); b = select_bucket(smap, storage); err = raw_res_spin_lock_irqsave(&b->lock, flags); if (err) goto uncharge; bpf_selem_link_map_nolock(b, first_selem); owner_storage_ptr = (struct bpf_local_storage **)owner_storage(smap, owner); /* Publish storage to the owner. * Instead of using any lock of the kernel object (i.e. owner), * cmpxchg will work with any kernel object regardless what * the running context is, bh, irq...etc. * * From now on, the owner->storage pointer (e.g. sk->sk_bpf_storage) * is protected by the storage->lock. Hence, when freeing * the owner->storage, the storage->lock must be held before * setting owner->storage ptr to NULL. */ prev_storage = cmpxchg(owner_storage_ptr, NULL, storage); if (unlikely(prev_storage)) { bpf_selem_unlink_map_nolock(first_selem); raw_res_spin_unlock_irqrestore(&b->lock, flags); err = -EAGAIN; goto uncharge; } raw_res_spin_unlock_irqrestore(&b->lock, flags); return 0; uncharge: bpf_local_storage_free(storage, true); mem_uncharge(smap, owner, sizeof(*storage)); return err; } /* sk cannot be going away because it is linking new elem * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). * Otherwise, it will become a leak (and other memory issues * during map destruction). */ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, void *value, u64 map_flags, bool swap_uptrs) { struct bpf_local_storage_data *old_sdata = NULL; struct bpf_local_storage_elem *alloc_selem, *selem = NULL; struct bpf_local_storage *local_storage; struct bpf_local_storage_map_bucket *b; HLIST_HEAD(old_selem_free_list); unsigned long flags, b_flags; int err; /* BPF_EXIST and BPF_NOEXIST cannot be both set */ if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || /* BPF_F_LOCK can only be used in a value with spin_lock */ unlikely((map_flags & BPF_F_LOCK) && !btf_record_has_field(smap->map.record, BPF_SPIN_LOCK))) return ERR_PTR(-EINVAL); local_storage = rcu_dereference_check(*owner_storage(smap, owner), bpf_rcu_lock_held()); if (!local_storage || hlist_empty(&local_storage->list)) { /* Very first elem for the owner */ err = check_flags(NULL, map_flags); if (err) return ERR_PTR(err); selem = bpf_selem_alloc(smap, owner, value, swap_uptrs); if (!selem) return ERR_PTR(-ENOMEM); err = bpf_local_storage_alloc(owner, smap, selem); if (err) { bpf_selem_free(selem, true); mem_uncharge(smap, owner, smap->elem_size); return ERR_PTR(err); } return SDATA(selem); } if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { /* Hoping to find an old_sdata to do inline update * such that it can avoid taking the local_storage->lock * and changing the lists. */ old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) return ERR_PTR(err); if (old_sdata && selem_linked_to_storage_lockless(SELEM(old_sdata))) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); return old_sdata; } } /* A lookup has just been done before and concluded a new selem is * needed. The chance of an unnecessary alloc is unlikely. */ alloc_selem = selem = bpf_selem_alloc(smap, owner, value, swap_uptrs); if (!alloc_selem) return ERR_PTR(-ENOMEM); err = raw_res_spin_lock_irqsave(&local_storage->lock, flags); if (err) goto free_selem; /* Recheck local_storage->list under local_storage->lock */ if (unlikely(hlist_empty(&local_storage->list))) { /* A parallel del is happening and local_storage is going * away. It has just been checked before, so very * unlikely. Return instead of retry to keep things * simple. */ err = -EAGAIN; goto unlock; } old_sdata = bpf_local_storage_lookup(local_storage, smap, false); err = check_flags(old_sdata, map_flags); if (err) goto unlock; if (old_sdata && (map_flags & BPF_F_LOCK)) { copy_map_value_locked(&smap->map, old_sdata->data, value, false); selem = SELEM(old_sdata); goto unlock; } b = select_bucket(smap, local_storage); err = raw_res_spin_lock_irqsave(&b->lock, b_flags); if (err) goto unlock; alloc_selem = NULL; /* First, link the new selem to the map */ bpf_selem_link_map_nolock(b, selem); /* Second, link (and publish) the new selem to local_storage */ bpf_selem_link_storage_nolock(local_storage, selem); /* Third, remove old selem, SELEM(old_sdata) */ if (old_sdata) { bpf_selem_unlink_map_nolock(SELEM(old_sdata)); bpf_selem_unlink_storage_nolock(local_storage, SELEM(old_sdata), &old_selem_free_list); } raw_res_spin_unlock_irqrestore(&b->lock, b_flags); unlock: raw_res_spin_unlock_irqrestore(&local_storage->lock, flags); free_selem: bpf_selem_free_list(&old_selem_free_list, false); if (alloc_selem) { mem_uncharge(smap, owner, smap->elem_size); bpf_selem_free(alloc_selem, true); } return err ? ERR_PTR(err) : SDATA(selem); } static u16 bpf_local_storage_cache_idx_get(struct bpf_local_storage_cache *cache) { u64 min_usage = U64_MAX; u16 i, res = 0; spin_lock(&cache->idx_lock); for (i = 0; i < BPF_LOCAL_STORAGE_CACHE_SIZE; i++) { if (cache->idx_usage_counts[i] < min_usage) { min_usage = cache->idx_usage_counts[i]; res = i; /* Found a free cache_idx */ if (!min_usage) break; } } cache->idx_usage_counts[res]++; spin_unlock(&cache->idx_lock); return res; } static void bpf_local_storage_cache_idx_free(struct bpf_local_storage_cache *cache, u16 idx) { spin_lock(&cache->idx_lock); cache->idx_usage_counts[idx]--; spin_unlock(&cache->idx_lock); } int bpf_local_storage_map_alloc_check(union bpf_attr *attr) { if (attr->map_flags & ~BPF_LOCAL_STORAGE_CREATE_FLAG_MASK || !(attr->map_flags & BPF_F_NO_PREALLOC) || attr->max_entries || attr->key_size != sizeof(int) || !attr->value_size || /* Enforce BTF for userspace sk dumping */ !attr->btf_key_type_id || !attr->btf_value_type_id) return -EINVAL; if (attr->value_size > BPF_LOCAL_STORAGE_MAX_VALUE_SIZE) return -E2BIG; return 0; } int bpf_local_storage_map_check_btf(struct bpf_map *map, const struct btf *btf, const struct btf_type *key_type, const struct btf_type *value_type) { if (!btf_type_is_i32(key_type)) return -EINVAL; return 0; } /* * Destroy local storage when the owner is going away. Caller must uncharge memory * if memory charging is used. */ u32 bpf_local_storage_destroy(struct bpf_local_storage *local_storage) { struct bpf_local_storage_elem *selem; /* Neither the bpf_prog nor the bpf_map's syscall * could be modifying the local_storage->list now. * Thus, no elem can be added to or deleted from the * local_storage->list by the bpf_prog or by the bpf_map's syscall. * * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the local_storage->list and * the map's bucket->list. */ hlist_for_each_entry_rcu(selem, &local_storage->list, snode) bpf_selem_unlink_nofail(selem, NULL); if (!refcount_dec_and_test(&local_storage->owner_refcnt)) { while (refcount_read(&local_storage->owner_refcnt)) cpu_relax(); /* * Paired with refcount_dec() in bpf_selem_unlink_nofail() * to make sure destroy() sees the correct local_storage->mem_charge. */ smp_mb(); } return local_storage->mem_charge; } u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map) { struct bpf_local_storage_map *smap = (struct bpf_local_storage_map *)map; u64 usage = sizeof(*smap); /* The dynamically callocated selems are not counted currently. */ usage += sizeof(*smap->buckets) * (1ULL << smap->bucket_log); return usage; } struct bpf_map * bpf_local_storage_map_alloc(union bpf_attr *attr, struct bpf_local_storage_cache *cache) { struct bpf_local_storage_map *smap; unsigned int i; u32 nbuckets; int err; smap = bpf_map_area_alloc(sizeof(*smap), NUMA_NO_NODE); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); nbuckets = roundup_pow_of_two(num_possible_cpus()); /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ nbuckets = max_t(u32, 2, nbuckets); smap->bucket_log = ilog2(nbuckets); smap->buckets = bpf_map_kvcalloc(&smap->map, nbuckets, sizeof(*smap->buckets), GFP_USER | __GFP_NOWARN); if (!smap->buckets) { err = -ENOMEM; goto free_smap; } for (i = 0; i < nbuckets; i++) { INIT_HLIST_HEAD(&smap->buckets[i].list); raw_res_spin_lock_init(&smap->buckets[i].lock); } smap->elem_size = offsetof(struct bpf_local_storage_elem, sdata.data[attr->value_size]); smap->cache_idx = bpf_local_storage_cache_idx_get(cache); return &smap->map; free_smap: kvfree(smap->buckets); bpf_map_area_free(smap); return ERR_PTR(err); } void bpf_local_storage_map_free(struct bpf_map *map, struct bpf_local_storage_cache *cache) { struct bpf_local_storage_map_bucket *b; struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; unsigned int i; smap = (struct bpf_local_storage_map *)map; bpf_local_storage_cache_idx_free(cache, smap->cache_idx); /* Note that this map might be concurrently cloned from * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone * RCU read section to finish before proceeding. New RCU * read sections should be prevented via bpf_map_inc_not_zero. */ synchronize_rcu(); /* bpf prog and the userspace can no longer access this map * now. No new selem (of this map) can be added * to the owner->storage or to the map bucket's list. * * The elem of this map can be cleaned up here * or when the storage is freed e.g. * by bpf_sk_storage_free() during __sk_destruct(). */ for (i = 0; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; rcu_read_lock(); /* No one is adding to b->list now */ restart: hlist_for_each_entry_rcu(selem, &b->list, map_node) { bpf_selem_unlink_nofail(selem, b); if (need_resched()) { cond_resched_rcu(); goto restart; } } rcu_read_unlock(); } /* While freeing the storage we may still need to access the map. * * e.g. when bpf_sk_storage_free() has unlinked selem from the map * which then made the above while((selem = ...)) loop * exit immediately. * * However, while freeing the storage one still needs to access the * smap->elem_size to do the uncharging in * bpf_selem_unlink_storage_nolock(). * * Hence, wait another rcu grace period for the storage to be freed. */ synchronize_rcu(); /* smap remains in use regardless of kmalloc_nolock, so wait unconditionally. */ rcu_barrier_tasks_trace(); rcu_barrier(); kvfree(smap->buckets); bpf_map_area_free(smap); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_TC_MIR_H #define __NET_TC_MIR_H #include <net/act_api.h> #include <linux/tc_act/tc_mirred.h> struct tcf_mirred { struct tc_action common; int tcfm_eaction; u32 tcfm_blockid; bool tcfm_mac_header_xmit; struct net_device __rcu *tcfm_dev; netdevice_tracker tcfm_dev_tracker; struct list_head tcfm_list; }; #define to_mirred(a) ((struct tcf_mirred *)a) static inline bool is_tcf_mirred_egress_redirect(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->id == TCA_ID_MIRRED) return to_mirred(a)->tcfm_eaction == TCA_EGRESS_REDIR; #endif return false; } static inline bool is_tcf_mirred_egress_mirror(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->id == TCA_ID_MIRRED) return to_mirred(a)->tcfm_eaction == TCA_EGRESS_MIRROR; #endif return false; } static inline bool is_tcf_mirred_ingress_redirect(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->id == TCA_ID_MIRRED) return to_mirred(a)->tcfm_eaction == TCA_INGRESS_REDIR; #endif return false; } static inline bool is_tcf_mirred_ingress_mirror(const struct tc_action *a) { #ifdef CONFIG_NET_CLS_ACT if (a->ops && a->ops->id == TCA_ID_MIRRED) return to_mirred(a)->tcfm_eaction == TCA_INGRESS_MIRROR; #endif return false; } static inline struct net_device *tcf_mirred_dev(const struct tc_action *a) { return rtnl_dereference(to_mirred(a)->tcfm_dev); } #endif /* __NET_TC_MIR_H */ |
| 22 3 1 2 11 5 2 1 1 15 2 3 10 10 3 6 7 9 4 3 10 13 13 7 2 5 8 8 8 8 8 8 8 8 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_skbmod.c skb data modifier * * Copyright (c) 2016 Jamal Hadi Salim <jhs@mojatatu.com> */ #include <linux/module.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/inet_ecn.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <linux/tc_act/tc_skbmod.h> #include <net/tc_act/tc_skbmod.h> static struct tc_action_ops act_skbmod_ops; TC_INDIRECT_SCOPE int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_skbmod *d = to_skbmod(a); struct tcf_skbmod_params *p; int max_edit_len, err; u64 flags; tcf_lastuse_update(&d->tcf_tm); bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb); p = rcu_dereference_bh(d->skbmod_p); if (unlikely(p->action == TC_ACT_SHOT)) goto drop; max_edit_len = skb_mac_header_len(skb); flags = p->flags; /* tcf_skbmod_init() guarantees "flags" to be one of the following: * 1. a combination of SKBMOD_F_{DMAC,SMAC,ETYPE} * 2. SKBMOD_F_SWAPMAC * 3. SKBMOD_F_ECN * SKBMOD_F_ECN only works with IP packets; all other flags only work with Ethernet * packets. */ if (flags == SKBMOD_F_ECN) { switch (skb_protocol(skb, true)) { case cpu_to_be16(ETH_P_IP): case cpu_to_be16(ETH_P_IPV6): max_edit_len += skb_network_header_len(skb); break; default: goto out; } } else if (!skb->dev || skb->dev->type != ARPHRD_ETHER) { goto out; } err = skb_ensure_writable(skb, max_edit_len); if (unlikely(err)) /* best policy is to drop on the floor */ goto drop; if (flags & SKBMOD_F_DMAC) ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst); if (flags & SKBMOD_F_SMAC) ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src); if (flags & SKBMOD_F_ETYPE) eth_hdr(skb)->h_proto = p->eth_type; if (flags & SKBMOD_F_SWAPMAC) { u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */ /*XXX: I am sure we can come up with more efficient swapping*/ ether_addr_copy((u8 *)tmpaddr, eth_hdr(skb)->h_dest); ether_addr_copy(eth_hdr(skb)->h_dest, eth_hdr(skb)->h_source); ether_addr_copy(eth_hdr(skb)->h_source, (u8 *)tmpaddr); } if (flags & SKBMOD_F_ECN) INET_ECN_set_ce(skb); out: return p->action; drop: qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats)); return TC_ACT_SHOT; } static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = { [TCA_SKBMOD_PARMS] = { .len = sizeof(struct tc_skbmod) }, [TCA_SKBMOD_DMAC] = { .len = ETH_ALEN }, [TCA_SKBMOD_SMAC] = { .len = ETH_ALEN }, [TCA_SKBMOD_ETYPE] = { .type = NLA_U16 }, }; static int tcf_skbmod_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_skbmod_ops.net_id); bool ovr = flags & TCA_ACT_FLAGS_REPLACE; bool bind = flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_SKBMOD_MAX + 1]; struct tcf_skbmod_params *p, *p_old; struct tcf_chain *goto_ch = NULL; struct tc_skbmod *parm; u32 lflags = 0, index; struct tcf_skbmod *d; bool exists = false; u8 *daddr = NULL; u8 *saddr = NULL; u16 eth_type = 0; int ret = 0, err; if (!nla) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_SKBMOD_MAX, nla, skbmod_policy, NULL); if (err < 0) return err; if (!tb[TCA_SKBMOD_PARMS]) return -EINVAL; if (tb[TCA_SKBMOD_DMAC]) { daddr = nla_data(tb[TCA_SKBMOD_DMAC]); lflags |= SKBMOD_F_DMAC; } if (tb[TCA_SKBMOD_SMAC]) { saddr = nla_data(tb[TCA_SKBMOD_SMAC]); lflags |= SKBMOD_F_SMAC; } if (tb[TCA_SKBMOD_ETYPE]) { eth_type = nla_get_u16(tb[TCA_SKBMOD_ETYPE]); lflags |= SKBMOD_F_ETYPE; } parm = nla_data(tb[TCA_SKBMOD_PARMS]); index = parm->index; if (parm->flags & SKBMOD_F_SWAPMAC) lflags = SKBMOD_F_SWAPMAC; if (parm->flags & SKBMOD_F_ECN) lflags = SKBMOD_F_ECN; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (!lflags) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_skbmod_ops, bind, true, flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (!ovr) { tcf_idr_release(*a, bind); return -EEXIST; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; d = to_skbmod(*a); p = kzalloc_obj(struct tcf_skbmod_params); if (unlikely(!p)) { err = -ENOMEM; goto put_chain; } p->flags = lflags; p->action = parm->action; if (ovr) spin_lock_bh(&d->tcf_lock); /* Protected by tcf_lock if overwriting existing action. */ goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); p_old = rcu_dereference_protected(d->skbmod_p, 1); if (lflags & SKBMOD_F_DMAC) ether_addr_copy(p->eth_dst, daddr); if (lflags & SKBMOD_F_SMAC) ether_addr_copy(p->eth_src, saddr); if (lflags & SKBMOD_F_ETYPE) p->eth_type = htons(eth_type); rcu_assign_pointer(d->skbmod_p, p); if (ovr) spin_unlock_bh(&d->tcf_lock); if (p_old) kfree_rcu(p_old, rcu); if (goto_ch) tcf_chain_put_by_act(goto_ch); 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_skbmod_cleanup(struct tc_action *a) { struct tcf_skbmod *d = to_skbmod(a); struct tcf_skbmod_params *p; p = rcu_dereference_protected(d->skbmod_p, 1); if (p) kfree_rcu(p, rcu); } static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { struct tcf_skbmod *d = to_skbmod(a); unsigned char *b = skb_tail_pointer(skb); struct tcf_skbmod_params *p; struct tc_skbmod opt; struct tcf_t t; memset(&opt, 0, sizeof(opt)); opt.index = d->tcf_index; opt.refcnt = refcount_read(&d->tcf_refcnt) - ref; opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind; rcu_read_lock(); p = rcu_dereference(d->skbmod_p); opt.action = p->action; opt.flags = p->flags; if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if ((p->flags & SKBMOD_F_DMAC) && nla_put(skb, TCA_SKBMOD_DMAC, ETH_ALEN, p->eth_dst)) goto nla_put_failure; if ((p->flags & SKBMOD_F_SMAC) && nla_put(skb, TCA_SKBMOD_SMAC, ETH_ALEN, p->eth_src)) goto nla_put_failure; if ((p->flags & SKBMOD_F_ETYPE) && nla_put_u16(skb, TCA_SKBMOD_ETYPE, ntohs(p->eth_type))) goto nla_put_failure; tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD)) goto nla_put_failure; rcu_read_unlock(); return skb->len; nla_put_failure: rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } static struct tc_action_ops act_skbmod_ops = { .kind = "skbmod", .id = TCA_ACT_SKBMOD, .owner = THIS_MODULE, .act = tcf_skbmod_act, .dump = tcf_skbmod_dump, .init = tcf_skbmod_init, .cleanup = tcf_skbmod_cleanup, .size = sizeof(struct tcf_skbmod), }; MODULE_ALIAS_NET_ACT("skbmod"); static __net_init int skbmod_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_skbmod_ops.net_id); return tc_action_net_init(net, tn, &act_skbmod_ops); } static void __net_exit skbmod_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_skbmod_ops.net_id); } static struct pernet_operations skbmod_net_ops = { .init = skbmod_init_net, .exit_batch = skbmod_exit_net, .id = &act_skbmod_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim, <jhs@mojatatu.com>"); MODULE_DESCRIPTION("SKB data mod-ing"); MODULE_LICENSE("GPL"); static int __init skbmod_init_module(void) { return tcf_register_action(&act_skbmod_ops, &skbmod_net_ops); } static void __exit skbmod_cleanup_module(void) { tcf_unregister_action(&act_skbmod_ops, &skbmod_net_ops); } module_init(skbmod_init_module); module_exit(skbmod_cleanup_module); |
| 5 5 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 2015 Red Hat GmbH * Author: Florian Westphal <fw@strlen.de> */ #include <linux/module.h> #include <linux/static_key.h> #include <linux/hash.h> #include <linux/siphash.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #define NFT_TRACETYPE_LL_HSIZE 20 #define NFT_TRACETYPE_NETWORK_HSIZE 40 #define NFT_TRACETYPE_TRANSPORT_HSIZE 20 DEFINE_STATIC_KEY_FALSE(nft_trace_enabled); EXPORT_SYMBOL_GPL(nft_trace_enabled); static int trace_fill_header(struct sk_buff *nlskb, u16 type, const struct sk_buff *skb, int off, unsigned int len) { struct nlattr *nla; if (len == 0) return 0; nla = nla_reserve(nlskb, type, len); if (!nla || skb_copy_bits(skb, off, nla_data(nla), len)) return -1; return 0; } static int nf_trace_fill_ll_header(struct sk_buff *nlskb, const struct sk_buff *skb) { struct vlan_ethhdr veth; int off; BUILD_BUG_ON(sizeof(veth) > NFT_TRACETYPE_LL_HSIZE); off = skb_mac_header(skb) - skb->data; if (off != -ETH_HLEN) return -1; if (skb_copy_bits(skb, off, &veth, ETH_HLEN)) return -1; veth.h_vlan_proto = skb->vlan_proto; veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); veth.h_vlan_encapsulated_proto = skb->protocol; return nla_put(nlskb, NFTA_TRACE_LL_HEADER, sizeof(veth), &veth); } static int nf_trace_fill_dev_info(struct sk_buff *nlskb, const struct net_device *indev, const struct net_device *outdev) { if (indev) { if (nla_put_be32(nlskb, NFTA_TRACE_IIF, htonl(indev->ifindex))) return -1; if (nla_put_be16(nlskb, NFTA_TRACE_IIFTYPE, htons(indev->type))) return -1; } if (outdev) { if (nla_put_be32(nlskb, NFTA_TRACE_OIF, htonl(outdev->ifindex))) return -1; if (nla_put_be16(nlskb, NFTA_TRACE_OIFTYPE, htons(outdev->type))) return -1; } return 0; } static int nf_trace_fill_ct_info(struct sk_buff *nlskb, const struct sk_buff *skb) { const struct nf_ct_hook *ct_hook; enum ip_conntrack_info ctinfo; const struct nf_conn *ct; u32 state; ct_hook = rcu_dereference(nf_ct_hook); if (!ct_hook) return 0; ct = nf_ct_get(skb, &ctinfo); if (!ct) { if (ctinfo != IP_CT_UNTRACKED) /* not seen by conntrack or invalid */ return 0; state = NF_CT_STATE_UNTRACKED_BIT; } else { state = NF_CT_STATE_BIT(ctinfo); } if (nla_put_be32(nlskb, NFTA_TRACE_CT_STATE, htonl(state))) return -1; if (ct) { u32 id = ct_hook->get_id(&ct->ct_general); u32 status = READ_ONCE(ct->status); u8 dir = CTINFO2DIR(ctinfo); if (nla_put_u8(nlskb, NFTA_TRACE_CT_DIRECTION, dir)) return -1; if (nla_put_be32(nlskb, NFTA_TRACE_CT_ID, (__force __be32)id)) return -1; /* Kernel implementation detail, withhold this from userspace for now */ status &= ~IPS_NAT_CLASH; if (status && nla_put_be32(nlskb, NFTA_TRACE_CT_STATUS, htonl(status))) return -1; } return 0; } static int nf_trace_fill_pkt_info(struct sk_buff *nlskb, const struct nft_pktinfo *pkt) { const struct sk_buff *skb = pkt->skb; int off = skb_network_offset(skb); unsigned int len, nh_end; nh_end = pkt->flags & NFT_PKTINFO_L4PROTO ? nft_thoff(pkt) : skb->len; len = min_t(unsigned int, nh_end - skb_network_offset(skb), NFT_TRACETYPE_NETWORK_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_NETWORK_HEADER, skb, off, len)) return -1; if (pkt->flags & NFT_PKTINFO_L4PROTO) { len = min_t(unsigned int, skb->len - nft_thoff(pkt), NFT_TRACETYPE_TRANSPORT_HSIZE); if (trace_fill_header(nlskb, NFTA_TRACE_TRANSPORT_HEADER, skb, nft_thoff(pkt), len)) return -1; } if (!skb_mac_header_was_set(skb)) return 0; if (skb_vlan_tag_get(skb)) return nf_trace_fill_ll_header(nlskb, skb); off = skb_mac_header(skb) - skb->data; len = min_t(unsigned int, -off, NFT_TRACETYPE_LL_HSIZE); return trace_fill_header(nlskb, NFTA_TRACE_LL_HEADER, skb, off, len); } static int nf_trace_fill_rule_info(struct sk_buff *nlskb, const struct nft_verdict *verdict, const struct nft_rule_dp *rule, const struct nft_traceinfo *info) { if (!rule || rule->is_last) return 0; /* a continue verdict with ->type == RETURN means that this is * an implicit return (end of chain reached). * * Since no rule matched, the ->rule pointer is invalid. */ if (info->type == NFT_TRACETYPE_RETURN && verdict->code == NFT_CONTINUE) return 0; return nla_put_be64(nlskb, NFTA_TRACE_RULE_HANDLE, cpu_to_be64(rule->handle), NFTA_TRACE_PAD); } static bool nft_trace_have_verdict_chain(const struct nft_verdict *verdict, struct nft_traceinfo *info) { switch (info->type) { case NFT_TRACETYPE_RETURN: case NFT_TRACETYPE_RULE: break; default: return false; } switch (verdict->code) { case NFT_JUMP: case NFT_GOTO: break; default: return false; } return true; } static const struct nft_chain *nft_trace_get_chain(const struct nft_rule_dp *rule, const struct nft_traceinfo *info) { const struct nft_rule_dp_last *last; if (!rule) return &info->basechain->chain; while (!rule->is_last) rule = nft_rule_next(rule); last = (const struct nft_rule_dp_last *)rule; if (WARN_ON_ONCE(!last->chain)) return &info->basechain->chain; return last->chain; } void nft_trace_notify(const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, const struct nft_rule_dp *rule, struct nft_traceinfo *info) { const struct nft_chain *chain; struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int size; u32 mark = 0; u16 event; if (!nfnetlink_has_listeners(nft_net(pkt), NFNLGRP_NFTRACE)) return; chain = nft_trace_get_chain(rule, info); size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(strlen(chain->table->name)) + nla_total_size(strlen(chain->name)) + nla_total_size_64bit(sizeof(__be64)) + /* rule handle */ nla_total_size(sizeof(__be32)) + /* trace type */ nla_total_size(0) + /* VERDICT, nested */ nla_total_size(sizeof(u32)) + /* verdict code */ nla_total_size(sizeof(u32)) + /* ct id */ nla_total_size(sizeof(u8)) + /* ct direction */ nla_total_size(sizeof(u32)) + /* ct state */ nla_total_size(sizeof(u32)) + /* ct status */ nla_total_size(sizeof(u32)) + /* trace id */ nla_total_size(NFT_TRACETYPE_LL_HSIZE) + nla_total_size(NFT_TRACETYPE_NETWORK_HSIZE) + nla_total_size(NFT_TRACETYPE_TRANSPORT_HSIZE) + nla_total_size(sizeof(u32)) + /* iif */ nla_total_size(sizeof(__be16)) + /* iiftype */ nla_total_size(sizeof(u32)) + /* oif */ nla_total_size(sizeof(__be16)) + /* oiftype */ nla_total_size(sizeof(u32)) + /* mark */ nla_total_size(sizeof(u32)) + /* nfproto */ nla_total_size(sizeof(u32)); /* policy */ if (nft_trace_have_verdict_chain(verdict, info)) size += nla_total_size(strlen(verdict->chain->name)); /* jump target */ skb = nlmsg_new(size, GFP_ATOMIC); if (!skb) return; event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, NFT_MSG_TRACE); nlh = nfnl_msg_put(skb, 0, 0, event, 0, info->basechain->type->family, NFNETLINK_V0, 0); if (!nlh) goto nla_put_failure; if (nla_put_be32(skb, NFTA_TRACE_NFPROTO, htonl(nft_pf(pkt)))) goto nla_put_failure; if (nla_put_be32(skb, NFTA_TRACE_TYPE, htonl(info->type))) goto nla_put_failure; if (nla_put_u32(skb, NFTA_TRACE_ID, info->skbid)) goto nla_put_failure; if (nla_put_string(skb, NFTA_TRACE_CHAIN, chain->name)) goto nla_put_failure; if (nla_put_string(skb, NFTA_TRACE_TABLE, chain->table->name)) goto nla_put_failure; if (nf_trace_fill_rule_info(skb, verdict, rule, info)) goto nla_put_failure; switch (info->type) { case NFT_TRACETYPE_UNSPEC: case __NFT_TRACETYPE_MAX: break; case NFT_TRACETYPE_RETURN: case NFT_TRACETYPE_RULE: { unsigned int v; if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, verdict)) goto nla_put_failure; /* pkt->skb undefined iff NF_STOLEN, disable dump */ v = verdict->code & NF_VERDICT_MASK; if (v == NF_STOLEN) info->packet_dumped = true; else mark = pkt->skb->mark; break; } case NFT_TRACETYPE_POLICY: mark = pkt->skb->mark; if (nla_put_be32(skb, NFTA_TRACE_POLICY, htonl(info->basechain->policy))) goto nla_put_failure; break; } if (mark && nla_put_be32(skb, NFTA_TRACE_MARK, htonl(mark))) goto nla_put_failure; if (!info->packet_dumped) { if (nf_trace_fill_dev_info(skb, nft_in(pkt), nft_out(pkt))) goto nla_put_failure; if (nf_trace_fill_pkt_info(skb, pkt)) goto nla_put_failure; if (nf_trace_fill_ct_info(skb, pkt->skb)) goto nla_put_failure; info->packet_dumped = true; } nlmsg_end(skb, nlh); nfnetlink_send(skb, nft_net(pkt), 0, NFNLGRP_NFTRACE, 0, GFP_ATOMIC); return; nla_put_failure: WARN_ON_ONCE(1); kfree_skb(skb); } void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, const struct nft_chain *chain) { static siphash_key_t trace_key __read_mostly; struct sk_buff *skb = pkt->skb; info->basechain = nft_base_chain(chain); info->trace = true; info->nf_trace = pkt->skb->nf_trace; info->packet_dumped = false; net_get_random_once(&trace_key, sizeof(trace_key)); info->skbid = (u32)siphash_3u32(hash32_ptr(skb), skb_get_hash_net(nft_net(pkt), skb), skb->skb_iif, &trace_key); } |
| 1306 32 32 32 32 32 32 32 32 31 32 32 32 32 31 32 10 10 10 10 10 32 32 29 3 32 10 1 1 71 71 1198 1193 1195 1198 1198 1198 1181 1181 1 1 1044 967 964 966 967 963 894 343 339 282 296 113 296 298 113 297 352 303 305 305 303 6 6 6 6 1 5 6 1113 1217 1046 1045 308 260 247 309 309 14 10 5 919 922 923 921 922 918 922 921 922 919 3 918 4 117 813 1110 1112 1110 1116 1039 5 5 839 840 5 5 5 275 5 829 830 1 288 106 286 285 286 283 200 200 130 133 133 115 2 113 106 1061 975 1069 1069 1069 1064 149 149 920 919 922 912 917 119 925 303 305 305 24 304 304 302 304 304 303 303 303 305 305 304 305 304 304 215 215 199 199 192 106 104 405 280 301 71 71 71 71 71 14 57 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/dir.c - kernfs directory implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/sched.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/idr.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/hash.h> #include <linux/ns_common.h> #include "kernfs-internal.h" /* * Don't use rename_lock to piggy back on pr_cont_buf. We don't want to * call pr_cont() while holding rename_lock. Because sometimes pr_cont() * will perform wakeups when releasing console_sem. Holding rename_lock * will introduce deadlock if the scheduler reads the kernfs_name in the * wakeup path. */ static DEFINE_SPINLOCK(kernfs_pr_cont_lock); static char kernfs_pr_cont_buf[PATH_MAX]; /* protected by pr_cont_lock */ #define rb_to_kn(X) rb_entry((X), struct kernfs_node, rb) static bool __kernfs_active(struct kernfs_node *kn) { return atomic_read(&kn->active) >= 0; } static bool kernfs_active(struct kernfs_node *kn) { lockdep_assert_held(&kernfs_root(kn)->kernfs_rwsem); return __kernfs_active(kn); } static bool kernfs_lockdep(struct kernfs_node *kn) { #ifdef CONFIG_DEBUG_LOCK_ALLOC return kn->flags & KERNFS_LOCKDEP; #else return false; #endif } /* kernfs_node_depth - compute depth from @from to @to */ static size_t kernfs_depth(struct kernfs_node *from, struct kernfs_node *to) { size_t depth = 0; while (rcu_dereference(to->__parent) && to != from) { depth++; to = rcu_dereference(to->__parent); } return depth; } static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a, struct kernfs_node *b) { size_t da, db; struct kernfs_root *ra = kernfs_root(a), *rb = kernfs_root(b); if (ra != rb) return NULL; da = kernfs_depth(ra->kn, a); db = kernfs_depth(rb->kn, b); while (da > db) { a = rcu_dereference(a->__parent); da--; } while (db > da) { b = rcu_dereference(b->__parent); db--; } /* worst case b and a will be the same at root */ while (b != a) { b = rcu_dereference(b->__parent); a = rcu_dereference(a->__parent); } return a; } /** * kernfs_path_from_node_locked - find a pseudo-absolute path to @kn_to, * where kn_from is treated as root of the path. * @kn_from: kernfs node which should be treated as root for the path * @kn_to: kernfs node to which path is needed * @buf: buffer to copy the path into * @buflen: size of @buf * * We need to handle couple of scenarios here: * [1] when @kn_from is an ancestor of @kn_to at some level * kn_from: /n1/n2/n3 * kn_to: /n1/n2/n3/n4/n5 * result: /n4/n5 * * [2] when @kn_from is on a different hierarchy and we need to find common * ancestor between @kn_from and @kn_to. * kn_from: /n1/n2/n3/n4 * kn_to: /n1/n2/n5 * result: /../../n5 * OR * kn_from: /n1/n2/n3/n4/n5 [depth=5] * kn_to: /n1/n2/n3 [depth=3] * result: /../.. * * [3] when @kn_to is %NULL result will be "(null)" * * Return: the length of the constructed path. If the path would have been * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to, struct kernfs_node *kn_from, char *buf, size_t buflen) { struct kernfs_node *kn, *common; const char parent_str[] = "/.."; size_t depth_from, depth_to, len = 0; ssize_t copied; int i, j; if (!kn_to) return strscpy(buf, "(null)", buflen); if (!kn_from) kn_from = kernfs_root(kn_to)->kn; if (kn_from == kn_to) return strscpy(buf, "/", buflen); common = kernfs_common_ancestor(kn_from, kn_to); if (WARN_ON(!common)) return -EINVAL; depth_to = kernfs_depth(common, kn_to); depth_from = kernfs_depth(common, kn_from); buf[0] = '\0'; for (i = 0; i < depth_from; i++) { copied = strscpy(buf + len, parent_str, buflen - len); if (copied < 0) return copied; len += copied; } /* Calculate how many bytes we need for the rest */ for (i = depth_to - 1; i >= 0; i--) { const char *name; for (kn = kn_to, j = 0; j < i; j++) kn = rcu_dereference(kn->__parent); name = rcu_dereference(kn->name); len += scnprintf(buf + len, buflen - len, "/%s", name); } return len; } /** * kernfs_name - obtain the name of a given node * @kn: kernfs_node of interest * @buf: buffer to copy @kn's name into * @buflen: size of @buf * * Copies the name of @kn into @buf of @buflen bytes. The behavior is * similar to strscpy(). * * Fills buffer with "(null)" if @kn is %NULL. * * Return: the resulting length of @buf. If @buf isn't long enough, * it's filled up to @buflen-1 and nul terminated, and returns -E2BIG. * * This function can be called from any context. */ int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen) { struct kernfs_node *kn_parent; if (!kn) return strscpy(buf, "(null)", buflen); guard(rcu)(); /* * KERNFS_ROOT_INVARIANT_PARENT is ignored here. The name is RCU freed and * the parent is either existing or not. */ kn_parent = rcu_dereference(kn->__parent); return strscpy(buf, kn_parent ? rcu_dereference(kn->name) : "/", buflen); } /** * kernfs_path_from_node - build path of node @to relative to @from. * @from: parent kernfs_node relative to which we need to build the path * @to: kernfs_node of interest * @buf: buffer to copy @to's path into * @buflen: size of @buf * * Builds @to's path relative to @from in @buf. @from and @to must * be on the same kernfs-root. If @from is not parent of @to, then a relative * path (which includes '..'s) as needed to reach from @from to @to is * returned. * * Return: the length of the constructed path. If the path would have been * greater than @buflen, @buf contains the truncated path with the trailing * '\0'. On error, -errno is returned. */ int kernfs_path_from_node(struct kernfs_node *to, struct kernfs_node *from, char *buf, size_t buflen) { struct kernfs_root *root; guard(rcu)(); if (to) { root = kernfs_root(to); if (!(root->flags & KERNFS_ROOT_INVARIANT_PARENT)) { guard(read_lock_irqsave)(&root->kernfs_rename_lock); return kernfs_path_from_node_locked(to, from, buf, buflen); } } return kernfs_path_from_node_locked(to, from, buf, buflen); } EXPORT_SYMBOL_GPL(kernfs_path_from_node); /** * pr_cont_kernfs_name - pr_cont name of a kernfs_node * @kn: kernfs_node of interest * * This function can be called from any context. */ void pr_cont_kernfs_name(struct kernfs_node *kn) { unsigned long flags; spin_lock_irqsave(&kernfs_pr_cont_lock, flags); kernfs_name(kn, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); pr_cont("%s", kernfs_pr_cont_buf); spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags); } /** * pr_cont_kernfs_path - pr_cont path of a kernfs_node * @kn: kernfs_node of interest * * This function can be called from any context. */ void pr_cont_kernfs_path(struct kernfs_node *kn) { unsigned long flags; int sz; spin_lock_irqsave(&kernfs_pr_cont_lock, flags); sz = kernfs_path_from_node(kn, NULL, kernfs_pr_cont_buf, sizeof(kernfs_pr_cont_buf)); if (sz < 0) { if (sz == -E2BIG) pr_cont("(name too long)"); else pr_cont("(error)"); goto out; } pr_cont("%s", kernfs_pr_cont_buf); out: spin_unlock_irqrestore(&kernfs_pr_cont_lock, flags); } /** * kernfs_get_parent - determine the parent node and pin it * @kn: kernfs_node of interest * * Determines @kn's parent, pins and returns it. This function can be * called from any context. * * Return: parent node of @kn */ struct kernfs_node *kernfs_get_parent(struct kernfs_node *kn) { struct kernfs_node *parent; struct kernfs_root *root; unsigned long flags; root = kernfs_root(kn); read_lock_irqsave(&root->kernfs_rename_lock, flags); parent = kernfs_parent(kn); kernfs_get(parent); read_unlock_irqrestore(&root->kernfs_rename_lock, flags); return parent; } /* * kernfs_ns_id - return the namespace id for a given namespace * @ns: namespace tag (may be NULL) * * Use the 64-bit namespace id instead of raw pointers for hashing * and comparison to avoid leaking kernel addresses to userspace. */ static u64 kernfs_ns_id(const struct ns_common *ns) { return ns ? ns->ns_id : 0; } /** * kernfs_name_hash - calculate hash of @ns + @name * @name: Null terminated string to hash * @ns: Namespace tag to hash * * Return: 31-bit hash of ns + name (so it fits in an off_t) */ static unsigned int kernfs_name_hash(const char *name, const struct ns_common *ns) { unsigned long hash = init_name_hash(kernfs_ns_id(ns)); unsigned int len = strlen(name); while (len--) hash = partial_name_hash(*name++, hash); hash = end_name_hash(hash); hash &= 0x7fffffffU; /* Reserve hash numbers 0, 1 and INT_MAX for magic directory entries */ if (hash < 2) hash += 2; if (hash >= INT_MAX) hash = INT_MAX - 1; return hash; } static int kernfs_name_compare(unsigned int hash, const char *name, const struct ns_common *ns, const struct kernfs_node *kn) { u64 ns_id = kernfs_ns_id(ns); u64 kn_ns_id = kernfs_ns_id(kn->ns); if (hash < kn->hash) return -1; if (hash > kn->hash) return 1; if (ns_id < kn_ns_id) return -1; if (ns_id > kn_ns_id) return 1; return strcmp(name, kernfs_rcu_name(kn)); } static int kernfs_sd_compare(const struct kernfs_node *left, const struct kernfs_node *right) { return kernfs_name_compare(left->hash, kernfs_rcu_name(left), left->ns, right); } /** * kernfs_link_sibling - link kernfs_node into sibling rbtree * @kn: kernfs_node of interest * * Link @kn into its sibling rbtree which starts from * @kn->parent->dir.children. * * Locking: * kernfs_rwsem held exclusive * * Return: * %0 on success, -EEXIST on failure. */ static int kernfs_link_sibling(struct kernfs_node *kn) { struct rb_node *parent = NULL; struct kernfs_node *kn_parent; struct rb_node **node; kn_parent = kernfs_parent(kn); node = &kn_parent->dir.children.rb_node; while (*node) { struct kernfs_node *pos; int result; pos = rb_to_kn(*node); parent = *node; result = kernfs_sd_compare(kn, pos); if (result < 0) node = &pos->rb.rb_left; else if (result > 0) node = &pos->rb.rb_right; else return -EEXIST; } /* add new node and rebalance the tree */ rb_link_node(&kn->rb, parent, node); rb_insert_color(&kn->rb, &kn_parent->dir.children); /* successfully added, account subdir number */ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) kn_parent->dir.subdirs++; kernfs_inc_rev(kn_parent); up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); return 0; } /** * kernfs_unlink_sibling - unlink kernfs_node from sibling rbtree * @kn: kernfs_node of interest * * Try to unlink @kn from its sibling rbtree which starts from * kn->parent->dir.children. * * Return: %true if @kn was actually removed, * %false if @kn wasn't on the rbtree. * * Locking: * kernfs_rwsem held exclusive */ static bool kernfs_unlink_sibling(struct kernfs_node *kn) { struct kernfs_node *kn_parent; if (RB_EMPTY_NODE(&kn->rb)) return false; kn_parent = kernfs_parent(kn); down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); if (kernfs_type(kn) == KERNFS_DIR) kn_parent->dir.subdirs--; kernfs_inc_rev(kn_parent); up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); rb_erase(&kn->rb, &kn_parent->dir.children); RB_CLEAR_NODE(&kn->rb); return true; } /** * kernfs_get_active - get an active reference to kernfs_node * @kn: kernfs_node to get an active reference to * * Get an active reference of @kn. This function is noop if @kn * is %NULL. * * Return: * Pointer to @kn on success, %NULL on failure. */ struct kernfs_node *kernfs_get_active(struct kernfs_node *kn) { if (unlikely(!kn)) return NULL; if (!atomic_inc_unless_negative(&kn->active)) return NULL; if (kernfs_lockdep(kn)) rwsem_acquire_read(&kn->dep_map, 0, 1, _RET_IP_); return kn; } /** * kernfs_put_active - put an active reference to kernfs_node * @kn: kernfs_node to put an active reference to * * Put an active reference to @kn. This function is noop if @kn * is %NULL. */ void kernfs_put_active(struct kernfs_node *kn) { int v; if (unlikely(!kn)) return; if (kernfs_lockdep(kn)) rwsem_release(&kn->dep_map, _RET_IP_); v = atomic_dec_return(&kn->active); if (likely(v != KN_DEACTIVATED_BIAS)) return; wake_up_all(&kernfs_root(kn)->deactivate_waitq); } /** * kernfs_drain - drain kernfs_node * @kn: kernfs_node to drain * @drop_supers: Set to true if this function is called with the * kernfs_supers_rwsem locked. * * Drain existing usages and nuke all existing mmaps of @kn. Multiple * removers may invoke this function concurrently on @kn and all will * return after draining is complete. */ static void kernfs_drain(struct kernfs_node *kn, bool drop_supers) __releases(&kernfs_root(kn)->kernfs_rwsem) __acquires(&kernfs_root(kn)->kernfs_rwsem) { struct kernfs_root *root = kernfs_root(kn); lockdep_assert_held_write(&root->kernfs_rwsem); WARN_ON_ONCE(kernfs_active(kn)); /* * Skip draining if already fully drained. This avoids draining and its * lockdep annotations for nodes which have never been activated * allowing embedding kernfs_remove() in create error paths without * worrying about draining. */ if (atomic_read(&kn->active) == KN_DEACTIVATED_BIAS && !kernfs_should_drain_open_files(kn)) return; up_write(&root->kernfs_rwsem); if (drop_supers) up_read(&root->kernfs_supers_rwsem); if (kernfs_lockdep(kn)) { rwsem_acquire(&kn->dep_map, 0, 0, _RET_IP_); if (atomic_read(&kn->active) != KN_DEACTIVATED_BIAS) lock_contended(&kn->dep_map, _RET_IP_); } wait_event(root->deactivate_waitq, atomic_read(&kn->active) == KN_DEACTIVATED_BIAS); if (kernfs_lockdep(kn)) { lock_acquired(&kn->dep_map, _RET_IP_); rwsem_release(&kn->dep_map, _RET_IP_); } if (kernfs_should_drain_open_files(kn)) kernfs_drain_open_files(kn); if (drop_supers) down_read(&root->kernfs_supers_rwsem); down_write(&root->kernfs_rwsem); } /** * kernfs_get - get a reference count on a kernfs_node * @kn: the target kernfs_node */ void kernfs_get(struct kernfs_node *kn) { if (kn) { WARN_ON(!atomic_read(&kn->count)); atomic_inc(&kn->count); } } EXPORT_SYMBOL_GPL(kernfs_get); static void kernfs_free_rcu(struct rcu_head *rcu) { struct kernfs_node *kn = container_of(rcu, struct kernfs_node, rcu); /* If the whole node goes away, then name can't be used outside */ kfree_const(rcu_access_pointer(kn->name)); if (kn->iattr) kmem_cache_free(kernfs_iattrs_cache, kn->iattr); kmem_cache_free(kernfs_node_cache, kn); } /** * kernfs_put - put a reference count on a kernfs_node * @kn: the target kernfs_node * * Put a reference count of @kn and destroy it if it reached zero. */ void kernfs_put(struct kernfs_node *kn) { struct kernfs_node *parent; struct kernfs_root *root; if (!kn || !atomic_dec_and_test(&kn->count)) return; root = kernfs_root(kn); repeat: /* * Moving/renaming is always done while holding reference. * kn->parent won't change beneath us. */ parent = kernfs_parent(kn); WARN_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS, "kernfs_put: %s/%s: released with incorrect active_ref %d\n", parent ? rcu_dereference(parent->name) : "", rcu_dereference(kn->name), atomic_read(&kn->active)); if (kernfs_type(kn) == KERNFS_LINK) kernfs_put(kn->symlink.target_kn); if (kn->iattr && kn->iattr->xattrs) { simple_xattrs_free(kn->iattr->xattrs, NULL); kfree(kn->iattr->xattrs); kn->iattr->xattrs = NULL; } spin_lock(&root->kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); spin_unlock(&root->kernfs_idr_lock); call_rcu(&kn->rcu, kernfs_free_rcu); kn = parent; if (kn) { if (atomic_dec_and_test(&kn->count)) goto repeat; } else { /* just released the root kn, free @root too */ idr_destroy(&root->ino_idr); kfree_rcu(root, rcu); } } EXPORT_SYMBOL_GPL(kernfs_put); /** * kernfs_node_from_dentry - determine kernfs_node associated with a dentry * @dentry: the dentry in question * * Return: the kernfs_node associated with @dentry. If @dentry is not a * kernfs one, %NULL is returned. * * While the returned kernfs_node will stay accessible as long as @dentry * is accessible, the returned node can be in any state and the caller is * fully responsible for determining what's accessible. */ struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry) { if (dentry->d_sb->s_op == &kernfs_sops) return kernfs_dentry_node(dentry); return NULL; } static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root, struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags) { struct kernfs_node *kn; u32 id_highbits; int ret; name = kstrdup_const(name, GFP_KERNEL); if (!name) return NULL; kn = kmem_cache_zalloc(kernfs_node_cache, GFP_KERNEL); if (!kn) goto err_out1; idr_preload(GFP_KERNEL); spin_lock(&root->kernfs_idr_lock); ret = idr_alloc_cyclic(&root->ino_idr, kn, 1, 0, GFP_ATOMIC); if (ret >= 0 && ret < root->last_id_lowbits) root->id_highbits++; id_highbits = root->id_highbits; root->last_id_lowbits = ret; spin_unlock(&root->kernfs_idr_lock); idr_preload_end(); if (ret < 0) goto err_out2; kn->id = (u64)id_highbits << 32 | ret; atomic_set(&kn->count, 1); atomic_set(&kn->active, KN_DEACTIVATED_BIAS); RB_CLEAR_NODE(&kn->rb); rcu_assign_pointer(kn->name, name); kn->mode = mode; kn->flags = flags; if (!uid_eq(uid, GLOBAL_ROOT_UID) || !gid_eq(gid, GLOBAL_ROOT_GID)) { struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID, .ia_uid = uid, .ia_gid = gid, }; ret = __kernfs_setattr(kn, &iattr); if (ret < 0) goto err_out3; } if (parent) { ret = security_kernfs_init_security(parent, kn); if (ret) goto err_out4; } return kn; err_out4: if (kn->iattr) { if (kn->iattr->xattrs) { simple_xattrs_free(kn->iattr->xattrs, NULL); kfree(kn->iattr->xattrs); } kmem_cache_free(kernfs_iattrs_cache, kn->iattr); } err_out3: spin_lock(&root->kernfs_idr_lock); idr_remove(&root->ino_idr, (u32)kernfs_ino(kn)); spin_unlock(&root->kernfs_idr_lock); err_out2: kmem_cache_free(kernfs_node_cache, kn); err_out1: kfree_const(name); return NULL; } struct kernfs_node *kernfs_new_node(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, unsigned flags) { struct kernfs_node *kn; if (parent->mode & S_ISGID) { /* this code block imitates inode_init_owner() for * kernfs */ if (parent->iattr) gid = parent->iattr->ia_gid; if (flags & KERNFS_DIR) mode |= S_ISGID; } kn = __kernfs_new_node(kernfs_root(parent), parent, name, mode, uid, gid, flags); if (kn) { kernfs_get(parent); rcu_assign_pointer(kn->__parent, parent); } return kn; } /* * kernfs_find_and_get_node_by_id - get kernfs_node from node id * @root: the kernfs root * @id: the target node id * * @id's lower 32bits encode ino and upper gen. If the gen portion is * zero, all generations are matched. * * Return: %NULL on failure, * otherwise a kernfs node with reference counter incremented. */ struct kernfs_node *kernfs_find_and_get_node_by_id(struct kernfs_root *root, u64 id) { struct kernfs_node *kn; ino_t ino = kernfs_id_ino(id); u32 gen = kernfs_id_gen(id); rcu_read_lock(); kn = idr_find(&root->ino_idr, (u32)ino); if (!kn) goto err_unlock; if (sizeof(ino_t) >= sizeof(u64)) { /* we looked up with the low 32bits, compare the whole */ if (kernfs_ino(kn) != ino) goto err_unlock; } else { /* 0 matches all generations */ if (unlikely(gen && kernfs_gen(kn) != gen)) goto err_unlock; } /* * We should fail if @kn has never been activated and guarantee success * if the caller knows that @kn is active. Both can be achieved by * __kernfs_active() which tests @kn->active without kernfs_rwsem. */ if (unlikely(!__kernfs_active(kn) || !atomic_inc_not_zero(&kn->count))) goto err_unlock; rcu_read_unlock(); return kn; err_unlock: rcu_read_unlock(); return NULL; } /** * kernfs_add_one - add kernfs_node to parent without warning * @kn: kernfs_node to be added * * The caller must already have initialized @kn->parent. This * function increments nlink of the parent's inode if @kn is a * directory and link into the children list of the parent. * * Return: * %0 on success, -EEXIST if entry with the given name already * exists. */ int kernfs_add_one(struct kernfs_node *kn) { struct kernfs_root *root = kernfs_root(kn); struct kernfs_iattrs *ps_iattr; struct kernfs_node *parent; bool has_ns; int ret; down_write(&root->kernfs_rwsem); parent = kernfs_parent(kn); ret = -EINVAL; has_ns = kernfs_ns_enabled(parent); if (WARN(has_ns != (bool)kn->ns, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", has_ns ? "required" : "invalid", kernfs_rcu_name(parent), kernfs_rcu_name(kn))) goto out_unlock; if (kernfs_type(parent) != KERNFS_DIR) goto out_unlock; ret = -ENOENT; if (parent->flags & (KERNFS_REMOVING | KERNFS_EMPTY_DIR)) goto out_unlock; kn->hash = kernfs_name_hash(kernfs_rcu_name(kn), kn->ns); ret = kernfs_link_sibling(kn); if (ret) goto out_unlock; /* Update timestamps on the parent */ down_write(&root->kernfs_iattr_rwsem); ps_iattr = parent->iattr; if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } up_write(&root->kernfs_iattr_rwsem); up_write(&root->kernfs_rwsem); /* * Activate the new node unless CREATE_DEACTIVATED is requested. * If not activated here, the kernfs user is responsible for * activating the node with kernfs_activate(). A node which hasn't * been activated is not visible to userland and its removal won't * trigger deactivation. */ if (!(kernfs_root(kn)->flags & KERNFS_ROOT_CREATE_DEACTIVATED)) kernfs_activate(kn); return 0; out_unlock: up_write(&root->kernfs_rwsem); return ret; } /** * kernfs_find_ns - find kernfs_node with the given name * @parent: kernfs_node to search under * @name: name to look for * @ns: the namespace tag to use * * Look for kernfs_node with name @name under @parent. * * Return: pointer to the found kernfs_node on success, %NULL on failure. */ static struct kernfs_node *kernfs_find_ns(struct kernfs_node *parent, const unsigned char *name, const struct ns_common *ns) { struct rb_node *node = parent->dir.children.rb_node; bool has_ns = kernfs_ns_enabled(parent); unsigned int hash; lockdep_assert_held(&kernfs_root(parent)->kernfs_rwsem); if (has_ns != (bool)ns) { WARN(1, KERN_WARNING "kernfs: ns %s in '%s' for '%s'\n", has_ns ? "required" : "invalid", kernfs_rcu_name(parent), name); return NULL; } hash = kernfs_name_hash(name, ns); while (node) { struct kernfs_node *kn; int result; kn = rb_to_kn(node); result = kernfs_name_compare(hash, name, ns, kn); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return kn; } return NULL; } static struct kernfs_node *kernfs_walk_ns(struct kernfs_node *parent, const unsigned char *path, const struct ns_common *ns) { ssize_t len; char *p, *name; lockdep_assert_held_read(&kernfs_root(parent)->kernfs_rwsem); spin_lock_irq(&kernfs_pr_cont_lock); len = strscpy(kernfs_pr_cont_buf, path, sizeof(kernfs_pr_cont_buf)); if (len < 0) { spin_unlock_irq(&kernfs_pr_cont_lock); return NULL; } p = kernfs_pr_cont_buf; while ((name = strsep(&p, "/")) && parent) { if (*name == '\0') continue; parent = kernfs_find_ns(parent, name, ns); } spin_unlock_irq(&kernfs_pr_cont_lock); return parent; } /** * kernfs_find_and_get_ns - find and get kernfs_node with the given name * @parent: kernfs_node to search under * @name: name to look for * @ns: the namespace tag to use * * Look for kernfs_node with name @name under @parent and get a reference * if found. This function may sleep. * * Return: pointer to the found kernfs_node on success, %NULL on failure. */ struct kernfs_node *kernfs_find_and_get_ns(struct kernfs_node *parent, const char *name, const struct ns_common *ns) { struct kernfs_node *kn; struct kernfs_root *root = kernfs_root(parent); down_read(&root->kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); kernfs_get(kn); up_read(&root->kernfs_rwsem); return kn; } EXPORT_SYMBOL_GPL(kernfs_find_and_get_ns); /** * kernfs_walk_and_get_ns - find and get kernfs_node with the given path * @parent: kernfs_node to search under * @path: path to look for * @ns: the namespace tag to use * * Look for kernfs_node with path @path under @parent and get a reference * if found. This function may sleep. * * Return: pointer to the found kernfs_node on success, %NULL on failure. */ struct kernfs_node *kernfs_walk_and_get_ns(struct kernfs_node *parent, const char *path, const struct ns_common *ns) { struct kernfs_node *kn; struct kernfs_root *root = kernfs_root(parent); down_read(&root->kernfs_rwsem); kn = kernfs_walk_ns(parent, path, ns); kernfs_get(kn); up_read(&root->kernfs_rwsem); return kn; } unsigned int kernfs_root_flags(struct kernfs_node *kn) { return kernfs_root(kn)->flags; } /** * kernfs_create_root - create a new kernfs hierarchy * @scops: optional syscall operations for the hierarchy * @flags: KERNFS_ROOT_* flags * @priv: opaque data associated with the new directory * * Return: the root of the new hierarchy on success, ERR_PTR() value on * failure. */ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags, void *priv) { struct kernfs_root *root; struct kernfs_node *kn; root = kzalloc_obj(*root); if (!root) return ERR_PTR(-ENOMEM); idr_init(&root->ino_idr); spin_lock_init(&root->kernfs_idr_lock); init_rwsem(&root->kernfs_rwsem); init_rwsem(&root->kernfs_iattr_rwsem); init_rwsem(&root->kernfs_supers_rwsem); INIT_LIST_HEAD(&root->supers); rwlock_init(&root->kernfs_rename_lock); /* * On 64bit ino setups, id is ino. On 32bit, low 32bits are ino. * High bits generation. The starting value for both ino and * genenration is 1. Initialize upper 32bit allocation * accordingly. */ if (sizeof(ino_t) >= sizeof(u64)) root->id_highbits = 0; else root->id_highbits = 1; kn = __kernfs_new_node(root, NULL, "", S_IFDIR | S_IRUGO | S_IXUGO, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) { idr_destroy(&root->ino_idr); kfree(root); return ERR_PTR(-ENOMEM); } kn->priv = priv; kn->dir.root = root; root->syscall_ops = scops; root->flags = flags; root->kn = kn; init_waitqueue_head(&root->deactivate_waitq); if (!(root->flags & KERNFS_ROOT_CREATE_DEACTIVATED)) kernfs_activate(kn); return root; } /** * kernfs_destroy_root - destroy a kernfs hierarchy * @root: root of the hierarchy to destroy * * Destroy the hierarchy anchored at @root by removing all existing * directories and destroying @root. */ void kernfs_destroy_root(struct kernfs_root *root) { /* * kernfs_remove holds kernfs_rwsem from the root so the root * shouldn't be freed during the operation. */ kernfs_get(root->kn); kernfs_remove(root->kn); kernfs_put(root->kn); /* will also free @root */ } /** * kernfs_root_to_node - return the kernfs_node associated with a kernfs_root * @root: root to use to lookup * * Return: @root's kernfs_node */ struct kernfs_node *kernfs_root_to_node(struct kernfs_root *root) { return root->kn; } /** * kernfs_create_dir_ns - create a directory * @parent: parent in which to create a new directory * @name: name of the new directory * @mode: mode of the new directory * @uid: uid of the new directory * @gid: gid of the new directory * @priv: opaque data associated with the new directory * @ns: optional namespace tag of the directory * * Return: the created node on success, ERR_PTR() value on failure. */ struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, void *priv, const struct ns_common *ns) { struct kernfs_node *kn; int rc; /* allocate */ kn = kernfs_new_node(parent, name, mode | S_IFDIR, uid, gid, KERNFS_DIR); if (!kn) return ERR_PTR(-ENOMEM); kn->dir.root = parent->dir.root; kn->ns = ns; kn->priv = priv; /* link in */ rc = kernfs_add_one(kn); if (!rc) return kn; kernfs_put(kn); return ERR_PTR(rc); } /** * kernfs_create_empty_dir - create an always empty directory * @parent: parent in which to create a new directory * @name: name of the new directory * * Return: the created node on success, ERR_PTR() value on failure. */ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent, const char *name) { struct kernfs_node *kn; int rc; /* allocate */ kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR); if (!kn) return ERR_PTR(-ENOMEM); kn->flags |= KERNFS_EMPTY_DIR; kn->dir.root = parent->dir.root; kn->ns = NULL; kn->priv = NULL; /* link in */ rc = kernfs_add_one(kn); if (!rc) return kn; kernfs_put(kn); return ERR_PTR(rc); } static int kernfs_dop_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { struct kernfs_node *kn, *parent; struct kernfs_root *root; if (flags & LOOKUP_RCU) return -ECHILD; /* Negative hashed dentry? */ if (d_really_is_negative(dentry)) { /* If the kernfs parent node has changed discard and * proceed to ->lookup. * * There's nothing special needed here when getting the * dentry parent, even if a concurrent rename is in * progress. That's because the dentry is negative so * it can only be the target of the rename and it will * be doing a d_move() not a replace. Consequently the * dentry d_parent won't change over the d_move(). * * Also kernfs negative dentries transitioning from * negative to positive during revalidate won't happen * because they are invalidated on containing directory * changes and the lookup re-done so that a new positive * dentry can be properly created. */ root = kernfs_root_from_sb(dentry->d_sb); down_read(&root->kernfs_rwsem); parent = kernfs_dentry_node(dentry->d_parent); if (parent) { if (kernfs_dir_changed(parent, dentry)) { up_read(&root->kernfs_rwsem); return 0; } } up_read(&root->kernfs_rwsem); /* The kernfs parent node hasn't changed, leave the * dentry negative and return success. */ return 1; } kn = kernfs_dentry_node(dentry); root = kernfs_root(kn); down_read(&root->kernfs_rwsem); /* The kernfs node has been deactivated */ if (!kernfs_active(kn)) goto out_bad; parent = kernfs_parent(kn); /* The kernfs node has been moved? */ if (kernfs_dentry_node(dentry->d_parent) != parent) goto out_bad; /* The kernfs node has been renamed */ if (strcmp(dentry->d_name.name, kernfs_rcu_name(kn)) != 0) goto out_bad; /* The kernfs node has been moved to a different namespace */ if (parent && kernfs_ns_enabled(parent) && kernfs_ns_id(kernfs_info(dentry->d_sb)->ns) != kernfs_ns_id(kn->ns)) goto out_bad; up_read(&root->kernfs_rwsem); return 1; out_bad: up_read(&root->kernfs_rwsem); return 0; } const struct dentry_operations kernfs_dops = { .d_revalidate = kernfs_dop_revalidate, }; static struct dentry *kernfs_iop_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct kernfs_node *parent = dir->i_private; struct kernfs_node *kn; struct kernfs_root *root; struct inode *inode = NULL; const struct ns_common *ns = NULL; root = kernfs_root(parent); down_read(&root->kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dir->i_sb)->ns; kn = kernfs_find_ns(parent, dentry->d_name.name, ns); /* attach dentry and inode */ if (kn) { /* Inactive nodes are invisible to the VFS so don't * create a negative. */ if (!kernfs_active(kn)) { up_read(&root->kernfs_rwsem); return NULL; } inode = kernfs_get_inode(dir->i_sb, kn); if (!inode) inode = ERR_PTR(-ENOMEM); } /* * Needed for negative dentry validation. * The negative dentry can be created in kernfs_iop_lookup() * or transforms from positive dentry in dentry_unlink_inode() * called from vfs_rmdir(). */ if (!IS_ERR(inode)) kernfs_set_rev(parent, dentry); up_read(&root->kernfs_rwsem); /* instantiate and hash (possibly negative) dentry */ return d_splice_alias(inode, dentry); } static struct dentry *kernfs_iop_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct kernfs_node *parent = dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(parent)->syscall_ops; int ret; if (!scops || !scops->mkdir) return ERR_PTR(-EPERM); if (!kernfs_get_active(parent)) return ERR_PTR(-ENODEV); ret = scops->mkdir(parent, dentry->d_name.name, mode); kernfs_put_active(parent); return ERR_PTR(ret); } static int kernfs_iop_rmdir(struct inode *dir, struct dentry *dentry) { struct kernfs_node *kn = kernfs_dentry_node(dentry); struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; int ret; if (!scops || !scops->rmdir) return -EPERM; if (!kernfs_get_active(kn)) return -ENODEV; ret = scops->rmdir(kn); kernfs_put_active(kn); return ret; } static int kernfs_iop_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct kernfs_node *kn = kernfs_dentry_node(old_dentry); struct kernfs_node *new_parent = new_dir->i_private; struct kernfs_syscall_ops *scops = kernfs_root(kn)->syscall_ops; int ret; if (flags) return -EINVAL; if (!scops || !scops->rename) return -EPERM; if (!kernfs_get_active(kn)) return -ENODEV; if (!kernfs_get_active(new_parent)) { kernfs_put_active(kn); return -ENODEV; } ret = scops->rename(kn, new_parent, new_dentry->d_name.name); kernfs_put_active(new_parent); kernfs_put_active(kn); return ret; } const struct inode_operations kernfs_dir_iops = { .lookup = kernfs_iop_lookup, .permission = kernfs_iop_permission, .setattr = kernfs_iop_setattr, .getattr = kernfs_iop_getattr, .listxattr = kernfs_iop_listxattr, .mkdir = kernfs_iop_mkdir, .rmdir = kernfs_iop_rmdir, .rename = kernfs_iop_rename, }; static struct kernfs_node *kernfs_leftmost_descendant(struct kernfs_node *pos) { struct kernfs_node *last; while (true) { struct rb_node *rbn; last = pos; if (kernfs_type(pos) != KERNFS_DIR) break; rbn = rb_first(&pos->dir.children); if (!rbn) break; pos = rb_to_kn(rbn); } return last; } /** * kernfs_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: kernfs_node whose descendants to walk * * Find the next descendant to visit for post-order traversal of @root's * descendants. @root is included in the iteration and the last node to be * visited. * * Return: the next descendant to visit or %NULL when done. */ static struct kernfs_node *kernfs_next_descendant_post(struct kernfs_node *pos, struct kernfs_node *root) { struct rb_node *rbn; lockdep_assert_held_write(&kernfs_root(root)->kernfs_rwsem); /* if first iteration, visit leftmost descendant which may be root */ if (!pos) return kernfs_leftmost_descendant(root); /* if we visited @root, we're done */ if (pos == root) return NULL; /* if there's an unvisited sibling, visit its leftmost descendant */ rbn = rb_next(&pos->rb); if (rbn) return kernfs_leftmost_descendant(rb_to_kn(rbn)); /* no sibling left, visit parent */ return kernfs_parent(pos); } static void kernfs_activate_one(struct kernfs_node *kn) { lockdep_assert_held_write(&kernfs_root(kn)->kernfs_rwsem); kn->flags |= KERNFS_ACTIVATED; if (kernfs_active(kn) || (kn->flags & (KERNFS_HIDDEN | KERNFS_REMOVING))) return; WARN_ON_ONCE(rcu_access_pointer(kn->__parent) && RB_EMPTY_NODE(&kn->rb)); WARN_ON_ONCE(atomic_read(&kn->active) != KN_DEACTIVATED_BIAS); atomic_sub(KN_DEACTIVATED_BIAS, &kn->active); } /** * kernfs_activate - activate a node which started deactivated * @kn: kernfs_node whose subtree is to be activated * * If the root has KERNFS_ROOT_CREATE_DEACTIVATED set, a newly created node * needs to be explicitly activated. A node which hasn't been activated * isn't visible to userland and deactivation is skipped during its * removal. This is useful to construct atomic init sequences where * creation of multiple nodes should either succeed or fail atomically. * * The caller is responsible for ensuring that this function is not called * after kernfs_remove*() is invoked on @kn. */ void kernfs_activate(struct kernfs_node *kn) { struct kernfs_node *pos; struct kernfs_root *root = kernfs_root(kn); down_write(&root->kernfs_rwsem); pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) kernfs_activate_one(pos); up_write(&root->kernfs_rwsem); } /** * kernfs_show - show or hide a node * @kn: kernfs_node to show or hide * @show: whether to show or hide * * If @show is %false, @kn is marked hidden and deactivated. A hidden node is * ignored in future activaitons. If %true, the mark is removed and activation * state is restored. This function won't implicitly activate a new node in a * %KERNFS_ROOT_CREATE_DEACTIVATED root which hasn't been activated yet. * * To avoid recursion complexities, directories aren't supported for now. */ void kernfs_show(struct kernfs_node *kn, bool show) { struct kernfs_root *root = kernfs_root(kn); if (WARN_ON_ONCE(kernfs_type(kn) == KERNFS_DIR)) return; down_write(&root->kernfs_rwsem); if (show) { kn->flags &= ~KERNFS_HIDDEN; if (kn->flags & KERNFS_ACTIVATED) kernfs_activate_one(kn); } else { kn->flags |= KERNFS_HIDDEN; if (kernfs_active(kn)) atomic_add(KN_DEACTIVATED_BIAS, &kn->active); kernfs_drain(kn, false); } up_write(&root->kernfs_rwsem); } /* * This function enables VFS to send fsnotify events for deletions. * There is gap in this implementation for certain file removals due their * unique nature in kernfs. Directory removals that trigger file removals occur * through vfs_rmdir, which shrinks the dcache and emits fsnotify events after * the rmdir operation; there is no issue here. However kernfs writes to * particular files (e.g. cgroup.subtree_control) can also cause file removal, * but vfs_write does not attempt to emit fsnotify events after the write * operation, even if i_nlink counts are 0. As a usecase for monitoring this * category of file removals is not known, they are left without having * IN_DELETE or IN_DELETE_SELF events generated. * Fanotify recursive monitoring also does not work for kernfs nodes that do not * have inodes attached, as they are created on-demand in kernfs. */ static void kernfs_clear_inode_nlink(struct kernfs_node *kn) { struct kernfs_root *root = kernfs_root(kn); struct kernfs_super_info *info; lockdep_assert_held_read(&root->kernfs_supers_rwsem); list_for_each_entry(info, &root->supers, node) { struct inode *inode = ilookup(info->sb, kernfs_ino(kn)); if (inode) { clear_nlink(inode); iput(inode); } } } static void __kernfs_remove(struct kernfs_node *kn) { struct kernfs_node *pos, *parent; /* Short-circuit if non-root @kn has already finished removal. */ if (!kn) return; lockdep_assert_held_read(&kernfs_root(kn)->kernfs_supers_rwsem); lockdep_assert_held_write(&kernfs_root(kn)->kernfs_rwsem); /* * This is for kernfs_remove_self() which plays with active ref * after removal. */ if (kernfs_parent(kn) && RB_EMPTY_NODE(&kn->rb)) return; pr_debug("kernfs %s: removing\n", kernfs_rcu_name(kn)); /* prevent new usage by marking all nodes removing and deactivating */ down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); pos = NULL; while ((pos = kernfs_next_descendant_post(pos, kn))) { pos->flags |= KERNFS_REMOVING; if (kernfs_active(pos)) atomic_add(KN_DEACTIVATED_BIAS, &pos->active); } up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); /* deactivate and unlink the subtree node-by-node */ do { pos = kernfs_leftmost_descendant(kn); /* * kernfs_drain() may drop kernfs_rwsem temporarily and @pos's * base ref could have been put by someone else by the time * the function returns. Make sure it doesn't go away * underneath us. */ kernfs_get(pos); kernfs_drain(pos, true); parent = kernfs_parent(pos); /* * kernfs_unlink_sibling() succeeds once per node. Use it * to decide who's responsible for cleanups. */ if (!parent || kernfs_unlink_sibling(pos)) { struct kernfs_iattrs *ps_iattr = parent ? parent->iattr : NULL; down_write(&kernfs_root(kn)->kernfs_iattr_rwsem); kernfs_clear_inode_nlink(pos); /* update timestamps on the parent */ if (ps_iattr) { ktime_get_real_ts64(&ps_iattr->ia_ctime); ps_iattr->ia_mtime = ps_iattr->ia_ctime; } up_write(&kernfs_root(kn)->kernfs_iattr_rwsem); kernfs_put(pos); } kernfs_put(pos); } while (pos != kn); } /** * kernfs_remove - remove a kernfs_node recursively * @kn: the kernfs_node to remove * * Remove @kn along with all its subdirectories and files. */ void kernfs_remove(struct kernfs_node *kn) { struct kernfs_root *root; if (!kn) return; root = kernfs_root(kn); down_read(&root->kernfs_supers_rwsem); down_write(&root->kernfs_rwsem); __kernfs_remove(kn); up_write(&root->kernfs_rwsem); up_read(&root->kernfs_supers_rwsem); } /** * kernfs_break_active_protection - break out of active protection * @kn: the self kernfs_node * * The caller must be running off of a kernfs operation which is invoked * with an active reference - e.g. one of kernfs_ops. Each invocation of * this function must also be matched with an invocation of * kernfs_unbreak_active_protection(). * * This function releases the active reference of @kn the caller is * holding. Once this function is called, @kn may be removed at any point * and the caller is solely responsible for ensuring that the objects it * dereferences are accessible. */ void kernfs_break_active_protection(struct kernfs_node *kn) { /* * Take out ourself out of the active ref dependency chain. If * we're called without an active ref, lockdep will complain. */ kernfs_put_active(kn); } /** * kernfs_unbreak_active_protection - undo kernfs_break_active_protection() * @kn: the self kernfs_node * * If kernfs_break_active_protection() was called, this function must be * invoked before finishing the kernfs operation. Note that while this * function restores the active reference, it doesn't and can't actually * restore the active protection - @kn may already or be in the process of * being drained and removed. Once kernfs_break_active_protection() is * invoked, that protection is irreversibly gone for the kernfs operation * instance. * * While this function may be called at any point after * kernfs_break_active_protection() is invoked, its most useful location * would be right before the enclosing kernfs operation returns. */ void kernfs_unbreak_active_protection(struct kernfs_node *kn) { /* * @kn->active could be in any state; however, the increment we do * here will be undone as soon as the enclosing kernfs operation * finishes and this temporary bump can't break anything. If @kn * is alive, nothing changes. If @kn is being deactivated, the * soon-to-follow put will either finish deactivation or restore * deactivated state. If @kn is already removed, the temporary * bump is guaranteed to be gone before @kn is released. */ atomic_inc(&kn->active); if (kernfs_lockdep(kn)) rwsem_acquire(&kn->dep_map, 0, 1, _RET_IP_); } /** * kernfs_remove_self - remove a kernfs_node from its own method * @kn: the self kernfs_node to remove * * The caller must be running off of a kernfs operation which is invoked * with an active reference - e.g. one of kernfs_ops. This can be used to * implement a file operation which deletes itself. * * For example, the "delete" file for a sysfs device directory can be * implemented by invoking kernfs_remove_self() on the "delete" file * itself. This function breaks the circular dependency of trying to * deactivate self while holding an active ref itself. It isn't necessary * to modify the usual removal path to use kernfs_remove_self(). The * "delete" implementation can simply invoke kernfs_remove_self() on self * before proceeding with the usual removal path. kernfs will ignore later * kernfs_remove() on self. * * kernfs_remove_self() can be called multiple times concurrently on the * same kernfs_node. Only the first one actually performs removal and * returns %true. All others will wait until the kernfs operation which * won self-removal finishes and return %false. Note that the losers wait * for the completion of not only the winning kernfs_remove_self() but also * the whole kernfs_ops which won the arbitration. This can be used to * guarantee, for example, all concurrent writes to a "delete" file to * finish only after the whole operation is complete. * * Return: %true if @kn is removed by this call, otherwise %false. */ bool kernfs_remove_self(struct kernfs_node *kn) { bool ret; struct kernfs_root *root = kernfs_root(kn); down_read(&root->kernfs_supers_rwsem); down_write(&root->kernfs_rwsem); kernfs_break_active_protection(kn); /* * SUICIDAL is used to arbitrate among competing invocations. Only * the first one will actually perform removal. When the removal * is complete, SUICIDED is set and the active ref is restored * while kernfs_rwsem for held exclusive. The ones which lost * arbitration waits for SUICIDED && drained which can happen only * after the enclosing kernfs operation which executed the winning * instance of kernfs_remove_self() finished. */ if (!(kn->flags & KERNFS_SUICIDAL)) { kn->flags |= KERNFS_SUICIDAL; __kernfs_remove(kn); kn->flags |= KERNFS_SUICIDED; ret = true; } else { wait_queue_head_t *waitq = &kernfs_root(kn)->deactivate_waitq; DEFINE_WAIT(wait); while (true) { prepare_to_wait(waitq, &wait, TASK_UNINTERRUPTIBLE); if ((kn->flags & KERNFS_SUICIDED) && atomic_read(&kn->active) == KN_DEACTIVATED_BIAS) break; up_write(&root->kernfs_rwsem); up_read(&root->kernfs_supers_rwsem); schedule(); down_read(&root->kernfs_supers_rwsem); down_write(&root->kernfs_rwsem); } finish_wait(waitq, &wait); WARN_ON_ONCE(!RB_EMPTY_NODE(&kn->rb)); ret = false; } /* * This must be done while kernfs_rwsem held exclusive; otherwise, * waiting for SUICIDED && deactivated could finish prematurely. */ kernfs_unbreak_active_protection(kn); up_write(&root->kernfs_rwsem); up_read(&root->kernfs_supers_rwsem); return ret; } /** * kernfs_remove_by_name_ns - find a kernfs_node by name and remove it * @parent: parent of the target * @name: name of the kernfs_node to remove * @ns: namespace tag of the kernfs_node to remove * * Look for the kernfs_node with @name and @ns under @parent and remove it. * * Return: %0 on success, -ENOENT if such entry doesn't exist. */ int kernfs_remove_by_name_ns(struct kernfs_node *parent, const char *name, const struct ns_common *ns) { struct kernfs_node *kn; struct kernfs_root *root; if (!parent) { WARN(1, KERN_WARNING "kernfs: can not remove '%s', no directory\n", name); return -ENOENT; } root = kernfs_root(parent); down_read(&root->kernfs_supers_rwsem); down_write(&root->kernfs_rwsem); kn = kernfs_find_ns(parent, name, ns); if (kn) { kernfs_get(kn); __kernfs_remove(kn); kernfs_put(kn); } up_write(&root->kernfs_rwsem); up_read(&root->kernfs_supers_rwsem); if (kn) return 0; else return -ENOENT; } /** * kernfs_rename_ns - move and rename a kernfs_node * @kn: target node * @new_parent: new parent to put @sd under * @new_name: new name * @new_ns: new namespace tag * * Return: %0 on success, -errno on failure. */ int kernfs_rename_ns(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name, const struct ns_common *new_ns) { struct kernfs_node *old_parent; struct kernfs_root *root; const char *old_name; int error; /* can't move or rename root */ if (!rcu_access_pointer(kn->__parent)) return -EINVAL; root = kernfs_root(kn); down_write(&root->kernfs_rwsem); error = -ENOENT; if (!kernfs_active(kn) || !kernfs_active(new_parent) || (new_parent->flags & KERNFS_EMPTY_DIR)) goto out; old_parent = kernfs_parent(kn); if (root->flags & KERNFS_ROOT_INVARIANT_PARENT) { error = -EINVAL; if (WARN_ON_ONCE(old_parent != new_parent)) goto out; } error = 0; old_name = kernfs_rcu_name(kn); if (!new_name) new_name = old_name; if ((old_parent == new_parent) && (kernfs_ns_id(kn->ns) == kernfs_ns_id(new_ns)) && (strcmp(old_name, new_name) == 0)) goto out; /* nothing to rename */ error = -EEXIST; if (kernfs_find_ns(new_parent, new_name, new_ns)) goto out; /* rename kernfs_node */ if (strcmp(old_name, new_name) != 0) { error = -ENOMEM; new_name = kstrdup_const(new_name, GFP_KERNEL); if (!new_name) goto out; } else { new_name = NULL; } /* * Move to the appropriate place in the appropriate directories rbtree. */ kernfs_unlink_sibling(kn); /* rename_lock protects ->parent accessors */ if (old_parent != new_parent) { kernfs_get(new_parent); write_lock_irq(&root->kernfs_rename_lock); rcu_assign_pointer(kn->__parent, new_parent); kn->ns = new_ns; if (new_name) rcu_assign_pointer(kn->name, new_name); write_unlock_irq(&root->kernfs_rename_lock); kernfs_put(old_parent); } else { /* name assignment is RCU protected, parent is the same */ kn->ns = new_ns; if (new_name) rcu_assign_pointer(kn->name, new_name); } kn->hash = kernfs_name_hash(new_name ?: old_name, kn->ns); kernfs_link_sibling(kn); if (new_name && !is_kernel_rodata((unsigned long)old_name)) kfree_rcu_mightsleep(old_name); error = 0; out: up_write(&root->kernfs_rwsem); return error; } static int kernfs_dir_fop_release(struct inode *inode, struct file *filp) { kernfs_put(filp->private_data); return 0; } static struct kernfs_node *kernfs_dir_pos(const struct ns_common *ns, struct kernfs_node *parent, loff_t hash, struct kernfs_node *pos) { if (pos) { int valid = kernfs_active(pos) && rcu_access_pointer(pos->__parent) == parent && hash == pos->hash; kernfs_put(pos); if (!valid) pos = NULL; } if (!pos && (hash > 1) && (hash < INT_MAX)) { struct rb_node *node = parent->dir.children.rb_node; u64 ns_id = kernfs_ns_id(ns); while (node) { pos = rb_to_kn(node); if (hash < pos->hash) node = node->rb_left; else if (hash > pos->hash) node = node->rb_right; else if (ns_id < kernfs_ns_id(pos->ns)) node = node->rb_left; else if (ns_id > kernfs_ns_id(pos->ns)) node = node->rb_right; else break; } } /* Skip over entries which are dying/dead or in the wrong namespace */ while (pos && (!kernfs_active(pos) || kernfs_ns_id(pos->ns) != kernfs_ns_id(ns))) { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; else pos = rb_to_kn(node); } return pos; } static struct kernfs_node *kernfs_dir_next_pos(const struct ns_common *ns, struct kernfs_node *parent, ino_t ino, struct kernfs_node *pos) { pos = kernfs_dir_pos(ns, parent, ino, pos); if (pos) { do { struct rb_node *node = rb_next(&pos->rb); if (!node) pos = NULL; else pos = rb_to_kn(node); } while (pos && (!kernfs_active(pos) || kernfs_ns_id(pos->ns) != kernfs_ns_id(ns))); } return pos; } static int kernfs_fop_readdir(struct file *file, struct dir_context *ctx) { struct dentry *dentry = file->f_path.dentry; struct kernfs_node *parent = kernfs_dentry_node(dentry); struct kernfs_node *pos = file->private_data; struct kernfs_root *root; const struct ns_common *ns = NULL; if (!dir_emit_dots(file, ctx)) return 0; root = kernfs_root(parent); down_read(&root->kernfs_rwsem); if (kernfs_ns_enabled(parent)) ns = kernfs_info(dentry->d_sb)->ns; for (pos = kernfs_dir_pos(ns, parent, ctx->pos, pos); pos; pos = kernfs_dir_next_pos(ns, parent, ctx->pos, pos)) { const char *name = kernfs_rcu_name(pos); unsigned int type = fs_umode_to_dtype(pos->mode); int len = strlen(name); ino_t ino = kernfs_ino(pos); ctx->pos = pos->hash; file->private_data = pos; kernfs_get(pos); if (!dir_emit(ctx, name, len, ino, type)) { up_read(&root->kernfs_rwsem); return 0; } } up_read(&root->kernfs_rwsem); file->private_data = NULL; ctx->pos = INT_MAX; return 0; } const struct file_operations kernfs_dir_fops = { .read = generic_read_dir, .iterate_shared = kernfs_fop_readdir, .release = kernfs_dir_fop_release, .llseek = generic_file_llseek, }; |
| 297 319 10 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 | /* * net/tipc/core.h: Include file for TIPC global declarations * * Copyright (c) 2005-2006, 2013-2018 Ericsson AB * Copyright (c) 2005-2007, 2010-2013, Wind River Systems * Copyright (c) 2020, Red Hat Inc * 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. */ #ifndef _TIPC_CORE_H #define _TIPC_CORE_H #include <linux/tipc.h> #include <linux/tipc_config.h> #include <linux/tipc_netlink.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/hex.h> #include <linux/mm.h> #include <linux/timer.h> #include <linux/string.h> #include <linux/uaccess.h> #include <linux/interrupt.h> #include <linux/atomic.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/rtnetlink.h> #include <linux/etherdevice.h> #include <net/netns/generic.h> #include <linux/rhashtable.h> #include <net/genetlink.h> #include <net/netns/hash.h> #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt struct tipc_node; struct tipc_bearer; struct tipc_bc_base; struct tipc_link; struct tipc_topsrv; struct tipc_monitor; #ifdef CONFIG_TIPC_CRYPTO struct tipc_crypto; #endif #define TIPC_MOD_VER "2.0.0" #define NODE_HTABLE_SIZE 512 #define MAX_BEARERS 3 #define TIPC_DEF_MON_THRESHOLD 32 #define NODE_ID_LEN 16 #define NODE_ID_STR_LEN (NODE_ID_LEN * 2 + 1) extern unsigned int tipc_net_id __read_mostly; extern int sysctl_tipc_rmem[3] __read_mostly; extern int sysctl_tipc_named_timeout __read_mostly; struct tipc_net { u8 node_id[NODE_ID_LEN]; u32 node_addr; u32 trial_addr; unsigned long addr_trial_end; char node_id_string[NODE_ID_STR_LEN]; int net_id; int random; bool legacy_addr_format; /* Node table and node list */ spinlock_t node_list_lock; struct hlist_head node_htable[NODE_HTABLE_SIZE]; struct list_head node_list; u32 num_nodes; u32 num_links; /* Neighbor monitoring list */ struct tipc_monitor *monitors[MAX_BEARERS]; int mon_threshold; /* Bearer list */ struct tipc_bearer __rcu *bearer_list[MAX_BEARERS + 1]; /* Broadcast link */ spinlock_t bclock; struct tipc_bc_base *bcbase; struct tipc_link *bcl; /* Socket hash table */ struct rhashtable sk_rht; /* Name table */ spinlock_t nametbl_lock; struct name_table *nametbl; /* Topology subscription server */ struct tipc_topsrv *topsrv; atomic_t subscription_count; /* Cluster capabilities */ u16 capabilities; /* Tracing of node internal messages */ struct packet_type loopback_pt; #ifdef CONFIG_TIPC_CRYPTO /* TX crypto handler */ struct tipc_crypto *crypto_tx; #endif /* Work item for net finalize */ struct work_struct work; /* The numbers of work queues in schedule */ atomic_t wq_count; }; static inline struct tipc_net *tipc_net(struct net *net) { return net_generic(net, tipc_net_id); } static inline int tipc_netid(struct net *net) { return tipc_net(net)->net_id; } static inline struct list_head *tipc_nodes(struct net *net) { return &tipc_net(net)->node_list; } static inline struct name_table *tipc_name_table(struct net *net) { return tipc_net(net)->nametbl; } static inline struct tipc_topsrv *tipc_topsrv(struct net *net) { return tipc_net(net)->topsrv; } static inline unsigned int tipc_hashfn(u32 addr) { return addr & (NODE_HTABLE_SIZE - 1); } static inline u16 mod(u16 x) { return x & 0xffffu; } static inline int less_eq(u16 left, u16 right) { return mod(right - left) < 32768u; } static inline int more(u16 left, u16 right) { return !less_eq(left, right); } static inline int less(u16 left, u16 right) { return less_eq(left, right) && (mod(right) != mod(left)); } static inline int tipc_in_range(u16 val, u16 min, u16 max) { return !less(val, min) && !more(val, max); } static inline u32 tipc_net_hash_mixes(struct net *net, int tn_rand) { return net_hash_mix(&init_net) ^ net_hash_mix(net) ^ tn_rand; } static inline u32 hash128to32(char *bytes) { __be32 *tmp = (__be32 *)bytes; u32 res; res = ntohl(tmp[0] ^ tmp[1] ^ tmp[2] ^ tmp[3]); if (likely(res)) return res; return ntohl(tmp[0] | tmp[1] | tmp[2] | tmp[3]); } #ifdef CONFIG_SYSCTL int tipc_register_sysctl(void); void tipc_unregister_sysctl(void); #else #define tipc_register_sysctl() 0 #define tipc_unregister_sysctl() #endif #endif |
| 1314 1312 1092 1159 178 16 31 207 20 559 630 632 44 549 369 173 270 9 11 430 587 586 587 672 587 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NET_NEIGHBOUR_H #define _NET_NEIGHBOUR_H #include <linux/neighbour.h> /* * Generic neighbour manipulation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * * Changes: * * Harald Welte: <laforge@gnumonks.org> * - Add neighbour cache statistics like rtstat */ #include <linux/atomic.h> #include <linux/refcount.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rcupdate.h> #include <linux/seq_file.h> #include <linux/bitmap.h> #include <linux/err.h> #include <linux/sysctl.h> #include <linux/workqueue.h> #include <net/rtnetlink.h> #include <net/neighbour_tables.h> /* * NUD stands for "neighbor unreachability detection" */ #define NUD_IN_TIMER (NUD_INCOMPLETE|NUD_REACHABLE|NUD_DELAY|NUD_PROBE) #define NUD_VALID (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE|NUD_PROBE|NUD_STALE|NUD_DELAY) #define NUD_CONNECTED (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE) struct neighbour; enum { NEIGH_VAR_MCAST_PROBES, NEIGH_VAR_UCAST_PROBES, NEIGH_VAR_APP_PROBES, NEIGH_VAR_MCAST_REPROBES, NEIGH_VAR_RETRANS_TIME, NEIGH_VAR_BASE_REACHABLE_TIME, NEIGH_VAR_DELAY_PROBE_TIME, NEIGH_VAR_INTERVAL_PROBE_TIME_MS, NEIGH_VAR_GC_STALETIME, NEIGH_VAR_QUEUE_LEN_BYTES, NEIGH_VAR_PROXY_QLEN, NEIGH_VAR_ANYCAST_DELAY, NEIGH_VAR_PROXY_DELAY, NEIGH_VAR_LOCKTIME, #define NEIGH_VAR_DATA_MAX (NEIGH_VAR_LOCKTIME + 1) /* Following are used as a second way to access one of the above */ NEIGH_VAR_QUEUE_LEN, /* same data as NEIGH_VAR_QUEUE_LEN_BYTES */ NEIGH_VAR_RETRANS_TIME_MS, /* same data as NEIGH_VAR_RETRANS_TIME */ NEIGH_VAR_BASE_REACHABLE_TIME_MS, /* same data as NEIGH_VAR_BASE_REACHABLE_TIME */ /* Following are used by "default" only */ NEIGH_VAR_GC_INTERVAL, NEIGH_VAR_GC_THRESH1, NEIGH_VAR_GC_THRESH2, NEIGH_VAR_GC_THRESH3, NEIGH_VAR_MAX }; struct neigh_parms { possible_net_t net; struct net_device *dev; netdevice_tracker dev_tracker; struct list_head list; int (*neigh_setup)(struct neighbour *); struct neigh_table *tbl; void *sysctl_table; int dead; refcount_t refcnt; struct rcu_head rcu_head; int reachable_time; u32 qlen; int data[NEIGH_VAR_DATA_MAX]; DECLARE_BITMAP(data_state, NEIGH_VAR_DATA_MAX); }; static inline void neigh_var_set(struct neigh_parms *p, int index, int val) { set_bit(index, p->data_state); WRITE_ONCE(p->data[index], val); } #define __NEIGH_VAR(p, attr) ((p)->data[NEIGH_VAR_ ## attr]) #define NEIGH_VAR(p, attr) READ_ONCE(__NEIGH_VAR(p, attr)) #define NEIGH_VAR_PTR(p, attr) (&(__NEIGH_VAR(p, attr))) /* In ndo_neigh_setup, NEIGH_VAR_INIT should be used. * In other cases, NEIGH_VAR_SET should be used. */ #define NEIGH_VAR_INIT(p, attr, val) (__NEIGH_VAR(p, attr) = val) #define NEIGH_VAR_SET(p, attr, val) neigh_var_set(p, NEIGH_VAR_ ## attr, val) static inline void neigh_parms_data_state_setall(struct neigh_parms *p) { bitmap_fill(p->data_state, NEIGH_VAR_DATA_MAX); } static inline void neigh_parms_data_state_cleanall(struct neigh_parms *p) { bitmap_zero(p->data_state, NEIGH_VAR_DATA_MAX); } struct neigh_statistics { unsigned long allocs; /* number of allocated neighs */ unsigned long destroys; /* number of destroyed neighs */ unsigned long hash_grows; /* number of hash resizes */ unsigned long res_failed; /* number of failed resolutions */ unsigned long lookups; /* number of lookups */ unsigned long hits; /* number of hits (among lookups) */ unsigned long rcv_probes_mcast; /* number of received mcast ipv6 */ unsigned long rcv_probes_ucast; /* number of received ucast ipv6 */ unsigned long periodic_gc_runs; /* number of periodic GC runs */ unsigned long forced_gc_runs; /* number of forced GC runs */ unsigned long unres_discards; /* number of unresolved drops */ unsigned long table_fulls; /* times even gc couldn't help */ }; #define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field) struct neighbour { struct hlist_node hash; struct hlist_node dev_list; struct neigh_table *tbl; struct neigh_parms *parms; unsigned long confirmed; unsigned long updated; rwlock_t lock; refcount_t refcnt; unsigned int arp_queue_len_bytes; struct sk_buff_head arp_queue; struct timer_list timer; unsigned long used; atomic_t probes; u8 nud_state; u8 type; u8 dead; u8 protocol; u32 flags; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8); struct hh_cache hh; int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; struct list_head gc_list; struct list_head managed_list; struct rcu_head rcu; struct net_device *dev; netdevice_tracker dev_tracker; u8 primary_key[]; } __randomize_layout; struct neigh_ops { int family; void (*solicit)(struct neighbour *, struct sk_buff *); void (*error_report)(struct neighbour *, struct sk_buff *); int (*output)(struct neighbour *, struct sk_buff *); int (*connected_output)(struct neighbour *, struct sk_buff *); }; struct pneigh_entry { struct pneigh_entry __rcu *next; possible_net_t net; struct net_device *dev; netdevice_tracker dev_tracker; union { struct list_head free_node; struct rcu_head rcu; }; u32 flags; u8 protocol; bool permanent; u32 key[]; }; /* * neighbour table manipulation */ #define NEIGH_NUM_HASH_RND 4 struct neigh_hash_table { struct hlist_head *hash_heads; unsigned int hash_shift; __u32 hash_rnd[NEIGH_NUM_HASH_RND]; struct rcu_head rcu; }; struct neigh_table { int family; unsigned int entry_size; unsigned int key_len; __be16 protocol; __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd); bool (*key_eq)(const struct neighbour *, const void *pkey); int (*constructor)(struct neighbour *); int (*pconstructor)(struct pneigh_entry *); void (*pdestructor)(struct pneigh_entry *); void (*proxy_redo)(struct sk_buff *skb); int (*is_multicast)(const void *pkey); bool (*allow_add)(const struct net_device *dev, struct netlink_ext_ack *extack); char *id; struct neigh_parms parms; struct list_head parms_list; int gc_interval; int gc_thresh1; int gc_thresh2; int gc_thresh3; unsigned long last_flush; struct delayed_work gc_work; struct delayed_work managed_work; struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; atomic_t gc_entries; struct list_head gc_list; struct list_head managed_list; spinlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; struct neigh_hash_table __rcu *nht; struct mutex phash_lock; struct pneigh_entry __rcu **phash_buckets; }; static inline int neigh_parms_family(struct neigh_parms *p) { return p->tbl->family; } #define NEIGH_PRIV_ALIGN sizeof(long long) #define NEIGH_ENTRY_SIZE(size) ALIGN((size), NEIGH_PRIV_ALIGN) static inline void *neighbour_priv(const struct neighbour *n) { return (char *)n + n->tbl->entry_size; } /* flags for neigh_update() */ #define NEIGH_UPDATE_F_OVERRIDE BIT(0) #define NEIGH_UPDATE_F_WEAK_OVERRIDE BIT(1) #define NEIGH_UPDATE_F_OVERRIDE_ISROUTER BIT(2) #define NEIGH_UPDATE_F_USE BIT(3) #define NEIGH_UPDATE_F_MANAGED BIT(4) #define NEIGH_UPDATE_F_EXT_LEARNED BIT(5) #define NEIGH_UPDATE_F_ISROUTER BIT(6) #define NEIGH_UPDATE_F_ADMIN BIT(7) #define NEIGH_UPDATE_F_EXT_VALIDATED BIT(8) /* In-kernel representation for NDA_FLAGS_EXT flags: */ #define NTF_OLD_MASK 0xff #define NTF_EXT_SHIFT 8 #define NTF_EXT_MASK (NTF_EXT_MANAGED | NTF_EXT_EXT_VALIDATED) #define NTF_MANAGED (NTF_EXT_MANAGED << NTF_EXT_SHIFT) #define NTF_EXT_VALIDATED (NTF_EXT_EXT_VALIDATED << NTF_EXT_SHIFT) extern const struct nla_policy nda_policy[]; #define neigh_for_each_in_bucket(pos, head) hlist_for_each_entry(pos, head, hash) #define neigh_for_each_in_bucket_rcu(pos, head) \ hlist_for_each_entry_rcu(pos, head, hash) #define neigh_for_each_in_bucket_safe(pos, tmp, head) \ hlist_for_each_entry_safe(pos, tmp, head, hash) static inline bool neigh_key_eq32(const struct neighbour *n, const void *pkey) { return *(const u32 *)n->primary_key == *(const u32 *)pkey; } static inline bool neigh_key_eq128(const struct neighbour *n, const void *pkey) { const u32 *n32 = (const u32 *)n->primary_key; const u32 *p32 = pkey; return ((n32[0] ^ p32[0]) | (n32[1] ^ p32[1]) | (n32[2] ^ p32[2]) | (n32[3] ^ p32[3])) == 0; } static inline struct neighbour *___neigh_lookup_noref( struct neigh_table *tbl, bool (*key_eq)(const struct neighbour *n, const void *pkey), __u32 (*hash)(const void *pkey, const struct net_device *dev, __u32 *hash_rnd), const void *pkey, struct net_device *dev) { struct neigh_hash_table *nht = rcu_dereference(tbl->nht); struct neighbour *n; u32 hash_val; hash_val = hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); neigh_for_each_in_bucket_rcu(n, &nht->hash_heads[hash_val]) if (n->dev == dev && key_eq(n, pkey)) return n; return NULL; } static inline struct neighbour *__neigh_lookup_noref(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { return ___neigh_lookup_noref(tbl, tbl->key_eq, tbl->hash, pkey, dev); } static inline void neigh_confirm(struct neighbour *n) { if (n) { unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); } } void neigh_table_init(int index, struct neigh_table *tbl); int neigh_table_clear(int index, struct neigh_table *tbl); struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev); struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref); static inline struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { return __neigh_create(tbl, pkey, dev, true); } void neigh_destroy(struct neighbour *neigh); int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb, const bool immediate_ok); int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid); void __neigh_set_probe_once(struct neighbour *neigh); bool neigh_remove_one(struct neighbour *ndel); void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); int neigh_carrier_down(struct neigh_table *tbl, struct net_device *dev); int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb); int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb); struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev); struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl); void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms); static inline struct net *neigh_parms_net(const struct neigh_parms *parms) { return read_pnet(&parms->net); } unsigned long neigh_rand_reach_time(unsigned long base); static inline void neigh_set_reach_time(struct neigh_parms *p) { unsigned long base = NEIGH_VAR(p, BASE_REACHABLE_TIME); WRITE_ONCE(p->reachable_time, neigh_rand_reach_time(base)); } void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb); struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); int pneigh_create(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev, u32 flags, u8 protocol, bool permanent); int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); static inline struct net *pneigh_net(const struct pneigh_entry *pneigh) { return read_pnet(&pneigh->net); } void neigh_app_ns(struct neighbour *n); void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie); void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)); int neigh_xmit(int fam, struct net_device *, const void *, struct sk_buff *); struct neigh_seq_state { struct seq_net_private p; struct neigh_table *tbl; struct neigh_hash_table *nht; void *(*neigh_sub_iter)(struct neigh_seq_state *state, struct neighbour *n, loff_t *pos); unsigned int bucket; unsigned int flags; #define NEIGH_SEQ_NEIGH_ONLY 0x00000001 #define NEIGH_SEQ_IS_PNEIGH 0x00000002 #define NEIGH_SEQ_SKIP_NOARP 0x00000004 }; void *neigh_seq_start(struct seq_file *, loff_t *, struct neigh_table *, unsigned int); void *neigh_seq_next(struct seq_file *, void *, loff_t *); void neigh_seq_stop(struct seq_file *, void *); int neigh_proc_dointvec(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_proc_dointvec_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_proc_dointvec_ms_jiffies(const struct ctl_table *ctl, int write, void *buffer, size_t *lenp, loff_t *ppos); int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, proc_handler *proc_handler); void neigh_sysctl_unregister(struct neigh_parms *p); static inline void __neigh_parms_put(struct neigh_parms *parms) { refcount_dec(&parms->refcnt); } static inline struct neigh_parms *neigh_parms_clone(struct neigh_parms *parms) { refcount_inc(&parms->refcnt); return parms; } /* * Neighbour references */ static inline void neigh_release(struct neighbour *neigh) { if (refcount_dec_and_test(&neigh->refcnt)) neigh_destroy(neigh); } static inline struct neighbour * neigh_clone(struct neighbour *neigh) { if (neigh) refcount_inc(&neigh->refcnt); return neigh; } #define neigh_hold(n) refcount_inc(&(n)->refcnt) static __always_inline int neigh_event_send_probe(struct neighbour *neigh, struct sk_buff *skb, const bool immediate_ok) { unsigned long now = jiffies; if (READ_ONCE(neigh->used) != now) WRITE_ONCE(neigh->used, now); if (!(READ_ONCE(neigh->nud_state) & (NUD_CONNECTED | NUD_DELAY | NUD_PROBE))) return __neigh_event_send(neigh, skb, immediate_ok); return 0; } static inline int neigh_event_send(struct neighbour *neigh, struct sk_buff *skb) { return neigh_event_send_probe(neigh, skb, true); } #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb) { unsigned int seq, hh_alen; do { seq = read_seqbegin(&hh->hh_lock); hh_alen = HH_DATA_ALIGN(ETH_HLEN); memcpy(skb->data - hh_alen, hh->hh_data, ETH_ALEN + hh_alen - ETH_HLEN); } while (read_seqretry(&hh->hh_lock, seq)); return 0; } #endif static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) { unsigned int hh_alen = 0; unsigned int seq; unsigned int hh_len; do { seq = read_seqbegin(&hh->hh_lock); hh_len = READ_ONCE(hh->hh_len); if (likely(hh_len <= HH_DATA_MOD)) { hh_alen = HH_DATA_MOD; /* skb_push() would proceed silently if we have room for * the unaligned size but not for the aligned size: * check headroom explicitly. */ if (likely(skb_headroom(skb) >= HH_DATA_MOD)) { /* this is inlined by gcc */ memcpy(skb->data - HH_DATA_MOD, hh->hh_data, HH_DATA_MOD); } } else { hh_alen = HH_DATA_ALIGN(hh_len); if (likely(skb_headroom(skb) >= hh_alen)) { memcpy(skb->data - hh_alen, hh->hh_data, hh_alen); } } } while (read_seqretry(&hh->hh_lock, seq)); if (WARN_ON_ONCE(skb_headroom(skb) < hh_alen)) { kfree_skb(skb); return NET_XMIT_DROP; } __skb_push(skb, hh_len); return dev_queue_xmit(skb); } static inline int neigh_output(struct neighbour *n, struct sk_buff *skb, bool skip_cache) { const struct hh_cache *hh = &n->hh; /* n->nud_state and hh->hh_len could be changed under us. * neigh_hh_output() is taking care of the race later. */ if (!skip_cache && (READ_ONCE(n->nud_state) & NUD_CONNECTED) && READ_ONCE(hh->hh_len)) return neigh_hh_output(hh, skb); return READ_ONCE(n->output)(n, skb); } static inline struct neighbour * __neigh_lookup(struct neigh_table *tbl, const void *pkey, struct net_device *dev, int creat) { struct neighbour *n = neigh_lookup(tbl, pkey, dev); if (n || !creat) return n; n = neigh_create(tbl, pkey, dev); return IS_ERR(n) ? NULL : n; } static inline struct neighbour * __neigh_lookup_errno(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { struct neighbour *n = neigh_lookup(tbl, pkey, dev); if (n) return n; return neigh_create(tbl, pkey, dev); } struct neighbour_cb { unsigned long sched_next; unsigned int flags; }; #define LOCALLY_ENQUEUED 0x1 #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, const struct net_device *dev) { unsigned int seq; do { seq = read_seqbegin(&n->ha_lock); memcpy(dst, n->ha, dev->addr_len); } while (read_seqretry(&n->ha_lock, seq)); } static inline void neigh_update_is_router(struct neighbour *neigh, u32 flags, int *notify) { u8 ndm_flags = 0; ndm_flags |= (flags & NEIGH_UPDATE_F_ISROUTER) ? NTF_ROUTER : 0; if ((neigh->flags ^ ndm_flags) & NTF_ROUTER) { if (ndm_flags & NTF_ROUTER) neigh->flags |= NTF_ROUTER; else neigh->flags &= ~NTF_ROUTER; *notify = 1; } } #endif |
| 46 295 30 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* 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. * * This file is part of the SCTP kernel implementation * * Please send any bug reports or fixes you make to the * email addresses: * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * Randall Stewart <randall@sctp.chicago.il.us> * Ken Morneau <kmorneau@cisco.com> * Qiaobing Xie <qxie1@email.mot.com> * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Jon Grimm <jgrimm@us.ibm.com> * Xingang Guo <xingang.guo@intel.com> * Hui Huang <hui.huang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Daisy Chang <daisyc@us.ibm.com> * Dajiang Zhang <dajiang.zhang@nokia.com> * Ardelle Fan <ardelle.fan@intel.com> * Ryan Layer <rmlayer@us.ibm.com> * Anup Pemmaiah <pemmaiah@cc.usu.edu> * Kevin Gao <kevin.gao@intel.com> */ #ifndef __sctp_structs_h__ #define __sctp_structs_h__ #include <crypto/sha2.h> #include <linux/ktime.h> #include <linux/generic-radix-tree.h> #include <linux/rhashtable-types.h> #include <linux/socket.h> /* linux/in.h needs this!! */ #include <linux/in.h> /* We get struct sockaddr_in. */ #include <linux/in6.h> /* We get struct in6_addr */ #include <linux/ipv6.h> #include <asm/param.h> /* We get MAXHOSTNAMELEN. */ #include <linux/atomic.h> /* This gets us atomic counters. */ #include <linux/skbuff.h> /* We need sk_buff_head. */ #include <linux/workqueue.h> /* We need tq_struct. */ #include <linux/sctp.h> /* We need sctp* header structs. */ #include <net/sctp/auth.h> /* We need auth specific structs */ #include <net/ip.h> /* For inet_skb_parm */ /* A convenience structure for handling sockaddr structures. * We should wean ourselves off this. */ union sctp_addr { struct sockaddr_inet sa; /* Large enough for both address families */ struct sockaddr_in v4; struct sockaddr_in6 v6; }; /* Forward declarations for data structures. */ struct sctp_globals; struct sctp_endpoint; struct sctp_association; struct sctp_transport; struct sctp_packet; struct sctp_chunk; struct sctp_inq; struct sctp_outq; struct sctp_bind_addr; struct sctp_ulpq; struct sctp_ep_common; struct sctp_stream; #include <net/sctp/tsnmap.h> #include <net/sctp/ulpevent.h> #include <net/sctp/ulpqueue.h> #include <net/sctp/stream_interleave.h> /* Structures useful for managing bind/connect. */ struct sctp_bind_bucket { unsigned short port; signed char fastreuse; signed char fastreuseport; kuid_t fastuid; struct hlist_node node; struct hlist_head owner; struct net *net; }; struct sctp_bind_hashbucket { spinlock_t lock; struct hlist_head chain; }; /* Used for hashing all associations. */ struct sctp_hashbucket { rwlock_t lock; struct hlist_head chain; } __attribute__((__aligned__(8))); /* The SCTP globals structure. */ extern struct sctp_globals { /* This is a list of groups of functions for each address * family that we support. */ struct list_head address_families; /* This is the hash of all endpoints. */ struct sctp_hashbucket *ep_hashtable; /* This is the sctp port control hash. */ struct sctp_bind_hashbucket *port_hashtable; /* This is the hash of all transports. */ struct rhltable transport_hashtable; /* Sizes of above hashtables. */ int ep_hashsize; int port_hashsize; /* Default initialization values to be applied to new associations. */ __u16 max_instreams; __u16 max_outstreams; /* Flag to indicate whether computing and verifying checksum * is disabled. */ bool checksum_disable; } sctp_globals; #define sctp_max_instreams (sctp_globals.max_instreams) #define sctp_max_outstreams (sctp_globals.max_outstreams) #define sctp_address_families (sctp_globals.address_families) #define sctp_ep_hashsize (sctp_globals.ep_hashsize) #define sctp_ep_hashtable (sctp_globals.ep_hashtable) #define sctp_port_hashsize (sctp_globals.port_hashsize) #define sctp_port_hashtable (sctp_globals.port_hashtable) #define sctp_transport_hashtable (sctp_globals.transport_hashtable) #define sctp_checksum_disable (sctp_globals.checksum_disable) /* SCTP Socket type: UDP or TCP style. */ enum sctp_socket_type { SCTP_SOCKET_UDP = 0, SCTP_SOCKET_UDP_HIGH_BANDWIDTH, SCTP_SOCKET_TCP }; /* Per socket SCTP information. */ struct sctp_sock { /* inet_sock has to be the first member of sctp_sock */ struct inet_sock inet; /* What kind of a socket is this? */ enum sctp_socket_type type; /* PF_ family specific functions. */ struct sctp_pf *pf; /* What is our base endpointer? */ struct sctp_endpoint *ep; struct sctp_bind_bucket *bind_hash; /* Various Socket Options. */ __u16 default_stream; __u32 default_ppid; __u16 default_flags; __u32 default_context; __u32 default_timetolive; __u32 default_rcv_context; int max_burst; /* Heartbeat interval: The endpoint sends out a Heartbeat chunk to * the destination address every heartbeat interval. This value * will be inherited by all new associations. */ __u32 hbinterval; __u32 probe_interval; __be16 udp_port; __be16 encap_port; /* This is the max_retrans value for new associations. */ __u16 pathmaxrxt; __u32 flowlabel; __u8 dscp; __u16 pf_retrans; __u16 ps_retrans; /* The initial Path MTU to use for new associations. */ __u32 pathmtu; /* The default SACK delay timeout for new associations. */ __u32 sackdelay; __u32 sackfreq; /* Flags controlling Heartbeat, SACK delay, and Path MTU Discovery. */ __u32 param_flags; __u32 default_ss; struct sctp_rtoinfo rtoinfo; struct sctp_paddrparams paddrparam; struct sctp_assocparams assocparams; /* * These two structures must be grouped together for the usercopy * whitelist region. */ __u16 subscribe; struct sctp_initmsg initmsg; int user_frag; __u32 autoclose; __u32 adaptation_ind; __u32 pd_point; __u16 nodelay:1, pf_expose:2, reuse:1, disable_fragments:1, v4mapped:1, frag_interleave:1, recvrcvinfo:1, recvnxtinfo:1, data_ready_signalled:1, cookie_auth_enable:1; atomic_t pd_mode; /* Receive to here while partial delivery is in effect. */ struct sk_buff_head pd_lobby; struct list_head auto_asconf_list; int do_auto_asconf; }; #define sctp_sk(ptr) container_of_const(ptr, struct sctp_sock, inet.sk) static inline struct sock *sctp_opt2sk(const struct sctp_sock *sp) { return (struct sock *)sp; } #if IS_ENABLED(CONFIG_IPV6) struct sctp6_sock { struct sctp_sock sctp; struct ipv6_pinfo inet6; }; #endif /* CONFIG_IPV6 */ /* This is our APPLICATION-SPECIFIC state cookie. * THIS IS NOT DICTATED BY THE SPECIFICATION. */ /* These are the parts of an association which we send in the cookie. * Most of these are straight out of: * RFC2960 12.2 Parameters necessary per association (i.e. the TCB) * */ struct sctp_cookie { /* My : Tag expected in every inbound packet and sent * Verification: in the INIT or INIT ACK chunk. * Tag : */ __u32 my_vtag; /* Peer's : Tag expected in every outbound packet except * Verification: in the INIT chunk. * Tag : */ __u32 peer_vtag; /* The rest of these are not from the spec, but really need to * be in the cookie. */ /* My Tie Tag : Assist in discovering a restarting association. */ __u32 my_ttag; /* Peer's Tie Tag: Assist in discovering a restarting association. */ __u32 peer_ttag; /* When does this cookie expire? */ ktime_t expiration; /* Number of inbound/outbound streams which are set * and negotiated during the INIT process. */ __u16 sinit_num_ostreams; __u16 sinit_max_instreams; /* This is the first sequence number I used. */ __u32 initial_tsn; /* This holds the originating address of the INIT packet. */ union sctp_addr peer_addr; /* IG Section 2.35.3 * Include the source port of the INIT-ACK */ __u16 my_port; __u8 prsctp_capable; /* Padding for future use */ __u8 padding; __u32 adaptation_ind; __u8 auth_random[sizeof(struct sctp_paramhdr) + SCTP_AUTH_RANDOM_LENGTH]; __u8 auth_hmacs[SCTP_AUTH_NUM_HMACS * sizeof(__u16) + 2]; __u8 auth_chunks[sizeof(struct sctp_paramhdr) + SCTP_AUTH_MAX_CHUNKS]; /* This is a shim for my peer's INIT packet, followed by * a copy of the raw address list of the association. * The length of the raw address list is saved in the * raw_addr_list_len field, which will be used at the time when * the association TCB is re-constructed from the cookie. */ __u32 raw_addr_list_len; /* struct sctp_init_chunk peer_init[]; */ }; /* The format of our cookie that we send to our peer. */ struct sctp_signed_cookie { __u8 mac[SCTP_COOKIE_MAC_SIZE]; __u32 __pad; /* force sctp_cookie alignment to 64 bits */ struct sctp_cookie c; } __packed; /* This is another convenience type to allocate memory for address * params for the maximum size and pass such structures around * internally. */ union sctp_addr_param { struct sctp_paramhdr p; struct sctp_ipv4addr_param v4; struct sctp_ipv6addr_param v6; }; /* A convenience type to allow walking through the various * parameters and avoid casting all over the place. */ union sctp_params { void *v; struct sctp_paramhdr *p; struct sctp_cookie_preserve_param *life; struct sctp_hostname_param *dns; struct sctp_cookie_param *cookie; struct sctp_supported_addrs_param *sat; struct sctp_ipv4addr_param *v4; struct sctp_ipv6addr_param *v6; union sctp_addr_param *addr; struct sctp_adaptation_ind_param *aind; struct sctp_supported_ext_param *ext; struct sctp_random_param *random; struct sctp_chunks_param *chunks; struct sctp_hmac_algo_param *hmac_algo; struct sctp_addip_param *addip; }; /* RFC 2960. Section 3.3.5 Heartbeat. * Heartbeat Information: variable length * The Sender-specific Heartbeat Info field should normally include * information about the sender's current time when this HEARTBEAT * chunk is sent and the destination transport address to which this * HEARTBEAT is sent (see Section 8.3). */ struct sctp_sender_hb_info { struct sctp_paramhdr param_hdr; union sctp_addr daddr; unsigned long sent_at; __u64 hb_nonce; __u32 probe_size; }; int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, gfp_t gfp); int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid); void sctp_stream_free(struct sctp_stream *stream); void sctp_stream_clear(struct sctp_stream *stream); void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new); /* What is the current SSN number for this stream? */ #define sctp_ssn_peek(stream, type, sid) \ (sctp_stream_##type((stream), (sid))->ssn) /* Return the next SSN number for this stream. */ #define sctp_ssn_next(stream, type, sid) \ (sctp_stream_##type((stream), (sid))->ssn++) /* Skip over this ssn and all below. */ #define sctp_ssn_skip(stream, type, sid, ssn) \ (sctp_stream_##type((stream), (sid))->ssn = ssn + 1) /* What is the current MID number for this stream? */ #define sctp_mid_peek(stream, type, sid) \ (sctp_stream_##type((stream), (sid))->mid) /* Return the next MID number for this stream. */ #define sctp_mid_next(stream, type, sid) \ (sctp_stream_##type((stream), (sid))->mid++) /* Skip over this mid and all below. */ #define sctp_mid_skip(stream, type, sid, mid) \ (sctp_stream_##type((stream), (sid))->mid = mid + 1) /* What is the current MID_uo number for this stream? */ #define sctp_mid_uo_peek(stream, type, sid) \ (sctp_stream_##type((stream), (sid))->mid_uo) /* Return the next MID_uo number for this stream. */ #define sctp_mid_uo_next(stream, type, sid) \ (sctp_stream_##type((stream), (sid))->mid_uo++) /* * Pointers to address related SCTP functions. * (i.e. things that depend on the address family.) */ struct sctp_af { int (*sctp_xmit) (struct sk_buff *skb, struct sctp_transport *); 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 (*get_dst) (struct sctp_transport *t, union sctp_addr *saddr, struct flowi *fl, struct sock *sk); void (*get_saddr) (struct sctp_sock *sk, struct sctp_transport *t, struct flowi *fl); void (*copy_addrlist) (struct list_head *, struct net_device *); int (*cmp_addr) (const union sctp_addr *addr1, const union sctp_addr *addr2); void (*addr_copy) (union sctp_addr *dst, union sctp_addr *src); void (*from_skb) (union sctp_addr *, struct sk_buff *skb, int saddr); void (*from_sk) (union sctp_addr *, struct sock *sk); bool (*from_addr_param) (union sctp_addr *, union sctp_addr_param *, __be16 port, int iif); int (*to_addr_param) (const union sctp_addr *, union sctp_addr_param *); int (*addr_valid) (union sctp_addr *, struct sctp_sock *, const struct sk_buff *); enum sctp_scope (*scope)(union sctp_addr *); void (*inaddr_any) (union sctp_addr *, __be16); int (*is_any) (const union sctp_addr *); int (*available) (union sctp_addr *, struct sctp_sock *); int (*skb_iif) (const struct sk_buff *sk); int (*skb_sdif)(const struct sk_buff *sk); int (*is_ce) (const struct sk_buff *sk); void (*seq_dump_addr)(struct seq_file *seq, union sctp_addr *addr); void (*ecn_capable)(struct sock *sk); __u16 net_header_len; int sockaddr_len; int (*ip_options_len)(struct sock *sk); sa_family_t sa_family; struct list_head list; }; struct sctp_af *sctp_get_af_specific(sa_family_t); int sctp_register_af(struct sctp_af *); /* Protocol family functions. */ struct sctp_pf { void (*event_msgname)(struct sctp_ulpevent *, char *, int *); void (*skb_msgname) (struct sk_buff *, char *, int *); int (*af_supported) (sa_family_t, struct sctp_sock *); int (*cmp_addr) (const union sctp_addr *, const union sctp_addr *, struct sctp_sock *); int (*bind_verify) (struct sctp_sock *, union sctp_addr *); int (*send_verify) (struct sctp_sock *, union sctp_addr *); int (*supported_addrs)(const struct sctp_sock *, __be16 *); int (*addr_to_user)(struct sctp_sock *sk, union sctp_addr *addr); void (*to_sk_saddr)(union sctp_addr *, struct sock *sk); void (*to_sk_daddr)(union sctp_addr *, struct sock *sk); void (*copy_ip_options)(struct sock *sk, struct sock *newsk); struct sctp_af *af; }; /* Structure to track chunk fragments that have been acked, but peer * fragments of the same message have not. */ struct sctp_datamsg { /* Chunks waiting to be submitted to lower layer. */ struct list_head chunks; /* Reference counting. */ refcount_t refcnt; /* When is this message no longer interesting to the peer? */ unsigned long expires_at; /* Did the message fail to send? */ int send_error; u8 send_failed:1, can_delay:1, /* should this message be Nagle delayed */ abandoned:1; /* should this message be abandoned */ }; struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *, struct sctp_sndrcvinfo *, struct iov_iter *); void sctp_datamsg_free(struct sctp_datamsg *); void sctp_datamsg_put(struct sctp_datamsg *); void sctp_chunk_fail(struct sctp_chunk *, int error); int sctp_chunk_abandoned(struct sctp_chunk *); /* RFC2960 1.4 Key Terms * * o Chunk: A unit of information within an SCTP packet, consisting of * a chunk header and chunk-specific content. * * As a matter of convenience, we remember the SCTP common header for * each chunk as well as a few other header pointers... */ struct sctp_chunk { struct list_head list; refcount_t refcnt; /* How many times this chunk have been sent, for prsctp RTX policy */ int sent_count; union { /* This is our link to the per-transport transmitted list. */ struct list_head transmitted_list; /* List in specific stream outq */ struct list_head stream_list; }; /* This field is used by chunks that hold fragmented data. * For the first fragment this is the list that holds the rest of * fragments. For the remaining fragments, this is the link to the * frag_list maintained in the first fragment. */ struct list_head frag_list; /* This points to the sk_buff containing the actual data. */ struct sk_buff *skb; union { /* In case of GSO packets, this will store the head one */ struct sk_buff *head_skb; /* In case of auth enabled, this will point to the shkey */ struct sctp_shared_key *shkey; }; /* These are the SCTP headers by reverse order in a packet. * Note that some of these may happen more than once. In that * case, we point at the "current" one, whatever that means * for that level of header. */ /* We point this at the FIRST TLV parameter to chunk_hdr. */ union sctp_params param_hdr; union { __u8 *v; struct sctp_datahdr *data_hdr; struct sctp_inithdr *init_hdr; struct sctp_sackhdr *sack_hdr; struct sctp_heartbeathdr *hb_hdr; struct sctp_sender_hb_info *hbs_hdr; struct sctp_shutdownhdr *shutdown_hdr; struct sctp_signed_cookie *cookie_hdr; struct sctp_ecnehdr *ecne_hdr; struct sctp_cwrhdr *ecn_cwr_hdr; struct sctp_errhdr *err_hdr; struct sctp_addiphdr *addip_hdr; struct sctp_fwdtsn_hdr *fwdtsn_hdr; struct sctp_authhdr *auth_hdr; struct sctp_idatahdr *idata_hdr; struct sctp_ifwdtsn_hdr *ifwdtsn_hdr; } subh; __u8 *chunk_end; struct sctp_chunkhdr *chunk_hdr; struct sctphdr *sctp_hdr; /* This needs to be recoverable for SCTP_SEND_FAILED events. */ struct sctp_sndrcvinfo sinfo; /* Which association does this belong to? */ struct sctp_association *asoc; /* What endpoint received this chunk? */ struct sctp_ep_common *rcvr; /* We fill this in if we are calculating RTT. */ unsigned long sent_at; /* What is the origin IP address for this chunk? */ union sctp_addr source; /* Destination address for this chunk. */ union sctp_addr dest; /* For outbound message, track all fragments for SEND_FAILED. */ struct sctp_datamsg *msg; /* For an inbound chunk, this tells us where it came from. * For an outbound chunk, it tells us where we'd like it to * go. It is NULL if we have no preference. */ struct sctp_transport *transport; /* SCTP-AUTH: For the special case inbound processing of COOKIE-ECHO * we need save a pointer to the AUTH chunk, since the SCTP-AUTH * spec violates the principle premis that all chunks are processed * in order. */ struct sk_buff *auth_chunk; #define SCTP_CAN_FRTX 0x0 #define SCTP_NEED_FRTX 0x1 #define SCTP_DONT_FRTX 0x2 __u16 rtt_in_progress:1, /* This chunk used for RTT calc? */ has_tsn:1, /* Does this chunk have a TSN yet? */ has_ssn:1, /* Does this chunk have a SSN yet? */ #define has_mid has_ssn singleton:1, /* Only chunk in the packet? */ end_of_packet:1, /* Last chunk in the packet? */ ecn_ce_done:1, /* Have we processed the ECN CE bit? */ pdiscard:1, /* Discard the whole packet now? */ tsn_gap_acked:1, /* Is this chunk acked by a GAP ACK? */ data_accepted:1, /* At least 1 chunk accepted */ auth:1, /* IN: was auth'ed | OUT: needs auth */ has_asconf:1, /* IN: have seen an asconf before */ pmtu_probe:1, /* Used by PLPMTUD, can be set in s HB chunk */ tsn_missing_report:2, /* Data chunk missing counter. */ fast_retransmit:2; /* Is this chunk fast retransmitted? */ }; #define sctp_chunk_retransmitted(chunk) (chunk->sent_count > 1) void sctp_chunk_hold(struct sctp_chunk *); void sctp_chunk_put(struct sctp_chunk *); int sctp_user_addto_chunk(struct sctp_chunk *chunk, int len, struct iov_iter *from); void sctp_chunk_free(struct sctp_chunk *); void *sctp_addto_chunk(struct sctp_chunk *, int len, const void *data); struct sctp_chunk *sctp_chunkify(struct sk_buff *, const struct sctp_association *, struct sock *, gfp_t gfp); void sctp_init_addrs(struct sctp_chunk *, union sctp_addr *, union sctp_addr *); const union sctp_addr *sctp_source(const struct sctp_chunk *chunk); static inline __u16 sctp_chunk_stream_no(struct sctp_chunk *ch) { return ntohs(ch->subh.data_hdr->stream); } enum { SCTP_ADDR_NEW, /* new address added to assoc/ep */ SCTP_ADDR_SRC, /* address can be used as source */ SCTP_ADDR_DEL, /* address about to be deleted */ }; /* This is a structure for holding either an IPv6 or an IPv4 address. */ struct sctp_sockaddr_entry { struct list_head list; struct rcu_head rcu; union sctp_addr a; __u8 state; __u8 valid; }; #define SCTP_ADDRESS_TICK_DELAY 500 /* This structure holds lists of chunks as we are assembling for * transmission. */ struct sctp_packet { /* These are the SCTP header values (host order) for the packet. */ __u16 source_port; __u16 destination_port; __u32 vtag; /* This contains the payload chunks. */ struct list_head chunk_list; /* This is the overhead of the sctp and ip headers. */ size_t overhead; /* This is the total size of all chunks INCLUDING padding. */ size_t size; /* This is the maximum size this packet may have */ size_t max_size; /* The packet is destined for this transport address. * The function we finally use to pass down to the next lower * layer lives in the transport structure. */ struct sctp_transport *transport; /* pointer to the auth chunk for this packet */ struct sctp_chunk *auth; u8 has_cookie_echo:1, /* This packet contains a COOKIE-ECHO chunk. */ has_sack:1, /* This packet contains a SACK chunk. */ has_auth:1, /* This packet contains an AUTH chunk */ has_data:1, /* This packet contains at least 1 DATA chunk */ ipfragok:1; /* So let ip fragment this packet */ }; void sctp_packet_init(struct sctp_packet *, struct sctp_transport *, __u16 sport, __u16 dport); void sctp_packet_config(struct sctp_packet *, __u32 vtag, int); enum sctp_xmit sctp_packet_transmit_chunk(struct sctp_packet *packet, struct sctp_chunk *chunk, int one_packet, gfp_t gfp); enum sctp_xmit sctp_packet_append_chunk(struct sctp_packet *packet, struct sctp_chunk *chunk); int sctp_packet_transmit(struct sctp_packet *, gfp_t); void sctp_packet_free(struct sctp_packet *); static inline int sctp_packet_empty(struct sctp_packet *packet) { return packet->size == packet->overhead; } /* This represents a remote transport address. * For local transport addresses, we just use union sctp_addr. * * RFC2960 Section 1.4 Key Terms * * o Transport address: A Transport Address is traditionally defined * by Network Layer address, Transport Layer protocol and Transport * Layer port number. In the case of SCTP running over IP, a * transport address is defined by the combination of an IP address * and an SCTP port number (where SCTP is the Transport protocol). * * RFC2960 Section 7.1 SCTP Differences from TCP Congestion control * * o The sender keeps a separate congestion control parameter set for * each of the destination addresses it can send to (not each * source-destination pair but for each destination). The parameters * should decay if the address is not used for a long enough time * period. * */ struct sctp_transport { /* A list of transports. */ struct list_head transports; struct rhlist_head node; /* Reference counting. */ refcount_t refcnt; __u32 dead:1, /* RTO-Pending : A flag used to track if one of the DATA * chunks sent to this address is currently being * used to compute a RTT. If this flag is 0, * the next DATA chunk sent to this destination * should be used to compute a RTT and this flag * should be set. Every time the RTT * calculation completes (i.e. the DATA chunk * is SACK'd) clear this flag. */ rto_pending:1, /* * hb_sent : a flag that signals that we have a pending * heartbeat. */ hb_sent:1, /* Is the Path MTU update pending on this transport */ pmtu_pending:1, dst_pending_confirm:1, /* need to confirm neighbour */ /* Has this transport moved the ctsn since we last sacked */ sack_generation:1; u32 dst_cookie; struct flowi fl; /* This is the peer's IP address and port. */ union sctp_addr ipaddr; /* These are the functions we call to handle LLP stuff. */ struct sctp_af *af_specific; /* Which association do we belong to? */ struct sctp_association *asoc; /* RFC2960 * * 12.3 Per Transport Address Data * * For each destination transport address in the peer's * address list derived from the INIT or INIT ACK chunk, a * number of data elements needs to be maintained including: */ /* RTO : The current retransmission timeout value. */ unsigned long rto; __u32 rtt; /* This is the most recent RTT. */ /* RTTVAR : The current RTT variation. */ __u32 rttvar; /* SRTT : The current smoothed round trip time. */ __u32 srtt; /* * These are the congestion stats. */ /* cwnd : The current congestion window. */ __u32 cwnd; /* This is the actual cwnd. */ /* ssthresh : The current slow start threshold value. */ __u32 ssthresh; /* partial : The tracking method for increase of cwnd when in * bytes acked : congestion avoidance mode (see Section 6.2.2) */ __u32 partial_bytes_acked; /* Data that has been sent, but not acknowledged. */ __u32 flight_size; __u32 burst_limited; /* Holds old cwnd when max.burst is applied */ /* Destination */ struct dst_entry *dst; /* Source address. */ union sctp_addr saddr; /* Heartbeat interval: The endpoint sends out a Heartbeat chunk to * the destination address every heartbeat interval. */ unsigned long hbinterval; unsigned long probe_interval; /* SACK delay timeout */ unsigned long sackdelay; __u32 sackfreq; atomic_t mtu_info; /* When was the last time that we heard from this transport? We use * this to pick new active and retran paths. */ ktime_t last_time_heard; /* When was the last time that we sent a chunk using this * transport? We use this to check for idle transports */ unsigned long last_time_sent; /* Last time(in jiffies) when cwnd is reduced due to the congestion * indication based on ECNE chunk. */ unsigned long last_time_ecne_reduced; __be16 encap_port; /* This is the max_retrans value for the transport and will * be initialized from the assocs value. This can be changed * using the SCTP_SET_PEER_ADDR_PARAMS socket option. */ __u16 pathmaxrxt; __u32 flowlabel; __u8 dscp; /* This is the partially failed retrans value for the transport * and will be initialized from the assocs value. This can be changed * using the SCTP_PEER_ADDR_THLDS socket option */ __u16 pf_retrans; /* Used for primary path switchover. */ __u16 ps_retrans; /* PMTU : The current known path MTU. */ __u32 pathmtu; /* Flags controlling Heartbeat, SACK delay, and Path MTU Discovery. */ __u32 param_flags; /* The number of times INIT has been sent on this transport. */ int init_sent_count; /* state : The current state of this destination, * : i.e. SCTP_ACTIVE, SCTP_INACTIVE, SCTP_UNKNOWN. */ int state; /* These are the error stats for this destination. */ /* Error count : The current error count for this destination. */ unsigned short error_count; /* Per : A timer used by each destination. * Destination : * Timer : * * [Everywhere else in the text this is called T3-rtx. -ed] */ struct timer_list T3_rtx_timer; /* Heartbeat timer is per destination. */ struct timer_list hb_timer; /* Timer to handle ICMP proto unreachable envets */ struct timer_list proto_unreach_timer; /* Timer to handler reconf chunk rtx */ struct timer_list reconf_timer; /* Timer to send a probe HB packet for PLPMTUD */ struct timer_list probe_timer; /* Since we're using per-destination retransmission timers * (see above), we're also using per-destination "transmitted" * queues. This probably ought to be a private struct * accessible only within the outqueue, but it's not, yet. */ struct list_head transmitted; /* We build bundle-able packets for this transport here. */ struct sctp_packet packet; /* This is the list of transports that have chunks to send. */ struct list_head send_ready; /* State information saved for SFR_CACC algorithm. The key * idea in SFR_CACC is to maintain state at the sender on a * per-destination basis when a changeover happens. * char changeover_active; * char cycling_changeover; * __u32 next_tsn_at_change; * char cacc_saw_newack; */ struct { /* An unsigned integer, which stores the next TSN to be * used by the sender, at the moment of changeover. */ __u32 next_tsn_at_change; /* A flag which indicates the occurrence of a changeover */ char changeover_active; /* A flag which indicates whether the change of primary is * the first switch to this destination address during an * active switch. */ char cycling_changeover; /* A temporary flag, which is used during the processing of * a SACK to estimate the causative TSN(s)'s group. */ char cacc_saw_newack; } cacc; struct { __u16 pmtu; __u16 probe_size; __u16 probe_high; __u8 probe_count; __u8 state; } pl; /* plpmtud related */ /* 64-bit random number sent with heartbeat. */ __u64 hb_nonce; struct rcu_head rcu; }; struct sctp_transport *sctp_transport_new(struct net *, const union sctp_addr *, gfp_t); void sctp_transport_set_owner(struct sctp_transport *, struct sctp_association *); void sctp_transport_route(struct sctp_transport *, union sctp_addr *, struct sctp_sock *); void sctp_transport_pmtu(struct sctp_transport *, struct sock *sk); void sctp_transport_free(struct sctp_transport *); void sctp_transport_reset_t3_rtx(struct sctp_transport *); void sctp_transport_reset_hb_timer(struct sctp_transport *); void sctp_transport_reset_reconf_timer(struct sctp_transport *transport); void sctp_transport_reset_probe_timer(struct sctp_transport *transport); void sctp_transport_reset_raise_timer(struct sctp_transport *transport); int sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); void sctp_transport_raise_cwnd(struct sctp_transport *, __u32, __u32); void sctp_transport_lower_cwnd(struct sctp_transport *t, enum sctp_lower_cwnd reason); void sctp_transport_burst_limited(struct sctp_transport *); void sctp_transport_burst_reset(struct sctp_transport *); unsigned long sctp_transport_timeout(struct sctp_transport *); void sctp_transport_reset(struct sctp_transport *t); bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); void sctp_transport_immediate_rtx(struct sctp_transport *); void sctp_transport_dst_release(struct sctp_transport *t); void sctp_transport_dst_confirm(struct sctp_transport *t); void sctp_transport_pl_send(struct sctp_transport *t); bool sctp_transport_pl_recv(struct sctp_transport *t); /* This is the structure we use to queue packets as they come into * SCTP. We write packets to it and read chunks from it. */ struct sctp_inq { /* This is actually a queue of sctp_chunk each * containing a partially decoded packet. */ struct list_head in_chunk_list; /* This is the packet which is currently off the in queue and is * being worked on through the inbound chunk processing. */ struct sctp_chunk *in_progress; /* This is the delayed task to finish delivering inbound * messages. */ struct work_struct immediate; }; void sctp_inq_init(struct sctp_inq *); void sctp_inq_free(struct sctp_inq *); void sctp_inq_push(struct sctp_inq *, struct sctp_chunk *packet); struct sctp_chunk *sctp_inq_pop(struct sctp_inq *); struct sctp_chunkhdr *sctp_inq_peek(struct sctp_inq *); void sctp_inq_set_th_handler(struct sctp_inq *, work_func_t); /* This is the structure we use to hold outbound chunks. You push * chunks in and they automatically pop out the other end as bundled * packets (it calls (*output_handler)()). * * This structure covers sections 6.3, 6.4, 6.7, 6.8, 6.10, 7., 8.1, * and 8.2 of the v13 draft. * * It handles retransmissions. The connection to the timeout portion * of the state machine is through sctp_..._timeout() and timeout_handler. * * If you feed it SACKs, it will eat them. * * If you give it big chunks, it will fragment them. * * It assigns TSN's to data chunks. This happens at the last possible * instant before transmission. * * When free()'d, it empties itself out via output_handler(). */ struct sctp_outq { struct sctp_association *asoc; /* Data pending that has never been transmitted. */ struct list_head out_chunk_list; /* Stream scheduler being used */ const struct sctp_sched_ops *sched; unsigned int out_qlen; /* Total length of queued data chunks. */ /* Error of send failed, may used in SCTP_SEND_FAILED event. */ unsigned int error; /* These are control chunks we want to send. */ struct list_head control_chunk_list; /* These are chunks that have been sacked but are above the * CTSN, or cumulative tsn ack point. */ struct list_head sacked; /* Put chunks on this list to schedule them for * retransmission. */ struct list_head retransmit; /* Put chunks on this list to save them for FWD TSN processing as * they were abandoned. */ struct list_head abandoned; /* How many unackd bytes do we have in-flight? */ __u32 outstanding_bytes; /* Are we doing fast-rtx on this queue */ char fast_rtx; /* Corked? */ char cork; }; void sctp_outq_init(struct sctp_association *, struct sctp_outq *); void sctp_outq_teardown(struct sctp_outq *); void sctp_outq_free(struct sctp_outq*); void sctp_outq_tail(struct sctp_outq *, struct sctp_chunk *chunk, gfp_t); int sctp_outq_sack(struct sctp_outq *, struct sctp_chunk *); int sctp_outq_is_empty(const struct sctp_outq *); void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, enum sctp_retransmit_reason reason); void sctp_retransmit_mark(struct sctp_outq *, struct sctp_transport *, __u8); void sctp_outq_uncork(struct sctp_outq *, gfp_t gfp); void sctp_prsctp_prune(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len); void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn); /* Uncork and flush an outqueue. */ static inline void sctp_outq_cork(struct sctp_outq *q) { q->cork = 1; } /* SCTP skb control block. * sctp_input_cb is currently used on rx and sock rx queue */ struct sctp_input_cb { union { struct inet_skb_parm h4; #if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; struct sctp_chunk *chunk; struct sctp_af *af; __be16 encap_port; }; #define SCTP_INPUT_CB(__skb) ((struct sctp_input_cb *)&((__skb)->cb[0])) struct sctp_output_cb { struct sk_buff *last; }; #define SCTP_OUTPUT_CB(__skb) ((struct sctp_output_cb *)&((__skb)->cb[0])) static inline const struct sk_buff *sctp_gso_headskb(const struct sk_buff *skb) { const struct sctp_chunk *chunk = SCTP_INPUT_CB(skb)->chunk; return chunk->head_skb ? : skb; } /* These bind address data fields common between endpoints and associations */ struct sctp_bind_addr { /* RFC 2960 12.1 Parameters necessary for the SCTP instance * * SCTP Port: The local SCTP port number the endpoint is * bound to. */ __u16 port; /* RFC 2960 12.1 Parameters necessary for the SCTP instance * * Address List: The list of IP addresses that this instance * has bound. This information is passed to one's * peer(s) in INIT and INIT ACK chunks. */ struct list_head address_list; }; void sctp_bind_addr_init(struct sctp_bind_addr *, __u16 port); void sctp_bind_addr_free(struct sctp_bind_addr *); int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest, const struct sctp_bind_addr *src, enum sctp_scope scope, gfp_t gfp, int flags); int sctp_bind_addr_dup(struct sctp_bind_addr *dest, const struct sctp_bind_addr *src, gfp_t gfp); int sctp_add_bind_addr(struct sctp_bind_addr *, union sctp_addr *, int new_size, __u8 addr_state, gfp_t gfp); int sctp_del_bind_addr(struct sctp_bind_addr *, union sctp_addr *); int sctp_bind_addr_match(struct sctp_bind_addr *, const union sctp_addr *, struct sctp_sock *); int sctp_bind_addr_conflict(struct sctp_bind_addr *, const union sctp_addr *, struct sctp_sock *, struct sctp_sock *); int sctp_bind_addr_state(const struct sctp_bind_addr *bp, const union sctp_addr *addr); int sctp_bind_addrs_check(struct sctp_sock *sp, struct sctp_sock *sp2, int cnt2); union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr *bp, const union sctp_addr *addrs, int addrcnt, struct sctp_sock *opt); union sctp_params sctp_bind_addrs_to_raw(const struct sctp_bind_addr *bp, int *addrs_len, gfp_t gfp); int sctp_raw_to_bind_addrs(struct sctp_bind_addr *bp, __u8 *raw, int len, __u16 port, gfp_t gfp); enum sctp_scope sctp_scope(const union sctp_addr *addr); int sctp_in_scope(struct net *net, const union sctp_addr *addr, const enum sctp_scope scope); int sctp_is_any(struct sock *sk, const union sctp_addr *addr); int sctp_is_ep_boundall(struct sock *sk); /* What type of endpoint? */ enum sctp_endpoint_type { SCTP_EP_TYPE_SOCKET, SCTP_EP_TYPE_ASSOCIATION, }; /* * A common base class to bridge the implementation view of a * socket (usually listening) endpoint versus an association's * local endpoint. * This common structure is useful for several purposes: * 1) Common interface for lookup routines. * a) Subfunctions work for either endpoint or association * b) Single interface to lookup allows hiding the lookup lock rather * than acquiring it externally. * 2) Common interface for the inbound chunk handling/state machine. * 3) Common object handling routines for reference counting, etc. * 4) Disentangle association lookup from endpoint lookup, where we * do not have to find our endpoint to find our association. * */ struct sctp_ep_common { /* Runtime type information. What kind of endpoint is this? */ enum sctp_endpoint_type type; /* Some fields to help us manage this object. * refcnt - Reference count access to this object. * dead - Do not attempt to use this object. */ refcount_t refcnt; bool dead; /* What socket does this endpoint belong to? */ struct sock *sk; /* Cache netns and it won't change once set */ struct net *net; /* This is where we receive inbound chunks. */ struct sctp_inq inqueue; /* This substructure includes the defining parameters of the * endpoint: * bind_addr.port is our shared port number. * bind_addr.address_list is our set of local IP addresses. */ struct sctp_bind_addr bind_addr; }; /* RFC Section 1.4 Key Terms * * o SCTP endpoint: The logical sender/receiver of SCTP packets. On a * multi-homed host, an SCTP endpoint is represented to its peers as a * combination of a set of eligible destination transport addresses to * which SCTP packets can be sent and a set of eligible source * transport addresses from which SCTP packets can be received. * All transport addresses used by an SCTP endpoint must use the * same port number, but can use multiple IP addresses. A transport * address used by an SCTP endpoint must not be used by another * SCTP endpoint. In other words, a transport address is unique * to an SCTP endpoint. * * From an implementation perspective, each socket has one of these. * A TCP-style socket will have exactly one association on one of * these. An UDP-style socket will have multiple associations hanging * off one of these. */ struct sctp_endpoint { /* Common substructure for endpoint and association. */ struct sctp_ep_common base; /* Fields to help us manage our entries in the hash tables. */ struct hlist_node node; int hashent; /* Associations: A list of current associations and mappings * to the data consumers for each association. This * may be in the form of a hash table or other * implementation dependent structure. The data * consumers may be process identification * information such as file descriptors, named pipe * pointer, or table pointers dependent on how SCTP * is implemented. */ /* This is really a list of struct sctp_association entries. */ struct list_head asocs; /* Cookie authentication key used by this endpoint */ struct hmac_sha256_key cookie_auth_key; /* sendbuf acct. policy. */ __u32 sndbuf_policy; /* rcvbuf acct. policy. */ __u32 rcvbuf_policy; /* SCTP-AUTH: hmacs for the endpoint encoded into parameter */ struct sctp_hmac_algo_param *auth_hmacs_list; /* SCTP-AUTH: chunks to authenticate encoded into parameter */ struct sctp_chunks_param *auth_chunk_list; /* SCTP-AUTH: endpoint shared keys */ struct list_head endpoint_shared_keys; __u16 active_key_id; __u8 ecn_enable:1, auth_enable:1, intl_enable:1, prsctp_enable:1, asconf_enable:1, reconf_enable:1; __u8 strreset_enable; struct rcu_head rcu; }; /* Recover the outer endpoint structure. */ static inline struct sctp_endpoint *sctp_ep(struct sctp_ep_common *base) { struct sctp_endpoint *ep; ep = container_of(base, struct sctp_endpoint, base); return ep; } /* These are function signatures for manipulating endpoints. */ struct sctp_endpoint *sctp_endpoint_new(struct sock *, gfp_t); void sctp_endpoint_free(struct sctp_endpoint *); void sctp_endpoint_put(struct sctp_endpoint *); int sctp_endpoint_hold(struct sctp_endpoint *ep); void sctp_endpoint_add_asoc(struct sctp_endpoint *, struct sctp_association *); struct sctp_association *sctp_endpoint_lookup_assoc( const struct sctp_endpoint *ep, const union sctp_addr *paddr, struct sctp_transport **); bool sctp_endpoint_is_peeled_off(struct sctp_endpoint *ep, const union sctp_addr *paddr); struct sctp_endpoint *sctp_endpoint_is_match(struct sctp_endpoint *ep, struct net *net, const union sctp_addr *laddr, int dif, int sdif); bool sctp_has_association(struct net *net, const union sctp_addr *laddr, const union sctp_addr *paddr, int dif, int sdif); int sctp_verify_init(struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, enum sctp_cid cid, struct sctp_init_chunk *peer_init, struct sctp_chunk *chunk, struct sctp_chunk **err_chunk); int sctp_process_init(struct sctp_association *, struct sctp_chunk *chunk, const union sctp_addr *peer, struct sctp_init_chunk *init, gfp_t gfp); __u32 sctp_generate_tag(const struct sctp_endpoint *); __u32 sctp_generate_tsn(const struct sctp_endpoint *); struct sctp_inithdr_host { __u32 init_tag; __u32 a_rwnd; __u16 num_outbound_streams; __u16 num_inbound_streams; __u32 initial_tsn; }; struct sctp_stream_priorities { /* List of priorities scheduled */ struct list_head prio_sched; /* List of streams scheduled */ struct list_head active; /* The next stream in line */ struct sctp_stream_out_ext *next; __u16 prio; __u16 users; }; struct sctp_stream_out_ext { __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; struct list_head outq; /* chunks enqueued by this stream */ union { struct { /* Scheduled streams list */ struct list_head prio_list; struct sctp_stream_priorities *prio_head; }; /* Fields used by RR scheduler */ struct { struct list_head rr_list; }; struct { struct list_head fc_list; __u32 fc_length; __u16 fc_weight; }; }; }; struct sctp_stream_out { union { __u32 mid; __u16 ssn; }; __u32 mid_uo; struct sctp_stream_out_ext *ext; __u8 state; }; struct sctp_stream_in { union { __u32 mid; __u16 ssn; }; __u32 mid_uo; __u32 fsn; __u32 fsn_uo; char pd_mode; char pd_mode_uo; }; struct sctp_stream { GENRADIX(struct sctp_stream_out) out; GENRADIX(struct sctp_stream_in) in; __u16 outcnt; __u16 incnt; /* Current stream being sent, if any */ struct sctp_stream_out *out_curr; union { /* Fields used by priority scheduler */ struct { /* List of priorities scheduled */ struct list_head prio_list; }; /* Fields used by RR scheduler */ struct { /* List of streams scheduled */ struct list_head rr_list; /* The next stream in line */ struct sctp_stream_out_ext *rr_next; }; struct { struct list_head fc_list; }; }; struct sctp_stream_interleave *si; }; static inline struct sctp_stream_out *sctp_stream_out( struct sctp_stream *stream, __u16 sid) { return genradix_ptr(&stream->out, sid); } static inline struct sctp_stream_in *sctp_stream_in( struct sctp_stream *stream, __u16 sid) { return genradix_ptr(&stream->in, sid); } #define SCTP_SO(s, i) sctp_stream_out((s), (i)) #define SCTP_SI(s, i) sctp_stream_in((s), (i)) #define SCTP_STREAM_CLOSED 0x00 #define SCTP_STREAM_OPEN 0x01 static inline __u16 sctp_datachk_len(const struct sctp_stream *stream) { return stream->si->data_chunk_len; } static inline __u16 sctp_datahdr_len(const struct sctp_stream *stream) { return stream->si->data_chunk_len - sizeof(struct sctp_chunkhdr); } static inline __u16 sctp_ftsnchk_len(const struct sctp_stream *stream) { return stream->si->ftsn_chunk_len; } static inline __u16 sctp_ftsnhdr_len(const struct sctp_stream *stream) { return stream->si->ftsn_chunk_len - sizeof(struct sctp_chunkhdr); } /* SCTP_GET_ASSOC_STATS counters */ struct sctp_priv_assoc_stats { /* Maximum observed rto in the association during subsequent * observations. Value is set to 0 if no RTO measurement took place * The transport where the max_rto was observed is returned in * obs_rto_ipaddr */ struct sockaddr_storage obs_rto_ipaddr; __u64 max_obs_rto; /* Total In and Out SACKs received and sent */ __u64 isacks; __u64 osacks; /* Total In and Out packets received and sent */ __u64 opackets; __u64 ipackets; /* Total retransmitted chunks */ __u64 rtxchunks; /* TSN received > next expected */ __u64 outofseqtsns; /* Duplicate Chunks received */ __u64 idupchunks; /* Gap Ack Blocks received */ __u64 gapcnt; /* Unordered data chunks sent and received */ __u64 ouodchunks; __u64 iuodchunks; /* Ordered data chunks sent and received */ __u64 oodchunks; __u64 iodchunks; /* Control chunks sent and received */ __u64 octrlchunks; __u64 ictrlchunks; }; /* RFC2960 * * 12. Recommended Transmission Control Block (TCB) Parameters * * This section details a recommended set of parameters that should * be contained within the TCB for an implementation. This section is * for illustrative purposes and should not be deemed as requirements * on an implementation or as an exhaustive list of all parameters * inside an SCTP TCB. Each implementation may need its own additional * parameters for optimization. */ /* Here we have information about each individual association. */ struct sctp_association { /* A base structure common to endpoint and association. * In this context, it represents the associations's view * of the local endpoint of the association. */ struct sctp_ep_common base; /* Associations on the same socket. */ struct list_head asocs; /* association id. */ sctp_assoc_t assoc_id; /* This is our parent endpoint. */ struct sctp_endpoint *ep; /* These are those association elements needed in the cookie. */ struct sctp_cookie c; /* This is all information about our peer. */ struct { /* transport_addr_list * * Peer : A list of SCTP transport addresses that the * Transport : peer is bound to. This information is derived * Address : from the INIT or INIT ACK and is used to * List : associate an inbound packet with a given * : association. Normally this information is * : hashed or keyed for quick lookup and access * : of the TCB. * : The list is also initialized with the list * : of addresses passed with the sctp_connectx() * : call. * * It is a list of SCTP_transport's. */ struct list_head transport_addr_list; /* rwnd * * Peer Rwnd : Current calculated value of the peer's rwnd. */ __u32 rwnd; /* transport_count * * Peer : A count of the number of peer addresses * Transport : in the Peer Transport Address List. * Address : * Count : */ __u16 transport_count; /* port * The transport layer port number. */ __u16 port; /* primary_path * * Primary : This is the current primary destination * Path : transport address of the peer endpoint. It * : may also specify a source transport address * : on this endpoint. * * All of these paths live on transport_addr_list. * * At the bakeoffs, we discovered that the intent of * primaryPath is that it only changes when the ULP * asks to have it changed. We add the activePath to * designate the connection we are currently using to * transmit new data and most control chunks. */ struct sctp_transport *primary_path; /* Cache the primary path address here, when we * need a an address for msg_name. */ union sctp_addr primary_addr; /* active_path * The path that we are currently using to * transmit new data and most control chunks. */ struct sctp_transport *active_path; /* retran_path * * RFC2960 6.4 Multi-homed SCTP Endpoints * ... * Furthermore, when its peer is multi-homed, an * endpoint SHOULD try to retransmit a chunk to an * active destination transport address that is * different from the last destination address to * which the DATA chunk was sent. */ struct sctp_transport *retran_path; /* Pointer to last transport I have sent on. */ struct sctp_transport *last_sent_to; /* This is the last transport I have received DATA on. */ struct sctp_transport *last_data_from; /* * Mapping An array of bits or bytes indicating which out of * Array order TSN's have been received (relative to the * Last Rcvd TSN). If no gaps exist, i.e. no out of * order packets have been received, this array * will be set to all zero. This structure may be * in the form of a circular buffer or bit array. * * Last Rcvd : This is the last TSN received in * TSN : sequence. This value is set initially by * : taking the peer's Initial TSN, received in * : the INIT or INIT ACK chunk, and subtracting * : one from it. * * Throughout most of the specification this is called the * "Cumulative TSN ACK Point". In this case, we * ignore the advice in 12.2 in favour of the term * used in the bulk of the text. This value is hidden * in tsn_map--we get it by calling sctp_tsnmap_get_ctsn(). */ struct sctp_tsnmap tsn_map; /* This mask is used to disable sending the ASCONF chunk * with specified parameter to peer. */ __be16 addip_disabled_mask; /* These are capabilities which our peer advertised. */ __u16 ecn_capable:1, /* Can peer do ECN? */ ipv4_address:1, /* Peer understands IPv4 addresses? */ ipv6_address:1, /* Peer understands IPv6 addresses? */ asconf_capable:1, /* Does peer support ADDIP? */ prsctp_capable:1, /* Can peer do PR-SCTP? */ reconf_capable:1, /* Can peer do RE-CONFIG? */ intl_capable:1, /* Can peer do INTERLEAVE */ auth_capable:1, /* Is peer doing SCTP-AUTH? */ /* sack_needed: * This flag indicates if the next received * packet is to be responded to with a * SACK. This is initialized to 0. When a packet * is received sack_cnt is incremented. If this value * reaches 2 or more, a SACK is sent and the * value is reset to 0. Note: This is used only * when no DATA chunks are received out of * order. When DATA chunks are out of order, * SACK's are not delayed (see Section 6). */ sack_needed:1, /* Do we need to sack the peer? */ sack_generation:1, zero_window_announced:1; __u32 sack_cnt; __u32 adaptation_ind; /* Adaptation Code point. */ struct sctp_inithdr_host i; void *cookie; int cookie_len; /* ADDIP Section 4.2 Upon reception of an ASCONF Chunk. * C1) ... "Peer-Serial-Number'. This value MUST be initialized to the * Initial TSN Value minus 1 */ __u32 addip_serial; /* SCTP-AUTH: We need to know pears random number, hmac list * and authenticated chunk list. All that is part of the * cookie and these are just pointers to those locations */ struct sctp_random_param *peer_random; struct sctp_chunks_param *peer_chunks; struct sctp_hmac_algo_param *peer_hmacs; } peer; /* State : A state variable indicating what state the * : association is in, i.e. COOKIE-WAIT, * : COOKIE-ECHOED, ESTABLISHED, SHUTDOWN-PENDING, * : SHUTDOWN-SENT, SHUTDOWN-RECEIVED, SHUTDOWN-ACK-SENT. * * Note: No "CLOSED" state is illustrated since if a * association is "CLOSED" its TCB SHOULD be removed. * * In this implementation we DO have a CLOSED * state which is used during initiation and shutdown. * * State takes values from SCTP_STATE_*. */ enum sctp_state state; /* Overall : The overall association error count. * Error Count : [Clear this any time I get something.] */ int overall_error_count; /* The cookie life I award for any cookie. */ ktime_t cookie_life; /* These are the association's initial, max, and min RTO values. * These values will be initialized by system defaults, but can * be modified via the SCTP_RTOINFO socket option. */ unsigned long rto_initial; unsigned long rto_max; unsigned long rto_min; /* Maximum number of new data packets that can be sent in a burst. */ int max_burst; /* This is the max_retrans value for the association. This value will * be initialized from system defaults, but can be * modified by the SCTP_ASSOCINFO socket option. */ int max_retrans; /* This is the partially failed retrans value for the transport * and will be initialized from the assocs value. This can be * changed using the SCTP_PEER_ADDR_THLDS socket option */ __u16 pf_retrans; /* Used for primary path switchover. */ __u16 ps_retrans; /* Maximum number of times the endpoint will retransmit INIT */ __u16 max_init_attempts; /* How many times have we resent an INIT? */ __u16 init_retries; /* The largest timeout or RTO value to use in attempting an INIT */ unsigned long max_init_timeo; /* Heartbeat interval: The endpoint sends out a Heartbeat chunk to * the destination address every heartbeat interval. This value * will be inherited by all new transports. */ unsigned long hbinterval; unsigned long probe_interval; __be16 encap_port; /* This is the max_retrans value for new transports in the * association. */ __u16 pathmaxrxt; __u32 flowlabel; __u8 dscp; /* Flag that path mtu update is pending */ __u8 pmtu_pending; /* Association : The smallest PMTU discovered for all of the * PMTU : peer's transport addresses. */ __u32 pathmtu; /* Flags controlling Heartbeat, SACK delay, and Path MTU Discovery. */ __u32 param_flags; __u32 sackfreq; /* SACK delay timeout */ unsigned long sackdelay; unsigned long timeouts[SCTP_NUM_TIMEOUT_TYPES]; struct timer_list timers[SCTP_NUM_TIMEOUT_TYPES]; /* Transport to which SHUTDOWN chunk was last sent. */ struct sctp_transport *shutdown_last_sent_to; /* Transport to which INIT chunk was last sent. */ struct sctp_transport *init_last_sent_to; /* How many times have we resent a SHUTDOWN */ int shutdown_retries; /* Next TSN : The next TSN number to be assigned to a new * : DATA chunk. This is sent in the INIT or INIT * : ACK chunk to the peer and incremented each * : time a DATA chunk is assigned a TSN * : (normally just prior to transmit or during * : fragmentation). */ __u32 next_tsn; /* * Last Rcvd : This is the last TSN received in sequence. This value * TSN : is set initially by taking the peer's Initial TSN, * : received in the INIT or INIT ACK chunk, and * : subtracting one from it. * * Most of RFC 2960 refers to this as the Cumulative TSN Ack Point. */ __u32 ctsn_ack_point; /* PR-SCTP Advanced.Peer.Ack.Point */ __u32 adv_peer_ack_point; /* Highest TSN that is acknowledged by incoming SACKs. */ __u32 highest_sacked; /* TSN marking the fast recovery exit point */ __u32 fast_recovery_exit; /* Flag to track the current fast recovery state */ __u8 fast_recovery; /* The number of unacknowledged data chunks. Reported through * the SCTP_STATUS sockopt. */ __u16 unack_data; /* The total number of data chunks that we've had to retransmit * as the result of a T3 timer expiration */ __u32 rtx_data_chunks; /* This is the association's receive buffer space. This value is used * to set a_rwnd field in an INIT or a SACK chunk. */ __u32 rwnd; /* This is the last advertised value of rwnd over a SACK chunk. */ __u32 a_rwnd; /* Number of bytes by which the rwnd has slopped. The rwnd is allowed * to slop over a maximum of the association's frag_point. */ __u32 rwnd_over; /* Keeps treack of rwnd pressure. This happens when we have * a window, but not receive buffer (i.e small packets). This one * is releases slowly (1 PMTU at a time ). */ __u32 rwnd_press; /* This is the sndbuf size in use for the association. * This corresponds to the sndbuf size for the association, * as specified in the sk->sndbuf. */ int sndbuf_used; /* This is the amount of memory that this association has allocated * in the receive path at any given time. */ atomic_t rmem_alloc; /* This is the wait queue head for send requests waiting on * the association sndbuf space. */ wait_queue_head_t wait; /* The message size at which SCTP fragmentation will occur. */ __u32 frag_point; __u32 user_frag; /* Counter used to count INIT errors. */ int init_err_counter; /* Count the number of INIT cycles (for doubling timeout). */ int init_cycle; /* Default send parameters. */ __u16 default_stream; __u16 default_flags; __u32 default_ppid; __u32 default_context; __u32 default_timetolive; /* Default receive parameters */ __u32 default_rcv_context; /* Stream arrays */ struct sctp_stream stream; /* All outbound chunks go through this structure. */ struct sctp_outq outqueue; /* A smart pipe that will handle reordering and fragmentation, * as well as handle passing events up to the ULP. */ struct sctp_ulpq ulpq; /* Last TSN that caused an ECNE Chunk to be sent. */ __u32 last_ecne_tsn; /* Last TSN that caused a CWR Chunk to be sent. */ __u32 last_cwr_tsn; /* How many duplicated TSNs have we seen? */ int numduptsns; /* These are to support * "SCTP Extensions for Dynamic Reconfiguration of IP Addresses * and Enforcement of Flow and Message Limits" * <draft-ietf-tsvwg-addip-sctp-02.txt> * or "ADDIP" for short. */ /* ADDIP Section 4.1.1 Congestion Control of ASCONF Chunks * * R1) One and only one ASCONF Chunk MAY be in transit and * unacknowledged at any one time. If a sender, after sending * an ASCONF chunk, decides it needs to transfer another * ASCONF Chunk, it MUST wait until the ASCONF-ACK Chunk * returns from the previous ASCONF Chunk before sending a * subsequent ASCONF. Note this restriction binds each side, * so at any time two ASCONF may be in-transit on any given * association (one sent from each endpoint). * * [This is our one-and-only-one ASCONF in flight. If we do * not have an ASCONF in flight, this is NULL.] */ struct sctp_chunk *addip_last_asconf; /* ADDIP Section 5.2 Upon reception of an ASCONF Chunk. * * This is needed to implement items E1 - E4 of the updated * spec. Here is the justification: * * Since the peer may bundle multiple ASCONF chunks toward us, * we now need the ability to cache multiple ACKs. The section * describes in detail how they are cached and cleaned up. */ struct list_head asconf_ack_list; /* These ASCONF chunks are waiting to be sent. * * These chunks can't be pushed to outqueue until receiving * ASCONF_ACK for the previous ASCONF indicated by * addip_last_asconf, so as to guarantee that only one ASCONF * is in flight at any time. * * ADDIP Section 4.1.1 Congestion Control of ASCONF Chunks * * In defining the ASCONF Chunk transfer procedures, it is * essential that these transfers MUST NOT cause congestion * within the network. To achieve this, we place these * restrictions on the transfer of ASCONF Chunks: * * R1) One and only one ASCONF Chunk MAY be in transit and * unacknowledged at any one time. If a sender, after sending * an ASCONF chunk, decides it needs to transfer another * ASCONF Chunk, it MUST wait until the ASCONF-ACK Chunk * returns from the previous ASCONF Chunk before sending a * subsequent ASCONF. Note this restriction binds each side, * so at any time two ASCONF may be in-transit on any given * association (one sent from each endpoint). * * * [I really think this is EXACTLY the sort of intelligence * which already resides in sctp_outq. Please move this * queue and its supporting logic down there. --piggy] */ struct list_head addip_chunk_list; /* ADDIP Section 4.1 ASCONF Chunk Procedures * * A2) A serial number should be assigned to the Chunk. The * serial number SHOULD be a monotonically increasing * number. The serial number SHOULD be initialized at * the start of the association to the same value as the * Initial TSN and every time a new ASCONF chunk is created * it is incremented by one after assigning the serial number * to the newly created chunk. * * ADDIP * 3.1.1 Address/Stream Configuration Change Chunk (ASCONF) * * Serial Number : 32 bits (unsigned integer) * * This value represents a Serial Number for the ASCONF * Chunk. The valid range of Serial Number is from 0 to * 4294967295 (2^32 - 1). Serial Numbers wrap back to 0 * after reaching 4294967295. */ __u32 addip_serial; int src_out_of_asoc_ok; union sctp_addr *asconf_addr_del_pending; struct sctp_transport *new_transport; /* SCTP AUTH: list of the endpoint shared keys. These * keys are provided out of band by the user application * and can't change during the lifetime of the association */ struct list_head endpoint_shared_keys; /* SCTP AUTH: * The current generated association shared key (secret) */ struct sctp_auth_bytes *asoc_shared_key; struct sctp_shared_key *shkey; /* SCTP AUTH: hmac id of the first peer requested algorithm * that we support. */ __u16 default_hmac_id; __u16 active_key_id; __u8 need_ecne:1, /* Need to send an ECNE Chunk? */ temp:1, /* Is it a temporary association? */ pf_expose:2, /* Expose pf state? */ force_delay:1; __u8 strreset_enable; __u8 strreset_outstanding; /* request param count on the fly */ __u32 strreset_outseq; /* Update after receiving response */ __u32 strreset_inseq; /* Update after receiving request */ __u32 strreset_result[2]; /* save the results of last 2 responses */ struct sctp_chunk *strreset_chunk; /* save request chunk */ struct sctp_priv_assoc_stats stats; int sent_cnt_removable; __u16 subscribe; __u64 abandoned_unsent[SCTP_PR_INDEX(MAX) + 1]; __u64 abandoned_sent[SCTP_PR_INDEX(MAX) + 1]; /* Security identifiers from incoming (INIT). These are set by * security_sctp_assoc_request(). These will only be used by * SCTP TCP type sockets and peeled off connections as they * cause a new socket to be generated. security_sctp_sk_clone() * will then plug these into the new socket. */ u32 secid; u32 peer_secid; struct rcu_head rcu; }; /* An eyecatcher for determining if we are really looking at an * association data structure. */ enum { SCTP_ASSOC_EYECATCHER = 0xa550c123, }; /* Recover the outer association structure. */ static inline struct sctp_association *sctp_assoc(struct sctp_ep_common *base) { struct sctp_association *asoc; asoc = container_of(base, struct sctp_association, base); return asoc; } /* These are function signatures for manipulating associations. */ struct sctp_association * sctp_association_new(const struct sctp_endpoint *ep, const struct sock *sk, enum sctp_scope scope, gfp_t gfp); void sctp_association_free(struct sctp_association *); void sctp_association_put(struct sctp_association *); void sctp_association_hold(struct sctp_association *); struct sctp_transport *sctp_assoc_choose_alter_transport( struct sctp_association *, struct sctp_transport *); void sctp_assoc_update_retran_path(struct sctp_association *); struct sctp_transport *sctp_assoc_lookup_paddr(const struct sctp_association *, const union sctp_addr *); int sctp_assoc_lookup_laddr(struct sctp_association *asoc, const union sctp_addr *laddr); struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *, const union sctp_addr *address, const gfp_t gfp, const int peer_state); void sctp_assoc_rm_peer(struct sctp_association *asoc, struct sctp_transport *peer); void sctp_assoc_control_transport(struct sctp_association *asoc, struct sctp_transport *transport, enum sctp_transport_cmd command, sctp_sn_error_t error); struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *, __u32); void sctp_assoc_migrate(struct sctp_association *, struct sock *); int sctp_assoc_update(struct sctp_association *old, struct sctp_association *new); __u32 sctp_association_get_next_tsn(struct sctp_association *); void sctp_assoc_update_frag_point(struct sctp_association *asoc); void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu); void sctp_assoc_sync_pmtu(struct sctp_association *asoc); void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int); void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int); void sctp_assoc_set_primary(struct sctp_association *, struct sctp_transport *); void sctp_assoc_del_nonprimary_peers(struct sctp_association *, struct sctp_transport *); int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, enum sctp_scope scope, gfp_t gfp); int sctp_assoc_set_bind_addr_from_cookie(struct sctp_association *, struct sctp_cookie*, gfp_t gfp); int sctp_assoc_set_id(struct sctp_association *, gfp_t); void sctp_assoc_clean_asconf_ack_cache(const struct sctp_association *asoc); struct sctp_chunk *sctp_assoc_lookup_asconf_ack( const struct sctp_association *asoc, __be32 serial); void sctp_asconf_queue_teardown(struct sctp_association *asoc); int sctp_cmp_addr_exact(const union sctp_addr *ss1, const union sctp_addr *ss2); struct sctp_chunk *sctp_get_ecne_prepend(struct sctp_association *asoc); /* A convenience structure to parse out SCTP specific CMSGs. */ struct sctp_cmsgs { struct sctp_initmsg *init; struct sctp_sndrcvinfo *srinfo; struct sctp_sndinfo *sinfo; struct sctp_prinfo *prinfo; struct sctp_authinfo *authinfo; struct msghdr *addrs_msg; }; /* Structure for tracking memory objects */ struct sctp_dbg_objcnt_entry { char *label; atomic_t *counter; }; #endif /* __sctp_structs_h__ */ |
| 163 165 164 165 165 6 159 96 12 96 62 7 62 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 | // SPDX-License-Identifier: GPL-2.0-only /* (C) 1999-2001 Paul `Rusty' Russell * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/types.h> #include <linux/ipv6.h> #include <linux/in6.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/icmp.h> #include <linux/rcupdate.h> #include <linux/sysctl.h> #include <net/ipv6_frag.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_core.h> #include <net/netfilter/ipv6/nf_conntrack_ipv6.h> #endif #include <net/netfilter/nf_conntrack_zones.h> #include <net/netfilter/ipv6/nf_defrag_ipv6.h> static DEFINE_MUTEX(defrag6_mutex); static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum, struct sk_buff *skb) { u16 zone_id = NF_CT_DEFAULT_ZONE_ID; #if IS_ENABLED(CONFIG_NF_CONNTRACK) if (skb_nfct(skb)) { enum ip_conntrack_info ctinfo; const struct nf_conn *ct = nf_ct_get(skb, &ctinfo); zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo)); } #endif if (nf_bridge_in_prerouting(skb)) return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id; if (hooknum == NF_INET_PRE_ROUTING) return IP6_DEFRAG_CONNTRACK_IN + zone_id; else return IP6_DEFRAG_CONNTRACK_OUT + zone_id; } static unsigned int ipv6_defrag(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { int err; #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Previously seen (loopback)? */ if (skb_nfct(skb) && !nf_ct_is_template((struct nf_conn *)skb_nfct(skb))) return NF_ACCEPT; if (skb->_nfct == IP_CT_UNTRACKED) return NF_ACCEPT; #endif err = nf_ct_frag6_gather(state->net, skb, nf_ct6_defrag_user(state->hook, skb)); /* queued */ if (err == -EINPROGRESS) return NF_STOLEN; return err == 0 ? NF_ACCEPT : NF_DROP; } static const struct nf_hook_ops ipv6_defrag_ops[] = { { .hook = ipv6_defrag, .pf = NFPROTO_IPV6, .hooknum = NF_INET_PRE_ROUTING, .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, }, { .hook = ipv6_defrag, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_OUT, .priority = NF_IP6_PRI_CONNTRACK_DEFRAG, }, }; static void __net_exit defrag6_net_exit(struct net *net) { if (net->nf.defrag_ipv6_users) { nf_unregister_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); net->nf.defrag_ipv6_users = 0; } } static const struct nf_defrag_hook defrag_hook = { .owner = THIS_MODULE, .enable = nf_defrag_ipv6_enable, .disable = nf_defrag_ipv6_disable, }; static struct pernet_operations defrag6_net_ops = { .exit = defrag6_net_exit, }; static int __init nf_defrag_init(void) { int ret = 0; ret = nf_ct_frag6_init(); if (ret < 0) { pr_err("nf_defrag_ipv6: can't initialize frag6.\n"); return ret; } ret = register_pernet_subsys(&defrag6_net_ops); if (ret < 0) { pr_err("nf_defrag_ipv6: can't register pernet ops\n"); goto cleanup_frag6; } rcu_assign_pointer(nf_defrag_v6_hook, &defrag_hook); return ret; cleanup_frag6: nf_ct_frag6_cleanup(); return ret; } static void __exit nf_defrag_fini(void) { rcu_assign_pointer(nf_defrag_v6_hook, NULL); unregister_pernet_subsys(&defrag6_net_ops); nf_ct_frag6_cleanup(); } int nf_defrag_ipv6_enable(struct net *net) { int err = 0; mutex_lock(&defrag6_mutex); if (net->nf.defrag_ipv6_users == UINT_MAX) { err = -EOVERFLOW; goto out_unlock; } if (net->nf.defrag_ipv6_users) { net->nf.defrag_ipv6_users++; goto out_unlock; } err = nf_register_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); if (err == 0) net->nf.defrag_ipv6_users = 1; out_unlock: mutex_unlock(&defrag6_mutex); return err; } EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable); void nf_defrag_ipv6_disable(struct net *net) { mutex_lock(&defrag6_mutex); if (net->nf.defrag_ipv6_users) { net->nf.defrag_ipv6_users--; if (net->nf.defrag_ipv6_users == 0) nf_unregister_net_hooks(net, ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops)); } mutex_unlock(&defrag6_mutex); } EXPORT_SYMBOL_GPL(nf_defrag_ipv6_disable); module_init(nf_defrag_init); module_exit(nf_defrag_fini); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("IPv6 defragmentation support"); |
| 10 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 | // SPDX-License-Identifier: GPL-2.0 /* * This contains functions for filename crypto management * * Copyright (C) 2015, Google, Inc. * Copyright (C) 2015, Motorola Mobility * * Written by Uday Savagaonkar, 2014. * Modified by Jaegeuk Kim, 2015. * * This has not yet undergone a rigorous security audit. */ #include <crypto/sha2.h> #include <crypto/skcipher.h> #include <linux/export.h> #include <linux/namei.h> #include <linux/scatterlist.h> #include <linux/base64.h> #include "fscrypt_private.h" /* * The minimum message length (input and output length), in bytes, for all * filenames encryption modes. Filenames shorter than this will be zero-padded * before being encrypted. */ #define FSCRYPT_FNAME_MIN_MSG_LEN 16 /* * struct fscrypt_nokey_name - identifier for directory entry when key is absent * * When userspace lists an encrypted directory without access to the key, the * filesystem must present a unique "no-key name" for each filename that allows * it to find the directory entry again if requested. Naively, that would just * mean using the ciphertext filenames. However, since the ciphertext filenames * can contain illegal characters ('\0' and '/'), they must be encoded in some * way. We use base64url. But that can cause names to exceed NAME_MAX (255 * bytes), so we also need to use a strong hash to abbreviate long names. * * The filesystem may also need another kind of hash, the "dirhash", to quickly * find the directory entry. Since filesystems normally compute the dirhash * over the on-disk filename (i.e. the ciphertext), it's not computable from * no-key names that abbreviate the ciphertext using the strong hash to fit in * NAME_MAX. It's also not computable if it's a keyed hash taken over the * plaintext (but it may still be available in the on-disk directory entry); * casefolded directories use this type of dirhash. At least in these cases, * each no-key name must include the name's dirhash too. * * To meet all these requirements, we base64url-encode the following * variable-length structure. It contains the dirhash, or 0's if the filesystem * didn't provide one; up to 149 bytes of the ciphertext name; and for * ciphertexts longer than 149 bytes, also the SHA-256 of the remaining bytes. * * This ensures that each no-key name contains everything needed to find the * directory entry again, contains only legal characters, doesn't exceed * NAME_MAX, is unambiguous unless there's a SHA-256 collision, and that we only * take the performance hit of SHA-256 on very long filenames (which are rare). */ struct fscrypt_nokey_name { u32 dirhash[2]; u8 bytes[149]; u8 sha256[SHA256_DIGEST_SIZE]; }; /* 189 bytes => 252 bytes base64url-encoded, which is <= NAME_MAX (255) */ /* * Decoded size of max-size no-key name, i.e. a name that was abbreviated using * the strong hash and thus includes the 'sha256' field. This isn't simply * sizeof(struct fscrypt_nokey_name), as the padding at the end isn't included. */ #define FSCRYPT_NOKEY_NAME_MAX offsetofend(struct fscrypt_nokey_name, sha256) /* Encoded size of max-size no-key name */ #define FSCRYPT_NOKEY_NAME_MAX_ENCODED \ BASE64_CHARS(FSCRYPT_NOKEY_NAME_MAX) static inline bool fscrypt_is_dot_dotdot(const struct qstr *str) { return name_is_dot_dotdot(str->name, str->len); } /** * fscrypt_fname_encrypt() - encrypt a filename * @inode: inode of the parent directory (for regular filenames) * or of the symlink (for symlink targets). Key must already be * set up. * @iname: the filename to encrypt * @out: (output) the encrypted filename * @olen: size of the encrypted filename. It must be at least @iname->len. * Any extra space is filled with NUL padding before encryption. * * Return: 0 on success, -errno on failure */ int fscrypt_fname_encrypt(const struct inode *inode, const struct qstr *iname, u8 *out, unsigned int olen) { const struct fscrypt_inode_info *ci = fscrypt_get_inode_info_raw(inode); struct crypto_sync_skcipher *tfm = ci->ci_enc_key.tfm; SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm); union fscrypt_iv iv; struct scatterlist sg; int err; /* * Copy the filename to the output buffer for encrypting in-place and * pad it with the needed number of NUL bytes. */ if (WARN_ON_ONCE(olen < iname->len)) return -ENOBUFS; memcpy(out, iname->name, iname->len); memset(out + iname->len, 0, olen - iname->len); fscrypt_generate_iv(&iv, 0, ci); skcipher_request_set_callback( req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); sg_init_one(&sg, out, olen); skcipher_request_set_crypt(req, &sg, &sg, olen, &iv); err = crypto_skcipher_encrypt(req); if (err) fscrypt_err(inode, "Filename encryption failed: %d", err); return err; } EXPORT_SYMBOL_GPL(fscrypt_fname_encrypt); /** * fname_decrypt() - decrypt a filename * @inode: inode of the parent directory (for regular filenames) * or of the symlink (for symlink targets) * @iname: the encrypted filename to decrypt * @oname: (output) the decrypted filename. The caller must have allocated * enough space for this, e.g. using fscrypt_fname_alloc_buffer(). * * Return: 0 on success, -errno on failure */ static int fname_decrypt(const struct inode *inode, const struct fscrypt_str *iname, struct fscrypt_str *oname) { const struct fscrypt_inode_info *ci = fscrypt_get_inode_info_raw(inode); struct crypto_sync_skcipher *tfm = ci->ci_enc_key.tfm; SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm); union fscrypt_iv iv; struct scatterlist src_sg, dst_sg; int err; fscrypt_generate_iv(&iv, 0, ci); skcipher_request_set_callback( req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL); sg_init_one(&src_sg, iname->name, iname->len); sg_init_one(&dst_sg, oname->name, oname->len); skcipher_request_set_crypt(req, &src_sg, &dst_sg, iname->len, &iv); err = crypto_skcipher_decrypt(req); if (err) { fscrypt_err(inode, "Filename decryption failed: %d", err); return err; } oname->len = strnlen(oname->name, iname->len); return 0; } bool __fscrypt_fname_encrypted_size(const union fscrypt_policy *policy, u32 orig_len, u32 max_len, u32 *encrypted_len_ret) { int padding = 4 << (fscrypt_policy_flags(policy) & FSCRYPT_POLICY_FLAGS_PAD_MASK); u32 encrypted_len; if (orig_len > max_len) return false; encrypted_len = max_t(u32, orig_len, FSCRYPT_FNAME_MIN_MSG_LEN); encrypted_len = round_up(encrypted_len, padding); *encrypted_len_ret = min(encrypted_len, max_len); return true; } /** * fscrypt_fname_encrypted_size() - calculate length of encrypted filename * @inode: parent inode of dentry name being encrypted. Key must * already be set up. * @orig_len: length of the original filename * @max_len: maximum length to return * @encrypted_len_ret: where calculated length should be returned (on success) * * Filenames that are shorter than the maximum length may have their lengths * increased slightly by encryption, due to padding that is applied. * * Return: false if the orig_len is greater than max_len. Otherwise, true and * fill out encrypted_len_ret with the length (up to max_len). */ bool fscrypt_fname_encrypted_size(const struct inode *inode, u32 orig_len, u32 max_len, u32 *encrypted_len_ret) { const struct fscrypt_inode_info *ci = fscrypt_get_inode_info_raw(inode); return __fscrypt_fname_encrypted_size(&ci->ci_policy, orig_len, max_len, encrypted_len_ret); } EXPORT_SYMBOL_GPL(fscrypt_fname_encrypted_size); /** * fscrypt_fname_alloc_buffer() - allocate a buffer for presented filenames * @max_encrypted_len: maximum length of encrypted filenames the buffer will be * used to present * @crypto_str: (output) buffer to allocate * * Allocate a buffer that is large enough to hold any decrypted or encoded * filename (null-terminated), for the given maximum encrypted filename length. * * Return: 0 on success, -errno on failure */ int fscrypt_fname_alloc_buffer(u32 max_encrypted_len, struct fscrypt_str *crypto_str) { u32 max_presented_len = max_t(u32, FSCRYPT_NOKEY_NAME_MAX_ENCODED, max_encrypted_len); crypto_str->name = kmalloc(max_presented_len + 1, GFP_NOFS); if (!crypto_str->name) return -ENOMEM; crypto_str->len = max_presented_len; return 0; } EXPORT_SYMBOL(fscrypt_fname_alloc_buffer); /** * fscrypt_fname_free_buffer() - free a buffer for presented filenames * @crypto_str: the buffer to free * * Free a buffer that was allocated by fscrypt_fname_alloc_buffer(). */ void fscrypt_fname_free_buffer(struct fscrypt_str *crypto_str) { if (!crypto_str) return; kfree(crypto_str->name); crypto_str->name = NULL; } EXPORT_SYMBOL(fscrypt_fname_free_buffer); /** * fscrypt_fname_disk_to_usr() - convert an encrypted filename to * user-presentable form * @inode: inode of the parent directory (for regular filenames) * or of the symlink (for symlink targets) * @hash: first part of the name's dirhash, if applicable. This only needs to * be provided if the filename is located in an indexed directory whose * encryption key may be unavailable. Not needed for symlink targets. * @minor_hash: second part of the name's dirhash, if applicable * @iname: encrypted filename to convert. May also be "." or "..", which * aren't actually encrypted. * @oname: output buffer for the user-presentable filename. The caller must * have allocated enough space for this, e.g. using * fscrypt_fname_alloc_buffer(). * * If the key is available, we'll decrypt the disk name. Otherwise, we'll * encode it for presentation in fscrypt_nokey_name format. * See struct fscrypt_nokey_name for details. * * Return: 0 on success, -errno on failure */ int fscrypt_fname_disk_to_usr(const struct inode *inode, u32 hash, u32 minor_hash, const struct fscrypt_str *iname, struct fscrypt_str *oname) { const struct qstr qname = FSTR_TO_QSTR(iname); struct fscrypt_nokey_name nokey_name; u32 size; /* size of the unencoded no-key name */ if (fscrypt_is_dot_dotdot(&qname)) { oname->name[0] = '.'; oname->name[iname->len - 1] = '.'; oname->len = iname->len; return 0; } if (iname->len < FSCRYPT_FNAME_MIN_MSG_LEN) return -EUCLEAN; if (fscrypt_has_encryption_key(inode)) return fname_decrypt(inode, iname, oname); /* * Sanity check that struct fscrypt_nokey_name doesn't have padding * between fields and that its encoded size never exceeds NAME_MAX. */ BUILD_BUG_ON(offsetofend(struct fscrypt_nokey_name, dirhash) != offsetof(struct fscrypt_nokey_name, bytes)); BUILD_BUG_ON(offsetofend(struct fscrypt_nokey_name, bytes) != offsetof(struct fscrypt_nokey_name, sha256)); BUILD_BUG_ON(FSCRYPT_NOKEY_NAME_MAX_ENCODED > NAME_MAX); nokey_name.dirhash[0] = hash; nokey_name.dirhash[1] = minor_hash; if (iname->len <= sizeof(nokey_name.bytes)) { memcpy(nokey_name.bytes, iname->name, iname->len); size = offsetof(struct fscrypt_nokey_name, bytes[iname->len]); } else { memcpy(nokey_name.bytes, iname->name, sizeof(nokey_name.bytes)); /* Compute strong hash of remaining part of name. */ sha256(&iname->name[sizeof(nokey_name.bytes)], iname->len - sizeof(nokey_name.bytes), nokey_name.sha256); size = FSCRYPT_NOKEY_NAME_MAX; } oname->len = base64_encode((const u8 *)&nokey_name, size, oname->name, false, BASE64_URLSAFE); return 0; } EXPORT_SYMBOL(fscrypt_fname_disk_to_usr); /** * fscrypt_setup_filename() - prepare to search a possibly encrypted directory * @dir: the directory that will be searched * @iname: the user-provided filename being searched for * @lookup: 1 if we're allowed to proceed without the key because it's * ->lookup() or we're finding the dir_entry for deletion; 0 if we cannot * proceed without the key because we're going to create the dir_entry. * @fname: the filename information to be filled in * * Given a user-provided filename @iname, this function sets @fname->disk_name * to the name that would be stored in the on-disk directory entry, if possible. * If the directory is unencrypted this is simply @iname. Else, if we have the * directory's encryption key, then @iname is the plaintext, so we encrypt it to * get the disk_name. * * Else, for keyless @lookup operations, @iname should be a no-key name, so we * decode it to get the struct fscrypt_nokey_name. Non-@lookup operations will * be impossible in this case, so we fail them with ENOKEY. * * If successful, fscrypt_free_filename() must be called later to clean up. * * Return: 0 on success, -errno on failure */ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname, int lookup, struct fscrypt_name *fname) { struct fscrypt_nokey_name *nokey_name; int ret; memset(fname, 0, sizeof(struct fscrypt_name)); fname->usr_fname = iname; if (!IS_ENCRYPTED(dir) || fscrypt_is_dot_dotdot(iname)) { fname->disk_name.name = (unsigned char *)iname->name; fname->disk_name.len = iname->len; return 0; } ret = fscrypt_get_encryption_info(dir, lookup); if (ret) return ret; if (fscrypt_has_encryption_key(dir)) { if (!fscrypt_fname_encrypted_size(dir, iname->len, NAME_MAX, &fname->crypto_buf.len)) return -ENAMETOOLONG; fname->crypto_buf.name = kmalloc(fname->crypto_buf.len, GFP_NOFS); if (!fname->crypto_buf.name) return -ENOMEM; ret = fscrypt_fname_encrypt(dir, iname, fname->crypto_buf.name, fname->crypto_buf.len); if (ret) goto errout; fname->disk_name.name = fname->crypto_buf.name; fname->disk_name.len = fname->crypto_buf.len; return 0; } if (!lookup) return -ENOKEY; fname->is_nokey_name = true; /* * We don't have the key and we are doing a lookup; decode the * user-supplied name */ if (iname->len > FSCRYPT_NOKEY_NAME_MAX_ENCODED) return -ENOENT; fname->crypto_buf.name = kmalloc(FSCRYPT_NOKEY_NAME_MAX, GFP_KERNEL); if (fname->crypto_buf.name == NULL) return -ENOMEM; ret = base64_decode(iname->name, iname->len, fname->crypto_buf.name, false, BASE64_URLSAFE); if (ret < (int)offsetof(struct fscrypt_nokey_name, bytes[1]) || (ret > offsetof(struct fscrypt_nokey_name, sha256) && ret != FSCRYPT_NOKEY_NAME_MAX)) { ret = -ENOENT; goto errout; } fname->crypto_buf.len = ret; nokey_name = (void *)fname->crypto_buf.name; fname->hash = nokey_name->dirhash[0]; fname->minor_hash = nokey_name->dirhash[1]; if (ret != FSCRYPT_NOKEY_NAME_MAX) { /* The full ciphertext filename is available. */ fname->disk_name.name = nokey_name->bytes; fname->disk_name.len = ret - offsetof(struct fscrypt_nokey_name, bytes); } return 0; errout: kfree(fname->crypto_buf.name); return ret; } EXPORT_SYMBOL(fscrypt_setup_filename); /** * fscrypt_match_name() - test whether the given name matches a directory entry * @fname: the name being searched for * @de_name: the name from the directory entry * @de_name_len: the length of @de_name in bytes * * Normally @fname->disk_name will be set, and in that case we simply compare * that to the name stored in the directory entry. The only exception is that * if we don't have the key for an encrypted directory and the name we're * looking for is very long, then we won't have the full disk_name and instead * we'll need to match against a fscrypt_nokey_name that includes a strong hash. * * Return: %true if the name matches, otherwise %false. */ bool fscrypt_match_name(const struct fscrypt_name *fname, const u8 *de_name, u32 de_name_len) { const struct fscrypt_nokey_name *nokey_name = (const void *)fname->crypto_buf.name; u8 digest[SHA256_DIGEST_SIZE]; if (likely(fname->disk_name.name)) { if (de_name_len != fname->disk_name.len) return false; return !memcmp(de_name, fname->disk_name.name, de_name_len); } if (de_name_len <= sizeof(nokey_name->bytes)) return false; if (memcmp(de_name, nokey_name->bytes, sizeof(nokey_name->bytes))) return false; sha256(&de_name[sizeof(nokey_name->bytes)], de_name_len - sizeof(nokey_name->bytes), digest); return !memcmp(digest, nokey_name->sha256, sizeof(digest)); } EXPORT_SYMBOL_GPL(fscrypt_match_name); /** * fscrypt_fname_siphash() - calculate the SipHash of a filename * @dir: the parent directory * @name: the filename to calculate the SipHash of * * Given a plaintext filename @name and a directory @dir which uses SipHash as * its dirhash method and has had its fscrypt key set up, this function * calculates the SipHash of that name using the directory's secret dirhash key. * * Return: the SipHash of @name using the hash key of @dir */ u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name) { const struct fscrypt_inode_info *ci = fscrypt_get_inode_info_raw(dir); WARN_ON_ONCE(!ci->ci_dirhash_key_initialized); return siphash(name->name, name->len, &ci->ci_dirhash_key); } EXPORT_SYMBOL_GPL(fscrypt_fname_siphash); /* * Validate dentries in encrypted directories to make sure we aren't potentially * caching stale dentries after a key has been added. */ int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { int err; /* * Plaintext names are always valid, since fscrypt doesn't support * reverting to no-key names without evicting the directory's inode * -- which implies eviction of the dentries in the directory. */ if (!(dentry->d_flags & DCACHE_NOKEY_NAME)) return 1; /* * No-key name; valid if the directory's key is still unavailable. * * Note in RCU mode we have to bail if we get here - * fscrypt_get_encryption_info() may block. */ if (flags & LOOKUP_RCU) return -ECHILD; /* * Pass allow_unsupported=true, so that files with an unsupported * encryption policy can be deleted. */ err = fscrypt_get_encryption_info(dir, true); if (err < 0) return err; return !fscrypt_has_encryption_key(dir); } EXPORT_SYMBOL_GPL(fscrypt_d_revalidate); |
| 615 613 615 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 | // SPDX-License-Identifier: GPL-2.0-only /* * Landlock - Credential hooks * * Copyright © 2017-2020 Mickaël Salaün <mic@digikod.net> * Copyright © 2018-2020 ANSSI * Copyright © 2024-2025 Microsoft Corporation */ #include <linux/binfmts.h> #include <linux/cred.h> #include <linux/lsm_hooks.h> #include "common.h" #include "cred.h" #include "ruleset.h" #include "setup.h" static void hook_cred_transfer(struct cred *const new, const struct cred *const old) { const struct landlock_cred_security *const old_llcred = landlock_cred(old); landlock_get_ruleset(old_llcred->domain); *landlock_cred(new) = *old_llcred; } static int hook_cred_prepare(struct cred *const new, const struct cred *const old, const gfp_t gfp) { hook_cred_transfer(new, old); return 0; } static void hook_cred_free(struct cred *const cred) { struct landlock_ruleset *const dom = landlock_cred(cred)->domain; if (dom) landlock_put_ruleset_deferred(dom); } #ifdef CONFIG_AUDIT static int hook_bprm_creds_for_exec(struct linux_binprm *const bprm) { /* Resets for each execution. */ landlock_cred(bprm->cred)->domain_exec = 0; return 0; } #endif /* CONFIG_AUDIT */ static struct security_hook_list landlock_hooks[] __ro_after_init = { LSM_HOOK_INIT(cred_prepare, hook_cred_prepare), LSM_HOOK_INIT(cred_transfer, hook_cred_transfer), LSM_HOOK_INIT(cred_free, hook_cred_free), #ifdef CONFIG_AUDIT LSM_HOOK_INIT(bprm_creds_for_exec, hook_bprm_creds_for_exec), #endif /* CONFIG_AUDIT */ }; __init void landlock_add_cred_hooks(void) { security_add_hooks(landlock_hooks, ARRAY_SIZE(landlock_hooks), &landlock_lsmid); } |
| 560 25 110 829 1146 1144 829 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_LWTUNNEL_H #define __NET_LWTUNNEL_H 1 #include <linux/lwtunnel.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/types.h> #include <net/route.h> #define LWTUNNEL_HASH_BITS 7 #define LWTUNNEL_HASH_SIZE (1 << LWTUNNEL_HASH_BITS) /* lw tunnel state flags */ #define LWTUNNEL_STATE_OUTPUT_REDIRECT BIT(0) #define LWTUNNEL_STATE_INPUT_REDIRECT BIT(1) #define LWTUNNEL_STATE_XMIT_REDIRECT BIT(2) /* LWTUNNEL_XMIT_CONTINUE should be distinguishable from dst_output return * values (NET_XMIT_xxx and NETDEV_TX_xxx in linux/netdevice.h) for safety. */ enum { LWTUNNEL_XMIT_DONE, LWTUNNEL_XMIT_CONTINUE = 0x100, }; struct lwtunnel_state { __u16 type; __u16 flags; __u16 headroom; atomic_t refcnt; int (*orig_output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*orig_input)(struct sk_buff *); struct rcu_head rcu; __u8 data[]; }; struct lwtunnel_encap_ops { int (*build_state)(struct net *net, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **ts, struct netlink_ext_ack *extack); void (*destroy_state)(struct lwtunnel_state *lws); int (*output)(struct net *net, struct sock *sk, struct sk_buff *skb); int (*input)(struct sk_buff *skb); int (*fill_encap)(struct sk_buff *skb, struct lwtunnel_state *lwtstate); int (*get_encap_size)(struct lwtunnel_state *lwtstate); int (*cmp_encap)(struct lwtunnel_state *a, struct lwtunnel_state *b); int (*xmit)(struct sk_buff *skb); struct module *owner; }; #ifdef CONFIG_LWTUNNEL DECLARE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled); void lwtstate_free(struct lwtunnel_state *lws); static inline struct lwtunnel_state * lwtstate_get(struct lwtunnel_state *lws) { if (lws) atomic_inc(&lws->refcnt); return lws; } static inline void lwtstate_put(struct lwtunnel_state *lws) { if (!lws) return; if (atomic_dec_and_test(&lws->refcnt)) lwtstate_free(lws); } static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_OUTPUT_REDIRECT)) return true; return false; } static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_INPUT_REDIRECT)) return true; return false; } static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) { if (lwtstate && (lwtstate->flags & LWTUNNEL_STATE_XMIT_REDIRECT)) return true; return false; } static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, unsigned int mtu) { if ((lwtunnel_xmit_redirect(lwtstate) || lwtunnel_output_redirect(lwtstate)) && lwtstate->headroom < mtu) return lwtstate->headroom; return 0; } int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, struct netlink_ext_ack *extack); int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack); int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr); int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate); struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len); int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b); int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb); int lwtunnel_input(struct sk_buff *skb); int lwtunnel_xmit(struct sk_buff *skb); int bpf_lwt_push_ip_encap(struct sk_buff *skb, void *hdr, u32 len, bool ingress); static inline void lwtunnel_set_redirect(struct dst_entry *dst) { if (lwtunnel_output_redirect(dst->lwtstate)) { dst->lwtstate->orig_output = READ_ONCE(dst->output); WRITE_ONCE(dst->output, lwtunnel_output); } if (lwtunnel_input_redirect(dst->lwtstate)) { dst->lwtstate->orig_input = READ_ONCE(dst->input); WRITE_ONCE(dst->input, lwtunnel_input); } } #else static inline void lwtstate_free(struct lwtunnel_state *lws) { } static inline struct lwtunnel_state * lwtstate_get(struct lwtunnel_state *lws) { return lws; } static inline void lwtstate_put(struct lwtunnel_state *lws) { } static inline bool lwtunnel_output_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline bool lwtunnel_input_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline bool lwtunnel_xmit_redirect(struct lwtunnel_state *lwtstate) { return false; } static inline void lwtunnel_set_redirect(struct dst_entry *dst) { } static inline unsigned int lwtunnel_headroom(struct lwtunnel_state *lwtstate, unsigned int mtu) { return 0; } static inline int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, unsigned int num) { return -EOPNOTSUPP; } static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num) { return -EOPNOTSUPP; } static inline int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel"); return -EOPNOTSUPP; } static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, struct netlink_ext_ack *extack) { /* return 0 since we are not walking attr looking for * RTA_ENCAP_TYPE attribute on nexthops. */ return 0; } static inline int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, struct lwtunnel_state **lws, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } static inline int lwtunnel_fill_encap(struct sk_buff *skb, struct lwtunnel_state *lwtstate, int encap_attr, int encap_type_attr) { return 0; } static inline int lwtunnel_get_encap_size(struct lwtunnel_state *lwtstate) { return 0; } static inline struct lwtunnel_state *lwtunnel_state_alloc(int hdr_len) { return NULL; } static inline int lwtunnel_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) { return 0; } static inline int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb) { return -EOPNOTSUPP; } static inline int lwtunnel_input(struct sk_buff *skb) { return -EOPNOTSUPP; } static inline int lwtunnel_xmit(struct sk_buff *skb) { return -EOPNOTSUPP; } #endif /* CONFIG_LWTUNNEL */ #define MODULE_ALIAS_RTNL_LWT(encap_type) MODULE_ALIAS("rtnl-lwt-" __stringify(encap_type)) #endif /* __NET_LWTUNNEL_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Driver for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright (C) 2001 Russell King. */ #include <linux/bits.h> #include <linux/serial_8250.h> #include <linux/serial_core.h> #include <linux/dmaengine.h> #include "../serial_mctrl_gpio.h" struct uart_8250_dma { int (*tx_dma)(struct uart_8250_port *p); int (*rx_dma)(struct uart_8250_port *p); void (*prepare_tx_dma)(struct uart_8250_port *p); void (*prepare_rx_dma)(struct uart_8250_port *p); /* Filter function */ dma_filter_fn fn; /* Parameter to the filter function */ void *rx_param; void *tx_param; struct dma_slave_config rxconf; struct dma_slave_config txconf; struct dma_chan *rxchan; struct dma_chan *txchan; /* Device address base for DMA operations */ phys_addr_t rx_dma_addr; phys_addr_t tx_dma_addr; /* DMA address of the buffer in memory */ dma_addr_t rx_addr; dma_addr_t tx_addr; dma_cookie_t rx_cookie; dma_cookie_t tx_cookie; void *rx_buf; size_t rx_size; size_t tx_size; unsigned char tx_running; unsigned char tx_err; unsigned char rx_running; }; struct old_serial_port { unsigned int uart; unsigned int baud_base; unsigned int port; unsigned int irq; upf_t flags; unsigned char io_type; unsigned char __iomem *iomem_base; unsigned short iomem_reg_shift; }; struct serial8250_config { const char *name; unsigned short fifo_size; unsigned short tx_loadsz; unsigned char fcr; unsigned char rxtrig_bytes[UART_FCR_R_TRIG_MAX_STATE]; unsigned int flags; }; #define UART_CAP_FIFO BIT(8) /* UART has FIFO */ #define UART_CAP_EFR BIT(9) /* UART has EFR */ #define UART_CAP_SLEEP BIT(10) /* UART has IER sleep */ #define UART_CAP_AFE BIT(11) /* MCR-based hw flow control */ #define UART_CAP_UUE BIT(12) /* UART needs IER bit 6 set (Xscale) */ #define UART_CAP_RTOIE BIT(13) /* UART needs IER bit 4 set (Xscale, Tegra) */ #define UART_CAP_HFIFO BIT(14) /* UART has a "hidden" FIFO */ #define UART_CAP_RPM BIT(15) /* Runtime PM is active while idle */ #define UART_CAP_IRDA BIT(16) /* UART supports IrDA line discipline */ #define UART_CAP_MINI BIT(17) /* Mini UART on BCM283X family lacks: * STOP PARITY EPAR SPAR WLEN5 WLEN6 */ #define UART_CAP_NOTEMT BIT(18) /* UART without interrupt on TEMT available */ #define UART_BUG_QUOT BIT(0) /* UART has buggy quot LSB */ #define UART_BUG_TXEN BIT(1) /* UART has buggy TX IIR status */ #define UART_BUG_NOMSR BIT(2) /* UART has buggy MSR status bits (Au1x00) */ #define UART_BUG_THRE BIT(3) /* UART has buggy THRE reassertion */ #define UART_BUG_TXRACE BIT(5) /* UART Tx fails to set remote DR */ /* Module parameters */ #define UART_NR CONFIG_SERIAL_8250_NR_UARTS extern unsigned int nr_uarts; #define SERIAL8250_PORT_FLAGS(_base, _irq, _flags) \ { \ .iobase = _base, \ .irq = _irq, \ .uartclk = 1843200, \ .iotype = UPIO_PORT, \ .flags = UPF_BOOT_AUTOCONF | (_flags), \ } #define SERIAL8250_PORT(_base, _irq) SERIAL8250_PORT_FLAGS(_base, _irq, 0) extern struct uart_driver serial8250_reg; void serial8250_register_ports(struct uart_driver *drv, struct device *dev); /* Legacy ISA bus related APIs */ typedef void (*serial8250_isa_config_fn)(int, struct uart_port *, u32 *); extern serial8250_isa_config_fn serial8250_isa_config; void serial8250_isa_init_ports(void); extern struct platform_device *serial8250_isa_devs; extern const struct uart_ops *univ8250_port_base_ops; extern struct uart_ops univ8250_port_ops; static inline int serial_in(struct uart_8250_port *up, int offset) { return up->port.serial_in(&up->port, offset); } static inline void serial_out(struct uart_8250_port *up, int offset, int value) { up->port.serial_out(&up->port, offset, value); } /** * serial_lsr_in - Read LSR register and preserve flags across reads * @up: uart 8250 port * * Read LSR register and handle saving non-preserved flags across reads. * The flags that are not preserved across reads are stored into * up->lsr_saved_flags. * * Returns LSR value or'ed with the preserved flags (if any). */ static inline u16 serial_lsr_in(struct uart_8250_port *up) { u16 lsr = up->lsr_saved_flags; lsr |= serial_in(up, UART_LSR); up->lsr_saved_flags = lsr & up->lsr_save_mask; return lsr; } /* * For the 16C950 */ static void serial_icr_write(struct uart_8250_port *up, int offset, int value) { serial_out(up, UART_SCR, offset); serial_out(up, UART_ICR, value); } static unsigned int __maybe_unused serial_icr_read(struct uart_8250_port *up, int offset) { unsigned int value; serial_icr_write(up, UART_ACR, up->acr | UART_ACR_ICRRD); serial_out(up, UART_SCR, offset); value = serial_in(up, UART_ICR); serial_icr_write(up, UART_ACR, up->acr); return value; } void serial8250_clear_fifos(struct uart_8250_port *p); void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p); void serial8250_fifo_wait_for_lsr_thre(struct uart_8250_port *up, unsigned int count); void serial8250_rpm_get(struct uart_8250_port *p); void serial8250_rpm_put(struct uart_8250_port *p); DEFINE_GUARD(serial8250_rpm, struct uart_8250_port *, serial8250_rpm_get(_T), serial8250_rpm_put(_T)); static inline u32 serial_dl_read(struct uart_8250_port *up) { return up->dl_read(up); } static inline void serial_dl_write(struct uart_8250_port *up, u32 value) { up->dl_write(up, value); } static inline bool serial8250_set_THRI(struct uart_8250_port *up) { /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&up->port.lock); if (up->ier & UART_IER_THRI) return false; up->ier |= UART_IER_THRI; serial_out(up, UART_IER, up->ier); return true; } static inline bool serial8250_clear_THRI(struct uart_8250_port *up) { /* Port locked to synchronize UART_IER access against the console. */ lockdep_assert_held_once(&up->port.lock); if (!(up->ier & UART_IER_THRI)) return false; up->ier &= ~UART_IER_THRI; serial_out(up, UART_IER, up->ier); return true; } struct uart_8250_port *serial8250_setup_port(int index); struct uart_8250_port *serial8250_get_port(int line); int serial8250_em485_config(struct uart_port *port, struct ktermios *termios, struct serial_rs485 *rs485); void serial8250_em485_start_tx(struct uart_8250_port *p, bool toggle_ier); void serial8250_em485_stop_tx(struct uart_8250_port *p, bool toggle_ier); void serial8250_em485_destroy(struct uart_8250_port *p); extern struct serial_rs485 serial8250_em485_supported; /* MCR <-> TIOCM conversion */ static inline int serial8250_TIOCM_to_MCR(int tiocm) { int mcr = 0; if (tiocm & TIOCM_RTS) mcr |= UART_MCR_RTS; if (tiocm & TIOCM_DTR) mcr |= UART_MCR_DTR; if (tiocm & TIOCM_OUT1) mcr |= UART_MCR_OUT1; if (tiocm & TIOCM_OUT2) mcr |= UART_MCR_OUT2; if (tiocm & TIOCM_LOOP) mcr |= UART_MCR_LOOP; return mcr; } static inline int serial8250_MCR_to_TIOCM(int mcr) { int tiocm = 0; if (mcr & UART_MCR_RTS) tiocm |= TIOCM_RTS; if (mcr & UART_MCR_DTR) tiocm |= TIOCM_DTR; if (mcr & UART_MCR_OUT1) tiocm |= TIOCM_OUT1; if (mcr & UART_MCR_OUT2) tiocm |= TIOCM_OUT2; if (mcr & UART_MCR_LOOP) tiocm |= TIOCM_LOOP; return tiocm; } /* MSR <-> TIOCM conversion */ static inline int serial8250_MSR_to_TIOCM(int msr) { int tiocm = 0; if (msr & UART_MSR_DCD) tiocm |= TIOCM_CAR; if (msr & UART_MSR_RI) tiocm |= TIOCM_RNG; if (msr & UART_MSR_DSR) tiocm |= TIOCM_DSR; if (msr & UART_MSR_CTS) tiocm |= TIOCM_CTS; return tiocm; } static inline void serial8250_out_MCR(struct uart_8250_port *up, int value) { serial_out(up, UART_MCR, value); if (up->gpios) mctrl_gpio_set(up->gpios, serial8250_MCR_to_TIOCM(value)); } static inline int serial8250_in_MCR(struct uart_8250_port *up) { int mctrl; mctrl = serial_in(up, UART_MCR); if (up->gpios) { unsigned int mctrl_gpio = 0; mctrl_gpio = mctrl_gpio_get_outputs(up->gpios, &mctrl_gpio); mctrl |= serial8250_TIOCM_to_MCR(mctrl_gpio); } return mctrl; } #ifdef CONFIG_SERIAL_8250_PNP int serial8250_pnp_init(void); void serial8250_pnp_exit(void); #else static inline int serial8250_pnp_init(void) { return 0; } static inline void serial8250_pnp_exit(void) { } #endif #ifdef CONFIG_SERIAL_8250_RSA void univ8250_rsa_support(struct uart_ops *ops, const struct uart_ops *core_ops); void rsa_enable(struct uart_8250_port *up); void rsa_disable(struct uart_8250_port *up); void rsa_autoconfig(struct uart_8250_port *up); void rsa_reset(struct uart_8250_port *up); #else static inline void univ8250_rsa_support(struct uart_ops *ops, const struct uart_ops *core_ops) { } static inline void rsa_enable(struct uart_8250_port *up) {} static inline void rsa_disable(struct uart_8250_port *up) {} static inline void rsa_autoconfig(struct uart_8250_port *up) {} static inline void rsa_reset(struct uart_8250_port *up) {} #endif #ifdef CONFIG_SERIAL_8250_FINTEK int fintek_8250_probe(struct uart_8250_port *uart); #else static inline int fintek_8250_probe(struct uart_8250_port *uart) { return 0; } #endif #ifdef CONFIG_ARCH_OMAP1 #include <linux/soc/ti/omap1-soc.h> static inline int is_omap1_8250(struct uart_8250_port *pt) { int res; switch (pt->port.mapbase) { case OMAP1_UART1_BASE: case OMAP1_UART2_BASE: case OMAP1_UART3_BASE: res = 1; break; default: res = 0; break; } return res; } static inline int is_omap1510_8250(struct uart_8250_port *pt) { if (!cpu_is_omap1510()) return 0; return is_omap1_8250(pt); } #else static inline int is_omap1_8250(struct uart_8250_port *pt) { return 0; } static inline int is_omap1510_8250(struct uart_8250_port *pt) { return 0; } #endif #ifdef CONFIG_SERIAL_8250_DMA extern int serial8250_tx_dma(struct uart_8250_port *); extern void serial8250_tx_dma_flush(struct uart_8250_port *); extern int serial8250_rx_dma(struct uart_8250_port *); extern void serial8250_rx_dma_flush(struct uart_8250_port *); extern int serial8250_request_dma(struct uart_8250_port *); extern void serial8250_release_dma(struct uart_8250_port *); static inline void serial8250_do_prepare_tx_dma(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; if (dma->prepare_tx_dma) dma->prepare_tx_dma(p); } static inline void serial8250_do_prepare_rx_dma(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; if (dma->prepare_rx_dma) dma->prepare_rx_dma(p); } static inline bool serial8250_tx_dma_running(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; return dma && dma->tx_running; } static inline void serial8250_tx_dma_pause(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; if (!dma->tx_running) return; dmaengine_pause(dma->txchan); } static inline void serial8250_tx_dma_resume(struct uart_8250_port *p) { struct uart_8250_dma *dma = p->dma; if (!dma->tx_running) return; dmaengine_resume(dma->txchan); } #else static inline int serial8250_tx_dma(struct uart_8250_port *p) { return -1; } static inline void serial8250_tx_dma_flush(struct uart_8250_port *p) { } static inline int serial8250_rx_dma(struct uart_8250_port *p) { return -1; } static inline void serial8250_rx_dma_flush(struct uart_8250_port *p) { } static inline int serial8250_request_dma(struct uart_8250_port *p) { return -1; } static inline void serial8250_release_dma(struct uart_8250_port *p) { } static inline bool serial8250_tx_dma_running(struct uart_8250_port *p) { return false; } static inline void serial8250_tx_dma_pause(struct uart_8250_port *p) { } static inline void serial8250_tx_dma_resume(struct uart_8250_port *p) { } #endif static inline int ns16550a_goto_highspeed(struct uart_8250_port *up) { unsigned char status; status = serial_in(up, 0x04); /* EXCR2 */ #define PRESL(x) ((x) & 0x30) if (PRESL(status) == 0x10) { /* already in high speed mode */ return 0; } else { status &= ~0xB0; /* Disable LOCK, mask out PRESL[01] */ status |= 0x10; /* 1.625 divisor for baud_base --> 921600 */ serial_out(up, 0x04, status); } return 1; } static inline int serial_index(struct uart_port *port) { return port->minor - 64; } |
| 2553 2557 2550 2557 1513 1517 3 3 3 3 3 4455 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* CPU control. * (C) 2001, 2002, 2003, 2004 Rusty Russell */ #include <linux/sched/mm.h> #include <linux/proc_fs.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> #include <linux/sched/isolation.h> #include <linux/sched/task.h> #include <linux/sched/smt.h> #include <linux/unistd.h> #include <linux/cpu.h> #include <linux/oom.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <linux/export.h> #include <linux/bug.h> #include <linux/kthread.h> #include <linux/stop_machine.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> #include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> #include <linux/scs.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> #include <linux/random.h> #include <linux/cc_platform.h> #include <linux/parser.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS #include <trace/events/cpuhp.h> #include "smpboot.h" /** * struct cpuhp_cpu_state - Per cpu hotplug state storage * @state: The current cpu state * @target: The target state * @fail: Current CPU hotplug callback state * @thread: Pointer to the hotplug thread * @should_run: Thread should execute * @rollback: Perform a rollback * @single: Single callback invocation * @bringup: Single callback bringup or teardown selector * @node: Remote CPU node; for multi-instance, do a * single entry callback for install/remove * @last: For multi-instance rollback, remember how far we got * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation * @ap_sync_state: State for AP synchronization * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; bool rollback; bool single; bool bringup; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; int result; atomic_t ap_sync_state; struct completion done_up; struct completion done_down; #endif }; static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; #ifdef CONFIG_SMP cpumask_t cpus_booted_once_mask; #endif #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); static struct lockdep_map cpuhp_state_down_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); static inline void cpuhp_lock_acquire(bool bringup) { lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } static inline void cpuhp_lock_release(bool bringup) { lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } #else static inline void cpuhp_lock_acquire(bool bringup) { } static inline void cpuhp_lock_release(bool bringup) { } #endif /** * struct cpuhp_step - Hotplug state machine step * @name: Name of the step * @startup: Startup function of the step * @teardown: Teardown function of the step * @cant_stop: Bringup/teardown can't be stopped at this step * @multi_instance: State has multiple instances which get added afterwards */ struct cpuhp_step { const char *name; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } startup; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } teardown; /* private: */ struct hlist_head list; /* public: */ bool cant_stop; bool multi_instance; }; static DEFINE_MUTEX(cpuhp_state_mutex); static struct cpuhp_step cpuhp_hp_states[]; static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) { return cpuhp_hp_states + state; } static bool cpuhp_step_empty(bool bringup, struct cpuhp_step *step) { return bringup ? !step->startup.single : !step->teardown.single; } /** * cpuhp_invoke_callback - Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked * @node: For multi-instance, do a single entry callback for install/remove * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. * * Return: %0 on success or a negative errno code */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node, struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); int (*cbm)(unsigned int cpu, struct hlist_node *node); int (*cb)(unsigned int cpu); int ret, cnt; if (st->fail == state) { st->fail = CPUHP_INVALID; return -EAGAIN; } if (cpuhp_step_empty(bringup, step)) { WARN_ON_ONCE(1); return 0; } if (!step->multi_instance) { WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; trace_cpuhp_enter(cpu, st->target, state, cb); ret = cb(cpu); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } cbm = bringup ? step->startup.multi : step->teardown.multi; /* Single invocation for instance add/remove */ if (node) { WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { if (lastp && node == *lastp) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); if (ret) { if (!lastp) goto err; *lastp = node; return ret; } cnt++; } if (lastp) *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ cbm = !bringup ? step->startup.multi : step->teardown.multi; if (!cbm) return ret; hlist_for_each(node, &step->list) { if (!cnt--) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); /* * Rollback must not fail, */ WARN_ON_ONCE(ret); } return ret; } /* * The former STARTING/DYING states, ran with IRQs disabled and must not fail. */ static bool cpuhp_is_atomic_state(enum cpuhp_state state) { return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } #ifdef CONFIG_SMP static bool cpuhp_is_ap_state(enum cpuhp_state state) { /* * The extra check for CPUHP_TEARDOWN_CPU is only for documentation * purposes as that state is handled explicitly in cpu_down. */ return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; wait_for_completion(done); } static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; complete(done); } /* Synchronization state management */ enum cpuhp_sync_state { SYNC_STATE_DEAD, SYNC_STATE_KICKED, SYNC_STATE_SHOULD_DIE, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE, SYNC_STATE_ONLINE, }; #ifdef CONFIG_HOTPLUG_CORE_SYNC /** * cpuhp_ap_update_sync_state - Update synchronization state during bringup/teardown * @state: The synchronization state to set * * No synchronization point. Just update of the synchronization state, but implies * a full barrier so that the AP changes are visible before the control CPU proceeds. */ static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); (void)atomic_xchg(st, state); } void __weak arch_cpuhp_sync_state_poll(void) { cpu_relax(); } static bool cpuhp_wait_for_sync_state(unsigned int cpu, enum cpuhp_sync_state state, enum cpuhp_sync_state next_state) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); ktime_t now, end, start = ktime_get(); int sync; end = start + 10ULL * NSEC_PER_SEC; sync = atomic_read(st); while (1) { if (sync == state) { if (!atomic_try_cmpxchg(st, &sync, next_state)) continue; return true; } now = ktime_get(); if (now > end) { /* Timeout. Leave the state unchanged */ return false; } else if (now - start < NSEC_PER_MSEC) { /* Poll for one millisecond */ arch_cpuhp_sync_state_poll(); } else { usleep_range(USEC_PER_MSEC, 2 * USEC_PER_MSEC); } sync = atomic_read(st); } return true; } #else /* CONFIG_HOTPLUG_CORE_SYNC */ static inline void cpuhp_ap_update_sync_state(enum cpuhp_sync_state state) { } #endif /* !CONFIG_HOTPLUG_CORE_SYNC */ #ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD /** * cpuhp_ap_report_dead - Update synchronization state to DEAD * * No synchronization point. Just update of the synchronization state. */ void cpuhp_ap_report_dead(void) { cpuhp_ap_update_sync_state(SYNC_STATE_DEAD); } void __weak arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { } /* * Late CPU shutdown synchronization point. Cannot use cpuhp_state::done_down * because the AP cannot issue complete() at this stage. */ static void cpuhp_bp_sync_dead(unsigned int cpu) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); int sync = atomic_read(st); do { /* CPU can have reported dead already. Don't overwrite that! */ if (sync == SYNC_STATE_DEAD) break; } while (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_SHOULD_DIE)); if (cpuhp_wait_for_sync_state(cpu, SYNC_STATE_DEAD, SYNC_STATE_DEAD)) { /* CPU reached dead state. Invoke the cleanup function */ arch_cpuhp_cleanup_dead_cpu(cpu); return; } /* No further action possible. Emit message and give up. */ pr_err("CPU%u failed to report dead state\n", cpu); } #else /* CONFIG_HOTPLUG_CORE_SYNC_DEAD */ static inline void cpuhp_bp_sync_dead(unsigned int cpu) { } #endif /* !CONFIG_HOTPLUG_CORE_SYNC_DEAD */ #ifdef CONFIG_HOTPLUG_CORE_SYNC_FULL /** * cpuhp_ap_sync_alive - Synchronize AP with the control CPU once it is alive * * Updates the AP synchronization state to SYNC_STATE_ALIVE and waits * for the BP to release it. */ void cpuhp_ap_sync_alive(void) { atomic_t *st = this_cpu_ptr(&cpuhp_state.ap_sync_state); cpuhp_ap_update_sync_state(SYNC_STATE_ALIVE); /* Wait for the control CPU to release it. */ while (atomic_read(st) != SYNC_STATE_SHOULD_ONLINE) cpu_relax(); } static bool cpuhp_can_boot_ap(unsigned int cpu) { atomic_t *st = per_cpu_ptr(&cpuhp_state.ap_sync_state, cpu); int sync = atomic_read(st); again: switch (sync) { case SYNC_STATE_DEAD: /* CPU is properly dead */ break; case SYNC_STATE_KICKED: /* CPU did not come up in previous attempt */ break; case SYNC_STATE_ALIVE: /* CPU is stuck cpuhp_ap_sync_alive(). */ break; default: /* CPU failed to report online or dead and is in limbo state. */ return false; } /* Prepare for booting */ if (!atomic_try_cmpxchg(st, &sync, SYNC_STATE_KICKED)) goto again; return true; } void __weak arch_cpuhp_cleanup_kick_cpu(unsigned int cpu) { } /* * Early CPU bringup synchronization point. Cannot use cpuhp_state::done_up * because the AP cannot issue complete() so early in the bringup. */ static int cpuhp_bp_sync_alive(unsigned int cpu) { int ret = 0; if (!IS_ENABLED(CONFIG_HOTPLUG_CORE_SYNC_FULL)) return 0; if (!cpuhp_wait_for_sync_state(cpu, SYNC_STATE_ALIVE, SYNC_STATE_SHOULD_ONLINE)) { pr_err("CPU%u failed to report alive state\n", cpu); ret = -EIO; } /* Let the architecture cleanup the kick alive mechanics. */ arch_cpuhp_cleanup_kick_cpu(cpu); return ret; } #else /* CONFIG_HOTPLUG_CORE_SYNC_FULL */ static inline int cpuhp_bp_sync_alive(unsigned int cpu) { return 0; } static inline bool cpuhp_can_boot_ap(unsigned int cpu) { return true; } #endif /* !CONFIG_HOTPLUG_CORE_SYNC_FULL */ /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when * attempting to serialize the updates to cpu_online_mask & cpu_present_mask. */ void cpu_maps_update_begin(void) { mutex_lock(&cpu_add_remove_lock); } void cpu_maps_update_done(void) { mutex_unlock(&cpu_add_remove_lock); } /* * If set, cpu_up and cpu_down will return -EBUSY and do nothing. * Should always be manipulated under cpu_add_remove_lock */ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); static bool cpu_hotplug_offline_disabled __ro_after_init; void cpus_read_lock(void) { percpu_down_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_lock); int cpus_read_trylock(void) { return percpu_down_read_trylock(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_trylock); void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_unlock); void cpus_write_lock(void) { percpu_down_write(&cpu_hotplug_lock); } void cpus_write_unlock(void) { percpu_up_write(&cpu_hotplug_lock); } void lockdep_assert_cpus_held(void) { /* * We can't have hotplug operations before userspace starts running, * and some init codepaths will knowingly not take the hotplug lock. * This is all valid, so mute lockdep until it makes sense to report * unheld locks. */ if (system_state < SYSTEM_RUNNING) return; percpu_rwsem_assert_held(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(lockdep_assert_cpus_held); #ifdef CONFIG_LOCKDEP int lockdep_is_cpus_held(void) { return percpu_rwsem_is_held(&cpu_hotplug_lock); } int lockdep_is_cpus_write_held(void) { return percpu_rwsem_is_write_held(&cpu_hotplug_lock); } #endif static void lockdep_acquire_cpus_lock(void) { rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_); } static void lockdep_release_cpus_lock(void) { rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_); } /* Declare CPU offlining not supported */ void cpu_hotplug_disable_offlining(void) { cpu_maps_update_begin(); cpu_hotplug_offline_disabled = true; cpu_maps_update_done(); } /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the * hotplug path before performing hotplug operations. So acquiring that lock * guarantees mutual exclusion from any currently running hotplug operations. */ void cpu_hotplug_disable(void) { cpu_maps_update_begin(); cpu_hotplug_disabled++; cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_disable); static void __cpu_hotplug_enable(void) { if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n")) return; cpu_hotplug_disabled--; } void cpu_hotplug_enable(void) { cpu_maps_update_begin(); __cpu_hotplug_enable(); cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #else static void lockdep_acquire_cpus_lock(void) { } static void lockdep_release_cpus_lock(void) { } #endif /* CONFIG_HOTPLUG_CPU */ /* * Architectures that need SMT-specific errata handling during SMT hotplug * should override this. */ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; static unsigned int cpu_smt_max_threads __ro_after_init; unsigned int cpu_smt_num_threads __read_mostly = UINT_MAX; void __init cpu_smt_disable(bool force) { if (!cpu_smt_possible()) return; if (force) { pr_info("SMT: Force disabled\n"); cpu_smt_control = CPU_SMT_FORCE_DISABLED; } else { pr_info("SMT: disabled\n"); cpu_smt_control = CPU_SMT_DISABLED; } cpu_smt_num_threads = 1; } /* * The decision whether SMT is supported can only be done after the full * CPU identification. Called from architecture code. */ void __init cpu_smt_set_num_threads(unsigned int num_threads, unsigned int max_threads) { WARN_ON(!num_threads || (num_threads > max_threads)); if (max_threads == 1) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; cpu_smt_max_threads = max_threads; /* * If SMT has been disabled via the kernel command line or SMT is * not supported, set cpu_smt_num_threads to 1 for consistency. * If enabled, take the architecture requested number of threads * to bring up into account. */ if (cpu_smt_control != CPU_SMT_ENABLED) cpu_smt_num_threads = 1; else if (num_threads < cpu_smt_num_threads) cpu_smt_num_threads = num_threads; } static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); return 0; } early_param("nosmt", smt_cmdline_disable); /* * For Archicture supporting partial SMT states check if the thread is allowed. * Otherwise this has already been checked through cpu_smt_max_threads when * setting the SMT level. */ static inline bool cpu_smt_thread_allowed(unsigned int cpu) { #ifdef CONFIG_SMT_NUM_THREADS_DYNAMIC return topology_smt_thread_allowed(cpu); #else return true; #endif } static inline bool cpu_bootable(unsigned int cpu) { if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) return true; /* All CPUs are bootable if controls are not configured */ if (cpu_smt_control == CPU_SMT_NOT_IMPLEMENTED) return true; /* All CPUs are bootable if CPU is not SMT capable */ if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return true; if (topology_is_primary_thread(cpu)) return true; /* * On x86 it's required to boot all logical CPUs at least once so * that the init code can get a chance to set CR4.MCE on each * CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any * core will shutdown the machine. */ return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } /* Returns true if SMT is supported and not forcefully (irreversibly) disabled */ bool cpu_smt_possible(void) { return cpu_smt_control != CPU_SMT_FORCE_DISABLED && cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); #else static inline bool cpu_bootable(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state cpuhp_set_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; bool bringup = st->state < target; st->rollback = false; st->last = NULL; st->target = target; st->single = false; st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); return prev_state; } static inline void cpuhp_reset_state(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) { bool bringup = !st->bringup; st->target = prev_state; /* * Already rolling back. No need invert the bringup value or to change * the current state. */ if (st->rollback) return; st->rollback = true; /* * If we have st->last we need to undo partial multi_instance of this * state first. Otherwise start undo at the previous state. */ if (!st->last) { if (st->bringup) st->state--; else st->state++; } st->bringup = bringup; if (cpu_dying(cpu) != !bringup) set_cpu_dying(cpu, !bringup); } /* Regular hotplug invocation of the AP hotplug thread */ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) { if (!st->single && st->state == st->target) return; st->result = 0; /* * Make sure the above stores are visible before should_run becomes * true. Paired with the mb() above in cpuhp_thread_fun() */ smp_mb(); st->should_run = true; wake_up_process(st->thread); wait_for_ap_thread(st, st->bringup); } static int cpuhp_kick_ap(int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; prev_state = cpuhp_set_state(cpu, st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } return ret; } static int bringup_wait_for_ap_online(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; /* Unpark the hotplug thread of the target cpu */ kthread_unpark(st->thread); /* * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the * cpu_bootable() check will now return false if this is not the * primary sibling. */ if (!cpu_bootable(cpu)) return -ECANCELED; return 0; } #ifdef CONFIG_HOTPLUG_SPLIT_STARTUP static int cpuhp_kick_ap_alive(unsigned int cpu) { if (!cpuhp_can_boot_ap(cpu)) return -EAGAIN; return arch_cpuhp_kick_ap_alive(cpu, idle_thread_get(cpu)); } static int cpuhp_bringup_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * Prevent irq alloc/free across the bringup. */ irq_lock_sparse(); ret = cpuhp_bp_sync_alive(cpu); if (ret) goto out_unlock; ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); out_unlock: irq_unlock_sparse(); return ret; } #else static int bringup_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle = idle_thread_get(cpu); int ret; if (!cpuhp_can_boot_ap(cpu)) return -EAGAIN; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * * Prevent irq alloc/free across the bringup by acquiring the * sparse irq lock. Hold it until the upcoming CPU completes the * startup in cpuhp_online_idle() which allows to avoid * intermediate synchronization points in the architecture code. */ irq_lock_sparse(); ret = __cpu_up(cpu, idle); if (ret) goto out_unlock; ret = cpuhp_bp_sync_alive(cpu); if (ret) goto out_unlock; ret = bringup_wait_for_ap_online(cpu); if (ret) goto out_unlock; irq_unlock_sparse(); if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(cpu, st, st->target); out_unlock: irq_unlock_sparse(); return ret; } #endif static int finish_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); struct mm_struct *mm = idle->active_mm; /* * sched_force_init_mm() ensured the use of &init_mm, * drop that refcount now that the CPU has stopped. */ WARN_ON(mm != &init_mm); idle->active_mm = NULL; mmdrop_lazy_tlb(mm); return 0; } /* * Hotplug state machine related functions */ /* * Get the next state to run. Empty ones will be skipped. Returns true if a * state must be run. * * st->state will be modified ahead of time, to match state_to_run, as if it * has already ran. */ static bool cpuhp_next_state(bool bringup, enum cpuhp_state *state_to_run, struct cpuhp_cpu_state *st, enum cpuhp_state target) { do { if (bringup) { if (st->state >= target) return false; *state_to_run = ++st->state; } else { if (st->state <= target) return false; *state_to_run = st->state--; } if (!cpuhp_step_empty(bringup, cpuhp_get_step(*state_to_run))) break; } while (true); return true; } static int __cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target, bool nofail) { enum cpuhp_state state; int ret = 0; while (cpuhp_next_state(bringup, &state, st, target)) { int err; err = cpuhp_invoke_callback(cpu, state, bringup, NULL, NULL); if (!err) continue; if (nofail) { pr_warn("CPU %u %s state %s (%d) failed (%d)\n", cpu, bringup ? "UP" : "DOWN", cpuhp_get_step(st->state)->name, st->state, err); ret = -1; } else { ret = err; break; } } return ret; } static inline int cpuhp_invoke_callback_range(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { return __cpuhp_invoke_callback_range(bringup, cpu, st, target, false); } static inline void cpuhp_invoke_callback_range_nofail(bool bringup, unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { __cpuhp_invoke_callback_range(bringup, cpu, st, target, true); } static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) { if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; /* * When CPU hotplug is disabled, then taking the CPU down is not * possible because takedown_cpu() and the architecture and * subsystem specific mechanisms are not available. So the CPU * which would be completely unplugged again needs to stay around * in the current state. */ return st->state <= CPUHP_BRINGUP_CPU; } static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(true, cpu, st, target); if (ret) { pr_debug("CPU UP failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (can_rollback_cpu(st)) WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, prev_state)); } return ret; } /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); return st->should_run; } /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. * * Each invocation of this function by the smpboot thread does a single AP * state callback. * * It has 3 modes of operation: * - single: runs st->cb_state * - up: runs ++st->state, while st->state < st->target * - down: runs st->state--, while st->state > st->target * * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); bool bringup = st->bringup; enum cpuhp_state state; if (WARN_ON_ONCE(!st->should_run)) return; /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); /* * The BP holds the hotplug lock, but we're now running on the AP, * ensure that anybody asserting the lock is held, will actually find * it so. */ lockdep_acquire_cpus_lock(); cpuhp_lock_acquire(bringup); if (st->single) { state = st->cb_state; st->should_run = false; } else { st->should_run = cpuhp_next_state(bringup, &state, st, st->target); if (!st->should_run) goto end; } WARN_ON_ONCE(!cpuhp_is_ap_state(state)); if (cpuhp_is_atomic_state(state)) { local_irq_disable(); st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); local_irq_enable(); /* * STARTING/DYING must not fail! */ WARN_ON_ONCE(st->result); } else { st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); } if (st->result) { /* * If we fail on a rollback, we're up a creek without no * paddle, no way forward, no way back. We loose, thanks for * playing. */ WARN_ON_ONCE(st->rollback); st->should_run = false; } end: cpuhp_lock_release(bringup); lockdep_release_cpus_lock(); if (!st->should_run) complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; if (!cpu_online(cpu)) return 0; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); st->rollback = false; st->last = NULL; st->node = node; st->bringup = bringup; st->cb_state = state; st->single = true; __cpuhp_kick_ap(st); /* * If we failed and did a partial, do a rollback. */ if ((ret = st->result) && st->last) { st->rollback = true; st->bringup = !bringup; __cpuhp_kick_ap(st); } /* * Clean up the leftovers so the next hotplug operation wont use stale * data. */ st->node = st->last = NULL; return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state prev_state = st->state; int ret; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); ret = cpuhp_kick_ap(cpu, st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; } static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; static __init void cpuhp_init_state(void) { struct cpuhp_cpu_state *st; int cpu; for_each_possible_cpu(cpu) { st = per_cpu_ptr(&cpuhp_state, cpu); init_completion(&st->done_up); init_completion(&st->done_down); } } void __init cpuhp_threads_init(void) { cpuhp_init_state(); BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); kthread_unpark(this_cpu_read(cpuhp_state.thread)); } #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) #endif /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id * * This function walks all processes, finds a valid mm struct for each one and * then clears a corresponding bit in mm's cpumask. While this all sounds * trivial, there are various non-obvious corner cases, which this function * tries to solve in a safe manner. * * Also note that the function uses a somewhat relaxed locking scheme, so it may * be called only for an already offlined CPU. */ void clear_tasks_mm_cpumask(int cpu) { struct task_struct *p; /* * This function is called after the cpu is taken down and marked * offline, so its not like new tasks will ever get this cpu set in * their mm mask. -- Peter Zijlstra * Thus, we may use rcu_read_lock() here, instead of grabbing * full-fledged tasklist_lock. */ WARN_ON(cpu_online(cpu)); rcu_read_lock(); for_each_process(p) { struct task_struct *t; /* * Main thread might exit, but other threads may still have * a valid mm. Find one. */ t = find_lock_task_mm(p); if (!t) continue; arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); } /* Take this CPU down. */ static int take_cpu_down(void *_param) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; /* * Must be called from CPUHP_TEARDOWN_CPU, which means, as we are going * down, that the current state is CPUHP_TEARDOWN_CPU - 1. */ WARN_ON(st->state != (CPUHP_TEARDOWN_CPU - 1)); /* * Invoke the former CPU_DYING callbacks. DYING must not fail! */ cpuhp_invoke_callback_range_nofail(false, cpu, st, target); /* Park the stopper thread */ stop_machine_park(cpu); return 0; } static int takedown_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; /* Park the smpboot threads */ kthread_park(st->thread); /* * Prevent irq alloc/free while the dying cpu reorganizes the * interrupt affinities. */ irq_lock_sparse(); err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ irq_unlock_sparse(); /* Unpark the hotplug thread so we can rollback there */ kthread_unpark(st->thread); return err; } BUG_ON(cpu_online(cpu)); /* * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed * all runnable tasks from the CPU, there's only the idle task left now * that the migration thread is done doing the stop_machine thing. * * Wait for the stop thread to go away. */ wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); cpuhp_bp_sync_dead(cpu); lockdep_cleanup_dead_cpu(cpu, idle_thread_get(cpu)); /* * Callbacks must be re-integrated right away to the RCU state machine. * Otherwise an RCU callback could block a further teardown function * waiting for its completion. */ rcutree_migrate_callbacks(cpu); return 0; } static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); tick_assert_timekeeping_handover(); rcutree_report_cpu_dead(); st->state = CPUHP_AP_IDLE_DEAD; /* * We cannot call complete after rcutree_report_cpu_dead() so we delegate it * to an online cpu. */ smp_call_function_single(cpumask_first(cpu_online_mask), cpuhp_complete_idle_dead, st, 0); } static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; ret = cpuhp_invoke_callback_range(false, cpu, st, target); if (ret) { pr_debug("CPU DOWN failed (%d) CPU %u state %s (%d)\n", ret, cpu, cpuhp_get_step(st->state)->name, st->state); cpuhp_reset_state(cpu, st, prev_state); if (st->state < prev_state) WARN_ON(cpuhp_invoke_callback_range(true, cpu, st, prev_state)); } return ret; } /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int prev_state, ret = 0; if (num_online_cpus() == 1) return -EBUSY; if (!cpu_present(cpu)) return -EINVAL; cpus_write_lock(); /* * Keep at least one housekeeping cpu onlined to avoid generating * an empty sched_domain span. */ if (cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)) >= nr_cpu_ids) { ret = -EBUSY; goto out; } cpuhp_tasks_frozen = tasks_frozen; prev_state = cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; /* * We might have stopped still in the range of the AP hotplug * thread. Nothing to do anymore. */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state < prev_state) { if (st->state == CPUHP_TEARDOWN_CPU) { cpuhp_reset_state(cpu, st, prev_state); __cpuhp_kick_ap(st); } else { WARN(1, "DEAD callback error for CPU%d", cpu); } } out: cpus_write_unlock(); arch_smt_update(); return ret; } static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { /* * If the platform does not support hotplug, report it explicitly to * differentiate it from a transient offlining failure. */ if (cpu_hotplug_offline_disabled) return -EOPNOTSUPP; if (cpu_hotplug_disabled) return -EBUSY; return _cpu_down(cpu, 0, target); } static int cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; cpu_maps_update_begin(); err = cpu_down_maps_locked(cpu, target); cpu_maps_update_done(); return err; } /** * cpu_device_down - Bring down a cpu device * @dev: Pointer to the cpu device to offline * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use remove_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_down(struct device *dev) { return cpu_down(dev->id, CPUHP_OFFLINE); } int remove_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_offline(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(remove_cpu); void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { unsigned int cpu; int error; cpu_maps_update_begin(); /* * Make certain the cpu I'm about to reboot on is online. * * This is inline to what migrate_to_reboot_cpu() already do. */ if (!cpu_online(primary_cpu)) primary_cpu = cpumask_first(cpu_online_mask); for_each_online_cpu(cpu) { if (cpu == primary_cpu) continue; error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (error) { pr_err("Failed to offline CPU%d - error=%d", cpu, error); break; } } /* * Ensure all but the reboot CPU are offline. */ BUG_ON(num_online_cpus() > 1); /* * Make sure the CPUs won't be enabled by someone else after this * point. Kexec will reboot to a new kernel shortly resetting * everything along the way. */ cpu_hotplug_disabled++; cpu_maps_update_done(); } #else #define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started * * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); rcutree_report_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ cpumask_set_cpu(cpu, &cpus_booted_once_mask); /* * STARTING must not fail! */ cpuhp_invoke_callback_range_nofail(true, cpu, st, target); } /* * Called from the idle task. Wake up the controlling task which brings the * hotplug thread of the upcoming CPU up and then delegates the rest of the * online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); /* Happens for the boot cpu */ if (state != CPUHP_AP_ONLINE_IDLE) return; cpuhp_ap_update_sync_state(SYNC_STATE_ONLINE); /* * Unpark the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); st->state = CPUHP_AP_ONLINE_IDLE; complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; int ret = 0; cpus_write_lock(); if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } /* * The caller of cpu_up() might have raced with another * caller. Nothing to do. */ if (st->state >= target) goto out; if (st->state == CPUHP_OFFLINE) { /* Let it fail before we try to bring the cpu up */ idle = idle_thread_get(cpu); if (IS_ERR(idle)) { ret = PTR_ERR(idle); goto out; } /* * Reset stale stack state from the last time this CPU was online. */ scs_task_reset(idle); kasan_unpoison_task_stack(idle); } cpuhp_tasks_frozen = tasks_frozen; cpuhp_set_state(cpu, st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. */ if (st->state > CPUHP_BRINGUP_CPU) { ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; } /* * Try to reach the target state. We max out on the BP at * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is * responsible for bringing it up to the target state. */ target = min((int)target, CPUHP_BRINGUP_CPU); ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); arch_smt_update(); return ret; } static int cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; if (!cpu_possible(cpu)) { pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n", cpu); return -EINVAL; } err = try_online_node(cpu_to_node(cpu)); if (err) return err; cpu_maps_update_begin(); if (cpu_hotplug_disabled) { err = -EBUSY; goto out; } if (!cpu_bootable(cpu)) { err = -EPERM; goto out; } err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); return err; } /** * cpu_device_up - Bring up a cpu device * @dev: Pointer to the cpu device to online * * This function is meant to be used by device core cpu subsystem only. * * Other subsystems should use add_cpu() instead. * * Return: %0 on success or a negative errno code */ int cpu_device_up(struct device *dev) { return cpu_up(dev->id, CPUHP_ONLINE); } int add_cpu(unsigned int cpu) { int ret; lock_device_hotplug(); ret = device_online(get_cpu_device(cpu)); unlock_device_hotplug(); return ret; } EXPORT_SYMBOL_GPL(add_cpu); /** * bringup_hibernate_cpu - Bring up the CPU that we hibernated on * @sleep_cpu: The cpu we hibernated on and should be brought up. * * On some architectures like arm64, we can hibernate on any CPU, but on * wake up the CPU we hibernated on might be offline as a side effect of * using maxcpus= for example. * * Return: %0 on success or a negative errno code */ int bringup_hibernate_cpu(unsigned int sleep_cpu) { int ret; if (!cpu_online(sleep_cpu)) { pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n"); ret = cpu_up(sleep_cpu, CPUHP_ONLINE); if (ret) { pr_err("Failed to bring hibernate-CPU up!\n"); return ret; } } return 0; } static void __init cpuhp_bringup_mask(const struct cpumask *mask, unsigned int ncpus, enum cpuhp_state target) { unsigned int cpu; for_each_cpu(cpu, mask) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); if (cpu_up(cpu, target) && can_rollback_cpu(st)) { /* * If this failed then cpu_up() might have only * rolled back to CPUHP_BP_KICK_AP for the final * online. Clean it up. NOOP if already rolled back. */ WARN_ON(cpuhp_invoke_callback_range(false, cpu, st, CPUHP_OFFLINE)); } if (!--ncpus) break; } } #ifdef CONFIG_HOTPLUG_PARALLEL static bool __cpuhp_parallel_bringup __ro_after_init = true; static int __init parallel_bringup_parse_param(char *arg) { return kstrtobool(arg, &__cpuhp_parallel_bringup); } early_param("cpuhp.parallel", parallel_bringup_parse_param); #ifdef CONFIG_HOTPLUG_SMT static inline bool cpuhp_smt_aware(void) { return cpu_smt_max_threads > 1; } static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) { return cpu_primary_thread_mask; } #else static inline bool cpuhp_smt_aware(void) { return false; } static inline const struct cpumask *cpuhp_get_primary_thread_mask(void) { return cpu_none_mask; } #endif bool __weak arch_cpuhp_init_parallel_bringup(void) { return true; } /* * On architectures which have enabled parallel bringup this invokes all BP * prepare states for each of the to be onlined APs first. The last state * sends the startup IPI to the APs. The APs proceed through the low level * bringup code in parallel and then wait for the control CPU to release * them one by one for the final onlining procedure. * * This avoids waiting for each AP to respond to the startup IPI in * CPUHP_BRINGUP_CPU. */ static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus) { const struct cpumask *mask = cpu_present_mask; if (__cpuhp_parallel_bringup) __cpuhp_parallel_bringup = arch_cpuhp_init_parallel_bringup(); if (!__cpuhp_parallel_bringup) return false; if (cpuhp_smt_aware()) { const struct cpumask *pmask = cpuhp_get_primary_thread_mask(); static struct cpumask tmp_mask __initdata; /* * X86 requires to prevent that SMT siblings stopped while * the primary thread does a microcode update for various * reasons. Bring the primary threads up first. */ cpumask_and(&tmp_mask, mask, pmask); cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_BP_KICK_AP); cpuhp_bringup_mask(&tmp_mask, ncpus, CPUHP_ONLINE); /* Account for the online CPUs */ ncpus -= num_online_cpus(); if (!ncpus) return true; /* Create the mask for secondary CPUs */ cpumask_andnot(&tmp_mask, mask, pmask); mask = &tmp_mask; } /* Bring the not-yet started CPUs up */ cpuhp_bringup_mask(mask, ncpus, CPUHP_BP_KICK_AP); cpuhp_bringup_mask(mask, ncpus, CPUHP_ONLINE); return true; } #else static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; } #endif /* CONFIG_HOTPLUG_PARALLEL */ void __init bringup_nonboot_cpus(unsigned int max_cpus) { if (!max_cpus) return; /* Try parallel bringup optimization if enabled */ if (cpuhp_bringup_cpus_parallel(max_cpus)) return; /* Full per CPU serialized bringup */ cpuhp_bringup_mask(cpu_present_mask, max_cpus, CPUHP_ONLINE); } #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; int freeze_secondary_cpus(int primary) { int cpu, error = 0; cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); if (!housekeeping_cpu(primary, HK_TYPE_TIMER)) primary = housekeeping_any_cpu(HK_TYPE_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); } /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time */ cpumask_clear(frozen_cpus); pr_info("Disabling non-boot CPUs ...\n"); for (cpu = nr_cpu_ids - 1; cpu >= 0; cpu--) { if (!cpu_online(cpu) || cpu == primary) continue; if (pm_wakeup_pending()) { pr_info("Wakeup pending. Abort CPU freeze\n"); error = -EBUSY; break; } trace_suspend_resume(TPS("CPU_OFF"), cpu, true); error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); else { pr_err("Error taking CPU%d down: %d\n", cpu, error); break; } } if (!error) BUG_ON(num_online_cpus() > 1); else pr_err("Non-boot CPUs are not disabled\n"); /* * Make sure the CPUs won't be enabled by someone else. We need to do * this even in case of failure as all freeze_secondary_cpus() users are * supposed to do thaw_secondary_cpus() on the failure path. */ cpu_hotplug_disabled++; cpu_maps_update_done(); return error; } void __weak arch_thaw_secondary_cpus_begin(void) { } void __weak arch_thaw_secondary_cpus_end(void) { } void thaw_secondary_cpus(void) { int cpu, error; /* Allow everyone to use the CPU hotplug again */ cpu_maps_update_begin(); __cpu_hotplug_enable(); if (cpumask_empty(frozen_cpus)) goto out; pr_info("Enabling non-boot CPUs ...\n"); arch_thaw_secondary_cpus_begin(); for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); continue; } pr_warn("Error taking CPU%d up: %d\n", cpu, error); } arch_thaw_secondary_cpus_end(); cpumask_clear(frozen_cpus); out: cpu_maps_update_done(); } static int __init alloc_frozen_cpus(void) { if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) return -ENOMEM; return 0; } core_initcall(alloc_frozen_cpus); /* * When callbacks for CPU hotplug notifications are being executed, we must * ensure that the state of the system with respect to the tasks being frozen * or not, as reported by the notification, remains unchanged *throughout the * duration* of the execution of the callbacks. * Hence we need to prevent the freezer from racing with regular CPU hotplug. * * This synchronization is implemented by mutually excluding regular CPU * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/ * Hibernate notifications. */ static int cpu_hotplug_pm_callback(struct notifier_block *nb, unsigned long action, void *ptr) { switch (action) { case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: cpu_hotplug_disable(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: cpu_hotplug_enable(); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static int __init cpu_hotplug_pm_sync_init(void) { /* * cpu_hotplug_pm_callback has higher priority than x86 * bsp_pm_callback which depends on cpu_hotplug_pm_callback * to disable cpu hotplug to avoid cpu hotplug race. */ pm_notifier(cpu_hotplug_pm_callback, 0); return 0; } core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ int __boot_cpu_id; #endif /* CONFIG_SMP */ /* Boot processor state steps */ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_OFFLINE] = { .name = "offline", .startup.single = NULL, .teardown.single = NULL, }, #ifdef CONFIG_SMP [CPUHP_CREATE_THREADS]= { .name = "threads:prepare", .startup.single = smpboot_create_threads, .teardown.single = NULL, .cant_stop = true, }, [CPUHP_RANDOM_PREPARE] = { .name = "random:prepare", .startup.single = random_prepare_cpu, .teardown.single = NULL, }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", .startup.single = workqueue_prepare_cpu, .teardown.single = NULL, }, [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, .teardown.single = NULL, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", .startup.single = smpcfd_prepare_cpu, .teardown.single = smpcfd_dead_cpu, }, [CPUHP_RELAY_PREPARE] = { .name = "relay:prepare", .startup.single = relay_prepare_cpu, .teardown.single = NULL, }, [CPUHP_RCUTREE_PREP] = { .name = "RCU/tree:prepare", .startup.single = rcutree_prepare_cpu, .teardown.single = rcutree_dead_cpu, }, /* * On the tear-down path, timers_dead_cpu() must be invoked * before blk_mq_queue_reinit_notify() from notify_dead(), * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, #ifdef CONFIG_HOTPLUG_SPLIT_STARTUP /* * Kicks the AP alive. AP will wait in cpuhp_ap_sync_alive() until * the next step will release it. */ [CPUHP_BP_KICK_AP] = { .name = "cpu:kick_ap", .startup.single = cpuhp_kick_ap_alive, }, /* * Waits for the AP to reach cpuhp_ap_sync_alive() and then * releases it for the complete bringup. */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = cpuhp_bringup_ap, .teardown.single = finish_cpu, .cant_stop = true, }, #else /* * All-in-one CPU bringup state which includes the kick alive. */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, #endif /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", }, /* * Last state before CPU enters the idle loop to die. Transient state * for synchronization. */ [CPUHP_AP_OFFLINE] = { .name = "ap:offline", .cant_stop = true, }, /* First state is scheduler control. Interrupts are disabled */ [CPUHP_AP_SCHED_STARTING] = { .name = "sched:starting", .startup.single = sched_cpu_starting, .teardown.single = sched_cpu_dying, }, [CPUHP_AP_RCUTREE_DYING] = { .name = "RCU/tree:dying", .startup.single = NULL, .teardown.single = rcutree_dying_cpu, }, [CPUHP_AP_SMPCFD_DYING] = { .name = "smpcfd:dying", .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, [CPUHP_AP_HRTIMERS_DYING] = { .name = "hrtimers:dying", .startup.single = hrtimers_cpu_starting, .teardown.single = hrtimers_cpu_dying, }, [CPUHP_AP_TICK_DYING] = { .name = "tick:dying", .startup.single = NULL, .teardown.single = tick_cpu_dying, }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { .name = "ap:online", }, /* * Handled on control processor until the plugged processor manages * this itself. */ [CPUHP_TEARDOWN_CPU] = { .name = "cpu:teardown", .startup.single = NULL, .teardown.single = takedown_cpu, .cant_stop = true, }, [CPUHP_AP_SCHED_WAIT_EMPTY] = { .name = "sched:waitempty", .startup.single = NULL, .teardown.single = sched_cpu_wait_empty, }, /* Handle smpboot threads park/unpark */ [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot/threads:online", .startup.single = smpboot_unpark_threads, .teardown.single = smpboot_park_threads, }, [CPUHP_AP_IRQ_AFFINITY_ONLINE] = { .name = "irq/affinity:online", .startup.single = irq_affinity_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_PERF_ONLINE] = { .name = "perf:online", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_AP_WATCHDOG_ONLINE] = { .name = "lockup_detector:online", .startup.single = lockup_detector_online_cpu, .teardown.single = lockup_detector_offline_cpu, }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = workqueue_online_cpu, .teardown.single = workqueue_offline_cpu, }, [CPUHP_AP_RANDOM_ONLINE] = { .name = "random:online", .startup.single = random_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, .teardown.single = rcutree_offline_cpu, }, #endif /* * The dynamically registered state space is here */ #ifdef CONFIG_SMP /* Last state is scheduler control setting the cpu active */ [CPUHP_AP_ACTIVE] = { .name = "sched:active", .startup.single = sched_cpu_activate, .teardown.single = sched_cpu_deactivate, }, #endif /* CPU is fully up and running. */ [CPUHP_ONLINE] = { .name = "online", .startup.single = NULL, .teardown.single = NULL, }, }; /* Sanity check for callbacks */ static int cpuhp_cb_check(enum cpuhp_state state) { if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) return -EINVAL; return 0; } /* * Returns a free for dynamic slot assignment of the Online state. The states * are protected by the cpuhp_slot_states mutex and an empty slot is identified * by having no name assigned. */ static int cpuhp_reserve_state(enum cpuhp_state state) { enum cpuhp_state i, end; struct cpuhp_step *step; switch (state) { case CPUHP_AP_ONLINE_DYN: step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN; end = CPUHP_AP_ONLINE_DYN_END; break; case CPUHP_BP_PREPARE_DYN: step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN; end = CPUHP_BP_PREPARE_DYN_END; break; default: return -EINVAL; } for (i = state; i <= end; i++, step++) { if (!step->name) return i; } WARN(1, "No more dynamic states available for CPU hotplug\n"); return -ENOSPC; } static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { /* (Un)Install the callbacks for further cpu hotplug operations */ struct cpuhp_step *sp; int ret = 0; /* * If name is NULL, then the state gets removed. * * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on * the first allocation from these dynamic ranges, so the removal * would trigger a new allocation and clear the wrong (already * empty) state, leaving the callbacks of the to be cleared state * dangling, which causes wreckage on the next hotplug operation. */ if (name && (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN)) { ret = cpuhp_reserve_state(state); if (ret < 0) return ret; state = ret; } sp = cpuhp_get_step(state); if (name && sp->name) return -EBUSY; sp->startup.single = startup; sp->teardown.single = teardown; sp->name = name; sp->multi_instance = multi_instance; INIT_HLIST_HEAD(&sp->list); return ret; } static void *cpuhp_get_teardown_cb(enum cpuhp_state state) { return cpuhp_get_step(state)->teardown.single; } /* * Call the startup/teardown function for a step either on the AP or * on the current CPU. */ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_step *sp = cpuhp_get_step(state); int ret; /* * If there's nothing to do, we done. * Relies on the union for multi_instance. */ if (cpuhp_step_empty(bringup, sp)) return 0; /* * The non AP bound callbacks can fail on bringup. On teardown * e.g. module removal we crash for now. */ #ifdef CONFIG_SMP if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else if (cpuhp_is_atomic_state(state)) { guard(irqsave)(); ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); /* STARTING/DYING must not fail! */ WARN_ON_ONCE(ret); } else { ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); } #endif BUG_ON(ret && !bringup); return ret; } /* * Called from __cpuhp_setup_state on a recoverable failure. * * Note: The teardown callbacks for rollback are not allowed to fail! */ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, struct hlist_node *node) { int cpu; /* Roll back the already executed steps on the other cpus */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpu >= failedcpu) break; /* Did we invoke the startup call on that cpu ? */ if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } } int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp; int cpu; int ret; lockdep_assert_cpus_held(); sp = cpuhp_get_step(state); if (sp->multi_instance == false) return -EINVAL; mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) goto add_node; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, node); if (ret) { if (sp->teardown.multi) cpuhp_rollback_install(cpu, state, node); goto unlock; } } add_node: ret = 0; hlist_add_head(node, &sp->list); unlock: mutex_unlock(&cpuhp_state_mutex); return ret; } int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { int ret; cpus_read_lock(); ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); /** * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state * @state: The state to setup * @name: Name of the step * @invoke: If true, the startup function is invoked for cpus where * cpu state >= @state * @startup: startup callback function * @teardown: teardown callback function * @multi_instance: State is set up for multiple instances which get * added afterwards. * * The caller needs to hold cpus read locked while calling this function. * Return: * On success: * Positive state number if @state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN; * 0 for all other states * On failure: proper (negative) error code */ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int cpu, ret = 0; bool dynstate; lockdep_assert_cpus_held(); if (cpuhp_cb_check(state) || !name) return -EINVAL; mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); dynstate = state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN; if (ret > 0 && dynstate) { state = ret; ret = 0; } if (ret || !invoke || !startup) goto out; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, NULL); if (ret) { if (teardown) cpuhp_rollback_install(cpu, state, NULL); cpuhp_store_callbacks(state, NULL, NULL, NULL, false); goto out; } } out: mutex_unlock(&cpuhp_state_mutex); /* * If the requested state is CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN, * return the dynamically allocated state in case of success. */ if (!ret && dynstate) return state; return ret; } EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked); int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int ret; cpus_read_lock(); ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup, teardown, multi_instance); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(__cpuhp_setup_state); int __cpuhp_state_remove_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); if (!sp->multi_instance) return -EINVAL; cpus_read_lock(); mutex_lock(&cpuhp_state_mutex); if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } remove: hlist_del(node); mutex_unlock(&cpuhp_state_mutex); cpus_read_unlock(); return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); /** * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state * @state: The state to remove * @invoke: If true, the teardown function is invoked for cpus where * cpu state >= @state * * The caller needs to hold cpus read locked while calling this function. * The teardown callback is currently not allowed to fail. Think * about module removal! */ void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); lockdep_assert_cpus_held(); mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { WARN(!hlist_empty(&sp->list), "Error: Removing state %d which has instances left.\n", state); goto remove; } if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, NULL); } remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); mutex_unlock(&cpuhp_state_mutex); } EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked); void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) { cpus_read_lock(); __cpuhp_remove_state_cpuslocked(state, invoke); cpus_read_unlock(); } EXPORT_SYMBOL(__cpuhp_remove_state); #ifdef CONFIG_HOTPLUG_SMT static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = true; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } static void cpuhp_online_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = false; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_ONLINE); } int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; cpu_maps_update_begin(); for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; /* * Disable can be called with CPU_SMT_ENABLED when changing * from a higher to lower number of SMT threads per core. */ if (ctrlval == CPU_SMT_ENABLED && cpu_smt_thread_allowed(cpu)) continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; /* * As this needs to hold the cpu maps lock it's impossible * to call device_offline() because that ends up calling * cpu_down() which takes cpu maps lock. cpu maps lock * needs to be held as this might race against in kernel * abusers of the hotplug machinery (thermal management). * * So nothing would update device:offline state. That would * leave the sysfs entry stale and prevent onlining after * smt control has been changed to 'off' again. This is * called under the sysfs hotplug lock, so it is properly * serialized against the regular offline usage. */ cpuhp_offline_cpu_device(cpu); } if (!ret) cpu_smt_control = ctrlval; cpu_maps_update_done(); return ret; } /* Check if the core a CPU belongs to is online */ #if !defined(topology_is_core_online) static inline bool topology_is_core_online(unsigned int cpu) { return true; } #endif int cpuhp_smt_enable(void) { int cpu, ret = 0; cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu)) continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; /* See comment in cpuhp_smt_disable() */ cpuhp_online_cpu_device(cpu); } cpu_maps_update_done(); return ret; } #endif #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t state_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->state); } static DEVICE_ATTR_RO(state); static ssize_t target_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int target, ret; ret = kstrtoint(buf, 10, &target); if (ret) return ret; #ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) return -EINVAL; #else if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) return -EINVAL; #endif ret = lock_device_hotplug_sysfs(); if (ret) return ret; mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(target); ret = !sp->name || sp->cant_stop ? -EINVAL : 0; mutex_unlock(&cpuhp_state_mutex); if (ret) goto out; if (st->state < target) ret = cpu_up(dev->id, target); else if (st->state > target) ret = cpu_down(dev->id, target); else if (WARN_ON(st->target != target)) st->target = target; out: unlock_device_hotplug(); return ret ? ret : count; } static ssize_t target_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->target); } static DEVICE_ATTR_RW(target); static ssize_t fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int fail, ret; ret = kstrtoint(buf, 10, &fail); if (ret) return ret; if (fail == CPUHP_INVALID) { st->fail = fail; return count; } if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE) return -EINVAL; /* * Cannot fail STARTING/DYING callbacks. */ if (cpuhp_is_atomic_state(fail)) return -EINVAL; /* * DEAD callbacks cannot fail... * ... neither can CPUHP_BRINGUP_CPU during hotunplug. The latter * triggering STARTING callbacks, a failure in this state would * hinder rollback. */ if (fail <= CPUHP_BRINGUP_CPU && st->state > CPUHP_BRINGUP_CPU) return -EINVAL; /* * Cannot fail anything that doesn't have callbacks. */ mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(fail); if (!sp->startup.single && !sp->teardown.single) ret = -EINVAL; mutex_unlock(&cpuhp_state_mutex); if (ret) return ret; st->fail = fail; return count; } static ssize_t fail_show(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->fail); } static DEVICE_ATTR_RW(fail); static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, &dev_attr_fail.attr, NULL }; static const struct attribute_group cpuhp_cpu_attr_group = { .attrs = cpuhp_cpu_attrs, .name = "hotplug", }; static ssize_t states_show(struct device *dev, struct device_attribute *attr, char *buf) { ssize_t cur, res = 0; int i; mutex_lock(&cpuhp_state_mutex); for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { struct cpuhp_step *sp = cpuhp_get_step(i); if (sp->name) { cur = sprintf(buf, "%3d: %s\n", i, sp->name); buf += cur; res += cur; } } mutex_unlock(&cpuhp_state_mutex); return res; } static DEVICE_ATTR_RO(states); static struct attribute *cpuhp_cpu_root_attrs[] = { &dev_attr_states.attr, NULL }; static const struct attribute_group cpuhp_cpu_root_attr_group = { .attrs = cpuhp_cpu_root_attrs, .name = "hotplug", }; #ifdef CONFIG_HOTPLUG_SMT static bool cpu_smt_num_threads_valid(unsigned int threads) { if (IS_ENABLED(CONFIG_SMT_NUM_THREADS_DYNAMIC)) return threads >= 1 && threads <= cpu_smt_max_threads; return threads == 1 || threads == cpu_smt_max_threads; } static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ctrlval, ret, num_threads, orig_threads; bool force_off; if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) return -EPERM; if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return -ENODEV; if (sysfs_streq(buf, "on")) { ctrlval = CPU_SMT_ENABLED; num_threads = cpu_smt_max_threads; } else if (sysfs_streq(buf, "off")) { ctrlval = CPU_SMT_DISABLED; num_threads = 1; } else if (sysfs_streq(buf, "forceoff")) { ctrlval = CPU_SMT_FORCE_DISABLED; num_threads = 1; } else if (kstrtoint(buf, 10, &num_threads) == 0) { if (num_threads == 1) ctrlval = CPU_SMT_DISABLED; else if (cpu_smt_num_threads_valid(num_threads)) ctrlval = CPU_SMT_ENABLED; else return -EINVAL; } else { return -EINVAL; } ret = lock_device_hotplug_sysfs(); if (ret) return ret; orig_threads = cpu_smt_num_threads; cpu_smt_num_threads = num_threads; force_off = ctrlval != cpu_smt_control && ctrlval == CPU_SMT_FORCE_DISABLED; if (num_threads > orig_threads) ret = cpuhp_smt_enable(); else if (num_threads < orig_threads || force_off) ret = cpuhp_smt_disable(ctrlval); unlock_device_hotplug(); return ret ? ret : count; } #else /* !CONFIG_HOTPLUG_SMT */ static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return -ENODEV; } #endif /* CONFIG_HOTPLUG_SMT */ static const char *smt_states[] = { [CPU_SMT_ENABLED] = "on", [CPU_SMT_DISABLED] = "off", [CPU_SMT_FORCE_DISABLED] = "forceoff", [CPU_SMT_NOT_SUPPORTED] = "notsupported", [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", }; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *state = smt_states[cpu_smt_control]; #ifdef CONFIG_HOTPLUG_SMT /* * If SMT is enabled but not all threads are enabled then show the * number of threads. If all threads are enabled show "on". Otherwise * show the state name. */ if (cpu_smt_control == CPU_SMT_ENABLED && cpu_smt_num_threads != cpu_smt_max_threads) return sysfs_emit(buf, "%d\n", cpu_smt_num_threads); #endif return sysfs_emit(buf, "%s\n", state); } static ssize_t control_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return __store_smt_control(dev, attr, buf, count); } static DEVICE_ATTR_RW(control); static ssize_t active_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", sched_smt_active()); } static DEVICE_ATTR_RO(active); static struct attribute *cpuhp_smt_attrs[] = { &dev_attr_control.attr, &dev_attr_active.attr, NULL }; static const struct attribute_group cpuhp_smt_attr_group = { .attrs = cpuhp_smt_attrs, .name = "smt", }; static int __init cpu_smt_sysfs_init(void) { struct device *dev_root; int ret = -ENODEV; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &cpuhp_smt_attr_group); put_device(dev_root); } return ret; } static int __init cpuhp_sysfs_init(void) { struct device *dev_root; int cpu, ret; ret = cpu_smt_sysfs_init(); if (ret) return ret; dev_root = bus_get_dev_root(&cpu_subsys); if (dev_root) { ret = sysfs_create_group(&dev_root->kobj, &cpuhp_cpu_root_attr_group); put_device(dev_root); if (ret) return ret; } for_each_possible_cpu(cpu) { struct device *dev = get_cpu_device(cpu); if (!dev) continue; ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); if (ret) return ret; } return 0; } device_initcall(cpuhp_sysfs_init); #endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1<<nr. * * It is used by cpumask_of() to get a constant address to a CPU * mask value that has a single bit set only. */ /* cpu_bit_bitmap[0] is empty - so we can back into it */ #define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x)) #define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1) #define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2) #define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4) const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = { MASK_DECLARE_8(0), MASK_DECLARE_8(8), MASK_DECLARE_8(16), MASK_DECLARE_8(24), #if BITS_PER_LONG > 32 MASK_DECLARE_8(32), MASK_DECLARE_8(40), MASK_DECLARE_8(48), MASK_DECLARE_8(56), #endif }; EXPORT_SYMBOL_GPL(cpu_bit_bitmap); const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE struct cpumask __cpu_possible_mask __ro_after_init = {CPU_BITS_ALL}; unsigned int __num_possible_cpus __ro_after_init = NR_CPUS; #else struct cpumask __cpu_possible_mask __ro_after_init; unsigned int __num_possible_cpus __ro_after_init; #endif EXPORT_SYMBOL(__cpu_possible_mask); EXPORT_SYMBOL(__num_possible_cpus); struct cpumask __cpu_online_mask __read_mostly; EXPORT_SYMBOL(__cpu_online_mask); struct cpumask __cpu_enabled_mask __read_mostly; EXPORT_SYMBOL(__cpu_enabled_mask); struct cpumask __cpu_present_mask __read_mostly; EXPORT_SYMBOL(__cpu_present_mask); struct cpumask __cpu_active_mask __read_mostly; EXPORT_SYMBOL(__cpu_active_mask); struct cpumask __cpu_dying_mask __read_mostly; EXPORT_SYMBOL(__cpu_dying_mask); atomic_t __num_online_cpus __read_mostly; EXPORT_SYMBOL(__num_online_cpus); void init_cpu_present(const struct cpumask *src) { cpumask_copy(&__cpu_present_mask, src); } void init_cpu_possible(const struct cpumask *src) { cpumask_copy(&__cpu_possible_mask, src); __num_possible_cpus = cpumask_weight(&__cpu_possible_mask); } void set_cpu_online(unsigned int cpu, bool online) { /* * atomic_inc/dec() is required to handle the horrid abuse of this * function by the reboot and kexec code which invoke it from * IPI/NMI broadcasts when shutting down CPUs. Invocation from * regular CPU hotplug is properly serialized. * * Note, that the fact that __num_online_cpus is of type atomic_t * does not protect readers which are not serialized against * concurrent hotplug operations. */ if (online) { if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask)) atomic_inc(&__num_online_cpus); } else { if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask)) atomic_dec(&__num_online_cpus); } } /* * This should be marked __init, but there is a boatload of call sites * which need to be fixed up to do so. Sigh... */ void set_cpu_possible(unsigned int cpu, bool possible) { if (possible) { if (!cpumask_test_and_set_cpu(cpu, &__cpu_possible_mask)) __num_possible_cpus++; } else { if (cpumask_test_and_clear_cpu(cpu, &__cpu_possible_mask)) __num_possible_cpus--; } } /* * Activate the first processor. */ void __init boot_cpu_init(void) { int cpu = smp_processor_id(); /* Mark the boot cpu "present", "online" etc for SMP and UP case */ set_cpu_online(cpu, true); set_cpu_active(cpu, true); set_cpu_present(cpu, true); set_cpu_possible(cpu, true); #ifdef CONFIG_SMP __boot_cpu_id = cpu; #endif } /* * Must be called _AFTER_ setting up the per_cpu areas */ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); atomic_set(this_cpu_ptr(&cpuhp_state.ap_sync_state), SYNC_STATE_ONLINE); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); this_cpu_write(cpuhp_state.target, CPUHP_ONLINE); } #ifdef CONFIG_CPU_MITIGATIONS /* * All except the cross-thread attack vector are mitigated by default. * Cross-thread mitigation often requires disabling SMT which is expensive * so cross-thread mitigations are only partially enabled by default. * * Guest-to-Host and Guest-to-Guest vectors are only needed if KVM support is * present. */ static bool attack_vectors[NR_CPU_ATTACK_VECTORS] __ro_after_init = { [CPU_MITIGATE_USER_KERNEL] = true, [CPU_MITIGATE_USER_USER] = true, [CPU_MITIGATE_GUEST_HOST] = IS_ENABLED(CONFIG_KVM), [CPU_MITIGATE_GUEST_GUEST] = IS_ENABLED(CONFIG_KVM), }; bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v) { if (v < NR_CPU_ATTACK_VECTORS) return attack_vectors[v]; WARN_ONCE(1, "Invalid attack vector %d\n", v); return false; } /* * There are 3 global options, 'off', 'auto', 'auto,nosmt'. These may optionally * be combined with attack-vector disables which follow them. * * Examples: * mitigations=auto,no_user_kernel,no_user_user,no_cross_thread * mitigations=auto,nosmt,no_guest_host,no_guest_guest * * mitigations=off is equivalent to disabling all attack vectors. */ enum cpu_mitigations { CPU_MITIGATIONS_OFF, CPU_MITIGATIONS_AUTO, CPU_MITIGATIONS_AUTO_NOSMT, }; enum { NO_USER_KERNEL, NO_USER_USER, NO_GUEST_HOST, NO_GUEST_GUEST, NO_CROSS_THREAD, NR_VECTOR_PARAMS, }; enum smt_mitigations smt_mitigations __ro_after_init = SMT_MITIGATIONS_AUTO; static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static const match_table_t global_mitigations = { { CPU_MITIGATIONS_AUTO_NOSMT, "auto,nosmt"}, { CPU_MITIGATIONS_AUTO, "auto"}, { CPU_MITIGATIONS_OFF, "off"}, }; static const match_table_t vector_mitigations = { { NO_USER_KERNEL, "no_user_kernel"}, { NO_USER_USER, "no_user_user"}, { NO_GUEST_HOST, "no_guest_host"}, { NO_GUEST_GUEST, "no_guest_guest"}, { NO_CROSS_THREAD, "no_cross_thread"}, { NR_VECTOR_PARAMS, NULL}, }; static int __init mitigations_parse_global_opt(char *arg) { int i; for (i = 0; i < ARRAY_SIZE(global_mitigations); i++) { const char *pattern = global_mitigations[i].pattern; if (!strncmp(arg, pattern, strlen(pattern))) { cpu_mitigations = global_mitigations[i].token; return strlen(pattern); } } return 0; } static int __init mitigations_parse_cmdline(char *arg) { char *s, *p; int len; len = mitigations_parse_global_opt(arg); if (cpu_mitigations_off()) { memset(attack_vectors, 0, sizeof(attack_vectors)); smt_mitigations = SMT_MITIGATIONS_OFF; } else if (cpu_mitigations_auto_nosmt()) { smt_mitigations = SMT_MITIGATIONS_ON; } p = arg + len; if (!*p) return 0; /* Attack vector controls may come after the ',' */ if (*p++ != ',' || !IS_ENABLED(CONFIG_ARCH_HAS_CPU_ATTACK_VECTORS)) { pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", arg); return 0; } while ((s = strsep(&p, ",")) != NULL) { switch (match_token(s, vector_mitigations, NULL)) { case NO_USER_KERNEL: attack_vectors[CPU_MITIGATE_USER_KERNEL] = false; break; case NO_USER_USER: attack_vectors[CPU_MITIGATE_USER_USER] = false; break; case NO_GUEST_HOST: attack_vectors[CPU_MITIGATE_GUEST_HOST] = false; break; case NO_GUEST_GUEST: attack_vectors[CPU_MITIGATE_GUEST_GUEST] = false; break; case NO_CROSS_THREAD: smt_mitigations = SMT_MITIGATIONS_OFF; break; default: pr_crit("Unsupported mitigations options %s\n", s); return 0; } } return 0; } /* mitigations=off */ bool cpu_mitigations_off(void) { return cpu_mitigations == CPU_MITIGATIONS_OFF; } EXPORT_SYMBOL_GPL(cpu_mitigations_off); /* mitigations=auto,nosmt */ bool cpu_mitigations_auto_nosmt(void) { return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); #else static int __init mitigations_parse_cmdline(char *arg) { pr_crit("Kernel compiled without mitigations, ignoring 'mitigations'; system may still be vulnerable\n"); return 0; } #endif early_param("mitigations", mitigations_parse_cmdline); |
| 7 7 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Spanning tree protocol; BPDU handling * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/netfilter_bridge.h> #include <linux/etherdevice.h> #include <linux/llc.h> #include <linux/slab.h> #include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> #include <net/stp.h> #include <linux/unaligned.h> #include "br_private.h" #include "br_private_stp.h" #define STP_HZ 256 #define LLC_RESERVE sizeof(struct llc_pdu_un) static int br_send_bpdu_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { return dev_queue_xmit(skb); } static void br_send_bpdu(struct net_bridge_port *p, const unsigned char *data, int length) { struct sk_buff *skb; skb = dev_alloc_skb(length+LLC_RESERVE); if (!skb) return; skb->dev = p->dev; skb->protocol = htons(ETH_P_802_2); skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, LLC_RESERVE); __skb_put_data(skb, data, length); llc_pdu_header_init(skb, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, LLC_SAP_BSPAN, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); llc_mac_hdr_init(skb, p->dev->dev_addr, p->br->group_addr); skb_reset_mac_header(skb); NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT, dev_net(p->dev), NULL, skb, NULL, skb->dev, br_send_bpdu_finish); } static inline void br_set_ticks(unsigned char *dest, int j) { unsigned long ticks = (STP_HZ * j)/ HZ; put_unaligned_be16(ticks, dest); } static inline int br_get_ticks(const unsigned char *src) { unsigned long ticks = get_unaligned_be16(src); return DIV_ROUND_UP(ticks * HZ, STP_HZ); } /* called under bridge lock */ void br_send_config_bpdu(struct net_bridge_port *p, struct br_config_bpdu *bpdu) { unsigned char buf[35]; if (p->br->stp_enabled != BR_KERNEL_STP) return; buf[0] = 0; buf[1] = 0; buf[2] = 0; buf[3] = BPDU_TYPE_CONFIG; buf[4] = (bpdu->topology_change ? 0x01 : 0) | (bpdu->topology_change_ack ? 0x80 : 0); buf[5] = bpdu->root.prio[0]; buf[6] = bpdu->root.prio[1]; buf[7] = bpdu->root.addr[0]; buf[8] = bpdu->root.addr[1]; buf[9] = bpdu->root.addr[2]; buf[10] = bpdu->root.addr[3]; buf[11] = bpdu->root.addr[4]; buf[12] = bpdu->root.addr[5]; buf[13] = (bpdu->root_path_cost >> 24) & 0xFF; buf[14] = (bpdu->root_path_cost >> 16) & 0xFF; buf[15] = (bpdu->root_path_cost >> 8) & 0xFF; buf[16] = bpdu->root_path_cost & 0xFF; buf[17] = bpdu->bridge_id.prio[0]; buf[18] = bpdu->bridge_id.prio[1]; buf[19] = bpdu->bridge_id.addr[0]; buf[20] = bpdu->bridge_id.addr[1]; buf[21] = bpdu->bridge_id.addr[2]; buf[22] = bpdu->bridge_id.addr[3]; buf[23] = bpdu->bridge_id.addr[4]; buf[24] = bpdu->bridge_id.addr[5]; buf[25] = (bpdu->port_id >> 8) & 0xFF; buf[26] = bpdu->port_id & 0xFF; br_set_ticks(buf+27, bpdu->message_age); br_set_ticks(buf+29, bpdu->max_age); br_set_ticks(buf+31, bpdu->hello_time); br_set_ticks(buf+33, bpdu->forward_delay); br_send_bpdu(p, buf, 35); p->stp_xstats.tx_bpdu++; } /* called under bridge lock */ void br_send_tcn_bpdu(struct net_bridge_port *p) { unsigned char buf[4]; if (p->br->stp_enabled != BR_KERNEL_STP) return; buf[0] = 0; buf[1] = 0; buf[2] = 0; buf[3] = BPDU_TYPE_TCN; br_send_bpdu(p, buf, 4); p->stp_xstats.tx_tcn++; } /* * Called from llc. * * NO locks, but rcu_read_lock */ void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, struct net_device *dev) { struct net_bridge_port *p; struct net_bridge *br; const unsigned char *buf; if (!pskb_may_pull(skb, 4)) goto err; /* compare of protocol id and version */ buf = skb->data; if (buf[0] != 0 || buf[1] != 0 || buf[2] != 0) goto err; p = br_port_get_check_rcu(dev); if (!p) goto err; br = p->br; spin_lock(&br->lock); if (br->stp_enabled != BR_KERNEL_STP) goto out; if (!(br->dev->flags & IFF_UP)) goto out; if (p->state == BR_STATE_DISABLED) goto out; if (!ether_addr_equal(eth_hdr(skb)->h_dest, br->group_addr)) goto out; if (p->flags & BR_BPDU_GUARD) { br_notice(br, "BPDU received on blocked port %u(%s)\n", (unsigned int) p->port_no, p->dev->name); br_stp_disable_port(p); goto out; } buf = skb_pull(skb, 3); if (buf[0] == BPDU_TYPE_CONFIG) { struct br_config_bpdu bpdu; if (!pskb_may_pull(skb, 32)) goto out; buf = skb->data; bpdu.topology_change = (buf[1] & 0x01) ? 1 : 0; bpdu.topology_change_ack = (buf[1] & 0x80) ? 1 : 0; bpdu.root.prio[0] = buf[2]; bpdu.root.prio[1] = buf[3]; bpdu.root.addr[0] = buf[4]; bpdu.root.addr[1] = buf[5]; bpdu.root.addr[2] = buf[6]; bpdu.root.addr[3] = buf[7]; bpdu.root.addr[4] = buf[8]; bpdu.root.addr[5] = buf[9]; bpdu.root_path_cost = (buf[10] << 24) | (buf[11] << 16) | (buf[12] << 8) | buf[13]; bpdu.bridge_id.prio[0] = buf[14]; bpdu.bridge_id.prio[1] = buf[15]; bpdu.bridge_id.addr[0] = buf[16]; bpdu.bridge_id.addr[1] = buf[17]; bpdu.bridge_id.addr[2] = buf[18]; bpdu.bridge_id.addr[3] = buf[19]; bpdu.bridge_id.addr[4] = buf[20]; bpdu.bridge_id.addr[5] = buf[21]; bpdu.port_id = (buf[22] << 8) | buf[23]; bpdu.message_age = br_get_ticks(buf+24); bpdu.max_age = br_get_ticks(buf+26); bpdu.hello_time = br_get_ticks(buf+28); bpdu.forward_delay = br_get_ticks(buf+30); if (bpdu.message_age > bpdu.max_age) { if (net_ratelimit()) br_notice(p->br, "port %u config from %pM" " (message_age %ul > max_age %ul)\n", p->port_no, eth_hdr(skb)->h_source, bpdu.message_age, bpdu.max_age); goto out; } br_received_config_bpdu(p, &bpdu); } else if (buf[0] == BPDU_TYPE_TCN) { br_received_tcn_bpdu(p); } out: spin_unlock(&br->lock); err: kfree_skb(skb); } |
| 91 103 103 103 99 105 105 104 105 105 105 1 1 1 104 105 1 1 104 104 104 104 1 1 1 1 1 1 103 3 3 20 14 13 13 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 | // SPDX-License-Identifier: GPL-2.0-or-later /* * drivers/net/bond/bond_netlink.c - Netlink interface for bonding * Copyright (c) 2013 Jiri Pirko <jiri@resnulli.us> * Copyright (c) 2013 Scott Feldman <sfeldma@cumulusnetworks.com> */ #include <linux/module.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/if_link.h> #include <linux/if_ether.h> #include <net/netlink.h> #include <net/rtnetlink.h> #include <net/bonding.h> #include <net/ipv6.h> static size_t bond_get_slave_size(const struct net_device *bond_dev, const struct net_device *slave_dev) { return nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_STATE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_MII_STATUS */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_SLAVE_LINK_FAILURE_COUNT */ nla_total_size(MAX_ADDR_LEN) + /* IFLA_BOND_SLAVE_PERM_HWADDR */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_QUEUE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_AD_AGGREGATOR_ID */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE */ nla_total_size(sizeof(s32)) + /* IFLA_BOND_SLAVE_PRIO */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_SLAVE_ACTOR_PORT_PRIO */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_AD_CHURN_ACTOR_STATE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_SLAVE_AD_CHURN_PARTNER_STATE */ 0; } static int bond_fill_slave_info(struct sk_buff *skb, const struct net_device *bond_dev, const struct net_device *slave_dev) { struct slave *slave = bond_slave_get_rtnl(slave_dev); if (nla_put_u8(skb, IFLA_BOND_SLAVE_STATE, bond_slave_state(slave))) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_SLAVE_MII_STATUS, slave->link)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_SLAVE_LINK_FAILURE_COUNT, slave->link_failure_count)) goto nla_put_failure; if (nla_put(skb, IFLA_BOND_SLAVE_PERM_HWADDR, slave_dev->addr_len, slave->perm_hwaddr)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_SLAVE_QUEUE_ID, READ_ONCE(slave->queue_id))) goto nla_put_failure; if (nla_put_s32(skb, IFLA_BOND_SLAVE_PRIO, slave->prio)) goto nla_put_failure; if (BOND_MODE(slave->bond) == BOND_MODE_8023AD) { const struct aggregator *agg; const struct port *ad_port; ad_port = &SLAVE_AD_INFO(slave)->port; rcu_read_lock(); agg = rcu_dereference(SLAVE_AD_INFO(slave)->port.aggregator); if (agg) { if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_AGGREGATOR_ID, agg->aggregator_identifier)) goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_ACTOR_OPER_PORT_STATE, ad_port->actor_oper_port_state)) goto nla_put_failure_rcu; if (nla_put_u16(skb, IFLA_BOND_SLAVE_AD_PARTNER_OPER_PORT_STATE, ad_port->partner_oper.port_state)) goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_ACTOR_STATE, ad_port->sm_churn_actor_state)) goto nla_put_failure_rcu; if (nla_put_u8(skb, IFLA_BOND_SLAVE_AD_CHURN_PARTNER_STATE, ad_port->sm_churn_partner_state)) goto nla_put_failure_rcu; } rcu_read_unlock(); if (nla_put_u16(skb, IFLA_BOND_SLAVE_ACTOR_PORT_PRIO, SLAVE_AD_INFO(slave)->port_priority)) goto nla_put_failure; } return 0; nla_put_failure_rcu: rcu_read_unlock(); nla_put_failure: return -EMSGSIZE; } /* Limit the max delay range to 300s */ static const struct netlink_range_validation delay_range = { .max = 300000, }; static const struct nla_policy bond_policy[IFLA_BOND_MAX + 1] = { [IFLA_BOND_MODE] = { .type = NLA_U8 }, [IFLA_BOND_ACTIVE_SLAVE] = { .type = NLA_U32 }, [IFLA_BOND_MIIMON] = { .type = NLA_U32 }, [IFLA_BOND_UPDELAY] = { .type = NLA_U32 }, [IFLA_BOND_DOWNDELAY] = { .type = NLA_U32 }, [IFLA_BOND_USE_CARRIER] = { .type = NLA_U8 }, [IFLA_BOND_ARP_INTERVAL] = { .type = NLA_U32 }, [IFLA_BOND_ARP_IP_TARGET] = { .type = NLA_NESTED }, [IFLA_BOND_ARP_VALIDATE] = { .type = NLA_U32 }, [IFLA_BOND_ARP_ALL_TARGETS] = { .type = NLA_U32 }, [IFLA_BOND_PRIMARY] = { .type = NLA_U32 }, [IFLA_BOND_PRIMARY_RESELECT] = { .type = NLA_U8 }, [IFLA_BOND_FAIL_OVER_MAC] = { .type = NLA_U8 }, [IFLA_BOND_XMIT_HASH_POLICY] = { .type = NLA_U8 }, [IFLA_BOND_RESEND_IGMP] = { .type = NLA_U32 }, [IFLA_BOND_NUM_PEER_NOTIF] = { .type = NLA_U8 }, [IFLA_BOND_ALL_SLAVES_ACTIVE] = { .type = NLA_U8 }, [IFLA_BOND_MIN_LINKS] = { .type = NLA_U32 }, [IFLA_BOND_LP_INTERVAL] = { .type = NLA_U32 }, [IFLA_BOND_PACKETS_PER_SLAVE] = { .type = NLA_U32 }, [IFLA_BOND_AD_LACP_ACTIVE] = { .type = NLA_U8 }, [IFLA_BOND_AD_LACP_RATE] = { .type = NLA_U8 }, [IFLA_BOND_AD_SELECT] = { .type = NLA_U8 }, [IFLA_BOND_AD_INFO] = { .type = NLA_NESTED }, [IFLA_BOND_AD_ACTOR_SYS_PRIO] = { .type = NLA_U16 }, [IFLA_BOND_AD_USER_PORT_KEY] = { .type = NLA_U16 }, [IFLA_BOND_AD_ACTOR_SYSTEM] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BOND_TLB_DYNAMIC_LB] = { .type = NLA_U8 }, [IFLA_BOND_PEER_NOTIF_DELAY] = NLA_POLICY_FULL_RANGE(NLA_U32, &delay_range), [IFLA_BOND_MISSED_MAX] = { .type = NLA_U8 }, [IFLA_BOND_NS_IP6_TARGET] = { .type = NLA_NESTED }, [IFLA_BOND_COUPLED_CONTROL] = { .type = NLA_U8 }, [IFLA_BOND_BROADCAST_NEIGH] = { .type = NLA_U8 }, }; static const struct nla_policy bond_slave_policy[IFLA_BOND_SLAVE_MAX + 1] = { [IFLA_BOND_SLAVE_QUEUE_ID] = { .type = NLA_U16 }, [IFLA_BOND_SLAVE_PRIO] = { .type = NLA_S32 }, [IFLA_BOND_SLAVE_ACTOR_PORT_PRIO] = { .type = NLA_U16 }, }; static int bond_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } return 0; } static int bond_slave_changelink(struct net_device *bond_dev, struct net_device *slave_dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); struct bond_opt_value newval; int err; if (!data) return 0; if (data[IFLA_BOND_SLAVE_QUEUE_ID]) { u16 queue_id = nla_get_u16(data[IFLA_BOND_SLAVE_QUEUE_ID]); char queue_id_str[IFNAMSIZ + 7]; /* queue_id option setting expects slave_name:queue_id */ snprintf(queue_id_str, sizeof(queue_id_str), "%s:%u\n", slave_dev->name, queue_id); bond_opt_initstr(&newval, queue_id_str); err = __bond_opt_set(bond, BOND_OPT_QUEUE_ID, &newval, data[IFLA_BOND_SLAVE_QUEUE_ID], extack); if (err) return err; } if (data[IFLA_BOND_SLAVE_PRIO]) { int prio = nla_get_s32(data[IFLA_BOND_SLAVE_PRIO]); bond_opt_slave_initval(&newval, &slave_dev, prio); err = __bond_opt_set(bond, BOND_OPT_PRIO, &newval, data[IFLA_BOND_SLAVE_PRIO], extack); if (err) return err; } if (data[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO]) { u16 ad_prio = nla_get_u16(data[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO]); bond_opt_slave_initval(&newval, &slave_dev, ad_prio); err = __bond_opt_set(bond, BOND_OPT_ACTOR_PORT_PRIO, &newval, data[IFLA_BOND_SLAVE_ACTOR_PORT_PRIO], extack); if (err) return err; } return 0; } static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); struct bond_opt_value newval; int miimon = 0; int err; if (!data) return 0; if (data[IFLA_BOND_MODE]) { int mode = nla_get_u8(data[IFLA_BOND_MODE]); bond_opt_initval(&newval, mode); err = __bond_opt_set(bond, BOND_OPT_MODE, &newval, data[IFLA_BOND_MODE], extack); if (err) return err; } if (data[IFLA_BOND_ACTIVE_SLAVE]) { int ifindex = nla_get_u32(data[IFLA_BOND_ACTIVE_SLAVE]); struct net_device *slave_dev; char *active_slave = ""; if (ifindex != 0) { slave_dev = __dev_get_by_index(dev_net(bond_dev), ifindex); if (!slave_dev) return -ENODEV; active_slave = slave_dev->name; } bond_opt_initstr(&newval, active_slave); err = __bond_opt_set(bond, BOND_OPT_ACTIVE_SLAVE, &newval, data[IFLA_BOND_ACTIVE_SLAVE], extack); if (err) return err; } if (data[IFLA_BOND_MIIMON]) { miimon = nla_get_u32(data[IFLA_BOND_MIIMON]); bond_opt_initval(&newval, miimon); err = __bond_opt_set(bond, BOND_OPT_MIIMON, &newval, data[IFLA_BOND_MIIMON], extack); if (err) return err; } if (data[IFLA_BOND_UPDELAY]) { int updelay = nla_get_u32(data[IFLA_BOND_UPDELAY]); bond_opt_initval(&newval, updelay); err = __bond_opt_set(bond, BOND_OPT_UPDELAY, &newval, data[IFLA_BOND_UPDELAY], extack); if (err) return err; } if (data[IFLA_BOND_DOWNDELAY]) { int downdelay = nla_get_u32(data[IFLA_BOND_DOWNDELAY]); bond_opt_initval(&newval, downdelay); err = __bond_opt_set(bond, BOND_OPT_DOWNDELAY, &newval, data[IFLA_BOND_DOWNDELAY], extack); if (err) return err; } if (data[IFLA_BOND_PEER_NOTIF_DELAY]) { int delay = nla_get_u32(data[IFLA_BOND_PEER_NOTIF_DELAY]); bond_opt_initval(&newval, delay); err = __bond_opt_set(bond, BOND_OPT_PEER_NOTIF_DELAY, &newval, data[IFLA_BOND_PEER_NOTIF_DELAY], extack); if (err) return err; } if (data[IFLA_BOND_USE_CARRIER]) { if (nla_get_u8(data[IFLA_BOND_USE_CARRIER]) != 1) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_BOND_USE_CARRIER], "option obsolete, use_carrier cannot be disabled"); return -EINVAL; } } if (data[IFLA_BOND_ARP_INTERVAL]) { int arp_interval = nla_get_u32(data[IFLA_BOND_ARP_INTERVAL]); if (arp_interval && miimon) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_BOND_ARP_INTERVAL], "ARP monitoring cannot be used with MII monitoring"); return -EINVAL; } bond_opt_initval(&newval, arp_interval); err = __bond_opt_set(bond, BOND_OPT_ARP_INTERVAL, &newval, data[IFLA_BOND_ARP_INTERVAL], extack); if (err) return err; } if (data[IFLA_BOND_ARP_IP_TARGET]) { struct nlattr *attr; int i = 0, rem; bond_option_arp_ip_targets_clear(bond); nla_for_each_nested(attr, data[IFLA_BOND_ARP_IP_TARGET], rem) { __be32 target; if (nla_len(attr) < sizeof(target)) return -EINVAL; target = nla_get_be32(attr); bond_opt_initval(&newval, (__force u64)target); err = __bond_opt_set(bond, BOND_OPT_ARP_TARGETS, &newval, data[IFLA_BOND_ARP_IP_TARGET], extack); if (err) break; i++; } if (i == 0 && bond->params.arp_interval) netdev_warn(bond->dev, "Removing last arp target with arp_interval on\n"); if (err) return err; } #if IS_ENABLED(CONFIG_IPV6) if (data[IFLA_BOND_NS_IP6_TARGET]) { struct nlattr *attr; int i = 0, rem; bond_option_ns_ip6_targets_clear(bond); nla_for_each_nested(attr, data[IFLA_BOND_NS_IP6_TARGET], rem) { struct in6_addr addr6; if (nla_len(attr) < sizeof(addr6)) { NL_SET_ERR_MSG(extack, "Invalid IPv6 address"); return -EINVAL; } addr6 = nla_get_in6_addr(attr); bond_opt_initextra(&newval, &addr6, sizeof(addr6)); err = __bond_opt_set(bond, BOND_OPT_NS_TARGETS, &newval, data[IFLA_BOND_NS_IP6_TARGET], extack); if (err) break; i++; } if (i == 0 && bond->params.arp_interval) netdev_warn(bond->dev, "Removing last ns target with arp_interval on\n"); if (err) return err; } #endif if (data[IFLA_BOND_ARP_VALIDATE]) { int arp_validate = nla_get_u32(data[IFLA_BOND_ARP_VALIDATE]); if (arp_validate && miimon) { NL_SET_ERR_MSG_ATTR(extack, data[IFLA_BOND_ARP_INTERVAL], "ARP validating cannot be used with MII monitoring"); return -EINVAL; } bond_opt_initval(&newval, arp_validate); err = __bond_opt_set(bond, BOND_OPT_ARP_VALIDATE, &newval, data[IFLA_BOND_ARP_VALIDATE], extack); if (err) return err; } if (data[IFLA_BOND_ARP_ALL_TARGETS]) { int arp_all_targets = nla_get_u32(data[IFLA_BOND_ARP_ALL_TARGETS]); bond_opt_initval(&newval, arp_all_targets); err = __bond_opt_set(bond, BOND_OPT_ARP_ALL_TARGETS, &newval, data[IFLA_BOND_ARP_ALL_TARGETS], extack); if (err) return err; } if (data[IFLA_BOND_PRIMARY]) { int ifindex = nla_get_u32(data[IFLA_BOND_PRIMARY]); struct net_device *dev; char *primary = ""; dev = __dev_get_by_index(dev_net(bond_dev), ifindex); if (dev) primary = dev->name; bond_opt_initstr(&newval, primary); err = __bond_opt_set(bond, BOND_OPT_PRIMARY, &newval, data[IFLA_BOND_PRIMARY], extack); if (err) return err; } if (data[IFLA_BOND_PRIMARY_RESELECT]) { int primary_reselect = nla_get_u8(data[IFLA_BOND_PRIMARY_RESELECT]); bond_opt_initval(&newval, primary_reselect); err = __bond_opt_set(bond, BOND_OPT_PRIMARY_RESELECT, &newval, data[IFLA_BOND_PRIMARY_RESELECT], extack); if (err) return err; } if (data[IFLA_BOND_FAIL_OVER_MAC]) { int fail_over_mac = nla_get_u8(data[IFLA_BOND_FAIL_OVER_MAC]); bond_opt_initval(&newval, fail_over_mac); err = __bond_opt_set(bond, BOND_OPT_FAIL_OVER_MAC, &newval, data[IFLA_BOND_FAIL_OVER_MAC], extack); if (err) return err; } if (data[IFLA_BOND_XMIT_HASH_POLICY]) { int xmit_hash_policy = nla_get_u8(data[IFLA_BOND_XMIT_HASH_POLICY]); bond_opt_initval(&newval, xmit_hash_policy); err = __bond_opt_set(bond, BOND_OPT_XMIT_HASH, &newval, data[IFLA_BOND_XMIT_HASH_POLICY], extack); if (err) return err; } if (data[IFLA_BOND_RESEND_IGMP]) { int resend_igmp = nla_get_u32(data[IFLA_BOND_RESEND_IGMP]); bond_opt_initval(&newval, resend_igmp); err = __bond_opt_set(bond, BOND_OPT_RESEND_IGMP, &newval, data[IFLA_BOND_RESEND_IGMP], extack); if (err) return err; } if (data[IFLA_BOND_NUM_PEER_NOTIF]) { int num_peer_notif = nla_get_u8(data[IFLA_BOND_NUM_PEER_NOTIF]); bond_opt_initval(&newval, num_peer_notif); err = __bond_opt_set(bond, BOND_OPT_NUM_PEER_NOTIF, &newval, data[IFLA_BOND_NUM_PEER_NOTIF], extack); if (err) return err; } if (data[IFLA_BOND_ALL_SLAVES_ACTIVE]) { int all_slaves_active = nla_get_u8(data[IFLA_BOND_ALL_SLAVES_ACTIVE]); bond_opt_initval(&newval, all_slaves_active); err = __bond_opt_set(bond, BOND_OPT_ALL_SLAVES_ACTIVE, &newval, data[IFLA_BOND_ALL_SLAVES_ACTIVE], extack); if (err) return err; } if (data[IFLA_BOND_MIN_LINKS]) { int min_links = nla_get_u32(data[IFLA_BOND_MIN_LINKS]); bond_opt_initval(&newval, min_links); err = __bond_opt_set(bond, BOND_OPT_MINLINKS, &newval, data[IFLA_BOND_MIN_LINKS], extack); if (err) return err; } if (data[IFLA_BOND_LP_INTERVAL]) { int lp_interval = nla_get_u32(data[IFLA_BOND_LP_INTERVAL]); bond_opt_initval(&newval, lp_interval); err = __bond_opt_set(bond, BOND_OPT_LP_INTERVAL, &newval, data[IFLA_BOND_LP_INTERVAL], extack); if (err) return err; } if (data[IFLA_BOND_PACKETS_PER_SLAVE]) { int packets_per_slave = nla_get_u32(data[IFLA_BOND_PACKETS_PER_SLAVE]); bond_opt_initval(&newval, packets_per_slave); err = __bond_opt_set(bond, BOND_OPT_PACKETS_PER_SLAVE, &newval, data[IFLA_BOND_PACKETS_PER_SLAVE], extack); if (err) return err; } if (data[IFLA_BOND_AD_LACP_ACTIVE]) { int lacp_active = nla_get_u8(data[IFLA_BOND_AD_LACP_ACTIVE]); bond_opt_initval(&newval, lacp_active); err = __bond_opt_set(bond, BOND_OPT_LACP_ACTIVE, &newval, data[IFLA_BOND_AD_LACP_ACTIVE], extack); if (err) return err; } if (data[IFLA_BOND_AD_LACP_RATE]) { int lacp_rate = nla_get_u8(data[IFLA_BOND_AD_LACP_RATE]); bond_opt_initval(&newval, lacp_rate); err = __bond_opt_set(bond, BOND_OPT_LACP_RATE, &newval, data[IFLA_BOND_AD_LACP_RATE], extack); if (err) return err; } if (data[IFLA_BOND_AD_SELECT]) { int ad_select = nla_get_u8(data[IFLA_BOND_AD_SELECT]); bond_opt_initval(&newval, ad_select); err = __bond_opt_set(bond, BOND_OPT_AD_SELECT, &newval, data[IFLA_BOND_AD_SELECT], extack); if (err) return err; } if (data[IFLA_BOND_AD_ACTOR_SYS_PRIO]) { int actor_sys_prio = nla_get_u16(data[IFLA_BOND_AD_ACTOR_SYS_PRIO]); bond_opt_initval(&newval, actor_sys_prio); err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYS_PRIO, &newval, data[IFLA_BOND_AD_ACTOR_SYS_PRIO], extack); if (err) return err; } if (data[IFLA_BOND_AD_USER_PORT_KEY]) { int port_key = nla_get_u16(data[IFLA_BOND_AD_USER_PORT_KEY]); bond_opt_initval(&newval, port_key); err = __bond_opt_set(bond, BOND_OPT_AD_USER_PORT_KEY, &newval, data[IFLA_BOND_AD_USER_PORT_KEY], extack); if (err) return err; } if (data[IFLA_BOND_AD_ACTOR_SYSTEM]) { if (nla_len(data[IFLA_BOND_AD_ACTOR_SYSTEM]) != ETH_ALEN) return -EINVAL; bond_opt_initval(&newval, nla_get_u64(data[IFLA_BOND_AD_ACTOR_SYSTEM])); err = __bond_opt_set(bond, BOND_OPT_AD_ACTOR_SYSTEM, &newval, data[IFLA_BOND_AD_ACTOR_SYSTEM], extack); if (err) return err; } if (data[IFLA_BOND_TLB_DYNAMIC_LB]) { int dynamic_lb = nla_get_u8(data[IFLA_BOND_TLB_DYNAMIC_LB]); bond_opt_initval(&newval, dynamic_lb); err = __bond_opt_set(bond, BOND_OPT_TLB_DYNAMIC_LB, &newval, data[IFLA_BOND_TLB_DYNAMIC_LB], extack); if (err) return err; } if (data[IFLA_BOND_MISSED_MAX]) { int missed_max = nla_get_u8(data[IFLA_BOND_MISSED_MAX]); bond_opt_initval(&newval, missed_max); err = __bond_opt_set(bond, BOND_OPT_MISSED_MAX, &newval, data[IFLA_BOND_MISSED_MAX], extack); if (err) return err; } if (data[IFLA_BOND_COUPLED_CONTROL]) { int coupled_control = nla_get_u8(data[IFLA_BOND_COUPLED_CONTROL]); bond_opt_initval(&newval, coupled_control); err = __bond_opt_set(bond, BOND_OPT_COUPLED_CONTROL, &newval, data[IFLA_BOND_COUPLED_CONTROL], extack); if (err) return err; } if (data[IFLA_BOND_BROADCAST_NEIGH]) { int broadcast_neigh = nla_get_u8(data[IFLA_BOND_BROADCAST_NEIGH]); bond_opt_initval(&newval, broadcast_neigh); err = __bond_opt_set(bond, BOND_OPT_BROADCAST_NEIGH, &newval, data[IFLA_BOND_BROADCAST_NEIGH], extack); if (err) return err; } return 0; } static int bond_newlink(struct net_device *bond_dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct bonding *bond = netdev_priv(bond_dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; int err; err = register_netdevice(bond_dev); if (err) return err; netif_carrier_off(bond_dev); bond_work_init_all(bond); err = bond_changelink(bond_dev, tb, data, extack); if (err) { bond_work_cancel_all(bond); unregister_netdevice(bond_dev); } return err; } static size_t bond_get_size(const struct net_device *bond_dev) { return nla_total_size(sizeof(u8)) + /* IFLA_BOND_MODE */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_ACTIVE_SLAVE */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIIMON */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_UPDELAY */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_DOWNDELAY */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_USE_CARRIER */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_INTERVAL */ /* IFLA_BOND_ARP_IP_TARGET */ nla_total_size(sizeof(struct nlattr)) + nla_total_size(sizeof(u32)) * BOND_MAX_ARP_TARGETS + nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_VALIDATE */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_ARP_ALL_TARGETS */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_PRIMARY */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_PRIMARY_RESELECT */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_FAIL_OVER_MAC */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_XMIT_HASH_POLICY */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_RESEND_IGMP */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_NUM_PEER_NOTIF */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_ALL_SLAVES_ACTIVE */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_MIN_LINKS */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_LP_INTERVAL */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_PACKETS_PER_SLAVE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_LACP_ACTIVE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_LACP_RATE */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_AD_SELECT */ nla_total_size(sizeof(struct nlattr)) + /* IFLA_BOND_AD_INFO */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_AGGREGATOR */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_NUM_PORTS */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_ACTOR_KEY */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_INFO_PARTNER_KEY*/ nla_total_size(ETH_ALEN) + /* IFLA_BOND_AD_INFO_PARTNER_MAC*/ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_ACTOR_SYS_PRIO */ nla_total_size(sizeof(u16)) + /* IFLA_BOND_AD_USER_PORT_KEY */ nla_total_size(ETH_ALEN) + /* IFLA_BOND_AD_ACTOR_SYSTEM */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_TLB_DYNAMIC_LB */ nla_total_size(sizeof(u32)) + /* IFLA_BOND_PEER_NOTIF_DELAY */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_MISSED_MAX */ /* IFLA_BOND_NS_IP6_TARGET */ nla_total_size(sizeof(struct nlattr)) + nla_total_size(sizeof(struct in6_addr)) * BOND_MAX_NS_TARGETS + nla_total_size(sizeof(u8)) + /* IFLA_BOND_COUPLED_CONTROL */ nla_total_size(sizeof(u8)) + /* IFLA_BOND_BROADCAST_NEIGH */ 0; } static int bond_option_active_slave_get_ifindex(struct bonding *bond) { const struct net_device *slave; int ifindex; rcu_read_lock(); slave = bond_option_active_slave_get_rcu(bond); ifindex = slave ? slave->ifindex : 0; rcu_read_unlock(); return ifindex; } static int bond_fill_info(struct sk_buff *skb, const struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); unsigned int packets_per_slave; int ifindex, i, targets_added; struct nlattr *targets; struct slave *primary; if (nla_put_u8(skb, IFLA_BOND_MODE, BOND_MODE(bond))) goto nla_put_failure; ifindex = bond_option_active_slave_get_ifindex(bond); if (ifindex && nla_put_u32(skb, IFLA_BOND_ACTIVE_SLAVE, ifindex)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_MIIMON, bond->params.miimon)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_UPDELAY, bond->params.updelay * bond->params.miimon)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_DOWNDELAY, bond->params.downdelay * bond->params.miimon)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_PEER_NOTIF_DELAY, bond->params.peer_notif_delay * bond->params.miimon)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_USE_CARRIER, 1)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_ARP_INTERVAL, bond->params.arp_interval)) goto nla_put_failure; targets = nla_nest_start_noflag(skb, IFLA_BOND_ARP_IP_TARGET); if (!targets) goto nla_put_failure; targets_added = 0; for (i = 0; i < BOND_MAX_ARP_TARGETS; i++) { if (bond->params.arp_targets[i]) { if (nla_put_be32(skb, i, bond->params.arp_targets[i])) goto nla_put_failure; targets_added = 1; } } if (targets_added) nla_nest_end(skb, targets); else nla_nest_cancel(skb, targets); if (nla_put_u32(skb, IFLA_BOND_ARP_VALIDATE, bond->params.arp_validate)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_ARP_ALL_TARGETS, bond->params.arp_all_targets)) goto nla_put_failure; #if IS_ENABLED(CONFIG_IPV6) targets = nla_nest_start(skb, IFLA_BOND_NS_IP6_TARGET); if (!targets) goto nla_put_failure; targets_added = 0; for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { if (!ipv6_addr_any(&bond->params.ns_targets[i])) { if (nla_put_in6_addr(skb, i, &bond->params.ns_targets[i])) goto nla_put_failure; targets_added = 1; } } if (targets_added) nla_nest_end(skb, targets); else nla_nest_cancel(skb, targets); #endif primary = rtnl_dereference(bond->primary_slave); if (primary && nla_put_u32(skb, IFLA_BOND_PRIMARY, primary->dev->ifindex)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_PRIMARY_RESELECT, bond->params.primary_reselect)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_FAIL_OVER_MAC, bond->params.fail_over_mac)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_XMIT_HASH_POLICY, bond->params.xmit_policy)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_RESEND_IGMP, bond->params.resend_igmp)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_NUM_PEER_NOTIF, bond->params.num_peer_notif)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_ALL_SLAVES_ACTIVE, bond->params.all_slaves_active)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_MIN_LINKS, bond->params.min_links)) goto nla_put_failure; if (nla_put_u32(skb, IFLA_BOND_LP_INTERVAL, bond->params.lp_interval)) goto nla_put_failure; packets_per_slave = bond->params.packets_per_slave; if (nla_put_u32(skb, IFLA_BOND_PACKETS_PER_SLAVE, packets_per_slave)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_AD_LACP_ACTIVE, bond->params.lacp_active)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_AD_LACP_RATE, bond->params.lacp_fast)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_AD_SELECT, bond->params.ad_select)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_TLB_DYNAMIC_LB, bond->params.tlb_dynamic_lb)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_MISSED_MAX, bond->params.missed_max)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_COUPLED_CONTROL, bond->params.coupled_control)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_BOND_BROADCAST_NEIGH, bond->params.broadcast_neighbor)) goto nla_put_failure; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct ad_info info; if (capable(CAP_NET_ADMIN)) { if (nla_put_u16(skb, IFLA_BOND_AD_ACTOR_SYS_PRIO, bond->params.ad_actor_sys_prio)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_USER_PORT_KEY, bond->params.ad_user_port_key)) goto nla_put_failure; if (nla_put(skb, IFLA_BOND_AD_ACTOR_SYSTEM, ETH_ALEN, &bond->params.ad_actor_system)) goto nla_put_failure; } if (!bond_3ad_get_active_agg_info(bond, &info)) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, IFLA_BOND_AD_INFO); if (!nest) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_INFO_AGGREGATOR, info.aggregator_id)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_INFO_NUM_PORTS, info.ports)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_INFO_ACTOR_KEY, info.actor_key)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_BOND_AD_INFO_PARTNER_KEY, info.partner_key)) goto nla_put_failure; if (nla_put(skb, IFLA_BOND_AD_INFO_PARTNER_MAC, sizeof(info.partner_system), &info.partner_system)) goto nla_put_failure; nla_nest_end(skb, nest); } } return 0; nla_put_failure: return -EMSGSIZE; } static size_t bond_get_linkxstats_size(const struct net_device *dev, int attr) { switch (attr) { case IFLA_STATS_LINK_XSTATS: case IFLA_STATS_LINK_XSTATS_SLAVE: break; default: return 0; } return bond_3ad_stats_size() + nla_total_size(0); } static int bond_fill_linkxstats(struct sk_buff *skb, const struct net_device *dev, int *prividx, int attr) { struct nlattr *nla __maybe_unused; struct slave *slave = NULL; struct nlattr *nest, *nest2; struct bonding *bond; switch (attr) { case IFLA_STATS_LINK_XSTATS: bond = netdev_priv(dev); break; case IFLA_STATS_LINK_XSTATS_SLAVE: slave = bond_slave_get_rtnl(dev); if (!slave) return 0; bond = slave->bond; break; default: return -EINVAL; } nest = nla_nest_start_noflag(skb, LINK_XSTATS_TYPE_BOND); if (!nest) return -EMSGSIZE; if (BOND_MODE(bond) == BOND_MODE_8023AD) { struct bond_3ad_stats *stats; if (slave) stats = &SLAVE_AD_INFO(slave)->stats; else stats = &BOND_AD_INFO(bond).stats; nest2 = nla_nest_start_noflag(skb, BOND_XSTATS_3AD); if (!nest2) { nla_nest_end(skb, nest); return -EMSGSIZE; } if (bond_3ad_stats_fill(skb, stats)) { nla_nest_cancel(skb, nest2); nla_nest_end(skb, nest); return -EMSGSIZE; } nla_nest_end(skb, nest2); } nla_nest_end(skb, nest); return 0; } struct rtnl_link_ops bond_link_ops __read_mostly = { .kind = "bond", .priv_size = sizeof(struct bonding), .setup = bond_setup, .maxtype = IFLA_BOND_MAX, .policy = bond_policy, .validate = bond_validate, .newlink = bond_newlink, .changelink = bond_changelink, .get_size = bond_get_size, .fill_info = bond_fill_info, .get_num_tx_queues = bond_get_num_tx_queues, .get_num_rx_queues = bond_get_num_tx_queues, /* Use the same number as for TX queues */ .fill_linkxstats = bond_fill_linkxstats, .get_linkxstats_size = bond_get_linkxstats_size, .slave_maxtype = IFLA_BOND_SLAVE_MAX, .slave_policy = bond_slave_policy, .slave_changelink = bond_slave_changelink, .get_slave_size = bond_get_slave_size, .fill_slave_info = bond_fill_slave_info, }; int __init bond_netlink_init(void) { return rtnl_link_register(&bond_link_ops); } void bond_netlink_fini(void) { rtnl_link_unregister(&bond_link_ops); } MODULE_ALIAS_RTNL_LINK("bond"); |
| 555 554 190 189 162 162 36 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 | // SPDX-License-Identifier: GPL-2.0 /* * shstk.c - Intel shadow stack support * * Copyright (c) 2021, Intel Corporation. * Yu-cheng Yu <yu-cheng.yu@intel.com> */ #include <linux/sched.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/sched/signal.h> #include <linux/compat.h> #include <linux/sizes.h> #include <linux/user.h> #include <linux/syscalls.h> #include <asm/msr.h> #include <asm/fpu/xstate.h> #include <asm/fpu/types.h> #include <asm/shstk.h> #include <asm/special_insns.h> #include <asm/fpu/api.h> #include <asm/prctl.h> #define SS_FRAME_SIZE 8 static bool features_enabled(unsigned long features) { return current->thread.features & features; } static void features_set(unsigned long features) { current->thread.features |= features; } static void features_clr(unsigned long features) { current->thread.features &= ~features; } /* * Create a restore token on the shadow stack. A token is always 8-byte * and aligned to 8. */ static int create_rstor_token(unsigned long ssp, unsigned long *token_addr) { unsigned long addr; /* Token must be aligned */ if (!IS_ALIGNED(ssp, 8)) return -EINVAL; addr = ssp - SS_FRAME_SIZE; /* * SSP is aligned, so reserved bits and mode bit are a zero, just mark * the token 64-bit. */ ssp |= BIT(0); if (write_user_shstk_64((u64 __user *)addr, (u64)ssp)) return -EFAULT; if (token_addr) *token_addr = addr; return 0; } /* * VM_SHADOW_STACK will have a guard page. This helps userspace protect * itself from attacks. The reasoning is as follows: * * The shadow stack pointer(SSP) is moved by CALL, RET, and INCSSPQ. The * INCSSP instruction can increment the shadow stack pointer. It is the * shadow stack analog of an instruction like: * * addq $0x80, %rsp * * However, there is one important difference between an ADD on %rsp * and INCSSP. In addition to modifying SSP, INCSSP also reads from the * memory of the first and last elements that were "popped". It can be * thought of as acting like this: * * READ_ONCE(ssp); // read+discard top element on stack * ssp += nr_to_pop * 8; // move the shadow stack * READ_ONCE(ssp-8); // read+discard last popped stack element * * The maximum distance INCSSP can move the SSP is 2040 bytes, before * it would read the memory. Therefore a single page gap will be enough * to prevent any operation from shifting the SSP to an adjacent stack, * since it would have to land in the gap at least once, causing a * fault. */ static unsigned long alloc_shstk(unsigned long addr, unsigned long size, unsigned long token_offset, bool set_res_tok) { unsigned long mapped_addr; mapped_addr = vm_mmap_shadow_stack(addr, size, MAP_ABOVE4G); if (!set_res_tok || IS_ERR_VALUE(mapped_addr)) goto out; if (create_rstor_token(mapped_addr + token_offset, NULL)) { vm_munmap(mapped_addr, size); return -EINVAL; } out: return mapped_addr; } static unsigned long adjust_shstk_size(unsigned long size) { if (size) return PAGE_ALIGN(size); return PAGE_ALIGN(min_t(unsigned long long, rlimit(RLIMIT_STACK), SZ_4G)); } static void unmap_shadow_stack(u64 base, u64 size) { int r; r = vm_munmap(base, size); /* * mmap_write_lock_killable() failed with -EINTR. This means * the process is about to die and have it's MM cleaned up. * This task shouldn't ever make it back to userspace. In this * case it is ok to leak a shadow stack, so just exit out. */ if (r == -EINTR) return; /* * For all other types of vm_munmap() failure, either the * system is out of memory or there is bug. */ WARN_ON_ONCE(r); } static int shstk_setup(void) { struct thread_shstk *shstk = ¤t->thread.shstk; unsigned long addr, size; /* Already enabled */ if (features_enabled(ARCH_SHSTK_SHSTK)) return 0; /* Also not supported for 32 bit */ if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || in_ia32_syscall()) return -EOPNOTSUPP; size = adjust_shstk_size(0); addr = alloc_shstk(0, size, 0, false); if (IS_ERR_VALUE(addr)) return PTR_ERR((void *)addr); fpregs_lock_and_load(); wrmsrq(MSR_IA32_PL3_SSP, addr + size); wrmsrq(MSR_IA32_U_CET, CET_SHSTK_EN); fpregs_unlock(); shstk->base = addr; shstk->size = size; features_set(ARCH_SHSTK_SHSTK); return 0; } void reset_thread_features(void) { memset(¤t->thread.shstk, 0, sizeof(struct thread_shstk)); current->thread.features = 0; current->thread.features_locked = 0; } unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, u64 clone_flags, unsigned long stack_size) { struct thread_shstk *shstk = &tsk->thread.shstk; unsigned long addr, size; /* * If shadow stack is not enabled on the new thread, skip any * switch to a new shadow stack. */ if (!features_enabled(ARCH_SHSTK_SHSTK)) return 0; /* * For CLONE_VFORK the child will share the parents shadow stack. * Make sure to clear the internal tracking of the thread shadow * stack so the freeing logic run for child knows to leave it alone. */ if (clone_flags & CLONE_VFORK) { shstk->base = 0; shstk->size = 0; return 0; } /* * For !CLONE_VM the child will use a copy of the parents shadow * stack. */ if (!(clone_flags & CLONE_VM)) return 0; size = adjust_shstk_size(stack_size); addr = alloc_shstk(0, size, 0, false); if (IS_ERR_VALUE(addr)) return addr; shstk->base = addr; shstk->size = size; return addr + size; } static unsigned long get_user_shstk_addr(void) { unsigned long long ssp; fpregs_lock_and_load(); rdmsrq(MSR_IA32_PL3_SSP, ssp); fpregs_unlock(); return ssp; } int shstk_pop(u64 *val) { int ret = 0; u64 ssp; if (!features_enabled(ARCH_SHSTK_SHSTK)) return -ENOTSUPP; fpregs_lock_and_load(); rdmsrq(MSR_IA32_PL3_SSP, ssp); if (val && get_user(*val, (__user u64 *)ssp)) ret = -EFAULT; else wrmsrq(MSR_IA32_PL3_SSP, ssp + SS_FRAME_SIZE); fpregs_unlock(); return ret; } int shstk_push(u64 val) { u64 ssp; int ret; if (!features_enabled(ARCH_SHSTK_SHSTK)) return -ENOTSUPP; fpregs_lock_and_load(); rdmsrq(MSR_IA32_PL3_SSP, ssp); ssp -= SS_FRAME_SIZE; ret = write_user_shstk_64((__user void *)ssp, val); if (!ret) wrmsrq(MSR_IA32_PL3_SSP, ssp); fpregs_unlock(); return ret; } #define SHSTK_DATA_BIT BIT(63) static int put_shstk_data(u64 __user *addr, u64 data) { if (WARN_ON_ONCE(data & SHSTK_DATA_BIT)) return -EINVAL; /* * Mark the high bit so that the sigframe can't be processed as a * return address. */ if (write_user_shstk_64(addr, data | SHSTK_DATA_BIT)) return -EFAULT; return 0; } static int get_shstk_data(unsigned long *data, unsigned long __user *addr) { unsigned long ldata; if (unlikely(get_user(ldata, addr))) return -EFAULT; if (!(ldata & SHSTK_DATA_BIT)) return -EINVAL; *data = ldata & ~SHSTK_DATA_BIT; return 0; } static int shstk_push_sigframe(unsigned long *ssp) { unsigned long target_ssp = *ssp; /* Token must be aligned */ if (!IS_ALIGNED(target_ssp, 8)) return -EINVAL; *ssp -= SS_FRAME_SIZE; if (put_shstk_data((void __user *)*ssp, target_ssp)) return -EFAULT; return 0; } static int shstk_pop_sigframe(unsigned long *ssp) { unsigned long token_addr; unsigned int seq; /* * It is possible for the SSP to be off the end of a shadow stack by 4 * or 8 bytes. If the shadow stack is at the start of a page or 4 bytes * before it, it might be this case, so check that the address being * read is actually shadow stack. */ if (!IS_ALIGNED(*ssp, 8)) return -EINVAL; do { struct vm_area_struct *vma; bool valid_vma; int err; if (mmap_read_lock_killable(current->mm)) return -EINTR; vma = find_vma(current->mm, *ssp); valid_vma = vma && (vma->vm_flags & VM_SHADOW_STACK); /* * VMAs can change between get_shstk_data() and find_vma(). * Watch for changes and ensure that 'token_addr' comes from * 'vma' by recording a seqcount. * * Ignore the return value of mmap_lock_speculate_try_begin() * because the mmap lock excludes the possibility of writers. */ mmap_lock_speculate_try_begin(current->mm, &seq); mmap_read_unlock(current->mm); if (!valid_vma) return -EINVAL; err = get_shstk_data(&token_addr, (unsigned long __user *)*ssp); if (err) return err; } while (mmap_lock_speculate_retry(current->mm, seq)); /* Restore SSP aligned? */ if (unlikely(!IS_ALIGNED(token_addr, 8))) return -EINVAL; /* SSP in userspace? */ if (unlikely(token_addr >= TASK_SIZE_MAX)) return -EINVAL; *ssp = token_addr; return 0; } int setup_signal_shadow_stack(struct ksignal *ksig) { void __user *restorer = ksig->ka.sa.sa_restorer; unsigned long ssp; int err; if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || !features_enabled(ARCH_SHSTK_SHSTK)) return 0; if (!restorer) return -EINVAL; ssp = get_user_shstk_addr(); if (unlikely(!ssp)) return -EINVAL; err = shstk_push_sigframe(&ssp); if (unlikely(err)) return err; /* Push restorer address */ ssp -= SS_FRAME_SIZE; err = write_user_shstk_64((u64 __user *)ssp, (u64)restorer); if (unlikely(err)) return -EFAULT; fpregs_lock_and_load(); wrmsrq(MSR_IA32_PL3_SSP, ssp); fpregs_unlock(); return 0; } int restore_signal_shadow_stack(void) { unsigned long ssp; int err; if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || !features_enabled(ARCH_SHSTK_SHSTK)) return 0; ssp = get_user_shstk_addr(); if (unlikely(!ssp)) return -EINVAL; err = shstk_pop_sigframe(&ssp); if (unlikely(err)) return err; fpregs_lock_and_load(); wrmsrq(MSR_IA32_PL3_SSP, ssp); fpregs_unlock(); return 0; } void shstk_free(struct task_struct *tsk) { struct thread_shstk *shstk = &tsk->thread.shstk; if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) || !features_enabled(ARCH_SHSTK_SHSTK)) return; /* * When fork() with CLONE_VM fails, the child (tsk) already has a * shadow stack allocated, and exit_thread() calls this function to * free it. In this case the parent (current) and the child share * the same mm struct. */ if (!tsk->mm || tsk->mm != current->mm) return; /* * If shstk->base is NULL, then this task is not managing its * own shadow stack (CLONE_VFORK). So skip freeing it. */ if (!shstk->base) return; /* * shstk->base is NULL for CLONE_VFORK child tasks, and so is * normal. But size = 0 on a shstk->base is not normal and * indicated an attempt to free the thread shadow stack twice. * Warn about it. */ if (WARN_ON(!shstk->size)) return; unmap_shadow_stack(shstk->base, shstk->size); shstk->size = 0; } static int wrss_control(bool enable) { u64 msrval; if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) return -EOPNOTSUPP; /* * Only enable WRSS if shadow stack is enabled. If shadow stack is not * enabled, WRSS will already be disabled, so don't bother clearing it * when disabling. */ if (!features_enabled(ARCH_SHSTK_SHSTK)) return -EPERM; /* Already enabled/disabled? */ if (features_enabled(ARCH_SHSTK_WRSS) == enable) return 0; fpregs_lock_and_load(); rdmsrq(MSR_IA32_U_CET, msrval); if (enable) { features_set(ARCH_SHSTK_WRSS); msrval |= CET_WRSS_EN; } else { features_clr(ARCH_SHSTK_WRSS); if (!(msrval & CET_WRSS_EN)) goto unlock; msrval &= ~CET_WRSS_EN; } wrmsrq(MSR_IA32_U_CET, msrval); unlock: fpregs_unlock(); return 0; } static int shstk_disable(void) { if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) return -EOPNOTSUPP; /* Already disabled? */ if (!features_enabled(ARCH_SHSTK_SHSTK)) return 0; fpregs_lock_and_load(); /* Disable WRSS too when disabling shadow stack */ wrmsrq(MSR_IA32_U_CET, 0); wrmsrq(MSR_IA32_PL3_SSP, 0); fpregs_unlock(); shstk_free(current); features_clr(ARCH_SHSTK_SHSTK | ARCH_SHSTK_WRSS); return 0; } SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags) { bool set_tok = flags & SHADOW_STACK_SET_TOKEN; unsigned long aligned_size; if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK)) return -EOPNOTSUPP; if (flags & ~SHADOW_STACK_SET_TOKEN) return -EINVAL; /* If there isn't space for a token */ if (set_tok && size < 8) return -ENOSPC; if (addr && addr < SZ_4G) return -ERANGE; /* * An overflow would result in attempting to write the restore token * to the wrong location. Not catastrophic, but just return the right * error code and block it. */ aligned_size = PAGE_ALIGN(size); if (aligned_size < size) return -EOVERFLOW; return alloc_shstk(addr, aligned_size, size, set_tok); } long shstk_prctl(struct task_struct *task, int option, unsigned long arg2) { unsigned long features = arg2; if (option == ARCH_SHSTK_STATUS) { return put_user(task->thread.features, (unsigned long __user *)arg2); } if (option == ARCH_SHSTK_LOCK) { task->thread.features_locked |= features; return 0; } /* Only allow via ptrace */ if (task != current) { if (option == ARCH_SHSTK_UNLOCK && IS_ENABLED(CONFIG_CHECKPOINT_RESTORE)) { task->thread.features_locked &= ~features; return 0; } return -EINVAL; } /* Do not allow to change locked features */ if (features & task->thread.features_locked) return -EPERM; /* Only support enabling/disabling one feature at a time. */ if (hweight_long(features) > 1) return -EINVAL; if (option == ARCH_SHSTK_DISABLE) { if (features & ARCH_SHSTK_WRSS) return wrss_control(false); if (features & ARCH_SHSTK_SHSTK) return shstk_disable(); return -EINVAL; } /* Handle ARCH_SHSTK_ENABLE */ if (features & ARCH_SHSTK_SHSTK) return shstk_setup(); if (features & ARCH_SHSTK_WRSS) return wrss_control(true); return -EINVAL; } int shstk_update_last_frame(unsigned long val) { unsigned long ssp; if (!features_enabled(ARCH_SHSTK_SHSTK)) return 0; ssp = get_user_shstk_addr(); return write_user_shstk_64((u64 __user *)ssp, (u64)val); } bool shstk_is_enabled(void) { return features_enabled(ARCH_SHSTK_SHSTK); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Routines to manage notifier chains for passing status changes to any * interested routines. We need this instead of hard coded call lists so * that modules can poke their nose into the innards. The network devices * needed them so here they are for the rest of you. * * Alan Cox <Alan.Cox@linux.org> */ #ifndef _LINUX_NOTIFIER_H #define _LINUX_NOTIFIER_H #include <linux/errno.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/srcu.h> /* * Notifier chains are of four types: * * Atomic notifier chains: Chain callbacks run in interrupt/atomic * context. Callouts are not allowed to block. * Blocking notifier chains: Chain callbacks run in process context. * Callouts are allowed to block. * Raw notifier chains: There are no restrictions on callbacks, * registration, or unregistration. All locking and protection * must be provided by the caller. * SRCU notifier chains: A variant of blocking notifier chains, with * the same restrictions. * * atomic_notifier_chain_register() may be called from an atomic context, * but blocking_notifier_chain_register() and srcu_notifier_chain_register() * must be called from a process context. Ditto for the corresponding * _unregister() routines. * * atomic_notifier_chain_unregister(), blocking_notifier_chain_unregister(), * and srcu_notifier_chain_unregister() _must not_ be called from within * the call chain. * * SRCU notifier chains are an alternative form of blocking notifier chains. * They use SRCU (Sleepable Read-Copy Update) instead of rw-semaphores for * protection of the chain links. This means there is _very_ low overhead * in srcu_notifier_call_chain(): no cache bounces and no memory barriers. * As compensation, srcu_notifier_chain_unregister() is rather expensive. * SRCU notifier chains should be used when the chain will be called very * often but notifier_blocks will seldom be removed. */ struct notifier_block; typedef int (*notifier_fn_t)(struct notifier_block *nb, unsigned long action, void *data); struct notifier_block { notifier_fn_t notifier_call; struct notifier_block __rcu *next; int priority; }; struct atomic_notifier_head { spinlock_t lock; struct notifier_block __rcu *head; }; struct blocking_notifier_head { struct rw_semaphore rwsem; struct notifier_block __rcu *head; }; struct raw_notifier_head { struct notifier_block __rcu *head; }; struct srcu_notifier_head { struct mutex mutex; struct srcu_usage srcuu; struct srcu_struct srcu; struct notifier_block __rcu *head; }; #define ATOMIC_INIT_NOTIFIER_HEAD(name) do { \ spin_lock_init(&(name)->lock); \ (name)->head = NULL; \ } while (0) #define BLOCKING_INIT_NOTIFIER_HEAD(name) do { \ init_rwsem(&(name)->rwsem); \ (name)->head = NULL; \ } while (0) #define RAW_INIT_NOTIFIER_HEAD(name) do { \ (name)->head = NULL; \ } while (0) /* srcu_notifier_heads must be cleaned up dynamically */ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh); #define srcu_cleanup_notifier_head(name) \ cleanup_srcu_struct(&(name)->srcu); #define ATOMIC_NOTIFIER_INIT(name) { \ .lock = __SPIN_LOCK_UNLOCKED(name.lock), \ .head = NULL } #define BLOCKING_NOTIFIER_INIT(name) { \ .rwsem = __RWSEM_INITIALIZER((name).rwsem), \ .head = NULL } #define RAW_NOTIFIER_INIT(name) { \ .head = NULL } #define SRCU_NOTIFIER_INIT(name, pcpu) \ { \ .mutex = __MUTEX_INITIALIZER(name.mutex), \ .head = NULL, \ .srcuu = __SRCU_USAGE_INIT(name.srcuu), \ .srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu, 0), \ } #define ATOMIC_NOTIFIER_HEAD(name) \ struct atomic_notifier_head name = \ ATOMIC_NOTIFIER_INIT(name) #define BLOCKING_NOTIFIER_HEAD(name) \ struct blocking_notifier_head name = \ BLOCKING_NOTIFIER_INIT(name) #define RAW_NOTIFIER_HEAD(name) \ struct raw_notifier_head name = \ RAW_NOTIFIER_INIT(name) #ifdef CONFIG_TREE_SRCU #define _SRCU_NOTIFIER_HEAD(name, mod) \ static DEFINE_PER_CPU(struct srcu_data, name##_head_srcu_data); \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name##_head_srcu_data) #else #define _SRCU_NOTIFIER_HEAD(name, mod) \ mod struct srcu_notifier_head name = \ SRCU_NOTIFIER_INIT(name, name) #endif #define SRCU_NOTIFIER_HEAD(name) \ _SRCU_NOTIFIER_HEAD(name, /* not static */) #define SRCU_NOTIFIER_HEAD_STATIC(name) \ _SRCU_NOTIFIER_HEAD(name, static) #ifdef __KERNEL__ extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_register(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_register(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_register(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_chain_register_unique_prio( struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_register_unique_prio( struct blocking_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_chain_unregister(struct atomic_notifier_head *nh, struct notifier_block *nb); extern int blocking_notifier_chain_unregister(struct blocking_notifier_head *nh, struct notifier_block *nb); extern int raw_notifier_chain_unregister(struct raw_notifier_head *nh, struct notifier_block *nb); extern int srcu_notifier_chain_unregister(struct srcu_notifier_head *nh, struct notifier_block *nb); extern int atomic_notifier_call_chain(struct atomic_notifier_head *nh, unsigned long val, void *v); extern int blocking_notifier_call_chain(struct blocking_notifier_head *nh, unsigned long val, void *v); extern int raw_notifier_call_chain(struct raw_notifier_head *nh, unsigned long val, void *v); extern int srcu_notifier_call_chain(struct srcu_notifier_head *nh, unsigned long val, void *v); extern int blocking_notifier_call_chain_robust(struct blocking_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern int raw_notifier_call_chain_robust(struct raw_notifier_head *nh, unsigned long val_up, unsigned long val_down, void *v); extern bool atomic_notifier_call_chain_is_empty(struct atomic_notifier_head *nh); #define NOTIFY_DONE 0x0000 /* Don't care */ #define NOTIFY_OK 0x0001 /* Suits me */ #define NOTIFY_STOP_MASK 0x8000 /* Don't call further */ #define NOTIFY_BAD (NOTIFY_STOP_MASK|0x0002) /* Bad/Veto action */ /* * Clean way to return from the notifier and stop further calls. */ #define NOTIFY_STOP (NOTIFY_OK|NOTIFY_STOP_MASK) /* Encapsulate (negative) errno value (in particular, NOTIFY_BAD <=> EPERM). */ static inline int notifier_from_errno(int err) { if (err) return NOTIFY_STOP_MASK | (NOTIFY_OK - err); return NOTIFY_OK; } /* Restore (negative) errno value from notify return value. */ static inline int notifier_to_errno(int ret) { ret &= ~NOTIFY_STOP_MASK; return ret > NOTIFY_OK ? NOTIFY_OK - ret : 0; } /* * Declared notifiers so far. I can imagine quite a few more chains * over time (eg laptop power reset chains, reboot chain (to clean * device units up), device [un]mount chain, module load/unload chain, * low memory chain, screenblank chain (for plug in modular screenblankers) * VC switch chains (for loadable kernel svgalib VC switch helpers) etc... */ /* CPU notfiers are defined in include/linux/cpu.h. */ /* netdevice notifiers are defined in include/linux/netdevice.h */ /* reboot notifiers are defined in include/linux/reboot.h. */ /* Hibernation and suspend events are defined in include/linux/suspend.h. */ /* Virtual Terminal events are defined in include/linux/vt.h. */ #define NETLINK_URELEASE 0x0001 /* Unicast netlink socket released */ /* Console keyboard events. * Note: KBD_KEYCODE is always sent before KBD_UNBOUND_KEYCODE, KBD_UNICODE and * KBD_KEYSYM. */ #define KBD_KEYCODE 0x0001 /* Keyboard keycode, called before any other */ #define KBD_UNBOUND_KEYCODE 0x0002 /* Keyboard keycode which is not bound to any other */ #define KBD_UNICODE 0x0003 /* Keyboard unicode */ #define KBD_KEYSYM 0x0004 /* Keyboard keysym */ #define KBD_POST_KEYSYM 0x0005 /* Called after keyboard keysym interpretation */ #endif /* __KERNEL__ */ #endif /* _LINUX_NOTIFIER_H */ |
| 12 9 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/phy.h> #include <linux/phylib_stubs.h> #include "bitset.h" #include "common.h" #include "netlink.h" struct stats_req_info { struct ethnl_req_info base; DECLARE_BITMAP(stat_mask, __ETHTOOL_STATS_CNT); enum ethtool_mac_stats_src src; }; #define STATS_REQINFO(__req_base) \ container_of(__req_base, struct stats_req_info, base) struct stats_reply_data { struct ethnl_reply_data base; struct_group(stats, struct ethtool_eth_phy_stats phy_stats; struct ethtool_eth_mac_stats mac_stats; struct ethtool_eth_ctrl_stats ctrl_stats; struct ethtool_rmon_stats rmon_stats; struct ethtool_phy_stats phydev_stats; ); const struct ethtool_rmon_hist_range *rmon_ranges; }; #define STATS_REPDATA(__reply_base) \ container_of(__reply_base, struct stats_reply_data, base) const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_STATS_ETH_PHY] = "eth-phy", [ETHTOOL_STATS_ETH_MAC] = "eth-mac", [ETHTOOL_STATS_ETH_CTRL] = "eth-ctrl", [ETHTOOL_STATS_RMON] = "rmon", [ETHTOOL_STATS_PHY] = "phydev", }; const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_ETH_PHY_5_SYM_ERR] = "SymbolErrorDuringCarrier", }; const char stats_eth_mac_names[__ETHTOOL_A_STATS_ETH_MAC_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_ETH_MAC_2_TX_PKT] = "FramesTransmittedOK", [ETHTOOL_A_STATS_ETH_MAC_3_SINGLE_COL] = "SingleCollisionFrames", [ETHTOOL_A_STATS_ETH_MAC_4_MULTI_COL] = "MultipleCollisionFrames", [ETHTOOL_A_STATS_ETH_MAC_5_RX_PKT] = "FramesReceivedOK", [ETHTOOL_A_STATS_ETH_MAC_6_FCS_ERR] = "FrameCheckSequenceErrors", [ETHTOOL_A_STATS_ETH_MAC_7_ALIGN_ERR] = "AlignmentErrors", [ETHTOOL_A_STATS_ETH_MAC_8_TX_BYTES] = "OctetsTransmittedOK", [ETHTOOL_A_STATS_ETH_MAC_9_TX_DEFER] = "FramesWithDeferredXmissions", [ETHTOOL_A_STATS_ETH_MAC_10_LATE_COL] = "LateCollisions", [ETHTOOL_A_STATS_ETH_MAC_11_XS_COL] = "FramesAbortedDueToXSColls", [ETHTOOL_A_STATS_ETH_MAC_12_TX_INT_ERR] = "FramesLostDueToIntMACXmitError", [ETHTOOL_A_STATS_ETH_MAC_13_CS_ERR] = "CarrierSenseErrors", [ETHTOOL_A_STATS_ETH_MAC_14_RX_BYTES] = "OctetsReceivedOK", [ETHTOOL_A_STATS_ETH_MAC_15_RX_INT_ERR] = "FramesLostDueToIntMACRcvError", [ETHTOOL_A_STATS_ETH_MAC_18_TX_MCAST] = "MulticastFramesXmittedOK", [ETHTOOL_A_STATS_ETH_MAC_19_TX_BCAST] = "BroadcastFramesXmittedOK", [ETHTOOL_A_STATS_ETH_MAC_20_XS_DEFER] = "FramesWithExcessiveDeferral", [ETHTOOL_A_STATS_ETH_MAC_21_RX_MCAST] = "MulticastFramesReceivedOK", [ETHTOOL_A_STATS_ETH_MAC_22_RX_BCAST] = "BroadcastFramesReceivedOK", [ETHTOOL_A_STATS_ETH_MAC_23_IR_LEN_ERR] = "InRangeLengthErrors", [ETHTOOL_A_STATS_ETH_MAC_24_OOR_LEN] = "OutOfRangeLengthField", [ETHTOOL_A_STATS_ETH_MAC_25_TOO_LONG_ERR] = "FrameTooLongErrors", }; const char stats_eth_ctrl_names[__ETHTOOL_A_STATS_ETH_CTRL_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_ETH_CTRL_3_TX] = "MACControlFramesTransmitted", [ETHTOOL_A_STATS_ETH_CTRL_4_RX] = "MACControlFramesReceived", [ETHTOOL_A_STATS_ETH_CTRL_5_RX_UNSUP] = "UnsupportedOpcodesReceived", }; const char stats_rmon_names[__ETHTOOL_A_STATS_RMON_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_RMON_UNDERSIZE] = "etherStatsUndersizePkts", [ETHTOOL_A_STATS_RMON_OVERSIZE] = "etherStatsOversizePkts", [ETHTOOL_A_STATS_RMON_FRAG] = "etherStatsFragments", [ETHTOOL_A_STATS_RMON_JABBER] = "etherStatsJabbers", }; const char stats_phy_names[__ETHTOOL_A_STATS_PHY_CNT][ETH_GSTRING_LEN] = { [ETHTOOL_A_STATS_PHY_RX_PKTS] = "RxFrames", [ETHTOOL_A_STATS_PHY_RX_BYTES] = "RxOctets", [ETHTOOL_A_STATS_PHY_RX_ERRORS] = "RxErrors", [ETHTOOL_A_STATS_PHY_TX_PKTS] = "TxFrames", [ETHTOOL_A_STATS_PHY_TX_BYTES] = "TxOctets", [ETHTOOL_A_STATS_PHY_TX_ERRORS] = "TxErrors", }; const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_SRC + 1] = { [ETHTOOL_A_STATS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), [ETHTOOL_A_STATS_GROUPS] = { .type = NLA_NESTED }, [ETHTOOL_A_STATS_SRC] = NLA_POLICY_MAX(NLA_U32, ETHTOOL_MAC_STATS_SRC_PMAC), }; static int stats_parse_request(struct ethnl_req_info *req_base, const struct genl_info *info, struct nlattr **tb, struct netlink_ext_ack *extack) { enum ethtool_mac_stats_src src = ETHTOOL_MAC_STATS_SRC_AGGREGATE; struct stats_req_info *req_info = STATS_REQINFO(req_base); bool mod = false; int err; err = ethnl_update_bitset(req_info->stat_mask, __ETHTOOL_STATS_CNT, tb[ETHTOOL_A_STATS_GROUPS], stats_std_names, extack, &mod); if (err) return err; if (!mod) { NL_SET_ERR_MSG(extack, "no stats requested"); return -EINVAL; } if (tb[ETHTOOL_A_STATS_SRC]) src = nla_get_u32(tb[ETHTOOL_A_STATS_SRC]); req_info->src = src; return 0; } static int stats_prepare_data(const struct ethnl_req_info *req_base, struct ethnl_reply_data *reply_base, const struct genl_info *info) { const struct stats_req_info *req_info = STATS_REQINFO(req_base); struct stats_reply_data *data = STATS_REPDATA(reply_base); enum ethtool_mac_stats_src src = req_info->src; struct net_device *dev = reply_base->dev; struct nlattr **tb = info->attrs; struct phy_device *phydev; int ret; phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_STATS_HEADER, info->extack); if (IS_ERR(phydev)) return PTR_ERR(phydev); ret = ethnl_ops_begin(dev); if (ret < 0) return ret; if ((src == ETHTOOL_MAC_STATS_SRC_EMAC || src == ETHTOOL_MAC_STATS_SRC_PMAC) && !__ethtool_dev_mm_supported(dev)) { NL_SET_ERR_MSG_MOD(info->extack, "Device does not support MAC merge layer"); ethnl_ops_complete(dev); return -EOPNOTSUPP; } /* Mark all stats as unset (see ETHTOOL_STAT_NOT_SET) to prevent them * from being reported to user space in case driver did not set them. */ memset(&data->stats, 0xff, sizeof(data->stats)); data->phy_stats.src = src; data->mac_stats.src = src; data->ctrl_stats.src = src; data->rmon_stats.src = src; if ((test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask) || test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask)) && src == ETHTOOL_MAC_STATS_SRC_AGGREGATE) { if (phydev) phy_ethtool_get_phy_stats(phydev, &data->phy_stats, &data->phydev_stats); } if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask) && dev->ethtool_ops->get_eth_phy_stats) dev->ethtool_ops->get_eth_phy_stats(dev, &data->phy_stats); if (test_bit(ETHTOOL_STATS_ETH_MAC, req_info->stat_mask) && dev->ethtool_ops->get_eth_mac_stats) dev->ethtool_ops->get_eth_mac_stats(dev, &data->mac_stats); if (test_bit(ETHTOOL_STATS_ETH_CTRL, req_info->stat_mask) && dev->ethtool_ops->get_eth_ctrl_stats) dev->ethtool_ops->get_eth_ctrl_stats(dev, &data->ctrl_stats); if (test_bit(ETHTOOL_STATS_RMON, req_info->stat_mask) && dev->ethtool_ops->get_rmon_stats) dev->ethtool_ops->get_rmon_stats(dev, &data->rmon_stats, &data->rmon_ranges); ethnl_ops_complete(dev); return 0; } static int stats_reply_size(const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct stats_req_info *req_info = STATS_REQINFO(req_base); unsigned int n_grps = 0, n_stats = 0; int len = 0; len += nla_total_size(sizeof(u32)); /* _STATS_SRC */ if (test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_eth_phy_stats) / sizeof(u64); n_grps++; } if (test_bit(ETHTOOL_STATS_ETH_MAC, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_eth_mac_stats) / sizeof(u64); n_grps++; } if (test_bit(ETHTOOL_STATS_ETH_CTRL, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_eth_ctrl_stats) / sizeof(u64); n_grps++; } if (test_bit(ETHTOOL_STATS_RMON, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_rmon_stats) / sizeof(u64); n_grps++; /* Above includes the space for _A_STATS_GRP_HIST_VALs */ len += (nla_total_size(0) + /* _A_STATS_GRP_HIST */ nla_total_size(4) + /* _A_STATS_GRP_HIST_BKT_LOW */ nla_total_size(4)) * /* _A_STATS_GRP_HIST_BKT_HI */ ETHTOOL_RMON_HIST_MAX * 2; } if (test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask)) { n_stats += sizeof(struct ethtool_phy_stats) / sizeof(u64); n_grps++; } len += n_grps * (nla_total_size(0) + /* _A_STATS_GRP */ nla_total_size(4) + /* _A_STATS_GRP_ID */ nla_total_size(4)); /* _A_STATS_GRP_SS_ID */ len += n_stats * (nla_total_size(0) + /* _A_STATS_GRP_STAT */ nla_total_size_64bit(sizeof(u64))); return len; } static int stat_put(struct sk_buff *skb, u16 attrtype, u64 val) { struct nlattr *nest; int ret; if (val == ETHTOOL_STAT_NOT_SET) return 0; /* We want to start stats attr types from 0, so we don't have a type * for pad inside ETHTOOL_A_STATS_GRP_STAT. Pad things on the outside * of ETHTOOL_A_STATS_GRP_STAT. Since we're one nest away from the * actual attr we're 4B off - nla_need_padding_for_64bit() & co. * can't be used. */ #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS if (!IS_ALIGNED((unsigned long)skb_tail_pointer(skb), 8)) if (!nla_reserve(skb, ETHTOOL_A_STATS_GRP_PAD, 0)) return -EMSGSIZE; #endif nest = nla_nest_start(skb, ETHTOOL_A_STATS_GRP_STAT); if (!nest) return -EMSGSIZE; ret = nla_put_u64_64bit(skb, attrtype, val, -1 /* not used */); if (ret) { nla_nest_cancel(skb, nest); return ret; } nla_nest_end(skb, nest); return 0; } static int stats_put_phy_stats(struct sk_buff *skb, const struct stats_reply_data *data) { if (stat_put(skb, ETHTOOL_A_STATS_ETH_PHY_5_SYM_ERR, data->phy_stats.SymbolErrorDuringCarrier)) return -EMSGSIZE; return 0; } static int stats_put_phydev_stats(struct sk_buff *skb, const struct stats_reply_data *data) { if (stat_put(skb, ETHTOOL_A_STATS_PHY_RX_PKTS, data->phydev_stats.rx_packets) || stat_put(skb, ETHTOOL_A_STATS_PHY_RX_BYTES, data->phydev_stats.rx_bytes) || stat_put(skb, ETHTOOL_A_STATS_PHY_RX_ERRORS, data->phydev_stats.rx_errors) || stat_put(skb, ETHTOOL_A_STATS_PHY_TX_PKTS, data->phydev_stats.tx_packets) || stat_put(skb, ETHTOOL_A_STATS_PHY_TX_BYTES, data->phydev_stats.tx_bytes) || stat_put(skb, ETHTOOL_A_STATS_PHY_TX_ERRORS, data->phydev_stats.tx_errors)) return -EMSGSIZE; return 0; } static int stats_put_mac_stats(struct sk_buff *skb, const struct stats_reply_data *data) { if (stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_2_TX_PKT, data->mac_stats.FramesTransmittedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_3_SINGLE_COL, data->mac_stats.SingleCollisionFrames) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_4_MULTI_COL, data->mac_stats.MultipleCollisionFrames) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_5_RX_PKT, data->mac_stats.FramesReceivedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_6_FCS_ERR, data->mac_stats.FrameCheckSequenceErrors) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_7_ALIGN_ERR, data->mac_stats.AlignmentErrors) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_8_TX_BYTES, data->mac_stats.OctetsTransmittedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_9_TX_DEFER, data->mac_stats.FramesWithDeferredXmissions) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_10_LATE_COL, data->mac_stats.LateCollisions) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_11_XS_COL, data->mac_stats.FramesAbortedDueToXSColls) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_12_TX_INT_ERR, data->mac_stats.FramesLostDueToIntMACXmitError) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_13_CS_ERR, data->mac_stats.CarrierSenseErrors) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_14_RX_BYTES, data->mac_stats.OctetsReceivedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_15_RX_INT_ERR, data->mac_stats.FramesLostDueToIntMACRcvError) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_18_TX_MCAST, data->mac_stats.MulticastFramesXmittedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_19_TX_BCAST, data->mac_stats.BroadcastFramesXmittedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_20_XS_DEFER, data->mac_stats.FramesWithExcessiveDeferral) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_21_RX_MCAST, data->mac_stats.MulticastFramesReceivedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_22_RX_BCAST, data->mac_stats.BroadcastFramesReceivedOK) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_23_IR_LEN_ERR, data->mac_stats.InRangeLengthErrors) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_24_OOR_LEN, data->mac_stats.OutOfRangeLengthField) || stat_put(skb, ETHTOOL_A_STATS_ETH_MAC_25_TOO_LONG_ERR, data->mac_stats.FrameTooLongErrors)) return -EMSGSIZE; return 0; } static int stats_put_ctrl_stats(struct sk_buff *skb, const struct stats_reply_data *data) { if (stat_put(skb, ETHTOOL_A_STATS_ETH_CTRL_3_TX, data->ctrl_stats.MACControlFramesTransmitted) || stat_put(skb, ETHTOOL_A_STATS_ETH_CTRL_4_RX, data->ctrl_stats.MACControlFramesReceived) || stat_put(skb, ETHTOOL_A_STATS_ETH_CTRL_5_RX_UNSUP, data->ctrl_stats.UnsupportedOpcodesReceived)) return -EMSGSIZE; return 0; } static int stats_put_rmon_hist(struct sk_buff *skb, u32 attr, const u64 *hist, const struct ethtool_rmon_hist_range *ranges) { struct nlattr *nest; int i; if (!ranges) return 0; for (i = 0; i < ETHTOOL_RMON_HIST_MAX; i++) { if (!ranges[i].low && !ranges[i].high) break; if (hist[i] == ETHTOOL_STAT_NOT_SET) continue; nest = nla_nest_start(skb, attr); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_STATS_GRP_HIST_BKT_LOW, ranges[i].low) || nla_put_u32(skb, ETHTOOL_A_STATS_GRP_HIST_BKT_HI, ranges[i].high) || nla_put_u64_64bit(skb, ETHTOOL_A_STATS_GRP_HIST_VAL, hist[i], ETHTOOL_A_STATS_GRP_PAD)) goto err_cancel_hist; nla_nest_end(skb, nest); } return 0; err_cancel_hist: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int stats_put_rmon_stats(struct sk_buff *skb, const struct stats_reply_data *data) { if (stats_put_rmon_hist(skb, ETHTOOL_A_STATS_GRP_HIST_RX, data->rmon_stats.hist, data->rmon_ranges) || stats_put_rmon_hist(skb, ETHTOOL_A_STATS_GRP_HIST_TX, data->rmon_stats.hist_tx, data->rmon_ranges)) return -EMSGSIZE; if (stat_put(skb, ETHTOOL_A_STATS_RMON_UNDERSIZE, data->rmon_stats.undersize_pkts) || stat_put(skb, ETHTOOL_A_STATS_RMON_OVERSIZE, data->rmon_stats.oversize_pkts) || stat_put(skb, ETHTOOL_A_STATS_RMON_FRAG, data->rmon_stats.fragments) || stat_put(skb, ETHTOOL_A_STATS_RMON_JABBER, data->rmon_stats.jabbers)) return -EMSGSIZE; return 0; } static int stats_put_stats(struct sk_buff *skb, const struct stats_reply_data *data, u32 id, u32 ss_id, int (*cb)(struct sk_buff *skb, const struct stats_reply_data *data)) { struct nlattr *nest; nest = nla_nest_start(skb, ETHTOOL_A_STATS_GRP); if (!nest) return -EMSGSIZE; if (nla_put_u32(skb, ETHTOOL_A_STATS_GRP_ID, id) || nla_put_u32(skb, ETHTOOL_A_STATS_GRP_SS_ID, ss_id)) goto err_cancel; if (cb(skb, data)) goto err_cancel; nla_nest_end(skb, nest); return 0; err_cancel: nla_nest_cancel(skb, nest); return -EMSGSIZE; } static int stats_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, const struct ethnl_reply_data *reply_base) { const struct stats_req_info *req_info = STATS_REQINFO(req_base); const struct stats_reply_data *data = STATS_REPDATA(reply_base); int ret = 0; if (nla_put_u32(skb, ETHTOOL_A_STATS_SRC, req_info->src)) return -EMSGSIZE; if (!ret && test_bit(ETHTOOL_STATS_ETH_PHY, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_ETH_PHY, ETH_SS_STATS_ETH_PHY, stats_put_phy_stats); if (!ret && test_bit(ETHTOOL_STATS_ETH_MAC, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_ETH_MAC, ETH_SS_STATS_ETH_MAC, stats_put_mac_stats); if (!ret && test_bit(ETHTOOL_STATS_ETH_CTRL, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_ETH_CTRL, ETH_SS_STATS_ETH_CTRL, stats_put_ctrl_stats); if (!ret && test_bit(ETHTOOL_STATS_RMON, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_RMON, ETH_SS_STATS_RMON, stats_put_rmon_stats); if (!ret && test_bit(ETHTOOL_STATS_PHY, req_info->stat_mask)) ret = stats_put_stats(skb, data, ETHTOOL_STATS_PHY, ETH_SS_STATS_PHY, stats_put_phydev_stats); return ret; } const struct ethnl_request_ops ethnl_stats_request_ops = { .request_cmd = ETHTOOL_MSG_STATS_GET, .reply_cmd = ETHTOOL_MSG_STATS_GET_REPLY, .hdr_attr = ETHTOOL_A_STATS_HEADER, .req_info_size = sizeof(struct stats_req_info), .reply_data_size = sizeof(struct stats_reply_data), .parse_request = stats_parse_request, .prepare_data = stats_prepare_data, .reply_size = stats_reply_size, .fill_reply = stats_fill_reply, }; static u64 ethtool_stats_sum(u64 a, u64 b) { if (a == ETHTOOL_STAT_NOT_SET) return b; if (b == ETHTOOL_STAT_NOT_SET) return a; return a + b; } /* Avoid modifying the aggregation procedure every time a new counter is added * by treating the structures as an array of u64 statistics. */ static void ethtool_aggregate_stats(void *aggr_stats, const void *emac_stats, const void *pmac_stats, size_t stats_size, size_t stats_offset) { size_t num_stats = stats_size / sizeof(u64); const u64 *s1 = emac_stats + stats_offset; const u64 *s2 = pmac_stats + stats_offset; u64 *s = aggr_stats + stats_offset; int i; for (i = 0; i < num_stats; i++) s[i] = ethtool_stats_sum(s1[i], s2[i]); } void ethtool_aggregate_mac_stats(struct net_device *dev, struct ethtool_eth_mac_stats *mac_stats) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_eth_mac_stats pmac, emac; memset(&emac, 0xff, sizeof(emac)); memset(&pmac, 0xff, sizeof(pmac)); emac.src = ETHTOOL_MAC_STATS_SRC_EMAC; pmac.src = ETHTOOL_MAC_STATS_SRC_PMAC; ops->get_eth_mac_stats(dev, &emac); ops->get_eth_mac_stats(dev, &pmac); ethtool_aggregate_stats(mac_stats, &emac, &pmac, sizeof(mac_stats->stats), offsetof(struct ethtool_eth_mac_stats, stats)); } EXPORT_SYMBOL(ethtool_aggregate_mac_stats); void ethtool_aggregate_phy_stats(struct net_device *dev, struct ethtool_eth_phy_stats *phy_stats) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_eth_phy_stats pmac, emac; memset(&emac, 0xff, sizeof(emac)); memset(&pmac, 0xff, sizeof(pmac)); emac.src = ETHTOOL_MAC_STATS_SRC_EMAC; pmac.src = ETHTOOL_MAC_STATS_SRC_PMAC; ops->get_eth_phy_stats(dev, &emac); ops->get_eth_phy_stats(dev, &pmac); ethtool_aggregate_stats(phy_stats, &emac, &pmac, sizeof(phy_stats->stats), offsetof(struct ethtool_eth_phy_stats, stats)); } EXPORT_SYMBOL(ethtool_aggregate_phy_stats); void ethtool_aggregate_ctrl_stats(struct net_device *dev, struct ethtool_eth_ctrl_stats *ctrl_stats) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_eth_ctrl_stats pmac, emac; memset(&emac, 0xff, sizeof(emac)); memset(&pmac, 0xff, sizeof(pmac)); emac.src = ETHTOOL_MAC_STATS_SRC_EMAC; pmac.src = ETHTOOL_MAC_STATS_SRC_PMAC; ops->get_eth_ctrl_stats(dev, &emac); ops->get_eth_ctrl_stats(dev, &pmac); ethtool_aggregate_stats(ctrl_stats, &emac, &pmac, sizeof(ctrl_stats->stats), offsetof(struct ethtool_eth_ctrl_stats, stats)); } EXPORT_SYMBOL(ethtool_aggregate_ctrl_stats); void ethtool_aggregate_pause_stats(struct net_device *dev, struct ethtool_pause_stats *pause_stats) { const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_pause_stats pmac, emac; memset(&emac, 0xff, sizeof(emac)); memset(&pmac, 0xff, sizeof(pmac)); emac.src = ETHTOOL_MAC_STATS_SRC_EMAC; pmac.src = ETHTOOL_MAC_STATS_SRC_PMAC; ops->get_pause_stats(dev, &emac); ops->get_pause_stats(dev, &pmac); ethtool_aggregate_stats(pause_stats, &emac, &pmac, sizeof(pause_stats->stats), offsetof(struct ethtool_pause_stats, stats)); } EXPORT_SYMBOL(ethtool_aggregate_pause_stats); void ethtool_aggregate_rmon_stats(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats) { const struct ethtool_ops *ops = dev->ethtool_ops; const struct ethtool_rmon_hist_range *dummy; struct ethtool_rmon_stats pmac, emac; memset(&emac, 0xff, sizeof(emac)); memset(&pmac, 0xff, sizeof(pmac)); emac.src = ETHTOOL_MAC_STATS_SRC_EMAC; pmac.src = ETHTOOL_MAC_STATS_SRC_PMAC; ops->get_rmon_stats(dev, &emac, &dummy); ops->get_rmon_stats(dev, &pmac, &dummy); ethtool_aggregate_stats(rmon_stats, &emac, &pmac, sizeof(rmon_stats->stats), offsetof(struct ethtool_rmon_stats, stats)); } EXPORT_SYMBOL(ethtool_aggregate_rmon_stats); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Xtables module to match the process control group. * * Might be used to implement individual "per-application" firewall * policies in contrast to global policies based on control groups. * Matching is based upon processes tagged to net_cls' classid marker. * * (C) 2013 Daniel Borkmann <dborkman@redhat.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/skbuff.h> #include <linux/module.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_cgroup.h> #include <net/sock.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>"); MODULE_DESCRIPTION("Xtables: process control group matching"); MODULE_ALIAS("ipt_cgroup"); MODULE_ALIAS("ip6t_cgroup"); #define NET_CLS_CLASSID_INVALID_MSG "xt_cgroup: classid invalid without net_cls cgroups\n" static int cgroup_mt_check_v0(const struct xt_mtchk_param *par) { struct xt_cgroup_info_v0 *info = par->matchinfo; if (info->invert & ~1) return -EINVAL; if (!IS_ENABLED(CONFIG_CGROUP_NET_CLASSID)) { pr_info(NET_CLS_CLASSID_INVALID_MSG); return -EINVAL; } return 0; } static int cgroup_mt_check_v1(const struct xt_mtchk_param *par) { struct xt_cgroup_info_v1 *info = par->matchinfo; struct cgroup *cgrp; if ((info->invert_path & ~1) || (info->invert_classid & ~1)) return -EINVAL; if (!info->has_path && !info->has_classid) { pr_info("xt_cgroup: no path or classid specified\n"); return -EINVAL; } if (info->has_path && info->has_classid) { pr_info_ratelimited("path and classid specified\n"); return -EINVAL; } if (info->has_classid && !IS_ENABLED(CONFIG_CGROUP_NET_CLASSID)) { pr_info(NET_CLS_CLASSID_INVALID_MSG); return -EINVAL; } info->priv = NULL; if (info->has_path) { if (strnlen(info->path, sizeof(info->path)) >= sizeof(info->path)) return -ENAMETOOLONG; cgrp = cgroup_get_from_path(info->path); if (IS_ERR(cgrp)) { pr_info_ratelimited("invalid path, errno=%ld\n", PTR_ERR(cgrp)); return -EINVAL; } info->priv = cgrp; } return 0; } static int cgroup_mt_check_v2(const struct xt_mtchk_param *par) { struct xt_cgroup_info_v2 *info = par->matchinfo; struct cgroup *cgrp; if ((info->invert_path & ~1) || (info->invert_classid & ~1)) return -EINVAL; if (!info->has_path && !info->has_classid) { pr_info("xt_cgroup: no path or classid specified\n"); return -EINVAL; } if (info->has_path && info->has_classid) { pr_info_ratelimited("path and classid specified\n"); return -EINVAL; } if (info->has_classid && !IS_ENABLED(CONFIG_CGROUP_NET_CLASSID)) { pr_info(NET_CLS_CLASSID_INVALID_MSG); return -EINVAL; } info->priv = NULL; if (info->has_path) { if (strnlen(info->path, sizeof(info->path)) >= sizeof(info->path)) return -ENAMETOOLONG; cgrp = cgroup_get_from_path(info->path); if (IS_ERR(cgrp)) { pr_info_ratelimited("invalid path, errno=%ld\n", PTR_ERR(cgrp)); return -EINVAL; } info->priv = cgrp; } return 0; } static bool cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par) { #ifdef CONFIG_CGROUP_NET_CLASSID const struct xt_cgroup_info_v0 *info = par->matchinfo; struct sock *sk = skb->sk; if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; return (info->id == sock_cgroup_classid(&skb->sk->sk_cgrp_data)) ^ info->invert; #endif return false; } static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_cgroup_info_v1 *info = par->matchinfo; struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data; struct cgroup *ancestor = info->priv; struct sock *sk = skb->sk; if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; if (ancestor) return cgroup_is_descendant(sock_cgroup_ptr(skcd), ancestor) ^ info->invert_path; #ifdef CONFIG_CGROUP_NET_CLASSID else return (info->classid == sock_cgroup_classid(skcd)) ^ info->invert_classid; #endif return false; } static bool cgroup_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_cgroup_info_v2 *info = par->matchinfo; struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data; struct cgroup *ancestor = info->priv; struct sock *sk = skb->sk; if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk))) return false; if (ancestor) return cgroup_is_descendant(sock_cgroup_ptr(skcd), ancestor) ^ info->invert_path; #ifdef CONFIG_CGROUP_NET_CLASSID else return (info->classid == sock_cgroup_classid(skcd)) ^ info->invert_classid; #endif return false; } static void cgroup_mt_destroy_v1(const struct xt_mtdtor_param *par) { struct xt_cgroup_info_v1 *info = par->matchinfo; if (info->priv) cgroup_put(info->priv); } static void cgroup_mt_destroy_v2(const struct xt_mtdtor_param *par) { struct xt_cgroup_info_v2 *info = par->matchinfo; if (info->priv) cgroup_put(info->priv); } static struct xt_match cgroup_mt_reg[] __read_mostly = { { .name = "cgroup", .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = cgroup_mt_check_v0, .match = cgroup_mt_v0, .matchsize = sizeof(struct xt_cgroup_info_v0), .me = THIS_MODULE, .hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN), }, { .name = "cgroup", .revision = 1, .family = NFPROTO_UNSPEC, .checkentry = cgroup_mt_check_v1, .match = cgroup_mt_v1, .matchsize = sizeof(struct xt_cgroup_info_v1), .usersize = offsetof(struct xt_cgroup_info_v1, priv), .destroy = cgroup_mt_destroy_v1, .me = THIS_MODULE, .hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN), }, { .name = "cgroup", .revision = 2, .family = NFPROTO_UNSPEC, .checkentry = cgroup_mt_check_v2, .match = cgroup_mt_v2, .matchsize = sizeof(struct xt_cgroup_info_v2), .usersize = offsetof(struct xt_cgroup_info_v2, priv), .destroy = cgroup_mt_destroy_v2, .me = THIS_MODULE, .hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN), }, }; static int __init cgroup_mt_init(void) { return xt_register_matches(cgroup_mt_reg, ARRAY_SIZE(cgroup_mt_reg)); } static void __exit cgroup_mt_exit(void) { xt_unregister_matches(cgroup_mt_reg, ARRAY_SIZE(cgroup_mt_reg)); } module_init(cgroup_mt_init); module_exit(cgroup_mt_exit); |
| 6 6 5 5 7 7 5 5 5 5 5 8 8 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C)2003,2004 USAGI/WIDE Project * * Authors Mitsuru KANDA <mk@linux-ipv6.org> * YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> */ #define pr_fmt(fmt) "IPv6: " fmt #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> static struct xfrm6_tunnel __rcu *tunnel6_handlers __read_mostly; static struct xfrm6_tunnel __rcu *tunnel46_handlers __read_mostly; static struct xfrm6_tunnel __rcu *tunnelmpls6_handlers __read_mostly; static DEFINE_MUTEX(tunnel6_mutex); static inline int xfrm6_tunnel_mpls_supported(void) { return IS_ENABLED(CONFIG_MPLS); } int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family) { struct xfrm6_tunnel __rcu **pprev; struct xfrm6_tunnel *t; int ret = -EEXIST; int priority = handler->priority; mutex_lock(&tunnel6_mutex); switch (family) { case AF_INET6: pprev = &tunnel6_handlers; break; case AF_INET: pprev = &tunnel46_handlers; break; case AF_MPLS: pprev = &tunnelmpls6_handlers; break; default: goto err; } for (; (t = rcu_dereference_protected(*pprev, lockdep_is_held(&tunnel6_mutex))) != NULL; pprev = &t->next) { if (t->priority > priority) break; if (t->priority == priority) goto err; } handler->next = *pprev; rcu_assign_pointer(*pprev, handler); ret = 0; err: mutex_unlock(&tunnel6_mutex); return ret; } EXPORT_SYMBOL(xfrm6_tunnel_register); int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family) { struct xfrm6_tunnel __rcu **pprev; struct xfrm6_tunnel *t; int ret = -ENOENT; mutex_lock(&tunnel6_mutex); switch (family) { case AF_INET6: pprev = &tunnel6_handlers; break; case AF_INET: pprev = &tunnel46_handlers; break; case AF_MPLS: pprev = &tunnelmpls6_handlers; break; default: goto err; } for (; (t = rcu_dereference_protected(*pprev, lockdep_is_held(&tunnel6_mutex))) != NULL; pprev = &t->next) { if (t == handler) { *pprev = handler->next; ret = 0; break; } } err: mutex_unlock(&tunnel6_mutex); synchronize_net(); return ret; } EXPORT_SYMBOL(xfrm6_tunnel_deregister); #define for_each_tunnel_rcu(head, handler) \ for (handler = rcu_dereference(head); \ handler != NULL; \ handler = rcu_dereference(handler->next)) \ static int tunnelmpls6_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; for_each_tunnel_rcu(tunnelmpls6_handlers, handler) if (!handler->handler(skb)) return 0; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static int tunnel6_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; for_each_tunnel_rcu(tunnel6_handlers, handler) if (!handler->handler(skb)) return 0; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } #if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) static int tunnel6_rcv_cb(struct sk_buff *skb, u8 proto, int err) { struct xfrm6_tunnel __rcu *head; struct xfrm6_tunnel *handler; int ret; head = (proto == IPPROTO_IPV6) ? tunnel6_handlers : tunnel46_handlers; for_each_tunnel_rcu(head, handler) { if (handler->cb_handler) { ret = handler->cb_handler(skb, err); if (ret <= 0) return ret; } } return 0; } static const struct xfrm_input_afinfo tunnel6_input_afinfo = { .family = AF_INET6, .is_ipip = true, .callback = tunnel6_rcv_cb, }; #endif static int tunnel46_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto drop; for_each_tunnel_rcu(tunnel46_handlers, handler) if (!handler->handler(skb)) return 0; icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static int tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_tunnel *handler; for_each_tunnel_rcu(tunnel6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int tunnel46_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_tunnel *handler; for_each_tunnel_rcu(tunnel46_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static int tunnelmpls6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct xfrm6_tunnel *handler; for_each_tunnel_rcu(tunnelmpls6_handlers, handler) if (!handler->err_handler(skb, opt, type, code, offset, info)) return 0; return -ENOENT; } static const struct inet6_protocol tunnel6_protocol = { .handler = tunnel6_rcv, .err_handler = tunnel6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; static const struct inet6_protocol tunnel46_protocol = { .handler = tunnel46_rcv, .err_handler = tunnel46_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; static const struct inet6_protocol tunnelmpls6_protocol = { .handler = tunnelmpls6_rcv, .err_handler = tunnelmpls6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, }; static int __init tunnel6_init(void) { if (inet6_add_protocol(&tunnel6_protocol, IPPROTO_IPV6)) { pr_err("%s: can't add protocol\n", __func__); return -EAGAIN; } if (inet6_add_protocol(&tunnel46_protocol, IPPROTO_IPIP)) { pr_err("%s: can't add protocol\n", __func__); inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); return -EAGAIN; } if (xfrm6_tunnel_mpls_supported() && inet6_add_protocol(&tunnelmpls6_protocol, IPPROTO_MPLS)) { pr_err("%s: can't add protocol\n", __func__); inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP); return -EAGAIN; } #if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) if (xfrm_input_register_afinfo(&tunnel6_input_afinfo)) { pr_err("%s: can't add input afinfo\n", __func__); inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6); inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP); if (xfrm6_tunnel_mpls_supported()) inet6_del_protocol(&tunnelmpls6_protocol, IPPROTO_MPLS); return -EAGAIN; } #endif return 0; } static void __exit tunnel6_fini(void) { #if IS_ENABLED(CONFIG_INET6_XFRM_TUNNEL) if (xfrm_input_unregister_afinfo(&tunnel6_input_afinfo)) pr_err("%s: can't remove input afinfo\n", __func__); #endif if (inet6_del_protocol(&tunnel46_protocol, IPPROTO_IPIP)) pr_err("%s: can't remove protocol\n", __func__); if (inet6_del_protocol(&tunnel6_protocol, IPPROTO_IPV6)) pr_err("%s: can't remove protocol\n", __func__); if (xfrm6_tunnel_mpls_supported() && inet6_del_protocol(&tunnelmpls6_protocol, IPPROTO_MPLS)) pr_err("%s: can't remove protocol\n", __func__); } module_init(tunnel6_init); module_exit(tunnel6_fini); MODULE_DESCRIPTION("IP-in-IPv6 tunnel driver"); MODULE_LICENSE("GPL"); |
| 601 780 779 780 5153 4959 860 1033 858 5157 4963 4969 281 5161 868 867 1028 5170 15 15 5137 14 5137 607 608 609 601 607 609 779 779 779 780 15 601 614 600 15 600 599 876 601 876 5160 876 5170 5147 15 258 5137 810 554 179 610 179 176 9 8 271 270 14 866 868 859 867 4967 4979 4971 4887 3817 4982 4981 4952 4968 2 15 15 15 15 15 15 258 621 600 866 868 865 867 867 13 13 13 13 13 14 14 14 14 13 1 14 14 14 14 14 13 13 855 257 257 257 257 867 601 257 14 15 28 856 876 852 14 15 877 15 868 855 853 13 867 280 279 13 267 257 10 281 271 15 268 15 258 268 268 268 268 268 268 268 177 9 170 170 169 169 170 168 9 178 178 179 169 168 178 170 175 179 178 9 615 9 615 617 617 615 613 614 612 617 616 9 1777 1775 1771 7 606 607 6 1777 616 1776 615 1775 1781 1775 614 595 258 258 258 258 258 258 258 258 258 797 795 907 258 268 267 15 258 258 258 258 258 600 600 602 601 601 9 9 9 597 876 13 9 9 9 9 192 13 178 9 9 187 13 177 615 13 13 13 628 614 617 628 630 13 13 13 13 13 13 281 13 13 13 13 13 268 268 13 600 600 601 602 601 601 602 602 602 602 600 602 600 602 4508 4508 4513 4510 23 1295 4500 24 4499 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 8 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 9 8 9 9 9 9 9 9 9 9 9 9 9 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Maple Tree implementation * Copyright (c) 2018-2022 Oracle Corporation * Authors: Liam R. Howlett <liam@infradead.org> * Matthew Wilcox <willy@infradead.org> * Copyright (c) 2023 ByteDance * Author: Peng Zhang <zhangpeng.00@bytedance.com> */ /* * DOC: Interesting implementation details of the Maple Tree * * Each node type has a number of slots for entries and a number of slots for * pivots. In the case of dense nodes, the pivots are implied by the position * and are simply the slot index + the minimum of the node. * * In regular B-Tree terms, pivots are called keys. The term pivot is used to * indicate that the tree is specifying ranges. Pivots may appear in the * subtree with an entry attached to the value whereas keys are unique to a * specific position of a B-tree. Pivot values are inclusive of the slot with * the same index. * * * The following illustrates the layout of a range64 nodes slots and pivots. * * * Slots -> | 0 | 1 | 2 | ... | 12 | 13 | 14 | 15 | * ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ ┬ * │ │ │ │ │ │ │ │ └─ Implied maximum * │ │ │ │ │ │ │ └─ Pivot 14 * │ │ │ │ │ │ └─ Pivot 13 * │ │ │ │ │ └─ Pivot 12 * │ │ │ │ └─ Pivot 11 * │ │ │ └─ Pivot 2 * │ │ └─ Pivot 1 * │ └─ Pivot 0 * └─ Implied minimum * * Slot contents: * Internal (non-leaf) nodes contain pointers to other nodes. * Leaf nodes contain entries. * * The location of interest is often referred to as an offset. All offsets have * a slot, but the last offset has an implied pivot from the node above (or * UINT_MAX for the root node. * * Ranges complicate certain write activities. When modifying any of * the B-tree variants, it is known that one entry will either be added or * deleted. When modifying the Maple Tree, one store operation may overwrite * the entire data set, or one half of the tree, or the middle half of the tree. * */ #include <linux/maple_tree.h> #include <linux/xarray.h> #include <linux/types.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/limits.h> #include <asm/barrier.h> #define CREATE_TRACE_POINTS #include <trace/events/maple_tree.h> #define TP_FCT tracepoint_string(__func__) /* * Kernel pointer hashing renders much of the maple tree dump useless as tagged * pointers get hashed to arbitrary values. * * If CONFIG_DEBUG_VM_MAPLE_TREE is set we are in a debug mode where it is * permissible to bypass this. Otherwise remain cautious and retain the hashing. * * Userland doesn't know about %px so also use %p there. */ #if defined(__KERNEL__) && defined(CONFIG_DEBUG_VM_MAPLE_TREE) #define PTR_FMT "%px" #else #define PTR_FMT "%p" #endif #define MA_ROOT_PARENT 1 /* * Maple state flags * * MA_STATE_PREALLOC - Preallocated nodes, WARN_ON allocation */ #define MA_STATE_PREALLOC 1 #define ma_parent_ptr(x) ((struct maple_pnode *)(x)) #define mas_tree_parent(x) ((unsigned long)(x->tree) | MA_ROOT_PARENT) #define ma_mnode_ptr(x) ((struct maple_node *)(x)) #define ma_enode_ptr(x) ((struct maple_enode *)(x)) static struct kmem_cache *maple_node_cache; #ifdef CONFIG_DEBUG_MAPLE_TREE static const unsigned long mt_max[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = ULONG_MAX, [maple_range_64] = ULONG_MAX, [maple_arange_64] = ULONG_MAX, [maple_copy] = ULONG_MAX, }; #define mt_node_max(x) mt_max[mte_node_type(x)] #endif static const unsigned char mt_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS, [maple_leaf_64] = MAPLE_RANGE64_SLOTS, [maple_range_64] = MAPLE_RANGE64_SLOTS, [maple_arange_64] = MAPLE_ARANGE64_SLOTS, [maple_copy] = 3, }; #define mt_slot_count(x) mt_slots[mte_node_type(x)] static const unsigned char mt_pivots[] = { [maple_dense] = 0, [maple_leaf_64] = MAPLE_RANGE64_SLOTS - 1, [maple_range_64] = MAPLE_RANGE64_SLOTS - 1, [maple_arange_64] = MAPLE_ARANGE64_SLOTS - 1, [maple_copy] = 3, }; #define mt_pivot_count(x) mt_pivots[mte_node_type(x)] static const unsigned char mt_min_slots[] = { [maple_dense] = MAPLE_NODE_SLOTS / 2, [maple_leaf_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_range_64] = (MAPLE_RANGE64_SLOTS / 2) - 2, [maple_arange_64] = (MAPLE_ARANGE64_SLOTS / 2) - 1, [maple_copy] = 1, /* Should never be used */ }; #define mt_min_slot_count(x) mt_min_slots[mte_node_type(x)] /* Functions */ static inline struct maple_node *mt_alloc_one(gfp_t gfp) { return kmem_cache_alloc(maple_node_cache, gfp); } static inline void mt_free_bulk(size_t size, void __rcu **nodes) { kmem_cache_free_bulk(maple_node_cache, size, (void **)nodes); } static void mt_return_sheaf(struct slab_sheaf *sheaf) { kmem_cache_return_sheaf(maple_node_cache, GFP_NOWAIT, sheaf); } static struct slab_sheaf *mt_get_sheaf(gfp_t gfp, int count) { return kmem_cache_prefill_sheaf(maple_node_cache, gfp, count); } static int mt_refill_sheaf(gfp_t gfp, struct slab_sheaf **sheaf, unsigned int size) { return kmem_cache_refill_sheaf(maple_node_cache, gfp, sheaf, size); } /* * ma_free_rcu() - Use rcu callback to free a maple node * @node: The node to free * * The maple tree uses the parent pointer to indicate this node is no longer in * use and will be freed. */ static void ma_free_rcu(struct maple_node *node) { WARN_ON(node->parent != ma_parent_ptr(node)); kfree_rcu(node, rcu); } static void mt_set_height(struct maple_tree *mt, unsigned char height) { unsigned int new_flags = mt->ma_flags; new_flags &= ~MT_FLAGS_HEIGHT_MASK; MT_BUG_ON(mt, height > MAPLE_HEIGHT_MAX); new_flags |= height << MT_FLAGS_HEIGHT_OFFSET; mt->ma_flags = new_flags; } static unsigned int mas_mt_height(struct ma_state *mas) { return mt_height(mas->tree); } static inline unsigned int mt_attr(struct maple_tree *mt) { return mt->ma_flags & ~MT_FLAGS_HEIGHT_MASK; } static __always_inline enum maple_type mte_node_type( const struct maple_enode *entry) { return ((unsigned long)entry >> MAPLE_NODE_TYPE_SHIFT) & MAPLE_NODE_TYPE_MASK; } static __always_inline bool ma_is_dense(const enum maple_type type) { return type < maple_leaf_64; } static __always_inline bool ma_is_leaf(const enum maple_type type) { return type < maple_range_64; } static __always_inline bool mte_is_leaf(const struct maple_enode *entry) { return ma_is_leaf(mte_node_type(entry)); } /* * We also reserve values with the bottom two bits set to '10' which are * below 4096 */ static __always_inline bool mt_is_reserved(const void *entry) { return ((unsigned long)entry < MAPLE_RESERVED_RANGE) && xa_is_internal(entry); } static __always_inline void mas_set_err(struct ma_state *mas, long err) { mas->node = MA_ERROR(err); mas->status = ma_error; } static __always_inline bool mas_is_ptr(const struct ma_state *mas) { return mas->status == ma_root; } static __always_inline bool mas_is_start(const struct ma_state *mas) { return mas->status == ma_start; } static __always_inline bool mas_is_none(const struct ma_state *mas) { return mas->status == ma_none; } static __always_inline bool mas_is_paused(const struct ma_state *mas) { return mas->status == ma_pause; } static __always_inline bool mas_is_overflow(struct ma_state *mas) { return mas->status == ma_overflow; } static inline bool mas_is_underflow(struct ma_state *mas) { return mas->status == ma_underflow; } static __always_inline struct maple_node *mte_to_node( const struct maple_enode *entry) { return (struct maple_node *)((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mte_to_mat() - Convert a maple encoded node to a maple topiary node. * @entry: The maple encoded node * * Return: a maple topiary pointer */ static inline struct maple_topiary *mte_to_mat(const struct maple_enode *entry) { return (struct maple_topiary *) ((unsigned long)entry & ~MAPLE_NODE_MASK); } /* * mas_mn() - Get the maple state node. * @mas: The maple state * * Return: the maple node (not encoded - bare pointer). */ static inline struct maple_node *mas_mn(const struct ma_state *mas) { return mte_to_node(mas->node); } /* * mte_set_node_dead() - Set a maple encoded node as dead. * @mn: The maple encoded node. */ static inline void mte_set_node_dead(struct maple_enode *mn) { mte_to_node(mn)->parent = ma_parent_ptr(mte_to_node(mn)); smp_wmb(); /* Needed for RCU */ } /* Bit 1 indicates the root is a node */ #define MAPLE_ROOT_NODE 0x02 /* maple_type stored bit 3-6 */ #define MAPLE_ENODE_TYPE_SHIFT 0x03 /* Bit 2 means a NULL somewhere below */ #define MAPLE_ENODE_NULL 0x04 static inline struct maple_enode *mt_mk_node(const struct maple_node *node, enum maple_type type) { return (void *)((unsigned long)node | (type << MAPLE_ENODE_TYPE_SHIFT) | MAPLE_ENODE_NULL); } static inline void ma_init_slot(void __rcu **slot, const struct maple_node *mn, const enum maple_type mt) { /* WARNING: this is unsafe if the slot is exposed to readers. */ RCU_INIT_POINTER(*slot, (void *)mt_mk_node(mn, mt)); } static inline void *mte_mk_root(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ROOT_NODE); } static inline void *mte_safe_root(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ROOT_NODE); } static inline void __maybe_unused *mte_set_full(const struct maple_enode *node) { return (void *)((unsigned long)node & ~MAPLE_ENODE_NULL); } static inline void __maybe_unused *mte_clear_full(const struct maple_enode *node) { return (void *)((unsigned long)node | MAPLE_ENODE_NULL); } static inline bool __maybe_unused mte_has_null(const struct maple_enode *node) { return (unsigned long)node & MAPLE_ENODE_NULL; } static __always_inline bool ma_is_root(struct maple_node *node) { return ((unsigned long)node->parent & MA_ROOT_PARENT); } static __always_inline bool mte_is_root(const struct maple_enode *node) { return ma_is_root(mte_to_node(node)); } static inline bool mas_is_root_limits(const struct ma_state *mas) { return !mas->min && mas->max == ULONG_MAX; } static __always_inline bool mt_is_alloc(struct maple_tree *mt) { return (mt->ma_flags & MT_FLAGS_ALLOC_RANGE); } /* * The Parent Pointer * Excluding root, the parent pointer is 256B aligned like all other tree nodes. * When storing a 32 or 64 bit values, the offset can fit into 5 bits. The 16 * bit values need an extra bit to store the offset. This extra bit comes from * a reuse of the last bit in the node type. This is possible by using bit 1 to * indicate if bit 2 is part of the type or the slot. * * Node types: * 0b??1 = Root * 0b?00 = 16 bit nodes * 0b010 = 32 bit nodes * 0b110 = 64 bit nodes * * Slot size and alignment * 0b??1 : Root * 0b?00 : 16 bit values, type in 0-1, slot in 2-7 * 0b010 : 32 bit values, type in 0-2, slot in 3-7 * 0b110 : 64 bit values, type in 0-2, slot in 3-7 */ #define MAPLE_PARENT_ROOT 0x01 #define MAPLE_PARENT_SLOT_SHIFT 0x03 #define MAPLE_PARENT_SLOT_MASK 0xF8 #define MAPLE_PARENT_16B_SLOT_SHIFT 0x02 #define MAPLE_PARENT_16B_SLOT_MASK 0xFC #define MAPLE_PARENT_RANGE64 0x06 #define MAPLE_PARENT_RANGE32 0x02 #define MAPLE_PARENT_NOT_RANGE16 0x02 /* * mte_parent_shift() - Get the parent shift for the slot storage. * @parent: The parent pointer cast as an unsigned long * Return: The shift into that pointer to the star to of the slot */ static inline unsigned long mte_parent_shift(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_SHIFT; return MAPLE_PARENT_16B_SLOT_SHIFT; } /* * mte_parent_slot_mask() - Get the slot mask for the parent. * @parent: The parent pointer cast as an unsigned long. * Return: The slot mask for that parent. */ static inline unsigned long mte_parent_slot_mask(unsigned long parent) { /* Note bit 1 == 0 means 16B */ if (likely(parent & MAPLE_PARENT_NOT_RANGE16)) return MAPLE_PARENT_SLOT_MASK; return MAPLE_PARENT_16B_SLOT_MASK; } /* * mas_parent_type() - Return the maple_type of the parent from the stored * parent type. * @mas: The maple state * @enode: The maple_enode to extract the parent's enum * Return: The node->parent maple_type */ static inline enum maple_type mas_parent_type(struct ma_state *mas, struct maple_enode *enode) { unsigned long p_type; p_type = (unsigned long)mte_to_node(enode)->parent; if (WARN_ON(p_type & MAPLE_PARENT_ROOT)) return 0; p_type &= MAPLE_NODE_MASK; p_type &= ~mte_parent_slot_mask(p_type); switch (p_type) { case MAPLE_PARENT_RANGE64: /* or MAPLE_PARENT_ARANGE64 */ if (mt_is_alloc(mas->tree)) return maple_arange_64; return maple_range_64; } return 0; } /* * mas_set_parent() - Set the parent node and encode the slot * @mas: The maple state * @enode: The encoded maple node. * @parent: The encoded maple node that is the parent of @enode. * @slot: The slot that @enode resides in @parent. * * Slot number is encoded in the enode->parent bit 3-6 or 2-6, depending on the * parent type. */ static inline void mas_set_parent(struct ma_state *mas, struct maple_enode *enode, const struct maple_enode *parent, unsigned char slot) { unsigned long val = (unsigned long)parent; unsigned long shift; unsigned long type; enum maple_type p_type = mte_node_type(parent); MAS_BUG_ON(mas, p_type == maple_dense); MAS_BUG_ON(mas, p_type == maple_leaf_64); switch (p_type) { case maple_range_64: case maple_arange_64: shift = MAPLE_PARENT_SLOT_SHIFT; type = MAPLE_PARENT_RANGE64; break; default: case maple_dense: case maple_leaf_64: shift = type = 0; break; } val &= ~MAPLE_NODE_MASK; /* Clear all node metadata in parent */ val |= (slot << shift) | type; mte_to_node(enode)->parent = ma_parent_ptr(val); } /* * mte_parent_slot() - get the parent slot of @enode. * @enode: The encoded maple node. * * Return: The slot in the parent node where @enode resides. */ static __always_inline unsigned int mte_parent_slot(const struct maple_enode *enode) { unsigned long val = (unsigned long)mte_to_node(enode)->parent; if (unlikely(val & MA_ROOT_PARENT)) return 0; /* * Okay to use MAPLE_PARENT_16B_SLOT_MASK as the last bit will be lost * by shift if the parent shift is MAPLE_PARENT_SLOT_SHIFT */ return (val & MAPLE_PARENT_16B_SLOT_MASK) >> mte_parent_shift(val); } /* * mte_parent() - Get the parent of @node. * @enode: The encoded maple node. * * Return: The parent maple node. */ static __always_inline struct maple_node *mte_parent(const struct maple_enode *enode) { return (void *)((unsigned long) (mte_to_node(enode)->parent) & ~MAPLE_NODE_MASK); } /* * ma_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool ma_dead_node(const struct maple_node *node) { struct maple_node *parent; /* Do not reorder reads from the node prior to the parent check */ smp_rmb(); parent = (void *)((unsigned long) node->parent & ~MAPLE_NODE_MASK); return (parent == node); } /* * mte_dead_node() - check if the @enode is dead. * @enode: The encoded maple node * * Return: true if dead, false otherwise. */ static __always_inline bool mte_dead_node(const struct maple_enode *enode) { struct maple_node *node; node = mte_to_node(enode); return ma_dead_node(node); } /* * ma_pivots() - Get a pointer to the maple node pivots. * @node: the maple node * @type: the node type * * In the event of a dead node, this array may be %NULL * * Return: A pointer to the maple node pivots */ static inline unsigned long *ma_pivots(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.pivot; case maple_range_64: case maple_leaf_64: return node->mr64.pivot; case maple_copy: return node->cp.pivot; case maple_dense: return NULL; } return NULL; } /* * ma_gaps() - Get a pointer to the maple node gaps. * @node: the maple node * @type: the node type * * Return: A pointer to the maple node gaps */ static inline unsigned long *ma_gaps(struct maple_node *node, enum maple_type type) { switch (type) { case maple_arange_64: return node->ma64.gap; case maple_copy: return node->cp.gap; case maple_range_64: case maple_leaf_64: case maple_dense: return NULL; } return NULL; } /* * mas_safe_pivot() - get the pivot at @piv or mas->max. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @piv: The pivot to fetch * @type: The maple node type * * Return: The pivot at @piv within the limit of the @pivots array, @mas->max * otherwise. */ static __always_inline unsigned long mas_safe_pivot(const struct ma_state *mas, unsigned long *pivots, unsigned char piv, enum maple_type type) { if (piv >= mt_pivots[type]) return mas->max; return pivots[piv]; } /* * mas_safe_min() - Return the minimum for a given offset. * @mas: The maple state * @pivots: The pointer to the maple node pivots * @offset: The offset into the pivot array * * Return: The minimum range value that is contained in @offset. */ static inline unsigned long mas_safe_min(struct ma_state *mas, unsigned long *pivots, unsigned char offset) { if (likely(offset)) return pivots[offset - 1] + 1; return mas->min; } /* * mte_set_pivot() - Set a pivot to a value in an encoded maple node. * @mn: The encoded maple node * @piv: The pivot offset * @val: The value of the pivot */ static inline void mte_set_pivot(struct maple_enode *mn, unsigned char piv, unsigned long val) { struct maple_node *node = mte_to_node(mn); enum maple_type type = mte_node_type(mn); BUG_ON(piv >= mt_pivots[type]); switch (type) { case maple_range_64: case maple_leaf_64: node->mr64.pivot[piv] = val; break; case maple_arange_64: node->ma64.pivot[piv] = val; break; case maple_copy: case maple_dense: break; } } /* * ma_slots() - Get a pointer to the maple node slots. * @mn: The maple node * @mt: The maple node type * * Return: A pointer to the maple node slots */ static inline void __rcu **ma_slots(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return mn->ma64.slot; case maple_range_64: case maple_leaf_64: return mn->mr64.slot; case maple_copy: return mn->cp.slot; case maple_dense: return mn->slot; } return NULL; } static inline bool mt_write_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_write_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline bool mt_locked(const struct maple_tree *mt) { return mt_external_lock(mt) ? mt_lock_is_held(mt) : lockdep_is_held(&mt->ma_lock); } static __always_inline void *mt_slot(const struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_check(slots[offset], mt_locked(mt)); } static __always_inline void *mt_slot_locked(struct maple_tree *mt, void __rcu **slots, unsigned char offset) { return rcu_dereference_protected(slots[offset], mt_write_locked(mt)); } /* * mas_slot_locked() - Get the slot value when holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset. */ static __always_inline void *mas_slot_locked(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot_locked(mas->tree, slots, offset); } /* * mas_slot() - Get the slot value when not holding the maple tree lock. * @mas: The maple state * @slots: The pointer to the slots * @offset: The offset into the slots array to fetch * * Return: The entry stored in @slots at the @offset */ static __always_inline void *mas_slot(struct ma_state *mas, void __rcu **slots, unsigned char offset) { return mt_slot(mas->tree, slots, offset); } /* * mas_root() - Get the maple tree root. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static __always_inline void *mas_root(struct ma_state *mas) { return rcu_dereference_check(mas->tree->ma_root, mt_locked(mas->tree)); } static inline void *mt_root_locked(struct maple_tree *mt) { return rcu_dereference_protected(mt->ma_root, mt_write_locked(mt)); } /* * mas_root_locked() - Get the maple tree root when holding the maple tree lock. * @mas: The maple state. * * Return: The pointer to the root of the tree */ static inline void *mas_root_locked(struct ma_state *mas) { return mt_root_locked(mas->tree); } static inline struct maple_metadata *ma_meta(struct maple_node *mn, enum maple_type mt) { switch (mt) { case maple_arange_64: return &mn->ma64.meta; default: return &mn->mr64.meta; } } /* * ma_set_meta() - Set the metadata information of a node. * @mn: The maple node * @mt: The maple node type * @offset: The offset of the highest sub-gap in this node. * @end: The end of the data in this node. */ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt, unsigned char offset, unsigned char end) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; meta->end = end; } /* * mt_clear_meta() - clear the metadata information of a node, if it exists * @mt: The maple tree * @mn: The maple node * @type: The maple node type */ static inline void mt_clear_meta(struct maple_tree *mt, struct maple_node *mn, enum maple_type type) { struct maple_metadata *meta; unsigned long *pivots; void __rcu **slots; void *next; switch (type) { case maple_range_64: pivots = mn->mr64.pivot; if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) { slots = mn->mr64.slot; next = mt_slot_locked(mt, slots, MAPLE_RANGE64_SLOTS - 1); if (unlikely((mte_to_node(next) && mte_node_type(next)))) return; /* no metadata, could be node */ } fallthrough; case maple_arange_64: meta = ma_meta(mn, type); break; default: return; } meta->gap = 0; meta->end = 0; } /* * ma_meta_end() - Get the data end of a node from the metadata * @mn: The maple node * @mt: The maple node type */ static inline unsigned char ma_meta_end(struct maple_node *mn, enum maple_type mt) { struct maple_metadata *meta = ma_meta(mn, mt); return meta->end; } /* * ma_meta_gap() - Get the largest gap location of a node from the metadata * @mn: The maple node */ static inline unsigned char ma_meta_gap(struct maple_node *mn) { return mn->ma64.meta.gap; } /* * ma_set_meta_gap() - Set the largest gap location in a nodes metadata * @mn: The maple node * @mt: The maple node type * @offset: The location of the largest gap. */ static inline void ma_set_meta_gap(struct maple_node *mn, enum maple_type mt, unsigned char offset) { struct maple_metadata *meta = ma_meta(mn, mt); meta->gap = offset; } /* * mat_add() - Add a @dead_enode to the ma_topiary of a list of dead nodes. * @mat: the ma_topiary, a linked list of dead nodes. * @dead_enode: the node to be marked as dead and added to the tail of the list * * Add the @dead_enode to the linked list in @mat. */ static inline void mat_add(struct ma_topiary *mat, struct maple_enode *dead_enode) { mte_set_node_dead(dead_enode); mte_to_mat(dead_enode)->next = NULL; if (!mat->tail) { mat->tail = mat->head = dead_enode; return; } mte_to_mat(mat->tail)->next = dead_enode; mat->tail = dead_enode; } static void mt_free_walk(struct rcu_head *head); static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free); /* * mas_mat_destroy() - Free all nodes and subtrees in a dead list. * @mas: the maple state * @mat: the ma_topiary linked list of dead nodes to free. * * Destroy walk a dead list. */ static void mas_mat_destroy(struct ma_state *mas, struct ma_topiary *mat) { struct maple_enode *next; struct maple_node *node; bool in_rcu = mt_in_rcu(mas->tree); while (mat->head) { next = mte_to_mat(mat->head)->next; node = mte_to_node(mat->head); mt_destroy_walk(mat->head, mas->tree, !in_rcu); if (in_rcu) call_rcu(&node->rcu, mt_free_walk); mat->head = next; } } /* * mas_descend() - Descend into the slot stored in the ma_state. * @mas: the maple state. * * Note: Not RCU safe, only use in write side or debug code. */ static inline void mas_descend(struct ma_state *mas) { enum maple_type type; unsigned long *pivots; struct maple_node *node; void __rcu **slots; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); slots = ma_slots(node, type); if (mas->offset) mas->min = pivots[mas->offset - 1] + 1; mas->max = mas_safe_pivot(mas, pivots, mas->offset, type); mas->node = mas_slot(mas, slots, mas->offset); } /* * mas_ascend() - Walk up a level of the tree. * @mas: The maple state * * Sets the @mas->max and @mas->min for the parent node of mas->node. This * may cause several levels of walking up to find the correct min and max. * May find a dead node which will cause a premature return. * Return: 1 on dead node, 0 otherwise */ static int mas_ascend(struct ma_state *mas) { struct maple_enode *p_enode; /* parent enode. */ struct maple_enode *a_enode; /* ancestor enode. */ struct maple_node *a_node; /* ancestor node. */ struct maple_node *p_node; /* parent node. */ unsigned char a_slot; enum maple_type a_type; unsigned long min, max; unsigned long *pivots; bool set_max = false, set_min = false; a_node = mas_mn(mas); if (ma_is_root(a_node)) { mas->offset = 0; return 0; } p_node = mte_parent(mas->node); if (unlikely(a_node == p_node)) return 1; a_type = mas_parent_type(mas, mas->node); mas->offset = mte_parent_slot(mas->node); a_enode = mt_mk_node(p_node, a_type); /* Check to make sure all parent information is still accurate */ if (p_node != mte_parent(mas->node)) return 1; mas->node = a_enode; if (mte_is_root(a_enode)) { mas->max = ULONG_MAX; mas->min = 0; return 0; } min = 0; max = ULONG_MAX; /* * !mas->offset implies that parent node min == mas->min. * mas->offset > 0 implies that we need to walk up to find the * implied pivot min. */ if (!mas->offset) { min = mas->min; set_min = true; } if (mas->max == ULONG_MAX) set_max = true; do { p_enode = a_enode; a_type = mas_parent_type(mas, p_enode); a_node = mte_parent(p_enode); a_slot = mte_parent_slot(p_enode); a_enode = mt_mk_node(a_node, a_type); pivots = ma_pivots(a_node, a_type); if (unlikely(ma_dead_node(a_node))) return 1; if (!set_min && a_slot) { set_min = true; min = pivots[a_slot - 1] + 1; } if (!set_max && a_slot < mt_pivots[a_type]) { set_max = true; max = pivots[a_slot]; } if (unlikely(ma_dead_node(a_node))) return 1; if (unlikely(ma_is_root(a_node))) break; } while (!set_min || !set_max); mas->max = max; mas->min = min; return 0; } /* * mas_pop_node() - Get a previously allocated maple node from the maple state. * @mas: The maple state * * Return: A pointer to a maple node. */ static __always_inline struct maple_node *mas_pop_node(struct ma_state *mas) { struct maple_node *ret; if (mas->alloc) { ret = mas->alloc; mas->alloc = NULL; goto out; } if (WARN_ON_ONCE(!mas->sheaf)) return NULL; ret = kmem_cache_alloc_from_sheaf(maple_node_cache, GFP_NOWAIT, mas->sheaf); out: memset(ret, 0, sizeof(*ret)); return ret; } /* * mas_alloc_nodes() - Allocate nodes into a maple state * @mas: The maple state * @gfp: The GFP Flags */ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp) { if (!mas->node_request) return; if (mas->node_request == 1) { if (mas->sheaf) goto use_sheaf; if (mas->alloc) return; mas->alloc = mt_alloc_one(gfp); if (!mas->alloc) goto error; mas->node_request = 0; return; } use_sheaf: if (unlikely(mas->alloc)) { kfree(mas->alloc); mas->alloc = NULL; } if (mas->sheaf) { unsigned long refill; refill = mas->node_request; if (kmem_cache_sheaf_size(mas->sheaf) >= refill) { mas->node_request = 0; return; } if (mt_refill_sheaf(gfp, &mas->sheaf, refill)) goto error; mas->node_request = 0; return; } mas->sheaf = mt_get_sheaf(gfp, mas->node_request); if (likely(mas->sheaf)) { mas->node_request = 0; return; } error: mas_set_err(mas, -ENOMEM); } static inline void mas_empty_nodes(struct ma_state *mas) { mas->node_request = 0; if (mas->sheaf) { mt_return_sheaf(mas->sheaf); mas->sheaf = NULL; } if (mas->alloc) { kfree(mas->alloc); mas->alloc = NULL; } } /* * mas_free() - Free an encoded maple node * @mas: The maple state * @used: The encoded maple node to free. * * Uses rcu free if necessary, pushes @used back on the maple state allocations * otherwise. */ static inline void mas_free(struct ma_state *mas, struct maple_enode *used) { ma_free_rcu(mte_to_node(used)); } /* * mas_start() - Sets up maple state for operations. * @mas: The maple state. * * If mas->status == ma_start, then set the min, max and depth to * defaults. * * Return: * - If mas->node is an error or not mas_start, return NULL. * - If it's an empty tree: NULL & mas->status == ma_none * - If it's a single entry: The entry & mas->status == ma_root * - If it's a tree: NULL & mas->status == ma_active */ static inline struct maple_enode *mas_start(struct ma_state *mas) { if (likely(mas_is_start(mas))) { struct maple_enode *root; mas->min = 0; mas->max = ULONG_MAX; retry: mas->depth = 0; root = mas_root(mas); /* Tree with nodes */ if (likely(xa_is_node(root))) { mas->depth = 0; mas->status = ma_active; mas->node = mte_safe_root(root); mas->offset = 0; if (mte_dead_node(mas->node)) goto retry; return NULL; } mas->node = NULL; /* empty tree */ if (unlikely(!root)) { mas->status = ma_none; mas->offset = MAPLE_NODE_SLOTS; return NULL; } /* Single entry tree */ mas->status = ma_root; mas->offset = MAPLE_NODE_SLOTS; /* Single entry tree. */ if (mas->index > 0) return NULL; return root; } return NULL; } /* * ma_data_end() - Find the end of the data in a node. * @node: The maple node * @type: The maple node type * @pivots: The array of pivots in the node * @max: The maximum value in the node * * Uses metadata to find the end of the data when possible. * Return: The zero indexed last slot with data (may be null). */ static __always_inline unsigned char ma_data_end(struct maple_node *node, enum maple_type type, unsigned long *pivots, unsigned long max) { unsigned char offset; if (!pivots) return 0; if (type == maple_arange_64) return ma_meta_end(node, type); offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == max)) return offset; return mt_pivots[type]; } /* * mas_data_end() - Find the end of the data (slot). * @mas: the maple state * * This method is optimized to check the metadata of a node if the node type * supports data end metadata. * * Return: The zero indexed last slot with data (may be null). */ static inline unsigned char mas_data_end(struct ma_state *mas) { enum maple_type type; struct maple_node *node; unsigned char offset; unsigned long *pivots; type = mte_node_type(mas->node); node = mas_mn(mas); if (type == maple_arange_64) return ma_meta_end(node, type); pivots = ma_pivots(node, type); if (unlikely(ma_dead_node(node))) return 0; offset = mt_pivots[type] - 1; if (likely(!pivots[offset])) return ma_meta_end(node, type); if (likely(pivots[offset] == mas->max)) return offset; return mt_pivots[type]; } static inline void wr_mas_setup(struct ma_wr_state *wr_mas, struct ma_state *mas) { wr_mas->node = mas_mn(mas); wr_mas->type = mte_node_type(mas->node); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type); wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, mas->offset); wr_mas->r_max = mas_safe_pivot(mas, wr_mas->pivots, mas->offset, wr_mas->type); } static inline void wr_mas_ascend(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; mas_ascend(mas); wr_mas_setup(wr_mas, mas); mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); /* Careful, this may be wrong.. */ wr_mas->end_piv = wr_mas->r_max; wr_mas->offset_end = mas->offset; } static inline unsigned long ma_leaf_max_gap(struct maple_node *mn, enum maple_type mt, unsigned long min, unsigned long max, unsigned long *pivots, void __rcu **slots) { unsigned long pstart, gap, max_gap; unsigned char i; unsigned char max_piv; max_gap = 0; if (unlikely(ma_is_dense(mt))) { gap = 0; for (i = 0; i < mt_slots[mt]; i++) { if (slots[i]) { if (gap > max_gap) max_gap = gap; gap = 0; } else { gap++; } } if (gap > max_gap) max_gap = gap; return max_gap; } /* * Check the first implied pivot optimizes the loop below and slot 1 may * be skipped if there is a gap in slot 0. */ if (likely(!slots[0])) { max_gap = pivots[0] - min + 1; i = 2; } else { i = 1; } /* reduce max_piv as the special case is checked before the loop */ max_piv = ma_data_end(mn, mt, pivots, max) - 1; /* * Check end implied pivot which can only be a gap on the right most * node. */ if (unlikely(max == ULONG_MAX) && !slots[max_piv + 1]) { gap = ULONG_MAX - pivots[max_piv]; if (gap > max_gap) max_gap = gap; if (max_gap > pivots[max_piv] - min) return max_gap; } for (; i <= max_piv; i++) { /* data == no gap. */ if (likely(slots[i])) continue; pstart = pivots[i - 1]; gap = pivots[i] - pstart; if (gap > max_gap) max_gap = gap; /* There cannot be two gaps in a row. */ i++; } return max_gap; } /* * mas_leaf_max_gap() - Returns the largest gap in a leaf node * @mas: the maple state * * Return: The maximum gap in the leaf. */ static inline unsigned long mas_leaf_max_gap(struct ma_state *mas) { enum maple_type mt; struct maple_node *mn; unsigned long *pivots; void __rcu **slots; mn = mas_mn(mas); mt = mte_node_type(mas->node); slots = ma_slots(mn, mt); pivots = ma_pivots(mn, mt); return ma_leaf_max_gap(mn, mt, mas->min, mas->max, pivots, slots); } /* * ma_max_gap() - Get the maximum gap in a maple node (non-leaf) * @node: The maple node * @gaps: The pointer to the gaps * @mt: The maple node type * @off: Pointer to store the offset location of the gap. * * Uses the metadata data end to scan backwards across set gaps. * * Return: The maximum gap value */ static inline unsigned long ma_max_gap(struct maple_node *node, unsigned long *gaps, enum maple_type mt, unsigned char *off) { unsigned char offset, i; unsigned long max_gap = 0; i = offset = ma_meta_end(node, mt); do { if (gaps[i] > max_gap) { max_gap = gaps[i]; offset = i; } } while (i--); *off = offset; return max_gap; } /* * mas_max_gap() - find the largest gap in a non-leaf node and set the slot. * @mas: The maple state. * * Return: The gap value. */ static inline unsigned long mas_max_gap(struct ma_state *mas) { unsigned long *gaps; unsigned char offset; enum maple_type mt; struct maple_node *node; mt = mte_node_type(mas->node); if (ma_is_leaf(mt)) return mas_leaf_max_gap(mas); node = mas_mn(mas); MAS_BUG_ON(mas, mt != maple_arange_64); offset = ma_meta_gap(node); gaps = ma_gaps(node, mt); return gaps[offset]; } /* * mas_parent_gap() - Set the parent gap and any gaps above, as needed * @mas: The maple state * @offset: The gap offset in the parent to set * @new: The new gap value. * * Set the parent gap then continue to set the gap upwards, using the metadata * of the parent to see if it is necessary to check the node above. */ static inline void mas_parent_gap(struct ma_state *mas, unsigned char offset, unsigned long new) { unsigned long meta_gap = 0; struct maple_node *pnode; struct maple_enode *penode; unsigned long *pgaps; unsigned char meta_offset; enum maple_type pmt; pnode = mte_parent(mas->node); pmt = mas_parent_type(mas, mas->node); penode = mt_mk_node(pnode, pmt); pgaps = ma_gaps(pnode, pmt); ascend: MAS_BUG_ON(mas, pmt != maple_arange_64); meta_offset = ma_meta_gap(pnode); meta_gap = pgaps[meta_offset]; pgaps[offset] = new; if (meta_gap == new) return; if (offset != meta_offset) { if (meta_gap > new) return; ma_set_meta_gap(pnode, pmt, offset); } else if (new < meta_gap) { new = ma_max_gap(pnode, pgaps, pmt, &meta_offset); ma_set_meta_gap(pnode, pmt, meta_offset); } if (ma_is_root(pnode)) return; /* Go to the parent node. */ pnode = mte_parent(penode); pmt = mas_parent_type(mas, penode); pgaps = ma_gaps(pnode, pmt); offset = mte_parent_slot(penode); penode = mt_mk_node(pnode, pmt); goto ascend; } /* * mas_update_gap() - Update a nodes gaps and propagate up if necessary. * @mas: the maple state. */ static inline void mas_update_gap(struct ma_state *mas) { unsigned char pslot; unsigned long p_gap; unsigned long max_gap; if (!mt_is_alloc(mas->tree)) return; if (mte_is_root(mas->node)) return; max_gap = mas_max_gap(mas); pslot = mte_parent_slot(mas->node); p_gap = ma_gaps(mte_parent(mas->node), mas_parent_type(mas, mas->node))[pslot]; if (p_gap != max_gap) mas_parent_gap(mas, pslot, max_gap); } /* * mas_adopt_children() - Set the parent pointer of all nodes in @parent to * @parent with the slot encoded. * @mas: the maple state (for the tree) * @parent: the maple encoded node containing the children. */ static inline void mas_adopt_children(struct ma_state *mas, struct maple_enode *parent) { enum maple_type type = mte_node_type(parent); struct maple_node *node = mte_to_node(parent); void __rcu **slots = ma_slots(node, type); unsigned long *pivots = ma_pivots(node, type); struct maple_enode *child; unsigned char offset; offset = ma_data_end(node, type, pivots, mas->max); do { child = mas_slot_locked(mas, slots, offset); mas_set_parent(mas, child, parent, offset); } while (offset--); } /* * mas_put_in_tree() - Put a new node in the tree, smp_wmb(), and mark the old * node as dead. * @mas: the maple state with the new node * @old_enode: The old maple encoded node to replace. * @new_height: if we are inserting a root node, update the height of the tree */ static inline void mas_put_in_tree(struct ma_state *mas, struct maple_enode *old_enode, char new_height) __must_hold(mas->tree->ma_lock) { unsigned char offset; void __rcu **slots; if (mte_is_root(mas->node)) { mas_mn(mas)->parent = ma_parent_ptr(mas_tree_parent(mas)); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); mt_set_height(mas->tree, new_height); } else { offset = mte_parent_slot(mas->node); slots = ma_slots(mte_parent(mas->node), mas_parent_type(mas, mas->node)); rcu_assign_pointer(slots[offset], mas->node); } mte_set_node_dead(old_enode); } /* * mas_replace_node() - Replace a node by putting it in the tree, marking it * dead, and freeing it. * the parent encoding to locate the maple node in the tree. * @mas: the ma_state with @mas->node pointing to the new node. * @old_enode: The old maple encoded node. * @new_height: The new height of the tree as a result of the operation */ static inline void mas_replace_node(struct ma_state *mas, struct maple_enode *old_enode, unsigned char new_height) __must_hold(mas->tree->ma_lock) { mas_put_in_tree(mas, old_enode, new_height); mas_free(mas, old_enode); } /* * mas_find_child() - Find a child who has the parent @mas->node. * @mas: the maple state with the parent. * @child: the maple state to store the child. */ static inline bool mas_find_child(struct ma_state *mas, struct ma_state *child) __must_hold(mas->tree->ma_lock) { enum maple_type mt; unsigned char offset; unsigned char end; unsigned long *pivots; struct maple_enode *entry; struct maple_node *node; void __rcu **slots; mt = mte_node_type(mas->node); node = mas_mn(mas); slots = ma_slots(node, mt); pivots = ma_pivots(node, mt); end = ma_data_end(node, mt, pivots, mas->max); for (offset = mas->offset; offset <= end; offset++) { entry = mas_slot_locked(mas, slots, offset); if (mte_parent(entry) == node) { *child = *mas; mas->offset = offset + 1; child->offset = offset; mas_descend(child); child->offset = 0; return true; } } return false; } /* * mas_leaf_set_meta() - Set the metadata of a leaf if possible. * @node: The maple node * @mt: The maple type * @end: The node end */ static inline void mas_leaf_set_meta(struct maple_node *node, enum maple_type mt, unsigned char end) { if (end < mt_slots[mt] - 1) ma_set_meta(node, mt, 0, end); } /* * mas_prev_sibling() - Find the previous node with the same parent. * @mas: the maple state * * Return: True if there is a previous sibling, false otherwise. */ static inline bool mas_prev_sibling(struct ma_state *mas) { unsigned int p_slot = mte_parent_slot(mas->node); /* For root node, p_slot is set to 0 by mte_parent_slot(). */ if (!p_slot) return false; mas_ascend(mas); mas->offset = p_slot - 1; mas_descend(mas); return true; } /* * mas_next_sibling() - Find the next node with the same parent. * @mas: the maple state * * Return: true if there is a next sibling, false otherwise. */ static inline bool mas_next_sibling(struct ma_state *mas) { MA_STATE(parent, mas->tree, mas->index, mas->last); if (mte_is_root(mas->node)) return false; parent = *mas; mas_ascend(&parent); parent.offset = mte_parent_slot(mas->node) + 1; if (parent.offset > mas_data_end(&parent)) return false; *mas = parent; mas_descend(mas); return true; } /* * mas_wr_node_walk() - Find the correct offset for the index in the @mas. * If @mas->index cannot be found within the containing * node, we traverse to the last entry in the node. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. */ static inline void mas_wr_node_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char count, offset; if (unlikely(ma_is_dense(wr_mas->type))) { wr_mas->r_max = wr_mas->r_min = mas->index; mas->offset = mas->index = mas->min; return; } wr_mas->node = mas_mn(wr_mas->mas); wr_mas->pivots = ma_pivots(wr_mas->node, wr_mas->type); count = mas->end = ma_data_end(wr_mas->node, wr_mas->type, wr_mas->pivots, mas->max); offset = mas->offset; while (offset < count && mas->index > wr_mas->pivots[offset]) offset++; wr_mas->r_max = offset < count ? wr_mas->pivots[offset] : mas->max; wr_mas->r_min = mas_safe_min(mas, wr_mas->pivots, offset); wr_mas->offset_end = mas->offset = offset; } static inline void rebalance_sib(struct ma_state *parent, struct ma_state *sib) { *sib = *parent; /* Prioritize move right to pull data left */ if (sib->offset < sib->end) sib->offset++; else sib->offset--; mas_descend(sib); sib->end = mas_data_end(sib); } static inline void spanning_sib(struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *nneighbour) { struct ma_state l_tmp = *l_wr_mas->mas; struct ma_state r_tmp = *r_wr_mas->mas; unsigned char depth = 0; do { mas_ascend(&r_tmp); mas_ascend(&l_tmp); depth++; if (r_tmp.offset < mas_data_end(&r_tmp)) { r_tmp.offset++; mas_descend(&r_tmp); r_tmp.offset = 0; while (--depth) mas_descend(&r_tmp); r_tmp.end = mas_data_end(&r_tmp); *nneighbour = r_tmp; return; } else if (l_tmp.offset) { l_tmp.offset--; do { mas_descend(&l_tmp); l_tmp.offset = mas_data_end(&l_tmp); } while (--depth); l_tmp.end = l_tmp.offset; *nneighbour = l_tmp; return; } } while (!mte_is_root(r_tmp.node)); WARN_ON_ONCE(1); } /* * mas_topiary_node() - Dispose of a single node * @mas: The maple state for pushing nodes * @in_rcu: If the tree is in rcu mode * * The node will either be RCU freed or pushed back on the maple state. */ static inline void mas_topiary_node(struct ma_state *mas, struct ma_state *tmp_mas, bool in_rcu) { struct maple_node *tmp; struct maple_enode *enode; if (mas_is_none(tmp_mas)) return; enode = tmp_mas->node; tmp = mte_to_node(enode); mte_set_node_dead(enode); ma_free_rcu(tmp); } /* * mas_topiary_replace() - Replace the data with new data, then repair the * parent links within the new tree. Iterate over the dead sub-tree and collect * the dead subtrees and topiary the nodes that are no longer of use. * * The new tree will have up to three children with the correct parent. Keep * track of the new entries as they need to be followed to find the next level * of new entries. * * The old tree will have up to three children with the old parent. Keep track * of the old entries as they may have more nodes below replaced. Nodes within * [index, last] are dead subtrees, others need to be freed and followed. * * @mas: The maple state pointing at the new data * @old_enode: The maple encoded node being replaced * @new_height: The new height of the tree as a result of the operation * */ static inline void mas_topiary_replace(struct ma_state *mas, struct maple_enode *old_enode, unsigned char new_height) { struct ma_state tmp[3], tmp_next[3]; MA_TOPIARY(subtrees, mas->tree); bool in_rcu; int i, n; /* Place data in tree & then mark node as old */ mas_put_in_tree(mas, old_enode, new_height); /* Update the parent pointers in the tree */ tmp[0] = *mas; tmp[0].offset = 0; tmp[1].status = ma_none; tmp[2].status = ma_none; while (!mte_is_leaf(tmp[0].node)) { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; n++; } mas_adopt_children(&tmp[i], tmp[i].node); } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) tmp[i] = tmp_next[i]; } /* Collect the old nodes that need to be discarded */ if (mte_is_leaf(old_enode)) return mas_free(mas, old_enode); tmp[0] = *mas; tmp[0].offset = 0; tmp[0].node = old_enode; tmp[1].status = ma_none; tmp[2].status = ma_none; in_rcu = mt_in_rcu(mas->tree); do { n = 0; for (i = 0; i < 3; i++) { if (mas_is_none(&tmp[i])) continue; while (n < 3) { if (!mas_find_child(&tmp[i], &tmp_next[n])) break; if ((tmp_next[n].min >= tmp_next->index) && (tmp_next[n].max <= tmp_next->last)) { mat_add(&subtrees, tmp_next[n].node); tmp_next[n].status = ma_none; } else { n++; } } } if (MAS_WARN_ON(mas, n == 0)) break; while (n < 3) tmp_next[n++].status = ma_none; for (i = 0; i < 3; i++) { mas_topiary_node(mas, &tmp[i], in_rcu); tmp[i] = tmp_next[i]; } } while (!mte_is_leaf(tmp[0].node)); for (i = 0; i < 3; i++) mas_topiary_node(mas, &tmp[i], in_rcu); mas_mat_destroy(mas, &subtrees); } /* * node_copy() - Copy from one node to another. * * @mas: The maple state * @src: The source node * @start: The offset into the src to start copying * @size: The size to copy (non-zero) * @s_max: The source node max * @s_mt: The source maple node type * @dst: The destination * @d_start: The start location in the destination node * @d_mt: The destination maple node type */ static inline unsigned long node_copy(struct ma_state *mas, struct maple_node *src, unsigned char start, unsigned char size, unsigned long s_max, enum maple_type s_mt, struct maple_node *dst, unsigned char d_start, enum maple_type d_mt) { unsigned long *s_pivots, *d_pivots; void __rcu **s_slots, **d_slots; unsigned long *s_gaps, *d_gaps; unsigned long d_max; d_slots = ma_slots(dst, d_mt) + d_start; d_pivots = ma_pivots(dst, d_mt) + d_start; s_slots = ma_slots(src, s_mt) + start; s_pivots = ma_pivots(src, s_mt) + start; memcpy(d_slots, s_slots, size * sizeof(void __rcu *)); if (!ma_is_leaf(d_mt) && s_mt == maple_copy) { struct maple_enode *edst = mt_mk_node(dst, d_mt); for (int i = 0; i < size; i++) mas_set_parent(mas, mt_slot_locked(mas->tree, d_slots, i), edst, d_start + i); } d_gaps = ma_gaps(dst, d_mt); if (d_gaps) { s_gaps = ma_gaps(src, s_mt) + start; d_gaps += d_start; memcpy(d_gaps, s_gaps, size * sizeof(unsigned long)); } if (start + size - 1 < mt_pivots[s_mt]) d_max = s_pivots[size - 1]; else d_max = s_max; if (d_start + size <= mt_pivots[d_mt]) d_pivots[size - 1] = d_max; size--; if (size) memcpy(d_pivots, s_pivots, size * sizeof(unsigned long)); return d_max; } /* * node_finalise() - Zero out unused area and populate metadata * @node: The maple node * @mt: The maple node type * @end: The end of the used area */ static inline void node_finalise(struct maple_node *node, enum maple_type mt, unsigned char end) { unsigned char max_end = mt_slots[mt]; unsigned char size; unsigned long *gaps; unsigned char gap_slot; gaps = ma_gaps(node, mt); if (end < max_end - 1) { size = max_end - end; memset(ma_slots(node, mt) + end, 0, size * sizeof(void *)); if (gaps) memset(gaps + end, 0, size * sizeof(unsigned long)); if (--size) memset(ma_pivots(node, mt) + end, 0, size * sizeof(unsigned long)); } gap_slot = 0; if (gaps && !ma_is_leaf(mt)) { unsigned long max_gap; max_gap = 0; for (int i = 0; i <= end; i++) if (gaps[i] > max_gap) { gap_slot = i; max_gap = gaps[i]; } } if (mt == maple_arange_64) ma_set_meta(node, mt, gap_slot, end - 1); else if (end <= max_end - 1) ma_set_meta(node, mt, gap_slot, end - 1); } static inline void *mtree_range_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next, *last; enum maple_type type; void __rcu **slots; unsigned char end; unsigned long max, min; unsigned long prev_max, prev_min; next = mas->node; min = mas->min; max = mas->max; do { last = next; node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = ma_data_end(node, type, pivots, max); prev_min = min; prev_max = max; if (pivots[0] >= mas->index) { offset = 0; max = pivots[0]; goto next; } offset = 1; while (offset < end) { if (pivots[offset] >= mas->index) { max = pivots[offset]; break; } offset++; } min = pivots[offset - 1] + 1; next: slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); mas->end = end; mas->offset = offset; mas->index = min; mas->last = max; mas->min = prev_min; mas->max = prev_max; mas->node = last; return (void *)next; dead_node: mas_reset(mas); return NULL; } /* * mas_wmb_replace() - Write memory barrier and replace * @mas: The maple state * @cp: The maple copy node * * Updates gap as necessary. */ static inline void mas_wmb_replace(struct ma_state *mas, struct maple_copy *cp) { struct maple_enode *old_enode; old_enode = mas->node; mas->node = mt_slot_locked(mas->tree, cp->slot, 0); /* Insert the new data in the tree */ mas_topiary_replace(mas, old_enode, cp->height); if (!mte_is_leaf(mas->node)) mas_update_gap(mas); mtree_range_walk(mas); } /* * cp_leaf_init() - Initialize a maple_copy node for the leaf level of a * spanning store * @cp: The maple copy node * @mas: The maple state * @l_wr_mas: The left write state of the spanning store * @r_wr_mas: The right write state of the spanning store */ static inline void cp_leaf_init(struct maple_copy *cp, struct ma_state *mas, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { unsigned char end = 0; /* * WARNING: The use of RCU_INIT_POINTER() makes it extremely important * to not expose the maple_copy node to any readers. Exposure may * result in buggy code when a compiler reorders the instructions. */ cp->height = 1; /* Create entries to insert including split entries to left and right */ if (l_wr_mas->r_min < mas->index) { end++; RCU_INIT_POINTER(cp->slot[0], l_wr_mas->content); cp->pivot[0] = mas->index - 1; } RCU_INIT_POINTER(cp->slot[end], l_wr_mas->entry); cp->pivot[end] = mas->last; if (r_wr_mas->end_piv > mas->last) { end++; RCU_INIT_POINTER(cp->slot[end], r_wr_mas->slots[r_wr_mas->offset_end]); cp->pivot[end] = r_wr_mas->end_piv; } cp->min = l_wr_mas->r_min; cp->max = cp->pivot[end]; cp->end = end; } /* * cp_data_calc() - Calculate the size of the data (1 indexed). * @cp: The maple copy struct with the new data populated. * @l_wr_mas: The maple write state containing the data to the left of the write * @r_wr_mas: The maple write state containing the data to the right of the * write * * cp->data is a size (not indexed by 0). */ static inline void cp_data_calc(struct maple_copy *cp, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { /* Add 1 every time for the 0th element */ cp->data = l_wr_mas->mas->offset; /* Add the new data and any partial overwrites */ cp->data += cp->end + 1; /* Data from right (offset + 1 to end), +1 for zero */ cp->data += r_wr_mas->mas->end - r_wr_mas->offset_end; } static bool data_fits(struct ma_state *sib, struct ma_state *mas, struct maple_copy *cp) { unsigned char new_data; enum maple_type type; unsigned char space; unsigned char end; type = mte_node_type(mas->node); space = 2 * mt_slots[type]; end = sib->end; new_data = end + 1 + cp->data; if (new_data > space) return false; /* * This is off by one by design. The extra space is left to reduce * jitter in operations that add then remove two entries. * * end is an index while new space and data are both sizes. Adding one * to end to convert the index to a size means that the below * calculation should be <=, but we want to keep an extra space in nodes * to reduce jitter. * * Note that it is still possible to get a full node on the left by the * NULL landing exactly on the split. The NULL ending of a node happens * in the dst_setup() function, where we will either increase the split * by one or decrease it by one, if possible. In the case of split * (this case), it is always possible to shift the spilt by one - again * because there is at least one slot free by the below checking. */ if (new_data < space) return true; return false; } static inline void push_data_sib(struct maple_copy *cp, struct ma_state *mas, struct ma_state *sib, struct ma_state *parent) { if (mte_is_root(mas->node)) goto no_push; *sib = *parent; if (sib->offset) { sib->offset--; mas_descend(sib); sib->end = mas_data_end(sib); if (data_fits(sib, mas, cp)) /* Push left */ return; *sib = *parent; } if (sib->offset >= sib->end) goto no_push; sib->offset++; mas_descend(sib); sib->end = mas_data_end(sib); if (data_fits(sib, mas, cp)) /* Push right*/ return; no_push: sib->end = 0; } /* * rebalance_data() - Calculate the @cp data, populate @sib if insufficient or * if the data can be pushed into a sibling. * @cp: The maple copy node * @wr_mas: The left write maple state * @sib: The maple state of the sibling. * * Note: @cp->data is a size and not indexed by 0. @sib->end may be set to 0 to * indicate it will not be used. * */ static inline void rebalance_data(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { cp_data_calc(cp, wr_mas, wr_mas); sib->end = 0; if (cp->data > mt_slots[wr_mas->type]) { push_data_sib(cp, wr_mas->mas, sib, parent); if (sib->end) goto use_sib; } else if (cp->data <= mt_min_slots[wr_mas->type]) { if ((wr_mas->mas->min != 0) || (wr_mas->mas->max != ULONG_MAX)) { rebalance_sib(parent, sib); goto use_sib; } } return; use_sib: cp->data += sib->end + 1; } /* * spanning_data() - Calculate the @cp data and populate @sib if insufficient * @cp: The maple copy node * @l_wr_mas: The left write maple state * @r_wr_mas: The right write maple state * @sib: The maple state of the sibling. * * Note: @cp->data is a size and not indexed by 0. @sib->end may be set to 0 to * indicate it will not be used. */ static inline void spanning_data(struct maple_copy *cp, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *sib) { cp_data_calc(cp, l_wr_mas, r_wr_mas); if (((l_wr_mas->mas->min != 0) || (r_wr_mas->mas->max != ULONG_MAX)) && (cp->data <= mt_min_slots[l_wr_mas->type])) { spanning_sib(l_wr_mas, r_wr_mas, sib); cp->data += sib->end + 1; } else { sib->end = 0; } } /* * dst_setup() - Set up one or more destinations for the new data. * @cp: The maple copy node * @mas: The maple state * @mt: The source node type */ static inline void dst_setup(struct maple_copy *cp, struct ma_state *mas, enum maple_type mt) { /* Data is 1 indexed, every src has +1 added. */ if (cp->data <= mt_slots[mt]) { cp->split = cp->data - 1; cp->d_count = 1; goto node_setup; } cp->split = (cp->data - 1) / 2; cp->d_count = 2; if (cp->data < mt_slots[mt] * 2) goto node_setup; if (cp->data == mt_slots[mt] * 2) { unsigned char off; unsigned char s; if (!ma_is_leaf(mt)) goto node_setup; /* * Leaf nodes are a bit tricky because we cannot assume the data * can fit due to the NULL limitation on node ends. */ off = cp->split; for (s = 0; s < cp->s_count; s++) { unsigned char s_off; s_off = cp->src[s].end - cp->src[s].start; if (s_off >= off) break; s_off++; off -= s_off; } off += cp->src[s].start; if (ma_slots(cp->src[s].node, cp->src[s].mt)[off]) goto node_setup; cp->split++; if (cp->split < mt_slots[mt]) goto node_setup; cp->split -= 2; if (cp->data - 2 - cp->split < mt_slots[mt]) goto node_setup; } /* No other choice but to 3-way split the data */ cp->split = (cp->data + 2) / 3; cp->d_count = 3; node_setup: for (int i = 0; i < cp->d_count; i++) { cp->dst[i].mt = mt; cp->dst[i].node = ma_mnode_ptr(mas_pop_node(mas)); } } static inline void append_mas_cp(struct maple_copy *cp, struct ma_state *mas, unsigned char start, unsigned char end) { struct maple_node *node; enum maple_type mt; unsigned char count; count = cp->s_count; node = mas_mn(mas); mt = mte_node_type(mas->node); cp->src[count].node = node; cp->src[count].mt = mt; if (mas->end <= end) cp->src[count].max = mas->max; else cp->src[count].max = ma_pivots(node, mt)[end]; cp->src[count].start = start; cp->src[count].end = end; cp->s_count++; } static inline void append_wr_mas_cp(struct maple_copy *cp, struct ma_wr_state *wr_mas, unsigned char start, unsigned char end) { unsigned char count; count = cp->s_count; cp->src[count].node = wr_mas->node; cp->src[count].mt = wr_mas->type; if (wr_mas->mas->end <= end) cp->src[count].max = wr_mas->mas->max; else cp->src[count].max = wr_mas->pivots[end]; cp->src[count].start = start; cp->src[count].end = end; cp->s_count++; } static inline void init_cp_src(struct maple_copy *cp) { cp->src[cp->s_count].node = ma_mnode_ptr(cp); cp->src[cp->s_count].mt = maple_copy; cp->src[cp->s_count].max = cp->max; cp->src[cp->s_count].start = 0; cp->src[cp->s_count].end = cp->end; cp->s_count++; } /* * multi_src_setup() - Set the @cp node up with multiple sources to copy from. * @cp: The maple copy node * @l_wr_mas: The left write maple state * @r_wr_mas: The right write maple state * @sib: The sibling maple state * * Note: @sib->end == 0 indicates no sibling will be used. */ static inline void multi_src_setup(struct maple_copy *cp, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *sib) { cp->s_count = 0; if (sib->end && sib->max < l_wr_mas->mas->min) append_mas_cp(cp, sib, 0, sib->end); /* Copy left 0 - offset */ if (l_wr_mas->mas->offset) { unsigned char off = l_wr_mas->mas->offset - 1; append_wr_mas_cp(cp, l_wr_mas, 0, off); cp->src[cp->s_count - 1].max = cp->min - 1; } init_cp_src(cp); /* Copy right either from offset or offset + 1 pending on r_max */ if (r_wr_mas->mas->end != r_wr_mas->offset_end) append_wr_mas_cp(cp, r_wr_mas, r_wr_mas->offset_end + 1, r_wr_mas->mas->end); if (sib->end && sib->min > r_wr_mas->mas->max) append_mas_cp(cp, sib, 0, sib->end); } static inline void cp_data_write(struct maple_copy *cp, struct ma_state *mas) { struct maple_node *dst, *src; unsigned char s, d; unsigned char dst_offset; unsigned char data_offset; unsigned char src_end, s_offset; unsigned char split; unsigned long s_max, d_max; unsigned char dst_size; enum maple_type s_mt, d_mt; data_offset = 0; s = d = 0; /* Readability help */ src = cp->src[s].node; dst = cp->dst[d].node; s_offset = cp->src[s].start; src_end = cp->src[s].end; split = cp->split; s_max = cp->src[s].max; s_mt = cp->src[s].mt; d_mt = cp->dst[d].mt; do { dst_offset = 0; d_max = 0; dst = cp->dst[d].node; d_mt = cp->dst[d].mt; dst_size = split + 1; while (dst_size) { unsigned char size; if (src_end - s_offset + 1 < dst_size) size = src_end - s_offset + 1; else size = dst_size; d_max = node_copy(mas, src, s_offset, size, s_max, s_mt, dst, dst_offset, d_mt); dst_offset += size; s_offset += size; if (s_offset > src_end) { /* This source is exhausted */ s++; if (s >= cp->s_count) { cp->dst[d].max = d_max; node_finalise(dst, d_mt, dst_offset); return; } /* Reset local src */ src = cp->src[s].node; s_offset = cp->src[s].start; src_end = cp->src[s].end; s_max = cp->src[s].max; s_mt = cp->src[s].mt; } dst_size -= size; data_offset += size; } split = cp->split; cp->dst[d].max = d_max; /* Handle null entries */ if (cp->dst[d].max != ULONG_MAX && !ma_slots(dst, d_mt)[dst_offset - 1]) { if (s_offset == cp->src[s].start) { s--; src = cp->src[s].node; src_end = cp->src[s].end; s_max = cp->src[s].max; s_mt = cp->src[s].mt; s_offset = src_end; } else { s_offset--; } /* Set dst max and clear pivot */ split++; data_offset--; dst_offset--; cp->dst[d].max = ma_pivots(dst, d_mt)[dst_offset - 1]; } node_finalise(dst, d_mt, dst_offset); ++d; /* Next destination */ if (d == cp->d_count - 1) split = cp->data - data_offset; if (d >= cp->d_count) { WARN_ON(data_offset < cp->data); return; } } while (data_offset <= cp->data); } /* * cp_dst_to_slots() - Migrate the maple copy destination to the maple copy * slots * @cp: The maple copy node * @min: The minimal value represented * @max: The maximum value represented * @mas: The maple state */ static inline void cp_dst_to_slots(struct maple_copy *cp, unsigned long min, unsigned long max, struct ma_state *mas) { unsigned char d; unsigned long slot_min = min; for (d = 0; d < cp->d_count; d++) { struct maple_node *mn = cp->dst[d].node; enum maple_type mt = cp->dst[d].mt; unsigned long slot_max = cp->dst[d].max; /* * Warning, see cp_leaf_init() comment and rcu_assign_pointer() * documentation. Since these are new nodes, there are no * read-side operations that can view them until they are * inserted into the tree after an rcu_assign_pointer() call. */ ma_init_slot(&cp->slot[d], mn, mt); cp->pivot[d] = slot_max; if (mt_is_alloc(mas->tree)) { if (ma_is_leaf(mt)) { cp->gap[d] = ma_leaf_max_gap(mn, mt, slot_min, slot_max, ma_pivots(mn, mt), ma_slots(mn, mt)); } else { unsigned long *gaps = ma_gaps(mn, mt); if (gaps) { unsigned char gap_slot; gap_slot = ma_meta_gap(mn); cp->gap[d] = gaps[gap_slot]; } } } slot_min = slot_max + 1; } cp->end = cp->d_count - 1; cp->min = min; cp->max = max; } static inline bool cp_is_new_root(struct maple_copy *cp, struct ma_state *mas) { if (cp->min || cp->max != ULONG_MAX) return false; if (cp->d_count != 1) { enum maple_type mt = maple_arange_64; if (!mt_is_alloc(mas->tree)) mt = maple_range_64; cp->data = cp->d_count; cp->s_count = 0; dst_setup(cp, mas, mt); init_cp_src(cp); node_copy(mas, cp->src[0].node, 0, cp->data, cp->max, maple_copy, cp->dst[0].node, 0, mt); node_finalise(cp->dst[0].node, mt, cp->end + 1); /* * Warning, see cp_leaf_init() comment and rcu_assign_pointer() * documentation. Since this is a new root, there are no * read-side operations that can view it until it is insert into * the tree after an rcu_assign_pointer() call. */ ma_init_slot(&cp->slot[0], cp->dst[0].node, mt); cp->height++; } WARN_ON_ONCE(cp->dst[0].node != mte_to_node( mt_slot_locked(mas->tree, cp->slot, 0))); cp->dst[0].node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->min = 0; mas->max = ULONG_MAX; mas->depth = 0; mas->node = mas_root_locked(mas); return true; } static inline bool cp_converged(struct maple_copy *cp, struct ma_state *mas, struct ma_state *sib) { if (cp->d_count != 1 || sib->end) return false; cp->dst[0].node->parent = ma_parent_ptr(mas_mn(mas)->parent); return true; } /* * spanning_ascend() - See if a spanning store operation has to keep walking up * the tree * @cp: The maple_copy node * @l_wr_mas: The left maple write state * @r_wr_mas: The right maple write state * @sib: the maple state of the sibling * * Returns: True if another iteration is necessary. */ static bool spanning_ascend(struct maple_copy *cp, struct ma_state *mas, struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas, struct ma_state *sib) { if (sib->end) { if (sib->max < l_wr_mas->mas->min) *l_wr_mas->mas = *sib; else *r_wr_mas->mas = *sib; } cp_dst_to_slots(cp, l_wr_mas->mas->min, r_wr_mas->mas->max, mas); if (cp_is_new_root(cp, mas)) return false; /* Converged and has a single destination */ if ((cp->d_count == 1) && (l_wr_mas->mas->node == r_wr_mas->mas->node)) { cp->dst[0].node->parent = ma_parent_ptr(mas_mn(mas)->parent); return false; } cp->height++; wr_mas_ascend(l_wr_mas); wr_mas_ascend(r_wr_mas); return true; } static inline void copy_tree_location(const struct ma_state *src, struct ma_state *dst) { dst->node = src->node; dst->offset = src->offset; dst->min = src->min; dst->max = src->max; dst->end = src->end; dst->depth = src->depth; } /* * rebalance_ascend() - Ascend the tree and set up for the next loop - if * necessary * * Return: True if there another rebalancing operation on the next level is * needed, false otherwise. */ static inline bool rebalance_ascend(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { struct ma_state *mas; unsigned long min, max; mas = wr_mas->mas; if (!sib->end) { min = mas->min; max = mas->max; } else if (sib->min > mas->max) { /* Move right succeeded */ min = mas->min; max = sib->max; wr_mas->offset_end = parent->offset + 1; } else { min = sib->min; max = mas->max; wr_mas->offset_end = parent->offset; parent->offset--; } cp_dst_to_slots(cp, min, max, mas); if (cp_is_new_root(cp, mas)) return false; if (cp_converged(cp, mas, sib)) return false; cp->height++; copy_tree_location(parent, mas); wr_mas_setup(wr_mas, mas); return true; } /* * mas_root_expand() - Expand a root to a node * @mas: The maple state * @entry: The entry to store into the tree */ static inline void mas_root_expand(struct ma_state *mas, void *entry) { void *contents = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; int slot = 0; node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; if (mas->index) { if (contents) { rcu_assign_pointer(slots[slot], contents); if (likely(mas->index > 1)) slot++; } pivots[slot++] = mas->index - 1; } rcu_assign_pointer(slots[slot], entry); mas->offset = slot; pivots[slot] = mas->last; if (mas->last != ULONG_MAX) pivots[++slot] = ULONG_MAX; mt_set_height(mas->tree, 1); ma_set_meta(node, maple_leaf_64, 0, slot); /* swap the new root into the tree */ rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); } /* * mas_store_root() - Storing value into root. * @mas: The maple state * @entry: The entry to store. * * There is no root node now and we are storing a value into the root - this * function either assigns the pointer or expands into a node. */ static inline void mas_store_root(struct ma_state *mas, void *entry) { if (!entry) { if (!mas->index) rcu_assign_pointer(mas->tree->ma_root, NULL); } else if (likely((mas->last != 0) || (mas->index != 0))) mas_root_expand(mas, entry); else if (((unsigned long) (entry) & 3) == 2) mas_root_expand(mas, entry); else { rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; } } /* * mas_is_span_wr() - Check if the write needs to be treated as a write that * spans the node. * @wr_mas: The maple write state * * Spanning writes are writes that start in one node and end in another OR if * the write of a %NULL will cause the node to end with a %NULL. * * Return: True if this is a spanning write, false otherwise. */ static bool mas_is_span_wr(struct ma_wr_state *wr_mas) { unsigned long max = wr_mas->r_max; unsigned long last = wr_mas->mas->last; enum maple_type type = wr_mas->type; void *entry = wr_mas->entry; /* Contained in this pivot, fast path */ if (last < max) return false; if (ma_is_leaf(type)) { max = wr_mas->mas->max; if (last < max) return false; } if (last == max) { /* * The last entry of leaf node cannot be NULL unless it is the * rightmost node (writing ULONG_MAX), otherwise it spans slots. */ if (entry || last == ULONG_MAX) return false; } trace_ma_write(TP_FCT, wr_mas->mas, wr_mas->r_max, entry); return true; } static inline void mas_wr_walk_descend(struct ma_wr_state *wr_mas) { wr_mas->type = mte_node_type(wr_mas->mas->node); mas_wr_node_walk(wr_mas); wr_mas->slots = ma_slots(wr_mas->node, wr_mas->type); } static inline void mas_wr_walk_traverse(struct ma_wr_state *wr_mas) { wr_mas->mas->max = wr_mas->r_max; wr_mas->mas->min = wr_mas->r_min; wr_mas->mas->node = wr_mas->content; wr_mas->mas->offset = 0; wr_mas->mas->depth++; } /* * mas_wr_walk() - Walk the tree for a write. * @wr_mas: The maple write state * * Uses mas_slot_locked() and does not need to worry about dead nodes. * * Return: True if it's contained in a node, false on spanning write. */ static bool mas_wr_walk(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); if (unlikely(mas_is_span_wr(wr_mas))) return false; wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return true; if (mas->end < mt_slots[wr_mas->type] - 1) wr_mas->vacant_height = mas->depth + 1; if (ma_is_root(mas_mn(mas))) { /* root needs more than 2 entries to be sufficient + 1 */ if (mas->end > 2) wr_mas->sufficient_height = 1; } else if (mas->end > mt_min_slots[wr_mas->type] + 1) wr_mas->sufficient_height = mas->depth + 1; mas_wr_walk_traverse(wr_mas); } return true; } static void mas_wr_walk_index(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; while (true) { mas_wr_walk_descend(wr_mas); wr_mas->content = mas_slot_locked(mas, wr_mas->slots, mas->offset); if (ma_is_leaf(wr_mas->type)) return; mas_wr_walk_traverse(wr_mas); } } /* * mas_extend_spanning_null() - Extend a store of a %NULL to include surrounding %NULLs. * @l_wr_mas: The left maple write state * @r_wr_mas: The right maple write state */ static inline void mas_extend_spanning_null(struct ma_wr_state *l_wr_mas, struct ma_wr_state *r_wr_mas) { struct ma_state *r_mas = r_wr_mas->mas; struct ma_state *l_mas = l_wr_mas->mas; unsigned char l_slot; l_slot = l_mas->offset; if (!l_wr_mas->content) l_mas->index = l_wr_mas->r_min; if ((l_mas->index == l_wr_mas->r_min) && (l_slot && !mas_slot_locked(l_mas, l_wr_mas->slots, l_slot - 1))) { if (l_slot > 1) l_mas->index = l_wr_mas->pivots[l_slot - 2] + 1; else l_mas->index = l_mas->min; l_mas->offset = l_slot - 1; l_wr_mas->r_min = l_mas->index; } if (!r_wr_mas->content) { if (r_mas->last < r_wr_mas->r_max) r_mas->last = r_wr_mas->r_max; r_mas->offset++; } else if ((r_mas->last == r_wr_mas->r_max) && (r_mas->last < r_mas->max) && !mas_slot_locked(r_mas, r_wr_mas->slots, r_mas->offset + 1)) { r_mas->last = mas_safe_pivot(r_mas, r_wr_mas->pivots, r_wr_mas->type, r_mas->offset + 1); r_mas->offset++; r_wr_mas->r_max = r_mas->last; } } static inline void *mas_state_walk(struct ma_state *mas) { void *entry; entry = mas_start(mas); if (mas_is_none(mas)) return NULL; if (mas_is_ptr(mas)) return entry; return mtree_range_walk(mas); } /* * mtree_lookup_walk() - Internal quick lookup that does not keep maple state up * to date. * * @mas: The maple state. * * Note: Leaves mas in undesirable state. * Return: The entry for @mas->index or %NULL on dead node. */ static inline void *mtree_lookup_walk(struct ma_state *mas) { unsigned long *pivots; unsigned char offset; struct maple_node *node; struct maple_enode *next; enum maple_type type; void __rcu **slots; unsigned char end; next = mas->node; do { node = mte_to_node(next); type = mte_node_type(next); pivots = ma_pivots(node, type); end = mt_pivots[type]; offset = 0; do { if (pivots[offset] >= mas->index) break; } while (++offset < end); slots = ma_slots(node, type); next = mt_slot(mas->tree, slots, offset); if (unlikely(ma_dead_node(node))) goto dead_node; } while (!ma_is_leaf(type)); return (void *)next; dead_node: mas_reset(mas); return NULL; } static void mte_destroy_walk(struct maple_enode *, struct maple_tree *); /* * mas_new_root() - Create a new root node that only contains the entry passed * in. * @mas: The maple state * @entry: The entry to store. * * Only valid when the index == 0 and the last == ULONG_MAX */ static inline void mas_new_root(struct ma_state *mas, void *entry) { struct maple_enode *root = mas_root_locked(mas); enum maple_type type = maple_leaf_64; struct maple_node *node; void __rcu **slots; unsigned long *pivots; WARN_ON_ONCE(mas->index || mas->last != ULONG_MAX); if (!entry) { mt_set_height(mas->tree, 0); rcu_assign_pointer(mas->tree->ma_root, entry); mas->status = ma_start; goto done; } node = mas_pop_node(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); node->parent = ma_parent_ptr(mas_tree_parent(mas)); mas->node = mt_mk_node(node, type); mas->status = ma_active; rcu_assign_pointer(slots[0], entry); pivots[0] = mas->last; mt_set_height(mas->tree, 1); rcu_assign_pointer(mas->tree->ma_root, mte_mk_root(mas->node)); done: if (xa_is_node(root)) mte_destroy_walk(root, mas->tree); } /* * mas_wr_spanning_store() - Create a subtree with the store operation completed * and new nodes where necessary, then place the sub-tree in the actual tree. * Note that mas is expected to point to the node which caused the store to * span. * @wr_mas: The maple write state */ static void mas_wr_spanning_store(struct ma_wr_state *wr_mas) { struct maple_copy cp; struct ma_state *mas; struct ma_state sib; /* Left and Right side of spanning store */ MA_STATE(r_mas, NULL, 0, 0); MA_WR_STATE(r_wr_mas, &r_mas, wr_mas->entry); /* * A store operation that spans multiple nodes is called a spanning * store and is handled early in the store call stack by the function * mas_is_span_wr(). When a spanning store is identified, the maple * state is duplicated. The first maple state walks the left tree path * to ``index``, the duplicate walks the right tree path to ``last``. * The data in the two nodes are combined into a single node, two nodes, * or possibly three nodes (see the 3-way split above). A ``NULL`` * written to the last entry of a node is considered a spanning store as * a rebalance is required for the operation to complete and an overflow * of data may happen. */ mas = wr_mas->mas; trace_ma_op(TP_FCT, mas); if (unlikely(!mas->index && mas->last == ULONG_MAX)) return mas_new_root(mas, wr_mas->entry); /* * Node rebalancing may occur due to this store, so there may be three new * entries per level plus a new root. */ /* * Set up right side. Need to get to the next offset after the spanning * store to ensure it's not NULL and to combine both the next node and * the node with the start together. */ r_mas = *mas; /* Avoid overflow, walk to next slot in the tree. */ if (r_mas.last + 1) r_mas.last++; r_mas.index = r_mas.last; mas_wr_walk_index(&r_wr_mas); r_mas.last = r_mas.index = mas->last; r_wr_mas.end_piv = r_wr_mas.r_max; /* Set up left side. */ mas_wr_walk_index(wr_mas); if (!wr_mas->entry) { mas_extend_spanning_null(wr_mas, &r_wr_mas); mas->last = r_mas.last; } /* expanding NULLs may make this cover the entire range */ if (!mas->index && r_mas.last == ULONG_MAX) { mas_set_range(mas, 0, ULONG_MAX); return mas_new_root(mas, wr_mas->entry); } cp_leaf_init(&cp, mas, wr_mas, &r_wr_mas); do { spanning_data(&cp, wr_mas, &r_wr_mas, &sib); multi_src_setup(&cp, wr_mas, &r_wr_mas, &sib); dst_setup(&cp, mas, wr_mas->type); cp_data_write(&cp, mas); } while (spanning_ascend(&cp, mas, wr_mas, &r_wr_mas, &sib)); mas_wmb_replace(mas, &cp); } /* * mas_wr_node_store() - Attempt to store the value in a node * @wr_mas: The maple write state * * Attempts to reuse the node, but may allocate. */ static inline void mas_wr_node_store(struct ma_wr_state *wr_mas) { unsigned char dst_offset, offset_end; unsigned char copy_size, node_pivots; struct maple_node reuse, *newnode; unsigned long *dst_pivots; void __rcu **dst_slots; unsigned char new_end; struct ma_state *mas; bool in_rcu; mas = wr_mas->mas; trace_ma_op(TP_FCT, mas); in_rcu = mt_in_rcu(mas->tree); offset_end = wr_mas->offset_end; node_pivots = mt_pivots[wr_mas->type]; /* Assume last adds an entry */ new_end = mas->end + 1 - offset_end + mas->offset; if (mas->last == wr_mas->end_piv) { offset_end++; /* don't copy this offset */ new_end--; } /* set up node. */ if (in_rcu) { newnode = mas_pop_node(mas); } else { memset(&reuse, 0, sizeof(struct maple_node)); newnode = &reuse; } newnode->parent = mas_mn(mas)->parent; dst_pivots = ma_pivots(newnode, wr_mas->type); dst_slots = ma_slots(newnode, wr_mas->type); /* Copy from start to insert point */ if (mas->offset) { memcpy(dst_pivots, wr_mas->pivots, sizeof(unsigned long) * mas->offset); memcpy(dst_slots, wr_mas->slots, sizeof(void __rcu *) * mas->offset); } /* Handle insert of new range starting after old range */ if (wr_mas->r_min < mas->index) { rcu_assign_pointer(dst_slots[mas->offset], wr_mas->content); dst_pivots[mas->offset++] = mas->index - 1; new_end++; } /* Store the new entry and range end. */ if (mas->offset < node_pivots) dst_pivots[mas->offset] = mas->last; rcu_assign_pointer(dst_slots[mas->offset], wr_mas->entry); /* * this range wrote to the end of the node or it overwrote the rest of * the data */ if (offset_end > mas->end) goto done; dst_offset = mas->offset + 1; /* Copy to the end of node if necessary. */ copy_size = mas->end - offset_end + 1; memcpy(dst_slots + dst_offset, wr_mas->slots + offset_end, sizeof(void __rcu *) * copy_size); memcpy(dst_pivots + dst_offset, wr_mas->pivots + offset_end, sizeof(unsigned long) * (copy_size - 1)); if (new_end < node_pivots) dst_pivots[new_end] = mas->max; done: mas_leaf_set_meta(newnode, maple_leaf_64, new_end); if (in_rcu) { struct maple_enode *old_enode = mas->node; mas->node = mt_mk_node(newnode, wr_mas->type); mas_replace_node(mas, old_enode, mas_mt_height(mas)); } else { memcpy(wr_mas->node, newnode, sizeof(struct maple_node)); } trace_ma_write(TP_FCT, mas, 0, wr_mas->entry); mas_update_gap(mas); mas->end = new_end; } /* * mas_wr_slot_store: Attempt to store a value in a slot. * @wr_mas: the maple write state */ static inline void mas_wr_slot_store(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char offset = mas->offset; void __rcu **slots = wr_mas->slots; bool gap = false; gap |= !mt_slot_locked(mas->tree, slots, offset); gap |= !mt_slot_locked(mas->tree, slots, offset + 1); if (wr_mas->offset_end - offset == 1) { if (mas->index == wr_mas->r_min) { /* Overwriting the range and a part of the next one */ rcu_assign_pointer(slots[offset], wr_mas->entry); wr_mas->pivots[offset] = mas->last; } else { /* Overwriting a part of the range and the next one */ rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; mas->offset++; /* Keep mas accurate. */ } } else { WARN_ON_ONCE(mt_in_rcu(mas->tree)); /* * Expand the range, only partially overwriting the previous and * next ranges */ gap |= !mt_slot_locked(mas->tree, slots, offset + 2); rcu_assign_pointer(slots[offset + 1], wr_mas->entry); wr_mas->pivots[offset] = mas->index - 1; wr_mas->pivots[offset + 1] = mas->last; mas->offset++; /* Keep mas accurate. */ } trace_ma_write(TP_FCT, mas, 0, wr_mas->entry); /* * Only update gap when the new entry is empty or there is an empty * entry in the original two ranges. */ if (!wr_mas->entry || gap) mas_update_gap(mas); } static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!wr_mas->slots[wr_mas->offset_end]) { /* If this one is null, the next and prev are not */ mas->last = wr_mas->end_piv; } else { /* Check next slot(s) if we are overwriting the end */ if ((mas->last == wr_mas->end_piv) && (mas->end != wr_mas->offset_end) && !wr_mas->slots[wr_mas->offset_end + 1]) { wr_mas->offset_end++; if (wr_mas->offset_end == mas->end) mas->last = mas->max; else mas->last = wr_mas->pivots[wr_mas->offset_end]; wr_mas->end_piv = mas->last; } } if (!wr_mas->content) { /* If this one is null, the next and prev are not */ mas->index = wr_mas->r_min; } else { /* Check prev slot if we are overwriting the start */ if (mas->index == wr_mas->r_min && mas->offset && !wr_mas->slots[mas->offset - 1]) { mas->offset--; wr_mas->r_min = mas->index = mas_safe_min(mas, wr_mas->pivots, mas->offset); wr_mas->r_max = wr_mas->pivots[mas->offset]; } } } static inline void mas_wr_end_piv(struct ma_wr_state *wr_mas) { while ((wr_mas->offset_end < wr_mas->mas->end) && (wr_mas->mas->last > wr_mas->pivots[wr_mas->offset_end])) wr_mas->offset_end++; if (wr_mas->offset_end < wr_mas->mas->end) wr_mas->end_piv = wr_mas->pivots[wr_mas->offset_end]; else wr_mas->end_piv = wr_mas->mas->max; } static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end = mas->end + 2; new_end -= wr_mas->offset_end - mas->offset; if (wr_mas->r_min == mas->index) new_end--; if (wr_mas->end_piv == mas->last) new_end--; return new_end; } /* * mas_wr_append: Attempt to append * @wr_mas: the maple write state * * This is currently unsafe in rcu mode since the end of the node may be cached * by readers while the node contents may be updated which could result in * inaccurate information. */ static inline void mas_wr_append(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; void __rcu **slots; unsigned char end = mas->end; unsigned char new_end = mas_wr_new_end(wr_mas); if (new_end < mt_pivots[wr_mas->type]) { wr_mas->pivots[new_end] = wr_mas->pivots[end]; ma_set_meta(wr_mas->node, wr_mas->type, 0, new_end); } slots = wr_mas->slots; if (new_end == end + 1) { if (mas->last == wr_mas->r_max) { /* Append to end of range */ rcu_assign_pointer(slots[new_end], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = new_end; } else { /* Append to start of range */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end] = mas->last; rcu_assign_pointer(slots[end], wr_mas->entry); } } else { /* Append to the range without touching any boundaries. */ rcu_assign_pointer(slots[new_end], wr_mas->content); wr_mas->pivots[end + 1] = mas->last; rcu_assign_pointer(slots[end + 1], wr_mas->entry); wr_mas->pivots[end] = mas->index - 1; mas->offset = end + 1; } if (!wr_mas->content || !wr_mas->entry) mas_update_gap(mas); mas->end = new_end; trace_ma_write(TP_FCT, mas, new_end, wr_mas->entry); } /* * split_ascend() - See if a split operation has to keep walking up the tree * @cp: The maple_copy node * @wr_mas: The maple write state * @sib: the maple state of the sibling * * Return: true if another split operation on the next level is needed, false * otherwise */ static inline bool split_ascend(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { struct ma_state *mas; unsigned long min, max; mas = wr_mas->mas; min = mas->min; /* push right, or normal split */ max = mas->max; wr_mas->offset_end = parent->offset; if (sib->end) { if (sib->max < mas->min) { min = sib->min; /* push left */ parent->offset--; } else { max = sib->max; /* push right */ wr_mas->offset_end++; } } cp_dst_to_slots(cp, min, max, mas); if (cp_is_new_root(cp, mas)) return false; if (cp_converged(cp, mas, sib)) return false; cp->height++; copy_tree_location(parent, mas); wr_mas_setup(wr_mas, mas); return true; } /* * split_data() - Calculate the @cp data, populate @sib if the data can be * pushed into a sibling. * @cp: The maple copy node * @wr_mas: The left write maple state * @sib: The maple state of the sibling. * * Note: @cp->data is a size and not indexed by 0. @sib->end may be set to 0 to * indicate it will not be used. * */ static inline void split_data(struct maple_copy *cp, struct ma_wr_state *wr_mas, struct ma_state *sib, struct ma_state *parent) { cp_data_calc(cp, wr_mas, wr_mas); if (cp->data <= mt_slots[wr_mas->type]) { sib->end = 0; return; } push_data_sib(cp, wr_mas->mas, sib, parent); if (sib->end) cp->data += sib->end + 1; } /* * mas_wr_split() - Expand one node into two * @wr_mas: The write maple state */ static void mas_wr_split(struct ma_wr_state *wr_mas) { struct ma_state parent; struct ma_state *mas; struct maple_copy cp; struct ma_state sib; mas = wr_mas->mas; trace_ma_write(TP_FCT, wr_mas->mas, 0, wr_mas->entry); parent = *mas; cp_leaf_init(&cp, mas, wr_mas, wr_mas); do { if (!mte_is_root(parent.node)) { mas_ascend(&parent); parent.end = mas_data_end(&parent); } split_data(&cp, wr_mas, &sib, &parent); multi_src_setup(&cp, wr_mas, wr_mas, &sib); dst_setup(&cp, mas, wr_mas->type); cp_data_write(&cp, mas); } while (split_ascend(&cp, wr_mas, &sib, &parent)); mas_wmb_replace(mas, &cp); } /* * mas_wr_rebalance() - Insufficient data in one node needs to either get data * from a sibling or absorb a sibling all together. * @wr_mas: The write maple state * * Rebalance is different than a spanning store in that the write state is * already at the leaf node that's being altered. */ static void mas_wr_rebalance(struct ma_wr_state *wr_mas) { struct ma_state parent; struct ma_state *mas; struct maple_copy cp; struct ma_state sib; /* * Rebalancing occurs if a node is insufficient. Data is rebalanced * against the node to the right if it exists, otherwise the node to the * left of this node is rebalanced against this node. If rebalancing * causes just one node to be produced instead of two, then the parent * is also examined and rebalanced if it is insufficient. Every level * tries to combine the data in the same way. If one node contains the * entire range of the tree, then that node is used as a new root node. */ mas = wr_mas->mas; trace_ma_op(TP_FCT, mas); parent = *mas; cp_leaf_init(&cp, mas, wr_mas, wr_mas); do { if (!mte_is_root(parent.node)) { mas_ascend(&parent); parent.end = mas_data_end(&parent); } rebalance_data(&cp, wr_mas, &sib, &parent); multi_src_setup(&cp, wr_mas, wr_mas, &sib); dst_setup(&cp, mas, wr_mas->type); cp_data_write(&cp, mas); } while (rebalance_ascend(&cp, wr_mas, &sib, &parent)); mas_wmb_replace(mas, &cp); } /* * mas_wr_store_entry() - Internal call to store a value * @wr_mas: The maple write state */ static inline void mas_wr_store_entry(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; switch (mas->store_type) { case wr_exact_fit: rcu_assign_pointer(wr_mas->slots[mas->offset], wr_mas->entry); if (!!wr_mas->entry ^ !!wr_mas->content) mas_update_gap(mas); break; case wr_append: mas_wr_append(wr_mas); break; case wr_slot_store: mas_wr_slot_store(wr_mas); break; case wr_node_store: mas_wr_node_store(wr_mas); break; case wr_spanning_store: mas_wr_spanning_store(wr_mas); break; case wr_split_store: mas_wr_split(wr_mas); break; case wr_rebalance: mas_wr_rebalance(wr_mas); break; case wr_new_root: mas_new_root(mas, wr_mas->entry); break; case wr_store_root: mas_store_root(mas, wr_mas->entry); break; case wr_invalid: MT_BUG_ON(mas->tree, 1); } } static inline void mas_wr_prealloc_setup(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; if (!mas_is_active(mas)) { if (mas_is_start(mas)) goto set_content; if (unlikely(mas_is_paused(mas))) goto reset; if (unlikely(mas_is_none(mas))) goto reset; if (unlikely(mas_is_overflow(mas))) goto reset; if (unlikely(mas_is_underflow(mas))) goto reset; } /* * A less strict version of mas_is_span_wr() where we allow spanning * writes within this node. This is to stop partial walks in * mas_prealloc() from being reset. */ if (mas->last > mas->max) goto reset; if (wr_mas->entry) goto set_content; if (mte_is_leaf(mas->node) && mas->last == mas->max) goto reset; goto set_content; reset: mas_reset(mas); set_content: wr_mas->content = mas_start(mas); } /** * mas_prealloc_calc() - Calculate number of nodes needed for a * given store oepration * @wr_mas: The maple write state * @entry: The entry to store into the tree * * Return: Number of nodes required for preallocation. */ static inline void mas_prealloc_calc(struct ma_wr_state *wr_mas, void *entry) { struct ma_state *mas = wr_mas->mas; unsigned char height = mas_mt_height(mas); int ret = height * 3 + 1; unsigned char delta = height - wr_mas->vacant_height; switch (mas->store_type) { case wr_exact_fit: case wr_append: case wr_slot_store: ret = 0; break; case wr_spanning_store: if (wr_mas->sufficient_height < wr_mas->vacant_height) ret = (height - wr_mas->sufficient_height) * 3 + 1; else ret = delta * 3 + 1; break; case wr_split_store: ret = delta * 2 + 1; break; case wr_rebalance: if (wr_mas->sufficient_height < wr_mas->vacant_height) ret = (height - wr_mas->sufficient_height) * 2 + 1; else ret = delta * 2 + 1; break; case wr_node_store: ret = mt_in_rcu(mas->tree) ? 1 : 0; break; case wr_new_root: ret = 1; break; case wr_store_root: if (likely((mas->last != 0) || (mas->index != 0))) ret = 1; else if (((unsigned long) (entry) & 3) == 2) ret = 1; else ret = 0; break; case wr_invalid: WARN_ON_ONCE(1); } mas->node_request = ret; } /* * mas_wr_store_type() - Determine the store type for a given * store operation. * @wr_mas: The maple write state * * Return: the type of store needed for the operation */ static inline enum store_type mas_wr_store_type(struct ma_wr_state *wr_mas) { struct ma_state *mas = wr_mas->mas; unsigned char new_end; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return wr_store_root; if (unlikely(!mas_wr_walk(wr_mas))) return wr_spanning_store; /* At this point, we are at the leaf node that needs to be altered. */ mas_wr_end_piv(wr_mas); if (!wr_mas->entry) mas_wr_extend_null(wr_mas); if ((wr_mas->r_min == mas->index) && (wr_mas->r_max == mas->last)) return wr_exact_fit; if (unlikely(!mas->index && mas->last == ULONG_MAX)) return wr_new_root; new_end = mas_wr_new_end(wr_mas); /* Potential spanning rebalance collapsing a node */ if (new_end < mt_min_slots[wr_mas->type]) { if (!mte_is_root(mas->node)) return wr_rebalance; return wr_node_store; } if (new_end >= mt_slots[wr_mas->type]) return wr_split_store; if (!mt_in_rcu(mas->tree) && (mas->offset == mas->end)) return wr_append; if ((new_end == mas->end) && (!mt_in_rcu(mas->tree) || (wr_mas->offset_end - mas->offset == 1))) return wr_slot_store; return wr_node_store; } /** * mas_wr_preallocate() - Preallocate enough nodes for a store operation * @wr_mas: The maple write state * @entry: The entry that will be stored * */ static inline void mas_wr_preallocate(struct ma_wr_state *wr_mas, void *entry) { struct ma_state *mas = wr_mas->mas; mas_wr_prealloc_setup(wr_mas); mas->store_type = mas_wr_store_type(wr_mas); mas_prealloc_calc(wr_mas, entry); if (!mas->node_request) return; mas_alloc_nodes(mas, GFP_NOWAIT); } /** * mas_insert() - Internal call to insert a value * @mas: The maple state * @entry: The entry to store * * Return: %NULL or the contents that already exists at the requested index * otherwise. The maple state needs to be checked for error conditions. */ static inline void *mas_insert(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); /* * Inserting a new range inserts either 0, 1, or 2 pivots within the * tree. If the insert fits exactly into an existing gap with a value * of NULL, then the slot only needs to be written with the new value. * If the range being inserted is adjacent to another range, then only a * single pivot needs to be inserted (as well as writing the entry). If * the new range is within a gap but does not touch any other ranges, * then two pivots need to be inserted: the start - 1, and the end. As * usual, the entry must be written. Most operations require a new node * to be allocated and replace an existing node to ensure RCU safety, * when in RCU mode. The exception to requiring a newly allocated node * is when inserting at the end of a node (appending). When done * carefully, appending can reuse the node in place. */ wr_mas.content = mas_start(mas); if (wr_mas.content) goto exists; mas_wr_preallocate(&wr_mas, entry); if (mas_is_err(mas)) return NULL; /* spanning writes always overwrite something */ if (mas->store_type == wr_spanning_store) goto exists; /* At this point, we are at the leaf node that needs to be altered. */ if (mas->store_type != wr_new_root && mas->store_type != wr_store_root) { wr_mas.offset_end = mas->offset; wr_mas.end_piv = wr_mas.r_max; if (wr_mas.content || (mas->last > wr_mas.r_max)) goto exists; } mas_wr_store_entry(&wr_mas); return wr_mas.content; exists: mas_set_err(mas, -EEXIST); return wr_mas.content; } /** * mas_alloc_cyclic() - Internal call to find somewhere to store an entry * @mas: The maple state. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, or -EBUSY if there are no * free entries. */ int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { unsigned long min = range_lo; int ret = 0; range_lo = max(min, *next); ret = mas_empty_area(mas, range_lo, range_hi, 1); if ((mas->tree->ma_flags & MT_FLAGS_ALLOC_WRAPPED) && ret == 0) { mas->tree->ma_flags &= ~MT_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && range_lo > min) { mas_reset(mas); ret = mas_empty_area(mas, min, range_hi, 1); if (ret == 0) ret = 1; } if (ret < 0) return ret; do { mas_insert(mas, entry); } while (mas_nomem(mas, gfp)); if (mas_is_err(mas)) return xa_err(mas->node); *startp = mas->index; *next = *startp + 1; if (*next == 0) mas->tree->ma_flags |= MT_FLAGS_ALLOC_WRAPPED; mas_destroy(mas); return ret; } EXPORT_SYMBOL(mas_alloc_cyclic); static __always_inline void mas_rewalk(struct ma_state *mas, unsigned long index) { retry: mas_set(mas, index); mas_state_walk(mas); if (mas_is_start(mas)) goto retry; } static __always_inline bool mas_rewalk_if_dead(struct ma_state *mas, struct maple_node *node, const unsigned long index) { if (unlikely(ma_dead_node(node))) { mas_rewalk(mas, index); return true; } return false; } /* * mas_prev_node() - Find the prev non-null entry at the same level in the * tree. The prev value will be mas->node[mas->offset] or the status will be * ma_none. * @mas: The maple state * @min: The lower limit to search * * The prev node value will be mas->node[mas->offset] or the status will be * ma_none. * Return: 1 if the node is dead, 0 otherwise. */ static int mas_prev_node(struct ma_state *mas, unsigned long min) { enum maple_type mt; int offset, level; void __rcu **slots; struct maple_node *node; unsigned long *pivots; unsigned long max; node = mas_mn(mas); if (!mas->min) goto no_entry; max = mas->min - 1; if (max < min) goto no_entry; level = 0; do { if (ma_is_root(node)) goto no_entry; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; offset = mas->offset; level++; node = mas_mn(mas); } while (!offset); offset--; mt = mte_node_type(mas->node); while (level > 1) { level--; slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); if (unlikely(ma_dead_node(node))) return 1; mt = mte_node_type(mas->node); node = mas_mn(mas); pivots = ma_pivots(node, mt); offset = ma_data_end(node, mt, pivots, max); if (unlikely(ma_dead_node(node))) return 1; } slots = ma_slots(node, mt); mas->node = mas_slot(mas, slots, offset); pivots = ma_pivots(node, mt); if (unlikely(ma_dead_node(node))) return 1; if (likely(offset)) mas->min = pivots[offset - 1] + 1; mas->max = max; mas->offset = mas_data_end(mas); if (unlikely(mte_dead_node(mas->node))) return 1; mas->end = mas->offset; return 0; no_entry: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_underflow; return 0; } /* * mas_prev_slot() - Get the entry in the previous slot * * @mas: The maple state * @min: The minimum starting range * @empty: Can be empty * * Return: The entry in the previous slot which is possibly NULL */ static void *mas_prev_slot(struct ma_state *mas, unsigned long min, bool empty) { void *entry; void __rcu **slots; unsigned long pivot; enum maple_type type; unsigned long *pivots; struct maple_node *node; unsigned long save_point = mas->index; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->min <= min) { pivot = mas_safe_min(mas, pivots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot <= min) goto underflow; } again: if (likely(mas->offset)) { mas->offset--; mas->last = mas->index - 1; mas->index = mas_safe_min(mas, pivots, mas->offset); } else { if (mas->index <= min) goto underflow; if (mas_prev_node(mas, min)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_underflow(mas))) return NULL; mas->last = mas->max; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->index = pivots[mas->offset - 1] + 1; } slots = ma_slots(node, type); entry = mas_slot(mas, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (likely(entry)) return entry; if (!empty) { if (mas->index <= min) goto underflow; goto again; } return entry; underflow: mas->status = ma_underflow; return NULL; } /* * mas_next_node() - Get the next node at the same level in the tree. * @mas: The maple state * @node: The maple node * @max: The maximum pivot value to check. * * The next value will be mas->node[mas->offset] or the status will have * overflowed. * Return: 1 on dead node, 0 otherwise. */ static int mas_next_node(struct ma_state *mas, struct maple_node *node, unsigned long max) { unsigned long min; unsigned long *pivots; struct maple_enode *enode; struct maple_node *tmp; int level = 0; unsigned char node_end; enum maple_type mt; void __rcu **slots; if (mas->max >= max) goto overflow; min = mas->max + 1; level = 0; do { if (ma_is_root(node)) goto overflow; /* Walk up. */ if (unlikely(mas_ascend(mas))) return 1; level++; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); node_end = ma_data_end(node, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; } while (unlikely(mas->offset == node_end)); slots = ma_slots(node, mt); mas->offset++; enode = mas_slot(mas, slots, mas->offset); if (unlikely(ma_dead_node(node))) return 1; if (level > 1) mas->offset = 0; while (unlikely(level > 1)) { level--; mas->node = enode; node = mas_mn(mas); mt = mte_node_type(mas->node); slots = ma_slots(node, mt); enode = mas_slot(mas, slots, 0); if (unlikely(ma_dead_node(node))) return 1; } if (!mas->offset) pivots = ma_pivots(node, mt); mas->max = mas_safe_pivot(mas, pivots, mas->offset, mt); tmp = mte_to_node(enode); mt = mte_node_type(enode); pivots = ma_pivots(tmp, mt); mas->end = ma_data_end(tmp, mt, pivots, mas->max); if (unlikely(ma_dead_node(node))) return 1; mas->node = enode; mas->min = min; return 0; overflow: if (unlikely(ma_dead_node(node))) return 1; mas->status = ma_overflow; return 0; } /* * mas_next_slot() - Get the entry in the next slot * * @mas: The maple state * @max: The maximum starting range * @empty: Can be empty * * Return: The entry in the next slot which is possibly NULL */ static void *mas_next_slot(struct ma_state *mas, unsigned long max, bool empty) { void __rcu **slots; unsigned long *pivots; unsigned long pivot; enum maple_type type; struct maple_node *node; unsigned long save_point = mas->last; void *entry; retry: node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (mas->max >= max) { if (likely(mas->offset < mas->end)) pivot = pivots[mas->offset]; else pivot = mas->max; if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (pivot >= max) { /* Was at the limit, next will extend beyond */ mas->status = ma_overflow; return NULL; } } if (likely(mas->offset < mas->end)) { mas->index = pivots[mas->offset] + 1; again: mas->offset++; if (likely(mas->offset < mas->end)) mas->last = pivots[mas->offset]; else mas->last = mas->max; } else { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } if (mas_next_node(mas, node, max)) { mas_rewalk(mas, save_point); goto retry; } if (WARN_ON_ONCE(mas_is_overflow(mas))) return NULL; mas->offset = 0; mas->index = mas->min; node = mas_mn(mas); type = mte_node_type(mas->node); pivots = ma_pivots(node, type); mas->last = pivots[0]; } slots = ma_slots(node, type); entry = mt_slot(mas->tree, slots, mas->offset); if (unlikely(mas_rewalk_if_dead(mas, node, save_point))) goto retry; if (entry) return entry; if (!empty) { if (mas->last >= max) { mas->status = ma_overflow; return NULL; } mas->index = mas->last + 1; goto again; } return entry; } /* * mas_rev_awalk() - Internal function. Reverse allocation walk. Find the * highest gap address of a given size in a given node and descend. * @mas: The maple state * @size: The needed size. * * Return: True if found in a leaf, false otherwise. * */ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size, unsigned long *gap_min, unsigned long *gap_max) { enum maple_type type = mte_node_type(mas->node); struct maple_node *node = mas_mn(mas); unsigned long *pivots, *gaps; void __rcu **slots; unsigned long gap = 0; unsigned long max, min; unsigned char offset; if (unlikely(mas_is_err(mas))) return true; if (ma_is_dense(type)) { /* dense nodes. */ mas->offset = (unsigned char)(mas->index - mas->min); return true; } pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); /* Skip out of bounds. */ while (mas->last < min) min = mas_safe_min(mas, pivots, --offset); max = mas_safe_pivot(mas, pivots, offset, type); while (mas->index <= max) { gap = 0; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = max - min + 1; if (gap) { if ((size <= gap) && (size <= mas->last - min + 1)) break; if (!gaps) { /* Skip the next slot, it cannot be a gap. */ if (offset < 2) goto ascend; offset -= 2; max = pivots[offset]; min = mas_safe_min(mas, pivots, offset); continue; } } if (!offset) goto ascend; offset--; max = min - 1; min = mas_safe_min(mas, pivots, offset); } if (unlikely((mas->index > max) || (size - 1 > max - mas->index))) goto no_space; if (unlikely(ma_is_leaf(type))) { mas->offset = offset; *gap_min = min; *gap_max = min + gap - 1; return true; } /* descend, only happens under lock. */ mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = max; mas->offset = mas_data_end(mas); return false; ascend: if (!mte_is_root(mas->node)) return false; no_space: mas_set_err(mas, -EBUSY); return false; } static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size) { enum maple_type type = mte_node_type(mas->node); unsigned long pivot, min, gap = 0; unsigned char offset, data_end; unsigned long *gaps, *pivots; void __rcu **slots; struct maple_node *node; bool found = false; if (ma_is_dense(type)) { mas->offset = (unsigned char)(mas->index - mas->min); return true; } node = mas_mn(mas); pivots = ma_pivots(node, type); slots = ma_slots(node, type); gaps = ma_gaps(node, type); offset = mas->offset; min = mas_safe_min(mas, pivots, offset); data_end = ma_data_end(node, type, pivots, mas->max); for (; offset <= data_end; offset++) { pivot = mas_safe_pivot(mas, pivots, offset, type); /* Not within lower bounds */ if (mas->index > pivot) goto next_slot; if (gaps) gap = gaps[offset]; else if (!mas_slot(mas, slots, offset)) gap = min(pivot, mas->last) - max(mas->index, min) + 1; else goto next_slot; if (gap >= size) { if (ma_is_leaf(type)) { found = true; break; } mas->node = mas_slot(mas, slots, offset); mas->min = min; mas->max = pivot; offset = 0; break; } next_slot: min = pivot + 1; if (mas->last <= pivot) { mas_set_err(mas, -EBUSY); return true; } } mas->offset = offset; return found; } /** * mas_walk() - Search for @mas->index in the tree. * @mas: The maple state. * * mas->index and mas->last will be set to the range if there is a value. If * mas->status is ma_none, reset to ma_start * * Return: the entry at the location or %NULL. */ void *mas_walk(struct ma_state *mas) { void *entry; if (!mas_is_active(mas) && !mas_is_start(mas)) mas->status = ma_start; retry: entry = mas_state_walk(mas); if (mas_is_start(mas)) { goto retry; } else if (mas_is_none(mas)) { mas->index = 0; mas->last = ULONG_MAX; } else if (mas_is_ptr(mas)) { if (!mas->index) { mas->last = 0; return entry; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return NULL; } return entry; } EXPORT_SYMBOL_GPL(mas_walk); static inline bool mas_rewind_node(struct ma_state *mas) { unsigned char slot; do { if (mte_is_root(mas->node)) { slot = mas->offset; if (!slot) return false; } else { mas_ascend(mas); slot = mas->offset; } } while (!slot); mas->offset = --slot; return true; } /* * mas_skip_node() - Internal function. Skip over a node. * @mas: The maple state. * * Return: true if there is another node, false otherwise. */ static inline bool mas_skip_node(struct ma_state *mas) { if (mas_is_err(mas)) return false; do { if (mte_is_root(mas->node)) { if (mas->offset >= mas_data_end(mas)) { mas_set_err(mas, -EBUSY); return false; } } else { mas_ascend(mas); } } while (mas->offset >= mas_data_end(mas)); mas->offset++; return true; } /* * mas_awalk() - Allocation walk. Search from low address to high, for a gap of * @size * @mas: The maple state * @size: The size of the gap required * * Search between @mas->index and @mas->last for a gap of @size. */ static inline void mas_awalk(struct ma_state *mas, unsigned long size) { struct maple_enode *last = NULL; /* * There are 4 options: * go to child (descend) * go back to parent (ascend) * no gap found. (return, error == -EBUSY) * found the gap. (return) */ while (!mas_is_err(mas) && !mas_anode_descend(mas, size)) { if (last == mas->node) mas_skip_node(mas); else last = mas->node; } } /* * mas_sparse_area() - Internal function. Return upper or lower limit when * searching for a gap in an empty tree. * @mas: The maple state * @min: the minimum range * @max: The maximum range * @size: The size of the gap * @fwd: Searching forward or back */ static inline int mas_sparse_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size, bool fwd) { if (!unlikely(mas_is_none(mas)) && min == 0) { min++; /* * At this time, min is increased, we need to recheck whether * the size is satisfied. */ if (min > max || max - min + 1 < size) return -EBUSY; } /* mas_is_ptr */ if (fwd) { mas->index = min; mas->last = min + size - 1; } else { mas->last = max; mas->index = max - size + 1; } return 0; } /* * mas_empty_area() - Get the lowest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { unsigned char offset; unsigned long *pivots; enum maple_type mt; struct maple_node *node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if (mas->offset >= 2) mas->offset -= 2; else if (!mas_skip_node(mas)) return -EBUSY; /* Empty set */ if (mas_is_none(mas) || mas_is_ptr(mas)) return mas_sparse_area(mas, min, max, size, true); /* The start of the window can only be within these values */ mas->index = min; mas->last = max; mas_awalk(mas, size); if (unlikely(mas_is_err(mas))) return xa_err(mas->node); offset = mas->offset; node = mas_mn(mas); mt = mte_node_type(mas->node); pivots = ma_pivots(node, mt); min = mas_safe_min(mas, pivots, offset); if (mas->index < min) mas->index = min; mas->last = mas->index + size - 1; mas->end = ma_data_end(node, mt, pivots, mas->max); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area); /* * mas_empty_area_rev() - Get the highest address within the range that is * sufficient for the size requested. * @mas: The maple state * @min: The lowest value of the range * @max: The highest value of the range * @size: The size needed */ int mas_empty_area_rev(struct ma_state *mas, unsigned long min, unsigned long max, unsigned long size) { struct maple_enode *last = mas->node; if (min > max) return -EINVAL; if (size == 0 || max - min < size - 1) return -EINVAL; if (mas_is_start(mas)) mas_start(mas); else if ((mas->offset < 2) && (!mas_rewind_node(mas))) return -EBUSY; if (unlikely(mas_is_none(mas) || mas_is_ptr(mas))) return mas_sparse_area(mas, min, max, size, false); else if (mas->offset >= 2) mas->offset -= 2; else mas->offset = mas_data_end(mas); /* The start of the window can only be within these values. */ mas->index = min; mas->last = max; while (!mas_rev_awalk(mas, size, &min, &max)) { if (last == mas->node) { if (!mas_rewind_node(mas)) return -EBUSY; } else { last = mas->node; } } if (mas_is_err(mas)) return xa_err(mas->node); if (unlikely(mas->offset == MAPLE_NODE_SLOTS)) return -EBUSY; /* Trim the upper limit to the max. */ if (max < mas->last) mas->last = max; mas->index = mas->last - size + 1; mas->end = mas_data_end(mas); return 0; } EXPORT_SYMBOL_GPL(mas_empty_area_rev); /* * mte_dead_leaves() - Mark all leaves of a node as dead. * @enode: the encoded node * @mt: the maple tree * @slots: Pointer to the slot array * * Must hold the write lock. * * Return: The number of leaves marked as dead. */ static inline unsigned char mte_dead_leaves(struct maple_enode *enode, struct maple_tree *mt, void __rcu **slots) { struct maple_node *node; enum maple_type type; void *entry; int offset; for (offset = 0; offset < mt_slot_count(enode); offset++) { entry = mt_slot(mt, slots, offset); type = mte_node_type(entry); node = mte_to_node(entry); /* Use both node and type to catch LE & BE metadata */ if (!node || !type) break; mte_set_node_dead(entry); node->type = type; rcu_assign_pointer(slots[offset], node); } return offset; } /** * mte_dead_walk() - Walk down a dead tree to just before the leaves * @enode: The maple encoded node * @offset: The starting offset * * Note: This can only be used from the RCU callback context. */ static void __rcu **mte_dead_walk(struct maple_enode **enode, unsigned char offset) { struct maple_node *node, *next; void __rcu **slots = NULL; next = mte_to_node(*enode); do { *enode = ma_enode_ptr(next); node = mte_to_node(*enode); slots = ma_slots(node, node->type); next = rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map)); offset = 0; } while (!ma_is_leaf(next->type)); return slots; } /** * mt_free_walk() - Walk & free a tree in the RCU callback context * @head: The RCU head that's within the node. * * Note: This can only be used from the RCU callback context. */ static void mt_free_walk(struct rcu_head *head) { void __rcu **slots; struct maple_node *node, *start; struct maple_enode *enode; unsigned char offset; enum maple_type type; node = container_of(head, struct maple_node, rcu); if (ma_is_leaf(node->type)) goto free_leaf; start = node; enode = mt_mk_node(node, node->type); slots = mte_dead_walk(&enode, 0); node = mte_to_node(enode); do { mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if ((offset < mt_slots[type]) && rcu_dereference_protected(slots[offset], lock_is_held(&rcu_callback_map))) slots = mte_dead_walk(&enode, offset); node = mte_to_node(enode); } while ((node != start) || (node->slot_len < offset)); slots = ma_slots(node, node->type); mt_free_bulk(node->slot_len, slots); free_leaf: kfree(node); } static inline void __rcu **mte_destroy_descend(struct maple_enode **enode, struct maple_tree *mt, struct maple_enode *prev, unsigned char offset) { struct maple_node *node; struct maple_enode *next = *enode; void __rcu **slots = NULL; enum maple_type type; unsigned char next_offset = 0; do { *enode = next; node = mte_to_node(*enode); type = mte_node_type(*enode); slots = ma_slots(node, type); next = mt_slot_locked(mt, slots, next_offset); if ((mte_dead_node(next))) next = mt_slot_locked(mt, slots, ++next_offset); mte_set_node_dead(*enode); node->type = type; node->piv_parent = prev; node->parent_slot = offset; offset = next_offset; next_offset = 0; prev = *enode; } while (!mte_is_leaf(next)); return slots; } static void mt_destroy_walk(struct maple_enode *enode, struct maple_tree *mt, bool free) { void __rcu **slots; struct maple_node *node = mte_to_node(enode); struct maple_enode *start; if (mte_is_leaf(enode)) { mte_set_node_dead(enode); node->type = mte_node_type(enode); goto free_leaf; } start = enode; slots = mte_destroy_descend(&enode, mt, start, 0); node = mte_to_node(enode); // Updated in the above call. do { enum maple_type type; unsigned char offset; struct maple_enode *parent, *tmp; node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); offset = node->parent_slot + 1; enode = node->piv_parent; if (mte_to_node(enode) == node) goto free_leaf; type = mte_node_type(enode); slots = ma_slots(mte_to_node(enode), type); if (offset >= mt_slots[type]) goto next; tmp = mt_slot_locked(mt, slots, offset); if (mte_node_type(tmp) && mte_to_node(tmp)) { parent = enode; enode = tmp; slots = mte_destroy_descend(&enode, mt, parent, offset); } next: node = mte_to_node(enode); } while (start != enode); node = mte_to_node(enode); node->slot_len = mte_dead_leaves(enode, mt, slots); if (free) mt_free_bulk(node->slot_len, slots); free_leaf: if (free) kfree(node); else mt_clear_meta(mt, node, node->type); } /* * mte_destroy_walk() - Free a tree or sub-tree. * @enode: the encoded maple node (maple_enode) to start * @mt: the tree to free - needed for node types. * * Must hold the write lock. */ static inline void mte_destroy_walk(struct maple_enode *enode, struct maple_tree *mt) { struct maple_node *node = mte_to_node(enode); if (mt_in_rcu(mt)) { mt_destroy_walk(enode, mt, false); call_rcu(&node->rcu, mt_free_walk); } else { mt_destroy_walk(enode, mt, true); } } /* Interface */ /** * mas_store() - Store an @entry. * @mas: The maple state. * @entry: The entry to store. * * The @mas->index and @mas->last is used to set the range for the @entry. * * Return: the first entry between mas->index and mas->last or %NULL. */ void *mas_store(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); trace_ma_write(TP_FCT, mas, 0, entry); #ifdef CONFIG_DEBUG_MAPLE_TREE if (MAS_WARN_ON(mas, mas->index > mas->last)) pr_err("Error %lX > %lX " PTR_FMT "\n", mas->index, mas->last, entry); if (mas->index > mas->last) { mas_set_err(mas, -EINVAL); return NULL; } #endif /* * Storing is the same operation as insert with the added caveat that it * can overwrite entries. Although this seems simple enough, one may * want to examine what happens if a single store operation was to * overwrite multiple entries within a self-balancing B-Tree. */ mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); if (mas->mas_flags & MA_STATE_PREALLOC) { mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); return wr_mas.content; } mas_prealloc_calc(&wr_mas, entry); if (!mas->node_request) goto store; mas_alloc_nodes(mas, GFP_NOWAIT); if (mas_is_err(mas)) return NULL; store: mas_wr_store_entry(&wr_mas); mas_destroy(mas); return wr_mas.content; } EXPORT_SYMBOL_GPL(mas_store); /** * mas_store_gfp() - Store a value into the tree. * @mas: The maple state * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations if necessary. * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mas_store_gfp(struct ma_state *mas, void *entry, gfp_t gfp) { unsigned long index = mas->index; unsigned long last = mas->last; MA_WR_STATE(wr_mas, mas, entry); int ret = 0; retry: mas_wr_preallocate(&wr_mas, entry); if (unlikely(mas_nomem(mas, gfp))) { if (!entry) __mas_set_range(mas, index, last); goto retry; } if (mas_is_err(mas)) { ret = xa_err(mas->node); goto out; } mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return ret; } EXPORT_SYMBOL_GPL(mas_store_gfp); /** * mas_store_prealloc() - Store a value into the tree using memory * preallocated in the maple state. * @mas: The maple state * @entry: The entry to store. */ void mas_store_prealloc(struct ma_state *mas, void *entry) { MA_WR_STATE(wr_mas, mas, entry); if (mas->store_type == wr_store_root) { mas_wr_prealloc_setup(&wr_mas); goto store; } mas_wr_walk_descend(&wr_mas); if (mas->store_type != wr_spanning_store) { /* set wr_mas->content to current slot */ wr_mas.content = mas_slot_locked(mas, wr_mas.slots, mas->offset); mas_wr_end_piv(&wr_mas); } store: trace_ma_write(TP_FCT, mas, 0, entry); mas_wr_store_entry(&wr_mas); MAS_WR_BUG_ON(&wr_mas, mas_is_err(mas)); mas_destroy(mas); } EXPORT_SYMBOL_GPL(mas_store_prealloc); /** * mas_preallocate() - Preallocate enough nodes for a store operation * @mas: The maple state * @entry: The entry that will be stored * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -ENOMEM if memory could not be allocated. */ int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp) { MA_WR_STATE(wr_mas, mas, entry); mas_wr_prealloc_setup(&wr_mas); mas->store_type = mas_wr_store_type(&wr_mas); mas_prealloc_calc(&wr_mas, entry); if (!mas->node_request) goto set_flag; mas->mas_flags &= ~MA_STATE_PREALLOC; mas_alloc_nodes(mas, gfp); if (mas_is_err(mas)) { int ret = xa_err(mas->node); mas->node_request = 0; mas_destroy(mas); mas_reset(mas); return ret; } set_flag: mas->mas_flags |= MA_STATE_PREALLOC; return 0; } EXPORT_SYMBOL_GPL(mas_preallocate); /* * mas_destroy() - destroy a maple state. * @mas: The maple state * * Upon completion, check the left-most node and rebalance against the node to * the right if necessary. Frees any allocated nodes associated with this maple * state. */ void mas_destroy(struct ma_state *mas) { mas->mas_flags &= ~MA_STATE_PREALLOC; mas_empty_nodes(mas); } EXPORT_SYMBOL_GPL(mas_destroy); static void mas_may_activate(struct ma_state *mas) { if (!mas->node) { mas->status = ma_start; } else if (mas->index > mas->max || mas->index < mas->min) { mas->status = ma_start; } else { mas->status = ma_active; } } static bool mas_next_setup(struct ma_state *mas, unsigned long max, void **entry) { bool was_none = mas_is_none(mas); if (unlikely(mas->last >= max)) { mas->status = ma_overflow; return true; } switch (mas->status) { case ma_active: return false; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; fallthrough; case ma_start: mas_walk(mas); /* Retries on dead nodes handled by mas_walk */ break; case ma_overflow: /* Overflowed before, but the max changed */ mas_may_activate(mas); break; case ma_underflow: /* The user expects the mas to be one before where it is */ mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (likely(mas_is_active(mas))) /* Fast path */ return false; if (mas_is_ptr(mas)) { *entry = NULL; if (was_none && mas->index == 0) { mas->index = mas->last = 0; return true; } mas->index = 1; mas->last = ULONG_MAX; mas->status = ma_none; return true; } if (mas_is_none(mas)) return true; return false; } /** * mas_next() - Get the next entry. * @mas: The maple state * @max: The maximum index to check. * * Returns the next entry after @mas->index. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, false); } EXPORT_SYMBOL_GPL(mas_next); /** * mas_next_range() - Advance the maple state to the next range * @mas: The maple state * @max: The maximum index to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Can return the zero entry. * * Return: The next entry or %NULL */ void *mas_next_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_next_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_next_range); /** * mt_next() - get the next value in the maple tree * @mt: The maple tree * @index: The start index * @max: The maximum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry higher than @index or %NULL if nothing is found. */ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_next(&mas, max); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_next); static bool mas_prev_setup(struct ma_state *mas, unsigned long min, void **entry) { if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } switch (mas->status) { case ma_active: return false; case ma_start: break; case ma_none: fallthrough; case ma_pause: mas->status = ma_start; break; case ma_underflow: /* underflowed before but the min changed */ mas_may_activate(mas); break; case ma_overflow: /* User expects mas to be one after where it is */ mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) mas_walk(mas); if (unlikely(mas_is_ptr(mas))) { if (!mas->index) { mas->status = ma_none; return true; } mas->index = mas->last = 0; *entry = mas_root(mas); return true; } if (mas_is_none(mas)) { if (mas->index) { /* Walked to out-of-range pointer? */ mas->index = mas->last = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } return true; } return false; } /** * mas_prev() - Get the previous entry * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the status is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_prev); /** * mas_prev_range() - Advance to the previous range * @mas: The maple state * @min: The minimum value to check. * * Sets @mas->index and @mas->last to the range. * Must hold rcu_read_lock or the write lock. * Will reset mas to ma_start if the node is ma_none. Will stop on not * searchable nodes. * * Return: the previous value or %NULL. */ void *mas_prev_range(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_prev_setup(mas, min, &entry)) return entry; return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_prev_range); /** * mt_prev() - get the previous value in the maple tree * @mt: The maple tree * @index: The start index * @min: The minimum index to check * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * Return: The entry before @index or %NULL if nothing is found. */ void *mt_prev(struct maple_tree *mt, unsigned long index, unsigned long min) { void *entry = NULL; MA_STATE(mas, mt, index, index); rcu_read_lock(); entry = mas_prev(&mas, min); rcu_read_unlock(); return entry; } EXPORT_SYMBOL_GPL(mt_prev); /** * mas_pause() - Pause a mas_find/mas_for_each to drop the lock. * @mas: The maple state to pause * * Some users need to pause a walk and drop the lock they're holding in * order to yield to a higher priority thread or carry out an operation * on an entry. Those users should call this function before they drop * the lock. It resets the @mas to be suitable for the next iteration * of the loop after the user has reacquired the lock. If most entries * found during a walk require you to call mas_pause(), the mt_for_each() * iterator may be more appropriate. * */ void mas_pause(struct ma_state *mas) { mas->status = ma_pause; mas->node = NULL; } EXPORT_SYMBOL_GPL(mas_pause); /** * mas_find_setup() - Internal function to set up mas_find*(). * @mas: The maple state * @max: The maximum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static __always_inline bool mas_find_setup(struct ma_state *mas, unsigned long max, void **entry) { switch (mas->status) { case ma_active: if (mas->last < max) return false; return true; case ma_start: break; case ma_pause: if (unlikely(mas->last >= max)) return true; mas->index = ++mas->last; mas->status = ma_start; break; case ma_none: if (unlikely(mas->last >= max)) return true; mas->index = mas->last; mas->status = ma_start; break; case ma_underflow: /* mas is pointing at entry before unable to go lower */ if (unlikely(mas->index >= max)) { mas->status = ma_overflow; return true; } mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_overflow: if (unlikely(mas->last >= max)) return true; mas_may_activate(mas); *entry = mas_walk(mas); if (*entry) return true; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index > max) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto ptr_out_of_range; if (unlikely(mas_is_none(mas))) return true; if (mas->index == max) return true; return false; ptr_out_of_range: mas->status = ma_none; mas->index = 1; mas->last = ULONG_MAX; return true; } /** * mas_find() - On the first call, find the entry at or after mas->index up to * %max. Otherwise, find the entry after mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ entry = mas_next_slot(mas, max, false); /* Ignore overflow */ mas->status = ma_active; return entry; } EXPORT_SYMBOL_GPL(mas_find); /** * mas_find_range() - On the first call, find the entry at or after * mas->index up to %max. Otherwise, advance to the next slot mas->index. * @mas: The maple state * @max: The maximum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_overflow. * * Return: The entry or %NULL. */ void *mas_find_range(struct ma_state *mas, unsigned long max) { void *entry = NULL; if (mas_find_setup(mas, max, &entry)) return entry; /* Retries on dead nodes handled by mas_next_slot */ return mas_next_slot(mas, max, true); } EXPORT_SYMBOL_GPL(mas_find_range); /** * mas_find_rev_setup() - Internal function to set up mas_find_*_rev() * @mas: The maple state * @min: The minimum index * @entry: Pointer to the entry * * Returns: True if entry is the answer, false otherwise. */ static bool mas_find_rev_setup(struct ma_state *mas, unsigned long min, void **entry) { switch (mas->status) { case ma_active: goto active; case ma_start: break; case ma_pause: if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->last = --mas->index; mas->status = ma_start; break; case ma_none: if (mas->index <= min) goto none; mas->last = mas->index; mas->status = ma_start; break; case ma_overflow: /* user expects the mas to be one after where it is */ if (unlikely(mas->index <= min)) { mas->status = ma_underflow; return true; } mas->status = ma_active; break; case ma_underflow: /* user expects the mas to be one before where it is */ if (unlikely(mas->index <= min)) return true; mas->status = ma_active; break; case ma_root: break; case ma_error: return true; } if (mas_is_start(mas)) { /* First run or continue */ if (mas->index < min) return true; *entry = mas_walk(mas); if (*entry) return true; } if (unlikely(mas_is_ptr(mas))) goto none; if (unlikely(mas_is_none(mas))) { /* * Walked to the location, and there was nothing so the previous * location is 0. */ mas->last = mas->index = 0; mas->status = ma_root; *entry = mas_root(mas); return true; } active: if (mas->index < min) return true; return false; none: mas->status = ma_none; return true; } /** * mas_find_rev: On the first call, find the first non-null entry at or below * mas->index down to %min. Otherwise find the first non-null entry below * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, false); } EXPORT_SYMBOL_GPL(mas_find_rev); /** * mas_find_range_rev: On the first call, find the first non-null entry at or * below mas->index down to %min. Otherwise advance to the previous slot after * mas->index down to %min. * @mas: The maple state * @min: The minimum value to check. * * Must hold rcu_read_lock or the write lock. * If an entry exists, last and index are updated accordingly. * May set @mas->status to ma_underflow. * * Return: The entry or %NULL. */ void *mas_find_range_rev(struct ma_state *mas, unsigned long min) { void *entry = NULL; if (mas_find_rev_setup(mas, min, &entry)) return entry; /* Retries on dead nodes handled by mas_prev_slot */ return mas_prev_slot(mas, min, true); } EXPORT_SYMBOL_GPL(mas_find_range_rev); /** * mas_erase() - Find the range in which index resides and erase the entire * range. * @mas: The maple state * * Must hold the write lock. * Searches for @mas->index, sets @mas->index and @mas->last to the range and * erases that range. * * Return: the entry that was erased or %NULL, @mas->index and @mas->last are updated. */ void *mas_erase(struct ma_state *mas) { void *entry; unsigned long index = mas->index; MA_WR_STATE(wr_mas, mas, NULL); if (!mas_is_active(mas) || !mas_is_start(mas)) mas->status = ma_start; write_retry: entry = mas_state_walk(mas); if (!entry) return NULL; /* Must reset to ensure spanning writes of last slot are detected */ mas_reset(mas); mas_wr_preallocate(&wr_mas, NULL); if (mas_nomem(mas, GFP_KERNEL)) { /* in case the range of entry changed when unlocked */ mas->index = mas->last = index; goto write_retry; } if (mas_is_err(mas)) goto out; mas_wr_store_entry(&wr_mas); out: mas_destroy(mas); return entry; } EXPORT_SYMBOL_GPL(mas_erase); /** * mas_nomem() - Check if there was an error allocating and do the allocation * if necessary If there are allocations, then free them. * @mas: The maple state * @gfp: The GFP_FLAGS to use for allocations * Return: true on allocation, false otherwise. */ bool mas_nomem(struct ma_state *mas, gfp_t gfp) __must_hold(mas->tree->ma_lock) { if (likely(mas->node != MA_ERROR(-ENOMEM))) return false; if (gfpflags_allow_blocking(gfp) && !mt_external_lock(mas->tree)) { mtree_unlock(mas->tree); mas_alloc_nodes(mas, gfp); mtree_lock(mas->tree); } else { mas_alloc_nodes(mas, gfp); } if (!mas->sheaf && !mas->alloc) return false; mas->status = ma_start; return true; } void __init maple_tree_init(void) { struct kmem_cache_args args = { .align = sizeof(struct maple_node), .sheaf_capacity = 32, }; maple_node_cache = kmem_cache_create("maple_node", sizeof(struct maple_node), &args, SLAB_PANIC); } /** * mtree_load() - Load a value stored in a maple tree * @mt: The maple tree * @index: The index to load * * Return: the entry or %NULL */ void *mtree_load(struct maple_tree *mt, unsigned long index) { MA_STATE(mas, mt, index, index); void *entry; trace_ma_read(TP_FCT, &mas); rcu_read_lock(); retry: entry = mas_start(&mas); if (unlikely(mas_is_none(&mas))) goto unlock; if (unlikely(mas_is_ptr(&mas))) { if (index) entry = NULL; goto unlock; } entry = mtree_lookup_walk(&mas); if (!entry && unlikely(mas_is_start(&mas))) goto retry; unlock: rcu_read_unlock(); if (xa_is_zero(entry)) return NULL; return entry; } EXPORT_SYMBOL(mtree_load); /** * mtree_store_range() - Store an entry at a given range. * @mt: The maple tree * @index: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store_range(struct maple_tree *mt, unsigned long index, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(mas, mt, index, last); int ret = 0; trace_ma_write(TP_FCT, &mas, 0, entry); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (index > last) return -EINVAL; mtree_lock(mt); ret = mas_store_gfp(&mas, entry, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_store_range); /** * mtree_store() - Store an entry at a given index. * @mt: The maple tree * @index: The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations * * Return: 0 on success, -EINVAL on invalid request, -ENOMEM if memory could not * be allocated. */ int mtree_store(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_store_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_store); /** * mtree_insert_range() - Insert an entry at a given range if there is no value. * @mt: The maple tree * @first: The start of the range * @last: The end of the range * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert_range(struct maple_tree *mt, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { MA_STATE(ms, mt, first, last); int ret = 0; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (first > last) return -EINVAL; mtree_lock(mt); retry: mas_insert(&ms, entry); if (mas_nomem(&ms, gfp)) goto retry; mtree_unlock(mt); if (mas_is_err(&ms)) ret = xa_err(ms.node); mas_destroy(&ms); return ret; } EXPORT_SYMBOL(mtree_insert_range); /** * mtree_insert() - Insert an entry at a given index if there is no value. * @mt: The maple tree * @index : The index to store the value * @entry: The entry to store * @gfp: The GFP_FLAGS to use for allocations. * * Return: 0 on success, -EEXISTS if the range is occupied, -EINVAL on invalid * request, -ENOMEM if memory could not be allocated. */ int mtree_insert(struct maple_tree *mt, unsigned long index, void *entry, gfp_t gfp) { return mtree_insert_range(mt, index, index, entry, gfp); } EXPORT_SYMBOL(mtree_insert); int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_range); /** * mtree_alloc_cyclic() - Find somewhere to store this entry in the tree. * @mt: The maple tree. * @startp: Pointer to ID. * @range_lo: Lower bound of range to search. * @range_hi: Upper bound of range to search. * @entry: The entry to store. * @next: Pointer to next ID to allocate. * @gfp: The GFP_FLAGS to use for allocations. * * Finds an empty entry in @mt after @next, stores the new index into * the @id pointer, stores the entry at that index, then updates @next. * * @mt must be initialized with the MT_FLAGS_ALLOC_RANGE flag. * * Context: Any context. Takes and releases the mt.lock. May sleep if * the @gfp flags permit. * * Return: 0 if the allocation succeeded without wrapping, 1 if the * allocation succeeded after wrapping, -ENOMEM if memory could not be * allocated, -EINVAL if @mt cannot be used, or -EBUSY if there are no * free entries. */ int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long range_lo, unsigned long range_hi, unsigned long *next, gfp_t gfp) { int ret; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); ret = mas_alloc_cyclic(&mas, startp, entry, range_lo, range_hi, next, gfp); mtree_unlock(mt); return ret; } EXPORT_SYMBOL(mtree_alloc_cyclic); int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp, void *entry, unsigned long size, unsigned long min, unsigned long max, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); if (!mt_is_alloc(mt)) return -EINVAL; if (WARN_ON_ONCE(mt_is_reserved(entry))) return -EINVAL; mtree_lock(mt); retry: ret = mas_empty_area_rev(&mas, min, max, size); if (ret) goto unlock; mas_insert(&mas, entry); /* * mas_nomem() may release the lock, causing the allocated area * to be unavailable, so try to allocate a free area again. */ if (mas_nomem(&mas, gfp)) goto retry; if (mas_is_err(&mas)) ret = xa_err(mas.node); else *startp = mas.index; unlock: mtree_unlock(mt); mas_destroy(&mas); return ret; } EXPORT_SYMBOL(mtree_alloc_rrange); /** * mtree_erase() - Find an index and erase the entire range. * @mt: The maple tree * @index: The index to erase * * Erasing is the same as a walk to an entry then a store of a NULL to that * ENTIRE range. In fact, it is implemented as such using the advanced API. * * Return: The entry stored at the @index or %NULL */ void *mtree_erase(struct maple_tree *mt, unsigned long index) { void *entry = NULL; MA_STATE(mas, mt, index, index); trace_ma_op(TP_FCT, &mas); mtree_lock(mt); entry = mas_erase(&mas); mtree_unlock(mt); return entry; } EXPORT_SYMBOL(mtree_erase); /* * mas_dup_free() - Free an incomplete duplication of a tree. * @mas: The maple state of a incomplete tree. * * The parameter @mas->node passed in indicates that the allocation failed on * this node. This function frees all nodes starting from @mas->node in the * reverse order of mas_dup_build(). There is no need to hold the source tree * lock at this time. */ static void mas_dup_free(struct ma_state *mas) { struct maple_node *node; enum maple_type type; void __rcu **slots; unsigned char count, i; /* Maybe the first node allocation failed. */ if (mas_is_none(mas)) return; while (!mte_is_root(mas->node)) { mas_ascend(mas); if (mas->offset) { mas->offset--; do { mas_descend(mas); mas->offset = mas_data_end(mas); } while (!mte_is_leaf(mas->node)); mas_ascend(mas); } node = mte_to_node(mas->node); type = mte_node_type(mas->node); slots = ma_slots(node, type); count = mas_data_end(mas) + 1; for (i = 0; i < count; i++) ((unsigned long *)slots)[i] &= ~MAPLE_NODE_MASK; mt_free_bulk(count, slots); } node = mte_to_node(mas->node); kfree(node); } /* * mas_copy_node() - Copy a maple node and replace the parent. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @parent: The parent of the new node. * * Copy @mas->node to @new_mas->node, set @parent to be the parent of * @new_mas->node. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_copy_node(struct ma_state *mas, struct ma_state *new_mas, struct maple_pnode *parent) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); unsigned long val; /* Copy the node completely. */ memcpy(new_node, node, sizeof(struct maple_node)); /* Update the parent node pointer. */ val = (unsigned long)node->parent & MAPLE_NODE_MASK; new_node->parent = ma_parent_ptr(val | (unsigned long)parent); } /* * mas_dup_alloc() - Allocate child nodes for a maple node. * @mas: The maple state of source tree. * @new_mas: The maple state of new tree. * @gfp: The GFP_FLAGS to use for allocations. * * This function allocates child nodes for @new_mas->node during the duplication * process. If memory allocation fails, @mas is set to -ENOMEM. */ static inline void mas_dup_alloc(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node = mte_to_node(mas->node); struct maple_node *new_node = mte_to_node(new_mas->node); enum maple_type type; unsigned char count, i; void __rcu **slots; void __rcu **new_slots; unsigned long val; /* Allocate memory for child nodes. */ type = mte_node_type(mas->node); new_slots = ma_slots(new_node, type); count = mas->node_request = mas_data_end(mas) + 1; mas_alloc_nodes(mas, gfp); if (unlikely(mas_is_err(mas))) return; slots = ma_slots(node, type); for (i = 0; i < count; i++) { val = (unsigned long)mt_slot_locked(mas->tree, slots, i); val &= MAPLE_NODE_MASK; /* * Warning, see rcu_assign_pointer() documentation. Since this * is a duplication of a tree, there are no readers walking the * tree until after the rcu_assign_pointer() call in * mas_dup_build(). */ RCU_INIT_POINTER(new_slots[i], ma_mnode_ptr((unsigned long)mas_pop_node(mas) | val)); } } /* * mas_dup_build() - Build a new maple tree from a source tree * @mas: The maple state of source tree, need to be in MAS_START state. * @new_mas: The maple state of new tree, need to be in MAS_START state. * @gfp: The GFP_FLAGS to use for allocations. * * This function builds a new tree in DFS preorder. If the memory allocation * fails, the error code -ENOMEM will be set in @mas, and @new_mas points to the * last node. mas_dup_free() will free the incomplete duplication of a tree. * * Note that the attributes of the two trees need to be exactly the same, and the * new tree needs to be empty, otherwise -EINVAL will be set in @mas. */ static inline void mas_dup_build(struct ma_state *mas, struct ma_state *new_mas, gfp_t gfp) { struct maple_node *node; struct maple_pnode *parent = NULL; struct maple_enode *root; enum maple_type type; if (unlikely(mt_attr(mas->tree) != mt_attr(new_mas->tree)) || unlikely(!mtree_empty(new_mas->tree))) { mas_set_err(mas, -EINVAL); return; } root = mas_start(mas); if (mas_is_ptr(mas) || mas_is_none(mas)) goto set_new_tree; node = mt_alloc_one(gfp); if (!node) { new_mas->status = ma_none; mas_set_err(mas, -ENOMEM); return; } type = mte_node_type(mas->node); root = mt_mk_node(node, type); new_mas->node = root; new_mas->min = 0; new_mas->max = ULONG_MAX; root = mte_mk_root(root); while (1) { mas_copy_node(mas, new_mas, parent); if (!mte_is_leaf(mas->node)) { /* Only allocate child nodes for non-leaf nodes. */ mas_dup_alloc(mas, new_mas, gfp); if (unlikely(mas_is_err(mas))) goto empty_mas; } else { /* * This is the last leaf node and duplication is * completed. */ if (mas->max == ULONG_MAX) goto done; /* This is not the last leaf node and needs to go up. */ do { mas_ascend(mas); mas_ascend(new_mas); } while (mas->offset == mas_data_end(mas)); /* Move to the next subtree. */ mas->offset++; new_mas->offset++; } mas_descend(mas); parent = ma_parent_ptr(mte_to_node(new_mas->node)); mas_descend(new_mas); mas->offset = 0; new_mas->offset = 0; } done: /* Specially handle the parent of the root node. */ mte_to_node(root)->parent = ma_parent_ptr(mas_tree_parent(new_mas)); set_new_tree: /* Make them the same height */ new_mas->tree->ma_flags = mas->tree->ma_flags; rcu_assign_pointer(new_mas->tree->ma_root, root); empty_mas: mas_empty_nodes(mas); } /** * __mt_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * Note that the user needs to manually lock the source tree and the new tree. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_dup_build(&mas, &new_mas, gfp); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } return ret; } EXPORT_SYMBOL(__mt_dup); /** * mtree_dup(): Duplicate an entire maple tree * @mt: The source maple tree * @new: The new maple tree * @gfp: The GFP_FLAGS to use for allocations * * This function duplicates a maple tree in Depth-First Search (DFS) pre-order * traversal. It uses memcpy() to copy nodes in the source tree and allocate * new child nodes in non-leaf nodes. The new node is exactly the same as the * source node except for all the addresses stored in it. It will be faster than * traversing all elements in the source tree and inserting them one by one into * the new tree. * The user needs to ensure that the attributes of the source tree and the new * tree are the same, and the new tree needs to be an empty tree, otherwise * -EINVAL will be returned. * * Return: 0 on success, -ENOMEM if memory could not be allocated, -EINVAL If * the attributes of the two trees are different or the new tree is not an empty * tree. */ int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp) { int ret = 0; MA_STATE(mas, mt, 0, 0); MA_STATE(new_mas, new, 0, 0); mas_lock(&new_mas); mas_lock_nested(&mas, SINGLE_DEPTH_NESTING); mas_dup_build(&mas, &new_mas, gfp); mas_unlock(&mas); if (unlikely(mas_is_err(&mas))) { ret = xa_err(mas.node); if (ret == -ENOMEM) mas_dup_free(&new_mas); } mas_unlock(&new_mas); return ret; } EXPORT_SYMBOL(mtree_dup); /** * __mt_destroy() - Walk and free all nodes of a locked maple tree. * @mt: The maple tree * * Note: Does not handle locking. */ void __mt_destroy(struct maple_tree *mt) { void *root = mt_root_locked(mt); rcu_assign_pointer(mt->ma_root, NULL); if (xa_is_node(root)) mte_destroy_walk(root, mt); mt->ma_flags = mt_attr(mt); } EXPORT_SYMBOL_GPL(__mt_destroy); /** * mtree_destroy() - Destroy a maple tree * @mt: The maple tree * * Frees all resources used by the tree. Handles locking. */ void mtree_destroy(struct maple_tree *mt) { mtree_lock(mt); __mt_destroy(mt); mtree_unlock(mt); } EXPORT_SYMBOL(mtree_destroy); /** * mt_find() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value of the search range * * Takes RCU read lock internally to protect the search, which does not * protect the returned pointer after dropping RCU read lock. * See also: Documentation/core-api/maple_tree.rst * * In case that an entry is found @index is updated to point to the next * possible entry independent whether the found entry is occupying a * single index or a range if indices. * * Return: The entry at or after the @index or %NULL */ void *mt_find(struct maple_tree *mt, unsigned long *index, unsigned long max) { MA_STATE(mas, mt, *index, *index); void *entry; #ifdef CONFIG_DEBUG_MAPLE_TREE unsigned long copy = *index; #endif trace_ma_read(TP_FCT, &mas); if ((*index) > max) return NULL; rcu_read_lock(); retry: entry = mas_state_walk(&mas); if (mas_is_start(&mas)) goto retry; if (unlikely(xa_is_zero(entry))) entry = NULL; if (entry) goto unlock; while (mas_is_active(&mas) && (mas.last < max)) { entry = mas_next_slot(&mas, max, false); if (likely(entry && !xa_is_zero(entry))) break; } if (unlikely(xa_is_zero(entry))) entry = NULL; unlock: rcu_read_unlock(); if (likely(entry)) { *index = mas.last + 1; #ifdef CONFIG_DEBUG_MAPLE_TREE if (MT_WARN_ON(mt, (*index) && ((*index) <= copy))) pr_err("index not increased! %lx <= %lx\n", *index, copy); #endif } return entry; } EXPORT_SYMBOL(mt_find); /** * mt_find_after() - Search from the start up until an entry is found. * @mt: The maple tree * @index: Pointer which contains the start location of the search * @max: The maximum value to check * * Same as mt_find() except that it checks @index for 0 before * searching. If @index == 0, the search is aborted. This covers a wrap * around of @index to 0 in an iterator loop. * * Return: The entry at or after the @index or %NULL */ void *mt_find_after(struct maple_tree *mt, unsigned long *index, unsigned long max) { if (!(*index)) return NULL; return mt_find(mt, index, max); } EXPORT_SYMBOL(mt_find_after); #ifdef CONFIG_DEBUG_MAPLE_TREE atomic_t maple_tree_tests_run; EXPORT_SYMBOL_GPL(maple_tree_tests_run); atomic_t maple_tree_tests_passed; EXPORT_SYMBOL_GPL(maple_tree_tests_passed); #ifndef __KERNEL__ extern void kmem_cache_set_non_kernel(struct kmem_cache *, unsigned int); void mt_set_non_kernel(unsigned int val) { kmem_cache_set_non_kernel(maple_node_cache, val); } extern void kmem_cache_set_callback(struct kmem_cache *cachep, void (*callback)(void *)); void mt_set_callback(void (*callback)(void *)) { kmem_cache_set_callback(maple_node_cache, callback); } extern void kmem_cache_set_private(struct kmem_cache *cachep, void *private); void mt_set_private(void *private) { kmem_cache_set_private(maple_node_cache, private); } extern unsigned long kmem_cache_get_alloc(struct kmem_cache *); unsigned long mt_get_alloc_size(void) { return kmem_cache_get_alloc(maple_node_cache); } extern void kmem_cache_zero_nr_tallocated(struct kmem_cache *); void mt_zero_nr_tallocated(void) { kmem_cache_zero_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_tallocated(struct kmem_cache *); unsigned int mt_nr_tallocated(void) { return kmem_cache_nr_tallocated(maple_node_cache); } extern unsigned int kmem_cache_nr_allocated(struct kmem_cache *); unsigned int mt_nr_allocated(void) { return kmem_cache_nr_allocated(maple_node_cache); } void mt_cache_shrink(void) { } #else /* * mt_cache_shrink() - For testing, don't use this. * * Certain testcases can trigger an OOM when combined with other memory * debugging configuration options. This function is used to reduce the * possibility of an out of memory even due to kmem_cache objects remaining * around for longer than usual. */ void mt_cache_shrink(void) { kmem_cache_shrink(maple_node_cache); } EXPORT_SYMBOL_GPL(mt_cache_shrink); #endif /* not defined __KERNEL__ */ /* * mas_get_slot() - Get the entry in the maple state node stored at @offset. * @mas: The maple state * @offset: The offset into the slot array to fetch. * * Return: The entry stored at @offset. */ static inline struct maple_enode *mas_get_slot(struct ma_state *mas, unsigned char offset) { return mas_slot(mas, ma_slots(mas_mn(mas), mte_node_type(mas->node)), offset); } /* Depth first search, post-order */ static void mas_dfs_postorder(struct ma_state *mas, unsigned long max) { struct maple_enode *p, *mn = mas->node; unsigned long p_min, p_max; mas_next_node(mas, mas_mn(mas), max); if (!mas_is_overflow(mas)) return; if (mte_is_root(mn)) return; mas->node = mn; mas_ascend(mas); do { p = mas->node; p_min = mas->min; p_max = mas->max; mas_prev_node(mas, 0); } while (!mas_is_underflow(mas)); mas->node = p; mas->max = p_max; mas->min = p_min; } /* Tree validations */ static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format); static void mt_dump_range(unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { static const char spaces[] = " "; switch(format) { case mt_dump_hex: if (min == max) pr_info("%.*s%lx: ", depth * 2, spaces, min); else pr_info("%.*s%lx-%lx: ", depth * 2, spaces, min, max); break; case mt_dump_dec: if (min == max) pr_info("%.*s%lu: ", depth * 2, spaces, min); else pr_info("%.*s%lu-%lu: ", depth * 2, spaces, min, max); } } static void mt_dump_entry(void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { mt_dump_range(min, max, depth, format); if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [" PTR_FMT "]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else if (mt_is_reserved(entry)) pr_cont("UNKNOWN ENTRY (" PTR_FMT ")\n", entry); else pr_cont(PTR_FMT "\n", entry); } static void mt_dump_range64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_range_64 *node = &mte_to_node(entry)->mr64; bool leaf = mte_is_leaf(entry); unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_RANGE64_SLOTS - 1; i++) { switch(format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_RANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_RANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i] && max != mt_node_max(entry)) break; if (last == 0 && i > 0) break; if (leaf) mt_dump_entry(mt_slot(mt, node->slot, i), first, last, depth + 1, format); else if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_arange64(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_arange_64 *node = &mte_to_node(entry)->ma64; unsigned long first = min; int i; pr_cont(" contents: "); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { switch (format) { case mt_dump_hex: pr_cont("%lx ", node->gap[i]); break; case mt_dump_dec: pr_cont("%lu ", node->gap[i]); } } pr_cont("| %02X %02X| ", node->meta.end, node->meta.gap); for (i = 0; i < MAPLE_ARANGE64_SLOTS - 1; i++) { switch (format) { case mt_dump_hex: pr_cont(PTR_FMT " %lX ", node->slot[i], node->pivot[i]); break; case mt_dump_dec: pr_cont(PTR_FMT " %lu ", node->slot[i], node->pivot[i]); } } pr_cont(PTR_FMT "\n", node->slot[i]); for (i = 0; i < MAPLE_ARANGE64_SLOTS; i++) { unsigned long last = max; if (i < (MAPLE_ARANGE64_SLOTS - 1)) last = node->pivot[i]; else if (!node->slot[i]) break; if (last == 0 && i > 0) break; if (node->slot[i]) mt_dump_node(mt, mt_slot(mt, node->slot, i), first, last, depth + 1, format); if (last == max) break; if (last > max) { switch(format) { case mt_dump_hex: pr_err("node " PTR_FMT " last (%lx) > max (%lx) at pivot %d!\n", node, last, max, i); break; case mt_dump_dec: pr_err("node " PTR_FMT " last (%lu) > max (%lu) at pivot %d!\n", node, last, max, i); } } first = last + 1; } } static void mt_dump_node(const struct maple_tree *mt, void *entry, unsigned long min, unsigned long max, unsigned int depth, enum mt_dump_format format) { struct maple_node *node = mte_to_node(entry); unsigned int type = mte_node_type(entry); unsigned int i; mt_dump_range(min, max, depth, format); pr_cont("node " PTR_FMT " depth %d type %d parent " PTR_FMT, node, depth, type, node ? node->parent : NULL); switch (type) { case maple_dense: pr_cont("\n"); for (i = 0; i < MAPLE_NODE_SLOTS; i++) { if (min + i > max) pr_cont("OUT OF RANGE: "); mt_dump_entry(mt_slot(mt, node->slot, i), min + i, min + i, depth, format); } break; case maple_leaf_64: case maple_range_64: mt_dump_range64(mt, entry, min, max, depth, format); break; case maple_arange_64: mt_dump_arange64(mt, entry, min, max, depth, format); break; default: pr_cont(" UNKNOWN TYPE\n"); } } void mt_dump(const struct maple_tree *mt, enum mt_dump_format format) { void *entry = rcu_dereference_check(mt->ma_root, mt_locked(mt)); pr_info("maple_tree(" PTR_FMT ") flags %X, height %u root " PTR_FMT "\n", mt, mt->ma_flags, mt_height(mt), entry); if (xa_is_node(entry)) mt_dump_node(mt, entry, 0, mt_node_max(entry), 0, format); else if (entry) mt_dump_entry(entry, 0, 0, 0, format); else pr_info("(empty)\n"); } EXPORT_SYMBOL_GPL(mt_dump); /* * Calculate the maximum gap in a node and check if that's what is reported in * the parent (unless root). */ static void mas_validate_gaps(struct ma_state *mas) { struct maple_enode *mte = mas->node; struct maple_node *p_mn, *node = mte_to_node(mte); enum maple_type mt = mte_node_type(mas->node); unsigned long gap = 0, max_gap = 0; unsigned long p_end, p_start = mas->min; unsigned char p_slot, offset; unsigned long *gaps = NULL; unsigned long *pivots = ma_pivots(node, mt); unsigned int i; if (ma_is_dense(mt)) { for (i = 0; i < mt_slot_count(mte); i++) { if (mas_get_slot(mas, i)) { if (gap > max_gap) max_gap = gap; gap = 0; continue; } gap++; } goto counted; } gaps = ma_gaps(node, mt); for (i = 0; i < mt_slot_count(mte); i++) { p_end = mas_safe_pivot(mas, pivots, i, mt); if (!gaps) { if (!mas_get_slot(mas, i)) gap = p_end - p_start + 1; } else { void *entry = mas_get_slot(mas, i); gap = gaps[i]; MT_BUG_ON(mas->tree, !entry); if (gap > p_end - p_start + 1) { pr_err(PTR_FMT "[%u] %lu >= %lu - %lu + 1 (%lu)\n", mas_mn(mas), i, gap, p_end, p_start, p_end - p_start + 1); MT_BUG_ON(mas->tree, gap > p_end - p_start + 1); } } if (gap > max_gap) max_gap = gap; p_start = p_end + 1; if (p_end >= mas->max) break; } counted: if (mt == maple_arange_64) { MT_BUG_ON(mas->tree, !gaps); offset = ma_meta_gap(node); if (offset > i) { pr_err("gap offset " PTR_FMT "[%u] is invalid\n", node, offset); MT_BUG_ON(mas->tree, 1); } if (gaps[offset] != max_gap) { pr_err("gap " PTR_FMT "[%u] is not the largest gap %lu\n", node, offset, max_gap); MT_BUG_ON(mas->tree, 1); } for (i++ ; i < mt_slot_count(mte); i++) { if (gaps[i] != 0) { pr_err("gap " PTR_FMT "[%u] beyond node limit != 0\n", node, i); MT_BUG_ON(mas->tree, 1); } } } if (mte_is_root(mte)) return; p_slot = mte_parent_slot(mas->node); p_mn = mte_parent(mte); MT_BUG_ON(mas->tree, max_gap > mas->max); if (ma_gaps(p_mn, mas_parent_type(mas, mte))[p_slot] != max_gap) { pr_err("gap " PTR_FMT "[%u] != %lu\n", p_mn, p_slot, max_gap); mt_dump(mas->tree, mt_dump_hex); MT_BUG_ON(mas->tree, 1); } } static void mas_validate_parent_slot(struct ma_state *mas) { struct maple_node *parent; struct maple_enode *node; enum maple_type p_type; unsigned char p_slot; void __rcu **slots; int i; if (mte_is_root(mas->node)) return; p_slot = mte_parent_slot(mas->node); p_type = mas_parent_type(mas, mas->node); parent = mte_parent(mas->node); slots = ma_slots(parent, p_type); MT_BUG_ON(mas->tree, mas_mn(mas) == parent); /* Check prev/next parent slot for duplicate node entry */ for (i = 0; i < mt_slots[p_type]; i++) { node = mas_slot(mas, slots, i); if (i == p_slot) { if (node != mas->node) pr_err("parent " PTR_FMT "[%u] does not have " PTR_FMT "\n", parent, i, mas_mn(mas)); MT_BUG_ON(mas->tree, node != mas->node); } else if (node == mas->node) { pr_err("Invalid child " PTR_FMT " at parent " PTR_FMT "[%u] p_slot %u\n", mas_mn(mas), parent, i, p_slot); MT_BUG_ON(mas->tree, node == mas->node); } } } static void mas_validate_child_slot(struct ma_state *mas) { enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mte_to_node(mas->node), type); struct maple_enode *child; unsigned char i; if (mte_is_leaf(mas->node)) return; for (i = 0; i < mt_slots[type]; i++) { child = mas_slot(mas, slots, i); if (!child) { pr_err("Non-leaf node lacks child at " PTR_FMT "[%u]\n", mas_mn(mas), i); MT_BUG_ON(mas->tree, 1); } if (mte_parent_slot(child) != i) { pr_err("Slot error at " PTR_FMT "[%u]: child " PTR_FMT " has pslot %u\n", mas_mn(mas), i, mte_to_node(child), mte_parent_slot(child)); MT_BUG_ON(mas->tree, 1); } if (mte_parent(child) != mte_to_node(mas->node)) { pr_err("child " PTR_FMT " has parent " PTR_FMT " not " PTR_FMT "\n", mte_to_node(child), mte_parent(child), mte_to_node(mas->node)); MT_BUG_ON(mas->tree, 1); } if (i < mt_pivots[type] && pivots[i] == mas->max) break; } } /* * Validate all pivots are within mas->min and mas->max, check metadata ends * where the maximum ends and ensure there is no slots or pivots set outside of * the end of the data. */ static void mas_validate_limits(struct ma_state *mas) { int i; unsigned long prev_piv = 0; enum maple_type type = mte_node_type(mas->node); void __rcu **slots = ma_slots(mte_to_node(mas->node), type); unsigned long *pivots = ma_pivots(mas_mn(mas), type); for (i = 0; i < mt_slots[type]; i++) { unsigned long piv; piv = mas_safe_pivot(mas, pivots, i, type); if (!piv && (i != 0)) { pr_err("Missing node limit pivot at " PTR_FMT "[%u]", mas_mn(mas), i); MAS_WARN_ON(mas, 1); } if (prev_piv > piv) { pr_err(PTR_FMT "[%u] piv %lu < prev_piv %lu\n", mas_mn(mas), i, piv, prev_piv); MAS_WARN_ON(mas, piv < prev_piv); } if (piv < mas->min) { pr_err(PTR_FMT "[%u] %lu < %lu\n", mas_mn(mas), i, piv, mas->min); MAS_WARN_ON(mas, piv < mas->min); } if (piv > mas->max) { pr_err(PTR_FMT "[%u] %lu > %lu\n", mas_mn(mas), i, piv, mas->max); MAS_WARN_ON(mas, piv > mas->max); } prev_piv = piv; if (piv == mas->max) break; } if (mas_data_end(mas) != i) { pr_err("node" PTR_FMT ": data_end %u != the last slot offset %u\n", mas_mn(mas), mas_data_end(mas), i); MT_BUG_ON(mas->tree, 1); } for (i += 1; i < mt_slots[type]; i++) { void *entry = mas_slot(mas, slots, i); if (entry && (i != mt_slots[type] - 1)) { pr_err(PTR_FMT "[%u] should not have entry " PTR_FMT "\n", mas_mn(mas), i, entry); MT_BUG_ON(mas->tree, entry != NULL); } if (i < mt_pivots[type]) { unsigned long piv = pivots[i]; if (!piv) continue; pr_err(PTR_FMT "[%u] should not have piv %lu\n", mas_mn(mas), i, piv); MAS_WARN_ON(mas, i < mt_pivots[type] - 1); } } } static void mt_validate_nulls(struct maple_tree *mt) { void *entry, *last = (void *)1; unsigned char offset = 0; void __rcu **slots; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (mas_is_none(&mas) || (mas_is_ptr(&mas))) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); do { entry = mas_slot(&mas, slots, offset); if (!last && !entry) { pr_err("Sequential nulls end at " PTR_FMT "[%u]\n", mas_mn(&mas), offset); } MT_BUG_ON(mt, !last && !entry); last = entry; if (offset == mas_data_end(&mas)) { mas_next_node(&mas, mas_mn(&mas), ULONG_MAX); if (mas_is_overflow(&mas)) return; offset = 0; slots = ma_slots(mte_to_node(mas.node), mte_node_type(mas.node)); } else { offset++; } } while (!mas_is_overflow(&mas)); } /* * validate a maple tree by checking: * 1. The limits (pivots are within mas->min to mas->max) * 2. The gap is correctly set in the parents */ void mt_validate(struct maple_tree *mt) __must_hold(mas->tree->ma_lock) { unsigned char end; MA_STATE(mas, mt, 0, 0); mas_start(&mas); if (!mas_is_active(&mas)) return; while (!mte_is_leaf(mas.node)) mas_descend(&mas); while (!mas_is_overflow(&mas)) { MAS_WARN_ON(&mas, mte_dead_node(mas.node)); end = mas_data_end(&mas); if (MAS_WARN_ON(&mas, (end < mt_min_slot_count(mas.node)) && (!mte_is_root(mas.node)))) { pr_err("Invalid size %u of " PTR_FMT "\n", end, mas_mn(&mas)); } mas_validate_parent_slot(&mas); mas_validate_limits(&mas); mas_validate_child_slot(&mas); if (mt_is_alloc(mt)) mas_validate_gaps(&mas); mas_dfs_postorder(&mas, ULONG_MAX); } mt_validate_nulls(mt); } EXPORT_SYMBOL_GPL(mt_validate); void mas_dump(const struct ma_state *mas) { pr_err("MAS: tree=" PTR_FMT " enode=" PTR_FMT " ", mas->tree, mas->node); switch (mas->status) { case ma_active: pr_err("(ma_active)"); break; case ma_none: pr_err("(ma_none)"); break; case ma_root: pr_err("(ma_root)"); break; case ma_start: pr_err("(ma_start) "); break; case ma_pause: pr_err("(ma_pause) "); break; case ma_overflow: pr_err("(ma_overflow) "); break; case ma_underflow: pr_err("(ma_underflow) "); break; case ma_error: pr_err("(ma_error) "); break; } pr_err("Store Type: "); switch (mas->store_type) { case wr_invalid: pr_err("invalid store type\n"); break; case wr_new_root: pr_err("new_root\n"); break; case wr_store_root: pr_err("store_root\n"); break; case wr_exact_fit: pr_err("exact_fit\n"); break; case wr_split_store: pr_err("split_store\n"); break; case wr_slot_store: pr_err("slot_store\n"); break; case wr_append: pr_err("append\n"); break; case wr_node_store: pr_err("node_store\n"); break; case wr_spanning_store: pr_err("spanning_store\n"); break; case wr_rebalance: pr_err("rebalance\n"); break; } pr_err("[%u/%u] index=%lx last=%lx\n", mas->offset, mas->end, mas->index, mas->last); pr_err(" min=%lx max=%lx sheaf=" PTR_FMT ", request %lu depth=%u, flags=%x\n", mas->min, mas->max, mas->sheaf, mas->node_request, mas->depth, mas->mas_flags); if (mas->index > mas->last) pr_err("Check index & last\n"); } EXPORT_SYMBOL_GPL(mas_dump); void mas_wr_dump(const struct ma_wr_state *wr_mas) { pr_err("WR_MAS: node=" PTR_FMT " r_min=%lx r_max=%lx\n", wr_mas->node, wr_mas->r_min, wr_mas->r_max); pr_err(" type=%u off_end=%u, node_end=%u, end_piv=%lx\n", wr_mas->type, wr_mas->offset_end, wr_mas->mas->end, wr_mas->end_piv); } EXPORT_SYMBOL_GPL(mas_wr_dump); #endif /* CONFIG_DEBUG_MAPLE_TREE */ |
| 9 31 29 30 31 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #ifndef _WG_QUEUEING_H #define _WG_QUEUEING_H #include "peer.h" #include <linux/types.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <net/ip_tunnels.h> struct wg_device; struct wg_peer; struct multicore_worker; struct crypt_queue; struct prev_queue; struct sk_buff; /* queueing.c APIs: */ int wg_packet_queue_init(struct crypt_queue *queue, work_func_t function, unsigned int len); void wg_packet_queue_free(struct crypt_queue *queue, bool purge); struct multicore_worker __percpu * wg_packet_percpu_multicore_worker_alloc(work_func_t function, void *ptr); /* receive.c APIs: */ void wg_packet_receive(struct wg_device *wg, struct sk_buff *skb); void wg_packet_handshake_receive_worker(struct work_struct *work); /* NAPI poll function: */ int wg_packet_rx_poll(struct napi_struct *napi, int budget); /* Workqueue worker: */ void wg_packet_decrypt_worker(struct work_struct *work); /* send.c APIs: */ void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer, bool is_retry); void wg_packet_send_handshake_response(struct wg_peer *peer); void wg_packet_send_handshake_cookie(struct wg_device *wg, struct sk_buff *initiating_skb, __le32 sender_index); void wg_packet_send_keepalive(struct wg_peer *peer); void wg_packet_purge_staged_packets(struct wg_peer *peer); void wg_packet_send_staged_packets(struct wg_peer *peer); /* Workqueue workers: */ void wg_packet_handshake_send_worker(struct work_struct *work); void wg_packet_tx_worker(struct work_struct *work); void wg_packet_encrypt_worker(struct work_struct *work); enum packet_state { PACKET_STATE_UNCRYPTED, PACKET_STATE_CRYPTED, PACKET_STATE_DEAD }; struct packet_cb { u64 nonce; struct noise_keypair *keypair; atomic_t state; u32 mtu; u8 ds; }; #define PACKET_CB(skb) ((struct packet_cb *)((skb)->cb)) #define PACKET_PEER(skb) (PACKET_CB(skb)->keypair->entry.peer) static inline bool wg_check_packet_protocol(struct sk_buff *skb) { __be16 real_protocol = ip_tunnel_parse_protocol(skb); return real_protocol && skb->protocol == real_protocol; } static inline void wg_reset_packet(struct sk_buff *skb, bool encapsulating) { u8 l4_hash = skb->l4_hash; u8 sw_hash = skb->sw_hash; u32 hash = skb->hash; skb_scrub_packet(skb, true); memset(&skb->headers, 0, sizeof(skb->headers)); if (encapsulating) { skb->l4_hash = l4_hash; skb->sw_hash = sw_hash; skb->hash = hash; } skb->queue_mapping = 0; skb->nohdr = 0; skb->peeked = 0; skb->mac_len = 0; skb->dev = NULL; #ifdef CONFIG_NET_SCHED skb->tc_index = 0; #endif skb_reset_redirect(skb); skb->hdr_len = skb_headroom(skb); skb_reset_mac_header(skb); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb_probe_transport_header(skb); skb_reset_inner_headers(skb); } static inline int wg_cpumask_choose_online(int *stored_cpu, unsigned int id) { unsigned int cpu = *stored_cpu; while (unlikely(cpu >= nr_cpu_ids || !cpu_online(cpu))) cpu = *stored_cpu = cpumask_nth(id % num_online_cpus(), cpu_online_mask); return cpu; } /* This function is racy, in the sense that it's called while last_cpu is * unlocked, so it could return the same CPU twice. Adding locking or using * atomic sequence numbers is slower though, and the consequences of racing are * harmless, so live with it. */ static inline int wg_cpumask_next_online(int *last_cpu) { int cpu = cpumask_next(READ_ONCE(*last_cpu), cpu_online_mask); if (cpu >= nr_cpu_ids) cpu = cpumask_first(cpu_online_mask); WRITE_ONCE(*last_cpu, cpu); return cpu; } void wg_prev_queue_init(struct prev_queue *queue); /* Multi producer */ bool wg_prev_queue_enqueue(struct prev_queue *queue, struct sk_buff *skb); /* Single consumer */ struct sk_buff *wg_prev_queue_dequeue(struct prev_queue *queue); /* Single consumer */ static inline struct sk_buff *wg_prev_queue_peek(struct prev_queue *queue) { if (queue->peeked) return queue->peeked; queue->peeked = wg_prev_queue_dequeue(queue); return queue->peeked; } /* Single consumer */ static inline void wg_prev_queue_drop_peeked(struct prev_queue *queue) { queue->peeked = NULL; } static inline int wg_queue_enqueue_per_device_and_peer( struct crypt_queue *device_queue, struct prev_queue *peer_queue, struct sk_buff *skb, struct workqueue_struct *wq) { int cpu; atomic_set_release(&PACKET_CB(skb)->state, PACKET_STATE_UNCRYPTED); /* We first queue this up for the peer ingestion, but the consumer * will wait for the state to change to CRYPTED or DEAD before. */ if (unlikely(!wg_prev_queue_enqueue(peer_queue, skb))) return -ENOSPC; /* Then we queue it up in the device queue, which consumes the * packet as soon as it can. */ cpu = wg_cpumask_next_online(&device_queue->last_cpu); if (unlikely(ptr_ring_produce_bh(&device_queue->ring, skb))) return -EPIPE; queue_work_on(cpu, wq, &per_cpu_ptr(device_queue->worker, cpu)->work); return 0; } static inline void wg_queue_enqueue_per_peer_tx(struct sk_buff *skb, enum packet_state state) { /* We take a reference, because as soon as we call atomic_set, the * peer can be freed from below us. */ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); atomic_set_release(&PACKET_CB(skb)->state, state); queue_work_on(wg_cpumask_choose_online(&peer->serial_work_cpu, peer->internal_id), peer->device->packet_crypt_wq, &peer->transmit_packet_work); wg_peer_put(peer); } static inline void wg_queue_enqueue_per_peer_rx(struct sk_buff *skb, enum packet_state state) { /* We take a reference, because as soon as we call atomic_set, the * peer can be freed from below us. */ struct wg_peer *peer = wg_peer_get(PACKET_PEER(skb)); atomic_set_release(&PACKET_CB(skb)->state, state); napi_schedule(&peer->napi); wg_peer_put(peer); } #ifdef DEBUG bool wg_packet_counter_selftest(void); #endif #endif /* _WG_QUEUEING_H */ |
| 4361 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 | #undef TRACE_SYSTEM #define TRACE_SYSTEM netlink #if !defined(_TRACE_NETLINK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_NETLINK_H #include <linux/tracepoint.h> TRACE_EVENT(netlink_extack, TP_PROTO(const char *msg), TP_ARGS(msg), TP_STRUCT__entry( __string( msg, msg ) ), TP_fast_assign( __assign_str(msg); ), TP_printk("msg=%s", __get_str(msg)) ); #endif /* _TRACE_NETLINK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 41 41 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 | // SPDX-License-Identifier: GPL-2.0-or-later /* Socket buffer accounting * * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/net.h> #include <linux/skbuff.h> #include <net/sock.h> #include <net/af_rxrpc.h> #include "ar-internal.h" #define select_skb_count(skb) (&rxrpc_n_rx_skbs) /* * Note the allocation or reception of a socket buffer. */ void rxrpc_new_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { int n = atomic_inc_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); } /* * Note the re-emergence of a socket buffer from a queue or buffer. */ void rxrpc_see_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { if (skb) { int n = atomic_read(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); } } /* * Note the addition of a ref on a socket buffer. */ void rxrpc_get_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { int n = atomic_inc_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); skb_get(skb); } /* * Note the destruction of a socket buffer. */ void rxrpc_free_skb(struct sk_buff *skb, enum rxrpc_skb_trace why) { if (skb) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, why); consume_skb(skb); } } /* * Clear a queue of socket buffers. */ void rxrpc_purge_queue(struct sk_buff_head *list) { struct sk_buff *skb; while ((skb = skb_dequeue((list))) != NULL) { int n = atomic_dec_return(select_skb_count(skb)); trace_rxrpc_skb(skb, refcount_read(&skb->users), n, rxrpc_skb_put_purge); consume_skb(skb); } } |
| 4276 4271 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Detect hard and soft lockups on a system * * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. * * Note: Most of this code is borrowed heavily from the original softlockup * detector, so thanks to Ingo for the initial implementation. * Some chunks also taken from the old x86-specific nmi watchdog code, thanks * to those contributors as well. */ #define pr_fmt(fmt) "watchdog: " fmt #include <linux/cpu.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/irqdesc.h> #include <linux/kernel_stat.h> #include <linux/kvm_para.h> #include <linux/math64.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/nmi.h> #include <linux/stop_machine.h> #include <linux/sysctl.h> #include <linux/tick.h> #include <linux/sys_info.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <asm/irq_regs.h> static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HARDLOCKUP_DETECTOR_SPARC64) # define WATCHDOG_HARDLOCKUP_DEFAULT 1 #else # define WATCHDOG_HARDLOCKUP_DEFAULT 0 #endif #define NUM_SAMPLE_PERIODS 5 unsigned long __read_mostly watchdog_enabled; int __read_mostly watchdog_user_enabled = 1; static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT; static int __read_mostly watchdog_softlockup_user_enabled = 1; int __read_mostly watchdog_thresh = 10; static int __read_mostly watchdog_thresh_next; static int __read_mostly watchdog_hardlockup_available; struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); #ifdef CONFIG_HARDLOCKUP_DETECTOR # ifdef CONFIG_SMP int __read_mostly sysctl_hardlockup_all_cpu_backtrace; # endif /* CONFIG_SMP */ /* * Number of consecutive missed interrupts before declaring a lockup. * Default to 1 (immediate) for NMI/Perf. Buddy will overwrite this to 3. */ int __read_mostly watchdog_hardlockup_miss_thresh = 1; EXPORT_SYMBOL_GPL(watchdog_hardlockup_miss_thresh); /* * Should we panic when a soft-lockup or hard-lockup occurs: */ unsigned int __read_mostly hardlockup_panic = IS_ENABLED(CONFIG_BOOTPARAM_HARDLOCKUP_PANIC); /* * bitmasks to control what kinds of system info to be printed when * hard lockup is detected, it could be task, memory, lock etc. * Refer include/linux/sys_info.h for detailed bit definition. */ unsigned long hardlockup_si_mask; #ifdef CONFIG_SYSFS static unsigned int hardlockup_count; static ssize_t hardlockup_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return sysfs_emit(page, "%u\n", hardlockup_count); } static struct kobj_attribute hardlockup_count_attr = __ATTR_RO(hardlockup_count); static __init int kernel_hardlockup_sysfs_init(void) { sysfs_add_file_to_group(kernel_kobj, &hardlockup_count_attr.attr, NULL); return 0; } late_initcall(kernel_hardlockup_sysfs_init); #endif // CONFIG_SYSFS /* * We may not want to enable hard lockup detection by default in all cases, * for example when running the kernel as a guest on a hypervisor. In these * cases this function can be called to disable hard lockup detection. This * function should only be executed once by the boot processor before the * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ void __init hardlockup_detector_disable(void) { watchdog_hardlockup_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) { next: if (!strncmp(str, "panic", 5)) hardlockup_panic = 1; else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) watchdog_hardlockup_user_enabled = 0; else if (!strncmp(str, "1", 1)) watchdog_hardlockup_user_enabled = 1; else if (!strncmp(str, "r", 1)) hardlockup_config_perf_event(str + 1); while (*(str++)) { if (*str == ',') { str++; goto next; } } return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); #endif /* CONFIG_HARDLOCKUP_DETECTOR */ #if defined(CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER) static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts); static DEFINE_PER_CPU(int, hrtimer_interrupts_saved); static DEFINE_PER_CPU(int, hrtimer_interrupts_missed); static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned); static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched); static unsigned long hard_lockup_nmi_warn; notrace void arch_touch_nmi_watchdog(void) { /* * Using __raw here because some code paths have * preemption enabled. If preemption is enabled * then interrupts should be enabled too, in which * case we shouldn't have to worry about the watchdog * going off. */ raw_cpu_write(watchdog_hardlockup_touched, true); } EXPORT_SYMBOL(arch_touch_nmi_watchdog); void watchdog_hardlockup_touch_cpu(unsigned int cpu) { per_cpu(watchdog_hardlockup_touched, cpu) = true; } static void watchdog_hardlockup_update_reset(unsigned int cpu) { int hrint = atomic_read(&per_cpu(hrtimer_interrupts, cpu)); /* * NOTE: we don't need any fancy atomic_t or READ_ONCE/WRITE_ONCE * for hrtimer_interrupts_saved. hrtimer_interrupts_saved is * written/read by a single CPU. */ per_cpu(hrtimer_interrupts_saved, cpu) = hrint; per_cpu(hrtimer_interrupts_missed, cpu) = 0; } static bool is_hardlockup(unsigned int cpu) { int hrint = atomic_read(&per_cpu(hrtimer_interrupts, cpu)); if (per_cpu(hrtimer_interrupts_saved, cpu) != hrint) { watchdog_hardlockup_update_reset(cpu); return false; } per_cpu(hrtimer_interrupts_missed, cpu)++; if (per_cpu(hrtimer_interrupts_missed, cpu) % watchdog_hardlockup_miss_thresh) return false; return true; } static void watchdog_hardlockup_kick(void) { int new_interrupts; new_interrupts = atomic_inc_return(this_cpu_ptr(&hrtimer_interrupts)); watchdog_buddy_check_hardlockup(new_interrupts); } void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs) { int hardlockup_all_cpu_backtrace; unsigned int this_cpu; unsigned long flags; if (per_cpu(watchdog_hardlockup_touched, cpu)) { watchdog_hardlockup_update_reset(cpu); per_cpu(watchdog_hardlockup_touched, cpu) = false; return; } hardlockup_all_cpu_backtrace = (hardlockup_si_mask & SYS_INFO_ALL_BT) ? 1 : sysctl_hardlockup_all_cpu_backtrace; /* * Check for a hardlockup by making sure the CPU's timer * interrupt is incrementing. The timer interrupt should have * fired multiple times before we overflow'd. If it hasn't * then this is a good indication the cpu is stuck */ if (!is_hardlockup(cpu)) { per_cpu(watchdog_hardlockup_warned, cpu) = false; return; } #ifdef CONFIG_SYSFS ++hardlockup_count; #endif /* * A poorly behaving BPF scheduler can trigger hard lockup by * e.g. putting numerous affinitized tasks in a single queue and * directing all CPUs at it. The following call can return true * only once when sched_ext is enabled and will immediately * abort the BPF scheduler and print out a warning message. */ if (scx_hardlockup(cpu)) return; /* Only print hardlockups once. */ if (per_cpu(watchdog_hardlockup_warned, cpu)) return; /* * Prevent multiple hard-lockup reports if one cpu is already * engaged in dumping all cpu back traces. */ if (hardlockup_all_cpu_backtrace) { if (test_and_set_bit_lock(0, &hard_lockup_nmi_warn)) return; } /* * NOTE: we call printk_cpu_sync_get_irqsave() after printing * the lockup message. While it would be nice to serialize * that printout, we really want to make sure that if some * other CPU somehow locked up while holding the lock associated * with printk_cpu_sync_get_irqsave() that we can still at least * get the message about the lockup out. */ this_cpu = smp_processor_id(); pr_emerg("CPU%u: Watchdog detected hard LOCKUP on cpu %u\n", this_cpu, cpu); printk_cpu_sync_get_irqsave(flags); print_modules(); print_irqtrace_events(current); if (cpu == this_cpu) { if (regs) show_regs(regs); else dump_stack(); printk_cpu_sync_put_irqrestore(flags); } else { printk_cpu_sync_put_irqrestore(flags); trigger_single_cpu_backtrace(cpu); } if (hardlockup_all_cpu_backtrace) { trigger_allbutcpu_cpu_backtrace(cpu); if (!hardlockup_panic) clear_bit_unlock(0, &hard_lockup_nmi_warn); } sys_info(hardlockup_si_mask & ~SYS_INFO_ALL_BT); if (hardlockup_panic) nmi_panic(regs, "Hard LOCKUP"); per_cpu(watchdog_hardlockup_warned, cpu) = true; } #else /* CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */ static inline void watchdog_hardlockup_kick(void) { } #endif /* !CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */ /* * These functions can be overridden based on the configured hardlockdup detector. * * watchdog_hardlockup_enable/disable can be implemented to start and stop when * softlockup watchdog start and stop. The detector must select the * SOFTLOCKUP_DETECTOR Kconfig. */ void __weak watchdog_hardlockup_enable(unsigned int cpu) { } void __weak watchdog_hardlockup_disable(unsigned int cpu) { } /* * Watchdog-detector specific API. * * Return 0 when hardlockup watchdog is available, negative value otherwise. * Note that the negative value means that a delayed probe might * succeed later. */ int __weak __init watchdog_hardlockup_probe(void) { return -ENODEV; } /** * watchdog_hardlockup_stop - Stop the watchdog for reconfiguration * * The reconfiguration steps are: * watchdog_hardlockup_stop(); * update_variables(); * watchdog_hardlockup_start(); */ void __weak watchdog_hardlockup_stop(void) { } /** * watchdog_hardlockup_start - Start the watchdog after reconfiguration * * Counterpart to watchdog_hardlockup_stop(). * * The following variables have been updated in update_variables() and * contain the currently valid configuration: * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask */ void __weak watchdog_hardlockup_start(void) { } /** * lockup_detector_update_enable - Update the sysctl enable bit * * Caller needs to make sure that the hard watchdogs are off, so this * can't race with watchdog_hardlockup_disable(). */ static void lockup_detector_update_enable(void) { watchdog_enabled = 0; if (!watchdog_user_enabled) return; if (watchdog_hardlockup_available && watchdog_hardlockup_user_enabled) watchdog_enabled |= WATCHDOG_HARDLOCKUP_ENABLED; if (watchdog_softlockup_user_enabled) watchdog_enabled |= WATCHDOG_SOFTOCKUP_ENABLED; } #ifdef CONFIG_SOFTLOCKUP_DETECTOR /* * Delay the soflockup report when running a known slow code. * It does _not_ affect the timestamp of the last successdul reschedule. */ #define SOFTLOCKUP_DELAY_REPORT ULONG_MAX #ifdef CONFIG_SMP int __read_mostly sysctl_softlockup_all_cpu_backtrace; #endif /* * bitmasks to control what kinds of system info to be printed when * soft lockup is detected, it could be task, memory, lock etc. * Refer include/linux/sys_info.h for detailed bit definition. */ static unsigned long softlockup_si_mask; static struct cpumask watchdog_allowed_mask __read_mostly; /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC; static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; #ifdef CONFIG_SYSFS static unsigned int softlockup_count; static ssize_t softlockup_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return sysfs_emit(page, "%u\n", softlockup_count); } static struct kobj_attribute softlockup_count_attr = __ATTR_RO(softlockup_count); static __init int kernel_softlockup_sysfs_init(void) { sysfs_add_file_to_group(kernel_kobj, &softlockup_count_attr.attr, NULL); return 0; } late_initcall(kernel_softlockup_sysfs_init); #endif // CONFIG_SYSFS /* Timestamp taken after the last successful reschedule. */ static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); /* Timestamp of the last softlockup report. */ static DEFINE_PER_CPU(unsigned long, watchdog_report_ts); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static unsigned long soft_lockup_nmi_warn; static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); return 1; } __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { watchdog_softlockup_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); static int __init watchdog_thresh_setup(char *str) { get_option(&str, &watchdog_thresh); return 1; } __setup("watchdog_thresh=", watchdog_thresh_setup); #ifdef CONFIG_SOFTLOCKUP_DETECTOR_INTR_STORM enum stats_per_group { STATS_SYSTEM, STATS_SOFTIRQ, STATS_HARDIRQ, STATS_IDLE, NUM_STATS_PER_GROUP, }; static const enum cpu_usage_stat tracked_stats[NUM_STATS_PER_GROUP] = { CPUTIME_SYSTEM, CPUTIME_SOFTIRQ, CPUTIME_IRQ, CPUTIME_IDLE, }; static DEFINE_PER_CPU(u16, cpustat_old[NUM_STATS_PER_GROUP]); static DEFINE_PER_CPU(u8, cpustat_util[NUM_SAMPLE_PERIODS][NUM_STATS_PER_GROUP]); static DEFINE_PER_CPU(u8, cpustat_tail); /* * We don't need nanosecond resolution. A granularity of 16ms is * sufficient for our precision, allowing us to use u16 to store * cpustats, which will roll over roughly every ~1000 seconds. * 2^24 ~= 16 * 10^6 */ static u16 get_16bit_precision(u64 data_ns) { /* * 2^24ns ~= 16.8ms * Round to the nearest multiple of 16.8 milliseconds. */ return (data_ns + (1 << 23)) >> 24LL; } static void update_cpustat(void) { int i; u8 util; u16 old_stat, new_stat; struct kernel_cpustat kcpustat; u64 *cpustat = kcpustat.cpustat; u8 tail = __this_cpu_read(cpustat_tail); u16 sample_period_16 = get_16bit_precision(sample_period); kcpustat_cpu_fetch(&kcpustat, smp_processor_id()); for (i = 0; i < NUM_STATS_PER_GROUP; i++) { old_stat = __this_cpu_read(cpustat_old[i]); new_stat = get_16bit_precision(cpustat[tracked_stats[i]]); util = DIV_ROUND_UP(100 * (new_stat - old_stat), sample_period_16); /* * Since we use 16-bit precision, the raw data will undergo * integer division, which may sometimes result in data loss, * and then result might exceed 100%. To avoid confusion, * we enforce a 100% display cap when calculations exceed this threshold. */ if (util > 100) util = 100; __this_cpu_write(cpustat_util[tail][i], util); __this_cpu_write(cpustat_old[i], new_stat); } __this_cpu_write(cpustat_tail, (tail + 1) % NUM_SAMPLE_PERIODS); } static void print_cpustat(void) { int i, group; u8 tail = __this_cpu_read(cpustat_tail); u64 sample_period_msecond = sample_period; do_div(sample_period_msecond, NSEC_PER_MSEC); /* * Outputting the "watchdog" prefix on every line is redundant and not * concise, and the original alarm information is sufficient for * positioning in logs, hence here printk() is used instead of pr_crit(). */ printk(KERN_CRIT "CPU#%d Utilization every %llums during lockup:\n", smp_processor_id(), sample_period_msecond); for (i = 0; i < NUM_SAMPLE_PERIODS; i++) { group = (tail + i) % NUM_SAMPLE_PERIODS; printk(KERN_CRIT "\t#%d: %3u%% system,\t%3u%% softirq,\t" "%3u%% hardirq,\t%3u%% idle\n", i + 1, __this_cpu_read(cpustat_util[group][STATS_SYSTEM]), __this_cpu_read(cpustat_util[group][STATS_SOFTIRQ]), __this_cpu_read(cpustat_util[group][STATS_HARDIRQ]), __this_cpu_read(cpustat_util[group][STATS_IDLE])); } } #define HARDIRQ_PERCENT_THRESH 50 #define NUM_HARDIRQ_REPORT 5 struct irq_counts { int irq; u32 counts; }; static DEFINE_PER_CPU(bool, snapshot_taken); /* Tabulate the most frequent interrupts. */ static void tabulate_irq_count(struct irq_counts *irq_counts, int irq, u32 counts, int rank) { int i; struct irq_counts new_count = {irq, counts}; for (i = 0; i < rank; i++) { if (counts > irq_counts[i].counts) swap(new_count, irq_counts[i]); } } /* * If the hardirq time exceeds HARDIRQ_PERCENT_THRESH% of the sample_period, * then the cause of softlockup might be interrupt storm. In this case, it * would be useful to start interrupt counting. */ static bool need_counting_irqs(void) { u8 util; int tail = __this_cpu_read(cpustat_tail); tail = (tail + NUM_SAMPLE_PERIODS - 1) % NUM_SAMPLE_PERIODS; util = __this_cpu_read(cpustat_util[tail][STATS_HARDIRQ]); return util > HARDIRQ_PERCENT_THRESH; } static void start_counting_irqs(void) { if (!__this_cpu_read(snapshot_taken)) { kstat_snapshot_irqs(); __this_cpu_write(snapshot_taken, true); } } static void stop_counting_irqs(void) { __this_cpu_write(snapshot_taken, false); } static void print_irq_counts(void) { unsigned int i, count; struct irq_counts irq_counts_sorted[NUM_HARDIRQ_REPORT] = { {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0} }; if (__this_cpu_read(snapshot_taken)) { for_each_active_irq(i) { count = kstat_get_irq_since_snapshot(i); tabulate_irq_count(irq_counts_sorted, i, count, NUM_HARDIRQ_REPORT); } /* * Outputting the "watchdog" prefix on every line is redundant and not * concise, and the original alarm information is sufficient for * positioning in logs, hence here printk() is used instead of pr_crit(). */ printk(KERN_CRIT "CPU#%d Detect HardIRQ Time exceeds %d%%. Most frequent HardIRQs:\n", smp_processor_id(), HARDIRQ_PERCENT_THRESH); for (i = 0; i < NUM_HARDIRQ_REPORT; i++) { if (irq_counts_sorted[i].irq == -1) break; printk(KERN_CRIT "\t#%u: %-10u\tirq#%d\n", i + 1, irq_counts_sorted[i].counts, irq_counts_sorted[i].irq); } /* * If the hardirq time is less than HARDIRQ_PERCENT_THRESH% in the last * sample_period, then we suspect the interrupt storm might be subsiding. */ if (!need_counting_irqs()) stop_counting_irqs(); } } static void report_cpu_status(void) { print_cpustat(); print_irq_counts(); } #else static inline void update_cpustat(void) { } static inline void report_cpu_status(void) { } static inline bool need_counting_irqs(void) { return false; } static inline void start_counting_irqs(void) { } static inline void stop_counting_irqs(void) { } #endif /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally * want a higher threshold for soft lockups than for hard lockups. So we couple * the thresholds with a factor: we make the soft threshold twice the amount of * time the hard threshold is. */ static int get_softlockup_thresh(void) { return watchdog_thresh * 2; } /* * Returns seconds, approximately. We don't need nanosecond * resolution, and we don't need to waste time with a big divide when * 2^30ns == 1.074s. */ static unsigned long get_timestamp(void) { return running_clock() >> 30LL; /* 2^30 ~= 10^9 */ } static void set_sample_period(void) { /* * convert watchdog_thresh from seconds to ns * the divide by 5 is to give hrtimer several chances (two * or three with the current relation between the soft * and hard thresholds) to increment before the * hardlockup detector generates a warning */ sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / NUM_SAMPLE_PERIODS); watchdog_update_hrtimer_threshold(sample_period); } static void update_report_ts(void) { __this_cpu_write(watchdog_report_ts, get_timestamp()); } /* Commands for resetting the watchdog */ static void update_touch_ts(void) { __this_cpu_write(watchdog_touch_ts, get_timestamp()); update_report_ts(); } /** * touch_softlockup_watchdog_sched - touch watchdog on scheduler stalls * * Call when the scheduler may have stalled for legitimate reasons * preventing the watchdog task from executing - e.g. the scheduler * entering idle state. This should only be used for scheduler events. * Use touch_softlockup_watchdog() for everything else. */ notrace void touch_softlockup_watchdog_sched(void) { /* * Preemption can be enabled. It doesn't matter which CPU's watchdog * report period gets restarted here, so use the raw_ operation. */ raw_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT); } notrace void touch_softlockup_watchdog(void) { touch_softlockup_watchdog_sched(); wq_watchdog_touch(raw_smp_processor_id()); } EXPORT_SYMBOL(touch_softlockup_watchdog); void touch_all_softlockup_watchdogs(void) { int cpu; /* * watchdog_mutex cannpt be taken here, as this might be called * from (soft)interrupt context, so the access to * watchdog_allowed_cpumask might race with a concurrent update. * * The watchdog time stamp can race against a concurrent real * update as well, the only side effect might be a cycle delay for * the softlockup check. */ for_each_cpu(cpu, &watchdog_allowed_mask) { per_cpu(watchdog_report_ts, cpu) = SOFTLOCKUP_DELAY_REPORT; wq_watchdog_touch(cpu); } } void touch_softlockup_watchdog_sync(void) { __this_cpu_write(softlockup_touch_sync, true); __this_cpu_write(watchdog_report_ts, SOFTLOCKUP_DELAY_REPORT); } static int is_softlockup(unsigned long touch_ts, unsigned long period_ts, unsigned long now) { if ((watchdog_enabled & WATCHDOG_SOFTOCKUP_ENABLED) && watchdog_thresh) { /* * If period_ts has not been updated during a sample_period, then * in the subsequent few sample_periods, period_ts might also not * be updated, which could indicate a potential softlockup. In * this case, if we suspect the cause of the potential softlockup * might be interrupt storm, then we need to count the interrupts * to find which interrupt is storming. */ if (time_after_eq(now, period_ts + get_softlockup_thresh() / NUM_SAMPLE_PERIODS) && need_counting_irqs()) start_counting_irqs(); /* * A poorly behaving BPF scheduler can live-lock the system into * soft lockups. Tell sched_ext to try ejecting the BPF * scheduler when close to a soft lockup. */ if (time_after_eq(now, period_ts + get_softlockup_thresh() * 3 / 4)) scx_softlockup(now - touch_ts); /* Warn about unreasonable delays. */ if (time_after(now, period_ts + get_softlockup_thresh())) return now - touch_ts; } return 0; } /* watchdog detector functions */ static DEFINE_PER_CPU(struct completion, softlockup_completion); static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); /* * The watchdog feed function - touches the timestamp. * * It only runs once every sample_period seconds (4 seconds by * default) to reset the softlockup timestamp. If this gets delayed * for more than 2*watchdog_thresh seconds then the debug-printout * triggers in watchdog_timer_fn(). */ static int softlockup_fn(void *data) { update_touch_ts(); stop_counting_irqs(); complete(this_cpu_ptr(&softlockup_completion)); return 0; } /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { unsigned long touch_ts, period_ts, now; struct pt_regs *regs = get_irq_regs(); int softlockup_all_cpu_backtrace; int duration, thresh_count; unsigned long flags; if (!watchdog_enabled) return HRTIMER_NORESTART; /* * pass the buddy check if a panic is in process */ if (panic_in_progress()) return HRTIMER_NORESTART; softlockup_all_cpu_backtrace = (softlockup_si_mask & SYS_INFO_ALL_BT) ? 1 : sysctl_softlockup_all_cpu_backtrace; watchdog_hardlockup_kick(); /* kick the softlockup detector */ if (completion_done(this_cpu_ptr(&softlockup_completion))) { reinit_completion(this_cpu_ptr(&softlockup_completion)); stop_one_cpu_nowait(smp_processor_id(), softlockup_fn, NULL, this_cpu_ptr(&softlockup_stop_work)); } /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); /* * Read the current timestamp first. It might become invalid anytime * when a virtual machine is stopped by the host or when the watchog * is touched from NMI. */ now = get_timestamp(); /* * If a virtual machine is stopped by the host it can look to * the watchdog like a soft lockup. This function touches the watchdog. */ kvm_check_and_clear_guest_paused(); /* * The stored timestamp is comparable with @now only when not touched. * It might get touched anytime from NMI. Make sure that is_softlockup() * uses the same (valid) value. */ period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts)); update_cpustat(); /* Reset the interval when touched by known problematic code. */ if (period_ts == SOFTLOCKUP_DELAY_REPORT) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically * make sure the scheduler tick is up to date. */ __this_cpu_write(softlockup_touch_sync, false); sched_clock_tick(); } update_report_ts(); return HRTIMER_RESTART; } /* Check for a softlockup. */ touch_ts = __this_cpu_read(watchdog_touch_ts); duration = is_softlockup(touch_ts, period_ts, now); if (unlikely(duration)) { #ifdef CONFIG_SYSFS ++softlockup_count; #endif /* * Prevent multiple soft-lockup reports if one cpu is already * engaged in dumping all cpu back traces. */ if (softlockup_all_cpu_backtrace) { if (test_and_set_bit_lock(0, &soft_lockup_nmi_warn)) return HRTIMER_RESTART; } /* Start period for the next softlockup warning. */ update_report_ts(); printk_cpu_sync_get_irqsave(flags); pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); report_cpu_status(); print_modules(); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); printk_cpu_sync_put_irqrestore(flags); if (softlockup_all_cpu_backtrace) { trigger_allbutcpu_cpu_backtrace(smp_processor_id()); if (!softlockup_panic) clear_bit_unlock(0, &soft_lockup_nmi_warn); } add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); sys_info(softlockup_si_mask & ~SYS_INFO_ALL_BT); thresh_count = duration / get_softlockup_thresh(); if (softlockup_panic && thresh_count >= softlockup_panic) panic("softlockup: hung tasks"); } return HRTIMER_RESTART; } static void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); struct completion *done = this_cpu_ptr(&softlockup_completion); WARN_ON_ONCE(cpu != smp_processor_id()); init_completion(done); complete(done); /* * Start the timer first to prevent the hardlockup watchdog triggering * before the timer has a chance to fire. */ hrtimer_setup(hrtimer, watchdog_timer_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED_HARD); /* Initialize timestamp */ update_touch_ts(); /* Enable the hardlockup detector */ if (watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED) watchdog_hardlockup_enable(cpu); } static void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); WARN_ON_ONCE(cpu != smp_processor_id()); /* * Disable the hardlockup detector first. That prevents that a large * delay between disabling the timer and disabling the hardlockup * detector causes a false positive. */ watchdog_hardlockup_disable(cpu); hrtimer_cancel(hrtimer); wait_for_completion(this_cpu_ptr(&softlockup_completion)); } static int softlockup_stop_fn(void *data) { watchdog_disable(smp_processor_id()); return 0; } static void softlockup_stop_all(void) { int cpu; if (!softlockup_initialized) return; for_each_cpu(cpu, &watchdog_allowed_mask) smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false); cpumask_clear(&watchdog_allowed_mask); } static int softlockup_start_fn(void *data) { watchdog_enable(smp_processor_id()); return 0; } static void softlockup_start_all(void) { int cpu; cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); for_each_cpu(cpu, &watchdog_allowed_mask) smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false); } int lockup_detector_online_cpu(unsigned int cpu) { if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) watchdog_enable(cpu); return 0; } int lockup_detector_offline_cpu(unsigned int cpu) { if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) watchdog_disable(cpu); return 0; } static void __lockup_detector_reconfigure(bool thresh_changed) { cpus_read_lock(); watchdog_hardlockup_stop(); softlockup_stop_all(); /* * To prevent watchdog_timer_fn from using the old interval and * the new watchdog_thresh at the same time, which could lead to * false softlockup reports, it is necessary to update the * watchdog_thresh after the softlockup is completed. */ if (thresh_changed) watchdog_thresh = READ_ONCE(watchdog_thresh_next); set_sample_period(); lockup_detector_update_enable(); if (watchdog_enabled && watchdog_thresh) softlockup_start_all(); watchdog_hardlockup_start(); cpus_read_unlock(); } void lockup_detector_reconfigure(void) { mutex_lock(&watchdog_mutex); __lockup_detector_reconfigure(false); mutex_unlock(&watchdog_mutex); } /* * Create the watchdog infrastructure and configure the detector(s). */ static __init void lockup_detector_setup(void) { /* * If sysctl is off and watchdog got disabled on the command line, * nothing to do here. */ lockup_detector_update_enable(); if (!IS_ENABLED(CONFIG_SYSCTL) && !(watchdog_enabled && watchdog_thresh)) return; mutex_lock(&watchdog_mutex); __lockup_detector_reconfigure(false); softlockup_initialized = true; mutex_unlock(&watchdog_mutex); } #else /* CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_reconfigure(bool thresh_changed) { cpus_read_lock(); watchdog_hardlockup_stop(); if (thresh_changed) watchdog_thresh = READ_ONCE(watchdog_thresh_next); lockup_detector_update_enable(); watchdog_hardlockup_start(); cpus_read_unlock(); } void lockup_detector_reconfigure(void) { __lockup_detector_reconfigure(false); } static inline void lockup_detector_setup(void) { __lockup_detector_reconfigure(false); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ /** * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) * * Special interface for parisc. It prevents lockup detector warnings from * the default pm_poweroff() function which busy loops forever. */ void lockup_detector_soft_poweroff(void) { watchdog_enabled = 0; } #ifdef CONFIG_SYSCTL /* Propagate any changes to the watchdog infrastructure */ static void proc_watchdog_update(bool thresh_changed) { /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); __lockup_detector_reconfigure(thresh_changed); } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * * caller | table->data points to | 'which' * -------------------|----------------------------------|------------------------------- * proc_watchdog | watchdog_user_enabled | WATCHDOG_HARDLOCKUP_ENABLED | * | | WATCHDOG_SOFTOCKUP_ENABLED * -------------------|----------------------------------|------------------------------- * proc_nmi_watchdog | watchdog_hardlockup_user_enabled | WATCHDOG_HARDLOCKUP_ENABLED * -------------------|----------------------------------|------------------------------- * proc_soft_watchdog | watchdog_softlockup_user_enabled | WATCHDOG_SOFTOCKUP_ENABLED */ static int proc_watchdog_common(int which, const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err, old, *param = table->data; mutex_lock(&watchdog_mutex); old = *param; if (!write) { /* * On read synchronize the userspace interface. This is a * racy snapshot. */ *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); *param = old; } else { err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!err && old != READ_ONCE(*param)) proc_watchdog_update(false); } mutex_unlock(&watchdog_mutex); return err; } /* * /proc/sys/kernel/watchdog */ static int proc_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED | WATCHDOG_SOFTOCKUP_ENABLED, table, write, buffer, lenp, ppos); } /* * /proc/sys/kernel/nmi_watchdog */ static int proc_nmi_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { if (!watchdog_hardlockup_available && write) return -ENOTSUPP; return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED, table, write, buffer, lenp, ppos); } #ifdef CONFIG_SOFTLOCKUP_DETECTOR /* * /proc/sys/kernel/soft_watchdog */ static int proc_soft_watchdog(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(WATCHDOG_SOFTOCKUP_ENABLED, table, write, buffer, lenp, ppos); } #endif /* * /proc/sys/kernel/watchdog_thresh */ static int proc_watchdog_thresh(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err, old; mutex_lock(&watchdog_mutex); watchdog_thresh_next = READ_ONCE(watchdog_thresh); old = watchdog_thresh_next; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!err && write && old != READ_ONCE(watchdog_thresh_next)) proc_watchdog_update(true); mutex_unlock(&watchdog_mutex); return err; } /* * The cpumask is the mask of possible cpus that the watchdog can run * on, not the mask of cpus it is actually running on. This allows the * user to specify a mask that will include cpus that have not yet * been brought online, if desired. */ static int proc_watchdog_cpumask(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int err; mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); if (!err && write) proc_watchdog_update(false); mutex_unlock(&watchdog_mutex); return err; } static const int sixty = 60; static const struct ctl_table watchdog_sysctls[] = { { .procname = "watchdog", .data = &watchdog_user_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_watchdog, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "watchdog_thresh", .data = &watchdog_thresh_next, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_watchdog_thresh, .extra1 = SYSCTL_ZERO, .extra2 = (void *)&sixty, }, { .procname = "watchdog_cpumask", .data = &watchdog_cpumask_bits, .maxlen = NR_CPUS, .mode = 0644, .proc_handler = proc_watchdog_cpumask, }, #ifdef CONFIG_SOFTLOCKUP_DETECTOR { .procname = "soft_watchdog", .data = &watchdog_softlockup_user_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_soft_watchdog, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "softlockup_panic", .data = &softlockup_panic, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_INT_MAX, }, { .procname = "softlockup_sys_info", .data = &softlockup_si_mask, .maxlen = sizeof(softlockup_si_mask), .mode = 0644, .proc_handler = sysctl_sys_info_handler, }, #ifdef CONFIG_SMP { .procname = "softlockup_all_cpu_backtrace", .data = &sysctl_softlockup_all_cpu_backtrace, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif /* CONFIG_SMP */ #endif #ifdef CONFIG_HARDLOCKUP_DETECTOR { .procname = "hardlockup_panic", .data = &hardlockup_panic, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "hardlockup_sys_info", .data = &hardlockup_si_mask, .maxlen = sizeof(hardlockup_si_mask), .mode = 0644, .proc_handler = sysctl_sys_info_handler, }, #ifdef CONFIG_SMP { .procname = "hardlockup_all_cpu_backtrace", .data = &sysctl_hardlockup_all_cpu_backtrace, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, #endif /* CONFIG_SMP */ #endif { .procname = "nmi_watchdog", .data = &watchdog_hardlockup_user_enabled, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_nmi_watchdog, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, }; static void __init watchdog_sysctl_init(void) { register_sysctl_init("kernel", watchdog_sysctls); } #else #define watchdog_sysctl_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static void __init lockup_detector_delay_init(struct work_struct *work); static bool allow_lockup_detector_init_retry __initdata; static struct work_struct detector_work __initdata = __WORK_INITIALIZER(detector_work, lockup_detector_delay_init); static void __init lockup_detector_delay_init(struct work_struct *work) { int ret; ret = watchdog_hardlockup_probe(); if (ret) { if (ret == -ENODEV) pr_info("NMI not fully supported\n"); else pr_info("Delayed init of the lockup detector failed: %d\n", ret); pr_info("Hard watchdog permanently disabled\n"); return; } allow_lockup_detector_init_retry = false; watchdog_hardlockup_available = true; lockup_detector_setup(); } /* * lockup_detector_retry_init - retry init lockup detector if possible. * * Retry hardlockup detector init. It is useful when it requires some * functionality that has to be initialized later on a particular * platform. */ void __init lockup_detector_retry_init(void) { /* Must be called before late init calls */ if (!allow_lockup_detector_init_retry) return; schedule_work(&detector_work); } /* * Ensure that optional delayed hardlockup init is proceed before * the init code and memory is freed. */ static int __init lockup_detector_check(void) { /* Prevent any later retry. */ allow_lockup_detector_init_retry = false; /* Make sure no work is pending. */ flush_work(&detector_work); watchdog_sysctl_init(); return 0; } late_initcall_sync(lockup_detector_check); void __init lockup_detector_init(void) { if (tick_nohz_full_enabled()) pr_info("Disabling watchdog on nohz_full cores by default\n"); cpumask_copy(&watchdog_cpumask, housekeeping_cpumask(HK_TYPE_TIMER)); if (!watchdog_hardlockup_probe()) watchdog_hardlockup_available = true; else allow_lockup_detector_init_retry = true; lockup_detector_setup(); } |
| 2330 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 | // SPDX-License-Identifier: GPL-2.0 /* * This is a maximally equidistributed combined Tausworthe generator * based on code from GNU Scientific Library 1.5 (30 Jun 2004) * * lfsr113 version: * * x_n = (s1_n ^ s2_n ^ s3_n ^ s4_n) * * s1_{n+1} = (((s1_n & 4294967294) << 18) ^ (((s1_n << 6) ^ s1_n) >> 13)) * s2_{n+1} = (((s2_n & 4294967288) << 2) ^ (((s2_n << 2) ^ s2_n) >> 27)) * s3_{n+1} = (((s3_n & 4294967280) << 7) ^ (((s3_n << 13) ^ s3_n) >> 21)) * s4_{n+1} = (((s4_n & 4294967168) << 13) ^ (((s4_n << 3) ^ s4_n) >> 12)) * * The period of this generator is about 2^113 (see erratum paper). * * From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe * Generators", Mathematics of Computation, 65, 213 (1996), 203--213: * http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps * ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps * * There is an erratum in the paper "Tables of Maximally Equidistributed * Combined LFSR Generators", Mathematics of Computation, 68, 225 (1999), * 261--269: http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps * * ... the k_j most significant bits of z_j must be non-zero, * for each j. (Note: this restriction also applies to the * computer code given in [4], but was mistakenly not mentioned * in that paper.) * * This affects the seeding procedure by imposing the requirement * s1 > 1, s2 > 7, s3 > 15, s4 > 127. */ #include <linux/types.h> #include <linux/percpu.h> #include <linux/export.h> #include <linux/jiffies.h> #include <linux/prandom.h> #include <linux/sched.h> #include <linux/bitops.h> #include <linux/slab.h> #include <linux/unaligned.h> /** * prandom_u32_state - seeded pseudo-random number generator. * @state: pointer to state structure holding seeded state. * * This is used for pseudo-randomness with no outside seeding. * For more random results, use get_random_u32(). */ u32 prandom_u32_state(struct rnd_state *state) { #define TAUSWORTHE(s, a, b, c, d) ((s & c) << d) ^ (((s << a) ^ s) >> b) state->s1 = TAUSWORTHE(state->s1, 6U, 13U, 4294967294U, 18U); state->s2 = TAUSWORTHE(state->s2, 2U, 27U, 4294967288U, 2U); state->s3 = TAUSWORTHE(state->s3, 13U, 21U, 4294967280U, 7U); state->s4 = TAUSWORTHE(state->s4, 3U, 12U, 4294967168U, 13U); return (state->s1 ^ state->s2 ^ state->s3 ^ state->s4); } EXPORT_SYMBOL(prandom_u32_state); /** * prandom_bytes_state - get the requested number of pseudo-random bytes * * @state: pointer to state structure holding seeded state. * @buf: where to copy the pseudo-random bytes to * @bytes: the requested number of bytes * * This is used for pseudo-randomness with no outside seeding. * For more random results, use get_random_bytes(). */ void prandom_bytes_state(struct rnd_state *state, void *buf, size_t bytes) { u8 *ptr = buf; while (bytes >= sizeof(u32)) { put_unaligned(prandom_u32_state(state), (u32 *) ptr); ptr += sizeof(u32); bytes -= sizeof(u32); } if (bytes > 0) { u32 rem = prandom_u32_state(state); do { *ptr++ = (u8) rem; bytes--; rem >>= BITS_PER_BYTE; } while (bytes > 0); } } EXPORT_SYMBOL(prandom_bytes_state); static void prandom_warmup(struct rnd_state *state) { /* Calling RNG ten times to satisfy recurrence condition */ prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); prandom_u32_state(state); } void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state) { int i; for_each_possible_cpu(i) { struct rnd_state *state = per_cpu_ptr(pcpu_state, i); u32 seeds[4]; get_random_bytes(&seeds, sizeof(seeds)); state->s1 = __seed(seeds[0], 2U); state->s2 = __seed(seeds[1], 8U); state->s3 = __seed(seeds[2], 16U); state->s4 = __seed(seeds[3], 128U); prandom_warmup(state); } } EXPORT_SYMBOL(prandom_seed_full_state); #ifdef CONFIG_RANDOM32_SELFTEST static struct prandom_test1 { u32 seed; u32 result; } test1[] = { { 1U, 3484351685U }, { 2U, 2623130059U }, { 3U, 3125133893U }, { 4U, 984847254U }, }; static struct prandom_test2 { u32 seed; u32 iteration; u32 result; } test2[] = { /* Test cases against taus113 from GSL library. */ { 931557656U, 959U, 2975593782U }, { 1339693295U, 876U, 3887776532U }, { 1545556285U, 961U, 1615538833U }, { 601730776U, 723U, 1776162651U }, { 1027516047U, 687U, 511983079U }, { 416526298U, 700U, 916156552U }, { 1395522032U, 652U, 2222063676U }, { 366221443U, 617U, 2992857763U }, { 1539836965U, 714U, 3783265725U }, { 556206671U, 994U, 799626459U }, { 684907218U, 799U, 367789491U }, { 2121230701U, 931U, 2115467001U }, { 1668516451U, 644U, 3620590685U }, { 768046066U, 883U, 2034077390U }, { 1989159136U, 833U, 1195767305U }, { 536585145U, 996U, 3577259204U }, { 1008129373U, 642U, 1478080776U }, { 1740775604U, 939U, 1264980372U }, { 1967883163U, 508U, 10734624U }, { 1923019697U, 730U, 3821419629U }, { 442079932U, 560U, 3440032343U }, { 1961302714U, 845U, 841962572U }, { 2030205964U, 962U, 1325144227U }, { 1160407529U, 507U, 240940858U }, { 635482502U, 779U, 4200489746U }, { 1252788931U, 699U, 867195434U }, { 1961817131U, 719U, 668237657U }, { 1071468216U, 983U, 917876630U }, { 1281848367U, 932U, 1003100039U }, { 582537119U, 780U, 1127273778U }, { 1973672777U, 853U, 1071368872U }, { 1896756996U, 762U, 1127851055U }, { 847917054U, 500U, 1717499075U }, { 1240520510U, 951U, 2849576657U }, { 1685071682U, 567U, 1961810396U }, { 1516232129U, 557U, 3173877U }, { 1208118903U, 612U, 1613145022U }, { 1817269927U, 693U, 4279122573U }, { 1510091701U, 717U, 638191229U }, { 365916850U, 807U, 600424314U }, { 399324359U, 702U, 1803598116U }, { 1318480274U, 779U, 2074237022U }, { 697758115U, 840U, 1483639402U }, { 1696507773U, 840U, 577415447U }, { 2081979121U, 981U, 3041486449U }, { 955646687U, 742U, 3846494357U }, { 1250683506U, 749U, 836419859U }, { 595003102U, 534U, 366794109U }, { 47485338U, 558U, 3521120834U }, { 619433479U, 610U, 3991783875U }, { 704096520U, 518U, 4139493852U }, { 1712224984U, 606U, 2393312003U }, { 1318233152U, 922U, 3880361134U }, { 855572992U, 761U, 1472974787U }, { 64721421U, 703U, 683860550U }, { 678931758U, 840U, 380616043U }, { 692711973U, 778U, 1382361947U }, { 677703619U, 530U, 2826914161U }, { 92393223U, 586U, 1522128471U }, { 1222592920U, 743U, 3466726667U }, { 358288986U, 695U, 1091956998U }, { 1935056945U, 958U, 514864477U }, { 735675993U, 990U, 1294239989U }, { 1560089402U, 897U, 2238551287U }, { 70616361U, 829U, 22483098U }, { 368234700U, 731U, 2913875084U }, { 20221190U, 879U, 1564152970U }, { 539444654U, 682U, 1835141259U }, { 1314987297U, 840U, 1801114136U }, { 2019295544U, 645U, 3286438930U }, { 469023838U, 716U, 1637918202U }, { 1843754496U, 653U, 2562092152U }, { 400672036U, 809U, 4264212785U }, { 404722249U, 965U, 2704116999U }, { 600702209U, 758U, 584979986U }, { 519953954U, 667U, 2574436237U }, { 1658071126U, 694U, 2214569490U }, { 420480037U, 749U, 3430010866U }, { 690103647U, 969U, 3700758083U }, { 1029424799U, 937U, 3787746841U }, { 2012608669U, 506U, 3362628973U }, { 1535432887U, 998U, 42610943U }, { 1330635533U, 857U, 3040806504U }, { 1223800550U, 539U, 3954229517U }, { 1322411537U, 680U, 3223250324U }, { 1877847898U, 945U, 2915147143U }, { 1646356099U, 874U, 965988280U }, { 805687536U, 744U, 4032277920U }, { 1948093210U, 633U, 1346597684U }, { 392609744U, 783U, 1636083295U }, { 690241304U, 770U, 1201031298U }, { 1360302965U, 696U, 1665394461U }, { 1220090946U, 780U, 1316922812U }, { 447092251U, 500U, 3438743375U }, { 1613868791U, 592U, 828546883U }, { 523430951U, 548U, 2552392304U }, { 726692899U, 810U, 1656872867U }, { 1364340021U, 836U, 3710513486U }, { 1986257729U, 931U, 935013962U }, { 407983964U, 921U, 728767059U }, }; static void prandom_state_selftest_seed(struct rnd_state *state, u32 seed) { #define LCG(x) ((x) * 69069U) /* super-duper LCG */ state->s1 = __seed(LCG(seed), 2U); state->s2 = __seed(LCG(state->s1), 8U); state->s3 = __seed(LCG(state->s2), 16U); state->s4 = __seed(LCG(state->s3), 128U); } static int __init prandom_state_selftest(void) { int i, j, errors = 0, runs = 0; bool error = false; for (i = 0; i < ARRAY_SIZE(test1); i++) { struct rnd_state state; prandom_state_selftest_seed(&state, test1[i].seed); prandom_warmup(&state); if (test1[i].result != prandom_u32_state(&state)) error = true; } if (error) pr_warn("prandom: seed boundary self test failed\n"); else pr_info("prandom: seed boundary self test passed\n"); for (i = 0; i < ARRAY_SIZE(test2); i++) { struct rnd_state state; prandom_state_selftest_seed(&state, test2[i].seed); prandom_warmup(&state); for (j = 0; j < test2[i].iteration - 1; j++) prandom_u32_state(&state); if (test2[i].result != prandom_u32_state(&state)) errors++; runs++; cond_resched(); } if (errors) pr_warn("prandom: %d/%d self tests failed\n", errors, runs); else pr_info("prandom: %d self tests passed\n", runs); return 0; } core_initcall(prandom_state_selftest); #endif |
| 3983 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * RCU-based infrastructure for lightweight reader-writer locking * * Copyright (c) 2015, Red Hat, Inc. * * Author: Oleg Nesterov <oleg@redhat.com> */ #ifndef _LINUX_RCU_SYNC_H_ #define _LINUX_RCU_SYNC_H_ #include <linux/wait.h> #include <linux/rcupdate.h> /* Structure to mediate between updaters and fastpath-using readers. */ struct rcu_sync { int gp_state; int gp_count; wait_queue_head_t gp_wait; struct rcu_head cb_head; }; /** * rcu_sync_is_idle() - Are readers permitted to use their fastpaths? * @rsp: Pointer to rcu_sync structure to use for synchronization * * Returns true if readers are permitted to use their fastpaths. Must be * invoked within some flavor of RCU read-side critical section. */ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) { RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), "suspicious rcu_sync_is_idle() usage"); return !READ_ONCE(rsp->gp_state); /* GP_IDLE */ } extern void rcu_sync_init(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); #define __RCU_SYNC_INITIALIZER(name) { \ .gp_state = 0, \ .gp_count = 0, \ .gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait), \ } #define DEFINE_RCU_SYNC(name) \ struct rcu_sync name = __RCU_SYNC_INITIALIZER(name) #endif /* _LINUX_RCU_SYNC_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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __PSP_PSP_H #define __PSP_PSP_H #include <linux/list.h> #include <linux/lockdep.h> #include <linux/mutex.h> #include <net/netns/generic.h> #include <net/psp.h> #include <net/sock.h> extern struct xarray psp_devs; extern struct mutex psp_devs_lock; void psp_dev_free(struct psp_dev *psd); int psp_dev_check_access(struct psp_dev *psd, struct net *net); void psp_nl_notify_dev(struct psp_dev *psd, u32 cmd); struct psp_assoc *psp_assoc_create(struct psp_dev *psd); struct psp_dev *psp_dev_get_for_sock(struct sock *sk); void psp_dev_tx_key_del(struct psp_dev *psd, struct psp_assoc *pas); int psp_sock_assoc_set_rx(struct sock *sk, struct psp_assoc *pas, struct psp_key_parsed *key, struct netlink_ext_ack *extack); int psp_sock_assoc_set_tx(struct sock *sk, struct psp_dev *psd, u32 version, struct psp_key_parsed *key, struct netlink_ext_ack *extack); void psp_assocs_key_rotated(struct psp_dev *psd); static inline void psp_dev_get(struct psp_dev *psd) { refcount_inc(&psd->refcnt); } static inline bool psp_dev_tryget(struct psp_dev *psd) { return refcount_inc_not_zero(&psd->refcnt); } static inline void psp_dev_put(struct psp_dev *psd) { if (refcount_dec_and_test(&psd->refcnt)) psp_dev_free(psd); } static inline bool psp_dev_is_registered(struct psp_dev *psd) { lockdep_assert_held(&psd->lock); return !!psd->ops; } #endif /* __PSP_PSP_H */ |
| 195 271 144 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> #include <linux/fs_struct.h> enum { MAX_NESTED_LINKS = 8 }; #define MAXSYMLINKS 40 /* * Type of the last component on LOOKUP_PARENT */ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ #define LOOKUP_FOLLOW BIT(0) /* follow links at the end */ #define LOOKUP_DIRECTORY BIT(1) /* require a directory */ #define LOOKUP_AUTOMOUNT BIT(2) /* force terminal automount */ #define LOOKUP_EMPTY BIT(3) /* accept empty path [user_... only] */ #define LOOKUP_LINKAT_EMPTY BIT(4) /* Linkat request with empty path. */ #define LOOKUP_DOWN BIT(5) /* follow mounts in the starting point */ #define LOOKUP_MOUNTPOINT BIT(6) /* follow mounts in the end */ #define LOOKUP_REVAL BIT(7) /* tell ->d_revalidate() to trust no cache */ #define LOOKUP_RCU BIT(8) /* RCU pathwalk mode; semi-internal */ #define LOOKUP_CACHED BIT(9) /* Only do cached lookup */ #define LOOKUP_PARENT BIT(10) /* Looking up final parent in path */ /* 5 spare bits for pathwalk */ /* These tell filesystem methods that we are dealing with the final component... */ #define LOOKUP_OPEN BIT(16) /* ... in open */ #define LOOKUP_CREATE BIT(17) /* ... in object creation */ #define LOOKUP_EXCL BIT(18) /* ... in target must not exist */ #define LOOKUP_RENAME_TARGET BIT(19) /* ... in destination of rename() */ /* 4 spare bits for intent */ /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS BIT(24) /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS BIT(25) /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV BIT(26) /* No mountpoint crossing. */ #define LOOKUP_BENEATH BIT(27) /* No escaping from starting point. */ #define LOOKUP_IN_ROOT BIT(28) /* Treat dirfd as fs root. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) /* 3 spare bits for scoping */ extern int path_pts(struct path *path); extern int user_path_at(int, const char __user *, unsigned, struct path *); extern int kern_path(const char *, unsigned, struct path *); struct dentry *kern_path_parent(const char *name, struct path *parent); extern struct dentry *start_creating_path(int, const char *, struct path *, unsigned int); extern struct dentry *start_creating_user_path(int, const char __user *, struct path *, unsigned int); extern void end_creating_path(const struct path *, struct dentry *); extern struct dentry *start_removing_path(const char *, struct path *); extern struct dentry *start_removing_user_path_at(int , const char __user *, struct path *); static inline void end_removing_path(const struct path *path , struct dentry *dentry) { end_creating_path(path, dentry); } int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *try_lookup_noperm(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm_unlocked(struct qstr *, struct dentry *); extern struct dentry *lookup_noperm_positive_unlocked(struct qstr *, struct dentry *); struct dentry *lookup_one(struct mnt_idmap *, struct qstr *, struct dentry *); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); struct dentry *start_creating(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_removing(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_creating_killable(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_removing_killable(struct mnt_idmap *idmap, struct dentry *parent, struct qstr *name); struct dentry *start_creating_noperm(struct dentry *parent, struct qstr *name); struct dentry *start_removing_noperm(struct dentry *parent, struct qstr *name); struct dentry *start_creating_dentry(struct dentry *parent, struct dentry *child); struct dentry *start_removing_dentry(struct dentry *parent, struct dentry *child); /* end_creating - finish action started with start_creating * @child: dentry returned by start_creating() or vfs_mkdir() * * Unlock and release the child. This can be called after * start_creating() whether that function succeeded or not, * but it is not needed on failure. * * If vfs_mkdir() was called then the value returned from that function * should be given for @child rather than the original dentry, as vfs_mkdir() * may have provided a new dentry. * * * If vfs_mkdir() was not called, then @child will be a valid dentry and * @parent will be ignored. */ static inline void end_creating(struct dentry *child) { end_dirop(child); } /* end_creating_keep - finish action started with start_creating() and return result * @child: dentry returned by start_creating() or vfs_mkdir() * * Unlock and return the child. This can be called after * start_creating() whether that function succeeded or not, * but it is not needed on failure. * * If vfs_mkdir() was called then the value returned from that function * should be given for @child rather than the original dentry, as vfs_mkdir() * may have provided a new dentry. * * Returns: @child, which may be a dentry or an error. * */ static inline struct dentry *end_creating_keep(struct dentry *child) { if (!IS_ERR(child)) dget(child); end_dirop(child); return child; } /** * end_removing - finish action started with start_removing * @child: dentry returned by start_removing() * @parent: dentry given to start_removing() * * Unlock and release the child. * * This is identical to end_dirop(). It can be passed the result of * start_removing() whether that was successful or not, but it not needed * if start_removing() failed. */ static inline void end_removing(struct dentry *child) { end_dirop(child); } extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); int start_renaming(struct renamedata *rd, int lookup_flags, struct qstr *old_last, struct qstr *new_last); int start_renaming_dentry(struct renamedata *rd, int lookup_flags, struct dentry *old_dentry, struct qstr *new_last); int start_renaming_two_dentries(struct renamedata *rd, struct dentry *old_dentry, struct dentry *new_dentry); void end_renaming(struct renamedata *rd); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * In most filesystems, umask stripping depends on whether or not the * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask * stripping is done directly in here. If the filesystem does support POSIX * ACLs umask stripping is deferred until the filesystem calls * posix_acl_create(). * * Some filesystems (like NFSv4) also want to avoid umask stripping by the * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK * to get this effect without declaring that they support POSIX ACLs. * * Returns: mode */ static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) mode &= ~current_umask(); return mode; } extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { ((char *) name)[min(len, maxlen)] = '\0'; } /** * retry_estale - determine whether the caller should retry an operation * @error: the error that would currently be returned * @flags: flags being used for next lookup attempt * * Check to see if the error code was -ESTALE, and then determine whether * to retry the call based on whether "flags" already has LOOKUP_REVAL set. * * Returns true if the caller should try the operation again. */ static inline bool retry_estale(const long error, const unsigned int flags) { return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_H */ |
| 31 31 12 10 12 399 11 12 12 12 12 10 10 10 13 11 12 12 12 11 9 11 10 9 11 11 11 1 9 10 9 10 10 10 10 10 11 11 11 12 11 11 11 11 12 12 12 12 12 11 11 12 12 12 12 11 1232 1235 399 357 116 397 11 11 10 11 11 11 11 10 12 12 12 12 12 12 11 10 1 1 1 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB /* * Copyright (c) 2005 Voltaire Inc. All rights reserved. * Copyright (c) 2002-2005, Network Appliance, Inc. All rights reserved. * Copyright (c) 1999-2019, Mellanox Technologies, Inc. All rights reserved. * Copyright (c) 2005-2006 Intel Corporation. All rights reserved. */ #include <linux/completion.h> #include <linux/in.h> #include <linux/in6.h> #include <linux/mutex.h> #include <linux/random.h> #include <linux/rbtree.h> #include <linux/igmp.h> #include <linux/xarray.h> #include <linux/inetdevice.h> #include <linux/slab.h> #include <linux/module.h> #include <net/route.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netevent.h> #include <net/tcp.h> #include <net/ipv6.h> #include <net/ip_fib.h> #include <net/ip6_route.h> #include <rdma/rdma_cm.h> #include <rdma/rdma_cm_ib.h> #include <rdma/rdma_netlink.h> #include <rdma/ib.h> #include <rdma/ib_cache.h> #include <rdma/ib_cm.h> #include <rdma/ib_sa.h> #include <rdma/iw_cm.h> #include "core_priv.h" #include "cma_priv.h" #include "cma_trace.h" MODULE_AUTHOR("Sean Hefty"); MODULE_DESCRIPTION("Generic RDMA CM Agent"); MODULE_LICENSE("Dual BSD/GPL"); #define CMA_CM_RESPONSE_TIMEOUT 20 #define CMA_MAX_CM_RETRIES 15 #define CMA_IBOE_PACKET_LIFETIME 16 #define CMA_PREFERRED_ROCE_GID_TYPE IB_GID_TYPE_ROCE_UDP_ENCAP static const char * const cma_events[] = { [RDMA_CM_EVENT_ADDR_RESOLVED] = "address resolved", [RDMA_CM_EVENT_ADDR_ERROR] = "address error", [RDMA_CM_EVENT_ROUTE_RESOLVED] = "route resolved ", [RDMA_CM_EVENT_ROUTE_ERROR] = "route error", [RDMA_CM_EVENT_CONNECT_REQUEST] = "connect request", [RDMA_CM_EVENT_CONNECT_RESPONSE] = "connect response", [RDMA_CM_EVENT_CONNECT_ERROR] = "connect error", [RDMA_CM_EVENT_UNREACHABLE] = "unreachable", [RDMA_CM_EVENT_REJECTED] = "rejected", [RDMA_CM_EVENT_ESTABLISHED] = "established", [RDMA_CM_EVENT_DISCONNECTED] = "disconnected", [RDMA_CM_EVENT_DEVICE_REMOVAL] = "device removal", [RDMA_CM_EVENT_MULTICAST_JOIN] = "multicast join", [RDMA_CM_EVENT_MULTICAST_ERROR] = "multicast error", [RDMA_CM_EVENT_ADDR_CHANGE] = "address change", [RDMA_CM_EVENT_TIMEWAIT_EXIT] = "timewait exit", }; static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type); static void cma_netevent_work_handler(struct work_struct *_work); const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event) { size_t index = event; return (index < ARRAY_SIZE(cma_events) && cma_events[index]) ? cma_events[index] : "unrecognized event"; } EXPORT_SYMBOL(rdma_event_msg); const char *__attribute_const__ rdma_reject_msg(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return ibcm_reject_msg(reason); if (rdma_protocol_iwarp(id->device, id->port_num)) return iwcm_reject_msg(reason); WARN_ON_ONCE(1); return "unrecognized transport"; } EXPORT_SYMBOL(rdma_reject_msg); /** * rdma_is_consumer_reject - return true if the consumer rejected the connect * request. * @id: Communication identifier that received the REJECT event. * @reason: Value returned in the REJECT event status field. */ static bool rdma_is_consumer_reject(struct rdma_cm_id *id, int reason) { if (rdma_ib_or_roce(id->device, id->port_num)) return reason == IB_CM_REJ_CONSUMER_DEFINED; if (rdma_protocol_iwarp(id->device, id->port_num)) return reason == -ECONNREFUSED; WARN_ON_ONCE(1); return false; } const void *rdma_consumer_reject_data(struct rdma_cm_id *id, struct rdma_cm_event *ev, u8 *data_len) { const void *p; if (rdma_is_consumer_reject(id, ev->status)) { *data_len = ev->param.conn.private_data_len; p = ev->param.conn.private_data; } else { *data_len = 0; p = NULL; } return p; } EXPORT_SYMBOL(rdma_consumer_reject_data); /** * rdma_iw_cm_id() - return the iw_cm_id pointer for this cm_id. * @id: Communication Identifier */ struct iw_cm_id *rdma_iw_cm_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); if (id->device->node_type == RDMA_NODE_RNIC) return id_priv->cm_id.iw; return NULL; } EXPORT_SYMBOL(rdma_iw_cm_id); static int cma_add_one(struct ib_device *device); static void cma_remove_one(struct ib_device *device, void *client_data); static struct ib_client cma_client = { .name = "cma", .add = cma_add_one, .remove = cma_remove_one }; static struct ib_sa_client sa_client; static LIST_HEAD(dev_list); static LIST_HEAD(listen_any_list); static DEFINE_MUTEX(lock); static struct rb_root id_table = RB_ROOT; /* Serialize operations of id_table tree */ static DEFINE_SPINLOCK(id_table_lock); static struct workqueue_struct *cma_wq; static unsigned int cma_pernet_id; struct cma_pernet { struct xarray tcp_ps; struct xarray udp_ps; struct xarray ipoib_ps; struct xarray ib_ps; }; static struct cma_pernet *cma_pernet(struct net *net) { return net_generic(net, cma_pernet_id); } static struct xarray *cma_pernet_xa(struct net *net, enum rdma_ucm_port_space ps) { struct cma_pernet *pernet = cma_pernet(net); switch (ps) { case RDMA_PS_TCP: return &pernet->tcp_ps; case RDMA_PS_UDP: return &pernet->udp_ps; case RDMA_PS_IPOIB: return &pernet->ipoib_ps; case RDMA_PS_IB: return &pernet->ib_ps; default: return NULL; } } struct id_table_entry { struct list_head id_list; struct rb_node rb_node; }; struct cma_device { struct list_head list; struct ib_device *device; struct completion comp; refcount_t refcount; struct list_head id_list; enum ib_gid_type *default_gid_type; u8 *default_roce_tos; }; struct rdma_bind_list { enum rdma_ucm_port_space ps; struct hlist_head owners; unsigned short port; }; static int cma_ps_alloc(struct net *net, enum rdma_ucm_port_space ps, struct rdma_bind_list *bind_list, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_insert(xa, snum, bind_list, GFP_KERNEL); } static struct rdma_bind_list *cma_ps_find(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); return xa_load(xa, snum); } static void cma_ps_remove(struct net *net, enum rdma_ucm_port_space ps, int snum) { struct xarray *xa = cma_pernet_xa(net, ps); xa_erase(xa, snum); } enum { CMA_OPTION_AFONLY, }; void cma_dev_get(struct cma_device *cma_dev) { refcount_inc(&cma_dev->refcount); } void cma_dev_put(struct cma_device *cma_dev) { if (refcount_dec_and_test(&cma_dev->refcount)) complete(&cma_dev->comp); } struct cma_device *cma_enum_devices_by_ibdev(cma_device_filter filter, void *cookie) { struct cma_device *cma_dev; struct cma_device *found_cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) if (filter(cma_dev->device, cookie)) { found_cma_dev = cma_dev; break; } if (found_cma_dev) cma_dev_get(found_cma_dev); mutex_unlock(&lock); return found_cma_dev; } int cma_get_default_gid_type(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_gid_type(struct cma_device *cma_dev, u32 port, enum ib_gid_type default_gid_type) { unsigned long supported_gids; if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; if (default_gid_type == IB_GID_TYPE_IB && rdma_protocol_roce_eth_encap(cma_dev->device, port)) default_gid_type = IB_GID_TYPE_ROCE; supported_gids = roce_gid_type_mask_support(cma_dev->device, port); if (!(supported_gids & 1 << default_gid_type)) return -EINVAL; cma_dev->default_gid_type[port - rdma_start_port(cma_dev->device)] = default_gid_type; return 0; } int cma_get_default_roce_tos(struct cma_device *cma_dev, u32 port) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; return cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)]; } int cma_set_default_roce_tos(struct cma_device *cma_dev, u32 port, u8 default_roce_tos) { if (!rdma_is_port_valid(cma_dev->device, port)) return -EINVAL; cma_dev->default_roce_tos[port - rdma_start_port(cma_dev->device)] = default_roce_tos; return 0; } struct ib_device *cma_get_ib_dev(struct cma_device *cma_dev) { return cma_dev->device; } /* * Device removal can occur at anytime, so we need extra handling to * serialize notifying the user of device removal with other callbacks. * We do this by disabling removal notification while a callback is in process, * and reporting it after the callback completes. */ struct cma_multicast { struct rdma_id_private *id_priv; union { struct ib_sa_multicast *sa_mc; struct { struct work_struct work; struct rdma_cm_event event; } iboe_join; }; struct list_head list; void *context; struct sockaddr_storage addr; u8 join_state; }; struct cma_work { struct work_struct work; struct rdma_id_private *id; enum rdma_cm_state old_state; enum rdma_cm_state new_state; struct rdma_cm_event event; }; union cma_ip_addr { struct in6_addr ip6; struct { __be32 pad[3]; __be32 addr; } ip4; }; struct cma_hdr { u8 cma_version; u8 ip_version; /* IP version: 7:4 */ __be16 port; union cma_ip_addr src_addr; union cma_ip_addr dst_addr; }; #define CMA_VERSION 0x00 struct cma_req_info { struct sockaddr_storage listen_addr_storage; struct sockaddr_storage src_addr_storage; struct ib_device *device; union ib_gid local_gid; __be64 service_id; int port; bool has_gid; u16 pkey; }; static int cma_comp_exch(struct rdma_id_private *id_priv, enum rdma_cm_state comp, enum rdma_cm_state exch) { unsigned long flags; int ret; /* * The FSM uses a funny double locking where state is protected by both * the handler_mutex and the spinlock. State is not allowed to change * to/from a handler_mutex protected value without also holding * handler_mutex. */ if (comp == RDMA_CM_CONNECT || exch == RDMA_CM_CONNECT) lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); if ((ret = (id_priv->state == comp))) id_priv->state = exch; spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } static inline u8 cma_get_ip_ver(const struct cma_hdr *hdr) { return hdr->ip_version >> 4; } static void cma_set_ip_ver(struct cma_hdr *hdr, u8 ip_ver) { hdr->ip_version = (ip_ver << 4) | (hdr->ip_version & 0xF); } static struct sockaddr *cma_src_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.src_addr; } static inline struct sockaddr *cma_dst_addr(struct rdma_id_private *id_priv) { return (struct sockaddr *)&id_priv->id.route.addr.dst_addr; } static int cma_igmp_send(struct net_device *ndev, union ib_gid *mgid, bool join) { struct in_device *in_dev = NULL; if (ndev) { rtnl_lock(); in_dev = __in_dev_get_rtnl(ndev); if (in_dev) { if (join) ip_mc_inc_group(in_dev, *(__be32 *)(mgid->raw + 12)); else ip_mc_dec_group(in_dev, *(__be32 *)(mgid->raw + 12)); } rtnl_unlock(); } return (in_dev) ? 0 : -ENODEV; } static int compare_netdev_and_ip(int ifindex_a, struct sockaddr *sa, struct id_table_entry *entry_b) { struct rdma_id_private *id_priv = list_first_entry( &entry_b->id_list, struct rdma_id_private, id_list_entry); int ifindex_b = id_priv->id.route.addr.dev_addr.bound_dev_if; struct sockaddr *sb = cma_dst_addr(id_priv); if (ifindex_a != ifindex_b) return (ifindex_a > ifindex_b) ? 1 : -1; if (sa->sa_family != sb->sa_family) return sa->sa_family - sb->sa_family; if (sa->sa_family == AF_INET && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in)) { return memcmp(&((struct sockaddr_in *)sa)->sin_addr, &((struct sockaddr_in *)sb)->sin_addr, sizeof(((struct sockaddr_in *)sa)->sin_addr)); } if (sa->sa_family == AF_INET6 && __builtin_object_size(sa, 0) >= sizeof(struct sockaddr_in6)) { return ipv6_addr_cmp(&((struct sockaddr_in6 *)sa)->sin6_addr, &((struct sockaddr_in6 *)sb)->sin6_addr); } return -1; } static int cma_add_id_to_tree(struct rdma_id_private *node_id_priv) { struct rb_node **new, *parent = NULL; struct id_table_entry *this, *node; unsigned long flags; int result; node = kzalloc_obj(*node); if (!node) return -ENOMEM; spin_lock_irqsave(&id_table_lock, flags); new = &id_table.rb_node; while (*new) { this = container_of(*new, struct id_table_entry, rb_node); result = compare_netdev_and_ip( node_id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(node_id_priv), this); parent = *new; if (result < 0) new = &((*new)->rb_left); else if (result > 0) new = &((*new)->rb_right); else { list_add_tail(&node_id_priv->id_list_entry, &this->id_list); kfree(node); goto unlock; } } INIT_LIST_HEAD(&node->id_list); list_add_tail(&node_id_priv->id_list_entry, &node->id_list); rb_link_node(&node->rb_node, parent, new); rb_insert_color(&node->rb_node, &id_table); unlock: spin_unlock_irqrestore(&id_table_lock, flags); return 0; } static struct id_table_entry * node_from_ndev_ip(struct rb_root *root, int ifindex, struct sockaddr *sa) { struct rb_node *node = root->rb_node; struct id_table_entry *data; int result; while (node) { data = container_of(node, struct id_table_entry, rb_node); result = compare_netdev_and_ip(ifindex, sa, data); if (result < 0) node = node->rb_left; else if (result > 0) node = node->rb_right; else return data; } return NULL; } static void cma_remove_id_from_tree(struct rdma_id_private *id_priv) { struct id_table_entry *data; unsigned long flags; spin_lock_irqsave(&id_table_lock, flags); if (list_empty(&id_priv->id_list_entry)) goto out; data = node_from_ndev_ip(&id_table, id_priv->id.route.addr.dev_addr.bound_dev_if, cma_dst_addr(id_priv)); if (!data) goto out; list_del_init(&id_priv->id_list_entry); if (list_empty(&data->id_list)) { rb_erase(&data->rb_node, &id_table); kfree(data); } out: spin_unlock_irqrestore(&id_table_lock, flags); } static void _cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { cma_dev_get(cma_dev); id_priv->cma_dev = cma_dev; id_priv->id.device = cma_dev->device; id_priv->id.route.addr.dev_addr.transport = rdma_node_get_transport(cma_dev->device->node_type); list_add_tail(&id_priv->device_item, &cma_dev->id_list); trace_cm_id_attach(id_priv, cma_dev->device); } static void cma_attach_to_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev) { _cma_attach_to_dev(id_priv, cma_dev); id_priv->gid_type = cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(cma_dev->device)]; } static void cma_release_dev(struct rdma_id_private *id_priv) { mutex_lock(&lock); list_del_init(&id_priv->device_item); cma_dev_put(id_priv->cma_dev); id_priv->cma_dev = NULL; id_priv->id.device = NULL; if (id_priv->id.route.addr.dev_addr.sgid_attr) { rdma_put_gid_attr(id_priv->id.route.addr.dev_addr.sgid_attr); id_priv->id.route.addr.dev_addr.sgid_attr = NULL; } mutex_unlock(&lock); } static inline unsigned short cma_family(struct rdma_id_private *id_priv) { return id_priv->id.route.addr.src_addr.ss_family; } static int cma_set_default_qkey(struct rdma_id_private *id_priv) { struct ib_sa_mcmember_rec rec; int ret = 0; switch (id_priv->id.ps) { case RDMA_PS_UDP: case RDMA_PS_IB: id_priv->qkey = RDMA_UDP_QKEY; break; case RDMA_PS_IPOIB: ib_addr_get_mgid(&id_priv->id.route.addr.dev_addr, &rec.mgid); ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num, &rec.mgid, &rec); if (!ret) id_priv->qkey = be32_to_cpu(rec.qkey); break; default: break; } return ret; } static int cma_set_qkey(struct rdma_id_private *id_priv, u32 qkey) { if (!qkey || (id_priv->qkey && (id_priv->qkey != qkey))) return -EINVAL; id_priv->qkey = qkey; return 0; } static void cma_translate_ib(struct sockaddr_ib *sib, struct rdma_dev_addr *dev_addr) { dev_addr->dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(dev_addr, (union ib_gid *) &sib->sib_addr); ib_addr_set_pkey(dev_addr, ntohs(sib->sib_pkey)); } static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_addr) { int ret; if (addr->sa_family != AF_IB) { ret = rdma_translate_ip(addr, dev_addr); } else { cma_translate_ib((struct sockaddr_ib *) addr, dev_addr); ret = 0; } return ret; } static const struct ib_gid_attr * cma_validate_port(struct ib_device *device, u32 port, enum ib_gid_type gid_type, union ib_gid *gid, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr = ERR_PTR(-ENODEV); int bound_if_index = dev_addr->bound_dev_if; int dev_type = dev_addr->dev_type; struct net_device *ndev = NULL; struct net_device *pdev = NULL; if (!rdma_dev_access_netns(device, id_priv->id.route.addr.dev_addr.net)) goto out; if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port)) goto out; if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port)) goto out; /* * For drivers that do not associate more than one net device with * their gid tables, such as iWARP drivers, it is sufficient to * return the first table entry. * * Other driver classes might be included in the future. */ if (rdma_protocol_iwarp(device, port)) { sgid_attr = rdma_get_gid_attr(device, port, 0); if (IS_ERR(sgid_attr)) goto out; rcu_read_lock(); ndev = rcu_dereference(sgid_attr->ndev); if (ndev->ifindex != bound_if_index) { pdev = dev_get_by_index_rcu(dev_addr->net, bound_if_index); if (pdev) { if (is_vlan_dev(pdev)) { pdev = vlan_dev_real_dev(pdev); if (ndev->ifindex == pdev->ifindex) bound_if_index = pdev->ifindex; } if (is_vlan_dev(ndev)) { pdev = vlan_dev_real_dev(ndev); if (bound_if_index == pdev->ifindex) bound_if_index = ndev->ifindex; } } } if (!net_eq(dev_net(ndev), dev_addr->net) || ndev->ifindex != bound_if_index) { rdma_put_gid_attr(sgid_attr); sgid_attr = ERR_PTR(-ENODEV); } rcu_read_unlock(); goto out; } /* * For a RXE device, it should work with TUN device and normal ethernet * devices. Use driver_id to check if a device is a RXE device or not. * ARPHDR_NONE means a TUN device. */ if (device->ops.driver_id == RDMA_DRIVER_RXE) { if ((dev_type == ARPHRD_NONE || dev_type == ARPHRD_ETHER) && rdma_protocol_roce(device, port)) { ndev = dev_get_by_index(dev_addr->net, bound_if_index); if (!ndev) goto out; } } else { if (dev_type == ARPHRD_ETHER && rdma_protocol_roce(device, port)) { ndev = dev_get_by_index(dev_addr->net, bound_if_index); if (!ndev) goto out; } else { gid_type = IB_GID_TYPE_IB; } } sgid_attr = rdma_find_gid_by_port(device, gid, gid_type, port, ndev); dev_put(ndev); out: return sgid_attr; } static void cma_bind_sgid_attr(struct rdma_id_private *id_priv, const struct ib_gid_attr *sgid_attr) { WARN_ON(id_priv->id.route.addr.dev_addr.sgid_attr); id_priv->id.route.addr.dev_addr.sgid_attr = sgid_attr; } /** * cma_acquire_dev_by_src_ip - Acquire cma device, port, gid attribute * based on source ip address. * @id_priv: cm_id which should be bound to cma device * * cma_acquire_dev_by_src_ip() binds cm id to cma device, port and GID attribute * based on source IP address. It returns 0 on success or error code otherwise. * It is applicable to active and passive side cm_id. */ static int cma_acquire_dev_by_src_ip(struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; union ib_gid gid, iboe_gid, *gidp; struct cma_device *cma_dev; enum ib_gid_type gid_type; int ret = -ENODEV; u32 port; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &iboe_gid); memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) { if (id_priv->restricted_node_type != RDMA_NODE_UNSPECIFIED && id_priv->restricted_node_type != cma_dev->device->node_type) continue; rdma_for_each_port (cma_dev->device, port) { gidp = rdma_protocol_roce(cma_dev->device, port) ? &iboe_gid : &gid; gid_type = cma_dev->default_gid_type[port - 1]; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, gidp, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); cma_attach_to_dev(id_priv, cma_dev); ret = 0; goto out; } } } out: mutex_unlock(&lock); return ret; } /** * cma_ib_acquire_dev - Acquire cma device, port and SGID attribute * @id_priv: cm id to bind to cma device * @listen_id_priv: listener cm id to match against * @req: Pointer to req structure containaining incoming * request information * cma_ib_acquire_dev() acquires cma device, port and SGID attribute when * rdma device matches for listen_id and incoming request. It also verifies * that a GID table entry is present for the source address. * Returns 0 on success, or returns error code otherwise. */ static int cma_ib_acquire_dev(struct rdma_id_private *id_priv, const struct rdma_id_private *listen_id_priv, struct cma_req_info *req) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; enum ib_gid_type gid_type; union ib_gid gid; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; if (rdma_protocol_roce(req->device, req->port)) rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &gid); else memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); gid_type = listen_id_priv->cma_dev->default_gid_type[req->port - 1]; sgid_attr = cma_validate_port(req->device, req->port, gid_type, &gid, id_priv); if (IS_ERR(sgid_attr)) return PTR_ERR(sgid_attr); id_priv->id.port_num = req->port; cma_bind_sgid_attr(id_priv, sgid_attr); /* Need to acquire lock to protect against reader * of cma_dev->id_list such as cma_netdev_callback() and * cma_process_remove(). */ mutex_lock(&lock); cma_attach_to_dev(id_priv, listen_id_priv->cma_dev); mutex_unlock(&lock); rdma_restrack_add(&id_priv->res); return 0; } static int cma_iw_acquire_dev(struct rdma_id_private *id_priv, const struct rdma_id_private *listen_id_priv) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; const struct ib_gid_attr *sgid_attr; struct cma_device *cma_dev; enum ib_gid_type gid_type; int ret = -ENODEV; union ib_gid gid; u32 port; if (dev_addr->dev_type != ARPHRD_INFINIBAND && id_priv->id.ps == RDMA_PS_IPOIB) return -EINVAL; memcpy(&gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof(gid)); mutex_lock(&lock); cma_dev = listen_id_priv->cma_dev; port = listen_id_priv->id.port_num; gid_type = listen_id_priv->gid_type; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, &gid, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); ret = 0; goto out; } list_for_each_entry(cma_dev, &dev_list, list) { rdma_for_each_port (cma_dev->device, port) { if (listen_id_priv->cma_dev == cma_dev && listen_id_priv->id.port_num == port) continue; gid_type = cma_dev->default_gid_type[port - 1]; sgid_attr = cma_validate_port(cma_dev->device, port, gid_type, &gid, id_priv); if (!IS_ERR(sgid_attr)) { id_priv->id.port_num = port; cma_bind_sgid_attr(id_priv, sgid_attr); ret = 0; goto out; } } } out: if (!ret) { cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); } mutex_unlock(&lock); return ret; } /* * Select the source IB device and address to reach the destination IB address. */ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv) { struct cma_device *cma_dev, *cur_dev; struct sockaddr_ib *addr; union ib_gid gid, sgid, *dgid; unsigned int p; u16 pkey, index; enum ib_port_state port_state; int ret; int i; cma_dev = NULL; addr = (struct sockaddr_ib *) cma_dst_addr(id_priv); dgid = (union ib_gid *) &addr->sib_addr; pkey = ntohs(addr->sib_pkey); mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { rdma_for_each_port (cur_dev->device, p) { if (!rdma_cap_af_ib(cur_dev->device, p)) continue; if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index)) continue; if (ib_get_cached_port_state(cur_dev->device, p, &port_state)) continue; for (i = 0; i < cur_dev->device->port_data[p].immutable.gid_tbl_len; ++i) { ret = rdma_query_gid(cur_dev->device, p, i, &gid); if (ret) continue; if (!memcmp(&gid, dgid, sizeof(gid))) { cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; goto found; } if (!cma_dev && (gid.global.subnet_prefix == dgid->global.subnet_prefix) && port_state == IB_PORT_ACTIVE) { cma_dev = cur_dev; sgid = gid; id_priv->id.port_num = p; goto found; } } } } mutex_unlock(&lock); return -ENODEV; found: cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); mutex_unlock(&lock); addr = (struct sockaddr_ib *)cma_src_addr(id_priv); memcpy(&addr->sib_addr, &sgid, sizeof(sgid)); cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr); return 0; } static void cma_id_get(struct rdma_id_private *id_priv) { refcount_inc(&id_priv->refcount); } static void cma_id_put(struct rdma_id_private *id_priv) { if (refcount_dec_and_test(&id_priv->refcount)) complete(&id_priv->comp); } static struct rdma_id_private * __rdma_create_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type, const struct rdma_id_private *parent) { struct rdma_id_private *id_priv; id_priv = kzalloc_obj(*id_priv); if (!id_priv) return ERR_PTR(-ENOMEM); id_priv->state = RDMA_CM_IDLE; id_priv->restricted_node_type = RDMA_NODE_UNSPECIFIED; id_priv->id.context = context; id_priv->id.event_handler = event_handler; id_priv->id.ps = ps; id_priv->id.qp_type = qp_type; id_priv->tos_set = false; id_priv->timeout_set = false; id_priv->min_rnr_timer_set = false; id_priv->gid_type = IB_GID_TYPE_IB; spin_lock_init(&id_priv->lock); mutex_init(&id_priv->qp_mutex); init_completion(&id_priv->comp); refcount_set(&id_priv->refcount, 1); mutex_init(&id_priv->handler_mutex); INIT_LIST_HEAD(&id_priv->device_item); INIT_LIST_HEAD(&id_priv->id_list_entry); INIT_LIST_HEAD(&id_priv->listen_list); INIT_LIST_HEAD(&id_priv->mc_list); get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num); id_priv->id.route.addr.dev_addr.net = get_net(net); id_priv->seq_num &= 0x00ffffff; INIT_WORK(&id_priv->id.net_work, cma_netevent_work_handler); rdma_restrack_new(&id_priv->res, RDMA_RESTRACK_CM_ID); if (parent) rdma_restrack_parent_name(&id_priv->res, &parent->res); return id_priv; } struct rdma_cm_id * __rdma_create_kernel_id(struct net *net, rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type, const char *caller) { struct rdma_id_private *ret; ret = __rdma_create_id(net, event_handler, context, ps, qp_type, NULL); if (IS_ERR(ret)) return ERR_CAST(ret); rdma_restrack_set_name(&ret->res, caller); return &ret->id; } EXPORT_SYMBOL(__rdma_create_kernel_id); struct rdma_cm_id *rdma_create_user_id(rdma_cm_event_handler event_handler, void *context, enum rdma_ucm_port_space ps, enum ib_qp_type qp_type) { struct rdma_id_private *ret; ret = __rdma_create_id(current->nsproxy->net_ns, event_handler, context, ps, qp_type, NULL); if (IS_ERR(ret)) return ERR_CAST(ret); rdma_restrack_set_name(&ret->res, NULL); return &ret->id; } EXPORT_SYMBOL(rdma_create_user_id); static int cma_init_ud_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) return ret; ret = ib_modify_qp(qp, &qp_attr, qp_attr_mask); if (ret) return ret; qp_attr.qp_state = IB_QPS_RTR; ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE); if (ret) return ret; qp_attr.qp_state = IB_QPS_RTS; qp_attr.sq_psn = 0; ret = ib_modify_qp(qp, &qp_attr, IB_QP_STATE | IB_QP_SQ_PSN); return ret; } static int cma_init_conn_qp(struct rdma_id_private *id_priv, struct ib_qp *qp) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) return ret; return ib_modify_qp(qp, &qp_attr, qp_attr_mask); } int rdma_create_qp(struct rdma_cm_id *id, struct ib_pd *pd, struct ib_qp_init_attr *qp_init_attr) { struct rdma_id_private *id_priv; struct ib_qp *qp; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (id->device != pd->device) { ret = -EINVAL; goto out_err; } qp_init_attr->port_num = id->port_num; qp = ib_create_qp(pd, qp_init_attr); if (IS_ERR(qp)) { ret = PTR_ERR(qp); goto out_err; } if (id->qp_type == IB_QPT_UD) ret = cma_init_ud_qp(id_priv, qp); else ret = cma_init_conn_qp(id_priv, qp); if (ret) goto out_destroy; id->qp = qp; id_priv->qp_num = qp->qp_num; id_priv->srq = (qp->srq != NULL); trace_cm_qp_create(id_priv, pd, qp_init_attr, 0); return 0; out_destroy: ib_destroy_qp(qp); out_err: trace_cm_qp_create(id_priv, pd, qp_init_attr, ret); return ret; } EXPORT_SYMBOL(rdma_create_qp); void rdma_destroy_qp(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); trace_cm_qp_destroy(id_priv); mutex_lock(&id_priv->qp_mutex); ib_destroy_qp(id_priv->id.qp); id_priv->id.qp = NULL; mutex_unlock(&id_priv->qp_mutex); } EXPORT_SYMBOL(rdma_destroy_qp); static int cma_modify_qp_rtr(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } /* Need to update QP attributes from default values. */ qp_attr.qp_state = IB_QPS_INIT; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); if (ret) goto out; qp_attr.qp_state = IB_QPS_RTR; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; BUG_ON(id_priv->cma_dev->device != id_priv->id.device); if (conn_param) qp_attr.max_dest_rd_atomic = conn_param->responder_resources; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_modify_qp_rts(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_qp_attr qp_attr; int qp_attr_mask, ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } qp_attr.qp_state = IB_QPS_RTS; ret = rdma_init_qp_attr(&id_priv->id, &qp_attr, &qp_attr_mask); if (ret) goto out; if (conn_param) qp_attr.max_rd_atomic = conn_param->initiator_depth; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_modify_qp_err(struct rdma_id_private *id_priv) { struct ib_qp_attr qp_attr; int ret; mutex_lock(&id_priv->qp_mutex); if (!id_priv->id.qp) { ret = 0; goto out; } qp_attr.qp_state = IB_QPS_ERR; ret = ib_modify_qp(id_priv->id.qp, &qp_attr, IB_QP_STATE); out: mutex_unlock(&id_priv->qp_mutex); return ret; } static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int ret; u16 pkey; if (rdma_cap_eth_ah(id_priv->id.device, id_priv->id.port_num)) pkey = 0xffff; else pkey = ib_addr_get_pkey(dev_addr); ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num, pkey, &qp_attr->pkey_index); if (ret) return ret; qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT; if (id_priv->id.qp_type == IB_QPT_UD) { ret = cma_set_default_qkey(id_priv); if (ret) return ret; qp_attr->qkey = id_priv->qkey; *qp_attr_mask |= IB_QP_QKEY; } else { qp_attr->qp_access_flags = 0; *qp_attr_mask |= IB_QP_ACCESS_FLAGS; } return 0; } int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr, int *qp_attr_mask) { struct rdma_id_private *id_priv; int ret = 0; id_priv = container_of(id, struct rdma_id_private, id); if (rdma_cap_ib_cm(id->device, id->port_num)) { if (!id_priv->cm_id.ib || (id_priv->id.qp_type == IB_QPT_UD)) ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask); else ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr, qp_attr_mask); if (qp_attr->qp_state == IB_QPS_RTR) qp_attr->rq_psn = id_priv->seq_num; } else if (rdma_cap_iw_cm(id->device, id->port_num)) { if (!id_priv->cm_id.iw) { qp_attr->qp_access_flags = 0; *qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS; } else ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr, qp_attr_mask); qp_attr->port_num = id_priv->id.port_num; *qp_attr_mask |= IB_QP_PORT; } else { ret = -ENOSYS; } if ((*qp_attr_mask & IB_QP_TIMEOUT) && id_priv->timeout_set) qp_attr->timeout = id_priv->timeout; if ((*qp_attr_mask & IB_QP_MIN_RNR_TIMER) && id_priv->min_rnr_timer_set) qp_attr->min_rnr_timer = id_priv->min_rnr_timer; return ret; } EXPORT_SYMBOL(rdma_init_qp_attr); static inline bool cma_zero_addr(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return ipv4_is_zeronet(((struct sockaddr_in *)addr)->sin_addr.s_addr); case AF_INET6: return ipv6_addr_any(&((struct sockaddr_in6 *)addr)->sin6_addr); case AF_IB: return ib_addr_any(&((struct sockaddr_ib *)addr)->sib_addr); default: return false; } } static inline bool cma_loopback_addr(const struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: return ipv4_is_loopback( ((struct sockaddr_in *)addr)->sin_addr.s_addr); case AF_INET6: return ipv6_addr_loopback( &((struct sockaddr_in6 *)addr)->sin6_addr); case AF_IB: return ib_addr_loopback( &((struct sockaddr_ib *)addr)->sib_addr); default: return false; } } static inline bool cma_any_addr(const struct sockaddr *addr) { return cma_zero_addr(addr) || cma_loopback_addr(addr); } static int cma_addr_cmp(const struct sockaddr *src, const struct sockaddr *dst) { if (src->sa_family != dst->sa_family) return -1; switch (src->sa_family) { case AF_INET: return ((struct sockaddr_in *)src)->sin_addr.s_addr != ((struct sockaddr_in *)dst)->sin_addr.s_addr; case AF_INET6: { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)src; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst; bool link_local; if (ipv6_addr_cmp(&src_addr6->sin6_addr, &dst_addr6->sin6_addr)) return 1; link_local = ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL; /* Link local must match their scope_ids */ return link_local ? (src_addr6->sin6_scope_id != dst_addr6->sin6_scope_id) : 0; } default: return ib_addr_cmp(&((struct sockaddr_ib *) src)->sib_addr, &((struct sockaddr_ib *) dst)->sib_addr); } } static __be16 cma_port(const struct sockaddr *addr) { struct sockaddr_ib *sib; switch (addr->sa_family) { case AF_INET: return ((struct sockaddr_in *) addr)->sin_port; case AF_INET6: return ((struct sockaddr_in6 *) addr)->sin6_port; case AF_IB: sib = (struct sockaddr_ib *) addr; return htons((u16) (be64_to_cpu(sib->sib_sid) & be64_to_cpu(sib->sib_sid_mask))); default: return 0; } } static inline int cma_any_port(const struct sockaddr *addr) { return !cma_port(addr); } static void cma_save_ib_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct rdma_cm_id *listen_id, const struct sa_path_rec *path) { struct sockaddr_ib *listen_ib, *ib; listen_ib = (struct sockaddr_ib *) &listen_id->route.addr.src_addr; if (src_addr) { ib = (struct sockaddr_ib *)src_addr; ib->sib_family = AF_IB; if (path) { ib->sib_pkey = path->pkey; ib->sib_flowinfo = path->flow_label; memcpy(&ib->sib_addr, &path->sgid, 16); ib->sib_sid = path->service_id; ib->sib_scope_id = 0; } else { ib->sib_pkey = listen_ib->sib_pkey; ib->sib_flowinfo = listen_ib->sib_flowinfo; ib->sib_addr = listen_ib->sib_addr; ib->sib_sid = listen_ib->sib_sid; ib->sib_scope_id = listen_ib->sib_scope_id; } ib->sib_sid_mask = cpu_to_be64(0xffffffffffffffffULL); } if (dst_addr) { ib = (struct sockaddr_ib *)dst_addr; ib->sib_family = AF_IB; if (path) { ib->sib_pkey = path->pkey; ib->sib_flowinfo = path->flow_label; memcpy(&ib->sib_addr, &path->dgid, 16); } } } static void cma_save_ip4_info(struct sockaddr_in *src_addr, struct sockaddr_in *dst_addr, struct cma_hdr *hdr, __be16 local_port) { if (src_addr) { *src_addr = (struct sockaddr_in) { .sin_family = AF_INET, .sin_addr.s_addr = hdr->dst_addr.ip4.addr, .sin_port = local_port, }; } if (dst_addr) { *dst_addr = (struct sockaddr_in) { .sin_family = AF_INET, .sin_addr.s_addr = hdr->src_addr.ip4.addr, .sin_port = hdr->port, }; } } static void cma_save_ip6_info(struct sockaddr_in6 *src_addr, struct sockaddr_in6 *dst_addr, struct cma_hdr *hdr, __be16 local_port) { if (src_addr) { *src_addr = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_addr = hdr->dst_addr.ip6, .sin6_port = local_port, }; } if (dst_addr) { *dst_addr = (struct sockaddr_in6) { .sin6_family = AF_INET6, .sin6_addr = hdr->src_addr.ip6, .sin6_port = hdr->port, }; } } static u16 cma_port_from_service_id(__be64 service_id) { return (u16)be64_to_cpu(service_id); } static int cma_save_ip_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct ib_cm_event *ib_event, __be64 service_id) { struct cma_hdr *hdr; __be16 port; hdr = ib_event->private_data; if (hdr->cma_version != CMA_VERSION) return -EINVAL; port = htons(cma_port_from_service_id(service_id)); switch (cma_get_ip_ver(hdr)) { case 4: cma_save_ip4_info((struct sockaddr_in *)src_addr, (struct sockaddr_in *)dst_addr, hdr, port); break; case 6: cma_save_ip6_info((struct sockaddr_in6 *)src_addr, (struct sockaddr_in6 *)dst_addr, hdr, port); break; default: return -EAFNOSUPPORT; } return 0; } static int cma_save_net_info(struct sockaddr *src_addr, struct sockaddr *dst_addr, const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, sa_family_t sa_family, __be64 service_id) { if (sa_family == AF_IB) { if (ib_event->event == IB_CM_REQ_RECEIVED) cma_save_ib_info(src_addr, dst_addr, listen_id, ib_event->param.req_rcvd.primary_path); else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) cma_save_ib_info(src_addr, dst_addr, listen_id, NULL); return 0; } return cma_save_ip_info(src_addr, dst_addr, ib_event, service_id); } static int cma_save_req_info(const struct ib_cm_event *ib_event, struct cma_req_info *req) { const struct ib_cm_req_event_param *req_param = &ib_event->param.req_rcvd; const struct ib_cm_sidr_req_event_param *sidr_param = &ib_event->param.sidr_req_rcvd; switch (ib_event->event) { case IB_CM_REQ_RECEIVED: req->device = req_param->listen_id->device; req->port = req_param->port; memcpy(&req->local_gid, &req_param->primary_path->sgid, sizeof(req->local_gid)); req->has_gid = true; req->service_id = req_param->primary_path->service_id; req->pkey = be16_to_cpu(req_param->primary_path->pkey); if (req->pkey != req_param->bth_pkey) pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and primary path P_Key (0x%x)\n" "RDMA CMA: in the future this may cause the request to be dropped\n", req_param->bth_pkey, req->pkey); break; case IB_CM_SIDR_REQ_RECEIVED: req->device = sidr_param->listen_id->device; req->port = sidr_param->port; req->has_gid = false; req->service_id = sidr_param->service_id; req->pkey = sidr_param->pkey; if (req->pkey != sidr_param->bth_pkey) pr_warn_ratelimited("RDMA CMA: got different BTH P_Key (0x%x) and SIDR request payload P_Key (0x%x)\n" "RDMA CMA: in the future this may cause the request to be dropped\n", sidr_param->bth_pkey, req->pkey); break; default: return -EINVAL; } return 0; } static bool validate_ipv4_net_dev(struct net_device *net_dev, const struct sockaddr_in *dst_addr, const struct sockaddr_in *src_addr) { __be32 daddr = dst_addr->sin_addr.s_addr, saddr = src_addr->sin_addr.s_addr; struct fib_result res; struct flowi4 fl4; int err; bool ret; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || ipv4_is_lbcast(daddr) || ipv4_is_zeronet(saddr) || ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr) || ipv4_is_loopback(saddr)) return false; memset(&fl4, 0, sizeof(fl4)); fl4.flowi4_oif = net_dev->ifindex; fl4.daddr = daddr; fl4.saddr = saddr; rcu_read_lock(); err = fib_lookup(dev_net(net_dev), &fl4, &res, 0); ret = err == 0 && FIB_RES_DEV(res) == net_dev; rcu_read_unlock(); return ret; } static bool validate_ipv6_net_dev(struct net_device *net_dev, const struct sockaddr_in6 *dst_addr, const struct sockaddr_in6 *src_addr) { #if IS_ENABLED(CONFIG_IPV6) const int strict = ipv6_addr_type(&dst_addr->sin6_addr) & IPV6_ADDR_LINKLOCAL; struct rt6_info *rt = rt6_lookup(dev_net(net_dev), &dst_addr->sin6_addr, &src_addr->sin6_addr, net_dev->ifindex, NULL, strict); bool ret; if (!rt) return false; ret = rt->rt6i_idev->dev == net_dev; ip6_rt_put(rt); return ret; #else return false; #endif } static bool validate_net_dev(struct net_device *net_dev, const struct sockaddr *daddr, const struct sockaddr *saddr) { const struct sockaddr_in *daddr4 = (const struct sockaddr_in *)daddr; const struct sockaddr_in *saddr4 = (const struct sockaddr_in *)saddr; const struct sockaddr_in6 *daddr6 = (const struct sockaddr_in6 *)daddr; const struct sockaddr_in6 *saddr6 = (const struct sockaddr_in6 *)saddr; switch (daddr->sa_family) { case AF_INET: return saddr->sa_family == AF_INET && validate_ipv4_net_dev(net_dev, daddr4, saddr4); case AF_INET6: return saddr->sa_family == AF_INET6 && validate_ipv6_net_dev(net_dev, daddr6, saddr6); default: return false; } } static struct net_device * roce_get_net_dev_by_cm_event(const struct ib_cm_event *ib_event) { const struct ib_gid_attr *sgid_attr = NULL; struct net_device *ndev; if (ib_event->event == IB_CM_REQ_RECEIVED) sgid_attr = ib_event->param.req_rcvd.ppath_sgid_attr; else if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) sgid_attr = ib_event->param.sidr_req_rcvd.sgid_attr; if (!sgid_attr) return NULL; rcu_read_lock(); ndev = rdma_read_gid_attr_ndev_rcu(sgid_attr); if (IS_ERR(ndev)) ndev = NULL; else dev_hold(ndev); rcu_read_unlock(); return ndev; } static struct net_device *cma_get_net_dev(const struct ib_cm_event *ib_event, struct cma_req_info *req) { struct sockaddr *listen_addr = (struct sockaddr *)&req->listen_addr_storage; struct sockaddr *src_addr = (struct sockaddr *)&req->src_addr_storage; struct net_device *net_dev; const union ib_gid *gid = req->has_gid ? &req->local_gid : NULL; int err; err = cma_save_ip_info(listen_addr, src_addr, ib_event, req->service_id); if (err) return ERR_PTR(err); if (rdma_protocol_roce(req->device, req->port)) net_dev = roce_get_net_dev_by_cm_event(ib_event); else net_dev = ib_get_net_dev_by_params(req->device, req->port, req->pkey, gid, listen_addr); if (!net_dev) return ERR_PTR(-ENODEV); return net_dev; } static enum rdma_ucm_port_space rdma_ps_from_service_id(__be64 service_id) { return (be64_to_cpu(service_id) >> 16) & 0xffff; } static bool cma_match_private_data(struct rdma_id_private *id_priv, const struct cma_hdr *hdr) { struct sockaddr *addr = cma_src_addr(id_priv); __be32 ip4_addr; struct in6_addr ip6_addr; if (cma_any_addr(addr) && !id_priv->afonly) return true; switch (addr->sa_family) { case AF_INET: ip4_addr = ((struct sockaddr_in *)addr)->sin_addr.s_addr; if (cma_get_ip_ver(hdr) != 4) return false; if (!cma_any_addr(addr) && hdr->dst_addr.ip4.addr != ip4_addr) return false; break; case AF_INET6: ip6_addr = ((struct sockaddr_in6 *)addr)->sin6_addr; if (cma_get_ip_ver(hdr) != 6) return false; if (!cma_any_addr(addr) && memcmp(&hdr->dst_addr.ip6, &ip6_addr, sizeof(ip6_addr))) return false; break; case AF_IB: return true; default: return false; } return true; } static bool cma_protocol_roce(const struct rdma_cm_id *id) { struct ib_device *device = id->device; const u32 port_num = id->port_num ?: rdma_start_port(device); return rdma_protocol_roce(device, port_num); } static bool cma_is_req_ipv6_ll(const struct cma_req_info *req) { const struct sockaddr *daddr = (const struct sockaddr *)&req->listen_addr_storage; const struct sockaddr_in6 *daddr6 = (const struct sockaddr_in6 *)daddr; /* Returns true if the req is for IPv6 link local */ return (daddr->sa_family == AF_INET6 && (ipv6_addr_type(&daddr6->sin6_addr) & IPV6_ADDR_LINKLOCAL)); } static bool cma_match_net_dev(const struct rdma_cm_id *id, const struct net_device *net_dev, const struct cma_req_info *req) { const struct rdma_addr *addr = &id->route.addr; if (!net_dev) /* This request is an AF_IB request */ return (!id->port_num || id->port_num == req->port) && (addr->src_addr.ss_family == AF_IB); /* * If the request is not for IPv6 link local, allow matching * request to any netdevice of the one or multiport rdma device. */ if (!cma_is_req_ipv6_ll(req)) return true; /* * Net namespaces must match, and if the listner is listening * on a specific netdevice than netdevice must match as well. */ if (net_eq(dev_net(net_dev), addr->dev_addr.net) && (!!addr->dev_addr.bound_dev_if == (addr->dev_addr.bound_dev_if == net_dev->ifindex))) return true; else return false; } static struct rdma_id_private *cma_find_listener( const struct rdma_bind_list *bind_list, const struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event, const struct cma_req_info *req, const struct net_device *net_dev) { struct rdma_id_private *id_priv, *id_priv_dev; lockdep_assert_held(&lock); if (!bind_list) return ERR_PTR(-EINVAL); hlist_for_each_entry(id_priv, &bind_list->owners, node) { if (cma_match_private_data(id_priv, ib_event->private_data)) { if (id_priv->id.device == cm_id->device && cma_match_net_dev(&id_priv->id, net_dev, req)) return id_priv; list_for_each_entry(id_priv_dev, &id_priv->listen_list, listen_item) { if (id_priv_dev->id.device == cm_id->device && cma_match_net_dev(&id_priv_dev->id, net_dev, req)) return id_priv_dev; } } } return ERR_PTR(-EINVAL); } static struct rdma_id_private * cma_ib_id_from_event(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event, struct cma_req_info *req, struct net_device **net_dev) { struct rdma_bind_list *bind_list; struct rdma_id_private *id_priv; int err; err = cma_save_req_info(ib_event, req); if (err) return ERR_PTR(err); *net_dev = cma_get_net_dev(ib_event, req); if (IS_ERR(*net_dev)) { if (PTR_ERR(*net_dev) == -EAFNOSUPPORT) { /* Assuming the protocol is AF_IB */ *net_dev = NULL; } else { return ERR_CAST(*net_dev); } } mutex_lock(&lock); /* * Net namespace might be getting deleted while route lookup, * cm_id lookup is in progress. Therefore, perform netdevice * validation, cm_id lookup under rcu lock. * RCU lock along with netdevice state check, synchronizes with * netdevice migrating to different net namespace and also avoids * case where net namespace doesn't get deleted while lookup is in * progress. * If the device state is not IFF_UP, its properties such as ifindex * and nd_net cannot be trusted to remain valid without rcu lock. * net/core/dev.c change_net_namespace() ensures to synchronize with * ongoing operations on net device after device is closed using * synchronize_net(). */ rcu_read_lock(); if (*net_dev) { /* * If netdevice is down, it is likely that it is administratively * down or it might be migrating to different namespace. * In that case avoid further processing, as the net namespace * or ifindex may change. */ if (((*net_dev)->flags & IFF_UP) == 0) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } if (!validate_net_dev(*net_dev, (struct sockaddr *)&req->src_addr_storage, (struct sockaddr *)&req->listen_addr_storage)) { id_priv = ERR_PTR(-EHOSTUNREACH); goto err; } } bind_list = cma_ps_find(*net_dev ? dev_net(*net_dev) : &init_net, rdma_ps_from_service_id(req->service_id), cma_port_from_service_id(req->service_id)); id_priv = cma_find_listener(bind_list, cm_id, ib_event, req, *net_dev); err: rcu_read_unlock(); mutex_unlock(&lock); if (IS_ERR(id_priv) && *net_dev) { dev_put(*net_dev); *net_dev = NULL; } return id_priv; } static inline u8 cma_user_data_offset(struct rdma_id_private *id_priv) { return cma_family(id_priv) == AF_IB ? 0 : sizeof(struct cma_hdr); } static void cma_cancel_route(struct rdma_id_private *id_priv) { if (rdma_cap_ib_sa(id_priv->id.device, id_priv->id.port_num)) { if (id_priv->query) ib_sa_cancel_query(id_priv->query_id, id_priv->query); } } static void _cma_cancel_listens(struct rdma_id_private *id_priv) { struct rdma_id_private *dev_id_priv; lockdep_assert_held(&lock); /* * Remove from listen_any_list to prevent added devices from spawning * additional listen requests. */ list_del_init(&id_priv->listen_any_item); while (!list_empty(&id_priv->listen_list)) { dev_id_priv = list_first_entry(&id_priv->listen_list, struct rdma_id_private, listen_item); /* sync with device removal to avoid duplicate destruction */ list_del_init(&dev_id_priv->device_item); list_del_init(&dev_id_priv->listen_item); mutex_unlock(&lock); rdma_destroy_id(&dev_id_priv->id); mutex_lock(&lock); } } static void cma_cancel_listens(struct rdma_id_private *id_priv) { mutex_lock(&lock); _cma_cancel_listens(id_priv); mutex_unlock(&lock); } static void cma_cancel_operation(struct rdma_id_private *id_priv, enum rdma_cm_state state) { switch (state) { case RDMA_CM_ADDR_QUERY: /* * We can avoid doing the rdma_addr_cancel() based on state, * only RDMA_CM_ADDR_QUERY has a work that could still execute. * Notice that the addr_handler work could still be exiting * outside this state, however due to the interaction with the * handler_mutex the work is guaranteed not to touch id_priv * during exit. */ rdma_addr_cancel(&id_priv->id.route.addr.dev_addr); break; case RDMA_CM_ROUTE_QUERY: cma_cancel_route(id_priv); break; case RDMA_CM_LISTEN: if (cma_any_addr(cma_src_addr(id_priv)) && !id_priv->cma_dev) cma_cancel_listens(id_priv); break; default: break; } } static void cma_release_port(struct rdma_id_private *id_priv) { struct rdma_bind_list *bind_list = id_priv->bind_list; struct net *net = id_priv->id.route.addr.dev_addr.net; if (!bind_list) return; mutex_lock(&lock); hlist_del(&id_priv->node); if (hlist_empty(&bind_list->owners)) { cma_ps_remove(net, bind_list->ps, bind_list->port); kfree(bind_list); } mutex_unlock(&lock); } static void destroy_mc(struct rdma_id_private *id_priv, struct cma_multicast *mc) { bool send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); if (rdma_cap_ib_mcast(id_priv->id.device, id_priv->id.port_num)) ib_sa_free_multicast(mc->sa_mc); if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) { struct rdma_cm_event *event = &mc->iboe_join.event; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct net_device *ndev = NULL; if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (ndev && !send_only) { enum ib_gid_type gid_type; union ib_gid mgid; gid_type = id_priv->cma_dev->default_gid_type [id_priv->id.port_num - rdma_start_port( id_priv->cma_dev->device)]; cma_iboe_set_mgid((struct sockaddr *)&mc->addr, &mgid, gid_type); cma_igmp_send(ndev, &mgid, false); } dev_put(ndev); cancel_work_sync(&mc->iboe_join.work); if (event->event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&event->param.ud.ah_attr); } kfree(mc); } static void cma_leave_mc_groups(struct rdma_id_private *id_priv) { struct cma_multicast *mc; while (!list_empty(&id_priv->mc_list)) { mc = list_first_entry(&id_priv->mc_list, struct cma_multicast, list); list_del(&mc->list); destroy_mc(id_priv, mc); } } static void _destroy_id(struct rdma_id_private *id_priv, enum rdma_cm_state state) { cma_cancel_operation(id_priv, state); rdma_restrack_del(&id_priv->res); cma_remove_id_from_tree(id_priv); if (id_priv->cma_dev) { if (rdma_cap_ib_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.ib) ib_destroy_cm_id(id_priv->cm_id.ib); } else if (rdma_cap_iw_cm(id_priv->id.device, 1)) { if (id_priv->cm_id.iw) iw_destroy_cm_id(id_priv->cm_id.iw); } cma_leave_mc_groups(id_priv); cma_release_dev(id_priv); } cma_release_port(id_priv); cma_id_put(id_priv); wait_for_completion(&id_priv->comp); if (id_priv->internal_id) cma_id_put(id_priv->id.context); kfree(id_priv->id.route.path_rec); kfree(id_priv->id.route.path_rec_inbound); kfree(id_priv->id.route.path_rec_outbound); kfree(id_priv->id.route.service_recs); put_net(id_priv->id.route.addr.dev_addr.net); kfree(id_priv); } /* * destroy an ID from within the handler_mutex. This ensures that no other * handlers can start running concurrently. */ static void destroy_id_handler_unlock(struct rdma_id_private *id_priv) __releases(&idprv->handler_mutex) { enum rdma_cm_state state; unsigned long flags; trace_cm_id_destroy(id_priv); /* * Setting the state to destroyed under the handler mutex provides a * fence against calling handler callbacks. If this is invoked due to * the failure of a handler callback then it guarentees that no future * handlers will be called. */ lockdep_assert_held(&id_priv->handler_mutex); spin_lock_irqsave(&id_priv->lock, flags); state = id_priv->state; id_priv->state = RDMA_CM_DESTROYING; spin_unlock_irqrestore(&id_priv->lock, flags); mutex_unlock(&id_priv->handler_mutex); _destroy_id(id_priv, state); } void rdma_destroy_id(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->handler_mutex); destroy_id_handler_unlock(id_priv); } EXPORT_SYMBOL(rdma_destroy_id); static int cma_rep_recv(struct rdma_id_private *id_priv) { int ret; ret = cma_modify_qp_rtr(id_priv, NULL); if (ret) goto reject; ret = cma_modify_qp_rts(id_priv, NULL); if (ret) goto reject; trace_cm_send_rtu(id_priv); ret = ib_send_cm_rtu(id_priv->cm_id.ib, NULL, 0); if (ret) goto reject; return 0; reject: pr_debug_ratelimited("RDMA CM: CONNECT_ERROR: failed to handle reply. status %d\n", ret); cma_modify_qp_err(id_priv); trace_cm_send_rej(id_priv); ib_send_cm_rej(id_priv->cm_id.ib, IB_CM_REJ_CONSUMER_DEFINED, NULL, 0, NULL, 0); return ret; } static void cma_set_rep_event_data(struct rdma_cm_event *event, const struct ib_cm_rep_event_param *rep_data, void *private_data) { event->param.conn.private_data = private_data; event->param.conn.private_data_len = IB_CM_REP_PRIVATE_DATA_SIZE; event->param.conn.responder_resources = rep_data->responder_resources; event->param.conn.initiator_depth = rep_data->initiator_depth; event->param.conn.flow_control = rep_data->flow_control; event->param.conn.rnr_retry_count = rep_data->rnr_retry_count; event->param.conn.srq = rep_data->srq; event->param.conn.qp_num = rep_data->remote_qpn; event->ece.vendor_id = rep_data->ece.vendor_id; event->ece.attr_mod = rep_data->ece.attr_mod; } static int cma_cm_event_handler(struct rdma_id_private *id_priv, struct rdma_cm_event *event) { int ret; lockdep_assert_held(&id_priv->handler_mutex); trace_cm_event_handler(id_priv, event); ret = id_priv->id.event_handler(&id_priv->id, event); trace_cm_event_done(id_priv, event, ret); return ret; } static int cma_ib_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; struct rdma_cm_event event = {}; enum rdma_cm_state state; int ret; mutex_lock(&id_priv->handler_mutex); state = READ_ONCE(id_priv->state); if ((ib_event->event != IB_CM_TIMEWAIT_EXIT && state != RDMA_CM_CONNECT) || (ib_event->event == IB_CM_TIMEWAIT_EXIT && state != RDMA_CM_DISCONNECT)) goto out; switch (ib_event->event) { case IB_CM_REQ_ERROR: case IB_CM_REP_ERROR: event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; break; case IB_CM_REP_RECEIVED: if (state == RDMA_CM_CONNECT && (id_priv->id.qp_type != IB_QPT_UD)) { trace_cm_prepare_mra(id_priv); ib_prepare_cm_mra(cm_id); } if (id_priv->id.qp) { event.status = cma_rep_recv(id_priv); event.event = event.status ? RDMA_CM_EVENT_CONNECT_ERROR : RDMA_CM_EVENT_ESTABLISHED; } else { event.event = RDMA_CM_EVENT_CONNECT_RESPONSE; } cma_set_rep_event_data(&event, &ib_event->param.rep_rcvd, ib_event->private_data); break; case IB_CM_RTU_RECEIVED: case IB_CM_USER_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; break; case IB_CM_DREQ_ERROR: event.status = -ETIMEDOUT; fallthrough; case IB_CM_DREQ_RECEIVED: case IB_CM_DREP_RECEIVED: if (!cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_DISCONNECT)) goto out; event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IB_CM_TIMEWAIT_EXIT: event.event = RDMA_CM_EVENT_TIMEWAIT_EXIT; break; case IB_CM_MRA_RECEIVED: /* ignore event */ goto out; case IB_CM_REJ_RECEIVED: pr_debug_ratelimited("RDMA CM: REJECTED: %s\n", rdma_reject_msg(&id_priv->id, ib_event->param.rej_rcvd.reason)); cma_modify_qp_err(id_priv); event.status = ib_event->param.rej_rcvd.reason; event.event = RDMA_CM_EVENT_REJECTED; event.param.conn.private_data = ib_event->private_data; event.param.conn.private_data_len = IB_CM_REJ_PRIVATE_DATA_SIZE; break; default: pr_err("RDMA CMA: unexpected IB CM event: %d\n", ib_event->event); goto out; } ret = cma_cm_event_handler(id_priv, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return 0; } static struct rdma_id_private * cma_ib_new_conn_id(const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, struct net_device *net_dev) { struct rdma_id_private *listen_id_priv; struct rdma_id_private *id_priv; struct rdma_cm_id *id; struct rdma_route *rt; const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family; struct sa_path_rec *path = ib_event->param.req_rcvd.primary_path; const __be64 service_id = ib_event->param.req_rcvd.primary_path->service_id; int ret; listen_id_priv = container_of(listen_id, struct rdma_id_private, id); id_priv = __rdma_create_id(listen_id->route.addr.dev_addr.net, listen_id->event_handler, listen_id->context, listen_id->ps, ib_event->param.req_rcvd.qp_type, listen_id_priv); if (IS_ERR(id_priv)) return NULL; id = &id_priv->id; if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr, (struct sockaddr *)&id->route.addr.dst_addr, listen_id, ib_event, ss_family, service_id)) goto err; rt = &id->route; rt->num_pri_alt_paths = ib_event->param.req_rcvd.alternate_path ? 2 : 1; rt->path_rec = kmalloc_objs(*rt->path_rec, rt->num_pri_alt_paths); if (!rt->path_rec) goto err; rt->path_rec[0] = *path; if (rt->num_pri_alt_paths == 2) rt->path_rec[1] = *ib_event->param.req_rcvd.alternate_path; if (net_dev) { rdma_copy_src_l2_addr(&rt->addr.dev_addr, net_dev); } else { if (!cma_protocol_roce(listen_id) && cma_any_addr(cma_src_addr(id_priv))) { rt->addr.dev_addr.dev_type = ARPHRD_INFINIBAND; rdma_addr_set_sgid(&rt->addr.dev_addr, &rt->path_rec[0].sgid); ib_addr_set_pkey(&rt->addr.dev_addr, be16_to_cpu(rt->path_rec[0].pkey)); } else if (!cma_any_addr(cma_src_addr(id_priv))) { ret = cma_translate_addr(cma_src_addr(id_priv), &rt->addr.dev_addr); if (ret) goto err; } } rdma_addr_set_dgid(&rt->addr.dev_addr, &rt->path_rec[0].dgid); id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); return NULL; } static struct rdma_id_private * cma_ib_new_udp_id(const struct rdma_cm_id *listen_id, const struct ib_cm_event *ib_event, struct net_device *net_dev) { const struct rdma_id_private *listen_id_priv; struct rdma_id_private *id_priv; struct rdma_cm_id *id; const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family; struct net *net = listen_id->route.addr.dev_addr.net; int ret; listen_id_priv = container_of(listen_id, struct rdma_id_private, id); id_priv = __rdma_create_id(net, listen_id->event_handler, listen_id->context, listen_id->ps, IB_QPT_UD, listen_id_priv); if (IS_ERR(id_priv)) return NULL; id = &id_priv->id; if (cma_save_net_info((struct sockaddr *)&id->route.addr.src_addr, (struct sockaddr *)&id->route.addr.dst_addr, listen_id, ib_event, ss_family, ib_event->param.sidr_req_rcvd.service_id)) goto err; if (net_dev) { rdma_copy_src_l2_addr(&id->route.addr.dev_addr, net_dev); } else { if (!cma_any_addr(cma_src_addr(id_priv))) { ret = cma_translate_addr(cma_src_addr(id_priv), &id->route.addr.dev_addr); if (ret) goto err; } } id_priv->state = RDMA_CM_CONNECT; return id_priv; err: rdma_destroy_id(id); return NULL; } static void cma_set_req_event_data(struct rdma_cm_event *event, const struct ib_cm_req_event_param *req_data, void *private_data, int offset) { event->param.conn.private_data = private_data + offset; event->param.conn.private_data_len = IB_CM_REQ_PRIVATE_DATA_SIZE - offset; event->param.conn.responder_resources = req_data->responder_resources; event->param.conn.initiator_depth = req_data->initiator_depth; event->param.conn.flow_control = req_data->flow_control; event->param.conn.retry_count = req_data->retry_count; event->param.conn.rnr_retry_count = req_data->rnr_retry_count; event->param.conn.srq = req_data->srq; event->param.conn.qp_num = req_data->remote_qpn; event->ece.vendor_id = req_data->ece.vendor_id; event->ece.attr_mod = req_data->ece.attr_mod; } static int cma_ib_check_req_qp_type(const struct rdma_cm_id *id, const struct ib_cm_event *ib_event) { return (((ib_event->event == IB_CM_REQ_RECEIVED) && (ib_event->param.req_rcvd.qp_type == id->qp_type)) || ((ib_event->event == IB_CM_SIDR_REQ_RECEIVED) && (id->qp_type == IB_QPT_UD)) || (!id->qp_type)); } static int cma_ib_req_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *listen_id, *conn_id = NULL; struct rdma_cm_event event = {}; struct cma_req_info req = {}; struct net_device *net_dev; u8 offset; int ret; listen_id = cma_ib_id_from_event(cm_id, ib_event, &req, &net_dev); if (IS_ERR(listen_id)) return PTR_ERR(listen_id); trace_cm_req_handler(listen_id, ib_event->event); if (!cma_ib_check_req_qp_type(&listen_id->id, ib_event)) { ret = -EINVAL; goto net_dev_put; } mutex_lock(&listen_id->handler_mutex); if (READ_ONCE(listen_id->state) != RDMA_CM_LISTEN) { ret = -ECONNABORTED; goto err_unlock; } offset = cma_user_data_offset(listen_id); event.event = RDMA_CM_EVENT_CONNECT_REQUEST; if (ib_event->event == IB_CM_SIDR_REQ_RECEIVED) { conn_id = cma_ib_new_udp_id(&listen_id->id, ib_event, net_dev); event.param.ud.private_data = ib_event->private_data + offset; event.param.ud.private_data_len = IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE - offset; } else { conn_id = cma_ib_new_conn_id(&listen_id->id, ib_event, net_dev); cma_set_req_event_data(&event, &ib_event->param.req_rcvd, ib_event->private_data, offset); } if (!conn_id) { ret = -ENOMEM; goto err_unlock; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); ret = cma_ib_acquire_dev(conn_id, listen_id, &req); if (ret) { destroy_id_handler_unlock(conn_id); goto err_unlock; } conn_id->cm_id.ib = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_ib_handler; ret = cma_cm_event_handler(conn_id, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ conn_id->cm_id.ib = NULL; mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); goto net_dev_put; } if (READ_ONCE(conn_id->state) == RDMA_CM_CONNECT && conn_id->id.qp_type != IB_QPT_UD) { trace_cm_prepare_mra(cm_id->context); ib_prepare_cm_mra(cm_id); } mutex_unlock(&conn_id->handler_mutex); err_unlock: mutex_unlock(&listen_id->handler_mutex); net_dev_put: dev_put(net_dev); return ret; } __be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr) { if (addr->sa_family == AF_IB) return ((struct sockaddr_ib *) addr)->sib_sid; return cpu_to_be64(((u64)id->ps << 16) + be16_to_cpu(cma_port(addr))); } EXPORT_SYMBOL(rdma_get_service_id); void rdma_read_gids(struct rdma_cm_id *cm_id, union ib_gid *sgid, union ib_gid *dgid) { struct rdma_addr *addr = &cm_id->route.addr; if (!cm_id->device) { if (sgid) memset(sgid, 0, sizeof(*sgid)); if (dgid) memset(dgid, 0, sizeof(*dgid)); return; } if (rdma_protocol_roce(cm_id->device, cm_id->port_num)) { if (sgid) rdma_ip2gid((struct sockaddr *)&addr->src_addr, sgid); if (dgid) rdma_ip2gid((struct sockaddr *)&addr->dst_addr, dgid); } else { if (sgid) rdma_addr_get_sgid(&addr->dev_addr, sgid); if (dgid) rdma_addr_get_dgid(&addr->dev_addr, dgid); } } EXPORT_SYMBOL(rdma_read_gids); static int cma_iw_handler(struct iw_cm_id *iw_id, struct iw_cm_event *iw_event) { struct rdma_id_private *id_priv = iw_id->context; struct rdma_cm_event event = {}; int ret = 0; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) goto out; switch (iw_event->event) { case IW_CM_EVENT_CLOSE: event.event = RDMA_CM_EVENT_DISCONNECTED; break; case IW_CM_EVENT_CONNECT_REPLY: memcpy(cma_src_addr(id_priv), laddr, rdma_addr_size(laddr)); memcpy(cma_dst_addr(id_priv), raddr, rdma_addr_size(raddr)); switch (iw_event->status) { case 0: event.event = RDMA_CM_EVENT_ESTABLISHED; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; break; case -ECONNRESET: case -ECONNREFUSED: event.event = RDMA_CM_EVENT_REJECTED; break; case -ETIMEDOUT: event.event = RDMA_CM_EVENT_UNREACHABLE; break; default: event.event = RDMA_CM_EVENT_CONNECT_ERROR; break; } break; case IW_CM_EVENT_ESTABLISHED: event.event = RDMA_CM_EVENT_ESTABLISHED; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; break; default: goto out; } event.status = iw_event->status; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; ret = cma_cm_event_handler(id_priv, &event); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.iw = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return ret; } static int iw_conn_req_handler(struct iw_cm_id *cm_id, struct iw_cm_event *iw_event) { struct rdma_id_private *listen_id, *conn_id; struct rdma_cm_event event = {}; int ret = -ECONNABORTED; struct sockaddr *laddr = (struct sockaddr *)&iw_event->local_addr; struct sockaddr *raddr = (struct sockaddr *)&iw_event->remote_addr; event.event = RDMA_CM_EVENT_CONNECT_REQUEST; event.param.conn.private_data = iw_event->private_data; event.param.conn.private_data_len = iw_event->private_data_len; event.param.conn.initiator_depth = iw_event->ird; event.param.conn.responder_resources = iw_event->ord; listen_id = cm_id->context; mutex_lock(&listen_id->handler_mutex); if (READ_ONCE(listen_id->state) != RDMA_CM_LISTEN) goto out; /* Create a new RDMA id for the new IW CM ID */ conn_id = __rdma_create_id(listen_id->id.route.addr.dev_addr.net, listen_id->id.event_handler, listen_id->id.context, RDMA_PS_TCP, IB_QPT_RC, listen_id); if (IS_ERR(conn_id)) { ret = -ENOMEM; goto out; } mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING); conn_id->state = RDMA_CM_CONNECT; ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr); if (ret) { mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } ret = cma_iw_acquire_dev(conn_id, listen_id); if (ret) { mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } conn_id->cm_id.iw = cm_id; cm_id->context = conn_id; cm_id->cm_handler = cma_iw_handler; memcpy(cma_src_addr(conn_id), laddr, rdma_addr_size(laddr)); memcpy(cma_dst_addr(conn_id), raddr, rdma_addr_size(raddr)); ret = cma_cm_event_handler(conn_id, &event); if (ret) { /* User wants to destroy the CM ID */ conn_id->cm_id.iw = NULL; mutex_unlock(&listen_id->handler_mutex); destroy_id_handler_unlock(conn_id); return ret; } mutex_unlock(&conn_id->handler_mutex); out: mutex_unlock(&listen_id->handler_mutex); return ret; } static int cma_ib_listen(struct rdma_id_private *id_priv) { struct sockaddr *addr; struct ib_cm_id *id; __be64 svc_id; addr = cma_src_addr(id_priv); svc_id = rdma_get_service_id(&id_priv->id, addr); id = ib_cm_insert_listen(id_priv->id.device, cma_ib_req_handler, svc_id); if (IS_ERR(id)) return PTR_ERR(id); id_priv->cm_id.ib = id; return 0; } static int cma_iw_listen(struct rdma_id_private *id_priv, int backlog) { int ret; struct iw_cm_id *id; id = iw_create_cm_id(id_priv->id.device, iw_conn_req_handler, id_priv); if (IS_ERR(id)) return PTR_ERR(id); mutex_lock(&id_priv->qp_mutex); id->tos = id_priv->tos; id->tos_set = id_priv->tos_set; mutex_unlock(&id_priv->qp_mutex); id->afonly = id_priv->afonly; id_priv->cm_id.iw = id; memcpy(&id_priv->cm_id.iw->local_addr, cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); ret = iw_cm_listen(id_priv->cm_id.iw, backlog); if (ret) { iw_destroy_cm_id(id_priv->cm_id.iw); id_priv->cm_id.iw = NULL; } return ret; } static int cma_listen_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) { struct rdma_id_private *id_priv = id->context; /* Listening IDs are always destroyed on removal */ if (event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) return -1; id->context = id_priv->id.context; id->event_handler = id_priv->id.event_handler; trace_cm_event_handler(id_priv, event); return id_priv->id.event_handler(id, event); } static int cma_listen_on_dev(struct rdma_id_private *id_priv, struct cma_device *cma_dev, struct rdma_id_private **to_destroy) { struct rdma_id_private *dev_id_priv; struct net *net = id_priv->id.route.addr.dev_addr.net; int ret; lockdep_assert_held(&lock); *to_destroy = NULL; if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1)) return 0; if (id_priv->restricted_node_type != RDMA_NODE_UNSPECIFIED && id_priv->restricted_node_type != cma_dev->device->node_type) return 0; dev_id_priv = __rdma_create_id(net, cma_listen_handler, id_priv, id_priv->id.ps, id_priv->id.qp_type, id_priv); if (IS_ERR(dev_id_priv)) return PTR_ERR(dev_id_priv); dev_id_priv->restricted_node_type = id_priv->restricted_node_type; dev_id_priv->state = RDMA_CM_ADDR_BOUND; memcpy(cma_src_addr(dev_id_priv), cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); _cma_attach_to_dev(dev_id_priv, cma_dev); rdma_restrack_add(&dev_id_priv->res); cma_id_get(id_priv); dev_id_priv->internal_id = 1; dev_id_priv->afonly = id_priv->afonly; mutex_lock(&id_priv->qp_mutex); dev_id_priv->tos_set = id_priv->tos_set; dev_id_priv->tos = id_priv->tos; mutex_unlock(&id_priv->qp_mutex); ret = rdma_listen(&dev_id_priv->id, id_priv->backlog); if (ret) goto err_listen; list_add_tail(&dev_id_priv->listen_item, &id_priv->listen_list); return 0; err_listen: /* Caller must destroy this after releasing lock */ *to_destroy = dev_id_priv; dev_warn(&cma_dev->device->dev, "RDMA CMA: %s, error %d\n", __func__, ret); return ret; } static int cma_listen_on_all(struct rdma_id_private *id_priv) { struct rdma_id_private *to_destroy; struct cma_device *cma_dev; int ret; mutex_lock(&lock); list_add_tail(&id_priv->listen_any_item, &listen_any_list); list_for_each_entry(cma_dev, &dev_list, list) { ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy); if (ret) { /* Prevent racing with cma_process_remove() */ if (to_destroy) list_del_init(&to_destroy->device_item); goto err_listen; } } mutex_unlock(&lock); return 0; err_listen: _cma_cancel_listens(id_priv); mutex_unlock(&lock); if (to_destroy) rdma_destroy_id(&to_destroy->id); return ret; } void rdma_set_service_type(struct rdma_cm_id *id, int tos) { struct rdma_id_private *id_priv; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->tos = (u8) tos; id_priv->tos_set = true; mutex_unlock(&id_priv->qp_mutex); } EXPORT_SYMBOL(rdma_set_service_type); /** * rdma_set_ack_timeout() - Set the ack timeout of QP associated * with a connection identifier. * @id: Communication identifier to associated with service type. * @timeout: Ack timeout to set a QP, expressed as 4.096 * 2^(timeout) usec. * * This function should be called before rdma_connect() on active side, * and on passive side before rdma_accept(). It is applicable to primary * path only. The timeout will affect the local side of the QP, it is not * negotiated with remote side and zero disables the timer. In case it is * set before rdma_resolve_route, the value will also be used to determine * PacketLifeTime for RoCE. * * Return: 0 for success */ int rdma_set_ack_timeout(struct rdma_cm_id *id, u8 timeout) { struct rdma_id_private *id_priv; if (id->qp_type != IB_QPT_RC && id->qp_type != IB_QPT_XRC_INI) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->timeout = timeout; id_priv->timeout_set = true; mutex_unlock(&id_priv->qp_mutex); return 0; } EXPORT_SYMBOL(rdma_set_ack_timeout); /** * rdma_set_min_rnr_timer() - Set the minimum RNR Retry timer of the * QP associated with a connection identifier. * @id: Communication identifier to associated with service type. * @min_rnr_timer: 5-bit value encoded as Table 45: "Encoding for RNR NAK * Timer Field" in the IBTA specification. * * This function should be called before rdma_connect() on active * side, and on passive side before rdma_accept(). The timer value * will be associated with the local QP. When it receives a send it is * not read to handle, typically if the receive queue is empty, an RNR * Retry NAK is returned to the requester with the min_rnr_timer * encoded. The requester will then wait at least the time specified * in the NAK before retrying. The default is zero, which translates * to a minimum RNR Timer value of 655 ms. * * Return: 0 for success */ int rdma_set_min_rnr_timer(struct rdma_cm_id *id, u8 min_rnr_timer) { struct rdma_id_private *id_priv; /* It is a five-bit value */ if (min_rnr_timer & 0xe0) return -EINVAL; if (WARN_ON(id->qp_type != IB_QPT_RC && id->qp_type != IB_QPT_XRC_TGT)) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->qp_mutex); id_priv->min_rnr_timer = min_rnr_timer; id_priv->min_rnr_timer_set = true; mutex_unlock(&id_priv->qp_mutex); return 0; } EXPORT_SYMBOL(rdma_set_min_rnr_timer); static int route_set_path_rec_inbound(struct cma_work *work, struct sa_path_rec *path_rec) { struct rdma_route *route = &work->id->id.route; if (!route->path_rec_inbound) { route->path_rec_inbound = kzalloc_obj(*route->path_rec_inbound); if (!route->path_rec_inbound) return -ENOMEM; } *route->path_rec_inbound = *path_rec; return 0; } static int route_set_path_rec_outbound(struct cma_work *work, struct sa_path_rec *path_rec) { struct rdma_route *route = &work->id->id.route; if (!route->path_rec_outbound) { route->path_rec_outbound = kzalloc_obj(*route->path_rec_outbound); if (!route->path_rec_outbound) return -ENOMEM; } *route->path_rec_outbound = *path_rec; return 0; } static void cma_query_handler(int status, struct sa_path_rec *path_rec, unsigned int num_prs, void *context) { struct cma_work *work = context; struct rdma_route *route; int i; route = &work->id->id.route; if (status) goto fail; for (i = 0; i < num_prs; i++) { if (!path_rec[i].flags || (path_rec[i].flags & IB_PATH_GMP)) *route->path_rec = path_rec[i]; else if (path_rec[i].flags & IB_PATH_INBOUND) status = route_set_path_rec_inbound(work, &path_rec[i]); else if (path_rec[i].flags & IB_PATH_OUTBOUND) status = route_set_path_rec_outbound(work, &path_rec[i]); else status = -EINVAL; if (status) goto fail; } route->num_pri_alt_paths = 1; queue_work(cma_wq, &work->work); return; fail: work->old_state = RDMA_CM_ROUTE_QUERY; work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_ERROR; work->event.status = status; pr_debug_ratelimited("RDMA CM: ROUTE_ERROR: failed to query path. status %d\n", status); queue_work(cma_wq, &work->work); } static int cma_query_ib_route(struct rdma_id_private *id_priv, unsigned long timeout_ms, struct cma_work *work) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct sa_path_rec path_rec; ib_sa_comp_mask comp_mask; struct sockaddr_in6 *sin6; struct sockaddr_ib *sib; memset(&path_rec, 0, sizeof path_rec); if (rdma_cap_opa_ah(id_priv->id.device, id_priv->id.port_num)) path_rec.rec_type = SA_PATH_REC_TYPE_OPA; else path_rec.rec_type = SA_PATH_REC_TYPE_IB; rdma_addr_get_sgid(dev_addr, &path_rec.sgid); rdma_addr_get_dgid(dev_addr, &path_rec.dgid); path_rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); path_rec.numb_path = 1; path_rec.reversible = 1; path_rec.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); comp_mask = IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID | IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH | IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID; switch (cma_family(id_priv)) { case AF_INET: path_rec.qos_class = cpu_to_be16((u16) id_priv->tos); comp_mask |= IB_SA_PATH_REC_QOS_CLASS; break; case AF_INET6: sin6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sin6->sin6_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; break; case AF_IB: sib = (struct sockaddr_ib *) cma_src_addr(id_priv); path_rec.traffic_class = (u8) (be32_to_cpu(sib->sib_flowinfo) >> 20); comp_mask |= IB_SA_PATH_REC_TRAFFIC_CLASS; break; } id_priv->query_id = ib_sa_path_rec_get(&sa_client, id_priv->id.device, id_priv->id.port_num, &path_rec, comp_mask, timeout_ms, GFP_KERNEL, cma_query_handler, work, &id_priv->query); return (id_priv->query_id < 0) ? id_priv->query_id : 0; } static void cma_iboe_join_work_handler(struct work_struct *work) { struct cma_multicast *mc = container_of(work, struct cma_multicast, iboe_join.work); struct rdma_cm_event *event = &mc->iboe_join.event; struct rdma_id_private *id_priv = mc->id_priv; int ret; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; ret = cma_cm_event_handler(id_priv, event); WARN_ON(ret); out_unlock: mutex_unlock(&id_priv->handler_mutex); if (event->event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&event->param.ud.ah_attr); } static void cma_work_handler(struct work_struct *_work) { struct cma_work *work = container_of(_work, struct cma_work, work); struct rdma_id_private *id_priv = work->id; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; if (work->old_state != 0 || work->new_state != 0) { if (!cma_comp_exch(id_priv, work->old_state, work->new_state)) goto out_unlock; } if (cma_cm_event_handler(id_priv, &work->event)) { cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); goto out_free; } out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); out_free: if (work->event.event == RDMA_CM_EVENT_MULTICAST_JOIN) rdma_destroy_ah_attr(&work->event.param.ud.ah_attr); kfree(work); } static void cma_init_resolve_route_work(struct cma_work *work, struct rdma_id_private *id_priv) { work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ROUTE_QUERY; work->new_state = RDMA_CM_ROUTE_RESOLVED; work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED; } static void enqueue_resolve_addr_work(struct cma_work *work, struct rdma_id_private *id_priv) { /* Balances with cma_id_put() in cma_work_handler */ cma_id_get(id_priv); work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ADDR_QUERY; work->new_state = RDMA_CM_ADDR_RESOLVED; work->event.event = RDMA_CM_EVENT_ADDR_RESOLVED; queue_work(cma_wq, &work->work); } static int cma_resolve_ib_route(struct rdma_id_private *id_priv, unsigned long timeout_ms) { struct rdma_route *route = &id_priv->id.route; struct cma_work *work; int ret; work = kzalloc_obj(*work); if (!work) return -ENOMEM; cma_init_resolve_route_work(work, id_priv); if (!route->path_rec) route->path_rec = kmalloc_obj(*route->path_rec); if (!route->path_rec) { ret = -ENOMEM; goto err1; } ret = cma_query_ib_route(id_priv, timeout_ms, work); if (ret) goto err2; return 0; err2: kfree(route->path_rec); route->path_rec = NULL; err1: kfree(work); return ret; } static enum ib_gid_type cma_route_gid_type(enum rdma_network_type network_type, unsigned long supported_gids, enum ib_gid_type default_gid) { if ((network_type == RDMA_NETWORK_IPV4 || network_type == RDMA_NETWORK_IPV6) && test_bit(IB_GID_TYPE_ROCE_UDP_ENCAP, &supported_gids)) return IB_GID_TYPE_ROCE_UDP_ENCAP; return default_gid; } /* * cma_iboe_set_path_rec_l2_fields() is helper function which sets * path record type based on GID type. * It also sets up other L2 fields which includes destination mac address * netdev ifindex, of the path record. * It returns the netdev of the bound interface for this path record entry. */ static struct net_device * cma_iboe_set_path_rec_l2_fields(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; enum ib_gid_type gid_type = IB_GID_TYPE_ROCE; struct rdma_addr *addr = &route->addr; unsigned long supported_gids; struct net_device *ndev; if (!addr->dev_addr.bound_dev_if) return NULL; ndev = dev_get_by_index(addr->dev_addr.net, addr->dev_addr.bound_dev_if); if (!ndev) return NULL; supported_gids = roce_gid_type_mask_support(id_priv->id.device, id_priv->id.port_num); gid_type = cma_route_gid_type(addr->dev_addr.network, supported_gids, id_priv->gid_type); /* Use the hint from IP Stack to select GID Type */ if (gid_type < ib_network_to_gid_type(addr->dev_addr.network)) gid_type = ib_network_to_gid_type(addr->dev_addr.network); route->path_rec->rec_type = sa_conv_gid_to_pathrec_type(gid_type); route->path_rec->roce.route_resolved = true; sa_path_set_dmac(route->path_rec, addr->dev_addr.dst_dev_addr); return ndev; } int rdma_set_ib_path(struct rdma_cm_id *id, struct sa_path_rec *path_rec) { struct rdma_id_private *id_priv; struct net_device *ndev; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_RESOLVED)) return -EINVAL; id->route.path_rec = kmemdup(path_rec, sizeof(*path_rec), GFP_KERNEL); if (!id->route.path_rec) { ret = -ENOMEM; goto err; } if (rdma_protocol_roce(id->device, id->port_num)) { ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err_free; } dev_put(ndev); } id->route.num_pri_alt_paths = 1; return 0; err_free: kfree(id->route.path_rec); id->route.path_rec = NULL; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_ADDR_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_set_ib_path); static int cma_resolve_iw_route(struct rdma_id_private *id_priv) { struct cma_work *work; work = kzalloc_obj(*work); if (!work) return -ENOMEM; cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; } static int get_vlan_ndev_tc(struct net_device *vlan_ndev, int prio) { struct net_device *dev; dev = vlan_dev_real_dev(vlan_ndev); if (dev->num_tc) return netdev_get_prio_tc_map(dev, prio); return (vlan_dev_get_egress_qos_mask(vlan_ndev, prio) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; } struct iboe_prio_tc_map { int input_prio; int output_tc; bool found; }; static int get_lower_vlan_dev_tc(struct net_device *dev, struct netdev_nested_priv *priv) { struct iboe_prio_tc_map *map = (struct iboe_prio_tc_map *)priv->data; if (is_vlan_dev(dev)) map->output_tc = get_vlan_ndev_tc(dev, map->input_prio); else if (dev->num_tc) map->output_tc = netdev_get_prio_tc_map(dev, map->input_prio); else map->output_tc = 0; /* We are interested only in first level VLAN device, so always * return 1 to stop iterating over next level devices. */ map->found = true; return 1; } static int iboe_tos_to_sl(struct net_device *ndev, int tos) { struct iboe_prio_tc_map prio_tc_map = {}; int prio = rt_tos2priority(tos); struct netdev_nested_priv priv; /* If VLAN device, get it directly from the VLAN netdev */ if (is_vlan_dev(ndev)) return get_vlan_ndev_tc(ndev, prio); prio_tc_map.input_prio = prio; priv.data = (void *)&prio_tc_map; rcu_read_lock(); netdev_walk_all_lower_dev_rcu(ndev, get_lower_vlan_dev_tc, &priv); rcu_read_unlock(); /* If map is found from lower device, use it; Otherwise * continue with the current netdevice to get priority to tc map. */ if (prio_tc_map.found) return prio_tc_map.output_tc; else if (ndev->num_tc) return netdev_get_prio_tc_map(ndev, prio); else return 0; } static __be32 cma_get_roce_udp_flow_label(struct rdma_id_private *id_priv) { struct sockaddr_in6 *addr6; u16 dport, sport; u32 hash, fl; addr6 = (struct sockaddr_in6 *)cma_src_addr(id_priv); fl = be32_to_cpu(addr6->sin6_flowinfo) & IB_GRH_FLOWLABEL_MASK; if ((cma_family(id_priv) != AF_INET6) || !fl) { dport = be16_to_cpu(cma_port(cma_dst_addr(id_priv))); sport = be16_to_cpu(cma_port(cma_src_addr(id_priv))); hash = (u32)sport * 31 + dport; fl = hash & IB_GRH_FLOWLABEL_MASK; } return cpu_to_be32(fl); } static int cma_resolve_iboe_route(struct rdma_id_private *id_priv) { struct rdma_route *route = &id_priv->id.route; struct rdma_addr *addr = &route->addr; struct cma_work *work; int ret; struct net_device *ndev; u8 default_roce_tos = id_priv->cma_dev->default_roce_tos[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; u8 tos; mutex_lock(&id_priv->qp_mutex); tos = id_priv->tos_set ? id_priv->tos : default_roce_tos; mutex_unlock(&id_priv->qp_mutex); work = kzalloc_obj(*work); if (!work) return -ENOMEM; route->path_rec = kzalloc_obj(*route->path_rec); if (!route->path_rec) { ret = -ENOMEM; goto err1; } route->num_pri_alt_paths = 1; ndev = cma_iboe_set_path_rec_l2_fields(id_priv); if (!ndev) { ret = -ENODEV; goto err2; } rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &route->path_rec->sgid); rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr, &route->path_rec->dgid); if (((struct sockaddr *)&id_priv->id.route.addr.dst_addr)->sa_family != AF_IB) /* TODO: get the hoplimit from the inet/inet6 device */ route->path_rec->hop_limit = addr->dev_addr.hoplimit; else route->path_rec->hop_limit = 1; route->path_rec->reversible = 1; route->path_rec->pkey = cpu_to_be16(0xffff); route->path_rec->mtu_selector = IB_SA_EQ; route->path_rec->sl = iboe_tos_to_sl(ndev, tos); route->path_rec->traffic_class = tos; route->path_rec->mtu = iboe_get_mtu(ndev->mtu); route->path_rec->rate_selector = IB_SA_EQ; route->path_rec->rate = IB_RATE_PORT_CURRENT; dev_put(ndev); route->path_rec->packet_life_time_selector = IB_SA_EQ; /* In case ACK timeout is set, use this value to calculate * PacketLifeTime. As per IBTA 12.7.34, * local ACK timeout = (2 * PacketLifeTime + Local CA’s ACK delay). * Assuming a negligible local ACK delay, we can use * PacketLifeTime = local ACK timeout/2 * as a reasonable approximation for RoCE networks. */ mutex_lock(&id_priv->qp_mutex); if (id_priv->timeout_set && id_priv->timeout) route->path_rec->packet_life_time = id_priv->timeout - 1; else route->path_rec->packet_life_time = CMA_IBOE_PACKET_LIFETIME; mutex_unlock(&id_priv->qp_mutex); if (!route->path_rec->mtu) { ret = -EINVAL; goto err2; } if (rdma_protocol_roce_udp_encap(id_priv->id.device, id_priv->id.port_num)) route->path_rec->flow_label = cma_get_roce_udp_flow_label(id_priv); cma_init_resolve_route_work(work, id_priv); queue_work(cma_wq, &work->work); return 0; err2: kfree(route->path_rec); route->path_rec = NULL; route->num_pri_alt_paths = 0; err1: kfree(work); return ret; } int rdma_resolve_route(struct rdma_cm_id *id, unsigned long timeout_ms) { struct rdma_id_private *id_priv; enum rdma_cm_state state; int ret; if (!timeout_ms) return -EINVAL; id_priv = container_of(id, struct rdma_id_private, id); state = id_priv->state; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ROUTE_QUERY) && !cma_comp_exch(id_priv, RDMA_CM_ADDRINFO_RESOLVED, RDMA_CM_ROUTE_QUERY)) return -EINVAL; cma_id_get(id_priv); if (rdma_cap_ib_sa(id->device, id->port_num)) ret = cma_resolve_ib_route(id_priv, timeout_ms); else if (rdma_protocol_roce(id->device, id->port_num)) { ret = cma_resolve_iboe_route(id_priv); if (!ret) cma_add_id_to_tree(id_priv); } else if (rdma_protocol_iwarp(id->device, id->port_num)) ret = cma_resolve_iw_route(id_priv); else ret = -ENOSYS; if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ROUTE_QUERY, state); cma_id_put(id_priv); return ret; } EXPORT_SYMBOL(rdma_resolve_route); static void cma_set_loopback(struct sockaddr *addr) { switch (addr->sa_family) { case AF_INET: ((struct sockaddr_in *) addr)->sin_addr.s_addr = htonl(INADDR_LOOPBACK); break; case AF_INET6: ipv6_addr_set(&((struct sockaddr_in6 *) addr)->sin6_addr, 0, 0, 0, htonl(1)); break; default: ib_addr_set(&((struct sockaddr_ib *) addr)->sib_addr, 0, 0, 0, htonl(1)); break; } } static int cma_bind_loopback(struct rdma_id_private *id_priv) { struct cma_device *cma_dev, *cur_dev; union ib_gid gid; enum ib_port_state port_state; unsigned int p; u16 pkey; int ret; cma_dev = NULL; mutex_lock(&lock); list_for_each_entry(cur_dev, &dev_list, list) { if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cur_dev->device, 1)) continue; if (!cma_dev) cma_dev = cur_dev; rdma_for_each_port (cur_dev->device, p) { if (!ib_get_cached_port_state(cur_dev->device, p, &port_state) && port_state == IB_PORT_ACTIVE) { cma_dev = cur_dev; goto port_found; } } } if (!cma_dev) { ret = -ENODEV; goto out; } p = 1; port_found: ret = rdma_query_gid(cma_dev->device, p, 0, &gid); if (ret) goto out; ret = ib_get_cached_pkey(cma_dev->device, p, 0, &pkey); if (ret) goto out; id_priv->id.route.addr.dev_addr.dev_type = (rdma_protocol_ib(cma_dev->device, p)) ? ARPHRD_INFINIBAND : ARPHRD_ETHER; rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid); ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, pkey); id_priv->id.port_num = p; cma_attach_to_dev(id_priv, cma_dev); rdma_restrack_add(&id_priv->res); cma_set_loopback(cma_src_addr(id_priv)); out: mutex_unlock(&lock); return ret; } static void addr_handler(int status, struct sockaddr *src_addr, struct rdma_dev_addr *dev_addr, void *context) { struct rdma_id_private *id_priv = context; struct rdma_cm_event event = {}; struct sockaddr *addr; struct sockaddr_storage old_addr; mutex_lock(&id_priv->handler_mutex); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_RESOLVED)) goto out; /* * Store the previous src address, so that if we fail to acquire * matching rdma device, old address can be restored back, which helps * to cancel the cma listen operation correctly. */ addr = cma_src_addr(id_priv); memcpy(&old_addr, addr, rdma_addr_size(addr)); memcpy(addr, src_addr, rdma_addr_size(src_addr)); if (!status && !id_priv->cma_dev) { status = cma_acquire_dev_by_src_ip(id_priv); if (status) pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to acquire device. status %d\n", status); rdma_restrack_add(&id_priv->res); } else if (status) { pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to resolve IP. status %d\n", status); } if (status) { memcpy(addr, &old_addr, rdma_addr_size((struct sockaddr *)&old_addr)); if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_RESOLVED, RDMA_CM_ADDR_BOUND)) goto out; event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = status; } else event.event = RDMA_CM_EVENT_ADDR_RESOLVED; if (cma_cm_event_handler(id_priv, &event)) { destroy_id_handler_unlock(id_priv); return; } out: mutex_unlock(&id_priv->handler_mutex); } static int cma_resolve_loopback(struct rdma_id_private *id_priv) { struct cma_work *work; union ib_gid gid; int ret; work = kzalloc_obj(*work); if (!work) return -ENOMEM; if (!id_priv->cma_dev) { ret = cma_bind_loopback(id_priv); if (ret) goto err; } rdma_addr_get_sgid(&id_priv->id.route.addr.dev_addr, &gid); rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, &gid); enqueue_resolve_addr_work(work, id_priv); return 0; err: kfree(work); return ret; } static int cma_resolve_ib_addr(struct rdma_id_private *id_priv) { struct cma_work *work; int ret; work = kzalloc_obj(*work); if (!work) return -ENOMEM; if (!id_priv->cma_dev) { ret = cma_resolve_ib_dev(id_priv); if (ret) goto err; } rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *) &(((struct sockaddr_ib *) &id_priv->id.route.addr.dst_addr)->sib_addr)); enqueue_resolve_addr_work(work, id_priv); return 0; err: kfree(work); return ret; } int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse) { struct rdma_id_private *id_priv; unsigned long flags; int ret; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irqsave(&id_priv->lock, flags); if ((reuse && id_priv->state != RDMA_CM_LISTEN) || id_priv->state == RDMA_CM_IDLE) { id_priv->reuseaddr = reuse; ret = 0; } else { ret = -EINVAL; } spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } EXPORT_SYMBOL(rdma_set_reuseaddr); int rdma_set_afonly(struct rdma_cm_id *id, int afonly) { struct rdma_id_private *id_priv; unsigned long flags; int ret; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irqsave(&id_priv->lock, flags); if (id_priv->state == RDMA_CM_IDLE || id_priv->state == RDMA_CM_ADDR_BOUND) { id_priv->options |= (1 << CMA_OPTION_AFONLY); id_priv->afonly = afonly; ret = 0; } else { ret = -EINVAL; } spin_unlock_irqrestore(&id_priv->lock, flags); return ret; } EXPORT_SYMBOL(rdma_set_afonly); static void cma_bind_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { struct sockaddr *addr; struct sockaddr_ib *sib; u64 sid, mask; __be16 port; lockdep_assert_held(&lock); addr = cma_src_addr(id_priv); port = htons(bind_list->port); switch (addr->sa_family) { case AF_INET: ((struct sockaddr_in *) addr)->sin_port = port; break; case AF_INET6: ((struct sockaddr_in6 *) addr)->sin6_port = port; break; case AF_IB: sib = (struct sockaddr_ib *) addr; sid = be64_to_cpu(sib->sib_sid); mask = be64_to_cpu(sib->sib_sid_mask); sib->sib_sid = cpu_to_be64((sid & mask) | (u64) ntohs(port)); sib->sib_sid_mask = cpu_to_be64(~0ULL); break; } id_priv->bind_list = bind_list; hlist_add_head(&id_priv->node, &bind_list->owners); } static int cma_alloc_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv, unsigned short snum) { struct rdma_bind_list *bind_list; int ret; lockdep_assert_held(&lock); bind_list = kzalloc_obj(*bind_list); if (!bind_list) return -ENOMEM; ret = cma_ps_alloc(id_priv->id.route.addr.dev_addr.net, ps, bind_list, snum); if (ret < 0) goto err; bind_list->ps = ps; bind_list->port = snum; cma_bind_port(bind_list, id_priv); return 0; err: kfree(bind_list); return ret == -ENOSPC ? -EADDRNOTAVAIL : ret; } static int cma_port_is_unique(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv) { struct rdma_id_private *cur_id; struct sockaddr *daddr = cma_dst_addr(id_priv); struct sockaddr *saddr = cma_src_addr(id_priv); __be16 dport = cma_port(daddr); lockdep_assert_held(&lock); hlist_for_each_entry(cur_id, &bind_list->owners, node) { struct sockaddr *cur_daddr = cma_dst_addr(cur_id); struct sockaddr *cur_saddr = cma_src_addr(cur_id); __be16 cur_dport = cma_port(cur_daddr); if (id_priv == cur_id) continue; /* different dest port -> unique */ if (!cma_any_port(daddr) && !cma_any_port(cur_daddr) && (dport != cur_dport)) continue; /* different src address -> unique */ if (!cma_any_addr(saddr) && !cma_any_addr(cur_saddr) && cma_addr_cmp(saddr, cur_saddr)) continue; /* different dst address -> unique */ if (!cma_any_addr(daddr) && !cma_any_addr(cur_daddr) && cma_addr_cmp(daddr, cur_daddr)) continue; return -EADDRNOTAVAIL; } return 0; } static int cma_alloc_any_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv) { static unsigned int last_used_port; int low, high, remaining; unsigned int rover; struct net *net = id_priv->id.route.addr.dev_addr.net; lockdep_assert_held(&lock); inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; rover = get_random_u32_inclusive(low, remaining + low - 1); retry: if (last_used_port != rover) { struct rdma_bind_list *bind_list; int ret; bind_list = cma_ps_find(net, ps, (unsigned short)rover); if (!bind_list) { ret = cma_alloc_port(ps, id_priv, rover); } else { ret = cma_port_is_unique(bind_list, id_priv); if (!ret) cma_bind_port(bind_list, id_priv); } /* * Remember previously used port number in order to avoid * re-using same port immediately after it is closed. */ if (!ret) last_used_port = rover; if (ret != -EADDRNOTAVAIL) return ret; } if (--remaining) { rover++; if ((rover < low) || (rover > high)) rover = low; goto retry; } return -EADDRNOTAVAIL; } /* * Check that the requested port is available. This is called when trying to * bind to a specific port, or when trying to listen on a bound port. In * the latter case, the provided id_priv may already be on the bind_list, but * we still need to check that it's okay to start listening. */ static int cma_check_port(struct rdma_bind_list *bind_list, struct rdma_id_private *id_priv, uint8_t reuseaddr) { struct rdma_id_private *cur_id; struct sockaddr *addr, *cur_addr; lockdep_assert_held(&lock); addr = cma_src_addr(id_priv); hlist_for_each_entry(cur_id, &bind_list->owners, node) { if (id_priv == cur_id) continue; if (reuseaddr && cur_id->reuseaddr) continue; cur_addr = cma_src_addr(cur_id); if (id_priv->afonly && cur_id->afonly && (addr->sa_family != cur_addr->sa_family)) continue; if (cma_any_addr(addr) || cma_any_addr(cur_addr)) return -EADDRNOTAVAIL; if (!cma_addr_cmp(addr, cur_addr)) return -EADDRINUSE; } return 0; } static int cma_use_port(enum rdma_ucm_port_space ps, struct rdma_id_private *id_priv) { struct rdma_bind_list *bind_list; unsigned short snum; int ret; lockdep_assert_held(&lock); snum = ntohs(cma_port(cma_src_addr(id_priv))); if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE)) return -EACCES; bind_list = cma_ps_find(id_priv->id.route.addr.dev_addr.net, ps, snum); if (!bind_list) { ret = cma_alloc_port(ps, id_priv, snum); } else { ret = cma_check_port(bind_list, id_priv, id_priv->reuseaddr); if (!ret) cma_bind_port(bind_list, id_priv); } return ret; } static enum rdma_ucm_port_space cma_select_inet_ps(struct rdma_id_private *id_priv) { switch (id_priv->id.ps) { case RDMA_PS_TCP: case RDMA_PS_UDP: case RDMA_PS_IPOIB: case RDMA_PS_IB: return id_priv->id.ps; default: return 0; } } static enum rdma_ucm_port_space cma_select_ib_ps(struct rdma_id_private *id_priv) { enum rdma_ucm_port_space ps = 0; struct sockaddr_ib *sib; u64 sid_ps, mask, sid; sib = (struct sockaddr_ib *) cma_src_addr(id_priv); mask = be64_to_cpu(sib->sib_sid_mask) & RDMA_IB_IP_PS_MASK; sid = be64_to_cpu(sib->sib_sid) & mask; if ((id_priv->id.ps == RDMA_PS_IB) && (sid == (RDMA_IB_IP_PS_IB & mask))) { sid_ps = RDMA_IB_IP_PS_IB; ps = RDMA_PS_IB; } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_TCP)) && (sid == (RDMA_IB_IP_PS_TCP & mask))) { sid_ps = RDMA_IB_IP_PS_TCP; ps = RDMA_PS_TCP; } else if (((id_priv->id.ps == RDMA_PS_IB) || (id_priv->id.ps == RDMA_PS_UDP)) && (sid == (RDMA_IB_IP_PS_UDP & mask))) { sid_ps = RDMA_IB_IP_PS_UDP; ps = RDMA_PS_UDP; } if (ps) { sib->sib_sid = cpu_to_be64(sid_ps | ntohs(cma_port((struct sockaddr *) sib))); sib->sib_sid_mask = cpu_to_be64(RDMA_IB_IP_PS_MASK | be64_to_cpu(sib->sib_sid_mask)); } return ps; } static int cma_get_port(struct rdma_id_private *id_priv) { enum rdma_ucm_port_space ps; int ret; if (cma_family(id_priv) != AF_IB) ps = cma_select_inet_ps(id_priv); else ps = cma_select_ib_ps(id_priv); if (!ps) return -EPROTONOSUPPORT; mutex_lock(&lock); if (cma_any_port(cma_src_addr(id_priv))) ret = cma_alloc_any_port(ps, id_priv); else ret = cma_use_port(ps, id_priv); mutex_unlock(&lock); return ret; } static int cma_check_linklocal(struct rdma_dev_addr *dev_addr, struct sockaddr *addr) { #if IS_ENABLED(CONFIG_IPV6) struct sockaddr_in6 *sin6; if (addr->sa_family != AF_INET6) return 0; sin6 = (struct sockaddr_in6 *) addr; if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)) return 0; if (!sin6->sin6_scope_id) return -EINVAL; dev_addr->bound_dev_if = sin6->sin6_scope_id; #endif return 0; } int rdma_listen(struct rdma_cm_id *id, int backlog) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN)) { struct sockaddr_in any_in = { .sin_family = AF_INET, .sin_addr.s_addr = htonl(INADDR_ANY), }; /* For a well behaved ULP state will be RDMA_CM_IDLE */ ret = rdma_bind_addr(id, (struct sockaddr *)&any_in); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_LISTEN))) return -EINVAL; } /* * Once the ID reaches RDMA_CM_LISTEN it is not allowed to be reusable * any more, and has to be unique in the bind list. */ if (id_priv->reuseaddr) { mutex_lock(&lock); ret = cma_check_port(id_priv->bind_list, id_priv, 0); if (!ret) id_priv->reuseaddr = 0; mutex_unlock(&lock); if (ret) goto err; } id_priv->backlog = backlog; if (id_priv->cma_dev) { if (rdma_cap_ib_cm(id->device, 1)) { ret = cma_ib_listen(id_priv); if (ret) goto err; } else if (rdma_cap_iw_cm(id->device, 1)) { ret = cma_iw_listen(id_priv, backlog); if (ret) goto err; } else { ret = -ENOSYS; goto err; } } else { ret = cma_listen_on_all(id_priv); if (ret) goto err; } return 0; err: id_priv->backlog = 0; /* * All the failure paths that lead here will not allow the req_handler's * to have run. */ cma_comp_exch(id_priv, RDMA_CM_LISTEN, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_listen); static int rdma_bind_addr_dst(struct rdma_id_private *id_priv, struct sockaddr *addr, const struct sockaddr *daddr) { struct sockaddr *id_daddr; int ret; if (addr->sa_family != AF_INET && addr->sa_family != AF_INET6 && addr->sa_family != AF_IB) return -EAFNOSUPPORT; if (!cma_comp_exch(id_priv, RDMA_CM_IDLE, RDMA_CM_ADDR_BOUND)) return -EINVAL; ret = cma_check_linklocal(&id_priv->id.route.addr.dev_addr, addr); if (ret) goto err1; memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr)); if (!cma_any_addr(addr)) { ret = cma_translate_addr(addr, &id_priv->id.route.addr.dev_addr); if (ret) goto err1; ret = cma_acquire_dev_by_src_ip(id_priv); if (ret) goto err1; } if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) { if (addr->sa_family == AF_INET) id_priv->afonly = 1; #if IS_ENABLED(CONFIG_IPV6) else if (addr->sa_family == AF_INET6) { struct net *net = id_priv->id.route.addr.dev_addr.net; id_priv->afonly = net->ipv6.sysctl.bindv6only; } #endif } id_daddr = cma_dst_addr(id_priv); if (daddr != id_daddr) memcpy(id_daddr, daddr, rdma_addr_size(addr)); id_daddr->sa_family = addr->sa_family; ret = cma_get_port(id_priv); if (ret) goto err2; if (!cma_any_addr(addr)) rdma_restrack_add(&id_priv->res); return 0; err2: if (id_priv->cma_dev) cma_release_dev(id_priv); err1: cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_IDLE); return ret; } static int cma_bind_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); struct sockaddr_storage zero_sock = {}; if (src_addr && src_addr->sa_family) return rdma_bind_addr_dst(id_priv, src_addr, dst_addr); /* * When the src_addr is not specified, automatically supply an any addr */ zero_sock.ss_family = dst_addr->sa_family; if (IS_ENABLED(CONFIG_IPV6) && dst_addr->sa_family == AF_INET6) { struct sockaddr_in6 *src_addr6 = (struct sockaddr_in6 *)&zero_sock; struct sockaddr_in6 *dst_addr6 = (struct sockaddr_in6 *)dst_addr; src_addr6->sin6_scope_id = dst_addr6->sin6_scope_id; if (ipv6_addr_type(&dst_addr6->sin6_addr) & IPV6_ADDR_LINKLOCAL) id->route.addr.dev_addr.bound_dev_if = dst_addr6->sin6_scope_id; } else if (dst_addr->sa_family == AF_IB) { ((struct sockaddr_ib *)&zero_sock)->sib_pkey = ((struct sockaddr_ib *)dst_addr)->sib_pkey; } return rdma_bind_addr_dst(id_priv, (struct sockaddr *)&zero_sock, dst_addr); } /* * If required, resolve the source address for bind and leave the id_priv in * state RDMA_CM_ADDR_BOUND. This oddly uses the state to determine the prior * calls made by ULP, a previously bound ID will not be re-bound and src_addr is * ignored. */ static int resolve_prepare_src(struct rdma_id_private *id_priv, struct sockaddr *src_addr, const struct sockaddr *dst_addr) { int ret; if (!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY)) { /* For a well behaved ULP state will be RDMA_CM_IDLE */ ret = cma_bind_addr(&id_priv->id, src_addr, dst_addr); if (ret) return ret; if (WARN_ON(!cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDR_QUERY))) return -EINVAL; } else { memcpy(cma_dst_addr(id_priv), dst_addr, rdma_addr_size(dst_addr)); } if (cma_family(id_priv) != dst_addr->sa_family) { ret = -EINVAL; goto err_state; } return 0; err_state: cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); return ret; } int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr, const struct sockaddr *dst_addr, unsigned long timeout_ms) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; ret = resolve_prepare_src(id_priv, src_addr, dst_addr); if (ret) return ret; if (cma_any_addr(dst_addr)) { ret = cma_resolve_loopback(id_priv); } else { if (dst_addr->sa_family == AF_IB) { ret = cma_resolve_ib_addr(id_priv); } else { /* * The FSM can return back to RDMA_CM_ADDR_BOUND after * rdma_resolve_ip() is called, eg through the error * path in addr_handler(). If this happens the existing * request must be canceled before issuing a new one. * Since canceling a request is a bit slow and this * oddball path is rare, keep track once a request has * been issued. The track turns out to be a permanent * state since this is the only cancel as it is * immediately before rdma_resolve_ip(). */ if (id_priv->used_resolve_ip) rdma_addr_cancel(&id->route.addr.dev_addr); else id_priv->used_resolve_ip = 1; ret = rdma_resolve_ip(cma_src_addr(id_priv), dst_addr, &id->route.addr.dev_addr, timeout_ms, addr_handler, false, id_priv); } } if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ADDR_QUERY, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_resolve_addr); int rdma_restrict_node_type(struct rdma_cm_id *id, u8 node_type) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret = 0; switch (node_type) { case RDMA_NODE_UNSPECIFIED: case RDMA_NODE_IB_CA: case RDMA_NODE_RNIC: break; default: return -EINVAL; } mutex_lock(&lock); if (READ_ONCE(id_priv->state) != RDMA_CM_IDLE) ret = -EALREADY; else id_priv->restricted_node_type = node_type; mutex_unlock(&lock); return ret; } EXPORT_SYMBOL(rdma_restrict_node_type); int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); return rdma_bind_addr_dst(id_priv, addr, cma_dst_addr(id_priv)); } EXPORT_SYMBOL(rdma_bind_addr); static int cma_format_hdr(void *hdr, struct rdma_id_private *id_priv) { struct cma_hdr *cma_hdr; cma_hdr = hdr; cma_hdr->cma_version = CMA_VERSION; if (cma_family(id_priv) == AF_INET) { struct sockaddr_in *src4, *dst4; src4 = (struct sockaddr_in *) cma_src_addr(id_priv); dst4 = (struct sockaddr_in *) cma_dst_addr(id_priv); cma_set_ip_ver(cma_hdr, 4); cma_hdr->src_addr.ip4.addr = src4->sin_addr.s_addr; cma_hdr->dst_addr.ip4.addr = dst4->sin_addr.s_addr; cma_hdr->port = src4->sin_port; } else if (cma_family(id_priv) == AF_INET6) { struct sockaddr_in6 *src6, *dst6; src6 = (struct sockaddr_in6 *) cma_src_addr(id_priv); dst6 = (struct sockaddr_in6 *) cma_dst_addr(id_priv); cma_set_ip_ver(cma_hdr, 6); cma_hdr->src_addr.ip6 = src6->sin6_addr; cma_hdr->dst_addr.ip6 = dst6->sin6_addr; cma_hdr->port = src6->sin6_port; } return 0; } static int cma_sidr_rep_handler(struct ib_cm_id *cm_id, const struct ib_cm_event *ib_event) { struct rdma_id_private *id_priv = cm_id->context; struct rdma_cm_event event = {}; const struct ib_cm_sidr_rep_event_param *rep = &ib_event->param.sidr_rep_rcvd; int ret; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) goto out; switch (ib_event->event) { case IB_CM_SIDR_REQ_ERROR: event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; break; case IB_CM_SIDR_REP_RECEIVED: event.param.ud.private_data = ib_event->private_data; event.param.ud.private_data_len = IB_CM_SIDR_REP_PRIVATE_DATA_SIZE; if (rep->status != IB_SIDR_SUCCESS) { event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = ib_event->param.sidr_rep_rcvd.status; pr_debug_ratelimited("RDMA CM: UNREACHABLE: bad SIDR reply. status %d\n", event.status); break; } ret = cma_set_qkey(id_priv, rep->qkey); if (ret) { pr_debug_ratelimited("RDMA CM: ADDR_ERROR: failed to set qkey. status %d\n", ret); event.event = RDMA_CM_EVENT_ADDR_ERROR; event.status = ret; break; } ib_init_ah_attr_from_path(id_priv->id.device, id_priv->id.port_num, id_priv->id.route.path_rec, &event.param.ud.ah_attr, rep->sgid_attr); event.param.ud.qp_num = rep->qpn; event.param.ud.qkey = rep->qkey; event.event = RDMA_CM_EVENT_ESTABLISHED; event.status = 0; break; default: pr_err("RDMA CMA: unexpected IB CM event: %d\n", ib_event->event); goto out; } ret = cma_cm_event_handler(id_priv, &event); rdma_destroy_ah_attr(&event.param.ud.ah_attr); if (ret) { /* Destroy the CM ID by returning a non-zero value. */ id_priv->cm_id.ib = NULL; destroy_id_handler_unlock(id_priv); return ret; } out: mutex_unlock(&id_priv->handler_mutex); return 0; } static int cma_resolve_ib_udp(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_sidr_req_param req; struct ib_cm_id *id; void *private_data; u8 offset; int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); if (check_add_overflow(offset, conn_param->private_data_len, &req.private_data_len)) return -EINVAL; if (req.private_data_len) { private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; } else { private_data = NULL; } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); if (private_data) { ret = cma_format_hdr(private_data, id_priv); if (ret) goto out; req.private_data = private_data; } id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler, id_priv); if (IS_ERR(id)) { ret = PTR_ERR(id); goto out; } id_priv->cm_id.ib = id; req.path = id_priv->id.route.path_rec; req.sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr; req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.timeout_ms = 1 << (CMA_CM_RESPONSE_TIMEOUT - 8); req.max_cm_retries = CMA_MAX_CM_RETRIES; trace_cm_send_sidr_req(id_priv); ret = ib_send_cm_sidr_req(id_priv->cm_id.ib, &req); if (ret) { ib_destroy_cm_id(id_priv->cm_id.ib); id_priv->cm_id.ib = NULL; } out: kfree(private_data); return ret; } static int cma_connect_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_req_param req; struct rdma_route *route; void *private_data; struct ib_cm_id *id; u8 offset; int ret; memset(&req, 0, sizeof req); offset = cma_user_data_offset(id_priv); if (check_add_overflow(offset, conn_param->private_data_len, &req.private_data_len)) return -EINVAL; if (req.private_data_len) { private_data = kzalloc(req.private_data_len, GFP_ATOMIC); if (!private_data) return -ENOMEM; } else { private_data = NULL; } if (conn_param->private_data && conn_param->private_data_len) memcpy(private_data + offset, conn_param->private_data, conn_param->private_data_len); id = ib_create_cm_id(id_priv->id.device, cma_ib_handler, id_priv); if (IS_ERR(id)) { ret = PTR_ERR(id); goto out; } id_priv->cm_id.ib = id; route = &id_priv->id.route; if (private_data) { ret = cma_format_hdr(private_data, id_priv); if (ret) goto out; req.private_data = private_data; } req.primary_path = &route->path_rec[0]; req.primary_path_inbound = route->path_rec_inbound; req.primary_path_outbound = route->path_rec_outbound; if (route->num_pri_alt_paths == 2) req.alternate_path = &route->path_rec[1]; req.ppath_sgid_attr = id_priv->id.route.addr.dev_addr.sgid_attr; /* Alternate path SGID attribute currently unsupported */ req.service_id = rdma_get_service_id(&id_priv->id, cma_dst_addr(id_priv)); req.qp_num = id_priv->qp_num; req.qp_type = id_priv->id.qp_type; req.starting_psn = id_priv->seq_num; req.responder_resources = conn_param->responder_resources; req.initiator_depth = conn_param->initiator_depth; req.flow_control = conn_param->flow_control; req.retry_count = min_t(u8, 7, conn_param->retry_count); req.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); req.remote_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.local_cm_response_timeout = CMA_CM_RESPONSE_TIMEOUT; req.max_cm_retries = CMA_MAX_CM_RETRIES; req.srq = id_priv->srq ? 1 : 0; req.ece.vendor_id = id_priv->ece.vendor_id; req.ece.attr_mod = id_priv->ece.attr_mod; trace_cm_send_req(id_priv); ret = ib_send_cm_req(id_priv->cm_id.ib, &req); out: if (ret && !IS_ERR(id)) { ib_destroy_cm_id(id); id_priv->cm_id.ib = NULL; } kfree(private_data); return ret; } static int cma_connect_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_id *cm_id; int ret; struct iw_cm_conn_param iw_param; cm_id = iw_create_cm_id(id_priv->id.device, cma_iw_handler, id_priv); if (IS_ERR(cm_id)) return PTR_ERR(cm_id); mutex_lock(&id_priv->qp_mutex); cm_id->tos = id_priv->tos; cm_id->tos_set = id_priv->tos_set; mutex_unlock(&id_priv->qp_mutex); id_priv->cm_id.iw = cm_id; memcpy(&cm_id->local_addr, cma_src_addr(id_priv), rdma_addr_size(cma_src_addr(id_priv))); memcpy(&cm_id->remote_addr, cma_dst_addr(id_priv), rdma_addr_size(cma_dst_addr(id_priv))); ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; if (conn_param) { iw_param.ord = conn_param->initiator_depth; iw_param.ird = conn_param->responder_resources; iw_param.private_data = conn_param->private_data; iw_param.private_data_len = conn_param->private_data_len; iw_param.qpn = id_priv->id.qp ? id_priv->qp_num : conn_param->qp_num; } else { memset(&iw_param, 0, sizeof iw_param); iw_param.qpn = id_priv->qp_num; } ret = iw_cm_connect(cm_id, &iw_param); out: if (ret) { iw_destroy_cm_id(cm_id); id_priv->cm_id.iw = NULL; } return ret; } /** * rdma_connect_locked - Initiate an active connection request. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * * Same as rdma_connect() but can only be called from the * RDMA_CM_EVENT_ROUTE_RESOLVED handler callback. */ int rdma_connect_locked(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; lockdep_assert_held(&id_priv->handler_mutex); if (!cma_comp_exch(id_priv, RDMA_CM_ROUTE_RESOLVED, RDMA_CM_CONNECT)) return -EINVAL; if (!id->qp) { id_priv->qp_num = conn_param->qp_num; id_priv->srq = conn_param->srq; } if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) ret = cma_resolve_ib_udp(id_priv, conn_param); else ret = cma_connect_ib(id_priv, conn_param); } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = cma_connect_iw(id_priv, conn_param); } else { ret = -ENOSYS; } if (ret) goto err_state; return 0; err_state: cma_comp_exch(id_priv, RDMA_CM_CONNECT, RDMA_CM_ROUTE_RESOLVED); return ret; } EXPORT_SYMBOL(rdma_connect_locked); /** * rdma_connect - Initiate an active connection request. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * * Users must have resolved a route for the rdma_cm_id to connect with by having * called rdma_resolve_route before calling this routine. * * This call will either connect to a remote QP or obtain remote QP information * for unconnected rdma_cm_id's. The actual operation is based on the * rdma_cm_id's port space. */ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; mutex_lock(&id_priv->handler_mutex); ret = rdma_connect_locked(id, conn_param); mutex_unlock(&id_priv->handler_mutex); return ret; } EXPORT_SYMBOL(rdma_connect); /** * rdma_connect_ece - Initiate an active connection request with ECE data. * @id: Connection identifier to connect. * @conn_param: Connection information used for connected QPs. * @ece: ECE parameters * * See rdma_connect() explanation. */ int rdma_connect_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); id_priv->ece.vendor_id = ece->vendor_id; id_priv->ece.attr_mod = ece->attr_mod; return rdma_connect(id, conn_param); } EXPORT_SYMBOL(rdma_connect_ece); static int cma_accept_ib(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct ib_cm_rep_param rep; int ret; ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) goto out; ret = cma_modify_qp_rts(id_priv, conn_param); if (ret) goto out; memset(&rep, 0, sizeof rep); rep.qp_num = id_priv->qp_num; rep.starting_psn = id_priv->seq_num; rep.private_data = conn_param->private_data; rep.private_data_len = conn_param->private_data_len; rep.responder_resources = conn_param->responder_resources; rep.initiator_depth = conn_param->initiator_depth; rep.failover_accepted = 0; rep.flow_control = conn_param->flow_control; rep.rnr_retry_count = min_t(u8, 7, conn_param->rnr_retry_count); rep.srq = id_priv->srq ? 1 : 0; rep.ece.vendor_id = id_priv->ece.vendor_id; rep.ece.attr_mod = id_priv->ece.attr_mod; trace_cm_send_rep(id_priv); ret = ib_send_cm_rep(id_priv->cm_id.ib, &rep); out: return ret; } static int cma_accept_iw(struct rdma_id_private *id_priv, struct rdma_conn_param *conn_param) { struct iw_cm_conn_param iw_param; int ret; if (!conn_param) return -EINVAL; ret = cma_modify_qp_rtr(id_priv, conn_param); if (ret) return ret; iw_param.ord = conn_param->initiator_depth; iw_param.ird = conn_param->responder_resources; iw_param.private_data = conn_param->private_data; iw_param.private_data_len = conn_param->private_data_len; if (id_priv->id.qp) iw_param.qpn = id_priv->qp_num; else iw_param.qpn = conn_param->qp_num; return iw_cm_accept(id_priv->cm_id.iw, &iw_param); } static int cma_send_sidr_rep(struct rdma_id_private *id_priv, enum ib_cm_sidr_status status, u32 qkey, const void *private_data, int private_data_len) { struct ib_cm_sidr_rep_param rep; int ret; memset(&rep, 0, sizeof rep); rep.status = status; if (status == IB_SIDR_SUCCESS) { if (qkey) ret = cma_set_qkey(id_priv, qkey); else ret = cma_set_default_qkey(id_priv); if (ret) return ret; rep.qp_num = id_priv->qp_num; rep.qkey = id_priv->qkey; rep.ece.vendor_id = id_priv->ece.vendor_id; rep.ece.attr_mod = id_priv->ece.attr_mod; } rep.private_data = private_data; rep.private_data_len = private_data_len; trace_cm_send_sidr_rep(id_priv); return ib_send_cm_sidr_rep(id_priv->cm_id.ib, &rep); } /** * rdma_accept - Called to accept a connection request or response. * @id: Connection identifier associated with the request. * @conn_param: Information needed to establish the connection. This must be * provided if accepting a connection request. If accepting a connection * response, this parameter must be NULL. * * Typically, this routine is only called by the listener to accept a connection * request. It must also be called on the active side of a connection if the * user is performing their own QP transitions. * * In the case of error, a reject message is sent to the remote side and the * state of the qp associated with the id is modified to error, such that any * previously posted receive buffers would be flushed. * * This function is for use by kernel ULPs and must be called from under the * handler callback. */ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); int ret; lockdep_assert_held(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) != RDMA_CM_CONNECT) return -EINVAL; if (!id->qp && conn_param) { id_priv->qp_num = conn_param->qp_num; id_priv->srq = conn_param->srq; } if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { if (conn_param) ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, conn_param->qkey, conn_param->private_data, conn_param->private_data_len); else ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS, 0, NULL, 0); } else { if (conn_param) ret = cma_accept_ib(id_priv, conn_param); else ret = cma_rep_recv(id_priv); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = cma_accept_iw(id_priv, conn_param); } else { ret = -ENOSYS; } if (ret) goto reject; return 0; reject: cma_modify_qp_err(id_priv); rdma_reject(id, NULL, 0, IB_CM_REJ_CONSUMER_DEFINED); return ret; } EXPORT_SYMBOL(rdma_accept); int rdma_accept_ece(struct rdma_cm_id *id, struct rdma_conn_param *conn_param, struct rdma_ucm_ece *ece) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); id_priv->ece.vendor_id = ece->vendor_id; id_priv->ece.attr_mod = ece->attr_mod; return rdma_accept(id, conn_param); } EXPORT_SYMBOL(rdma_accept_ece); void rdma_lock_handler(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_lock(&id_priv->handler_mutex); } EXPORT_SYMBOL(rdma_lock_handler); void rdma_unlock_handler(struct rdma_cm_id *id) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); mutex_unlock(&id_priv->handler_mutex); } EXPORT_SYMBOL(rdma_unlock_handler); int rdma_notify(struct rdma_cm_id *id, enum ib_event_type event) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; switch (id->device->node_type) { case RDMA_NODE_IB_CA: ret = ib_cm_notify(id_priv->cm_id.ib, event); break; default: ret = 0; break; } return ret; } EXPORT_SYMBOL(rdma_notify); int rdma_reject(struct rdma_cm_id *id, const void *private_data, u8 private_data_len, u8 reason) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; if (rdma_cap_ib_cm(id->device, id->port_num)) { if (id->qp_type == IB_QPT_UD) { ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0, private_data, private_data_len); } else { trace_cm_send_rej(id_priv); ret = ib_send_cm_rej(id_priv->cm_id.ib, reason, NULL, 0, private_data, private_data_len); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_reject(id_priv->cm_id.iw, private_data, private_data_len); } else { ret = -ENOSYS; } return ret; } EXPORT_SYMBOL(rdma_reject); int rdma_disconnect(struct rdma_cm_id *id) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cm_id.ib) return -EINVAL; if (rdma_cap_ib_cm(id->device, id->port_num)) { ret = cma_modify_qp_err(id_priv); if (ret) goto out; /* Initiate or respond to a disconnect. */ trace_cm_disconnect(id_priv); if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0)) { if (!ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0)) trace_cm_sent_drep(id_priv); } else { trace_cm_sent_dreq(id_priv); } } else if (rdma_cap_iw_cm(id->device, id->port_num)) { ret = iw_cm_disconnect(id_priv->cm_id.iw, 0); } else ret = -EINVAL; out: return ret; } EXPORT_SYMBOL(rdma_disconnect); static void cma_make_mc_event(int status, struct rdma_id_private *id_priv, struct ib_sa_multicast *multicast, struct rdma_cm_event *event, struct cma_multicast *mc) { struct rdma_dev_addr *dev_addr; enum ib_gid_type gid_type; struct net_device *ndev; if (status) pr_debug_ratelimited("RDMA CM: MULTICAST_ERROR: failed to join multicast. status %d\n", status); event->status = status; event->param.ud.private_data = mc->context; if (status) { event->event = RDMA_CM_EVENT_MULTICAST_ERROR; return; } dev_addr = &id_priv->id.route.addr.dev_addr; ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); gid_type = id_priv->cma_dev ->default_gid_type[id_priv->id.port_num - rdma_start_port( id_priv->cma_dev->device)]; event->event = RDMA_CM_EVENT_MULTICAST_JOIN; if (ib_init_ah_from_mcmember(id_priv->id.device, id_priv->id.port_num, &multicast->rec, ndev, gid_type, &event->param.ud.ah_attr)) { event->event = RDMA_CM_EVENT_MULTICAST_ERROR; goto out; } event->param.ud.qp_num = 0xFFFFFF; event->param.ud.qkey = id_priv->qkey; out: dev_put(ndev); } static int cma_ib_mc_handler(int status, struct ib_sa_multicast *multicast) { struct cma_multicast *mc = multicast->context; struct rdma_id_private *id_priv = mc->id_priv; struct rdma_cm_event event = {}; int ret = 0; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL || READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING) goto out; ret = cma_set_qkey(id_priv, be32_to_cpu(multicast->rec.qkey)); if (!ret) { cma_make_mc_event(status, id_priv, multicast, &event, mc); ret = cma_cm_event_handler(id_priv, &event); } rdma_destroy_ah_attr(&event.param.ud.ah_attr); WARN_ON(ret); out: mutex_unlock(&id_priv->handler_mutex); return 0; } static void cma_set_mgid(struct rdma_id_private *id_priv, struct sockaddr *addr, union ib_gid *mgid) { unsigned char mc_map[MAX_ADDR_LEN]; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; struct sockaddr_in *sin = (struct sockaddr_in *) addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) addr; if (cma_any_addr(addr)) { memset(mgid, 0, sizeof *mgid); } else if ((addr->sa_family == AF_INET6) && ((be32_to_cpu(sin6->sin6_addr.s6_addr32[0]) & 0xFFF0FFFF) == 0xFF10A01B)) { /* IPv6 address is an SA assigned MGID. */ memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else if (addr->sa_family == AF_IB) { memcpy(mgid, &((struct sockaddr_ib *) addr)->sib_addr, sizeof *mgid); } else if (addr->sa_family == AF_INET6) { ipv6_ib_mc_map(&sin6->sin6_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) mc_map[7] = 0x01; /* Use RDMA CM signature */ *mgid = *(union ib_gid *) (mc_map + 4); } else { ip_ib_mc_map(sin->sin_addr.s_addr, dev_addr->broadcast, mc_map); if (id_priv->id.ps == RDMA_PS_UDP) mc_map[7] = 0x01; /* Use RDMA CM signature */ *mgid = *(union ib_gid *) (mc_map + 4); } } static int cma_join_ib_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { struct ib_sa_mcmember_rec rec; struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; ib_sa_comp_mask comp_mask; int ret; ib_addr_get_mgid(dev_addr, &rec.mgid); ret = ib_sa_get_mcmember_rec(id_priv->id.device, id_priv->id.port_num, &rec.mgid, &rec); if (ret) return ret; if (!id_priv->qkey) { ret = cma_set_default_qkey(id_priv); if (ret) return ret; } cma_set_mgid(id_priv, (struct sockaddr *) &mc->addr, &rec.mgid); rec.qkey = cpu_to_be32(id_priv->qkey); rdma_addr_get_sgid(dev_addr, &rec.port_gid); rec.pkey = cpu_to_be16(ib_addr_get_pkey(dev_addr)); rec.join_state = mc->join_state; comp_mask = IB_SA_MCMEMBER_REC_MGID | IB_SA_MCMEMBER_REC_PORT_GID | IB_SA_MCMEMBER_REC_PKEY | IB_SA_MCMEMBER_REC_JOIN_STATE | IB_SA_MCMEMBER_REC_QKEY | IB_SA_MCMEMBER_REC_SL | IB_SA_MCMEMBER_REC_FLOW_LABEL | IB_SA_MCMEMBER_REC_TRAFFIC_CLASS; if (id_priv->id.ps == RDMA_PS_IPOIB) comp_mask |= IB_SA_MCMEMBER_REC_RATE | IB_SA_MCMEMBER_REC_RATE_SELECTOR | IB_SA_MCMEMBER_REC_MTU_SELECTOR | IB_SA_MCMEMBER_REC_MTU | IB_SA_MCMEMBER_REC_HOP_LIMIT; mc->sa_mc = ib_sa_join_multicast(&sa_client, id_priv->id.device, id_priv->id.port_num, &rec, comp_mask, GFP_KERNEL, cma_ib_mc_handler, mc); return PTR_ERR_OR_ZERO(mc->sa_mc); } static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid, enum ib_gid_type gid_type) { struct sockaddr_in *sin = (struct sockaddr_in *)addr; struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr; if (cma_any_addr(addr)) { memset(mgid, 0, sizeof *mgid); } else if (addr->sa_family == AF_INET6) { memcpy(mgid, &sin6->sin6_addr, sizeof *mgid); } else { mgid->raw[0] = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ? 0 : 0xff; mgid->raw[1] = (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) ? 0 : 0x0e; mgid->raw[2] = 0; mgid->raw[3] = 0; mgid->raw[4] = 0; mgid->raw[5] = 0; mgid->raw[6] = 0; mgid->raw[7] = 0; mgid->raw[8] = 0; mgid->raw[9] = 0; mgid->raw[10] = 0xff; mgid->raw[11] = 0xff; *(__be32 *)(&mgid->raw[12]) = sin->sin_addr.s_addr; } } static int cma_iboe_join_multicast(struct rdma_id_private *id_priv, struct cma_multicast *mc) { struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr; int err = 0; struct sockaddr *addr = (struct sockaddr *)&mc->addr; struct net_device *ndev = NULL; struct ib_sa_multicast ib = {}; enum ib_gid_type gid_type; bool send_only; send_only = mc->join_state == BIT(SENDONLY_FULLMEMBER_JOIN); if (cma_zero_addr(addr)) return -EINVAL; gid_type = id_priv->cma_dev->default_gid_type[id_priv->id.port_num - rdma_start_port(id_priv->cma_dev->device)]; cma_iboe_set_mgid(addr, &ib.rec.mgid, gid_type); ib.rec.pkey = cpu_to_be16(0xffff); if (dev_addr->bound_dev_if) ndev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if); if (!ndev) return -ENODEV; ib.rec.rate = IB_RATE_PORT_CURRENT; ib.rec.hop_limit = 1; ib.rec.mtu = iboe_get_mtu(ndev->mtu); if (addr->sa_family == AF_INET) { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) { ib.rec.hop_limit = IPV6_DEFAULT_HOPLIMIT; if (!send_only) { err = cma_igmp_send(ndev, &ib.rec.mgid, true); } } } else { if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) err = -ENOTSUPP; } dev_put(ndev); if (err || !ib.rec.mtu) return err ?: -EINVAL; if (!id_priv->qkey) cma_set_default_qkey(id_priv); rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr, &ib.rec.port_gid); INIT_WORK(&mc->iboe_join.work, cma_iboe_join_work_handler); cma_make_mc_event(0, id_priv, &ib, &mc->iboe_join.event, mc); queue_work(cma_wq, &mc->iboe_join.work); return 0; } int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr, u8 join_state, void *context) { struct rdma_id_private *id_priv = container_of(id, struct rdma_id_private, id); struct cma_multicast *mc; int ret; /* Not supported for kernel QPs */ if (WARN_ON(id->qp)) return -EINVAL; /* ULP is calling this wrong. */ if (!id->device || (READ_ONCE(id_priv->state) != RDMA_CM_ADDR_BOUND && READ_ONCE(id_priv->state) != RDMA_CM_ADDR_RESOLVED)) return -EINVAL; if (id_priv->id.qp_type != IB_QPT_UD) return -EINVAL; mc = kzalloc_obj(*mc); if (!mc) return -ENOMEM; memcpy(&mc->addr, addr, rdma_addr_size(addr)); mc->context = context; mc->id_priv = id_priv; mc->join_state = join_state; if (rdma_protocol_roce(id->device, id->port_num)) { ret = cma_iboe_join_multicast(id_priv, mc); if (ret) goto out_err; } else if (rdma_cap_ib_mcast(id->device, id->port_num)) { ret = cma_join_ib_multicast(id_priv, mc); if (ret) goto out_err; } else { ret = -ENOSYS; goto out_err; } spin_lock(&id_priv->lock); list_add(&mc->list, &id_priv->mc_list); spin_unlock(&id_priv->lock); return 0; out_err: kfree(mc); return ret; } EXPORT_SYMBOL(rdma_join_multicast); void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr) { struct rdma_id_private *id_priv; struct cma_multicast *mc; id_priv = container_of(id, struct rdma_id_private, id); spin_lock_irq(&id_priv->lock); list_for_each_entry(mc, &id_priv->mc_list, list) { if (memcmp(&mc->addr, addr, rdma_addr_size(addr)) != 0) continue; list_del(&mc->list); spin_unlock_irq(&id_priv->lock); WARN_ON(id_priv->cma_dev->device != id->device); destroy_mc(id_priv, mc); return; } spin_unlock_irq(&id_priv->lock); } EXPORT_SYMBOL(rdma_leave_multicast); static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id_priv) { struct rdma_dev_addr *dev_addr; struct cma_work *work; dev_addr = &id_priv->id.route.addr.dev_addr; if ((dev_addr->bound_dev_if == ndev->ifindex) && (net_eq(dev_net(ndev), dev_addr->net)) && memcmp(dev_addr->src_dev_addr, ndev->dev_addr, ndev->addr_len)) { pr_info("RDMA CM addr change for ndev %s used by id %p\n", ndev->name, &id_priv->id); work = kzalloc_obj(*work); if (!work) return -ENOMEM; INIT_WORK(&work->work, cma_work_handler); work->id = id_priv; work->event.event = RDMA_CM_EVENT_ADDR_CHANGE; cma_id_get(id_priv); queue_work(cma_wq, &work->work); } return 0; } static int cma_netdev_callback(struct notifier_block *self, unsigned long event, void *ptr) { struct net_device *ndev = netdev_notifier_info_to_dev(ptr); struct cma_device *cma_dev; struct rdma_id_private *id_priv; int ret = NOTIFY_DONE; if (event != NETDEV_BONDING_FAILOVER) return NOTIFY_DONE; if (!netif_is_bond_master(ndev)) return NOTIFY_DONE; mutex_lock(&lock); list_for_each_entry(cma_dev, &dev_list, list) list_for_each_entry(id_priv, &cma_dev->id_list, device_item) { ret = cma_netdev_change(ndev, id_priv); if (ret) goto out; } out: mutex_unlock(&lock); return ret; } static void cma_netevent_work_handler(struct work_struct *_work) { struct rdma_id_private *id_priv = container_of(_work, struct rdma_id_private, id.net_work); struct rdma_cm_event event = {}; mutex_lock(&id_priv->handler_mutex); if (READ_ONCE(id_priv->state) == RDMA_CM_DESTROYING || READ_ONCE(id_priv->state) == RDMA_CM_DEVICE_REMOVAL) goto out_unlock; event.event = RDMA_CM_EVENT_UNREACHABLE; event.status = -ETIMEDOUT; if (cma_cm_event_handler(id_priv, &event)) { __acquire(&id_priv->handler_mutex); id_priv->cm_id.ib = NULL; cma_id_put(id_priv); destroy_id_handler_unlock(id_priv); return; } out_unlock: mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); } static int cma_netevent_callback(struct notifier_block *self, unsigned long event, void *ctx) { struct id_table_entry *ips_node = NULL; struct rdma_id_private *current_id; struct neighbour *neigh = ctx; unsigned long flags; if (event != NETEVENT_NEIGH_UPDATE) return NOTIFY_DONE; spin_lock_irqsave(&id_table_lock, flags); if (neigh->tbl->family == AF_INET6) { struct sockaddr_in6 neigh_sock_6; neigh_sock_6.sin6_family = AF_INET6; neigh_sock_6.sin6_addr = *(struct in6_addr *)neigh->primary_key; ips_node = node_from_ndev_ip(&id_table, neigh->dev->ifindex, (struct sockaddr *)&neigh_sock_6); } else if (neigh->tbl->family == AF_INET) { struct sockaddr_in neigh_sock_4; neigh_sock_4.sin_family = AF_INET; neigh_sock_4.sin_addr.s_addr = *(__be32 *)(neigh->primary_key); ips_node = node_from_ndev_ip(&id_table, neigh->dev->ifindex, (struct sockaddr *)&neigh_sock_4); } else goto out; if (!ips_node) goto out; list_for_each_entry(current_id, &ips_node->id_list, id_list_entry) { if (!memcmp(current_id->id.route.addr.dev_addr.dst_dev_addr, neigh->ha, ETH_ALEN)) continue; cma_id_get(current_id); if (!queue_work(cma_wq, ¤t_id->id.net_work)) cma_id_put(current_id); } out: spin_unlock_irqrestore(&id_table_lock, flags); return NOTIFY_DONE; } static struct notifier_block cma_nb = { .notifier_call = cma_netdev_callback }; static struct notifier_block cma_netevent_cb = { .notifier_call = cma_netevent_callback }; static void cma_send_device_removal_put(struct rdma_id_private *id_priv) { struct rdma_cm_event event = { .event = RDMA_CM_EVENT_DEVICE_REMOVAL }; enum rdma_cm_state state; unsigned long flags; mutex_lock(&id_priv->handler_mutex); /* Record that we want to remove the device */ spin_lock_irqsave(&id_priv->lock, flags); state = id_priv->state; if (state == RDMA_CM_DESTROYING || state == RDMA_CM_DEVICE_REMOVAL) { spin_unlock_irqrestore(&id_priv->lock, flags); mutex_unlock(&id_priv->handler_mutex); cma_id_put(id_priv); return; } id_priv->state = RDMA_CM_DEVICE_REMOVAL; spin_unlock_irqrestore(&id_priv->lock, flags); if (cma_cm_event_handler(id_priv, &event)) { /* * At this point the ULP promises it won't call * rdma_destroy_id() concurrently */ cma_id_put(id_priv); mutex_unlock(&id_priv->handler_mutex); trace_cm_id_destroy(id_priv); _destroy_id(id_priv, state); return; } mutex_unlock(&id_priv->handler_mutex); /* * If this races with destroy then the thread that first assigns state * to a destroying does the cancel. */ cma_cancel_operation(id_priv, state); cma_id_put(id_priv); } static void cma_process_remove(struct cma_device *cma_dev) { mutex_lock(&lock); while (!list_empty(&cma_dev->id_list)) { struct rdma_id_private *id_priv = list_first_entry( &cma_dev->id_list, struct rdma_id_private, device_item); list_del_init(&id_priv->listen_item); list_del_init(&id_priv->device_item); cma_id_get(id_priv); mutex_unlock(&lock); cma_send_device_removal_put(id_priv); mutex_lock(&lock); } mutex_unlock(&lock); cma_dev_put(cma_dev); wait_for_completion(&cma_dev->comp); } static bool cma_supported(struct ib_device *device) { u32 i; rdma_for_each_port(device, i) { if (rdma_cap_ib_cm(device, i) || rdma_cap_iw_cm(device, i)) return true; } return false; } static int cma_add_one(struct ib_device *device) { struct rdma_id_private *to_destroy; struct cma_device *cma_dev; struct rdma_id_private *id_priv; unsigned long supported_gids = 0; int ret; u32 i; if (!cma_supported(device)) return -EOPNOTSUPP; cma_dev = kmalloc_obj(*cma_dev); if (!cma_dev) return -ENOMEM; cma_dev->device = device; cma_dev->default_gid_type = kzalloc_objs(*cma_dev->default_gid_type, device->phys_port_cnt); if (!cma_dev->default_gid_type) { ret = -ENOMEM; goto free_cma_dev; } cma_dev->default_roce_tos = kcalloc(device->phys_port_cnt, sizeof(*cma_dev->default_roce_tos), GFP_KERNEL); if (!cma_dev->default_roce_tos) { ret = -ENOMEM; goto free_gid_type; } rdma_for_each_port (device, i) { supported_gids = roce_gid_type_mask_support(device, i); WARN_ON(!supported_gids); if (supported_gids & (1 << CMA_PREFERRED_ROCE_GID_TYPE)) cma_dev->default_gid_type[i - rdma_start_port(device)] = CMA_PREFERRED_ROCE_GID_TYPE; else cma_dev->default_gid_type[i - rdma_start_port(device)] = find_first_bit(&supported_gids, BITS_PER_LONG); cma_dev->default_roce_tos[i - rdma_start_port(device)] = 0; } init_completion(&cma_dev->comp); refcount_set(&cma_dev->refcount, 1); INIT_LIST_HEAD(&cma_dev->id_list); ib_set_client_data(device, &cma_client, cma_dev); mutex_lock(&lock); list_add_tail(&cma_dev->list, &dev_list); list_for_each_entry(id_priv, &listen_any_list, listen_any_item) { ret = cma_listen_on_dev(id_priv, cma_dev, &to_destroy); if (ret) goto free_listen; } mutex_unlock(&lock); trace_cm_add_one(device); return 0; free_listen: list_del(&cma_dev->list); mutex_unlock(&lock); /* cma_process_remove() will delete to_destroy */ cma_process_remove(cma_dev); kfree(cma_dev->default_roce_tos); free_gid_type: kfree(cma_dev->default_gid_type); free_cma_dev: kfree(cma_dev); return ret; } static void cma_remove_one(struct ib_device *device, void *client_data) { struct cma_device *cma_dev = client_data; trace_cm_remove_one(device); mutex_lock(&lock); list_del(&cma_dev->list); mutex_unlock(&lock); cma_process_remove(cma_dev); kfree(cma_dev->default_roce_tos); kfree(cma_dev->default_gid_type); kfree(cma_dev); } static int cma_init_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); xa_init(&pernet->tcp_ps); xa_init(&pernet->udp_ps); xa_init(&pernet->ipoib_ps); xa_init(&pernet->ib_ps); return 0; } static void cma_exit_net(struct net *net) { struct cma_pernet *pernet = cma_pernet(net); WARN_ON(!xa_empty(&pernet->tcp_ps)); WARN_ON(!xa_empty(&pernet->udp_ps)); WARN_ON(!xa_empty(&pernet->ipoib_ps)); WARN_ON(!xa_empty(&pernet->ib_ps)); } static struct pernet_operations cma_pernet_operations = { .init = cma_init_net, .exit = cma_exit_net, .id = &cma_pernet_id, .size = sizeof(struct cma_pernet), }; static int __init cma_init(void) { int ret; /* * There is a rare lock ordering dependency in cma_netdev_callback() * that only happens when bonding is enabled. Teach lockdep that rtnl * must never be nested under lock so it can find these without having * to test with bonding. */ if (IS_ENABLED(CONFIG_LOCKDEP)) { rtnl_lock(); mutex_lock(&lock); mutex_unlock(&lock); rtnl_unlock(); } cma_wq = alloc_ordered_workqueue("rdma_cm", WQ_MEM_RECLAIM); if (!cma_wq) return -ENOMEM; ret = register_pernet_subsys(&cma_pernet_operations); if (ret) goto err_wq; ib_sa_register_client(&sa_client); register_netdevice_notifier(&cma_nb); register_netevent_notifier(&cma_netevent_cb); ret = ib_register_client(&cma_client); if (ret) goto err; ret = cma_configfs_init(); if (ret) goto err_ib; return 0; err_ib: ib_unregister_client(&cma_client); err: unregister_netevent_notifier(&cma_netevent_cb); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); unregister_pernet_subsys(&cma_pernet_operations); err_wq: destroy_workqueue(cma_wq); return ret; } static void __exit cma_cleanup(void) { cma_configfs_exit(); ib_unregister_client(&cma_client); unregister_netevent_notifier(&cma_netevent_cb); unregister_netdevice_notifier(&cma_nb); ib_sa_unregister_client(&sa_client); unregister_pernet_subsys(&cma_pernet_operations); destroy_workqueue(cma_wq); } module_init(cma_init); module_exit(cma_cleanup); static void cma_query_ib_service_handler(int status, struct sa_service_rec *recs, unsigned int num_recs, void *context) { struct cma_work *work = context; struct rdma_id_private *id_priv = work->id; struct sockaddr_ib *addr; if (status) goto fail; if (!num_recs) { status = -ENOENT; goto fail; } if (id_priv->id.route.service_recs) { status = -EALREADY; goto fail; } id_priv->id.route.service_recs = kmalloc_objs(*recs, num_recs); if (!id_priv->id.route.service_recs) { status = -ENOMEM; goto fail; } id_priv->id.route.num_service_recs = num_recs; memcpy(id_priv->id.route.service_recs, recs, sizeof(*recs) * num_recs); addr = (struct sockaddr_ib *)&id_priv->id.route.addr.dst_addr; addr->sib_family = AF_IB; addr->sib_addr = *(struct ib_addr *)&recs->gid; addr->sib_pkey = recs->pkey; addr->sib_sid = recs->id; rdma_addr_set_dgid(&id_priv->id.route.addr.dev_addr, (union ib_gid *)&addr->sib_addr); ib_addr_set_pkey(&id_priv->id.route.addr.dev_addr, ntohs(addr->sib_pkey)); queue_work(cma_wq, &work->work); return; fail: work->old_state = RDMA_CM_ADDRINFO_QUERY; work->new_state = RDMA_CM_ADDR_BOUND; work->event.event = RDMA_CM_EVENT_ADDRINFO_ERROR; work->event.status = status; pr_debug_ratelimited( "RDMA CM: SERVICE_ERROR: failed to query service record. status %d\n", status); queue_work(cma_wq, &work->work); } static int cma_resolve_ib_service(struct rdma_id_private *id_priv, struct rdma_ucm_ib_service *ibs) { struct sa_service_rec sr = {}; ib_sa_comp_mask mask = 0; struct cma_work *work; work = kzalloc_obj(*work); if (!work) return -ENOMEM; cma_id_get(id_priv); work->id = id_priv; INIT_WORK(&work->work, cma_work_handler); work->old_state = RDMA_CM_ADDRINFO_QUERY; work->new_state = RDMA_CM_ADDRINFO_RESOLVED; work->event.event = RDMA_CM_EVENT_ADDRINFO_RESOLVED; if (ibs->flags & RDMA_USER_CM_IB_SERVICE_FLAG_ID) { sr.id = cpu_to_be64(ibs->service_id); mask |= IB_SA_SERVICE_REC_SERVICE_ID; } if (ibs->flags & RDMA_USER_CM_IB_SERVICE_FLAG_NAME) { strscpy(sr.name, ibs->service_name, sizeof(sr.name)); mask |= IB_SA_SERVICE_REC_SERVICE_NAME; } id_priv->query_id = ib_sa_service_rec_get(&sa_client, id_priv->id.device, id_priv->id.port_num, &sr, mask, 2000, GFP_KERNEL, cma_query_ib_service_handler, work, &id_priv->query); if (id_priv->query_id < 0) { cma_id_put(id_priv); kfree(work); return id_priv->query_id; } return 0; } int rdma_resolve_ib_service(struct rdma_cm_id *id, struct rdma_ucm_ib_service *ibs) { struct rdma_id_private *id_priv; int ret; id_priv = container_of(id, struct rdma_id_private, id); if (!id_priv->cma_dev || !cma_comp_exch(id_priv, RDMA_CM_ADDR_BOUND, RDMA_CM_ADDRINFO_QUERY)) return -EINVAL; if (rdma_cap_ib_sa(id->device, id->port_num)) ret = cma_resolve_ib_service(id_priv, ibs); else ret = -EOPNOTSUPP; if (ret) goto err; return 0; err: cma_comp_exch(id_priv, RDMA_CM_ADDRINFO_QUERY, RDMA_CM_ADDR_BOUND); return ret; } EXPORT_SYMBOL(rdma_resolve_ib_service); |
| 7 1 7 1 1 29 10 13 3 4 7 10 14 7 1 1 51 45 3 3 40 9 47 2 41 8 48 1 27 19 41 5 3 3 3 2 36 9 32 3 29 10 3 7 2 2 2 2 9 3 2 4 4 5 5 2 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 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/module.h> #include <linux/errno.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/icmp.h> #include <linux/udp.h> #include <linux/types.h> #include <linux/kernel.h> #include <net/genetlink.h> #include <net/gro.h> #include <net/gue.h> #include <net/fou.h> #include <net/ip.h> #include <net/protocol.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <uapi/linux/fou.h> #include <uapi/linux/genetlink.h> #include "fou_nl.h" struct fou { struct socket *sock; u8 protocol; u8 flags; __be16 port; u8 family; u16 type; struct list_head list; struct rcu_head rcu; }; #define FOU_F_REMCSUM_NOPARTIAL BIT(0) struct fou_cfg { u16 type; u8 protocol; u8 flags; struct udp_port_cfg udp_config; }; static unsigned int fou_net_id; struct fou_net { struct list_head fou_list; struct mutex fou_lock; }; static inline struct fou *fou_from_sock(struct sock *sk) { return rcu_dereference_sk_user_data(sk); } static int fou_recv_pull(struct sk_buff *skb, struct fou *fou, size_t len) { /* Remove 'len' bytes from the packet (UDP header and * FOU header if present). */ if (fou->family == AF_INET) ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len); else ipv6_hdr(skb)->payload_len = htons(ntohs(ipv6_hdr(skb)->payload_len) - len); __skb_pull(skb, len); skb_postpull_rcsum(skb, udp_hdr(skb), len); skb_reset_transport_header(skb); return iptunnel_pull_offloads(skb); } static int fou_udp_recv(struct sock *sk, struct sk_buff *skb) { struct fou *fou = fou_from_sock(sk); if (!fou) return 1; if (fou_recv_pull(skb, fou, sizeof(struct udphdr))) goto drop; return -fou->protocol; drop: kfree_skb(skb); return 0; } static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, void *data, size_t hdrlen, u8 ipproto, bool nopartial) { __be16 *pd = data; size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); size_t plen = sizeof(struct udphdr) + hdrlen + max_t(size_t, offset + sizeof(u16), start); if (skb->remcsum_offload) return guehdr; if (!pskb_may_pull(skb, plen)) return NULL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; skb_remcsum_process(skb, (void *)guehdr + hdrlen, start, offset, nopartial); return guehdr; } static int gue_control_message(struct sk_buff *skb, struct guehdr *guehdr) { /* No support yet */ kfree_skb(skb); return 0; } static int gue_udp_recv(struct sock *sk, struct sk_buff *skb) { struct fou *fou = fou_from_sock(sk); size_t len, optlen, hdrlen; struct guehdr *guehdr; void *data; u16 doffset = 0; u8 proto_ctype; if (!fou) return 1; len = sizeof(struct udphdr) + sizeof(struct guehdr); if (!pskb_may_pull(skb, len)) goto drop; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; switch (guehdr->version) { case 0: /* Full GUE header present */ break; case 1: { /* Direct encapsulation of IPv4 or IPv6 */ int prot; switch (((struct iphdr *)guehdr)->version) { case 4: prot = IPPROTO_IPIP; break; case 6: prot = IPPROTO_IPV6; break; default: goto drop; } if (fou_recv_pull(skb, fou, sizeof(struct udphdr))) goto drop; return -prot; } default: /* Undefined version */ goto drop; } optlen = guehdr->hlen << 2; len += optlen; if (!pskb_may_pull(skb, len)) goto drop; /* guehdr may change after pull */ guehdr = (struct guehdr *)&udp_hdr(skb)[1]; if (validate_gue_flags(guehdr, optlen)) goto drop; hdrlen = sizeof(struct guehdr) + optlen; if (fou->family == AF_INET) ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len); else ipv6_hdr(skb)->payload_len = htons(ntohs(ipv6_hdr(skb)->payload_len) - len); /* Pull csum through the guehdr now . This can be used if * there is a remote checksum offload. */ skb_postpull_rcsum(skb, udp_hdr(skb), len); data = &guehdr[1]; if (guehdr->flags & GUE_FLAG_PRIV) { __be32 flags = *(__be32 *)(data + doffset); doffset += GUE_LEN_PRIV; if (flags & GUE_PFLAG_REMCSUM) { guehdr = gue_remcsum(skb, guehdr, data + doffset, hdrlen, guehdr->proto_ctype, !!(fou->flags & FOU_F_REMCSUM_NOPARTIAL)); if (!guehdr) goto drop; data = &guehdr[1]; doffset += GUE_PLEN_REMCSUM; } } if (unlikely(guehdr->control)) return gue_control_message(skb, guehdr); proto_ctype = guehdr->proto_ctype; if (unlikely(!proto_ctype)) goto drop; __skb_pull(skb, sizeof(struct udphdr) + hdrlen); skb_reset_transport_header(skb); if (iptunnel_pull_offloads(skb)) goto drop; return -proto_ctype; drop: kfree_skb(skb); return 0; } static const struct net_offload *fou_gro_ops(const struct sock *sk, int proto) { const struct net_offload __rcu **offloads; /* FOU doesn't allow IPv4 on IPv6 sockets. */ offloads = sk->sk_family == AF_INET6 ? inet6_offloads : inet_offloads; return rcu_dereference(offloads[proto]); } static struct sk_buff *fou_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { struct fou *fou = fou_from_sock(sk); const struct net_offload *ops; struct sk_buff *pp = NULL; if (!fou) goto out; /* We can clear the encap_mark for FOU as we are essentially doing * one of two possible things. We are either adding an L4 tunnel * header to the outer L3 tunnel header, or we are simply * treating the GRE tunnel header as though it is a UDP protocol * specific header such as VXLAN or GENEVE. */ NAPI_GRO_CB(skb)->encap_mark = 0; /* Flag this frame as already having an outer encap header */ NAPI_GRO_CB(skb)->is_fou = 1; ops = fou_gro_ops(sk, fou->protocol); if (!ops || !ops->callbacks.gro_receive) goto out; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); out: return pp; } static int fou_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct fou *fou = fou_from_sock(sk); const struct net_offload *ops; int err; if (!fou) { err = -ENOENT; goto out; } ops = fou_gro_ops(sk, fou->protocol); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) { err = -ENOSYS; goto out; } err = ops->callbacks.gro_complete(skb, nhoff); skb_set_inner_mac_header(skb, nhoff); out: return err; } static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, struct guehdr *guehdr, void *data, size_t hdrlen, struct gro_remcsum *grc, bool nopartial) { __be16 *pd = data; size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); if (skb->remcsum_offload) return guehdr; if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; guehdr = skb_gro_remcsum_process(skb, (void *)guehdr, off, hdrlen, start, offset, grc, nopartial); skb->remcsum_offload = 1; return guehdr; } static struct sk_buff *gue_gro_receive(struct sock *sk, struct list_head *head, struct sk_buff *skb) { const struct net_offload *ops; struct sk_buff *pp = NULL; struct sk_buff *p; struct guehdr *guehdr; size_t len, optlen, hdrlen, off; void *data; u16 doffset = 0; int flush = 1; struct fou *fou = fou_from_sock(sk); struct gro_remcsum grc; u8 proto; skb_gro_remcsum_init(&grc); if (!fou) goto out; off = skb_gro_offset(skb); len = off + sizeof(*guehdr); guehdr = skb_gro_header(skb, len, off); if (unlikely(!guehdr)) goto out; switch (guehdr->version) { case 0: break; case 1: switch (((struct iphdr *)guehdr)->version) { case 4: proto = IPPROTO_IPIP; break; case 6: proto = IPPROTO_IPV6; break; default: goto out; } goto next_proto; default: goto out; } optlen = guehdr->hlen << 2; len += optlen; if (!skb_gro_may_pull(skb, len)) { guehdr = skb_gro_header_slow(skb, len, off); if (unlikely(!guehdr)) goto out; } if (unlikely(guehdr->control) || guehdr->version != 0 || validate_gue_flags(guehdr, optlen)) goto out; hdrlen = sizeof(*guehdr) + optlen; /* Adjust NAPI_GRO_CB(skb)->csum to account for guehdr, * this is needed if there is a remote checkcsum offload. */ skb_gro_postpull_rcsum(skb, guehdr, hdrlen); data = &guehdr[1]; if (guehdr->flags & GUE_FLAG_PRIV) { __be32 flags = *(__be32 *)(data + doffset); doffset += GUE_LEN_PRIV; if (flags & GUE_PFLAG_REMCSUM) { guehdr = gue_gro_remcsum(skb, off, guehdr, data + doffset, hdrlen, &grc, !!(fou->flags & FOU_F_REMCSUM_NOPARTIAL)); if (!guehdr) goto out; data = &guehdr[1]; doffset += GUE_PLEN_REMCSUM; } } skb_gro_pull(skb, hdrlen); list_for_each_entry(p, head, list) { const struct guehdr *guehdr2; if (!NAPI_GRO_CB(p)->same_flow) continue; guehdr2 = (struct guehdr *)(p->data + off); /* Compare base GUE header to be equal (covers * hlen, version, proto_ctype, and flags. */ if (guehdr->word != guehdr2->word) { NAPI_GRO_CB(p)->same_flow = 0; continue; } /* Compare optional fields are the same. */ if (guehdr->hlen && memcmp(&guehdr[1], &guehdr2[1], guehdr->hlen << 2)) { NAPI_GRO_CB(p)->same_flow = 0; continue; } } proto = guehdr->proto_ctype; next_proto: /* We can clear the encap_mark for GUE as we are essentially doing * one of two possible things. We are either adding an L4 tunnel * header to the outer L3 tunnel header, or we are simply * treating the GRE tunnel header as though it is a UDP protocol * specific header such as VXLAN or GENEVE. */ NAPI_GRO_CB(skb)->encap_mark = 0; /* Flag this frame as already having an outer encap header */ NAPI_GRO_CB(skb)->is_fou = 1; ops = fou_gro_ops(sk, proto); if (!ops || !ops->callbacks.gro_receive) goto out; pp = call_gro_receive(ops->callbacks.gro_receive, head, skb); flush = 0; out: skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } static int gue_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff) { struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff); const struct net_offload *ops; unsigned int guehlen = 0; u8 proto; int err = -ENOENT; switch (guehdr->version) { case 0: proto = guehdr->proto_ctype; guehlen = sizeof(*guehdr) + (guehdr->hlen << 2); break; case 1: switch (((struct iphdr *)guehdr)->version) { case 4: proto = IPPROTO_IPIP; break; case 6: proto = IPPROTO_IPV6; break; default: return err; } break; default: return err; } ops = fou_gro_ops(sk, proto); if (WARN_ON(!ops || !ops->callbacks.gro_complete)) goto out; err = ops->callbacks.gro_complete(skb, nhoff + guehlen); skb_set_inner_mac_header(skb, nhoff + guehlen); out: return err; } static bool fou_cfg_cmp(struct fou *fou, struct fou_cfg *cfg) { struct sock *sk = fou->sock->sk; struct udp_port_cfg *udp_cfg = &cfg->udp_config; if (fou->family != udp_cfg->family || fou->port != udp_cfg->local_udp_port || sk->sk_dport != udp_cfg->peer_udp_port || sk->sk_bound_dev_if != udp_cfg->bind_ifindex) return false; if (fou->family == AF_INET) { if (sk->sk_rcv_saddr != udp_cfg->local_ip.s_addr || sk->sk_daddr != udp_cfg->peer_ip.s_addr) return false; else return true; #if IS_ENABLED(CONFIG_IPV6) } else { if (ipv6_addr_cmp(&sk->sk_v6_rcv_saddr, &udp_cfg->local_ip6) || ipv6_addr_cmp(&sk->sk_v6_daddr, &udp_cfg->peer_ip6)) return false; else return true; #endif } return false; } static int fou_add_to_port_list(struct net *net, struct fou *fou, struct fou_cfg *cfg) { struct fou_net *fn = net_generic(net, fou_net_id); struct fou *fout; mutex_lock(&fn->fou_lock); list_for_each_entry(fout, &fn->fou_list, list) { if (fou_cfg_cmp(fout, cfg)) { mutex_unlock(&fn->fou_lock); return -EALREADY; } } list_add(&fou->list, &fn->fou_list); mutex_unlock(&fn->fou_lock); return 0; } static void fou_release(struct fou *fou) { struct socket *sock = fou->sock; list_del(&fou->list); udp_tunnel_sock_release(sock); kfree_rcu(fou, rcu); } static int fou_create(struct net *net, struct fou_cfg *cfg, struct socket **sockp) { struct socket *sock = NULL; struct fou *fou = NULL; struct sock *sk; struct udp_tunnel_sock_cfg tunnel_cfg; int err; /* Open UDP socket */ err = udp_sock_create(net, &cfg->udp_config, &sock); if (err < 0) goto error; /* Allocate FOU port structure */ fou = kzalloc_obj(*fou); if (!fou) { err = -ENOMEM; goto error; } sk = sock->sk; fou->port = cfg->udp_config.local_udp_port; fou->family = cfg->udp_config.family; fou->flags = cfg->flags; fou->type = cfg->type; fou->sock = sock; memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); tunnel_cfg.encap_type = 1; tunnel_cfg.sk_user_data = fou; tunnel_cfg.encap_destroy = NULL; /* Initial for fou type */ switch (cfg->type) { case FOU_ENCAP_DIRECT: tunnel_cfg.encap_rcv = fou_udp_recv; tunnel_cfg.gro_receive = fou_gro_receive; tunnel_cfg.gro_complete = fou_gro_complete; fou->protocol = cfg->protocol; break; case FOU_ENCAP_GUE: tunnel_cfg.encap_rcv = gue_udp_recv; tunnel_cfg.gro_receive = gue_gro_receive; tunnel_cfg.gro_complete = gue_gro_complete; break; default: err = -EINVAL; goto error; } setup_udp_tunnel_sock(net, sock, &tunnel_cfg); sk->sk_allocation = GFP_ATOMIC; err = fou_add_to_port_list(net, fou, cfg); if (err) goto error; if (sockp) *sockp = sock; return 0; error: kfree(fou); if (sock) udp_tunnel_sock_release(sock); return err; } static int fou_destroy(struct net *net, struct fou_cfg *cfg) { struct fou_net *fn = net_generic(net, fou_net_id); int err = -EINVAL; struct fou *fou; mutex_lock(&fn->fou_lock); list_for_each_entry(fou, &fn->fou_list, list) { if (fou_cfg_cmp(fou, cfg)) { fou_release(fou); err = 0; break; } } mutex_unlock(&fn->fou_lock); return err; } static struct genl_family fou_nl_family; static int parse_nl_config(struct genl_info *info, struct fou_cfg *cfg) { bool has_local = false, has_peer = false; struct nlattr *attr; int ifindex; __be16 port; memset(cfg, 0, sizeof(*cfg)); cfg->udp_config.family = AF_INET; if (info->attrs[FOU_ATTR_AF]) { u8 family = nla_get_u8(info->attrs[FOU_ATTR_AF]); switch (family) { case AF_INET: break; case AF_INET6: cfg->udp_config.ipv6_v6only = 1; break; default: return -EAFNOSUPPORT; } cfg->udp_config.family = family; } if (info->attrs[FOU_ATTR_PORT]) { port = nla_get_be16(info->attrs[FOU_ATTR_PORT]); cfg->udp_config.local_udp_port = port; } if (info->attrs[FOU_ATTR_IPPROTO]) cfg->protocol = nla_get_u8(info->attrs[FOU_ATTR_IPPROTO]); if (info->attrs[FOU_ATTR_TYPE]) cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]); if (info->attrs[FOU_ATTR_REMCSUM_NOPARTIAL]) cfg->flags |= FOU_F_REMCSUM_NOPARTIAL; if (cfg->udp_config.family == AF_INET) { if (info->attrs[FOU_ATTR_LOCAL_V4]) { attr = info->attrs[FOU_ATTR_LOCAL_V4]; cfg->udp_config.local_ip.s_addr = nla_get_in_addr(attr); has_local = true; } if (info->attrs[FOU_ATTR_PEER_V4]) { attr = info->attrs[FOU_ATTR_PEER_V4]; cfg->udp_config.peer_ip.s_addr = nla_get_in_addr(attr); has_peer = true; } #if IS_ENABLED(CONFIG_IPV6) } else { if (info->attrs[FOU_ATTR_LOCAL_V6]) { attr = info->attrs[FOU_ATTR_LOCAL_V6]; cfg->udp_config.local_ip6 = nla_get_in6_addr(attr); has_local = true; } if (info->attrs[FOU_ATTR_PEER_V6]) { attr = info->attrs[FOU_ATTR_PEER_V6]; cfg->udp_config.peer_ip6 = nla_get_in6_addr(attr); has_peer = true; } #endif } if (has_peer) { if (info->attrs[FOU_ATTR_PEER_PORT]) { port = nla_get_be16(info->attrs[FOU_ATTR_PEER_PORT]); cfg->udp_config.peer_udp_port = port; } else { return -EINVAL; } } if (info->attrs[FOU_ATTR_IFINDEX]) { if (!has_local) return -EINVAL; ifindex = nla_get_s32(info->attrs[FOU_ATTR_IFINDEX]); cfg->udp_config.bind_ifindex = ifindex; } return 0; } int fou_nl_add_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct fou_cfg cfg; int err; err = parse_nl_config(info, &cfg); if (err) return err; return fou_create(net, &cfg, NULL); } int fou_nl_del_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct fou_cfg cfg; int err; err = parse_nl_config(info, &cfg); if (err) return err; return fou_destroy(net, &cfg); } static int fou_fill_info(struct fou *fou, struct sk_buff *msg) { struct sock *sk = fou->sock->sk; if (nla_put_u8(msg, FOU_ATTR_AF, fou->sock->sk->sk_family) || nla_put_be16(msg, FOU_ATTR_PORT, fou->port) || nla_put_be16(msg, FOU_ATTR_PEER_PORT, sk->sk_dport) || nla_put_u8(msg, FOU_ATTR_IPPROTO, fou->protocol) || nla_put_u8(msg, FOU_ATTR_TYPE, fou->type) || nla_put_s32(msg, FOU_ATTR_IFINDEX, sk->sk_bound_dev_if)) return -1; if (fou->flags & FOU_F_REMCSUM_NOPARTIAL) if (nla_put_flag(msg, FOU_ATTR_REMCSUM_NOPARTIAL)) return -1; if (fou->sock->sk->sk_family == AF_INET) { if (nla_put_in_addr(msg, FOU_ATTR_LOCAL_V4, sk->sk_rcv_saddr)) return -1; if (nla_put_in_addr(msg, FOU_ATTR_PEER_V4, sk->sk_daddr)) return -1; #if IS_ENABLED(CONFIG_IPV6) } else { if (nla_put_in6_addr(msg, FOU_ATTR_LOCAL_V6, &sk->sk_v6_rcv_saddr)) return -1; if (nla_put_in6_addr(msg, FOU_ATTR_PEER_V6, &sk->sk_v6_daddr)) return -1; #endif } return 0; } static int fou_dump_info(struct fou *fou, u32 portid, u32 seq, u32 flags, struct sk_buff *skb, u8 cmd) { void *hdr; hdr = genlmsg_put(skb, portid, seq, &fou_nl_family, flags, cmd); if (!hdr) return -ENOMEM; if (fou_fill_info(fou, skb) < 0) goto nla_put_failure; genlmsg_end(skb, hdr); return 0; nla_put_failure: genlmsg_cancel(skb, hdr); return -EMSGSIZE; } int fou_nl_get_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = genl_info_net(info); struct fou_net *fn = net_generic(net, fou_net_id); struct sk_buff *msg; struct fou_cfg cfg; struct fou *fout; __be16 port; u8 family; int ret; ret = parse_nl_config(info, &cfg); if (ret) return ret; port = cfg.udp_config.local_udp_port; if (port == 0) return -EINVAL; family = cfg.udp_config.family; if (family != AF_INET && family != AF_INET6) return -EINVAL; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; ret = -ESRCH; mutex_lock(&fn->fou_lock); list_for_each_entry(fout, &fn->fou_list, list) { if (fou_cfg_cmp(fout, &cfg)) { ret = fou_dump_info(fout, info->snd_portid, info->snd_seq, 0, msg, info->genlhdr->cmd); break; } } mutex_unlock(&fn->fou_lock); if (ret < 0) goto out_free; return genlmsg_reply(msg, info); out_free: nlmsg_free(msg); return ret; } int fou_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct fou_net *fn = net_generic(net, fou_net_id); struct fou *fout; int idx = 0, ret; mutex_lock(&fn->fou_lock); list_for_each_entry(fout, &fn->fou_list, list) { if (idx++ < cb->args[0]) continue; ret = fou_dump_info(fout, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, skb, FOU_CMD_GET); if (ret) break; } mutex_unlock(&fn->fou_lock); cb->args[0] = idx; return skb->len; } static struct genl_family fou_nl_family __ro_after_init = { .hdrsize = 0, .name = FOU_GENL_NAME, .version = FOU_GENL_VERSION, .maxattr = FOU_ATTR_MAX, .policy = fou_nl_policy, .netnsok = true, .module = THIS_MODULE, .small_ops = fou_nl_ops, .n_small_ops = ARRAY_SIZE(fou_nl_ops), .resv_start_op = FOU_CMD_GET + 1, }; size_t fou_encap_hlen(struct ip_tunnel_encap *e) { return sizeof(struct udphdr); } EXPORT_SYMBOL(fou_encap_hlen); size_t gue_encap_hlen(struct ip_tunnel_encap *e) { size_t len; bool need_priv = false; len = sizeof(struct udphdr) + sizeof(struct guehdr); if (e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) { len += GUE_PLEN_REMCSUM; need_priv = true; } len += need_priv ? GUE_LEN_PRIV : 0; return len; } EXPORT_SYMBOL(gue_encap_hlen); int __fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, __be16 *sport, int type) { int err; err = iptunnel_handle_offloads(skb, type); if (err) return err; *sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev), skb, 0, 0, false); return 0; } EXPORT_SYMBOL(__fou_build_header); int __gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, __be16 *sport, int type) { struct guehdr *guehdr; size_t hdrlen, optlen = 0; void *data; bool need_priv = false; int err; if ((e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) && skb->ip_summed == CHECKSUM_PARTIAL) { optlen += GUE_PLEN_REMCSUM; type |= SKB_GSO_TUNNEL_REMCSUM; need_priv = true; } optlen += need_priv ? GUE_LEN_PRIV : 0; err = iptunnel_handle_offloads(skb, type); if (err) return err; /* Get source port (based on flow hash) before skb_push */ *sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev), skb, 0, 0, false); hdrlen = sizeof(struct guehdr) + optlen; skb_push(skb, hdrlen); guehdr = (struct guehdr *)skb->data; guehdr->control = 0; guehdr->version = 0; guehdr->hlen = optlen >> 2; guehdr->flags = 0; guehdr->proto_ctype = *protocol; data = &guehdr[1]; if (need_priv) { __be32 *flags = data; guehdr->flags |= GUE_FLAG_PRIV; *flags = 0; data += GUE_LEN_PRIV; if (type & SKB_GSO_TUNNEL_REMCSUM) { u16 csum_start = skb_checksum_start_offset(skb); __be16 *pd = data; if (csum_start < hdrlen) return -EINVAL; csum_start -= hdrlen; pd[0] = htons(csum_start); pd[1] = htons(csum_start + skb->csum_offset); if (!skb_is_gso(skb)) { skb->ip_summed = CHECKSUM_NONE; skb->encapsulation = 0; } *flags |= GUE_PFLAG_REMCSUM; data += GUE_PLEN_REMCSUM; } } return 0; } EXPORT_SYMBOL(__gue_build_header); #ifdef CONFIG_NET_FOU_IP_TUNNELS static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e, struct flowi4 *fl4, u8 *protocol, __be16 sport) { struct udphdr *uh; skb_push(skb, sizeof(struct udphdr)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = e->dport; uh->source = sport; uh->len = htons(skb->len); udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb, fl4->saddr, fl4->daddr, skb->len); *protocol = IPPROTO_UDP; } static int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4) { int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; __be16 sport; int err; err = __fou_build_header(skb, e, protocol, &sport, type); if (err) return err; fou_build_udp(skb, e, fl4, protocol, sport); return 0; } static int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e, u8 *protocol, struct flowi4 *fl4) { int type = e->flags & TUNNEL_ENCAP_FLAG_CSUM ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL; __be16 sport; int err; err = __gue_build_header(skb, e, protocol, &sport, type); if (err) return err; fou_build_udp(skb, e, fl4, protocol, sport); return 0; } static int gue_err_proto_handler(int proto, struct sk_buff *skb, u32 info) { const struct net_protocol *ipprot = rcu_dereference(inet_protos[proto]); if (ipprot && ipprot->err_handler) { if (!ipprot->err_handler(skb, info)) return 0; } return -ENOENT; } static int gue_err(struct sk_buff *skb, u32 info) { int transport_offset = skb_transport_offset(skb); struct guehdr *guehdr; size_t len, optlen; int ret; len = sizeof(struct udphdr) + sizeof(struct guehdr); if (!pskb_may_pull(skb, transport_offset + len)) return -EINVAL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; switch (guehdr->version) { case 0: /* Full GUE header present */ break; case 1: { /* Direct encapsulation of IPv4 or IPv6 */ skb_set_transport_header(skb, -(int)sizeof(struct icmphdr)); switch (((struct iphdr *)guehdr)->version) { case 4: ret = gue_err_proto_handler(IPPROTO_IPIP, skb, info); goto out; #if IS_ENABLED(CONFIG_IPV6) case 6: ret = gue_err_proto_handler(IPPROTO_IPV6, skb, info); goto out; #endif default: ret = -EOPNOTSUPP; goto out; } } default: /* Undefined version */ return -EOPNOTSUPP; } if (guehdr->control) return -ENOENT; optlen = guehdr->hlen << 2; if (!pskb_may_pull(skb, transport_offset + len + optlen)) return -EINVAL; guehdr = (struct guehdr *)&udp_hdr(skb)[1]; if (validate_gue_flags(guehdr, optlen)) return -EINVAL; /* Handling exceptions for direct UDP encapsulation in GUE would lead to * recursion. Besides, this kind of encapsulation can't even be * configured currently. Discard this. */ if (guehdr->proto_ctype == IPPROTO_UDP) return -EOPNOTSUPP; skb_set_transport_header(skb, -(int)sizeof(struct icmphdr)); ret = gue_err_proto_handler(guehdr->proto_ctype, skb, info); out: skb_set_transport_header(skb, transport_offset); return ret; } static const struct ip_tunnel_encap_ops fou_iptun_ops = { .encap_hlen = fou_encap_hlen, .build_header = fou_build_header, .err_handler = gue_err, }; static const struct ip_tunnel_encap_ops gue_iptun_ops = { .encap_hlen = gue_encap_hlen, .build_header = gue_build_header, .err_handler = gue_err, }; static int ip_tunnel_encap_add_fou_ops(void) { int ret; ret = ip_tunnel_encap_add_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU); if (ret < 0) { pr_err("can't add fou ops\n"); return ret; } ret = ip_tunnel_encap_add_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE); if (ret < 0) { pr_err("can't add gue ops\n"); ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU); return ret; } return 0; } static void ip_tunnel_encap_del_fou_ops(void) { ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU); ip_tunnel_encap_del_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE); } #else static int ip_tunnel_encap_add_fou_ops(void) { return 0; } static void ip_tunnel_encap_del_fou_ops(void) { } #endif static __net_init int fou_init_net(struct net *net) { struct fou_net *fn = net_generic(net, fou_net_id); INIT_LIST_HEAD(&fn->fou_list); mutex_init(&fn->fou_lock); return 0; } static __net_exit void fou_exit_net(struct net *net) { struct fou_net *fn = net_generic(net, fou_net_id); struct fou *fou, *next; /* Close all the FOU sockets */ mutex_lock(&fn->fou_lock); list_for_each_entry_safe(fou, next, &fn->fou_list, list) fou_release(fou); mutex_unlock(&fn->fou_lock); } static struct pernet_operations fou_net_ops = { .init = fou_init_net, .exit = fou_exit_net, .id = &fou_net_id, .size = sizeof(struct fou_net), }; static int __init fou_init(void) { int ret; ret = register_pernet_device(&fou_net_ops); if (ret) goto exit; ret = genl_register_family(&fou_nl_family); if (ret < 0) goto unregister; ret = register_fou_bpf(); if (ret < 0) goto kfunc_failed; ret = ip_tunnel_encap_add_fou_ops(); if (ret == 0) return 0; kfunc_failed: genl_unregister_family(&fou_nl_family); unregister: unregister_pernet_device(&fou_net_ops); exit: return ret; } static void __exit fou_fini(void) { ip_tunnel_encap_del_fou_ops(); genl_unregister_family(&fou_nl_family); unregister_pernet_device(&fou_net_ops); } module_init(fou_init); module_exit(fou_fini); MODULE_AUTHOR("Tom Herbert <therbert@google.com>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Foo over UDP"); |
| 5 1 4 3 4 4 15 17 3 1 40 1 1 3 5 26 4 28 2 26 4 27 3 25 5 22 2 20 5 19 10 9 6 15 17 3 5 15 15 5 21 6 6 10 10 4 6 11 10 11 1 9 1 10 9 1 9 1 10 10 11 11 11 11 11 15 15 11 4 4 15 11 4 4 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (c) 2016, Amir Vadai <amir@vadai.me> * Copyright (c) 2016, Mellanox Technologies. All rights reserved. */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/geneve.h> #include <net/vxlan.h> #include <net/erspan.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/dst.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <linux/tc_act/tc_tunnel_key.h> #include <net/tc_act/tc_tunnel_key.h> static struct tc_action_ops act_tunnel_key_ops; TC_INDIRECT_SCOPE int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params; params = rcu_dereference_bh(t->params); tcf_lastuse_update(&t->tcf_tm); tcf_action_update_bstats(&t->common, skb); switch (params->tcft_action) { case TCA_TUNNEL_KEY_ACT_RELEASE: skb_dst_drop(skb); break; case TCA_TUNNEL_KEY_ACT_SET: skb_dst_drop(skb); skb_dst_set(skb, dst_clone(¶ms->tcft_enc_metadata->dst)); break; default: WARN_ONCE(1, "Bad tunnel_key action %d.\n", params->tcft_action); break; } return params->action; } static const struct nla_policy enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC] = { .strict_start_type = TCA_TUNNEL_KEY_ENC_OPTS_VXLAN }, [TCA_TUNNEL_KEY_ENC_OPTS_GENEVE] = { .type = NLA_NESTED }, [TCA_TUNNEL_KEY_ENC_OPTS_VXLAN] = { .type = NLA_NESTED }, [TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN] = { .type = NLA_NESTED }, }; static const struct nla_policy geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] = { .type = NLA_U16 }, [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA] = { .type = NLA_BINARY, .len = 127 }, }; static const struct nla_policy vxlan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP] = { .type = NLA_U32 }, }; static const struct nla_policy erspan_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1] = { [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID] = { .type = NLA_U8 }, }; static int tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1]; int err, data_len, opt_len; u8 *data; err = nla_parse_nested_deprecated(tb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX, nla, geneve_opt_policy, extack); if (err < 0) return err; if (!tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] || !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] || !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]) { NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data"); return -EINVAL; } data = nla_data(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]); data_len = nla_len(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]); if (data_len < 4) { NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long"); return -ERANGE; } if (data_len % 4) { NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long"); return -ERANGE; } opt_len = sizeof(struct geneve_opt) + data_len; if (dst) { struct geneve_opt *opt = dst; WARN_ON(dst_len < opt_len); opt->opt_class = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]); opt->type = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]); opt->length = data_len / 4; /* length is in units of 4 bytes */ opt->r1 = 0; opt->r2 = 0; opt->r3 = 0; memcpy(opt + 1, data, data_len); } return opt_len; } static int tunnel_key_copy_vxlan_opt(const struct nlattr *nla, void *dst, int dst_len, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX + 1]; int err; err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_MAX, nla, vxlan_opt_policy, extack); if (err < 0) return err; if (!tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]) { NL_SET_ERR_MSG(extack, "Missing tunnel key vxlan option gbp"); return -EINVAL; } if (dst) { struct vxlan_metadata *md = dst; md->gbp = nla_get_u32(tb[TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP]); md->gbp &= VXLAN_GBP_MASK; } return sizeof(struct vxlan_metadata); } static int tunnel_key_copy_erspan_opt(const struct nlattr *nla, void *dst, int dst_len, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX + 1]; int err; u8 ver; err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_MAX, nla, erspan_opt_policy, extack); if (err < 0) return err; if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]) { NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option ver"); return -EINVAL; } ver = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER]); if (ver == 1) { if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]) { NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option index"); return -EINVAL; } } else if (ver == 2) { if (!tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR] || !tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]) { NL_SET_ERR_MSG(extack, "Missing tunnel key erspan option dir or hwid"); return -EINVAL; } } else { NL_SET_ERR_MSG(extack, "Tunnel key erspan option ver is incorrect"); return -EINVAL; } if (dst) { struct erspan_metadata *md = dst; md->version = ver; if (ver == 1) { nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX]; md->u.index = nla_get_be32(nla); } else { nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR]; md->u.md2.dir = nla_get_u8(nla); nla = tb[TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID]; set_hwid(&md->u.md2, nla_get_u8(nla)); } } return sizeof(struct erspan_metadata); } static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, int dst_len, struct netlink_ext_ack *extack) { int err, rem, opt_len, len = nla_len(nla), opts_len = 0, type = 0; const struct nlattr *attr, *head = nla_data(nla); err = nla_validate_deprecated(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX, enc_opts_policy, extack); if (err) return err; nla_for_each_attr(attr, head, len, rem) { switch (nla_type(attr)) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: if (type && type != IP_TUNNEL_GENEVE_OPT_BIT) { NL_SET_ERR_MSG(extack, "Duplicate type for geneve options"); return -EINVAL; } opt_len = tunnel_key_copy_geneve_opt(attr, dst, dst_len, extack); if (opt_len < 0) return opt_len; opts_len += opt_len; if (opts_len > IP_TUNNEL_OPTS_MAX) { NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size"); return -EINVAL; } if (dst) { dst_len -= opt_len; dst += opt_len; } type = IP_TUNNEL_GENEVE_OPT_BIT; break; case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: if (type) { NL_SET_ERR_MSG(extack, "Duplicate type for vxlan options"); return -EINVAL; } opt_len = tunnel_key_copy_vxlan_opt(attr, dst, dst_len, extack); if (opt_len < 0) return opt_len; opts_len += opt_len; type = IP_TUNNEL_VXLAN_OPT_BIT; break; case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: if (type) { NL_SET_ERR_MSG(extack, "Duplicate type for erspan options"); return -EINVAL; } opt_len = tunnel_key_copy_erspan_opt(attr, dst, dst_len, extack); if (opt_len < 0) return opt_len; opts_len += opt_len; type = IP_TUNNEL_ERSPAN_OPT_BIT; break; } } if (!opts_len) { NL_SET_ERR_MSG(extack, "Empty list of tunnel options"); return -EINVAL; } if (rem > 0) { NL_SET_ERR_MSG(extack, "Trailing data after parsing tunnel key options attributes"); return -EINVAL; } return opts_len; } static int tunnel_key_get_opts_len(struct nlattr *nla, struct netlink_ext_ack *extack) { return tunnel_key_copy_opts(nla, NULL, 0, extack); } static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info, int opts_len, struct netlink_ext_ack *extack) { info->options_len = opts_len; switch (nla_type(nla_data(nla))) { case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE: #if IS_ENABLED(CONFIG_INET) __set_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else return -EAFNOSUPPORT; #endif case TCA_TUNNEL_KEY_ENC_OPTS_VXLAN: #if IS_ENABLED(CONFIG_INET) __set_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else return -EAFNOSUPPORT; #endif case TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN: #if IS_ENABLED(CONFIG_INET) __set_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags); return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info), opts_len, extack); #else return -EAFNOSUPPORT; #endif default: NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type"); return -EINVAL; } } static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = { [TCA_TUNNEL_KEY_PARMS] = { .len = sizeof(struct tc_tunnel_key) }, [TCA_TUNNEL_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_IPV4_DST] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, [TCA_TUNNEL_KEY_ENC_IPV6_DST] = { .len = sizeof(struct in6_addr) }, [TCA_TUNNEL_KEY_ENC_KEY_ID] = { .type = NLA_U32 }, [TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16}, [TCA_TUNNEL_KEY_NO_CSUM] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_OPTS] = { .type = NLA_NESTED }, [TCA_TUNNEL_KEY_ENC_TOS] = { .type = NLA_U8 }, [TCA_TUNNEL_KEY_ENC_TTL] = { .type = NLA_U8 }, }; static void tunnel_key_release_params(struct tcf_tunnel_key_params *p) { if (!p) return; if (p->tcft_action == TCA_TUNNEL_KEY_ACT_SET) dst_release(&p->tcft_enc_metadata->dst); kfree_rcu(p, rcu); } static int tunnel_key_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 act_flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_tunnel_key_ops.net_id); bool bind = act_flags & TCA_ACT_FLAGS_BIND; struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1]; struct tcf_tunnel_key_params *params_new; IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *metadata = NULL; struct tcf_chain *goto_ch = NULL; struct tc_tunnel_key *parm; struct tcf_tunnel_key *t; bool exists = false; __be16 dst_port = 0; __be64 key_id = 0; int opts_len = 0; u8 tos, ttl; int ret = 0; u32 index; int err; if (!nla) { NL_SET_ERR_MSG(extack, "Tunnel requires attributes to be passed"); return -EINVAL; } err = nla_parse_nested_deprecated(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy, extack); if (err < 0) { NL_SET_ERR_MSG(extack, "Failed to parse nested tunnel key attributes"); return err; } if (!tb[TCA_TUNNEL_KEY_PARMS]) { NL_SET_ERR_MSG(extack, "Missing tunnel key parameters"); return -EINVAL; } parm = nla_data(tb[TCA_TUNNEL_KEY_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; switch (parm->t_action) { case TCA_TUNNEL_KEY_ACT_RELEASE: break; case TCA_TUNNEL_KEY_ACT_SET: if (tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) { __be32 key32; key32 = nla_get_be32(tb[TCA_TUNNEL_KEY_ENC_KEY_ID]); key_id = key32_to_tunnel_id(key32); __set_bit(IP_TUNNEL_KEY_BIT, flags); } __set_bit(IP_TUNNEL_CSUM_BIT, flags); if (tb[TCA_TUNNEL_KEY_NO_CSUM] && nla_get_u8(tb[TCA_TUNNEL_KEY_NO_CSUM])) __clear_bit(IP_TUNNEL_CSUM_BIT, flags); if (nla_get_flag(tb[TCA_TUNNEL_KEY_NO_FRAG])) __set_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, flags); if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT]) dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]); if (tb[TCA_TUNNEL_KEY_ENC_OPTS]) { opts_len = tunnel_key_get_opts_len(tb[TCA_TUNNEL_KEY_ENC_OPTS], extack); if (opts_len < 0) { ret = opts_len; goto err_out; } } tos = 0; if (tb[TCA_TUNNEL_KEY_ENC_TOS]) tos = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TOS]); ttl = 0; if (tb[TCA_TUNNEL_KEY_ENC_TTL]) ttl = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TTL]); if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) { __be32 saddr; __be32 daddr; saddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]); daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]); metadata = __ip_tun_set_dst(saddr, daddr, tos, ttl, dst_port, flags, key_id, opts_len); } else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] && tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) { struct in6_addr saddr; struct in6_addr daddr; saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]); daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]); metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port, 0, flags, key_id, opts_len); } else { NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst"); ret = -EINVAL; goto err_out; } if (!metadata) { NL_SET_ERR_MSG(extack, "Cannot allocate tunnel metadata dst"); ret = -ENOMEM; goto err_out; } #ifdef CONFIG_DST_CACHE ret = dst_cache_init(&metadata->u.tun_info.dst_cache, GFP_KERNEL); if (ret) goto release_tun_meta; #endif if (opts_len) { ret = tunnel_key_opts_set(tb[TCA_TUNNEL_KEY_ENC_OPTS], &metadata->u.tun_info, opts_len, extack); if (ret < 0) goto release_tun_meta; } metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX; break; default: NL_SET_ERR_MSG(extack, "Unknown tunnel key action"); ret = -EINVAL; goto err_out; } if (!exists) { ret = tcf_idr_create_from_flags(tn, index, est, a, &act_tunnel_key_ops, bind, act_flags); if (ret) { NL_SET_ERR_MSG(extack, "Cannot create TC IDR"); goto release_tun_meta; } ret = ACT_P_CREATED; } else if (!(act_flags & TCA_ACT_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "TC IDR already exists"); ret = -EEXIST; goto release_tun_meta; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) { ret = err; exists = true; goto release_tun_meta; } t = to_tunnel_key(*a); params_new = kzalloc(sizeof(*params_new), GFP_KERNEL); if (unlikely(!params_new)) { NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters"); ret = -ENOMEM; exists = true; goto put_chain; } params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; params_new->action = parm->action; spin_lock_bh(&t->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); params_new = rcu_replace_pointer(t->params, params_new, lockdep_is_held(&t->tcf_lock)); spin_unlock_bh(&t->tcf_lock); tunnel_key_release_params(params_new); if (goto_ch) tcf_chain_put_by_act(goto_ch); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_tun_meta: if (metadata) dst_release(&metadata->dst); err_out: if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return ret; } static void tunnel_key_release(struct tc_action *a) { struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params; params = rcu_dereference_protected(t->params, 1); tunnel_key_release_params(params); } static int tunnel_key_geneve_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { const u8 *src = ip_tunnel_info_opts(info); int len = info->options_len; struct nlattr *start; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE); if (!start) return -EMSGSIZE; while (len > 0) { const struct geneve_opt *opt = (const struct geneve_opt *)src; if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS, opt->opt_class) || nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE, opt->type) || nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA, opt->length * 4, opt + 1)) { nla_nest_cancel(skb, start); return -EMSGSIZE; } len -= sizeof(struct geneve_opt) + opt->length * 4; src += sizeof(struct geneve_opt) + opt->length * 4; } nla_nest_end(skb, start); return 0; } static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { const struct vxlan_metadata *md = ip_tunnel_info_opts(info); struct nlattr *start; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN); if (!start) return -EMSGSIZE; if (nla_put_u32(skb, TCA_TUNNEL_KEY_ENC_OPT_VXLAN_GBP, md->gbp)) { nla_nest_cancel(skb, start); return -EMSGSIZE; } nla_nest_end(skb, start); return 0; } static int tunnel_key_erspan_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { const struct erspan_metadata *md = ip_tunnel_info_opts(info); struct nlattr *start; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN); if (!start) return -EMSGSIZE; if (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_VER, md->version)) goto err; if (md->version == 1 && nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_INDEX, md->u.index)) goto err; if (md->version == 2 && (nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_DIR, md->u.md2.dir) || nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_ERSPAN_HWID, get_hwid(&md->u.md2)))) goto err; nla_nest_end(skb, start); return 0; err: nla_nest_cancel(skb, start); return -EMSGSIZE; } static int tunnel_key_opts_dump(struct sk_buff *skb, const struct ip_tunnel_info *info) { struct nlattr *start; int err = -EINVAL; if (!info->options_len) return 0; start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS); if (!start) return -EMSGSIZE; if (test_bit(IP_TUNNEL_GENEVE_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_geneve_opts_dump(skb, info); if (err) goto err_out; } else if (test_bit(IP_TUNNEL_VXLAN_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_vxlan_opts_dump(skb, info); if (err) goto err_out; } else if (test_bit(IP_TUNNEL_ERSPAN_OPT_BIT, info->key.tun_flags)) { err = tunnel_key_erspan_opts_dump(skb, info); if (err) goto err_out; } else { err_out: nla_nest_cancel(skb, start); return err; } nla_nest_end(skb, start); return 0; } static int tunnel_key_dump_addresses(struct sk_buff *skb, const struct ip_tunnel_info *info) { unsigned short family = ip_tunnel_info_af(info); if (family == AF_INET) { __be32 saddr = info->key.u.ipv4.src; __be32 daddr = info->key.u.ipv4.dst; if (!nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_SRC, saddr) && !nla_put_in_addr(skb, TCA_TUNNEL_KEY_ENC_IPV4_DST, daddr)) return 0; } if (family == AF_INET6) { const struct in6_addr *saddr6 = &info->key.u.ipv6.src; const struct in6_addr *daddr6 = &info->key.u.ipv6.dst; if (!nla_put_in6_addr(skb, TCA_TUNNEL_KEY_ENC_IPV6_SRC, saddr6) && !nla_put_in6_addr(skb, TCA_TUNNEL_KEY_ENC_IPV6_DST, daddr6)) return 0; } return -EINVAL; } static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_tunnel_key *t = to_tunnel_key(a); struct tcf_tunnel_key_params *params; struct tc_tunnel_key opt = { .index = t->tcf_index, .refcnt = refcount_read(&t->tcf_refcnt) - ref, .bindcnt = atomic_read(&t->tcf_bindcnt) - bind, }; struct tcf_t tm; rcu_read_lock(); params = rcu_dereference(t->params); opt.action = params->action; opt.t_action = params->tcft_action; if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) { struct ip_tunnel_info *info = ¶ms->tcft_enc_metadata->u.tun_info; struct ip_tunnel_key *key = &info->key; __be32 key_id = tunnel_id_to_key32(key->tun_id); if ((test_bit(IP_TUNNEL_KEY_BIT, key->tun_flags) && nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id)) || tunnel_key_dump_addresses(skb, ¶ms->tcft_enc_metadata->u.tun_info) || (key->tp_dst && nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst)) || nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM, !test_bit(IP_TUNNEL_CSUM_BIT, key->tun_flags)) || (test_bit(IP_TUNNEL_DONT_FRAGMENT_BIT, key->tun_flags) && nla_put_flag(skb, TCA_TUNNEL_KEY_NO_FRAG)) || tunnel_key_opts_dump(skb, info)) goto nla_put_failure; if (key->tos && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TOS, key->tos)) goto nla_put_failure; if (key->ttl && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TTL, key->ttl)) goto nla_put_failure; } tcf_tm_dump(&tm, &t->tcf_tm); if (nla_put_64bit(skb, TCA_TUNNEL_KEY_TM, sizeof(tm), &tm, TCA_TUNNEL_KEY_PAD)) goto nla_put_failure; rcu_read_unlock(); return skb->len; nla_put_failure: rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } static void tcf_tunnel_encap_put_tunnel(void *priv) { struct ip_tunnel_info *tunnel = priv; kfree(tunnel); } static int tcf_tunnel_encap_get_tunnel(struct flow_action_entry *entry, const struct tc_action *act) { entry->tunnel = tcf_tunnel_info_copy(act); if (!entry->tunnel) return -ENOMEM; entry->destructor = tcf_tunnel_encap_put_tunnel; entry->destructor_priv = entry->tunnel; return 0; } static int tcf_tunnel_key_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { int err; if (bind) { struct flow_action_entry *entry = entry_data; if (is_tcf_tunnel_set(act)) { entry->id = FLOW_ACTION_TUNNEL_ENCAP; err = tcf_tunnel_encap_get_tunnel(entry, act); if (err) return err; } else if (is_tcf_tunnel_release(act)) { entry->id = FLOW_ACTION_TUNNEL_DECAP; } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported tunnel key mode offload"); return -EOPNOTSUPP; } *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; if (is_tcf_tunnel_set(act)) fl_action->id = FLOW_ACTION_TUNNEL_ENCAP; else if (is_tcf_tunnel_release(act)) fl_action->id = FLOW_ACTION_TUNNEL_DECAP; else return -EOPNOTSUPP; } return 0; } static struct tc_action_ops act_tunnel_key_ops = { .kind = "tunnel_key", .id = TCA_ID_TUNNEL_KEY, .owner = THIS_MODULE, .act = tunnel_key_act, .dump = tunnel_key_dump, .init = tunnel_key_init, .cleanup = tunnel_key_release, .offload_act_setup = tcf_tunnel_key_offload_act_setup, .size = sizeof(struct tcf_tunnel_key), }; MODULE_ALIAS_NET_ACT("tunnel_key"); static __net_init int tunnel_key_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_tunnel_key_ops.net_id); return tc_action_net_init(net, tn, &act_tunnel_key_ops); } static void __net_exit tunnel_key_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_tunnel_key_ops.net_id); } static struct pernet_operations tunnel_key_net_ops = { .init = tunnel_key_init_net, .exit_batch = tunnel_key_exit_net, .id = &act_tunnel_key_ops.net_id, .size = sizeof(struct tc_action_net), }; static int __init tunnel_key_init_module(void) { return tcf_register_action(&act_tunnel_key_ops, &tunnel_key_net_ops); } static void __exit tunnel_key_cleanup_module(void) { tcf_unregister_action(&act_tunnel_key_ops, &tunnel_key_net_ops); } module_init(tunnel_key_init_module); module_exit(tunnel_key_cleanup_module); MODULE_AUTHOR("Amir Vadai <amir@vadai.me>"); MODULE_DESCRIPTION("ip tunnel manipulation actions"); MODULE_LICENSE("GPL v2"); |
| 3945 2165 127 127 22 22 38 10 28 1860 146 190 25 65 2165 27 157 157 73 81 79 258 2164 749 748 1669 265 2945 2163 114 86 3 5 3 2164 1758 1025 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 | // SPDX-License-Identifier: GPL-2.0-only /* tnum: tracked (or tristate) numbers * * A tnum tracks knowledge about the bits of a value. Each bit can be either * known (0 or 1), or unknown (x). Arithmetic operations on tnums will * propagate the unknown bits such that the tnum result represents all the * possible results for possible values of the operands. */ #include <linux/kernel.h> #include <linux/tnum.h> #include <linux/swab.h> #define TNUM(_v, _m) (struct tnum){.value = _v, .mask = _m} /* A completely unknown value */ const struct tnum tnum_unknown = { .value = 0, .mask = -1 }; struct tnum tnum_const(u64 value) { return TNUM(value, 0); } struct tnum tnum_range(u64 min, u64 max) { u64 chi = min ^ max, delta; u8 bits = fls64(chi); /* special case, needed because 1ULL << 64 is undefined */ if (bits > 63) return tnum_unknown; /* e.g. if chi = 4, bits = 3, delta = (1<<3) - 1 = 7. * if chi = 0, bits = 0, delta = (1<<0) - 1 = 0, so we return * constant min (since min == max). */ delta = (1ULL << bits) - 1; return TNUM(min & ~delta, delta); } struct tnum tnum_lshift(struct tnum a, u8 shift) { return TNUM(a.value << shift, a.mask << shift); } struct tnum tnum_rshift(struct tnum a, u8 shift) { return TNUM(a.value >> shift, a.mask >> shift); } struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness) { /* if a.value is negative, arithmetic shifting by minimum shift * will have larger negative offset compared to more shifting. * If a.value is nonnegative, arithmetic shifting by minimum shift * will have larger positive offset compare to more shifting. */ if (insn_bitness == 32) return TNUM((u32)(((s32)a.value) >> min_shift), (u32)(((s32)a.mask) >> min_shift)); else return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift); } struct tnum tnum_add(struct tnum a, struct tnum b) { u64 sm, sv, sigma, chi, mu; sm = a.mask + b.mask; sv = a.value + b.value; sigma = sm + sv; chi = sigma ^ sv; mu = chi | a.mask | b.mask; return TNUM(sv & ~mu, mu); } struct tnum tnum_sub(struct tnum a, struct tnum b) { u64 dv, alpha, beta, chi, mu; dv = a.value - b.value; alpha = dv + a.mask; beta = dv - b.mask; chi = alpha ^ beta; mu = chi | a.mask | b.mask; return TNUM(dv & ~mu, mu); } struct tnum tnum_neg(struct tnum a) { return tnum_sub(TNUM(0, 0), a); } struct tnum tnum_and(struct tnum a, struct tnum b) { u64 alpha, beta, v; alpha = a.value | a.mask; beta = b.value | b.mask; v = a.value & b.value; return TNUM(v, alpha & beta & ~v); } struct tnum tnum_or(struct tnum a, struct tnum b) { u64 v, mu; v = a.value | b.value; mu = a.mask | b.mask; return TNUM(v, mu & ~v); } struct tnum tnum_xor(struct tnum a, struct tnum b) { u64 v, mu; v = a.value ^ b.value; mu = a.mask | b.mask; return TNUM(v & ~mu, mu); } /* Perform long multiplication, iterating through the bits in a using rshift: * - if LSB(a) is a known 0, keep current accumulator * - if LSB(a) is a known 1, add b to current accumulator * - if LSB(a) is unknown, take a union of the above cases. * * For example: * * acc_0: acc_1: * * 11 * -> 11 * -> 11 * -> union(0011, 1001) == x0x1 * x1 01 11 * ------ ------ ------ * 11 11 11 * xx 00 11 * ------ ------ ------ * ???? 0011 1001 */ struct tnum tnum_mul(struct tnum a, struct tnum b) { struct tnum acc = TNUM(0, 0); while (a.value || a.mask) { /* LSB of tnum a is a certain 1 */ if (a.value & 1) acc = tnum_add(acc, b); /* LSB of tnum a is uncertain */ else if (a.mask & 1) { /* acc = tnum_union(acc_0, acc_1), where acc_0 and * acc_1 are partial accumulators for cases * LSB(a) = certain 0 and LSB(a) = certain 1. * acc_0 = acc + 0 * b = acc. * acc_1 = acc + 1 * b = tnum_add(acc, b). */ acc = tnum_union(acc, tnum_add(acc, b)); } /* Note: no case for LSB is certain 0 */ a = tnum_rshift(a, 1); b = tnum_lshift(b, 1); } return acc; } bool tnum_overlap(struct tnum a, struct tnum b) { u64 mu; mu = ~a.mask & ~b.mask; return (a.value & mu) == (b.value & mu); } /* Note that if a and b disagree - i.e. one has a 'known 1' where the other has * a 'known 0' - this will return a 'known 1' for that bit. */ struct tnum tnum_intersect(struct tnum a, struct tnum b) { u64 v, mu; v = a.value | b.value; mu = a.mask & b.mask; return TNUM(v & ~mu, mu); } /* Returns a tnum with the uncertainty from both a and b, and in addition, new * uncertainty at any position that a and b disagree. This represents a * superset of the union of the concrete sets of both a and b. Despite the * overapproximation, it is optimal. */ struct tnum tnum_union(struct tnum a, struct tnum b) { u64 v = a.value & b.value; u64 mu = (a.value ^ b.value) | a.mask | b.mask; return TNUM(v & ~mu, mu); } struct tnum tnum_cast(struct tnum a, u8 size) { a.value &= (1ULL << (size * 8)) - 1; a.mask &= (1ULL << (size * 8)) - 1; return a; } bool tnum_is_aligned(struct tnum a, u64 size) { if (!size) return true; return !((a.value | a.mask) & (size - 1)); } bool tnum_in(struct tnum a, struct tnum b) { if (b.mask & ~a.mask) return false; b.value &= ~a.mask; return a.value == b.value; } int tnum_sbin(char *str, size_t size, struct tnum a) { size_t n; for (n = 64; n; n--) { if (n < size) { if (a.mask & 1) str[n - 1] = 'x'; else if (a.value & 1) str[n - 1] = '1'; else str[n - 1] = '0'; } a.mask >>= 1; a.value >>= 1; } str[min(size - 1, (size_t)64)] = 0; return 64; } struct tnum tnum_subreg(struct tnum a) { return tnum_cast(a, 4); } struct tnum tnum_clear_subreg(struct tnum a) { return tnum_lshift(tnum_rshift(a, 32), 32); } struct tnum tnum_with_subreg(struct tnum reg, struct tnum subreg) { return tnum_or(tnum_clear_subreg(reg), tnum_subreg(subreg)); } struct tnum tnum_const_subreg(struct tnum a, u32 value) { return tnum_with_subreg(a, tnum_const(value)); } struct tnum tnum_bswap16(struct tnum a) { return TNUM(swab16(a.value & 0xFFFF), swab16(a.mask & 0xFFFF)); } struct tnum tnum_bswap32(struct tnum a) { return TNUM(swab32(a.value & 0xFFFFFFFF), swab32(a.mask & 0xFFFFFFFF)); } struct tnum tnum_bswap64(struct tnum a) { return TNUM(swab64(a.value), swab64(a.mask)); } /* Given tnum t, and a number z such that tmin <= z < tmax, where tmin * is the smallest member of the t (= t.value) and tmax is the largest * member of t (= t.value | t.mask), returns the smallest member of t * larger than z. * * For example, * t = x11100x0 * z = 11110001 (241) * result = 11110010 (242) * * Note: if this function is called with z >= tmax, it just returns * early with tmax; if this function is called with z < tmin, the * algorithm already returns tmin. */ u64 tnum_step(struct tnum t, u64 z) { u64 tmax, d, carry_mask, filled, inc; tmax = t.value | t.mask; /* if z >= largest member of t, return largest member of t */ if (z >= tmax) return tmax; /* if z < smallest member of t, return smallest member of t */ if (z < t.value) return t.value; /* * Let r be the result tnum member, z = t.value + d. * Every tnum member is t.value | s for some submask s of t.mask, * and since t.value & t.mask == 0, t.value | s == t.value + s. * So r > z becomes s > d where d = z - t.value. * * Find the smallest submask s of t.mask greater than d by * "incrementing d within the mask": fill every non-mask * position with 1 (`filled`) so +1 ripples through the gaps, * then keep only mask bits. `carry_mask` additionally fills * positions below the highest non-mask 1 in d, preventing * it from trapping the carry. */ d = z - t.value; carry_mask = (1ULL << fls64(d & ~t.mask)) - 1; filled = d | carry_mask | ~t.mask; inc = (filled + 1) & t.mask; return t.value | inc; } |
| 7 7 5 4 4 10 4 10 10 10 10 7 3 3 4 3 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 10 10 10 10 10 10 10 10 7 4 5 10 10 10 10 10 7 10 10 10 4 4 4 4 4 4 4 4 4 4 4 4 3 3 3 3 3 7 4 4 4 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * * Copyright (C) 1991, 1992, 2002 Linus Torvalds */ /* * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95 * * Removed a lot of unnecessary code and simplified things now that * the buffer cache isn't our primary cache - Andrew Tridgell 12/96 * * Speed up hash, lru, and free list operations. Use gfp() for allocating * hash table, use SLAB cache for buffer heads. SMP threading. -DaveM * * Added 32k buffer block sizes - these are required older ARM systems. - RMK * * async buffer flushing, 1999 Andrea Arcangeli <andrea@suse.de> */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/iomap.h> #include <linux/mm.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/capability.h> #include <linux/blkdev.h> #include <linux/blk-crypto.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> #include <linux/folio_batch.h> #include <linux/sched/mm.h> #include <trace/events/block.h> #include <linux/fscrypt.h> #include <linux/fsverity.h> #include <linux/sched/isolation.h> #include "internal.h" static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) inline void touch_buffer(struct buffer_head *bh) { trace_block_touch_buffer(bh); folio_mark_accessed(bh->b_folio); } EXPORT_SYMBOL(touch_buffer); void __lock_buffer(struct buffer_head *bh) { wait_on_bit_lock_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__lock_buffer); void unlock_buffer(struct buffer_head *bh) { clear_bit_unlock(BH_Lock, &bh->b_state); smp_mb__after_atomic(); wake_up_bit(&bh->b_state, BH_Lock); } EXPORT_SYMBOL(unlock_buffer); /* * Returns if the folio has dirty or writeback buffers. If all the buffers * are unlocked and clean then the folio_test_dirty information is stale. If * any of the buffers are locked, it is assumed they are locked for IO. */ void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { struct buffer_head *head, *bh; *dirty = false; *writeback = false; BUG_ON(!folio_test_locked(folio)); head = folio_buffers(folio); if (!head) return; if (folio_test_writeback(folio)) *writeback = true; bh = head; do { if (buffer_locked(bh)) *writeback = true; if (buffer_dirty(bh)) *dirty = true; bh = bh->b_this_page; } while (bh != head); } /* * Block until a buffer comes unlocked. This doesn't stop it * from becoming locked again - you have to lock it yourself * if you want to preserve its state. */ void __wait_on_buffer(struct buffer_head * bh) { wait_on_bit_io(&bh->b_state, BH_Lock, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(__wait_on_buffer); static void buffer_io_error(struct buffer_head *bh, char *msg) { if (!test_bit(BH_Quiet, &bh->b_state)) printk_ratelimited(KERN_ERR "Buffer I/O error on dev %pg, logical block %llu%s\n", bh->b_bdev, (unsigned long long)bh->b_blocknr, msg); } /* * End-of-IO handler helper function which does not touch the bh after * unlocking it. * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but * a race there is benign: unlock_buffer() only use the bh's address for * hashing after unlocking the buffer, so it doesn't actually touch the bh * itself. */ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { /* This happens, due to failed read-ahead attempts. */ clear_buffer_uptodate(bh); } unlock_buffer(bh); } /* * Default synchronous end-of-IO handler.. Just mark it up-to-date and * unlock the buffer. */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { put_bh(bh); __end_buffer_read_notouch(bh, uptodate); } EXPORT_SYMBOL(end_buffer_read_sync); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost sync page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } unlock_buffer(bh); put_bh(bh); } EXPORT_SYMBOL(end_buffer_write_sync); static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block, bool atomic) { struct address_space *bd_mapping = bdev->bd_mapping; const int blkbits = bd_mapping->host->i_blkbits; struct buffer_head *ret = NULL; pgoff_t index; struct buffer_head *bh; struct buffer_head *head; struct folio *folio; int all_mapped = 1; static DEFINE_RATELIMIT_STATE(last_warned, HZ, 1); index = ((loff_t)block << blkbits) / PAGE_SIZE; folio = __filemap_get_folio(bd_mapping, index, FGP_ACCESSED, 0); if (IS_ERR(folio)) goto out; /* * Folio lock protects the buffers. Callers that cannot block * will fallback to serializing vs try_to_free_buffers() via * the i_private_lock. */ if (atomic) spin_lock(&bd_mapping->i_private_lock); else folio_lock(folio); head = folio_buffers(folio); if (!head) goto out_unlock; /* * Upon a noref migration, the folio lock serializes here; * otherwise bail. */ if (test_bit_acquire(BH_Migrate, &head->b_state)) { WARN_ON(!atomic); goto out_unlock; } bh = head; do { if (!buffer_mapped(bh)) all_mapped = 0; else if (bh->b_blocknr == block) { ret = bh; get_bh(bh); goto out_unlock; } bh = bh->b_this_page; } while (bh != head); /* we might be here because some of the buffers on this page are * not mapped. This is due to various races between * file io on the block device and getblk. It gets dealt with * elsewhere, don't buffer_error if we had some unmapped buffers */ ratelimit_set_flags(&last_warned, RATELIMIT_MSG_ON_RELEASE); if (all_mapped && __ratelimit(&last_warned)) { printk("__find_get_block_slow() failed. block=%llu, " "b_blocknr=%llu, b_state=0x%08lx, b_size=%zu, " "device %pg blocksize: %d\n", (unsigned long long)block, (unsigned long long)bh->b_blocknr, bh->b_state, bh->b_size, bdev, 1 << blkbits); } out_unlock: if (atomic) spin_unlock(&bd_mapping->i_private_lock); else folio_unlock(folio); folio_put(folio); out: return ret; } static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct folio *folio; int folio_uptodate = 1; BUG_ON(!buffer_async_read(bh)); folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { clear_buffer_uptodate(bh); buffer_io_error(bh, ", async page read"); } /* * Be _very_ careful from here on. Bad things can happen if * two buffer heads end IO at almost the same time and both * decide that the page is now completely done. */ first = folio_buffers(folio); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_read(bh); unlock_buffer(bh); tmp = bh; do { if (!buffer_uptodate(tmp)) folio_uptodate = 0; if (buffer_async_read(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } while (tmp != bh); spin_unlock_irqrestore(&first->b_uptodate_lock, flags); folio_end_read(folio, folio_uptodate); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); } struct postprocess_bh_ctx { struct work_struct work; struct buffer_head *bh; struct fsverity_info *vi; }; static void verify_bh(struct work_struct *work) { struct postprocess_bh_ctx *ctx = container_of(work, struct postprocess_bh_ctx, work); struct buffer_head *bh = ctx->bh; bool valid; valid = fsverity_verify_blocks(ctx->vi, bh->b_folio, bh->b_size, bh_offset(bh)); end_buffer_async_read(bh, valid); kfree(ctx); } static void decrypt_bh(struct work_struct *work) { struct postprocess_bh_ctx *ctx = container_of(work, struct postprocess_bh_ctx, work); struct buffer_head *bh = ctx->bh; int err; err = fscrypt_decrypt_pagecache_blocks(bh->b_folio, bh->b_size, bh_offset(bh)); if (err == 0 && ctx->vi) { /* * We use different work queues for decryption and for verity * because verity may require reading metadata pages that need * decryption, and we shouldn't recurse to the same workqueue. */ INIT_WORK(&ctx->work, verify_bh); fsverity_enqueue_verify_work(&ctx->work); return; } end_buffer_async_read(bh, err == 0); kfree(ctx); } /* * I/O completion handler for block_read_full_folio() - pages * which come unlocked at the end of I/O. */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { struct inode *inode = bh->b_folio->mapping->host; bool decrypt = fscrypt_inode_uses_fs_layer_crypto(inode); struct fsverity_info *vi = NULL; /* needed by ext4 */ if (bh->b_folio->index < DIV_ROUND_UP(inode->i_size, PAGE_SIZE)) vi = fsverity_get_info(inode); /* Decrypt (with fscrypt) and/or verify (with fsverity) if needed. */ if (uptodate && (decrypt || vi)) { struct postprocess_bh_ctx *ctx = kmalloc_obj(*ctx, GFP_ATOMIC); if (ctx) { ctx->bh = bh; ctx->vi = vi; if (decrypt) { INIT_WORK(&ctx->work, decrypt_bh); fscrypt_enqueue_decrypt_work(&ctx->work); } else { INIT_WORK(&ctx->work, verify_bh); fsverity_enqueue_verify_work(&ctx->work); } return; } uptodate = 0; } end_buffer_async_read(bh, uptodate); } /* * Completion handler for block_write_full_folio() - folios which are unlocked * during I/O, and which have the writeback flag cleared upon I/O completion. */ static void end_buffer_async_write(struct buffer_head *bh, int uptodate) { unsigned long flags; struct buffer_head *first; struct buffer_head *tmp; struct folio *folio; BUG_ON(!buffer_async_write(bh)); folio = bh->b_folio; if (uptodate) { set_buffer_uptodate(bh); } else { buffer_io_error(bh, ", lost async page write"); mark_buffer_write_io_error(bh); clear_buffer_uptodate(bh); } first = folio_buffers(folio); spin_lock_irqsave(&first->b_uptodate_lock, flags); clear_buffer_async_write(bh); unlock_buffer(bh); tmp = bh->b_this_page; while (tmp != bh) { if (buffer_async_write(tmp)) { BUG_ON(!buffer_locked(tmp)); goto still_busy; } tmp = tmp->b_this_page; } spin_unlock_irqrestore(&first->b_uptodate_lock, flags); folio_end_writeback(folio); return; still_busy: spin_unlock_irqrestore(&first->b_uptodate_lock, flags); } /* * If a page's buffers are under async readin (end_buffer_async_read * completion) then there is a possibility that another thread of * control could lock one of the buffers after it has completed * but while some of the other buffers have not completed. This * locked buffer would confuse end_buffer_async_read() into not unlocking * the page. So the absence of BH_Async_Read tells end_buffer_async_read() * that this buffer is not under async I/O. * * The page comes unlocked when it has no locked buffer_async buffers * left. * * PageLocked prevents anyone starting new async I/O reads any of * the buffers. * * PageWriteback is used to prevent simultaneous writeout of the same * page. * * PageLocked prevents anyone from starting writeback of a page which is * under read I/O (PageWriteback is only ever set against a locked page). */ static void mark_buffer_async_read(struct buffer_head *bh) { bh->b_end_io = end_buffer_async_read_io; set_buffer_async_read(bh); } static void mark_buffer_async_write_endio(struct buffer_head *bh, bh_end_io_t *handler) { bh->b_end_io = handler; set_buffer_async_write(bh); } void mark_buffer_async_write(struct buffer_head *bh) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } EXPORT_SYMBOL(mark_buffer_async_write); /* * fs/buffer.c contains helper functions for buffer-backed address space's * fsync functions. A common requirement for buffer-based filesystems is * that certain data from the backing blockdev needs to be written out for * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * * The functions mmb_mark_buffer_dirty(), mmb_sync(), mmb_has_buffers() * and mmb_invalidate() are provided for the management of a list of dependent * buffers in mapping_metadata_bhs struct. * * The locking is a little subtle: The list of buffer heads is protected by * the lock in mapping_metadata_bhs so functions coming from bdev mapping * (such as try_to_free_buffers()) need to safely get to mapping_metadata_bhs * using RCU, grab the lock, verify we didn't race with somebody detaching the * bh / moving it to different inode and only then proceeding. */ void mmb_init(struct mapping_metadata_bhs *mmb, struct address_space *mapping) { spin_lock_init(&mmb->lock); INIT_LIST_HEAD(&mmb->list); mmb->mapping = mapping; } EXPORT_SYMBOL(mmb_init); static void __remove_assoc_queue(struct mapping_metadata_bhs *mmb, struct buffer_head *bh) { lockdep_assert_held(&mmb->lock); list_del_init(&bh->b_assoc_buffers); WARN_ON(!bh->b_mmb); bh->b_mmb = NULL; } static void remove_assoc_queue(struct buffer_head *bh) { struct mapping_metadata_bhs *mmb; /* * The locking dance is ugly here. We need to acquire the lock * protecting the metadata bh list while possibly racing with bh * being removed from the list or moved to a different one. We * use RCU to pin mapping_metadata_bhs in memory to * opportunistically acquire the lock and then recheck the bh * didn't move under us. */ while (bh->b_mmb) { rcu_read_lock(); mmb = READ_ONCE(bh->b_mmb); if (mmb) { spin_lock(&mmb->lock); if (bh->b_mmb == mmb) __remove_assoc_queue(mmb, bh); spin_unlock(&mmb->lock); } rcu_read_unlock(); } } bool mmb_has_buffers(struct mapping_metadata_bhs *mmb) { return !list_empty(&mmb->list); } EXPORT_SYMBOL_GPL(mmb_has_buffers); /** * mmb_sync - write out & wait upon all buffers in a list * @mmb: the list of buffers to write * * Starts I/O against the buffers in the given list and waits upon * that I/O. Basically, this is a convenience function for fsync(). @mmb is * for a file or directory which needs those buffers to be written for a * successful fsync(). * * We have conflicting pressures: we want to make sure that all * initially dirty buffers get waited on, but that any subsequently * dirtied buffers don't. After all, we don't want fsync to last * forever if somebody is actively writing to the file. * * Do this in two main stages: first we copy dirty buffers to a * temporary inode list, queueing the writes as we go. Then we clean * up, waiting for those writes to complete. mark_buffer_dirty_inode() * doesn't touch b_assoc_buffers list if b_mmb is not NULL so we are sure the * buffer stays on our list until IO completes (at which point it can be * reaped). */ int mmb_sync(struct mapping_metadata_bhs *mmb) { struct buffer_head *bh; int err = 0; struct blk_plug plug; LIST_HEAD(tmp); if (!mmb_has_buffers(mmb)) return 0; blk_start_plug(&plug); spin_lock(&mmb->lock); while (!list_empty(&mmb->list)) { bh = BH_ENTRY(mmb->list.next); WARN_ON_ONCE(bh->b_mmb != mmb); __remove_assoc_queue(mmb, bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh) || buffer_locked(bh)) { list_add(&bh->b_assoc_buffers, &tmp); bh->b_mmb = mmb; if (buffer_dirty(bh)) { get_bh(bh); spin_unlock(&mmb->lock); /* * Ensure any pending I/O completes so that * write_dirty_buffer() actually writes the * current contents - it is a noop if I/O is * still in flight on potentially older * contents. */ write_dirty_buffer(bh, REQ_SYNC); /* * Kick off IO for the previous mapping. Note * that we will not run the very last mapping, * wait_on_buffer() will do that for us * through sync_buffer(). */ brelse(bh); spin_lock(&mmb->lock); } } } spin_unlock(&mmb->lock); blk_finish_plug(&plug); spin_lock(&mmb->lock); while (!list_empty(&tmp)) { bh = BH_ENTRY(tmp.prev); get_bh(bh); __remove_assoc_queue(mmb, bh); /* Avoid race with mark_buffer_dirty_inode() which does * a lockless check and we rely on seeing the dirty bit */ smp_mb(); if (buffer_dirty(bh)) { list_add(&bh->b_assoc_buffers, &mmb->list); bh->b_mmb = mmb; } spin_unlock(&mmb->lock); wait_on_buffer(bh); if (!buffer_uptodate(bh)) err = -EIO; brelse(bh); spin_lock(&mmb->lock); } spin_unlock(&mmb->lock); return err; } EXPORT_SYMBOL(mmb_sync); /** * mmb_fsync_noflush - fsync implementation for simple filesystems with * metadata buffers list * * @file: file to synchronize * @mmb: list of metadata bhs to flush * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is an implementation of the fsync method for simple filesystems which * track all non-inode metadata in the buffers list hanging off the @mmb * structure. */ int mmb_fsync_noflush(struct file *file, struct mapping_metadata_bhs *mmb, loff_t start, loff_t end, bool datasync) { struct inode *inode = file->f_mapping->host; int err; int ret = 0; err = file_write_and_wait_range(file, start, end); if (err) return err; if (mmb) ret = mmb_sync(mmb); if (!(inode_state_read_once(inode) & I_DIRTY_ALL)) goto out; if (datasync && !(inode_state_read_once(inode) & I_DIRTY_DATASYNC)) goto out; err = sync_inode_metadata(inode, 1); if (ret == 0) ret = err; out: /* check and advance again to catch errors after syncing out buffers */ err = file_check_and_advance_wb_err(file); if (ret == 0) ret = err; return ret; } EXPORT_SYMBOL(mmb_fsync_noflush); /** * mmb_fsync - fsync implementation for simple filesystems with metadata * buffers list * * @file: file to synchronize * @mmb: list of metadata bhs to flush * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is an implementation of the fsync method for simple filesystems which * track all non-inode metadata in the buffers list hanging off the @mmb * structure. This also makes sure that a device cache flush operation is * called at the end. */ int mmb_fsync(struct file *file, struct mapping_metadata_bhs *mmb, loff_t start, loff_t end, bool datasync) { struct inode *inode = file->f_mapping->host; int ret; ret = mmb_fsync_noflush(file, mmb, start, end, datasync); if (!ret) ret = blkdev_issue_flush(inode->i_sb->s_bdev); return ret; } EXPORT_SYMBOL(mmb_fsync); /* * Called when we've recently written block `bblock', and it is known that * `bblock' was for a buffer_boundary() buffer. This means that the block at * `bblock + 1' is probably a dirty indirect block. Hunt it down and, if it's * dirty, schedule it for IO. So that indirects merge nicely with their data. */ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize) { struct buffer_head *bh; bh = __find_get_block_nonatomic(bdev, bblock + 1, blocksize); if (bh) { if (buffer_dirty(bh)) write_dirty_buffer(bh, 0); put_bh(bh); } } void mmb_mark_buffer_dirty(struct buffer_head *bh, struct mapping_metadata_bhs *mmb) { mark_buffer_dirty(bh); if (!bh->b_mmb) { spin_lock(&mmb->lock); /* * For a corrupted filesystem with multiply claimed blocks this * can fail. Avoid corrupting the linked list in that case. */ if (cmpxchg(&bh->b_mmb, NULL, mmb) != NULL) { spin_unlock(&mmb->lock); return; } list_move_tail(&bh->b_assoc_buffers, &mmb->list); spin_unlock(&mmb->lock); } } EXPORT_SYMBOL(mmb_mark_buffer_dirty); /** * block_dirty_folio - Mark a folio as dirty. * @mapping: The address space containing this folio. * @folio: The folio to mark dirty. * * Filesystems which use buffer_heads can use this function as their * ->dirty_folio implementation. Some filesystems need to do a little * work before calling this function. Filesystems which do not use * buffer_heads should call filemap_dirty_folio() instead. * * If the folio has buffers, the uptodate buffers are set dirty, to * preserve dirty-state coherency between the folio and the buffers. * Buffers added to a dirty folio are created dirty. * * The buffers are dirtied before the folio is dirtied. There's a small * race window in which writeback may see the folio cleanness but not the * buffer dirtiness. That's fine. If this code were to set the folio * dirty before the buffers, writeback could clear the folio dirty flag, * see a bunch of clean buffers and we'd end up with dirty buffers/clean * folio on the dirty folio list. * * We use i_private_lock to lock against try_to_free_buffers() while * using the folio's buffer list. This also prevents clean buffers * being added to the folio after it was set dirty. * * Context: May only be called from process context. Does not sleep. * Caller must ensure that @folio cannot be truncated during this call, * typically by holding the folio lock or having a page in the folio * mapped and holding the page table lock. * * Return: True if the folio was dirtied; false if it was already dirtied. */ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) { struct buffer_head *head; bool newly_dirty; spin_lock(&mapping->i_private_lock); head = folio_buffers(folio); if (head) { struct buffer_head *bh = head; do { set_buffer_dirty(bh); bh = bh->b_this_page; } while (bh != head); } /* * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ newly_dirty = !folio_test_set_dirty(folio); spin_unlock(&mapping->i_private_lock); if (newly_dirty) __folio_mark_dirty(folio, mapping, 1); if (newly_dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); return newly_dirty; } EXPORT_SYMBOL(block_dirty_folio); /* * Invalidate any and all dirty buffers on a given buffers list. We are * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. */ void mmb_invalidate(struct mapping_metadata_bhs *mmb) { if (mmb_has_buffers(mmb)) { spin_lock(&mmb->lock); while (!list_empty(&mmb->list)) __remove_assoc_queue(mmb, BH_ENTRY(mmb->list.next)); spin_unlock(&mmb->lock); } } EXPORT_SYMBOL(mmb_invalidate); /* * Create the appropriate buffers when given a folio for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. * * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, gfp_t gfp) { struct buffer_head *bh, *head; long offset; struct mem_cgroup *memcg, *old_memcg; memcg = get_mem_cgroup_from_folio(folio); old_memcg = set_active_memcg(memcg); head = NULL; offset = folio_size(folio); while ((offset -= size) >= 0) { bh = alloc_buffer_head(gfp); if (!bh) goto no_grow; bh->b_this_page = head; bh->b_blocknr = -1; head = bh; bh->b_size = size; /* Link the buffer to its folio */ folio_set_bh(bh, folio, offset); } out: set_active_memcg(old_memcg); mem_cgroup_put(memcg); return head; /* * In case anything failed, we just free everything we got. */ no_grow: if (head) { do { bh = head; head = head->b_this_page; free_buffer_head(bh); } while (head); } goto out; } EXPORT_SYMBOL_GPL(folio_alloc_buffers); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size) { gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT; return folio_alloc_buffers(page_folio(page), size, gfp); } EXPORT_SYMBOL_GPL(alloc_page_buffers); static inline void link_dev_buffers(struct folio *folio, struct buffer_head *head) { struct buffer_head *bh, *tail; bh = head; do { tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; folio_attach_private(folio, head); } static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { sector_t retval = ~((sector_t)0); loff_t sz = bdev_nr_bytes(bdev); if (sz) { unsigned int sizebits = blksize_bits(size); retval = (sz >> sizebits); } return retval; } /* * Initialise the state of a blockdev folio's buffers. */ static sector_t folio_init_buffers(struct folio *folio, struct block_device *bdev, unsigned size) { struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh = head; bool uptodate = folio_test_uptodate(folio); sector_t block = div_u64(folio_pos(folio), size); sector_t end_block = blkdev_max_block(bdev, size); do { if (!buffer_mapped(bh)) { bh->b_end_io = NULL; bh->b_private = NULL; bh->b_bdev = bdev; bh->b_blocknr = block; if (uptodate) set_buffer_uptodate(bh); if (block < end_block) set_buffer_mapped(bh); } block++; bh = bh->b_this_page; } while (bh != head); /* * Caller needs to validate requested block against end of device. */ return end_block; } /* * Create the page-cache folio that contains the requested block. * * This is used purely for blockdev mappings. * * Returns false if we have a failure which cannot be cured by retrying * without sleeping. Returns true if we succeeded, or the caller should retry. */ static bool grow_dev_folio(struct block_device *bdev, sector_t block, pgoff_t index, unsigned size, gfp_t gfp) { struct address_space *mapping = bdev->bd_mapping; struct folio *folio; struct buffer_head *bh; sector_t end_block = 0; folio = __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, gfp); if (IS_ERR(folio)) return false; bh = folio_buffers(folio); if (bh) { if (bh->b_size == size) { end_block = folio_init_buffers(folio, bdev, size); goto unlock; } /* * Retrying may succeed; for example the folio may finish * writeback, or buffers may be cleaned. This should not * happen very often; maybe we have old buffers attached to * this blockdev's page cache and we're trying to change * the block size? */ if (!try_to_free_buffers(folio)) { end_block = ~0ULL; goto unlock; } } bh = folio_alloc_buffers(folio, size, gfp | __GFP_ACCOUNT); if (!bh) goto unlock; /* * Link the folio to the buffers and initialise them. Take the * lock to be atomic wrt __find_get_block(), which does not * run under the folio lock. */ spin_lock(&mapping->i_private_lock); link_dev_buffers(folio, bh); end_block = folio_init_buffers(folio, bdev, size); spin_unlock(&mapping->i_private_lock); unlock: folio_unlock(folio); folio_put(folio); return block < end_block; } /* * Create buffers for the specified block device block's folio. If * that folio was dirty, the buffers are set dirty also. Returns false * if we've hit a permanent error. */ static bool grow_buffers(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { loff_t pos; /* * Check for a block which lies outside our maximum possible * pagecache index. */ if (check_mul_overflow(block, (sector_t)size, &pos) || pos > MAX_LFS_FILESIZE) { printk(KERN_ERR "%s: requested out-of-range block %llu for device %pg\n", __func__, (unsigned long long)block, bdev); return false; } /* Create a folio with the proper size buffers */ return grow_dev_folio(bdev, block, pos / PAGE_SIZE, size, gfp); } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { bool blocking = gfpflags_allow_blocking(gfp); if (WARN_ON_ONCE(!IS_ALIGNED(size, bdev_logical_block_size(bdev)))) { printk(KERN_ERR "getblk(): block size %d not aligned to logical block size %d\n", size, bdev_logical_block_size(bdev)); return NULL; } for (;;) { struct buffer_head *bh; if (!grow_buffers(bdev, block, size, gfp)) return NULL; if (blocking) bh = __find_get_block_nonatomic(bdev, block, size); else bh = __find_get_block(bdev, block, size); if (bh) return bh; } } /* * The relationship between dirty buffers and dirty pages: * * Whenever a page has any dirty buffers, the page's dirty bit is set, and * the page is tagged dirty in the page cache. * * At all times, the dirtiness of the buffers represents the dirtiness of * subsections of the page. If the page has buffers, the page dirty bit is * merely a hint about the true dirty state. * * When a page is set dirty in its entirety, all its buffers are marked dirty * (if the page has buffers). * * When a buffer is marked dirty, its page is dirtied, but the page's other * buffers are not. * * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent * block_read_full_folio() against that folio will discover all the uptodate * buffers, will set the folio uptodate and will perform no I/O. */ /** * mark_buffer_dirty - mark a buffer_head as needing writeout * @bh: the buffer_head to mark dirty * * mark_buffer_dirty() will set the dirty bit against the buffer, then set * its backing page dirty, then tag the page as dirty in the page cache * and then attach the address_space's inode to its superblock's dirty * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->i_private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { WARN_ON_ONCE(!buffer_uptodate(bh)); trace_block_dirty_buffer(bh); /* * Very *carefully* optimize the it-is-already-dirty case. * * Don't let the final "is it dirty" escape to before we * perhaps modified the buffer. */ if (buffer_dirty(bh)) { smp_mb(); if (buffer_dirty(bh)) return; } if (!test_set_buffer_dirty(bh)) { struct folio *folio = bh->b_folio; struct address_space *mapping = NULL; if (!folio_test_set_dirty(folio)) { mapping = folio->mapping; if (mapping) __folio_mark_dirty(folio, mapping, 0); } if (mapping) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } } EXPORT_SYMBOL(mark_buffer_dirty); void mark_buffer_write_io_error(struct buffer_head *bh) { set_buffer_write_io_error(bh); /* FIXME: do we need to set this in both places? */ if (bh->b_folio && bh->b_folio->mapping) mapping_set_error(bh->b_folio->mapping, -EIO); if (bh->b_mmb) mapping_set_error(bh->b_mmb->mapping, -EIO); } EXPORT_SYMBOL(mark_buffer_write_io_error); /** * __brelse - Release a buffer. * @bh: The buffer to release. * * This variant of brelse() can be called if @bh is guaranteed to not be NULL. */ void __brelse(struct buffer_head *bh) { if (atomic_read(&bh->b_count)) { put_bh(bh); return; } WARN(1, KERN_ERR "VFS: brelse: Trying to free free buffer\n"); } EXPORT_SYMBOL(__brelse); /** * __bforget - Discard any dirty data in a buffer. * @bh: The buffer to forget. * * This variant of bforget() can be called if @bh is guaranteed to not * be NULL. */ void __bforget(struct buffer_head *bh) { clear_buffer_dirty(bh); remove_assoc_queue(bh); __brelse(bh); } EXPORT_SYMBOL(__bforget); static struct buffer_head *__bread_slow(struct buffer_head *bh) { lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); return bh; } else { get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ, bh); wait_on_buffer(bh); if (buffer_uptodate(bh)) return bh; } brelse(bh); return NULL; } /* * Per-cpu buffer LRU implementation. To reduce the cost of __find_get_block(). * The bhs[] array is sorted - newest buffer is at bhs[0]. Buffers have their * refcount elevated by one when they're in an LRU. A buffer can only appear * once in a particular CPU's LRU. A single buffer can be present in multiple * CPU's LRUs at the same time. * * This is a transparent caching front-end to sb_bread(), sb_getblk() and * sb_find_get_block(). * * The LRUs themselves only need locking against invalidate_bh_lrus. We use * a local interrupt disable for that. */ #define BH_LRU_SIZE 16 struct bh_lru { struct buffer_head *bhs[BH_LRU_SIZE]; }; static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = {{ NULL }}; #ifdef CONFIG_SMP #define bh_lru_lock() local_irq_disable() #define bh_lru_unlock() local_irq_enable() #else #define bh_lru_lock() preempt_disable() #define bh_lru_unlock() preempt_enable() #endif static inline void check_irqs_on(void) { #ifdef irqs_disabled BUG_ON(irqs_disabled()); #endif } /* * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is * inserted at the front, and the buffer_head at the back if any is evicted. * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { struct buffer_head *evictee = bh; struct bh_lru *b; int i; check_irqs_on(); bh_lru_lock(); /* * the refcount of buffer_head in bh_lru prevents dropping the * attached page(i.e., try_to_free_buffers) so it could cause * failing page migration. * Skip putting upcoming bh into bh_lru until migration is done. */ if (lru_cache_disabled() || cpu_is_isolated(smp_processor_id())) { bh_lru_unlock(); return; } b = this_cpu_ptr(&bh_lrus); for (i = 0; i < BH_LRU_SIZE; i++) { swap(evictee, b->bhs[i]); if (evictee == bh) { bh_lru_unlock(); return; } } get_bh(bh); bh_lru_unlock(); brelse(evictee); } /* * Look up the bh in this cpu's LRU. If it's there, move it to the head. */ static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *ret = NULL; unsigned int i; check_irqs_on(); bh_lru_lock(); if (cpu_is_isolated(smp_processor_id())) { bh_lru_unlock(); return NULL; } for (i = 0; i < BH_LRU_SIZE; i++) { struct buffer_head *bh = __this_cpu_read(bh_lrus.bhs[i]); if (bh && bh->b_blocknr == block && bh->b_bdev == bdev && bh->b_size == size) { if (i) { while (i) { __this_cpu_write(bh_lrus.bhs[i], __this_cpu_read(bh_lrus.bhs[i - 1])); i--; } __this_cpu_write(bh_lrus.bhs[0], bh); } get_bh(bh); ret = bh; break; } } bh_lru_unlock(); return ret; } /* * Perform a pagecache lookup for the matching buffer. If it's there, refresh * it in the LRU and mark it as accessed. If it is not present then return * NULL. Atomic context callers may also return NULL if the buffer is being * migrated; similarly the page is not marked accessed either. */ static struct buffer_head * find_get_block_common(struct block_device *bdev, sector_t block, unsigned size, bool atomic) { struct buffer_head *bh = lookup_bh_lru(bdev, block, size); if (bh == NULL) { /* __find_get_block_slow will mark the page accessed */ bh = __find_get_block_slow(bdev, block, atomic); if (bh) bh_lru_install(bh); } else touch_buffer(bh); return bh; } struct buffer_head * __find_get_block(struct block_device *bdev, sector_t block, unsigned size) { return find_get_block_common(bdev, block, size, true); } EXPORT_SYMBOL(__find_get_block); /* same as __find_get_block() but allows sleeping contexts */ struct buffer_head * __find_get_block_nonatomic(struct block_device *bdev, sector_t block, unsigned size) { return find_get_block_common(bdev, block, size, false); } EXPORT_SYMBOL(__find_get_block_nonatomic); /** * bdev_getblk - Get a buffer_head in a block device's buffer cache. * @bdev: The block device. * @block: The block number. * @size: The size of buffer_heads for this @bdev. * @gfp: The memory allocation flags to use. * * The returned buffer head has its reference count incremented, but is * not locked. The caller should call brelse() when it has finished * with the buffer. The buffer may not be uptodate. If needed, the * caller can bring it uptodate either by reading it or overwriting it. * * Return: The buffer head, or NULL if memory could not be allocated. */ struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh; if (gfpflags_allow_blocking(gfp)) bh = __find_get_block_nonatomic(bdev, block, size); else bh = __find_get_block(bdev, block, size); might_alloc(gfp); if (bh) return bh; return __getblk_slow(bdev, block, size, gfp); } EXPORT_SYMBOL(bdev_getblk); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { struct buffer_head *bh = bdev_getblk(bdev, block, size, GFP_NOWAIT | __GFP_MOVABLE); if (likely(bh)) { bh_readahead(bh, REQ_RAHEAD); brelse(bh); } } EXPORT_SYMBOL(__breadahead); /** * __bread_gfp() - Read a block. * @bdev: The block device to read from. * @block: Block number in units of block size. * @size: The block size of this device in bytes. * @gfp: Not page allocation flags; see below. * * You are not expected to call this function. You should use one of * sb_bread(), sb_bread_unmovable() or __bread(). * * Read a specified block, and return the buffer head that refers to it. * If @gfp is 0, the memory will be allocated using the block device's * default GFP flags. If @gfp is __GFP_MOVABLE, the memory may be * allocated from a movable area. Do not pass in a complete set of * GFP flags. * * The returned buffer head has its refcount increased. The caller should * call brelse() when it has finished with the buffer. * * Context: May sleep waiting for I/O. * Return: NULL if the block was unreadable. */ struct buffer_head *__bread_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { struct buffer_head *bh; gfp |= mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS); /* * Prefer looping in the allocator rather than here, at least that * code knows what it's doing. */ gfp |= __GFP_NOFAIL; bh = bdev_getblk(bdev, block, size, gfp); if (likely(bh) && !buffer_uptodate(bh)) bh = __bread_slow(bh); return bh; } EXPORT_SYMBOL(__bread_gfp); static void __invalidate_bh_lrus(struct bh_lru *b) { int i; for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } } /* * invalidate_bh_lrus() is called rarely - but not only at unmount. * This doesn't race because it runs in each cpu either in irq * or with preempt disabled. */ static void invalidate_bh_lru(void *arg) { struct bh_lru *b = &get_cpu_var(bh_lrus); __invalidate_bh_lrus(b); put_cpu_var(bh_lrus); } bool has_bh_in_lru(int cpu, void *dummy) { struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu); int i; for (i = 0; i < BH_LRU_SIZE; i++) { if (b->bhs[i]) return true; } return false; } void invalidate_bh_lrus(void) { on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1); } EXPORT_SYMBOL_GPL(invalidate_bh_lrus); /* * It's called from workqueue context so we need a bh_lru_lock to close * the race with preemption/irq. */ void invalidate_bh_lrus_cpu(void) { struct bh_lru *b; bh_lru_lock(); b = this_cpu_ptr(&bh_lrus); __invalidate_bh_lrus(b); bh_lru_unlock(); } void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset) { bh->b_folio = folio; BUG_ON(offset >= folio_size(folio)); if (folio_test_highmem(folio)) /* * This catches illegal uses and preserves the offset: */ bh->b_data = (char *)(0 + offset); else bh->b_data = folio_address(folio) + offset; } EXPORT_SYMBOL(folio_set_bh); /* * Called when truncating a buffer on a page completely. */ /* Bits that are cleared during an invalidate */ #define BUFFER_FLAGS_DISCARD \ (1 << BH_Mapped | 1 << BH_New | 1 << BH_Req | \ 1 << BH_Delay | 1 << BH_Unwritten) static void discard_buffer(struct buffer_head * bh) { unsigned long b_state; lock_buffer(bh); clear_buffer_dirty(bh); bh->b_bdev = NULL; b_state = READ_ONCE(bh->b_state); do { } while (!try_cmpxchg_relaxed(&bh->b_state, &b_state, b_state & ~BUFFER_FLAGS_DISCARD)); unlock_buffer(bh); } /** * block_invalidate_folio - Invalidate part or all of a buffer-backed folio. * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * * block_invalidate_folio() is called when all or part of the folio has been * invalidated by a truncate operation. * * block_invalidate_folio() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void block_invalidate_folio(struct folio *folio, size_t offset, size_t length) { struct buffer_head *head, *bh, *next; size_t curr_off = 0; size_t stop = length + offset; BUG_ON(!folio_test_locked(folio)); /* * Check for overflow */ BUG_ON(stop > folio_size(folio) || stop < length); head = folio_buffers(folio); if (!head) return; bh = head; do { size_t next_off = curr_off + bh->b_size; next = bh->b_this_page; /* * Are we still fully in range ? */ if (next_off > stop) goto out; /* * is this block fully invalidated? */ if (offset <= curr_off) discard_buffer(bh); curr_off = next_off; bh = next; } while (bh != head); /* * We release buffers only if the entire folio is being invalidated. * The get_block cached value has been unconditionally invalidated, * so real IO is not possible anymore. */ if (length == folio_size(folio)) filemap_release_folio(folio, 0); out: folio_clear_mappedtodisk(folio); } EXPORT_SYMBOL(block_invalidate_folio); /* * We attach and possibly dirty the buffers atomically wrt * block_dirty_folio() via i_private_lock. try_to_free_buffers * is already excluded via the folio lock. */ struct buffer_head *create_empty_buffers(struct folio *folio, unsigned long blocksize, unsigned long b_state) { struct buffer_head *bh, *head, *tail; gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT | __GFP_NOFAIL; head = folio_alloc_buffers(folio, blocksize, gfp); bh = head; do { bh->b_state |= b_state; tail = bh; bh = bh->b_this_page; } while (bh); tail->b_this_page = head; spin_lock(&folio->mapping->i_private_lock); if (folio_test_uptodate(folio) || folio_test_dirty(folio)) { bh = head; do { if (folio_test_dirty(folio)) set_buffer_dirty(bh); if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); bh = bh->b_this_page; } while (bh != head); } folio_attach_private(folio, head); spin_unlock(&folio->mapping->i_private_lock); return head; } EXPORT_SYMBOL(create_empty_buffers); /** * clean_bdev_aliases: clean a range of buffers in block device * @bdev: Block device to clean buffers in * @block: Start of a range of blocks to clean * @len: Number of blocks to clean * * We are taking a range of blocks for data and we don't want writeback of any * buffer-cache aliases starting from return from this function and until the * moment when something will explicitly mark the buffer dirty (hopefully that * will not happen until we will free that block ;-) We don't even need to mark * it not-uptodate - nobody can expect anything from a newly allocated buffer * anyway. We used to use unmap_buffer() for such invalidation, but that was * wrong. We definitely don't want to mark the alias unmapped, for example - it * would confuse anyone who might pick it with bread() afterwards... * * Also.. Note that bforget() doesn't lock the buffer. So there can be * writeout I/O going on against recently-freed buffers. We don't wait on that * I/O in bforget() - it's more efficient to wait on the I/O only if we really * need to. That happens here. */ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) { struct address_space *bd_mapping = bdev->bd_mapping; const int blkbits = bd_mapping->host->i_blkbits; struct folio_batch fbatch; pgoff_t index = ((loff_t)block << blkbits) / PAGE_SIZE; pgoff_t end; int i, count; struct buffer_head *bh; struct buffer_head *head; end = ((loff_t)(block + len - 1) << blkbits) / PAGE_SIZE; folio_batch_init(&fbatch); while (filemap_get_folios(bd_mapping, &index, end, &fbatch)) { count = folio_batch_count(&fbatch); for (i = 0; i < count; i++) { struct folio *folio = fbatch.folios[i]; if (!folio_buffers(folio)) continue; /* * We use folio lock instead of bd_mapping->i_private_lock * to pin buffers here since we can afford to sleep and * it scales better than a global spinlock lock. */ folio_lock(folio); /* Recheck when the folio is locked which pins bhs */ head = folio_buffers(folio); if (!head) goto unlock_page; bh = head; do { if (!buffer_mapped(bh) || (bh->b_blocknr < block)) goto next; if (bh->b_blocknr >= block + len) break; clear_buffer_dirty(bh); wait_on_buffer(bh); clear_buffer_req(bh); next: bh = bh->b_this_page; } while (bh != head); unlock_page: folio_unlock(folio); } folio_batch_release(&fbatch); cond_resched(); /* End of range already reached? */ if (index > end || !index) break; } } EXPORT_SYMBOL(clean_bdev_aliases); static struct buffer_head *folio_create_buffers(struct folio *folio, struct inode *inode, unsigned int b_state) { struct buffer_head *bh; BUG_ON(!folio_test_locked(folio)); bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, 1 << READ_ONCE(inode->i_blkbits), b_state); return bh; } /* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning * * No No "unknown" - must do get_block() * No Yes "hole" - zero-filled * Yes No "allocated" - allocated on disk, not read in * Yes Yes "valid" - allocated and up-to-date in memory. * * "Dirty" is valid only with the last case (mapped+uptodate). */ /* * While block_write_full_folio is writing back the dirty buffers under * the page lock, whoever dirtied the buffers may decide to clean them * again at any time. We handle that by only looking at the buffer * state inside lock_buffer(). * * If block_write_full_folio() is called for regular writeback * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. * * If block_write_full_folio() is called with wbc->sync_mode == * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this * causes the writes to be flagged as synchronous writes. */ int __block_write_full_folio(struct inode *inode, struct folio *folio, get_block_t *get_block, struct writeback_control *wbc) { int err; sector_t block; sector_t last_block; struct buffer_head *bh, *head; size_t blocksize; int nr_underway = 0; blk_opf_t write_flags = wbc_to_write_flags(wbc); head = folio_create_buffers(folio, inode, (1 << BH_Dirty) | (1 << BH_Uptodate)); /* * Be very careful. We have no exclusion from block_dirty_folio * here, and the (potentially unmapped) buffers may become dirty at * any time. If a buffer becomes dirty here after we've inspected it * then we just miss that fact, and the folio stays dirty. * * Buffers outside i_size may be dirtied by block_dirty_folio; * handle that here by just cleaning them. */ bh = head; blocksize = bh->b_size; block = div_u64(folio_pos(folio), blocksize); last_block = div_u64(i_size_read(inode) - 1, blocksize); /* * Get all the dirty buffers mapped to disk addresses and * handle any aliases from the underlying blockdev's mapping. */ do { if (block > last_block) { /* * mapped buffers outside i_size will occur, because * this folio can be outside i_size when there is a * truncate in progress. */ /* * The buffer was zeroed by block_write_full_folio() */ clear_buffer_dirty(bh); set_buffer_uptodate(bh); } else if ((!buffer_mapped(bh) || buffer_delay(bh)) && buffer_dirty(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, block, bh, 1); if (err) goto recover; clear_buffer_delay(bh); if (buffer_new(bh)) { /* blockdev mappings never come here */ clear_buffer_new(bh); clean_bdev_bh_alias(bh); } } bh = bh->b_this_page; block++; } while (bh != head); do { if (!buffer_mapped(bh)) continue; /* * If it's a fully non-blocking write attempt and we cannot * lock the buffer then redirty the folio. Note that this can * potentially cause a busy-wait loop from writeback threads * and kswapd activity, but those code paths have their own * higher-level throttling. */ if (wbc->sync_mode != WB_SYNC_NONE) { lock_buffer(bh); } else if (!trylock_buffer(bh)) { folio_redirty_for_writepage(wbc, folio); continue; } if (test_clear_buffer_dirty(bh)) { mark_buffer_async_write_endio(bh, end_buffer_async_write); } else { unlock_buffer(bh); } } while ((bh = bh->b_this_page) != head); /* * The folio and its buffers are protected by the writeback flag, * so we can drop the bh refcounts early. */ BUG_ON(folio_test_writeback(folio)); folio_start_writeback(folio); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); folio_unlock(folio); err = 0; done: if (nr_underway == 0) { /* * The folio was marked dirty, but the buffers were * clean. Someone wrote them back by hand with * write_dirty_buffer/submit_bh. A rare case. */ folio_end_writeback(folio); /* * The folio and buffer_heads can be released at any time from * here on. */ } return err; recover: /* * ENOSPC, or some other error. We may already have added some * blocks to the file, so we need to write these out to avoid * exposing stale data. * The folio is currently locked and not marked for writeback */ bh = head; /* Recovery: lock and submit the mapped buffers */ do { if (buffer_mapped(bh) && buffer_dirty(bh) && !buffer_delay(bh)) { lock_buffer(bh); mark_buffer_async_write_endio(bh, end_buffer_async_write); } else { /* * The buffer may have been set dirty during * attachment to a dirty folio. */ clear_buffer_dirty(bh); } } while ((bh = bh->b_this_page) != head); BUG_ON(folio_test_writeback(folio)); mapping_set_error(folio->mapping, err); folio_start_writeback(folio); do { struct buffer_head *next = bh->b_this_page; if (buffer_async_write(bh)) { clear_buffer_dirty(bh); submit_bh_wbc(REQ_OP_WRITE | write_flags, bh, inode->i_write_hint, wbc); nr_underway++; } bh = next; } while (bh != head); folio_unlock(folio); goto done; } EXPORT_SYMBOL(__block_write_full_folio); /* * If a folio has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to) { size_t block_start, block_end; struct buffer_head *head, *bh; BUG_ON(!folio_test_locked(folio)); head = folio_buffers(folio); if (!head) return; bh = head; block_start = 0; do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!folio_test_uptodate(folio)) { size_t start, xend; start = max(from, block_start); xend = min(to, block_end); folio_zero_segment(folio, start, xend); set_buffer_uptodate(bh); } clear_buffer_new(bh); mark_buffer_dirty(bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } EXPORT_SYMBOL(folio_zero_new_buffers); static int iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, const struct iomap *iomap) { loff_t offset = (loff_t)block << inode->i_blkbits; bh->b_bdev = iomap->bdev; /* * Block points to offset in file we need to map, iomap contains * the offset at which the map starts. If the map ends before the * current block, then do not map the buffer and let the caller * handle it. */ if (offset >= iomap->offset + iomap->length) return -EIO; switch (iomap->type) { case IOMAP_HOLE: /* * If the buffer is not up to date or beyond the current EOF, * we need to mark it as new to ensure sub-block zeroing is * executed if necessary. */ if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); return 0; case IOMAP_DELALLOC: if (!buffer_uptodate(bh) || (offset >= i_size_read(inode))) set_buffer_new(bh); set_buffer_uptodate(bh); set_buffer_mapped(bh); set_buffer_delay(bh); return 0; case IOMAP_UNWRITTEN: /* * For unwritten regions, we always need to ensure that regions * in the block we are not writing to are zeroed. Mark the * buffer as new to ensure this. */ set_buffer_new(bh); set_buffer_unwritten(bh); fallthrough; case IOMAP_MAPPED: if ((iomap->flags & IOMAP_F_NEW) || offset >= i_size_read(inode)) { /* * This can happen if truncating the block device races * with the check in the caller as i_size updates on * block devices aren't synchronized by i_rwsem for * block devices. */ if (S_ISBLK(inode->i_mode)) return -EIO; set_buffer_new(bh); } bh->b_blocknr = (iomap->addr + offset - iomap->offset) >> inode->i_blkbits; set_buffer_mapped(bh); return 0; default: WARN_ON_ONCE(1); return -EIO; } } int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap) { size_t from = offset_in_folio(folio, pos); size_t to = from + len; struct inode *inode = folio->mapping->host; size_t block_start, block_end; sector_t block; int err = 0; size_t blocksize; struct buffer_head *bh, *head, *wait[2], **wait_bh=wait; BUG_ON(!folio_test_locked(folio)); BUG_ON(to > folio_size(folio)); BUG_ON(from > to); head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; block = div_u64(folio_pos(folio), blocksize); for (bh = head, block_start = 0; bh != head || !block_start; block++, block_start=block_end, bh = bh->b_this_page) { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (folio_test_uptodate(folio)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); } continue; } if (buffer_new(bh)) clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); if (get_block) err = get_block(inode, block, bh, 1); else err = iomap_to_bh(inode, block, bh, iomap); if (err) break; if (buffer_new(bh)) { clean_bdev_bh_alias(bh); if (folio_test_uptodate(folio)) { clear_buffer_new(bh); set_buffer_uptodate(bh); mark_buffer_dirty(bh); continue; } if (block_end > to || block_start < from) folio_zero_segments(folio, to, block_end, block_start, from); continue; } } if (folio_test_uptodate(folio)) { if (!buffer_uptodate(bh)) set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { bh_read_nowait(bh, 0); *wait_bh++=bh; } } /* * If we issued read requests - let them complete. */ while(wait_bh > wait) { wait_on_buffer(*--wait_bh); if (!buffer_uptodate(*wait_bh)) err = -EIO; } if (unlikely(err)) folio_zero_new_buffers(folio, from, to); return err; } int __block_write_begin(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block) { return __block_write_begin_int(folio, pos, len, get_block, NULL); } EXPORT_SYMBOL(__block_write_begin); void block_commit_write(struct folio *folio, size_t from, size_t to) { size_t block_start, block_end; bool partial = false; unsigned blocksize; struct buffer_head *bh, *head; bh = head = folio_buffers(folio); if (!bh) return; blocksize = bh->b_size; block_start = 0; do { block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (!buffer_uptodate(bh)) partial = true; } else { set_buffer_uptodate(bh); mark_buffer_dirty(bh); } if (buffer_new(bh)) clear_buffer_new(bh); block_start = block_end; bh = bh->b_this_page; } while (bh != head); /* * If this is a partial write which happened to make all buffers * uptodate then we can optimize away a bogus read_folio() for * the next read(). Here we 'discover' whether the folio went * uptodate as a result of this (potentially partial) write. */ if (!partial) folio_mark_uptodate(folio); } EXPORT_SYMBOL(block_commit_write); /* * block_write_begin takes care of the basic task of block allocation and * bringing partial write blocks uptodate first. * * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, get_block_t *get_block) { pgoff_t index = pos >> PAGE_SHIFT; struct folio *folio; int status; folio = __filemap_get_folio(mapping, index, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) return PTR_ERR(folio); status = __block_write_begin_int(folio, pos, len, get_block, NULL); if (unlikely(status)) { folio_unlock(folio); folio_put(folio); folio = NULL; } *foliop = folio; return status; } EXPORT_SYMBOL(block_write_begin); int block_write_end(loff_t pos, unsigned len, unsigned copied, struct folio *folio) { size_t start = pos - folio_pos(folio); if (unlikely(copied < len)) { /* * The buffers that were written will now be uptodate, so * we don't have to worry about a read_folio reading them * and overwriting a partial write. However if we have * encountered a short write and only partially written * into a buffer, it will not be marked uptodate, so a * read_folio might come in and destroy our partial write. * * Do the simplest thing, and just treat any short write to a * non uptodate folio as a zero-length write, and force the * caller to redo the whole thing. */ if (!folio_test_uptodate(folio)) copied = 0; folio_zero_new_buffers(folio, start+copied, start+len); } flush_dcache_folio(folio); /* This could be a short (even 0-length) commit */ block_commit_write(folio, start, start + copied); return copied; } EXPORT_SYMBOL(block_write_end); int generic_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool i_size_changed = false; copied = block_write_end(pos, len, copied, folio); /* * No need to use i_size_read() here, the i_size cannot change under us * because we hold i_rwsem. * * But it's important to update i_size while still holding folio lock: * page writeout could otherwise come in and zero beyond i_size. */ if (pos + copied > inode->i_size) { i_size_write(inode, pos + copied); i_size_changed = true; } folio_unlock(folio); folio_put(folio); if (old_size < pos) pagecache_isize_extended(inode, old_size, pos); /* * Don't mark the inode dirty under page lock. First, it unnecessarily * makes the holding time of page lock longer. Second, it forces lock * ordering of page lock and transaction start for journaling * filesystems. */ if (i_size_changed) mark_inode_dirty(inode); return copied; } EXPORT_SYMBOL(generic_write_end); /* * block_is_partially_uptodate checks whether buffers within a folio are * uptodate or not. * * Returns true if all buffers which correspond to the specified part * of the folio are uptodate. */ bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count) { unsigned block_start, block_end, blocksize; unsigned to; struct buffer_head *bh, *head; bool ret = true; head = folio_buffers(folio); if (!head) return false; blocksize = head->b_size; to = min(folio_size(folio) - from, count); to = from + to; if (from < blocksize && to > folio_size(folio) - blocksize) return false; bh = head; block_start = 0; do { block_end = block_start + blocksize; if (block_end > from && block_start < to) { if (!buffer_uptodate(bh)) { ret = false; break; } if (block_end >= to) break; } block_start = block_end; bh = bh->b_this_page; } while (bh != head); return ret; } EXPORT_SYMBOL(block_is_partially_uptodate); /* * Generic "read_folio" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. * Reads the folio asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the * folio once IO has completed. */ int block_read_full_folio(struct folio *folio, get_block_t *get_block) { struct inode *inode = folio->mapping->host; sector_t iblock, lblock; struct buffer_head *bh, *head, *prev = NULL; size_t blocksize; int fully_mapped = 1; bool page_error = false; loff_t limit = i_size_read(inode); /* This is needed for ext4. */ if (IS_ENABLED(CONFIG_FS_VERITY) && IS_VERITY(inode)) limit = inode->i_sb->s_maxbytes; head = folio_create_buffers(folio, inode, 0); blocksize = head->b_size; iblock = div_u64(folio_pos(folio), blocksize); lblock = div_u64(limit + blocksize - 1, blocksize); bh = head; do { if (buffer_uptodate(bh)) continue; if (!buffer_mapped(bh)) { int err = 0; fully_mapped = 0; if (iblock < lblock) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) page_error = true; } if (!buffer_mapped(bh)) { folio_zero_range(folio, bh_offset(bh), blocksize); if (!err) set_buffer_uptodate(bh); continue; } /* * get_block() might have updated the buffer * synchronously */ if (buffer_uptodate(bh)) continue; } lock_buffer(bh); if (buffer_uptodate(bh)) { unlock_buffer(bh); continue; } mark_buffer_async_read(bh); if (prev) submit_bh(REQ_OP_READ, prev); prev = bh; } while (iblock++, (bh = bh->b_this_page) != head); if (fully_mapped) folio_set_mappedtodisk(folio); /* * All buffers are uptodate or get_block() returned an error * when trying to map them - we must finish the read because * end_buffer_async_read() will never be called on any buffer * in this folio. */ if (prev) submit_bh(REQ_OP_READ, prev); else folio_end_read(folio, !page_error); return 0; } EXPORT_SYMBOL(block_read_full_folio); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to * deal with the hole. */ int generic_cont_expand_simple(struct inode *inode, loff_t size) { struct address_space *mapping = inode->i_mapping; const struct address_space_operations *aops = mapping->a_ops; struct folio *folio; void *fsdata = NULL; int err; err = inode_newsize_ok(inode, size); if (err) goto out; err = aops->write_begin(NULL, mapping, size, 0, &folio, &fsdata); if (err) goto out; err = aops->write_end(NULL, mapping, size, 0, 0, folio, fsdata); BUG_ON(err > 0); out: return err; } EXPORT_SYMBOL(generic_cont_expand_simple); static int cont_expand_zero(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, loff_t *bytes) { struct inode *inode = mapping->host; const struct address_space_operations *aops = mapping->a_ops; unsigned int blocksize = i_blocksize(inode); struct folio *folio; void *fsdata = NULL; pgoff_t index, curidx; loff_t curpos; unsigned zerofrom, offset, len; int err = 0; index = pos >> PAGE_SHIFT; offset = pos & ~PAGE_MASK; while (index > (curidx = (curpos = *bytes)>>PAGE_SHIFT)) { zerofrom = curpos & ~PAGE_MASK; if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = PAGE_SIZE - zerofrom; err = aops->write_begin(iocb, mapping, curpos, len, &folio, &fsdata); if (err) goto out; folio_zero_range(folio, offset_in_folio(folio, curpos), len); err = aops->write_end(iocb, mapping, curpos, len, len, folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; balance_dirty_pages_ratelimited(mapping); if (fatal_signal_pending(current)) { err = -EINTR; goto out; } } /* page covers the boundary, find the boundary offset */ if (index == curidx) { zerofrom = curpos & ~PAGE_MASK; /* if we will expand the thing last block will be filled */ if (offset <= zerofrom) { goto out; } if (zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } len = offset - zerofrom; err = aops->write_begin(iocb, mapping, curpos, len, &folio, &fsdata); if (err) goto out; folio_zero_range(folio, offset_in_folio(folio, curpos), len); err = aops->write_end(iocb, mapping, curpos, len, len, folio, fsdata); if (err < 0) goto out; BUG_ON(err != len); err = 0; } out: return err; } /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ int cont_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata, get_block_t *get_block, loff_t *bytes) { struct inode *inode = mapping->host; unsigned int blocksize = i_blocksize(inode); unsigned int zerofrom; int err; err = cont_expand_zero(iocb, mapping, pos, bytes); if (err) return err; zerofrom = *bytes & ~PAGE_MASK; if (pos+len > *bytes && zerofrom & (blocksize-1)) { *bytes |= (blocksize-1); (*bytes)++; } return block_write_begin(mapping, pos, len, foliop, get_block); } EXPORT_SYMBOL(cont_write_begin); /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must * be careful to check for EOF conditions here. We set the page up correctly * for a written page which means we get ENOSPC checking when writing into * holes and correct delalloc and unwritten extent mapping on filesystems that * support these features. * * We are not allowed to take the i_rwsem here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. * * Direct callers of this function should protect against filesystem freezing * using sb_start_pagefault() - sb_end_pagefault() functions. */ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { struct folio *folio = page_folio(vmf->page); struct inode *inode = file_inode(vma->vm_file); unsigned long end; loff_t size; int ret; folio_lock(folio); size = i_size_read(inode); if ((folio->mapping != inode->i_mapping) || (folio_pos(folio) >= size)) { /* We overload EFAULT to mean page got truncated */ ret = -EFAULT; goto out_unlock; } end = folio_size(folio); /* folio is wholly or partially inside EOF */ if (folio_pos(folio) + end > size) end = size - folio_pos(folio); ret = __block_write_begin_int(folio, 0, end, get_block, NULL); if (unlikely(ret)) goto out_unlock; block_commit_write(folio, 0, end); folio_mark_dirty(folio); folio_wait_stable(folio); return 0; out_unlock: folio_unlock(folio); return ret; } EXPORT_SYMBOL(block_page_mkwrite); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { pgoff_t index = from >> PAGE_SHIFT; unsigned blocksize; sector_t iblock; size_t offset, length, pos; struct inode *inode = mapping->host; struct folio *folio; struct buffer_head *bh; int err = 0; blocksize = i_blocksize(inode); length = from & (blocksize - 1); /* Block boundary? Nothing to do */ if (!length) return 0; length = blocksize - length; iblock = ((loff_t)index * PAGE_SIZE) >> inode->i_blkbits; folio = filemap_grab_folio(mapping, index); if (IS_ERR(folio)) return PTR_ERR(folio); bh = folio_buffers(folio); if (!bh) bh = create_empty_buffers(folio, blocksize, 0); /* Find the buffer that contains "offset" */ offset = offset_in_folio(folio, from); pos = blocksize; while (offset >= pos) { bh = bh->b_this_page; iblock++; pos += blocksize; } if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = get_block(inode, iblock, bh, 0); if (err) goto unlock; /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) goto unlock; } /* Ok, it's mapped. Make sure it's up-to-date */ if (folio_test_uptodate(folio)) set_buffer_uptodate(bh); if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh)) { err = bh_read(bh, 0); /* Uhhuh. Read error. Complain and punt. */ if (err < 0) goto unlock; } folio_zero_range(folio, offset, length); mark_buffer_dirty(bh); unlock: folio_unlock(folio); folio_put(folio); return err; } EXPORT_SYMBOL(block_truncate_page); /* * The generic write folio function for buffer-backed address_spaces */ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc, void *get_block) { struct inode * const inode = folio->mapping->host; loff_t i_size = i_size_read(inode); /* Is the folio fully inside i_size? */ if (folio_next_pos(folio) <= i_size) return __block_write_full_folio(inode, folio, get_block, wbc); /* Is the folio fully outside i_size? (truncate in progress) */ if (folio_pos(folio) >= i_size) { folio_unlock(folio); return 0; /* don't care */ } /* * The folio straddles i_size. It must be zeroed out on each and every * writeback invocation because it may be mmapped. "A file is mapped * in multiples of the page size. For a file that is not a multiple of * the page size, the remaining memory is zeroed when mapped, and * writes to that region are not written out to the file." */ folio_zero_segment(folio, offset_in_folio(folio, i_size), folio_size(folio)); return __block_write_full_folio(inode, folio, get_block, wbc); } sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { struct inode *inode = mapping->host; struct buffer_head tmp = { .b_size = i_blocksize(inode), }; get_block(inode, block, &tmp, 0); return tmp.b_blocknr; } EXPORT_SYMBOL(generic_block_bmap); static void end_bio_bh_io_sync(struct bio *bio) { struct buffer_head *bh = bio->bi_private; if (unlikely(bio_flagged(bio, BIO_QUIET))) set_bit(BH_Quiet, &bh->b_state); bh->b_end_io(bh, !bio->bi_status); bio_put(bio); } static void buffer_set_crypto_ctx(struct bio *bio, const struct buffer_head *bh, gfp_t gfp_mask) { const struct address_space *mapping = folio_mapping(bh->b_folio); /* * The ext4 journal (jbd2) can submit a buffer_head it directly created * for a non-pagecache page. fscrypt doesn't care about these. */ if (!mapping) return; fscrypt_set_bio_crypt_ctx(bio, mapping->host, folio_pos(bh->b_folio) + bh_offset(bh), gfp_mask); } static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, enum rw_hint write_hint, struct writeback_control *wbc) { const enum req_op op = opf & REQ_OP_MASK; struct bio *bio; BUG_ON(!buffer_locked(bh)); BUG_ON(!buffer_mapped(bh)); BUG_ON(!bh->b_end_io); BUG_ON(buffer_delay(bh)); BUG_ON(buffer_unwritten(bh)); /* * Only clear out a write error when rewriting */ if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); if (buffer_meta(bh)) opf |= REQ_META; if (buffer_prio(bh)) opf |= REQ_PRIO; bio = bio_alloc(bh->b_bdev, 1, opf, GFP_NOIO); if (IS_ENABLED(CONFIG_FS_ENCRYPTION)) buffer_set_crypto_ctx(bio, bh, GFP_NOIO); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio->bi_write_hint = write_hint; bio_add_folio_nofail(bio, bh->b_folio, bh->b_size, bh_offset(bh)); bio->bi_end_io = end_bio_bh_io_sync; bio->bi_private = bh; /* Take care of bh's that straddle the end of the device */ guard_bio_eod(bio); if (wbc) { wbc_init_bio(wbc, bio); wbc_account_cgroup_owner(wbc, bh->b_folio, bh->b_size); } blk_crypto_submit_bio(bio); } void submit_bh(blk_opf_t opf, struct buffer_head *bh) { submit_bh_wbc(opf, bh, WRITE_LIFE_NOT_SET, NULL); } EXPORT_SYMBOL(submit_bh); void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { lock_buffer(bh); if (!test_clear_buffer_dirty(bh)) { unlock_buffer(bh); return; } bh->b_end_io = end_buffer_write_sync; get_bh(bh); submit_bh(REQ_OP_WRITE | op_flags, bh); } EXPORT_SYMBOL(write_dirty_buffer); /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { WARN_ON(atomic_read(&bh->b_count) < 1); lock_buffer(bh); if (test_clear_buffer_dirty(bh)) { /* * The bh should be mapped, but it might not be if the * device was hot-removed. Not much we can do but fail the I/O. */ if (!buffer_mapped(bh)) { unlock_buffer(bh); return -EIO; } get_bh(bh); bh->b_end_io = end_buffer_write_sync; submit_bh(REQ_OP_WRITE | op_flags, bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) return -EIO; } else { unlock_buffer(bh); } return 0; } EXPORT_SYMBOL(__sync_dirty_buffer); int sync_dirty_buffer(struct buffer_head *bh) { return __sync_dirty_buffer(bh, REQ_SYNC); } EXPORT_SYMBOL(sync_dirty_buffer); static inline int buffer_busy(struct buffer_head *bh) { return atomic_read(&bh->b_count) | (bh->b_state & ((1 << BH_Dirty) | (1 << BH_Lock))); } static bool drop_buffers(struct folio *folio, struct buffer_head **buffers_to_free) { struct buffer_head *head = folio_buffers(folio); struct buffer_head *bh; bh = head; do { if (buffer_busy(bh)) goto failed; bh = bh->b_this_page; } while (bh != head); do { struct buffer_head *next = bh->b_this_page; remove_assoc_queue(bh); bh = next; } while (bh != head); *buffers_to_free = head; folio_detach_private(folio); return true; failed: return false; } /** * try_to_free_buffers - Release buffers attached to this folio. * @folio: The folio. * * If any buffers are in use (dirty, under writeback, elevated refcount), * no buffers will be freed. * * If the folio is dirty but all the buffers are clean then we need to * be sure to mark the folio clean as well. This is because the folio * may be against a block device, and a later reattachment of buffers * to a dirty folio will set *all* buffers dirty. Which would corrupt * filesystem data on the same device. * * The same applies to regular filesystem folios: if all the buffers are * clean then we set the folio clean and proceed. To do that, we require * total exclusion from block_dirty_folio(). That is obtained with * i_private_lock. * * Exclusion against try_to_free_buffers may be obtained by either * locking the folio or by holding its mapping's i_private_lock. * * Context: Process context. @folio must be locked. Will not sleep. * Return: true if all buffers attached to this folio were freed. */ bool try_to_free_buffers(struct folio *folio) { struct address_space * const mapping = folio->mapping; struct buffer_head *buffers_to_free = NULL; bool ret = 0; BUG_ON(!folio_test_locked(folio)); if (folio_test_writeback(folio)) return false; /* Misconfigured folio check */ if (WARN_ON_ONCE(!folio_buffers(folio))) return true; if (mapping == NULL) { /* can this still happen? */ ret = drop_buffers(folio, &buffers_to_free); goto out; } spin_lock(&mapping->i_private_lock); ret = drop_buffers(folio, &buffers_to_free); /* * If the filesystem writes its buffers by hand (eg ext3) * then we can have clean buffers against a dirty folio. We * clean the folio here; otherwise the VM will never notice * that the filesystem did any IO at all. * * Also, during truncate, discard_buffer will have marked all * the folio's buffers clean. We discover that here and clean * the folio also. * * i_private_lock must be held over this entire operation in order * to synchronise against block_dirty_folio and prevent the * dirty bit from being lost. */ if (ret) folio_cancel_dirty(folio); spin_unlock(&mapping->i_private_lock); out: if (buffers_to_free) { struct buffer_head *bh = buffers_to_free; do { struct buffer_head *next = bh->b_this_page; free_buffer_head(bh); bh = next; } while (bh != buffers_to_free); } return ret; } EXPORT_SYMBOL(try_to_free_buffers); /* * Buffer-head allocation */ static struct kmem_cache *bh_cachep __ro_after_init; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ static unsigned long max_buffer_heads __ro_after_init; int buffer_heads_over_limit; struct bh_accounting { int nr; /* Number of live bh's */ int ratelimit; /* Limit cacheline bouncing */ }; static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = {0, 0}; static void recalc_bh_state(void) { int i; int tot = 0; if (__this_cpu_inc_return(bh_accounting.ratelimit) - 1 < 4096) return; __this_cpu_write(bh_accounting.ratelimit, 0); for_each_online_cpu(i) tot += per_cpu(bh_accounting, i).nr; buffer_heads_over_limit = (tot > max_buffer_heads); } struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); if (ret) { INIT_LIST_HEAD(&ret->b_assoc_buffers); spin_lock_init(&ret->b_uptodate_lock); preempt_disable(); __this_cpu_inc(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } return ret; } EXPORT_SYMBOL(alloc_buffer_head); void free_buffer_head(struct buffer_head *bh) { BUG_ON(!list_empty(&bh->b_assoc_buffers)); kmem_cache_free(bh_cachep, bh); preempt_disable(); __this_cpu_dec(bh_accounting.nr); recalc_bh_state(); preempt_enable(); } EXPORT_SYMBOL(free_buffer_head); static int buffer_exit_cpu_dead(unsigned int cpu) { int i; struct bh_lru *b = &per_cpu(bh_lrus, cpu); for (i = 0; i < BH_LRU_SIZE; i++) { brelse(b->bhs[i]); b->bhs[i] = NULL; } this_cpu_add(bh_accounting.nr, per_cpu(bh_accounting, cpu).nr); per_cpu(bh_accounting, cpu).nr = 0; return 0; } /** * bh_uptodate_or_lock - Test whether the buffer is uptodate * @bh: struct buffer_head * * Return true if the buffer is up-to-date and false, * with the buffer locked, if not. */ int bh_uptodate_or_lock(struct buffer_head *bh) { if (!buffer_uptodate(bh)) { lock_buffer(bh); if (!buffer_uptodate(bh)) return 0; unlock_buffer(bh); } return 1; } EXPORT_SYMBOL(bh_uptodate_or_lock); /** * __bh_read - Submit read for a locked buffer * @bh: struct buffer_head * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ * @wait: wait until reading finish * * Returns zero on success or don't wait, and -EIO on error. */ int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { int ret = 0; BUG_ON(!buffer_locked(bh)); get_bh(bh); bh->b_end_io = end_buffer_read_sync; submit_bh(REQ_OP_READ | op_flags, bh); if (wait) { wait_on_buffer(bh); if (!buffer_uptodate(bh)) ret = -EIO; } return ret; } EXPORT_SYMBOL(__bh_read); /** * __bh_read_batch - Submit read for a batch of unlocked buffers * @nr: entry number of the buffer batch * @bhs: a batch of struct buffer_head * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ * @force_lock: force to get a lock on the buffer if set, otherwise drops any * buffer that cannot lock. * * Returns zero on success or don't wait, and -EIO on error. */ void __bh_read_batch(int nr, struct buffer_head *bhs[], blk_opf_t op_flags, bool force_lock) { int i; for (i = 0; i < nr; i++) { struct buffer_head *bh = bhs[i]; if (buffer_uptodate(bh)) continue; if (force_lock) lock_buffer(bh); else if (!trylock_buffer(bh)) continue; if (buffer_uptodate(bh)) { unlock_buffer(bh); continue; } bh->b_end_io = end_buffer_read_sync; get_bh(bh); submit_bh(REQ_OP_READ | op_flags, bh); } } EXPORT_SYMBOL(__bh_read_batch); void __init buffer_init(void) { unsigned long nrpages; int ret; bh_cachep = KMEM_CACHE(buffer_head, SLAB_RECLAIM_ACCOUNT|SLAB_PANIC); /* * Limit the bh occupancy to 10% of ZONE_NORMAL */ nrpages = (nr_free_buffer_pages() * 10) / 100; max_buffer_heads = nrpages * (PAGE_SIZE / sizeof(struct buffer_head)); ret = cpuhp_setup_state_nocalls(CPUHP_FS_BUFF_DEAD, "fs/buffer:dead", NULL, buffer_exit_cpu_dead); WARN_ON(ret < 0); } |
| 3 1 2 23 12 4 5 2 14 3 3 2 1 3 3 3 3 7 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.org> */ #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_nat.h> #include <net/netfilter/nf_nat_redirect.h> #include <net/netfilter/nf_tables.h> struct nft_redir { u8 sreg_proto_min; u8 sreg_proto_max; u16 flags; }; static const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = { [NFTA_REDIR_REG_PROTO_MIN] = { .type = NLA_U32 }, [NFTA_REDIR_REG_PROTO_MAX] = { .type = NLA_U32 }, [NFTA_REDIR_FLAGS] = NLA_POLICY_MASK(NLA_BE32, NF_NAT_RANGE_MASK), }; static int nft_redir_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { int err; err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); if (err < 0) return err; return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT)); } static int nft_redir_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_redir *priv = nft_expr_priv(expr); unsigned int plen; int err; plen = sizeof_field(struct nf_nat_range, min_proto.all); if (tb[NFTA_REDIR_REG_PROTO_MIN]) { err = nft_parse_register_load(ctx, tb[NFTA_REDIR_REG_PROTO_MIN], &priv->sreg_proto_min, plen); if (err < 0) return err; if (tb[NFTA_REDIR_REG_PROTO_MAX]) { err = nft_parse_register_load(ctx, tb[NFTA_REDIR_REG_PROTO_MAX], &priv->sreg_proto_max, plen); if (err < 0) return err; } else { priv->sreg_proto_max = priv->sreg_proto_min; } priv->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } if (tb[NFTA_REDIR_FLAGS]) priv->flags = ntohl(nla_get_be32(tb[NFTA_REDIR_FLAGS])); return nf_ct_netns_get(ctx->net, ctx->family); } static int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_redir *priv = nft_expr_priv(expr); if (priv->sreg_proto_min) { if (nft_dump_register(skb, NFTA_REDIR_REG_PROTO_MIN, priv->sreg_proto_min)) goto nla_put_failure; if (nft_dump_register(skb, NFTA_REDIR_REG_PROTO_MAX, priv->sreg_proto_max)) goto nla_put_failure; } if (priv->flags != 0 && nla_put_be32(skb, NFTA_REDIR_FLAGS, htonl(priv->flags))) goto nla_put_failure; return 0; nla_put_failure: return -1; } static void nft_redir_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_redir *priv = nft_expr_priv(expr); struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); range.flags = priv->flags; if (priv->sreg_proto_min) { range.min_proto.all = (__force __be16) nft_reg_load16(®s->data[priv->sreg_proto_min]); range.max_proto.all = (__force __be16) nft_reg_load16(®s->data[priv->sreg_proto_max]); } switch (nft_pf(pkt)) { case NFPROTO_IPV4: regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &range, nft_hook(pkt)); break; #ifdef CONFIG_NF_TABLES_IPV6 case NFPROTO_IPV6: regs->verdict.code = nf_nat_redirect_ipv6(pkt->skb, &range, nft_hook(pkt)); break; #endif default: WARN_ON_ONCE(1); break; } } static void nft_redir_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nf_ct_netns_put(ctx->net, NFPROTO_IPV4); } static struct nft_expr_type nft_redir_ipv4_type; static const struct nft_expr_ops nft_redir_ipv4_ops = { .type = &nft_redir_ipv4_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_redir)), .eval = nft_redir_eval, .init = nft_redir_init, .destroy = nft_redir_ipv4_destroy, .dump = nft_redir_dump, .validate = nft_redir_validate, }; static struct nft_expr_type nft_redir_ipv4_type __read_mostly = { .family = NFPROTO_IPV4, .name = "redir", .ops = &nft_redir_ipv4_ops, .policy = nft_redir_policy, .maxattr = NFTA_REDIR_MAX, .owner = THIS_MODULE, }; #ifdef CONFIG_NF_TABLES_IPV6 static void nft_redir_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nf_ct_netns_put(ctx->net, NFPROTO_IPV6); } static struct nft_expr_type nft_redir_ipv6_type; static const struct nft_expr_ops nft_redir_ipv6_ops = { .type = &nft_redir_ipv6_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_redir)), .eval = nft_redir_eval, .init = nft_redir_init, .destroy = nft_redir_ipv6_destroy, .dump = nft_redir_dump, .validate = nft_redir_validate, }; static struct nft_expr_type nft_redir_ipv6_type __read_mostly = { .family = NFPROTO_IPV6, .name = "redir", .ops = &nft_redir_ipv6_ops, .policy = nft_redir_policy, .maxattr = NFTA_REDIR_MAX, .owner = THIS_MODULE, }; #endif #ifdef CONFIG_NF_TABLES_INET static void nft_redir_inet_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { nf_ct_netns_put(ctx->net, NFPROTO_INET); } static struct nft_expr_type nft_redir_inet_type; static const struct nft_expr_ops nft_redir_inet_ops = { .type = &nft_redir_inet_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_redir)), .eval = nft_redir_eval, .init = nft_redir_init, .destroy = nft_redir_inet_destroy, .dump = nft_redir_dump, .validate = nft_redir_validate, }; static struct nft_expr_type nft_redir_inet_type __read_mostly = { .family = NFPROTO_INET, .name = "redir", .ops = &nft_redir_inet_ops, .policy = nft_redir_policy, .maxattr = NFTA_REDIR_MAX, .owner = THIS_MODULE, }; static int __init nft_redir_module_init_inet(void) { return nft_register_expr(&nft_redir_inet_type); } #else static inline int nft_redir_module_init_inet(void) { return 0; } #endif static int __init nft_redir_module_init(void) { int ret = nft_register_expr(&nft_redir_ipv4_type); if (ret) return ret; #ifdef CONFIG_NF_TABLES_IPV6 ret = nft_register_expr(&nft_redir_ipv6_type); if (ret) { nft_unregister_expr(&nft_redir_ipv4_type); return ret; } #endif ret = nft_redir_module_init_inet(); if (ret < 0) { nft_unregister_expr(&nft_redir_ipv4_type); #ifdef CONFIG_NF_TABLES_IPV6 nft_unregister_expr(&nft_redir_ipv6_type); #endif return ret; } return ret; } static void __exit nft_redir_module_exit(void) { nft_unregister_expr(&nft_redir_ipv4_type); #ifdef CONFIG_NF_TABLES_IPV6 nft_unregister_expr(&nft_redir_ipv6_type); #endif #ifdef CONFIG_NF_TABLES_INET nft_unregister_expr(&nft_redir_inet_type); #endif } module_init(nft_redir_module_init); module_exit(nft_redir_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>"); MODULE_ALIAS_NFT_EXPR("redir"); MODULE_DESCRIPTION("Netfilter nftables redirect support"); |
| 4 4 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 | // SPDX-License-Identifier: GPL-2.0 /* Watch queue and general notification mechanism, built on pipes * * Copyright (C) 2020 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * See Documentation/core-api/watch_queue.rst */ #define pr_fmt(fmt) "watchq: " fmt #include <linux/module.h> #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/printk.h> #include <linux/miscdevice.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/poll.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/file.h> #include <linux/security.h> #include <linux/cred.h> #include <linux/sched/signal.h> #include <linux/watch_queue.h> #include <linux/pipe_fs_i.h> MODULE_DESCRIPTION("Watch queue"); MODULE_AUTHOR("Red Hat, Inc."); #define WATCH_QUEUE_NOTE_SIZE 128 #define WATCH_QUEUE_NOTES_PER_PAGE (PAGE_SIZE / WATCH_QUEUE_NOTE_SIZE) /* * This must be called under the RCU read-lock, which makes * sure that the wqueue still exists. It can then take the lock, * and check that the wqueue hasn't been destroyed, which in * turn makes sure that the notification pipe still exists. */ static inline bool lock_wqueue(struct watch_queue *wqueue) { spin_lock_bh(&wqueue->lock); if (unlikely(!wqueue->pipe)) { spin_unlock_bh(&wqueue->lock); return false; } return true; } static inline void unlock_wqueue(struct watch_queue *wqueue) { spin_unlock_bh(&wqueue->lock); } static void watch_queue_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct watch_queue *wqueue = (struct watch_queue *)buf->private; struct page *page; unsigned int bit; /* We need to work out which note within the page this refers to, but * the note might have been maximum size, so merely ANDing the offset * off doesn't work. OTOH, the note must've been more than zero size. */ bit = buf->offset + buf->len; if ((bit & (WATCH_QUEUE_NOTE_SIZE - 1)) == 0) bit -= WATCH_QUEUE_NOTE_SIZE; bit /= WATCH_QUEUE_NOTE_SIZE; page = buf->page; bit += page->private; set_bit(bit, wqueue->notes_bitmap); generic_pipe_buf_release(pipe, buf); } // No try_steal function => no stealing #define watch_queue_pipe_buf_try_steal NULL /* New data written to a pipe may be appended to a buffer with this type. */ static const struct pipe_buf_operations watch_queue_pipe_buf_ops = { .release = watch_queue_pipe_buf_release, .try_steal = watch_queue_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* * Post a notification to a watch queue. * * Must be called with the RCU lock for reading, and the * watch_queue lock held, which guarantees that the pipe * hasn't been released. */ static bool post_one_notification(struct watch_queue *wqueue, struct watch_notification *n) { void *p; struct pipe_inode_info *pipe = wqueue->pipe; struct pipe_buffer *buf; struct page *page; unsigned int head, tail, note, offset, len; bool done = false; spin_lock_irq(&pipe->rd_wait.lock); head = pipe->head; tail = pipe->tail; if (pipe_full(head, tail, pipe->ring_size)) goto lost; note = find_first_bit(wqueue->notes_bitmap, wqueue->nr_notes); if (note >= wqueue->nr_notes) goto lost; page = wqueue->notes[note / WATCH_QUEUE_NOTES_PER_PAGE]; offset = note % WATCH_QUEUE_NOTES_PER_PAGE * WATCH_QUEUE_NOTE_SIZE; get_page(page); len = n->info & WATCH_INFO_LENGTH; p = kmap_local_page(page); memcpy(p + offset, n, len); kunmap_local(p); buf = pipe_buf(pipe, head); buf->page = page; buf->private = (unsigned long)wqueue; buf->ops = &watch_queue_pipe_buf_ops; buf->offset = offset; buf->len = len; buf->flags = PIPE_BUF_FLAG_WHOLE; smp_store_release(&pipe->head, head + 1); /* vs pipe_read() */ if (!test_and_clear_bit(note, wqueue->notes_bitmap)) { spin_unlock_irq(&pipe->rd_wait.lock); BUG(); } wake_up_interruptible_sync_poll_locked(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); done = true; out: spin_unlock_irq(&pipe->rd_wait.lock); if (done) kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); return done; lost: buf = pipe_buf(pipe, head - 1); buf->flags |= PIPE_BUF_FLAG_LOSS; goto out; } /* * Apply filter rules to a notification. */ static bool filter_watch_notification(const struct watch_filter *wf, const struct watch_notification *n) { const struct watch_type_filter *wt; unsigned int st_bits = sizeof(wt->subtype_filter[0]) * 8; unsigned int st_index = n->subtype / st_bits; unsigned int st_bit = 1U << (n->subtype % st_bits); int i; if (!test_bit(n->type, wf->type_filter)) return false; for (i = 0; i < wf->nr_filters; i++) { wt = &wf->filters[i]; if (n->type == wt->type && (wt->subtype_filter[st_index] & st_bit) && (n->info & wt->info_mask) == wt->info_filter) return true; } return false; /* If there is a filter, the default is to reject. */ } /** * __post_watch_notification - Post an event notification * @wlist: The watch list to post the event to. * @n: The notification record to post. * @cred: The creds of the process that triggered the notification. * @id: The ID to match on the watch. * * Post a notification of an event into a set of watch queues and let the users * know. * * The size of the notification should be set in n->info & WATCH_INFO_LENGTH and * should be in units of sizeof(*n). */ void __post_watch_notification(struct watch_list *wlist, struct watch_notification *n, const struct cred *cred, u64 id) { const struct watch_filter *wf; struct watch_queue *wqueue; struct watch *watch; if (((n->info & WATCH_INFO_LENGTH) >> WATCH_INFO_LENGTH__SHIFT) == 0) { WARN_ON(1); return; } rcu_read_lock(); hlist_for_each_entry_rcu(watch, &wlist->watchers, list_node) { if (watch->id != id) continue; n->info &= ~WATCH_INFO_ID; n->info |= watch->info_id; wqueue = rcu_dereference(watch->queue); wf = rcu_dereference(wqueue->filter); if (wf && !filter_watch_notification(wf, n)) continue; if (security_post_notification(watch->cred, cred, n) < 0) continue; if (lock_wqueue(wqueue)) { post_one_notification(wqueue, n); unlock_wqueue(wqueue); } } rcu_read_unlock(); } EXPORT_SYMBOL(__post_watch_notification); /* * Allocate sufficient pages to preallocation for the requested number of * notifications. */ long watch_queue_set_size(struct pipe_inode_info *pipe, unsigned int nr_notes) { struct watch_queue *wqueue = pipe->watch_queue; struct page **pages; unsigned long *bitmap; unsigned long user_bufs; int ret, i, nr_pages; if (!wqueue) return -ENODEV; if (wqueue->notes) return -EBUSY; if (nr_notes < 1 || nr_notes > 512) /* TODO: choose a better hard limit */ return -EINVAL; nr_pages = (nr_notes + WATCH_QUEUE_NOTES_PER_PAGE - 1); nr_pages /= WATCH_QUEUE_NOTES_PER_PAGE; user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_pages); if (nr_pages > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && pipe_is_unprivileged_user()) { ret = -EPERM; goto error; } nr_notes = nr_pages * WATCH_QUEUE_NOTES_PER_PAGE; ret = pipe_resize_ring(pipe, roundup_pow_of_two(nr_notes)); if (ret < 0) goto error; /* * pipe_resize_ring() does not update nr_accounted for watch_queue * pipes, because the above vastly overprovisions. Set nr_accounted on * and max_usage this pipe to the number that was actually charged to * the user above via account_pipe_buffers. */ pipe->max_usage = nr_pages; pipe->nr_accounted = nr_pages; ret = -ENOMEM; pages = kzalloc_objs(struct page *, nr_pages); if (!pages) goto error; for (i = 0; i < nr_pages; i++) { pages[i] = alloc_page(GFP_KERNEL); if (!pages[i]) goto error_p; pages[i]->private = i * WATCH_QUEUE_NOTES_PER_PAGE; } bitmap = bitmap_alloc(nr_notes, GFP_KERNEL); if (!bitmap) goto error_p; bitmap_fill(bitmap, nr_notes); wqueue->notes = pages; wqueue->notes_bitmap = bitmap; wqueue->nr_pages = nr_pages; wqueue->nr_notes = nr_notes; return 0; error_p: while (--i >= 0) __free_page(pages[i]); kfree(pages); error: (void) account_pipe_buffers(pipe->user, nr_pages, pipe->nr_accounted); return ret; } /* * Set the filter on a watch queue. */ long watch_queue_set_filter(struct pipe_inode_info *pipe, struct watch_notification_filter __user *_filter) { struct watch_notification_type_filter *tf; struct watch_notification_filter filter; struct watch_type_filter *q; struct watch_filter *wfilter; struct watch_queue *wqueue = pipe->watch_queue; int ret, nr_filter = 0, i; if (!wqueue) return -ENODEV; if (!_filter) { /* Remove the old filter */ wfilter = NULL; goto set; } /* Grab the user's filter specification */ if (copy_from_user(&filter, _filter, sizeof(filter)) != 0) return -EFAULT; if (filter.nr_filters == 0 || filter.nr_filters > 16 || filter.__reserved != 0) return -EINVAL; tf = memdup_array_user(_filter->filters, filter.nr_filters, sizeof(*tf)); if (IS_ERR(tf)) return PTR_ERR(tf); ret = -EINVAL; for (i = 0; i < filter.nr_filters; i++) { if ((tf[i].info_filter & ~tf[i].info_mask) || tf[i].info_mask & WATCH_INFO_LENGTH) goto err_filter; /* Ignore any unknown types */ if (tf[i].type >= WATCH_TYPE__NR) continue; nr_filter++; } /* Now we need to build the internal filter from only the relevant * user-specified filters. */ ret = -ENOMEM; wfilter = kzalloc_flex(*wfilter, filters, nr_filter); if (!wfilter) goto err_filter; wfilter->nr_filters = nr_filter; q = wfilter->filters; for (i = 0; i < filter.nr_filters; i++) { if (tf[i].type >= WATCH_TYPE__NR) continue; q->type = tf[i].type; q->info_filter = tf[i].info_filter; q->info_mask = tf[i].info_mask; q->subtype_filter[0] = tf[i].subtype_filter[0]; __set_bit(q->type, wfilter->type_filter); q++; } kfree(tf); set: pipe_lock(pipe); wfilter = rcu_replace_pointer(wqueue->filter, wfilter, lockdep_is_held(&pipe->mutex)); pipe_unlock(pipe); if (wfilter) kfree_rcu(wfilter, rcu); return 0; err_filter: kfree(tf); return ret; } static void __put_watch_queue(struct kref *kref) { struct watch_queue *wqueue = container_of(kref, struct watch_queue, usage); struct watch_filter *wfilter; int i; for (i = 0; i < wqueue->nr_pages; i++) __free_page(wqueue->notes[i]); kfree(wqueue->notes); bitmap_free(wqueue->notes_bitmap); wfilter = rcu_access_pointer(wqueue->filter); if (wfilter) kfree_rcu(wfilter, rcu); kfree_rcu(wqueue, rcu); } /** * put_watch_queue - Dispose of a ref on a watchqueue. * @wqueue: The watch queue to unref. */ void put_watch_queue(struct watch_queue *wqueue) { kref_put(&wqueue->usage, __put_watch_queue); } EXPORT_SYMBOL(put_watch_queue); static void free_watch(struct rcu_head *rcu) { struct watch *watch = container_of(rcu, struct watch, rcu); put_watch_queue(rcu_access_pointer(watch->queue)); atomic_dec(&watch->cred->user->nr_watches); put_cred(watch->cred); kfree(watch); } static void __put_watch(struct kref *kref) { struct watch *watch = container_of(kref, struct watch, usage); call_rcu(&watch->rcu, free_watch); } /* * Discard a watch. */ static void put_watch(struct watch *watch) { kref_put(&watch->usage, __put_watch); } /** * init_watch - Initialise a watch * @watch: The watch to initialise. * @wqueue: The queue to assign. * * Initialise a watch and set the watch queue. */ void init_watch(struct watch *watch, struct watch_queue *wqueue) { kref_init(&watch->usage); INIT_HLIST_NODE(&watch->list_node); INIT_HLIST_NODE(&watch->queue_node); rcu_assign_pointer(watch->queue, wqueue); } static int add_one_watch(struct watch *watch, struct watch_list *wlist, struct watch_queue *wqueue) { const struct cred *cred; struct watch *w; hlist_for_each_entry(w, &wlist->watchers, list_node) { struct watch_queue *wq = rcu_access_pointer(w->queue); if (wqueue == wq && watch->id == w->id) return -EBUSY; } cred = current_cred(); if (atomic_inc_return(&cred->user->nr_watches) > task_rlimit(current, RLIMIT_NOFILE)) { atomic_dec(&cred->user->nr_watches); return -EAGAIN; } watch->cred = get_cred(cred); rcu_assign_pointer(watch->watch_list, wlist); kref_get(&wqueue->usage); kref_get(&watch->usage); hlist_add_head(&watch->queue_node, &wqueue->watches); hlist_add_head_rcu(&watch->list_node, &wlist->watchers); return 0; } /** * add_watch_to_object - Add a watch on an object to a watch list * @watch: The watch to add * @wlist: The watch list to add to * * @watch->queue must have been set to point to the queue to post notifications * to and the watch list of the object to be watched. @watch->cred must also * have been set to the appropriate credentials and a ref taken on them. * * The caller must pin the queue and the list both and must hold the list * locked against racing watch additions/removals. */ int add_watch_to_object(struct watch *watch, struct watch_list *wlist) { struct watch_queue *wqueue; int ret = -ENOENT; rcu_read_lock(); wqueue = rcu_access_pointer(watch->queue); if (lock_wqueue(wqueue)) { spin_lock(&wlist->lock); ret = add_one_watch(watch, wlist, wqueue); spin_unlock(&wlist->lock); unlock_wqueue(wqueue); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(add_watch_to_object); /** * remove_watch_from_object - Remove a watch or all watches from an object. * @wlist: The watch list to remove from * @wq: The watch queue of interest (ignored if @all is true) * @id: The ID of the watch to remove (ignored if @all is true) * @all: True to remove all objects * * Remove a specific watch or all watches from an object. A notification is * sent to the watcher to tell them that this happened. */ int remove_watch_from_object(struct watch_list *wlist, struct watch_queue *wq, u64 id, bool all) { struct watch_notification_removal n; struct watch_queue *wqueue; struct watch *watch; int ret = -EBADSLT; rcu_read_lock(); again: spin_lock(&wlist->lock); hlist_for_each_entry(watch, &wlist->watchers, list_node) { if (all || (watch->id == id && rcu_access_pointer(watch->queue) == wq)) goto found; } spin_unlock(&wlist->lock); goto out; found: ret = 0; hlist_del_init_rcu(&watch->list_node); rcu_assign_pointer(watch->watch_list, NULL); spin_unlock(&wlist->lock); /* We now own the reference on watch that used to belong to wlist. */ n.watch.type = WATCH_TYPE_META; n.watch.subtype = WATCH_META_REMOVAL_NOTIFICATION; n.watch.info = watch->info_id | watch_sizeof(n.watch); n.id = id; if (id != 0) n.watch.info = watch->info_id | watch_sizeof(n); wqueue = rcu_dereference(watch->queue); if (lock_wqueue(wqueue)) { post_one_notification(wqueue, &n.watch); if (!hlist_unhashed(&watch->queue_node)) { hlist_del_init_rcu(&watch->queue_node); put_watch(watch); } unlock_wqueue(wqueue); } if (wlist->release_watch) { void (*release_watch)(struct watch *); release_watch = wlist->release_watch; rcu_read_unlock(); (*release_watch)(watch); rcu_read_lock(); } put_watch(watch); if (all && !hlist_empty(&wlist->watchers)) goto again; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL(remove_watch_from_object); /* * Remove all the watches that are contributory to a queue. This has the * potential to race with removal of the watches by the destruction of the * objects being watched or with the distribution of notifications. */ void watch_queue_clear(struct watch_queue *wqueue) { struct watch_list *wlist; struct watch *watch; bool release; rcu_read_lock(); spin_lock_bh(&wqueue->lock); /* * This pipe can be freed by callers like free_pipe_info(). * Removing this reference also prevents new notifications. */ wqueue->pipe = NULL; while (!hlist_empty(&wqueue->watches)) { watch = hlist_entry(wqueue->watches.first, struct watch, queue_node); hlist_del_init_rcu(&watch->queue_node); /* We now own a ref on the watch. */ spin_unlock_bh(&wqueue->lock); /* We can't do the next bit under the queue lock as we need to * get the list lock - which would cause a deadlock if someone * was removing from the opposite direction at the same time or * posting a notification. */ wlist = rcu_dereference(watch->watch_list); if (wlist) { void (*release_watch)(struct watch *); spin_lock(&wlist->lock); release = !hlist_unhashed(&watch->list_node); if (release) { hlist_del_init_rcu(&watch->list_node); rcu_assign_pointer(watch->watch_list, NULL); /* We now own a second ref on the watch. */ } release_watch = wlist->release_watch; spin_unlock(&wlist->lock); if (release) { if (release_watch) { rcu_read_unlock(); /* This might need to call dput(), so * we have to drop all the locks. */ (*release_watch)(watch); rcu_read_lock(); } put_watch(watch); } } put_watch(watch); spin_lock_bh(&wqueue->lock); } spin_unlock_bh(&wqueue->lock); rcu_read_unlock(); } /** * get_watch_queue - Get a watch queue from its file descriptor. * @fd: The fd to query. */ struct watch_queue *get_watch_queue(int fd) { struct pipe_inode_info *pipe; struct watch_queue *wqueue = ERR_PTR(-EINVAL); CLASS(fd, f)(fd); if (!fd_empty(f)) { pipe = get_pipe_info(fd_file(f), false); if (pipe && pipe->watch_queue) { wqueue = pipe->watch_queue; kref_get(&wqueue->usage); } } return wqueue; } EXPORT_SYMBOL(get_watch_queue); /* * Initialise a watch queue */ int watch_queue_init(struct pipe_inode_info *pipe) { struct watch_queue *wqueue; wqueue = kzalloc_obj(*wqueue); if (!wqueue) return -ENOMEM; wqueue->pipe = pipe; kref_init(&wqueue->usage); spin_lock_init(&wqueue->lock); INIT_HLIST_HEAD(&wqueue->watches); pipe->watch_queue = wqueue; return 0; } |
| 5 41 8 33 33 33 22 22 2 1 1 3 1 2 5 5 65 64 1 1 1 1 5 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/ctype.h> #include <linux/kmod.h> #include <linux/sort.h> #include <linux/delay.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/vmalloc.h> #include <linux/delayacct.h> #include <linux/pid_namespace.h> #include <linux/cgroupstats.h> #include <linux/fs_parser.h> #include <trace/events/cgroup.h> /* * pidlists linger the following amount before being destroyed. The goal * is avoiding frequent destruction in the middle of consecutive read calls * Expiring in the middle is a performance problem not a correctness one. * 1 sec should be enough. */ #define CGROUP_PIDLIST_DESTROY_DELAY HZ /* Controllers blocked by the commandline in v1 */ static u32 cgroup_no_v1_mask; /* disable named v1 mounts */ static bool cgroup_no_v1_named; /* Show unavailable controllers in /proc/cgroups */ static bool proc_show_all; /* * pidlist destructions need to be flushed on cgroup destruction. Use a * separate workqueue as flush domain. */ static struct workqueue_struct *cgroup_pidlist_destroy_wq; /* protects cgroup_subsys->release_agent_path */ static DEFINE_SPINLOCK(release_agent_path_lock); bool cgroup1_ssid_disabled(int ssid) { return cgroup_no_v1_mask & (1 << ssid); } static bool cgroup1_subsys_absent(struct cgroup_subsys *ss) { /* Check also dfl_cftypes for file-less controllers, i.e. perf_event */ return ss->legacy_cftypes == NULL && ss->dfl_cftypes; } /** * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' * @from: attach to all cgroups of a given task * @tsk: the task to be attached * * Return: %0 on success or a negative errno code on failure */ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroup_root *root; int retval = 0; cgroup_lock(); cgroup_attach_lock(CGRP_ATTACH_LOCK_GLOBAL, NULL); for_each_root(root) { struct cgroup *from_cgrp; spin_lock_irq(&css_set_lock); from_cgrp = task_cgroup_from_root(from, root); spin_unlock_irq(&css_set_lock); retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) break; } cgroup_attach_unlock(CGRP_ATTACH_LOCK_GLOBAL, NULL); cgroup_unlock(); return retval; } EXPORT_SYMBOL_GPL(cgroup_attach_task_all); /** * cgroup_transfer_tasks - move tasks from one cgroup to another * @to: cgroup to which the tasks will be moved * @from: cgroup in which the tasks currently reside * * Locking rules between cgroup_post_fork() and the migration path * guarantee that, if a task is forking while being migrated, the new child * is guaranteed to be either visible in the source cgroup after the * parent's migration is complete or put into the target cgroup. No task * can slip out of migration through forking. * * Return: %0 on success or a negative errno code on failure */ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) { DEFINE_CGROUP_MGCTX(mgctx); struct cgrp_cset_link *link; struct css_task_iter it; struct task_struct *task; int ret; if (cgroup_on_dfl(to)) return -EINVAL; ret = cgroup_migrate_vet_dst(to); if (ret) return ret; cgroup_lock(); cgroup_attach_lock(CGRP_ATTACH_LOCK_GLOBAL, NULL); /* all tasks in @from are being moved, all csets are source */ spin_lock_irq(&css_set_lock); list_for_each_entry(link, &from->cset_links, cset_link) cgroup_migrate_add_src(link->cset, to, &mgctx); spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_err; /* * Migrate tasks one-by-one until @from is empty. This fails iff * ->can_attach() fails. */ do { css_task_iter_start(&from->self, 0, &it); do { task = css_task_iter_next(&it); } while (task && (task->flags & PF_EXITING)); if (task) get_task_struct(task); css_task_iter_end(&it); if (task) { ret = cgroup_migrate(task, false, &mgctx); if (!ret) TRACE_CGROUP_PATH(transfer_tasks, to, task, false); put_task_struct(task); } } while (task && !ret); out_err: cgroup_migrate_finish(&mgctx); cgroup_attach_unlock(CGRP_ATTACH_LOCK_GLOBAL, NULL); cgroup_unlock(); return ret; } /* * Stuff for reading the 'tasks'/'procs' files. * * Reading this file can return large amounts of data if a cgroup has * *lots* of attached tasks. So it may need several calls to read(), * but we cannot guarantee that the information we produce is correct * unless we produce it entirely atomically. * */ /* which pidlist file are we talking about? */ enum cgroup_filetype { CGROUP_FILE_PROCS, CGROUP_FILE_TASKS, }; /* * A pidlist is a list of pids that virtually represents the contents of one * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, * a pair (one each for procs, tasks) for each pid namespace that's relevant * to the cgroup. */ struct cgroup_pidlist { /* * used to find which pidlist is wanted. doesn't change as long as * this particular list stays in the list. */ struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; /* array of xids */ pid_t *list; /* how many elements the above list has */ int length; /* each of these stored in a list by its cgroup */ struct list_head links; /* pointer to the cgroup we belong to, for list removal purposes */ struct cgroup *owner; /* for delayed destruction */ struct delayed_work destroy_dwork; }; /* * Used to destroy all pidlists lingering waiting for destroy timer. None * should be left afterwards. */ void cgroup1_pidlist_destroy_all(struct cgroup *cgrp) { struct cgroup_pidlist *l, *tmp_l; mutex_lock(&cgrp->pidlist_mutex); list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0); mutex_unlock(&cgrp->pidlist_mutex); flush_workqueue(cgroup_pidlist_destroy_wq); BUG_ON(!list_empty(&cgrp->pidlists)); } static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist, destroy_dwork); struct cgroup_pidlist *tofree = NULL; mutex_lock(&l->owner->pidlist_mutex); /* * Destroy iff we didn't get queued again. The state won't change * as destroy_dwork can only be queued while locked. */ if (!delayed_work_pending(dwork)) { list_del(&l->links); kvfree(l->list); put_pid_ns(l->key.ns); tofree = l; } mutex_unlock(&l->owner->pidlist_mutex); kfree(tofree); } /* * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries * Returns the number of unique elements. */ static int pidlist_uniq(pid_t *list, int length) { int src, dest = 1; /* * we presume the 0th element is unique, so i starts at 1. trivial * edge cases first; no work needs to be done for either */ if (length == 0 || length == 1) return length; /* src and dest walk down the list; dest counts unique elements */ for (src = 1; src < length; src++) { /* find next unique element */ while (list[src] == list[src-1]) { src++; if (src == length) goto after; } /* dest always points to where the next unique element goes */ list[dest] = list[src]; dest++; } after: return dest; } /* * The two pid files - task and cgroup.procs - guaranteed that the result * is sorted, which forced this whole pidlist fiasco. As pid order is * different per namespace, each namespace needs differently sorted list, * making it impossible to use, for example, single rbtree of member tasks * sorted by task pointer. As pidlists can be fairly large, allocating one * per open file is dangerous, so cgroup had to implement shared pool of * pidlists keyed by cgroup and namespace. */ static int cmppid(const void *a, const void *b) { return *(pid_t *)a - *(pid_t *)b; } static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; /* don't need task_nsproxy() if we're looking at ourself */ struct pid_namespace *ns = task_active_pid_ns(current); lockdep_assert_held(&cgrp->pidlist_mutex); list_for_each_entry(l, &cgrp->pidlists, links) if (l->key.type == type && l->key.ns == ns) return l; return NULL; } /* * find the appropriate pidlist for our purpose (given procs vs tasks) * returns with the lock on that pidlist already held, and takes care * of the use count, or returns NULL with no locks held if we're out of * memory. */ static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); l = cgroup_pidlist_find(cgrp, type); if (l) return l; /* entry not found; create a new one */ l = kzalloc_obj(struct cgroup_pidlist); if (!l) return l; INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn); l->key.type = type; /* don't need task_nsproxy() if we're looking at ourself */ l->key.ns = get_pid_ns(task_active_pid_ns(current)); l->owner = cgrp; list_add(&l->links, &cgrp->pidlists); return l; } /* * Load a cgroup's pidarray with either procs' tgids or tasks' pids */ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, struct cgroup_pidlist **lp) { pid_t *array; int length; int pid, n = 0; /* used for populating the array */ struct css_task_iter it; struct task_struct *tsk; struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); /* * If cgroup gets more users after we read count, we won't have * enough space - tough. This race is indistinguishable to the * caller from the case that the additional cgroup users didn't * show up until sometime later on. */ length = cgroup_task_count(cgrp); array = kvmalloc_objs(pid_t, length); if (!array) return -ENOMEM; /* now, populate the array */ css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { if (unlikely(n == length)) break; /* get tgid or pid for procs or tasks file respectively */ if (type == CGROUP_FILE_PROCS) pid = task_tgid_vnr(tsk); else pid = task_pid_vnr(tsk); if (pid > 0) /* make sure to only use valid results */ array[n++] = pid; } css_task_iter_end(&it); length = n; /* now sort & strip out duplicates (tgids or recycled thread PIDs) */ sort(array, length, sizeof(pid_t), cmppid, NULL); length = pidlist_uniq(array, length); l = cgroup_pidlist_find_create(cgrp, type); if (!l) { kvfree(array); return -ENOMEM; } /* store array, freeing old if necessary */ kvfree(l->list); l->list = array; l->length = length; *lp = l; return 0; } /* * seq_file methods for the tasks/procs files. The seq_file position is the * next pid to display; the seq_file iterator is a pointer to the pid * in the cgroup->l->list array. */ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) { /* * Initially we receive a position value that corresponds to * one more than the last pid shown (or 0 on the first call or * after a seek to the start). Use a binary-search to find the * next pid to display, if any */ struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_pidlist *l; enum cgroup_filetype type = seq_cft(s)->private; int index = 0, pid = *pos; int *iter, ret; mutex_lock(&cgrp->pidlist_mutex); /* * !NULL @ctx->procs1.pidlist indicates that this isn't the first * start() after open. If the matching pidlist is around, we can use * that. Look for it. Note that @ctx->procs1.pidlist can't be used * directly. It could already have been destroyed. */ if (ctx->procs1.pidlist) ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type); /* * Either this is the first start() after open or the matching * pidlist has been destroyed inbetween. Create a new one. */ if (!ctx->procs1.pidlist) { ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist); if (ret) return ERR_PTR(ret); } l = ctx->procs1.pidlist; if (pid) { int end = l->length; while (index < end) { int mid = (index + end) / 2; if (l->list[mid] == pid) { index = mid; break; } else if (l->list[mid] < pid) index = mid + 1; else end = mid; } } /* If we're off the end of the array, we're done */ if (index >= l->length) return NULL; /* Update the abstract position to be the actual pid that we found */ iter = l->list + index; *pos = *iter; return iter; } static void cgroup_pidlist_stop(struct seq_file *s, void *v) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup_pidlist *l = ctx->procs1.pidlist; if (l) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, CGROUP_PIDLIST_DESTROY_DELAY); mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); } static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup_pidlist *l = ctx->procs1.pidlist; pid_t *p = v; pid_t *end = l->list + l->length; /* * Advance to the next pid in the array. If this goes off the * end, we're done */ p++; if (p >= end) { (*pos)++; return NULL; } else { *pos = *p; return p; } } static int cgroup_pidlist_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", *(int *)v); return 0; } static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool threadgroup) { struct cgroup *cgrp; struct task_struct *task; const struct cred *cred, *tcred; ssize_t ret; enum cgroup_attach_lock_mode lock_mode; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup, &lock_mode); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; /* * Even if we're attaching all tasks in the thread group, we only need * to check permissions on one of them. Check permissions using the * credentials from file open to protect against inherited fd attacks. */ cred = of->file->f_cred; tcred = get_task_cred(task); if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && !uid_eq(cred->euid, tcred->suid)) ret = -EACCES; put_cred(tcred); if (ret) goto out_finish; ret = cgroup_attach_task(cgrp, task, threadgroup); out_finish: cgroup_procs_write_finish(task, lock_mode); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static ssize_t cgroup1_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup1_procs_write(of, buf, nbytes, off, true); } static ssize_t cgroup1_tasks_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup1_procs_write(of, buf, nbytes, off, false); } static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; struct cgroup_file_ctx *ctx; BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); /* * Release agent gets called with all capabilities, * require capabilities to set release agent. */ ctx = of->priv; if ((ctx->ns->user_ns != &init_user_ns) || !file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN)) return -EPERM; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; spin_lock(&release_agent_path_lock); strscpy(cgrp->root->release_agent_path, strstrip(buf), sizeof(cgrp->root->release_agent_path)); spin_unlock(&release_agent_path_lock); cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_release_agent_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; spin_lock(&release_agent_path_lock); seq_puts(seq, cgrp->root->release_agent_path); spin_unlock(&release_agent_path_lock); seq_putc(seq, '\n'); return 0; } static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) { seq_puts(seq, "0\n"); return 0; } static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft) { return notify_on_release(css->cgroup); } static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); else clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); return 0; } static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, struct cftype *cft) { return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); } static int cgroup_clone_children_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); else clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); return 0; } /* cgroup core interface files for the legacy hierarchies */ struct cftype cgroup1_base_files[] = { { .name = "cgroup.procs", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_PROCS, .write = cgroup1_procs_write, }, { .name = "cgroup.clone_children", .read_u64 = cgroup_clone_children_read, .write_u64 = cgroup_clone_children_write, }, { .name = "cgroup.sane_behavior", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_sane_behavior_show, }, { .name = "tasks", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_TASKS, .write = cgroup1_tasks_write, }, { .name = "notify_on_release", .read_u64 = cgroup_read_notify_on_release, .write_u64 = cgroup_write_notify_on_release, }, { .name = "release_agent", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_release_agent_show, .write = cgroup_release_agent_write, .max_write_len = PATH_MAX - 1, }, { } /* terminate */ }; /* Display information about each subsystem and each hierarchy */ int proc_cgroupstats_show(struct seq_file *m, void *v) { struct cgroup_subsys *ss; bool cgrp_v1_visible = false; int i; seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); /* * Grab the subsystems state racily. No need to add avenue to * cgroup_mutex contention. */ for_each_subsys(ss, i) { cgrp_v1_visible |= ss->root != &cgrp_dfl_root; if (!proc_show_all && cgroup1_subsys_absent(ss)) continue; seq_printf(m, "%s\t%d\t%d\t%d\n", ss->legacy_name, ss->root->hierarchy_id, atomic_read(&ss->root->nr_cgrps), cgroup_ssid_enabled(i)); } if (cgrp_dfl_visible && !cgrp_v1_visible) pr_info_once("/proc/cgroups lists only v1 controllers, use cgroup.controllers of root cgroup for v2 info\n"); return 0; } /** * cgroupstats_build - build and fill cgroupstats * @stats: cgroupstats to fill information into * @dentry: A dentry entry belonging to the cgroup for which stats have * been requested. * * Build and fill cgroupstats so that taskstats can export it to user * space. * * Return: %0 on success or a negative errno code on failure */ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct cgroup *cgrp; struct css_task_iter it; struct task_struct *tsk; /* it should be kernfs_node belonging to cgroupfs and is a directory */ if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || kernfs_type(kn) != KERNFS_DIR) return -EINVAL; /* * We aren't being called from kernfs and there's no guarantee on * @kn->priv's validity. For this and css_tryget_online_from_dir(), * @kn->priv is RCU safe. Let's do the RCU dancing. */ rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || !cgroup_tryget(cgrp)) { rcu_read_unlock(); return -ENOENT; } rcu_read_unlock(); css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { switch (READ_ONCE(tsk->__state)) { case TASK_RUNNING: stats->nr_running++; break; case TASK_INTERRUPTIBLE: stats->nr_sleeping++; break; case TASK_UNINTERRUPTIBLE: stats->nr_uninterruptible++; break; case TASK_STOPPED: stats->nr_stopped++; break; default: if (tsk->in_iowait) stats->nr_io_wait++; break; } } css_task_iter_end(&it); cgroup_put(cgrp); return 0; } void cgroup1_check_for_release(struct cgroup *cgrp) { if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) && !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) schedule_work(&cgrp->release_agent_work); } /* * Notify userspace when a cgroup is released, by running the * configured release agent with the name of the cgroup (path * relative to the root of cgroup file system) as the argument. * * Most likely, this user command will try to rmdir this cgroup. * * This races with the possibility that some other task will be * attached to this cgroup before it is removed, or that some other * user task will 'mkdir' a child cgroup of this cgroup. That's ok. * The presumed 'rmdir' will fail quietly if this cgroup is no longer * unused, and this cgroup will be reprieved from its death sentence, * to continue to serve a useful existence. Next time it's released, * we will get notified again, if it still has 'notify_on_release' set. * * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which * means only wait until the task is successfully execve()'d. The * separate release agent task is forked by call_usermodehelper(), * then control in this thread returns here, without waiting for the * release agent task. We don't bother to wait because the caller of * this routine has no use for the exit status of the release agent * task, so no sense holding our caller up for that. */ void cgroup1_release_agent(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, release_agent_work); char *pathbuf, *agentbuf; char *argv[3], *envp[3]; int ret; /* snoop agent path and exit early if empty */ if (!cgrp->root->release_agent_path[0]) return; /* prepare argument buffers */ pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); agentbuf = kmalloc(PATH_MAX, GFP_KERNEL); if (!pathbuf || !agentbuf) goto out_free; spin_lock(&release_agent_path_lock); strscpy(agentbuf, cgrp->root->release_agent_path, PATH_MAX); spin_unlock(&release_agent_path_lock); if (!agentbuf[0]) goto out_free; ret = cgroup_path_ns(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); if (ret < 0) goto out_free; argv[0] = agentbuf; argv[1] = pathbuf; argv[2] = NULL; /* minimal command environment */ envp[0] = "HOME=/"; envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; envp[2] = NULL; call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); out_free: kfree(agentbuf); kfree(pathbuf); } /* * cgroup_rename - Only allow simple rename of directories in place. */ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name_str) { struct cgroup *cgrp = kn->priv; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(new_name_str, '\n')) return -EINVAL; if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; if (rcu_access_pointer(kn->__parent) != new_parent) return -EIO; /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. kernfs_rename() doesn't require active_ref * protection. Break them before grabbing cgroup_mutex. */ kernfs_break_active_protection(new_parent); kernfs_break_active_protection(kn); cgroup_lock(); ret = kernfs_rename(kn, new_parent, new_name_str); if (!ret) TRACE_CGROUP_PATH(rename, cgrp); cgroup_unlock(); kernfs_unbreak_active_protection(kn); kernfs_unbreak_active_protection(new_parent); return ret; } static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { struct cgroup_root *root = cgroup_root_from_kf(kf_root); struct cgroup_subsys *ss; int ssid; for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_show_option(seq, ss->legacy_name, NULL); if (root->flags & CGRP_ROOT_NOPREFIX) seq_puts(seq, ",noprefix"); if (root->flags & CGRP_ROOT_XATTR) seq_puts(seq, ",xattr"); if (root->flags & CGRP_ROOT_CPUSET_V2_MODE) seq_puts(seq, ",cpuset_v2_mode"); if (root->flags & CGRP_ROOT_FAVOR_DYNMODS) seq_puts(seq, ",favordynmods"); spin_lock(&release_agent_path_lock); if (strlen(root->release_agent_path)) seq_show_option(seq, "release_agent", root->release_agent_path); spin_unlock(&release_agent_path_lock); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_show_option(seq, "name", root->name); return 0; } enum cgroup1_param { Opt_all, Opt_clone_children, Opt_cpuset_v2_mode, Opt_name, Opt_none, Opt_noprefix, Opt_release_agent, Opt_xattr, Opt_favordynmods, Opt_nofavordynmods, }; const struct fs_parameter_spec cgroup1_fs_parameters[] = { fsparam_flag ("all", Opt_all), fsparam_flag ("clone_children", Opt_clone_children), fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), fsparam_string("name", Opt_name), fsparam_flag ("none", Opt_none), fsparam_flag ("noprefix", Opt_noprefix), fsparam_string("release_agent", Opt_release_agent), fsparam_flag ("xattr", Opt_xattr), fsparam_flag ("favordynmods", Opt_favordynmods), fsparam_flag ("nofavordynmods", Opt_nofavordynmods), {} }; int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_subsys *ss; struct fs_parse_result result; int opt, i; opt = fs_parse(fc, cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { int ret; ret = vfs_parse_fs_param_source(fc, param); if (ret != -ENOPARAM) return ret; for_each_subsys(ss, i) { if (strcmp(param->key, ss->legacy_name) || cgroup1_subsys_absent(ss)) continue; if (!cgroup_ssid_enabled(i) || cgroup1_ssid_disabled(i)) return invalfc(fc, "Disabled controller '%s'", param->key); ctx->subsys_mask |= (1 << i); return 0; } return invalfc(fc, "Unknown subsys name '%s'", param->key); } if (opt < 0) return opt; switch (opt) { case Opt_none: /* Explicitly have no subsystems */ ctx->none = true; break; case Opt_all: ctx->all_ss = true; break; case Opt_noprefix: ctx->flags |= CGRP_ROOT_NOPREFIX; break; case Opt_clone_children: ctx->cpuset_clone_children = true; break; case Opt_cpuset_v2_mode: ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; break; case Opt_xattr: ctx->flags |= CGRP_ROOT_XATTR; break; case Opt_favordynmods: ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; break; case Opt_nofavordynmods: ctx->flags &= ~CGRP_ROOT_FAVOR_DYNMODS; break; case Opt_release_agent: /* Specifying two release agents is forbidden */ if (ctx->release_agent) return invalfc(fc, "release_agent respecified"); /* * Release agent gets called with all capabilities, * require capabilities to set release agent. */ if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) return invalfc(fc, "Setting release_agent not allowed"); ctx->release_agent = param->string; param->string = NULL; break; case Opt_name: /* blocked by boot param? */ if (cgroup_no_v1_named) return -ENOENT; /* Can't specify an empty name */ if (!param->size) return invalfc(fc, "Empty name"); if (param->size > MAX_CGROUP_ROOT_NAMELEN - 1) return invalfc(fc, "Name too long"); /* Must match [\w.-]+ */ for (i = 0; i < param->size; i++) { char c = param->string[i]; if (isalnum(c)) continue; if ((c == '.') || (c == '-') || (c == '_')) continue; return invalfc(fc, "Invalid name"); } /* Specifying two names is forbidden */ if (ctx->name) return invalfc(fc, "name respecified"); ctx->name = param->string; param->string = NULL; break; } return 0; } static int check_cgroupfs_options(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); u32 mask = U32_MAX; u32 enabled = 0; struct cgroup_subsys *ss; int i; #ifdef CONFIG_CPUSETS mask = ~((u32)1 << cpuset_cgrp_id); #endif for_each_subsys(ss, i) if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i) && !cgroup1_subsys_absent(ss)) enabled |= 1 << i; ctx->subsys_mask &= enabled; /* * In absence of 'none', 'name=' and subsystem name options, * let's default to 'all'. */ if (!ctx->subsys_mask && !ctx->none && !ctx->name) ctx->all_ss = true; if (ctx->all_ss) { /* Mutually exclusive option 'all' + subsystem name */ if (ctx->subsys_mask) return invalfc(fc, "subsys name conflicts with all"); /* 'all' => select all the subsystems */ ctx->subsys_mask = enabled; } /* * We either have to specify by name or by subsystems. (So all * empty hierarchies must have a name). */ if (!ctx->subsys_mask && !ctx->name) return invalfc(fc, "Need name or subsystem set"); /* * Option noprefix was introduced just for backward compatibility * with the old cpuset, so we allow noprefix only if mounting just * the cpuset subsystem. */ if ((ctx->flags & CGRP_ROOT_NOPREFIX) && (ctx->subsys_mask & mask)) return invalfc(fc, "noprefix used incorrectly"); /* Can't specify "none" and some subsystems */ if (ctx->subsys_mask && ctx->none) return invalfc(fc, "none used incorrectly"); return 0; } int cgroup1_reconfigure(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct kernfs_root *kf_root = kernfs_root_from_sb(fc->root->d_sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); int ret = 0; u32 added_mask, removed_mask; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); /* See what subsystems are wanted */ ret = check_cgroupfs_options(fc); if (ret) goto out_unlock; if (ctx->subsys_mask != root->subsys_mask || ctx->release_agent) pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); added_mask = ctx->subsys_mask & ~root->subsys_mask; removed_mask = root->subsys_mask & ~ctx->subsys_mask; /* Don't allow flags or name to change at remount */ if ((ctx->flags ^ root->flags) || (ctx->name && strcmp(ctx->name, root->name))) { errorfc(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"", ctx->flags, ctx->name ?: "", root->flags, root->name); ret = -EINVAL; goto out_unlock; } /* remounting is not allowed for populated hierarchies */ if (!list_empty(&root->cgrp.self.children)) { ret = -EBUSY; goto out_unlock; } ret = rebind_subsystems(root, added_mask); if (ret) goto out_unlock; WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); if (ctx->release_agent) { spin_lock(&release_agent_path_lock); strscpy(root->release_agent_path, ctx->release_agent); spin_unlock(&release_agent_path_lock); } trace_cgroup_remount(root); out_unlock: cgroup_unlock(); return ret; } struct kernfs_syscall_ops cgroup1_kf_syscall_ops = { .rename = cgroup1_rename, .show_options = cgroup1_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; /* * The guts of cgroup1 mount - find or create cgroup_root to use. * Called with cgroup_mutex held; returns 0 on success, -E... on * error and positive - in case when the candidate is busy dying. * On success it stashes a reference to cgroup_root into given * cgroup_fs_context; that reference is *NOT* counting towards the * cgroup_root refcount. */ static int cgroup1_root_to_use(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_root *root; struct cgroup_subsys *ss; int i, ret; /* First find the desired set of subsystems */ ret = check_cgroupfs_options(fc); if (ret) return ret; /* * Destruction of cgroup root is asynchronous, so subsystems may * still be dying after the previous unmount. Let's drain the * dying subsystems. We just need to ensure that the ones * unmounted previously finish dying and don't care about new ones * starting. Testing ref liveliness is good enough. */ for_each_subsys(ss, i) { if (!(ctx->subsys_mask & (1 << i)) || ss->root == &cgrp_dfl_root) continue; if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) return 1; /* restart */ cgroup_put(&ss->root->cgrp); } for_each_root(root) { bool name_match = false; if (root == &cgrp_dfl_root) continue; /* * If we asked for a name then it must match. Also, if * name matches but sybsys_mask doesn't, we should fail. * Remember whether name matched. */ if (ctx->name) { if (strcmp(ctx->name, root->name)) continue; name_match = true; } /* * If we asked for subsystems (or explicitly for no * subsystems) then they must match. */ if ((ctx->subsys_mask || ctx->none) && (ctx->subsys_mask != root->subsys_mask)) { if (!name_match) continue; return -EBUSY; } if (root->flags ^ ctx->flags) pr_warn("new mount options do not match the existing superblock, will be ignored\n"); ctx->root = root; return 0; } /* * No such thing, create a new one. name= matching without subsys * specification is allowed for already existing hierarchies but we * can't create new one without subsys specification. */ if (!ctx->subsys_mask && !ctx->none) return invalfc(fc, "No subsys list or none specified"); /* Hierarchies may only be created in the initial cgroup namespace. */ if (ctx->ns != &init_cgroup_ns) return -EPERM; root = kzalloc_obj(*root); if (!root) return -ENOMEM; ctx->root = root; init_cgroup_root(ctx); ret = cgroup_setup_root(root, ctx->subsys_mask); if (!ret) cgroup_favor_dynmods(root, ctx->flags & CGRP_ROOT_FAVOR_DYNMODS); else cgroup_free_root(root); return ret; } int cgroup1_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; /* Check if the caller has permission to mount. */ if (!ns_capable(ctx->ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); ret = cgroup1_root_to_use(fc); if (!ret && !percpu_ref_tryget_live(&ctx->root->cgrp.self.refcnt)) ret = 1; /* restart */ cgroup_unlock(); if (!ret) ret = cgroup_do_get_tree(fc); if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { fc_drop_locked(fc); ret = 1; } if (unlikely(ret > 0)) { msleep(10); return restart_syscall(); } return ret; } /** * task_get_cgroup1 - Acquires the associated cgroup of a task within a * specific cgroup1 hierarchy. The cgroup1 hierarchy is identified by its * hierarchy ID. * @tsk: The target task * @hierarchy_id: The ID of a cgroup1 hierarchy * * On success, the cgroup is returned. On failure, ERR_PTR is returned. * We limit it to cgroup1 only. */ struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id) { struct cgroup *cgrp = ERR_PTR(-ENOENT); struct cgroup_root *root; unsigned long flags; rcu_read_lock(); for_each_root(root) { /* cgroup1 only*/ if (root == &cgrp_dfl_root) continue; if (root->hierarchy_id != hierarchy_id) continue; spin_lock_irqsave(&css_set_lock, flags); cgrp = task_cgroup_from_root(tsk, root); if (!cgrp || !cgroup_tryget(cgrp)) cgrp = ERR_PTR(-ENOENT); spin_unlock_irqrestore(&css_set_lock, flags); break; } rcu_read_unlock(); return cgrp; } static int __init cgroup1_wq_init(void) { /* * Used to destroy pidlists and separate to serve as flush domain. * Cap @max_active to 1 too. */ cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy", WQ_PERCPU, 1); BUG_ON(!cgroup_pidlist_destroy_wq); return 0; } core_initcall(cgroup1_wq_init); static int __init cgroup_no_v1(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; if (!strcmp(token, "all")) { cgroup_no_v1_mask = U32_MAX; continue; } if (!strcmp(token, "named")) { cgroup_no_v1_named = true; continue; } for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; cgroup_no_v1_mask |= 1 << i; break; } } return 1; } __setup("cgroup_no_v1=", cgroup_no_v1); static int __init cgroup_v1_proc(char *str) { return (kstrtobool(str, &proc_show_all) == 0); } __setup("cgroup_v1_proc=", cgroup_v1_proc); |
| 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic hugetlb support. * (C) Nadia Yvette Chambers, April 2004 */ #include <linux/list.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/seq_file.h> #include <linux/highmem.h> #include <linux/mmu_notifier.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <linux/mempolicy.h> #include <linux/compiler.h> #include <linux/cpumask.h> #include <linux/cpuset.h> #include <linux/mutex.h> #include <linux/memblock.h> #include <linux/minmax.h> #include <linux/slab.h> #include <linux/sched/mm.h> #include <linux/mmdebug.h> #include <linux/sched/signal.h> #include <linux/rmap.h> #include <linux/string_choices.h> #include <linux/string_helpers.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/jhash.h> #include <linux/numa.h> #include <linux/llist.h> #include <linux/cma.h> #include <linux/migrate.h> #include <linux/nospec.h> #include <linux/delayacct.h> #include <linux/memory.h> #include <linux/mm_inline.h> #include <linux/padata.h> #include <linux/pgalloc.h> #include <asm/page.h> #include <asm/tlb.h> #include <asm/setup.h> #include <linux/io.h> #include <linux/node.h> #include <linux/page_owner.h> #include "internal.h" #include "hugetlb_vmemmap.h" #include "hugetlb_cma.h" #include "hugetlb_internal.h" #include <linux/page-isolation.h> int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; struct hstate hstates[HUGE_MAX_HSTATE]; __initdata nodemask_t hugetlb_bootmem_nodes; __initdata struct list_head huge_boot_pages[MAX_NUMNODES]; static unsigned long hstate_boot_nrinvalid[HUGE_MAX_HSTATE] __initdata; /* * Due to ordering constraints across the init code for various * architectures, hugetlb hstate cmdline parameters can't simply * be early_param. early_param might call the setup function * before valid hugetlb page sizes are determined, leading to * incorrect rejection of valid hugepagesz= options. * * So, record the parameters early and consume them whenever the * init code is ready for them, by calling hugetlb_parse_params(). */ /* one (hugepagesz=,hugepages=) pair per hstate, one default_hugepagesz */ #define HUGE_MAX_CMDLINE_ARGS (2 * HUGE_MAX_HSTATE + 1) struct hugetlb_cmdline { char *val; int (*setup)(char *val); }; /* for command line parsing */ static struct hstate * __initdata parsed_hstate; static unsigned long __initdata default_hstate_max_huge_pages; static bool __initdata parsed_valid_hugepagesz = true; static bool __initdata parsed_default_hugepagesz; static unsigned int default_hugepages_in_node[MAX_NUMNODES] __initdata; static unsigned long hugepage_allocation_threads __initdata; static char hstate_cmdline_buf[COMMAND_LINE_SIZE] __initdata; static int hstate_cmdline_index __initdata; static struct hugetlb_cmdline hugetlb_params[HUGE_MAX_CMDLINE_ARGS] __initdata; static int hugetlb_param_index __initdata; static __init int hugetlb_add_param(char *s, int (*setup)(char *val)); static __init void hugetlb_parse_params(void); #define hugetlb_early_param(str, func) \ static __init int func##args(char *s) \ { \ return hugetlb_add_param(s, func); \ } \ early_param(str, func##args) /* * Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages, * free_huge_pages, and surplus_huge_pages. */ __cacheline_aligned_in_smp DEFINE_SPINLOCK(hugetlb_lock); /* * Serializes faults on the same logical page. This is used to * prevent spurious OOMs when the hugepage pool is fully utilized. */ static int num_fault_mutexes __ro_after_init; struct mutex *hugetlb_fault_mutex_table __ro_after_init; /* Forward declaration */ static int hugetlb_acct_memory(struct hstate *h, long delta); static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool take_locks); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static inline bool subpool_is_free(struct hugepage_subpool *spool) { if (spool->count) return false; if (spool->max_hpages != -1) return spool->used_hpages == 0; if (spool->min_hpages != -1) return spool->rsv_hpages == spool->min_hpages; return true; } static inline void unlock_or_release_subpool(struct hugepage_subpool *spool, unsigned long irq_flags) { spin_unlock_irqrestore(&spool->lock, irq_flags); /* If no pages are used, and no other handles to the subpool * remain, give up any reservations based on minimum size and * free the subpool */ if (subpool_is_free(spool)) { if (spool->min_hpages != -1) hugetlb_acct_memory(spool->hstate, -spool->min_hpages); kfree(spool); } } struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages) { struct hugepage_subpool *spool; spool = kzalloc_obj(*spool); if (!spool) return NULL; spin_lock_init(&spool->lock); spool->count = 1; spool->max_hpages = max_hpages; spool->hstate = h; spool->min_hpages = min_hpages; if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) { kfree(spool); return NULL; } spool->rsv_hpages = min_hpages; return spool; } void hugepage_put_subpool(struct hugepage_subpool *spool) { unsigned long flags; spin_lock_irqsave(&spool->lock, flags); BUG_ON(!spool->count); spool->count--; unlock_or_release_subpool(spool, flags); } /* * Subpool accounting for allocating and reserving pages. * Return -ENOMEM if there are not enough resources to satisfy the * request. Otherwise, return the number of pages by which the * global pools must be adjusted (upward). The returned value may * only be different than the passed value (delta) in the case where * a subpool minimum size must be maintained. */ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; if (!spool) return ret; spin_lock_irq(&spool->lock); if (spool->max_hpages != -1) { /* maximum size accounting */ if ((spool->used_hpages + delta) <= spool->max_hpages) spool->used_hpages += delta; else { ret = -ENOMEM; goto unlock_ret; } } /* minimum size accounting */ if (spool->min_hpages != -1 && spool->rsv_hpages) { if (delta > spool->rsv_hpages) { /* * Asking for more reserves than those already taken on * behalf of subpool. Return difference. */ ret = delta - spool->rsv_hpages; spool->rsv_hpages = 0; } else { ret = 0; /* reserves already accounted for */ spool->rsv_hpages -= delta; } } unlock_ret: spin_unlock_irq(&spool->lock); return ret; } /* * Subpool accounting for freeing and unreserving pages. * Return the number of global page reservations that must be dropped. * The return value may only be different than the passed value (delta) * in the case where a subpool minimum size must be maintained. */ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool, long delta) { long ret = delta; unsigned long flags; if (!spool) return delta; spin_lock_irqsave(&spool->lock, flags); if (spool->max_hpages != -1) /* maximum size accounting */ spool->used_hpages -= delta; /* minimum size accounting */ if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) { if (spool->rsv_hpages + delta <= spool->min_hpages) ret = 0; else ret = spool->rsv_hpages + delta - spool->min_hpages; spool->rsv_hpages += delta; if (spool->rsv_hpages > spool->min_hpages) spool->rsv_hpages = spool->min_hpages; } /* * If hugetlbfs_put_super couldn't free spool due to an outstanding * quota reference, free it now. */ unlock_or_release_subpool(spool, flags); return ret; } static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) { return subpool_inode(file_inode(vma->vm_file)); } /* * hugetlb vma_lock helper routines */ void hugetlb_vma_lock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_read(&resv_map->rw_sema); } } void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_read(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_read(&resv_map->rw_sema); } } void hugetlb_vma_lock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); down_write(&resv_map->rw_sema); } } void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_write(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); up_write(&resv_map->rw_sema); } } int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; return down_write_trylock(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); return down_write_trylock(&resv_map->rw_sema); } return 1; } void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; lockdep_assert_held(&vma_lock->rw_sema); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); lockdep_assert_held(&resv_map->rw_sema); } } void hugetlb_vma_lock_release(struct kref *kref) { struct hugetlb_vma_lock *vma_lock = container_of(kref, struct hugetlb_vma_lock, refs); kfree(vma_lock); } static void __hugetlb_vma_unlock_write_put(struct hugetlb_vma_lock *vma_lock) { struct vm_area_struct *vma = vma_lock->vma; /* * vma_lock structure may or not be released as a result of put, * it certainly will no longer be attached to vma so clear pointer. * Semaphore synchronizes access to vma_lock->vma field. */ vma_lock->vma = NULL; vma->vm_private_data = NULL; up_write(&vma_lock->rw_sema); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); } static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) { if (__vma_shareable_lock(vma)) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; __hugetlb_vma_unlock_write_put(vma_lock); } else if (__vma_private_lock(vma)) { struct resv_map *resv_map = vma_resv_map(vma); /* no free for anon vmas, but still need to unlock */ up_write(&resv_map->rw_sema); } } static void hugetlb_vma_lock_free(struct vm_area_struct *vma) { /* * Only present in sharable vmas. */ if (!vma || !__vma_shareable_lock(vma)) return; if (vma->vm_private_data) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); __hugetlb_vma_unlock_write_put(vma_lock); } } /* * vma specific semaphore used for pmd sharing and fault/truncation * synchronization */ int hugetlb_vma_lock_alloc(struct vm_area_struct *vma) { struct hugetlb_vma_lock *vma_lock; /* Only establish in (flags) sharable vmas */ if (!vma || !(vma->vm_flags & VM_MAYSHARE)) return 0; /* Should never get here with non-NULL vm_private_data */ if (vma->vm_private_data) return -EINVAL; vma_lock = kmalloc_obj(*vma_lock); if (!vma_lock) { /* * If we can not allocate structure, then vma can not * participate in pmd sharing. This is only a possible * performance enhancement and memory saving issue. * However, the lock is also used to synchronize page * faults with truncation. If the lock is not present, * unlikely races could leave pages in a file past i_size * until the file is removed. Warn in the unlikely case of * allocation failure. */ pr_warn_once("HugeTLB: unable to allocate vma specific lock\n"); return -EINVAL; } kref_init(&vma_lock->refs); init_rwsem(&vma_lock->rw_sema); vma_lock->vma = vma; vma->vm_private_data = vma_lock; return 0; } /* Helper that removes a struct file_region from the resv_map cache and returns * it for use. */ static struct file_region * get_file_region_entry_from_cache(struct resv_map *resv, long from, long to) { struct file_region *nrg; VM_BUG_ON(resv->region_cache_count <= 0); resv->region_cache_count--; nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); nrg->from = from; nrg->to = to; return nrg; } static void copy_hugetlb_cgroup_uncharge_info(struct file_region *nrg, struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB nrg->reservation_counter = rg->reservation_counter; nrg->css = rg->css; if (rg->css) css_get(rg->css); #endif } /* Helper that records hugetlb_cgroup uncharge info. */ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg, struct hstate *h, struct resv_map *resv, struct file_region *nrg) { #ifdef CONFIG_CGROUP_HUGETLB if (h_cg) { nrg->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; nrg->css = &h_cg->css; /* * The caller will hold exactly one h_cg->css reference for the * whole contiguous reservation region. But this area might be * scattered when there are already some file_regions reside in * it. As a result, many file_regions may share only one css * reference. In order to ensure that one file_region must hold * exactly one h_cg->css reference, we should do css_get for * each file_region and leave the reference held by caller * untouched. */ css_get(&h_cg->css); if (!resv->pages_per_hpage) resv->pages_per_hpage = pages_per_huge_page(h); /* pages_per_hpage should be the same for all entries in * a resv_map. */ VM_BUG_ON(resv->pages_per_hpage != pages_per_huge_page(h)); } else { nrg->reservation_counter = NULL; nrg->css = NULL; } #endif } static void put_uncharge_info(struct file_region *rg) { #ifdef CONFIG_CGROUP_HUGETLB if (rg->css) css_put(rg->css); #endif } static bool has_same_uncharge_info(struct file_region *rg, struct file_region *org) { #ifdef CONFIG_CGROUP_HUGETLB return rg->reservation_counter == org->reservation_counter && rg->css == org->css; #else return true; #endif } static void coalesce_file_region(struct resv_map *resv, struct file_region *rg) { struct file_region *nrg, *prg; prg = list_prev_entry(rg, link); if (&prg->link != &resv->regions && prg->to == rg->from && has_same_uncharge_info(prg, rg)) { prg->to = rg->to; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); rg = prg; } nrg = list_next_entry(rg, link); if (&nrg->link != &resv->regions && nrg->from == rg->to && has_same_uncharge_info(nrg, rg)) { nrg->from = rg->from; list_del(&rg->link); put_uncharge_info(rg); kfree(rg); } } static inline long hugetlb_resv_map_add(struct resv_map *map, struct list_head *rg, long from, long to, struct hstate *h, struct hugetlb_cgroup *cg, long *regions_needed) { struct file_region *nrg; if (!regions_needed) { nrg = get_file_region_entry_from_cache(map, from, to); record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg); list_add(&nrg->link, rg); coalesce_file_region(map, nrg); } else { *regions_needed += 1; } return to - from; } /* * Must be called with resv->lock held. * * Calling this with regions_needed != NULL will count the number of pages * to be added but will not modify the linked list. And regions_needed will * indicate the number of file_regions needed in the cache to carry out to add * the regions for this range. */ static long add_reservation_in_range(struct resv_map *resv, long f, long t, struct hugetlb_cgroup *h_cg, struct hstate *h, long *regions_needed) { long add = 0; struct list_head *head = &resv->regions; long last_accounted_offset = f; struct file_region *iter, *trg = NULL; struct list_head *rg = NULL; if (regions_needed) *regions_needed = 0; /* In this loop, we essentially handle an entry for the range * [last_accounted_offset, iter->from), at every iteration, with some * bounds checking. */ list_for_each_entry_safe(iter, trg, head, link) { /* Skip irrelevant regions that start before our range. */ if (iter->from < f) { /* If this region ends after the last accounted offset, * then we need to update last_accounted_offset. */ if (iter->to > last_accounted_offset) last_accounted_offset = iter->to; continue; } /* When we find a region that starts beyond our range, we've * finished. */ if (iter->from >= t) { rg = iter->link.prev; break; } /* Add an entry for last_accounted_offset -> iter->from, and * update last_accounted_offset. */ if (iter->from > last_accounted_offset) add += hugetlb_resv_map_add(resv, iter->link.prev, last_accounted_offset, iter->from, h, h_cg, regions_needed); last_accounted_offset = iter->to; } /* Handle the case where our range extends beyond * last_accounted_offset. */ if (!rg) rg = head->prev; if (last_accounted_offset < t) add += hugetlb_resv_map_add(resv, rg, last_accounted_offset, t, h, h_cg, regions_needed); return add; } /* Must be called with resv->lock acquired. Will drop lock to allocate entries. */ static int allocate_file_region_entries(struct resv_map *resv, int regions_needed) __must_hold(&resv->lock) { LIST_HEAD(allocated_regions); int to_allocate = 0, i = 0; struct file_region *trg = NULL, *rg = NULL; VM_BUG_ON(regions_needed < 0); /* * Check for sufficient descriptors in the cache to accommodate * the number of in progress add operations plus regions_needed. * * This is a while loop because when we drop the lock, some other call * to region_add or region_del may have consumed some region_entries, * so we keep looping here until we finally have enough entries for * (adds_in_progress + regions_needed). */ while (resv->region_cache_count < (resv->adds_in_progress + regions_needed)) { to_allocate = resv->adds_in_progress + regions_needed - resv->region_cache_count; /* At this point, we should have enough entries in the cache * for all the existing adds_in_progress. We should only be * needing to allocate for regions_needed. */ VM_BUG_ON(resv->region_cache_count < resv->adds_in_progress); spin_unlock(&resv->lock); for (i = 0; i < to_allocate; i++) { trg = kmalloc_obj(*trg); if (!trg) goto out_of_memory; list_add(&trg->link, &allocated_regions); } spin_lock(&resv->lock); list_splice(&allocated_regions, &resv->region_cache); resv->region_cache_count += to_allocate; } return 0; out_of_memory: list_for_each_entry_safe(rg, trg, &allocated_regions, link) { list_del(&rg->link); kfree(rg); } return -ENOMEM; } /* * Add the huge page range represented by [f, t) to the reserve * map. Regions will be taken from the cache to fill in this range. * Sufficient regions should exist in the cache due to the previous * call to region_chg with the same range, but in some cases the cache will not * have sufficient entries due to races with other code doing region_add or * region_del. The extra needed entries will be allocated. * * regions_needed is the out value provided by a previous call to region_chg. * * Return the number of new huge pages added to the map. This number is greater * than or equal to zero. If file_region entries needed to be allocated for * this operation and we were not able to allocate, it returns -ENOMEM. * region_add of regions of length 1 never allocate file_regions and cannot * fail; region_chg will always allocate at least 1 entry and a region_add for * 1 page will only require at most 1 entry. */ static long region_add(struct resv_map *resv, long f, long t, long in_regions_needed, struct hstate *h, struct hugetlb_cgroup *h_cg) { long add = 0, actual_regions_needed = 0; spin_lock(&resv->lock); retry: /* Count how many regions are actually needed to execute this add. */ add_reservation_in_range(resv, f, t, NULL, NULL, &actual_regions_needed); /* * Check for sufficient descriptors in the cache to accommodate * this add operation. Note that actual_regions_needed may be greater * than in_regions_needed, as the resv_map may have been modified since * the region_chg call. In this case, we need to make sure that we * allocate extra entries, such that we have enough for all the * existing adds_in_progress, plus the excess needed for this * operation. */ if (actual_regions_needed > in_regions_needed && resv->region_cache_count < resv->adds_in_progress + (actual_regions_needed - in_regions_needed)) { /* region_add operation of range 1 should never need to * allocate file_region entries. */ VM_BUG_ON(t - f <= 1); if (allocate_file_region_entries( resv, actual_regions_needed - in_regions_needed)) { return -ENOMEM; } goto retry; } add = add_reservation_in_range(resv, f, t, h_cg, h, NULL); resv->adds_in_progress -= in_regions_needed; spin_unlock(&resv->lock); return add; } /* * Examine the existing reserve map and determine how many * huge pages in the specified range [f, t) are NOT currently * represented. This routine is called before a subsequent * call to region_add that will actually modify the reserve * map to add the specified range [f, t). region_chg does * not change the number of huge pages represented by the * map. A number of new file_region structures is added to the cache as a * placeholder, for the subsequent region_add call to use. At least 1 * file_region structure is added. * * out_regions_needed is the number of regions added to the * resv->adds_in_progress. This value needs to be provided to a follow up call * to region_add or region_abort for proper accounting. * * Returns the number of huge pages that need to be added to the existing * reservation map for the range [f, t). This number is greater or equal to * zero. -ENOMEM is returned if a new file_region structure or cache entry * is needed and can not be allocated. */ static long region_chg(struct resv_map *resv, long f, long t, long *out_regions_needed) { long chg = 0; spin_lock(&resv->lock); /* Count how many hugepages in this range are NOT represented. */ chg = add_reservation_in_range(resv, f, t, NULL, NULL, out_regions_needed); if (*out_regions_needed == 0) *out_regions_needed = 1; if (allocate_file_region_entries(resv, *out_regions_needed)) return -ENOMEM; resv->adds_in_progress += *out_regions_needed; spin_unlock(&resv->lock); return chg; } /* * Abort the in progress add operation. The adds_in_progress field * of the resv_map keeps track of the operations in progress between * calls to region_chg and region_add. Operations are sometimes * aborted after the call to region_chg. In such cases, region_abort * is called to decrement the adds_in_progress counter. regions_needed * is the value returned by the region_chg call, it is used to decrement * the adds_in_progress counter. * * NOTE: The range arguments [f, t) are not needed or used in this * routine. They are kept to make reading the calling code easier as * arguments will match the associated region_chg call. */ static void region_abort(struct resv_map *resv, long f, long t, long regions_needed) { spin_lock(&resv->lock); VM_BUG_ON(!resv->region_cache_count); resv->adds_in_progress -= regions_needed; spin_unlock(&resv->lock); } /* * Delete the specified range [f, t) from the reserve map. If the * t parameter is LONG_MAX, this indicates that ALL regions after f * should be deleted. Locate the regions which intersect [f, t) * and either trim, delete or split the existing regions. * * Returns the number of huge pages deleted from the reserve map. * In the normal case, the return value is zero or more. In the * case where a region must be split, a new region descriptor must * be allocated. If the allocation fails, -ENOMEM will be returned. * NOTE: If the parameter t == LONG_MAX, then we will never split * a region and possibly return -ENOMEM. Callers specifying * t == LONG_MAX do not need to check for -ENOMEM error. */ static long region_del(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg, *trg; struct file_region *nrg = NULL; long del = 0; retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { /* * Skip regions before the range to be deleted. file_region * ranges are normally of the form [from, to). However, there * may be a "placeholder" entry in the map which is of the form * (from, to) with from == to. Check for placeholder entries * at the beginning of the range to be deleted. */ if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; if (rg->from >= t) break; if (f > rg->from && t < rg->to) { /* Must split region */ /* * Check for an entry in the cache before dropping * lock and attempting allocation. */ if (!nrg && resv->region_cache_count > resv->adds_in_progress) { nrg = list_first_entry(&resv->region_cache, struct file_region, link); list_del(&nrg->link); resv->region_cache_count--; } if (!nrg) { spin_unlock(&resv->lock); nrg = kmalloc_obj(*nrg); if (!nrg) return -ENOMEM; goto retry; } del += t - f; hugetlb_cgroup_uncharge_file_region( resv, rg, t - f, false); /* New entry for end of split region */ nrg->from = t; nrg->to = rg->to; copy_hugetlb_cgroup_uncharge_info(nrg, rg); INIT_LIST_HEAD(&nrg->link); /* Original entry is trimmed */ rg->to = f; list_add(&nrg->link, &rg->link); nrg = NULL; break; } if (f <= rg->from && t >= rg->to) { /* Remove entire region */ del += rg->to - rg->from; hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - rg->from, true); list_del(&rg->link); kfree(rg); continue; } if (f <= rg->from) { /* Trim beginning of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, t - rg->from, false); del += t - rg->from; rg->from = t; } else { /* Trim end of region */ hugetlb_cgroup_uncharge_file_region(resv, rg, rg->to - f, false); del += rg->to - f; rg->to = f; } } spin_unlock(&resv->lock); kfree(nrg); return del; } /* * A rare out of memory error was encountered which prevented removal of * the reserve map region for a page. The huge page itself was free'ed * and removed from the page cache. This routine will adjust the subpool * usage count, and the global reserve count if needed. By incrementing * these counts, the reserve map entry which could not be deleted will * appear as a "reserved" entry instead of simply dangling with incorrect * counts. */ void hugetlb_fix_reserve_counts(struct inode *inode) { struct hugepage_subpool *spool = subpool_inode(inode); long rsv_adjust; bool reserved = false; rsv_adjust = hugepage_subpool_get_pages(spool, 1); if (rsv_adjust > 0) { struct hstate *h = hstate_inode(inode); if (!hugetlb_acct_memory(h, 1)) reserved = true; } else if (!rsv_adjust) { reserved = true; } if (!reserved) pr_warn("hugetlb: Huge Page Reserved count may go negative.\n"); } /* * Count and return the number of huge pages in the reserve map * that intersect with the range [f, t). */ static long region_count(struct resv_map *resv, long f, long t) { struct list_head *head = &resv->regions; struct file_region *rg; long chg = 0; spin_lock(&resv->lock); /* Locate each segment we overlap with, and count that overlap. */ list_for_each_entry(rg, head, link) { long seg_from; long seg_to; if (rg->to <= f) continue; if (rg->from >= t) break; seg_from = max(rg->from, f); seg_to = min(rg->to, t); chg += seg_to - seg_from; } spin_unlock(&resv->lock); return chg; } /* * Convert the address within this vma to the page offset within * the mapping, huge page units here. */ static pgoff_t vma_hugecache_offset(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return ((address - vma->vm_start) >> huge_page_shift(h)) + (vma->vm_pgoff >> huge_page_order(h)); } /* * Flags for MAP_PRIVATE reservations. These are stored in the bottom * bits of the reservation map pointer, which are always clear due to * alignment. */ #define HPAGE_RESV_OWNER (1UL << 0) #define HPAGE_RESV_UNMAPPED (1UL << 1) #define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED) /* * These helpers are used to track how many pages are reserved for * faults in a MAP_PRIVATE mapping. Only the process that called mmap() * is guaranteed to have their future faults succeed. * * With the exception of hugetlb_dup_vma_private() which is called at fork(), * the reserve counters are updated with the hugetlb_lock held. It is safe * to reset the VMA at fork() time as it is not in use yet and there is no * chance of the global counters getting corrupted as a result of the values. * * The private mapping reservation is represented in a subtly different * manner to a shared mapping. A shared mapping has a region map associated * with the underlying file, this region map represents the backing file * pages which have ever had a reservation assigned which this persists even * after the page is instantiated. A private mapping has a region map * associated with the original mmap which is attached to all VMAs which * reference it, this region map represents those offsets which have consumed * reservation ie. where pages have been instantiated. */ static unsigned long get_vma_private_data(struct vm_area_struct *vma) { return (unsigned long)vma->vm_private_data; } static void set_vma_private_data(struct vm_area_struct *vma, unsigned long value) { vma->vm_private_data = (void *)value; } static void resv_map_set_hugetlb_cgroup_uncharge_info(struct resv_map *resv_map, struct hugetlb_cgroup *h_cg, struct hstate *h) { #ifdef CONFIG_CGROUP_HUGETLB if (!h_cg || !h) { resv_map->reservation_counter = NULL; resv_map->pages_per_hpage = 0; resv_map->css = NULL; } else { resv_map->reservation_counter = &h_cg->rsvd_hugepage[hstate_index(h)]; resv_map->pages_per_hpage = pages_per_huge_page(h); resv_map->css = &h_cg->css; } #endif } struct resv_map *resv_map_alloc(void) { struct resv_map *resv_map = kmalloc_obj(*resv_map); struct file_region *rg = kmalloc_obj(*rg); if (!resv_map || !rg) { kfree(resv_map); kfree(rg); return NULL; } kref_init(&resv_map->refs); spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); init_rwsem(&resv_map->rw_sema); resv_map->adds_in_progress = 0; /* * Initialize these to 0. On shared mappings, 0's here indicate these * fields don't do cgroup accounting. On private mappings, these will be * re-initialized to the proper values, to indicate that hugetlb cgroup * reservations are to be un-charged from here. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, NULL, NULL); INIT_LIST_HEAD(&resv_map->region_cache); list_add(&rg->link, &resv_map->region_cache); resv_map->region_cache_count = 1; return resv_map; } void resv_map_release(struct kref *ref) { struct resv_map *resv_map = container_of(ref, struct resv_map, refs); struct list_head *head = &resv_map->region_cache; struct file_region *rg, *trg; /* Clear out any active regions before we release the map. */ region_del(resv_map, 0, LONG_MAX); /* ... and any entries left in the cache */ list_for_each_entry_safe(rg, trg, head, link) { list_del(&rg->link); kfree(rg); } VM_BUG_ON(resv_map->adds_in_progress); kfree(resv_map); } static inline struct resv_map *inode_resv_map(struct inode *inode) { return HUGETLBFS_I(inode)->resv_map; } static struct resv_map *vma_resv_map(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); if (vma->vm_flags & VM_MAYSHARE) { struct address_space *mapping = vma->vm_file->f_mapping; struct inode *inode = mapping->host; return inode_resv_map(inode); } else { return (struct resv_map *)(get_vma_private_data(vma) & ~HPAGE_RESV_MASK); } } static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) { VM_WARN_ON_ONCE_VMA(!is_vm_hugetlb_page(vma), vma); VM_WARN_ON_ONCE_VMA(vma->vm_flags & VM_MAYSHARE, vma); set_vma_private_data(vma, get_vma_private_data(vma) | flags); } static void set_vma_desc_resv_map(struct vm_area_desc *desc, struct resv_map *map) { VM_WARN_ON_ONCE(!is_vma_hugetlb_flags(&desc->vma_flags)); VM_WARN_ON_ONCE(vma_desc_test(desc, VMA_MAYSHARE_BIT)); desc->private_data = map; } static void set_vma_desc_resv_flags(struct vm_area_desc *desc, unsigned long flags) { VM_WARN_ON_ONCE(!is_vma_hugetlb_flags(&desc->vma_flags)); VM_WARN_ON_ONCE(vma_desc_test(desc, VMA_MAYSHARE_BIT)); desc->private_data = (void *)((unsigned long)desc->private_data | flags); } static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); return (get_vma_private_data(vma) & flag) != 0; } static bool is_vma_desc_resv_set(struct vm_area_desc *desc, unsigned long flag) { VM_WARN_ON_ONCE(!is_vma_hugetlb_flags(&desc->vma_flags)); return ((unsigned long)desc->private_data) & flag; } bool __vma_private_lock(struct vm_area_struct *vma) { return !(vma->vm_flags & VM_MAYSHARE) && get_vma_private_data(vma) & ~HPAGE_RESV_MASK && is_vma_resv_set(vma, HPAGE_RESV_OWNER); } void hugetlb_dup_vma_private(struct vm_area_struct *vma) { VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); /* * Clear vm_private_data * - For shared mappings this is a per-vma semaphore that may be * allocated in a subsequent call to hugetlb_vm_op_open. * Before clearing, make sure pointer is not associated with vma * as this will leak the structure. This is the case when called * via clear_vma_resv_huge_pages() and hugetlb_vm_op_open has already * been called to allocate a new structure. * - For MAP_PRIVATE mappings, this is the reserve map which does * not apply to children. Faults generated by the children are * not guaranteed to succeed, even if read-only. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock && vma_lock->vma != vma) vma->vm_private_data = NULL; } else { vma->vm_private_data = NULL; } } /* * Reset and decrement one ref on hugepage private reservation. * Called with mm->mmap_lock writer semaphore held. * This function should be only used by mremap and operate on * same sized vma. It should never come here with last ref on the * reservation. */ void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { /* * Clear the old hugetlb private page reservation. * It has already been transferred to new_vma. * * During a mremap() operation of a hugetlb vma we call move_vma() * which copies vma into new_vma and unmaps vma. After the copy * operation both new_vma and vma share a reference to the resv_map * struct, and at that point vma is about to be unmapped. We don't * want to return the reservation to the pool at unmap of vma because * the reservation still lives on in new_vma, so simply decrement the * ref here and remove the resv_map reference from this vma. */ struct resv_map *reservations = vma_resv_map(vma); if (reservations && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_put_hugetlb_cgroup_uncharge_info(reservations); kref_put(&reservations->refs, resv_map_release); } hugetlb_dup_vma_private(vma); } static void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio) { int nid = folio_nid(folio); lockdep_assert_held(&hugetlb_lock); VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); list_move(&folio->lru, &h->hugepage_freelists[nid]); h->free_huge_pages++; h->free_huge_pages_node[nid]++; folio_set_hugetlb_freed(folio); } static struct folio *dequeue_hugetlb_folio_node_exact(struct hstate *h, int nid) { struct folio *folio; bool pin = !!(current->flags & PF_MEMALLOC_PIN); lockdep_assert_held(&hugetlb_lock); list_for_each_entry(folio, &h->hugepage_freelists[nid], lru) { if (pin && !folio_is_longterm_pinnable(folio)) continue; if (folio_test_hwpoison(folio)) continue; if (is_migrate_isolate_page(&folio->page)) continue; list_move(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; return folio; } return NULL; } static struct folio *dequeue_hugetlb_folio_nodemask(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { unsigned int cpuset_mems_cookie; struct zonelist *zonelist; struct zone *zone; struct zoneref *z; int node = NUMA_NO_NODE; /* 'nid' should not be NUMA_NO_NODE. Try to catch any misuse of it and rectifiy. */ if (nid == NUMA_NO_NODE) nid = numa_node_id(); zonelist = node_zonelist(nid, gfp_mask); retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) { struct folio *folio; if (!cpuset_zone_allowed(zone, gfp_mask)) continue; /* * no need to ask again on the same node. Pool is node rather than * zone aware */ if (zone_to_nid(zone) == node) continue; node = zone_to_nid(zone); folio = dequeue_hugetlb_folio_node_exact(h, node); if (folio) return folio; } if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return NULL; } static unsigned long available_huge_pages(struct hstate *h) { return h->free_huge_pages - h->resv_huge_pages; } static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, long gbl_chg) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask; nodemask_t *nodemask; int nid; /* * gbl_chg==1 means the allocation requires a new page that was not * reserved before. Making sure there's at least one free page. */ if (gbl_chg && !available_huge_pages(h)) goto err; gfp_mask = htlb_alloc_mask(h); nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); return folio; err: return NULL; } #if defined(CONFIG_ARCH_HAS_GIGANTIC_PAGE) && defined(CONFIG_CONTIG_ALLOC) static struct folio *alloc_gigantic_frozen_folio(int order, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { struct folio *folio; folio = hugetlb_cma_alloc_frozen_folio(order, gfp_mask, nid, nodemask); if (folio) return folio; if (hugetlb_cma_exclusive_alloc()) return NULL; folio = (struct folio *)alloc_contig_frozen_pages(1 << order, gfp_mask, nid, nodemask); return folio; } #else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE || !CONFIG_CONTIG_ALLOC */ static struct folio *alloc_gigantic_frozen_folio(int order, gfp_t gfp_mask, int nid, nodemask_t *nodemask) { return NULL; } #endif /* * Remove hugetlb folio from lists. * If vmemmap exists for the folio, clear the hugetlb flag so that the * folio appears as just a compound page. Otherwise, wait until after * allocating vmemmap to clear the flag. * * Must be called with hugetlb lock held. */ void remove_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int nid = folio_nid(folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio(folio), folio); VM_BUG_ON_FOLIO(hugetlb_cgroup_from_folio_rsvd(folio), folio); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic_no_runtime(h)) return; list_del(&folio->lru); if (folio_test_hugetlb_freed(folio)) { folio_clear_hugetlb_freed(folio); h->free_huge_pages--; h->free_huge_pages_node[nid]--; } if (adjust_surplus) { h->surplus_huge_pages--; h->surplus_huge_pages_node[nid]--; } /* * We can only clear the hugetlb flag after allocating vmemmap * pages. Otherwise, someone (memory error handling) may try to write * to tail struct pages. */ if (!folio_test_hugetlb_vmemmap_optimized(folio)) __folio_clear_hugetlb(folio); h->nr_huge_pages--; h->nr_huge_pages_node[nid]--; } void add_hugetlb_folio(struct hstate *h, struct folio *folio, bool adjust_surplus) { int nid = folio_nid(folio); VM_BUG_ON_FOLIO(!folio_test_hugetlb_vmemmap_optimized(folio), folio); lockdep_assert_held(&hugetlb_lock); INIT_LIST_HEAD(&folio->lru); h->nr_huge_pages++; h->nr_huge_pages_node[nid]++; if (adjust_surplus) { h->surplus_huge_pages++; h->surplus_huge_pages_node[nid]++; } __folio_set_hugetlb(folio); folio_change_private(folio, NULL); /* * We have to set hugetlb_vmemmap_optimized again as above * folio_change_private(folio, NULL) cleared it. */ folio_set_hugetlb_vmemmap_optimized(folio); arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); } static void __update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio) { bool clear_flag = folio_test_hugetlb_vmemmap_optimized(folio); if (hstate_is_gigantic_no_runtime(h)) return; /* * If we don't know which subpages are hwpoisoned, we can't free * the hugepage, so it's leaked intentionally. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; /* * If folio is not vmemmap optimized (!clear_flag), then the folio * is no longer identified as a hugetlb page. hugetlb_vmemmap_restore_folio * can only be passed hugetlb pages and will BUG otherwise. */ if (clear_flag && hugetlb_vmemmap_restore_folio(h, folio)) { spin_lock_irq(&hugetlb_lock); /* * If we cannot allocate vmemmap pages, just refuse to free the * page and put the page back on the hugetlb free list and treat * as a surplus page. */ add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); return; } /* * If vmemmap pages were allocated above, then we need to clear the * hugetlb flag under the hugetlb lock. */ if (folio_test_hugetlb(folio)) { spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } /* * Move PageHWPoison flag from head page to the raw error pages, * which makes any healthy subpages reusable. */ if (unlikely(folio_test_hwpoison(folio))) folio_clear_hugetlb_hwpoison(folio); VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); if (folio_test_hugetlb_cma(folio)) hugetlb_cma_free_frozen_folio(folio); else free_frozen_pages(&folio->page, folio_order(folio)); } /* * As update_and_free_hugetlb_folio() can be called under any context, so we cannot * use GFP_KERNEL to allocate vmemmap pages. However, we can defer the * actual freeing in a workqueue to prevent from using GFP_ATOMIC to allocate * the vmemmap pages. * * free_hpage_workfn() locklessly retrieves the linked list of pages to be * freed and frees them one-by-one. As the page->mapping pointer is going * to be cleared in free_hpage_workfn() anyway, it is reused as the llist_node * structure of a lockless linked list of huge pages to be freed. */ static LLIST_HEAD(hpage_freelist); static void free_hpage_workfn(struct work_struct *work) { struct llist_node *node; node = llist_del_all(&hpage_freelist); while (node) { struct folio *folio; struct hstate *h; folio = container_of((struct address_space **)node, struct folio, mapping); node = node->next; folio->mapping = NULL; /* * The VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio) in * folio_hstate() is going to trigger because a previous call to * remove_hugetlb_folio() will clear the hugetlb bit, so do * not use folio_hstate() directly. */ h = size_to_hstate(folio_size(folio)); __update_and_free_hugetlb_folio(h, folio); cond_resched(); } } static DECLARE_WORK(free_hpage_work, free_hpage_workfn); static inline void flush_free_hpage_work(struct hstate *h) { if (hugetlb_vmemmap_optimizable(h)) flush_work(&free_hpage_work); } static void update_and_free_hugetlb_folio(struct hstate *h, struct folio *folio, bool atomic) { if (!folio_test_hugetlb_vmemmap_optimized(folio) || !atomic) { __update_and_free_hugetlb_folio(h, folio); return; } /* * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap pages. * * Only call schedule_work() if hpage_freelist is previously * empty. Otherwise, schedule_work() had been called but the workfn * hasn't retrieved the list yet. */ if (llist_add((struct llist_node *)&folio->mapping, &hpage_freelist)) schedule_work(&free_hpage_work); } static void bulk_vmemmap_restore_error(struct hstate *h, struct list_head *folio_list, struct list_head *non_hvo_folios) { struct folio *folio, *t_folio; if (!list_empty(non_hvo_folios)) { /* * Free any restored hugetlb pages so that restore of the * entire list can be retried. * The idea is that in the common case of ENOMEM errors freeing * hugetlb pages with vmemmap we will free up memory so that we * can allocate vmemmap for more hugetlb pages. */ list_for_each_entry_safe(folio, t_folio, non_hvo_folios, lru) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } else { /* * In the case where there are no folios which can be * immediately freed, we loop through the list trying to restore * vmemmap individually in the hope that someone elsewhere may * have done something to cause success (such as freeing some * memory). If unable to restore a hugetlb page, the hugetlb * page is made a surplus page and removed from the list. * If are able to restore vmemmap and free one hugetlb page, we * quit processing the list to retry the bulk operation. */ list_for_each_entry_safe(folio, t_folio, folio_list, lru) if (hugetlb_vmemmap_restore_folio(h, folio)) { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, true); spin_unlock_irq(&hugetlb_lock); } else { list_del(&folio->lru); spin_lock_irq(&hugetlb_lock); __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, folio, false); cond_resched(); break; } } } static void update_and_free_pages_bulk(struct hstate *h, struct list_head *folio_list) { long ret; struct folio *folio, *t_folio; LIST_HEAD(non_hvo_folios); /* * First allocate required vmemmmap (if necessary) for all folios. * Carefully handle errors and free up any available hugetlb pages * in an effort to make forward progress. */ retry: ret = hugetlb_vmemmap_restore_folios(h, folio_list, &non_hvo_folios); if (ret < 0) { bulk_vmemmap_restore_error(h, folio_list, &non_hvo_folios); goto retry; } /* * At this point, list should be empty, ret should be >= 0 and there * should only be pages on the non_hvo_folios list. * Do note that the non_hvo_folios list could be empty. * Without HVO enabled, ret will be 0 and there is no need to call * __folio_clear_hugetlb as this was done previously. */ VM_WARN_ON(!list_empty(folio_list)); VM_WARN_ON(ret < 0); if (!list_empty(&non_hvo_folios) && ret) { spin_lock_irq(&hugetlb_lock); list_for_each_entry(folio, &non_hvo_folios, lru) __folio_clear_hugetlb(folio); spin_unlock_irq(&hugetlb_lock); } list_for_each_entry_safe(folio, t_folio, &non_hvo_folios, lru) { update_and_free_hugetlb_folio(h, folio, false); cond_resched(); } } struct hstate *size_to_hstate(unsigned long size) { struct hstate *h; for_each_hstate(h) { if (huge_page_size(h) == size) return h; } return NULL; } void free_huge_folio(struct folio *folio) { /* * Can't pass hstate in here because it is called from the * generic mm code. */ struct hstate *h = folio_hstate(folio); int nid = folio_nid(folio); struct hugepage_subpool *spool = hugetlb_folio_subpool(folio); bool restore_reserve; unsigned long flags; VM_BUG_ON_FOLIO(folio_ref_count(folio), folio); VM_BUG_ON_FOLIO(folio_mapcount(folio), folio); hugetlb_set_folio_subpool(folio, NULL); if (folio_test_anon(folio)) __ClearPageAnonExclusive(&folio->page); folio->mapping = NULL; restore_reserve = folio_test_hugetlb_restore_reserve(folio); folio_clear_hugetlb_restore_reserve(folio); /* * If HPageRestoreReserve was set on page, page allocation consumed a * reservation. If the page was associated with a subpool, there * would have been a page reserved in the subpool before allocation * via hugepage_subpool_get_pages(). Since we are 'restoring' the * reservation, do not call hugepage_subpool_put_pages() as this will * remove the reserved page from the subpool. */ if (!restore_reserve) { /* * A return code of zero implies that the subpool will be * under its minimum size if the reservation is not restored * after page is free. Therefore, force restore_reserve * operation. */ if (hugepage_subpool_put_pages(spool, 1) == 0) restore_reserve = true; } spin_lock_irqsave(&hugetlb_lock, flags); folio_clear_hugetlb_migratable(folio); hugetlb_cgroup_uncharge_folio(hstate_index(h), pages_per_huge_page(h), folio); hugetlb_cgroup_uncharge_folio_rsvd(hstate_index(h), pages_per_huge_page(h), folio); lruvec_stat_mod_folio(folio, NR_HUGETLB, -pages_per_huge_page(h)); mem_cgroup_uncharge(folio); if (restore_reserve) h->resv_huge_pages++; if (folio_test_hugetlb_temporary(folio)) { remove_hugetlb_folio(h, folio, false); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else if (h->surplus_huge_pages_node[nid]) { /* remove the page from active list */ remove_hugetlb_folio(h, folio, true); spin_unlock_irqrestore(&hugetlb_lock, flags); update_and_free_hugetlb_folio(h, folio, true); } else { arch_clear_hugetlb_flags(folio); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } /* * Must be called with the hugetlb lock held */ static void account_new_hugetlb_folio(struct hstate *h, struct folio *folio) { lockdep_assert_held(&hugetlb_lock); h->nr_huge_pages++; h->nr_huge_pages_node[folio_nid(folio)]++; } void init_new_hugetlb_folio(struct folio *folio) { __folio_set_hugetlb(folio); INIT_LIST_HEAD(&folio->lru); hugetlb_set_folio_subpool(folio, NULL); set_hugetlb_cgroup(folio, NULL); set_hugetlb_cgroup_rsvd(folio, NULL); } /* * Find and lock address space (mapping) in write mode. * * Upon entry, the folio is locked which means that folio_mapping() is * stable. Due to locking order, we can only trylock_write. If we can * not get the lock, simply return NULL to caller. */ struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); if (!mapping) return mapping; if (i_mmap_trylock_write(mapping)) return mapping; return NULL; } static struct folio *alloc_buddy_frozen_folio(int order, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; bool alloc_try_hard = true; /* * By default we always try hard to allocate the folio with * __GFP_RETRY_MAYFAIL flag. However, if we are allocating folios in * a loop (to adjust global huge page counts) and previous allocation * failed, do not continue to try hard on the same node. Use the * node_alloc_noretry bitmap to manage this state information. */ if (node_alloc_noretry && node_isset(nid, *node_alloc_noretry)) alloc_try_hard = false; if (alloc_try_hard) gfp_mask |= __GFP_RETRY_MAYFAIL; folio = (struct folio *)__alloc_frozen_pages(gfp_mask, order, nid, nmask); /* * If we did not specify __GFP_RETRY_MAYFAIL, but still got a * folio this indicates an overall state change. Clear bit so * that we resume normal 'try hard' allocations. */ if (node_alloc_noretry && folio && !alloc_try_hard) node_clear(nid, *node_alloc_noretry); /* * If we tried hard to get a folio but failed, set bit so that * subsequent attempts will not try as hard until there is an * overall state change. */ if (node_alloc_noretry && !folio && alloc_try_hard) node_set(nid, *node_alloc_noretry); if (!folio) { __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL); return NULL; } __count_vm_event(HTLB_BUDDY_PGALLOC); return folio; } static struct folio *only_alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask, nodemask_t *node_alloc_noretry) { struct folio *folio; int order = huge_page_order(h); if (nid == NUMA_NO_NODE) nid = numa_mem_id(); if (order_is_gigantic(order)) folio = alloc_gigantic_frozen_folio(order, gfp_mask, nid, nmask); else folio = alloc_buddy_frozen_folio(order, gfp_mask, nid, nmask, node_alloc_noretry); if (folio) init_new_hugetlb_folio(folio); return folio; } /* * Common helper to allocate a fresh hugetlb folio. All specific allocators * should use this function to get new hugetlb folio * * Note that returned folio is 'frozen': ref count of head page and all tail * pages is zero, and the accounting must be done in the caller. */ static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask, NULL); if (folio) hugetlb_vmemmap_optimize_folio(h, folio); return folio; } void prep_and_add_allocated_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_folios(h, folio_list); /* Add all new pool pages to free lists in one lock cycle */ spin_lock_irqsave(&hugetlb_lock, flags); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { account_new_hugetlb_folio(h, folio); enqueue_hugetlb_folio(h, folio); } spin_unlock_irqrestore(&hugetlb_lock, flags); } /* * Allocates a fresh hugetlb page in a node interleaved manner. The page * will later be added to the appropriate hugetlb pool. */ static struct folio *alloc_pool_huge_folio(struct hstate *h, nodemask_t *nodes_allowed, nodemask_t *node_alloc_noretry, int *next_node) { gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; int nr_nodes, node; for_each_node_mask_to_alloc(next_node, nr_nodes, node, nodes_allowed) { struct folio *folio; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node, nodes_allowed, node_alloc_noretry); if (folio) return folio; } return NULL; } /* * Remove huge page from pool from next node to free. Attempt to keep * persistent huge pages more or less balanced over allowed nodes. * This routine only 'removes' the hugetlb page. The caller must make * an additional call to free the page to low level allocators. * Called with hugetlb_lock locked. */ static struct folio *remove_pool_hugetlb_folio(struct hstate *h, nodemask_t *nodes_allowed, bool acct_surplus) { int nr_nodes, node; struct folio *folio = NULL; lockdep_assert_held(&hugetlb_lock); for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { /* * If we're returning unused surplus pages, only examine * nodes with surplus pages. */ if ((!acct_surplus || h->surplus_huge_pages_node[node]) && !list_empty(&h->hugepage_freelists[node])) { folio = list_entry(h->hugepage_freelists[node].next, struct folio, lru); remove_hugetlb_folio(h, folio, acct_surplus); break; } } return folio; } /* * Dissolve a given free hugetlb folio into free buddy pages. This function * does nothing for in-use hugetlb folios and non-hugetlb folios. * This function returns values like below: * * -ENOMEM: failed to allocate vmemmap pages to free the freed hugepages * when the system is under memory pressure and the feature of * freeing unused vmemmap pages associated with each hugetlb page * is enabled. * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use * (allocated or reserved.) * 0: successfully dissolved free hugepages or the page is not a * hugepage (considered as already dissolved) */ int dissolve_free_hugetlb_folio(struct folio *folio) { int rc = -EBUSY; retry: /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!folio_test_hugetlb(folio)) return 0; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio)) { rc = 0; goto out; } if (!folio_ref_count(folio)) { struct hstate *h = folio_hstate(folio); bool adjust_surplus = false; if (!available_huge_pages(h)) goto out; /* * We should make sure that the page is already on the free list * when it is dissolved. */ if (unlikely(!folio_test_hugetlb_freed(folio))) { spin_unlock_irq(&hugetlb_lock); cond_resched(); /* * Theoretically, we should return -EBUSY when we * encounter this race. In fact, we have a chance * to successfully dissolve the page if we do a * retry. Because the race window is quite small. * If we seize this opportunity, it is an optimization * for increasing the success rate of dissolving page. */ goto retry; } if (h->surplus_huge_pages_node[folio_nid(folio)]) adjust_surplus = true; remove_hugetlb_folio(h, folio, adjust_surplus); h->max_huge_pages--; spin_unlock_irq(&hugetlb_lock); /* * Normally update_and_free_hugtlb_folio will allocate required vmemmmap * before freeing the page. update_and_free_hugtlb_folio will fail to * free the page if it can not allocate required vmemmap. We * need to adjust max_huge_pages if the page is not freed. * Attempt to allocate vmemmmap here so that we can take * appropriate action on failure. * * The folio_test_hugetlb check here is because * remove_hugetlb_folio will clear hugetlb folio flag for * non-vmemmap optimized hugetlb folios. */ if (folio_test_hugetlb(folio)) { rc = hugetlb_vmemmap_restore_folio(h, folio); if (rc) { spin_lock_irq(&hugetlb_lock); add_hugetlb_folio(h, folio, adjust_surplus); h->max_huge_pages++; goto out; } } else { rc = 0; } update_and_free_hugetlb_folio(h, folio, false); return rc; } out: spin_unlock_irq(&hugetlb_lock); return rc; } /* * Dissolve free hugepages in a given pfn range. Used by memory hotplug to * make specified memory blocks removable from the system. * Note that this will dissolve a free gigantic hugepage completely, if any * part of it lies within the given range. * Also note that if dissolve_free_hugetlb_folio() returns with an error, all * free hugetlb folios that were dissolved before that error are lost. */ int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { unsigned long pfn; struct folio *folio; int rc = 0; unsigned int order; struct hstate *h; if (!hugepages_supported()) return rc; order = huge_page_order(&default_hstate); for_each_hstate(h) order = min(order, huge_page_order(h)); for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << order) { folio = pfn_folio(pfn); rc = dissolve_free_hugetlb_folio(folio); if (rc) break; } return rc; } /* * Allocates a fresh surplus page from the page allocator. */ static struct folio *alloc_surplus_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio = NULL; if (hstate_is_gigantic_no_runtime(h)) return NULL; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) goto out_unlock; spin_unlock_irq(&hugetlb_lock); folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask); if (!folio) return NULL; spin_lock_irq(&hugetlb_lock); /* * nr_huge_pages needs to be adjusted within the same lock cycle * as surplus_pages, otherwise it might confuse * persistent_huge_pages() momentarily. */ account_new_hugetlb_folio(h, folio); /* * We could have raced with the pool size change. * Double check that and simply deallocate the new page * if we would end up overcommiting the surpluses. Abuse * temporary page to workaround the nasty free_huge_folio * codeflow */ if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) { folio_set_hugetlb_temporary(folio); spin_unlock_irq(&hugetlb_lock); free_huge_folio(folio); return NULL; } h->surplus_huge_pages++; h->surplus_huge_pages_node[folio_nid(folio)]++; out_unlock: spin_unlock_irq(&hugetlb_lock); return folio; } static struct folio *alloc_migrate_hugetlb_folio(struct hstate *h, gfp_t gfp_mask, int nid, nodemask_t *nmask) { struct folio *folio; if (hstate_is_gigantic(h)) return NULL; folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, nmask); if (!folio) return NULL; spin_lock_irq(&hugetlb_lock); account_new_hugetlb_folio(h, folio); spin_unlock_irq(&hugetlb_lock); /* fresh huge pages are frozen */ folio_ref_unfreeze(folio, 1); /* * We do not account these pages as surplus because they are only * temporary and will be released properly on the last reference */ folio_set_hugetlb_temporary(folio); return folio; } /* * Use the VMA's mpolicy to allocate a huge page from the buddy. */ static struct folio *alloc_buddy_hugetlb_folio_with_mpol(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { struct folio *folio = NULL; struct mempolicy *mpol; gfp_t gfp_mask = htlb_alloc_mask(h); int nid; nodemask_t *nodemask; nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask); if (mpol_is_preferred_many(mpol)) { gfp_t gfp = gfp_mask & ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); folio = alloc_surplus_hugetlb_folio(h, gfp, nid, nodemask); /* Fallback to all nodes if page==NULL */ nodemask = NULL; } if (!folio) folio = alloc_surplus_hugetlb_folio(h, gfp_mask, nid, nodemask); mpol_cond_put(mpol); return folio; } struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { struct folio *folio; spin_lock_irq(&hugetlb_lock); if (!h->resv_huge_pages) { spin_unlock_irq(&hugetlb_lock); return NULL; } folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); if (folio) h->resv_huge_pages--; spin_unlock_irq(&hugetlb_lock); return folio; } /* folio migration callback function */ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { spin_lock_irq(&hugetlb_lock); if (available_huge_pages(h)) { struct folio *folio; folio = dequeue_hugetlb_folio_nodemask(h, gfp_mask, preferred_nid, nmask); if (folio) { spin_unlock_irq(&hugetlb_lock); return folio; } } spin_unlock_irq(&hugetlb_lock); /* We cannot fallback to other nodes, as we could break the per-node pool. */ if (!allow_alloc_fallback) gfp_mask |= __GFP_THISNODE; return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask); } static nodemask_t *policy_mbind_nodemask(gfp_t gfp) { #ifdef CONFIG_NUMA struct mempolicy *mpol = get_task_policy(current); /* * Only enforce MPOL_BIND policy which overlaps with cpuset policy * (from policy_nodemask) specifically for hugetlb case */ if (mpol->mode == MPOL_BIND && (apply_policy_zone(mpol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&mpol->nodes))) return &mpol->nodes; #endif return NULL; } /* * Increase the hugetlb pool such that it can accommodate a reservation * of size 'delta'. */ static int gather_surplus_pages(struct hstate *h, long delta) __must_hold(&hugetlb_lock) { LIST_HEAD(surplus_list); struct folio *folio, *tmp; int ret; long i; long needed, allocated; bool alloc_ok = true; nodemask_t *mbind_nodemask, alloc_nodemask; mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h)); if (mbind_nodemask) nodes_and(alloc_nodemask, *mbind_nodemask, cpuset_current_mems_allowed); else alloc_nodemask = cpuset_current_mems_allowed; lockdep_assert_held(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { h->resv_huge_pages += delta; return 0; } allocated = 0; ret = -ENOMEM; retry: spin_unlock_irq(&hugetlb_lock); for (i = 0; i < needed; i++) { folio = NULL; /* * It is okay to use NUMA_NO_NODE because we use numa_mem_id() * down the road to pick the current node if that is the case. */ folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h), NUMA_NO_NODE, &alloc_nodemask); if (!folio) { alloc_ok = false; break; } list_add(&folio->lru, &surplus_list); cond_resched(); } allocated += i; /* * After retaking hugetlb_lock, we need to recalculate 'needed' * because either resv_huge_pages or free_huge_pages may have changed. */ spin_lock_irq(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); if (needed > 0) { if (alloc_ok) goto retry; /* * We were not able to allocate enough pages to * satisfy the entire reservation so we free what * we've allocated so far. */ goto free; } /* * The surplus_list now contains _at_least_ the number of extra pages * needed to accommodate the reservation. Add the appropriate number * of pages to the hugetlb pool and free the extras back to the buddy * allocator. Commit the entire reservation here to prevent another * process from stealing the pages as they are added to the pool but * before they are reserved. */ needed += allocated; h->resv_huge_pages += delta; ret = 0; /* Free the needed pages to the hugetlb pool */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) { if ((--needed) < 0) break; /* Add the page to the hugetlb allocator */ enqueue_hugetlb_folio(h, folio); } free: spin_unlock_irq(&hugetlb_lock); /* * Free unnecessary surplus pages to the buddy allocator. * Pages have no ref count, call free_huge_folio directly. */ list_for_each_entry_safe(folio, tmp, &surplus_list, lru) free_huge_folio(folio); spin_lock_irq(&hugetlb_lock); return ret; } /* * This routine has two main purposes: * 1) Decrement the reservation count (resv_huge_pages) by the value passed * in unused_resv_pages. This corresponds to the prior adjustments made * to the associated reservation map. * 2) Free any unused surplus pages that may have been allocated to satisfy * the reservation. As many as unused_resv_pages may be freed. */ static void return_unused_surplus_pages(struct hstate *h, unsigned long unused_resv_pages) { unsigned long nr_pages; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); /* Uncommit the reservation */ h->resv_huge_pages -= unused_resv_pages; if (hstate_is_gigantic_no_runtime(h)) goto out; /* * Part (or even all) of the reservation could have been backed * by pre-allocated pages. Only free surplus pages. */ nr_pages = min(unused_resv_pages, h->surplus_huge_pages); /* * We want to release as many surplus pages as possible, spread * evenly across all nodes with memory. Iterate across these nodes * until we can no longer free unreserved surplus pages. This occurs * when the nodes with surplus pages have no free pages. * remove_pool_hugetlb_folio() will balance the freed pages across the * on-line nodes with memory and will handle the hstate accounting. */ while (nr_pages--) { struct folio *folio; folio = remove_pool_hugetlb_folio(h, &node_states[N_MEMORY], 1); if (!folio) goto out; list_add(&folio->lru, &page_list); } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * vma_needs_reservation, vma_commit_reservation and vma_end_reservation * are used by the huge page allocation routines to manage reservations. * * vma_needs_reservation is called to determine if the huge page at addr * within the vma has an associated reservation. If a reservation is * needed, the value 1 is returned. The caller is then responsible for * managing the global reservation and subpool usage counts. After * the huge page has been allocated, vma_commit_reservation is called * to add the page to the reservation map. If the page allocation fails, * the reservation must be ended instead of committed. vma_end_reservation * is called in such cases. * * In the normal case, vma_commit_reservation returns the same value * as the preceding vma_needs_reservation call. The only time this * is not the case is if a reserve map was changed between calls. It * is the responsibility of the caller to notice the difference and * take appropriate action. * * vma_add_reservation is used in error paths where a reservation must * be restored when a newly allocated huge page must be freed. It is * to be called after calling vma_needs_reservation to determine if a * reservation exists. * * vma_del_reservation is used in error paths where an entry in the reserve * map was created during huge page allocation and must be removed. It is to * be called after calling vma_needs_reservation to determine if a reservation * exists. */ enum vma_resv_mode { VMA_NEEDS_RESV, VMA_COMMIT_RESV, VMA_END_RESV, VMA_ADD_RESV, VMA_DEL_RESV, }; static long __vma_reservation_common(struct hstate *h, struct vm_area_struct *vma, unsigned long addr, enum vma_resv_mode mode) { struct resv_map *resv; pgoff_t idx; long ret; long dummy_out_regions_needed; resv = vma_resv_map(vma); if (!resv) return 1; idx = vma_hugecache_offset(h, vma, addr); switch (mode) { case VMA_NEEDS_RESV: ret = region_chg(resv, idx, idx + 1, &dummy_out_regions_needed); /* We assume that vma_reservation_* routines always operate on * 1 page, and that adding to resv map a 1 page entry can only * ever require 1 region. */ VM_BUG_ON(dummy_out_regions_needed != 1); break; case VMA_COMMIT_RESV: ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); break; case VMA_END_RESV: region_abort(resv, idx, idx + 1, 1); ret = 0; break; case VMA_ADD_RESV: if (vma->vm_flags & VM_MAYSHARE) { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } else { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } break; case VMA_DEL_RESV: if (vma->vm_flags & VM_MAYSHARE) { region_abort(resv, idx, idx + 1, 1); ret = region_del(resv, idx, idx + 1); } else { ret = region_add(resv, idx, idx + 1, 1, NULL, NULL); /* region_add calls of range 1 should never fail. */ VM_BUG_ON(ret < 0); } break; default: BUG(); } if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV) return ret; /* * We know private mapping must have HPAGE_RESV_OWNER set. * * In most cases, reserves always exist for private mappings. * However, a file associated with mapping could have been * hole punched or truncated after reserves were consumed. * As subsequent fault on such a range will not use reserves. * Subtle - The reserve map for private mappings has the * opposite meaning than that of shared mappings. If NO * entry is in the reserve map, it means a reservation exists. * If an entry exists in the reserve map, it means the * reservation has already been consumed. As a result, the * return value of this routine is the opposite of the * value returned from reserve map manipulation routines above. */ if (ret > 0) return 0; if (ret == 0) return 1; return ret; } static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV); } static long vma_commit_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV); } static void vma_end_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { (void)__vma_reservation_common(h, vma, addr, VMA_END_RESV); } static long vma_add_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV); } static long vma_del_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) { return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV); } /* * This routine is called to restore reservation information on error paths. * It should ONLY be called for folios allocated via alloc_hugetlb_folio(), * and the hugetlb mutex should remain held when calling this routine. * * It handles two specific cases: * 1) A reservation was in place and the folio consumed the reservation. * hugetlb_restore_reserve is set in the folio. * 2) No reservation was in place for the page, so hugetlb_restore_reserve is * not set. However, alloc_hugetlb_folio always updates the reserve map. * * In case 1, free_huge_folio later in the error path will increment the * global reserve count. But, free_huge_folio does not have enough context * to adjust the reservation map. This case deals primarily with private * mappings. Adjust the reserve map here to be consistent with global * reserve count adjustments to be made by free_huge_folio. Make sure the * reserve map indicates there is a reservation present. * * In case 2, simply undo reserve map modifications done by alloc_hugetlb_folio. */ void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio) { long rc = vma_needs_reservation(h, vma, address); if (folio_test_hugetlb_restore_reserve(folio)) { if (unlikely(rc < 0)) /* * Rare out of memory condition in reserve map * manipulation. Clear hugetlb_restore_reserve so * that global reserve count will not be incremented * by free_huge_folio. This will make it appear * as though the reservation for this folio was * consumed. This may prevent the task from * faulting in the folio at a later time. This * is better than inconsistent global huge page * accounting of reserve counts. */ folio_clear_hugetlb_restore_reserve(folio); else if (rc) (void)vma_add_reservation(h, vma, address); else vma_end_reservation(h, vma, address); } else { if (!rc) { /* * This indicates there is an entry in the reserve map * not added by alloc_hugetlb_folio. We know it was added * before the alloc_hugetlb_folio call, otherwise * hugetlb_restore_reserve would be set on the folio. * Remove the entry so that a subsequent allocation * does not consume a reservation. */ rc = vma_del_reservation(h, vma, address); if (rc < 0) /* * VERY rare out of memory condition. Since * we can not delete the entry, set * hugetlb_restore_reserve so that the reserve * count will be incremented when the folio * is freed. This reserve will be consumed * on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else if (rc < 0) { /* * Rare out of memory condition from * vma_needs_reservation call. Memory allocation is * only attempted if a new entry is needed. Therefore, * this implies there is not an entry in the * reserve map. * * For shared mappings, no entry in the map indicates * no reservation. We are done. */ if (!(vma->vm_flags & VM_MAYSHARE)) /* * For private mappings, no entry indicates * a reservation is present. Since we can * not add an entry, set hugetlb_restore_reserve * on the folio so reserve count will be * incremented when freed. This reserve will * be consumed on a subsequent allocation. */ folio_set_hugetlb_restore_reserve(folio); } else { /* * No reservation present, do nothing */ vma_end_reservation(h, vma, address); } } } /* * alloc_and_dissolve_hugetlb_folio - Allocate a new folio and dissolve * the old one * @old_folio: Old folio to dissolve * @list: List to isolate the page in case we need to * Returns 0 on success, otherwise negated error. */ static int alloc_and_dissolve_hugetlb_folio(struct folio *old_folio, struct list_head *list) { gfp_t gfp_mask; struct hstate *h; int nid = folio_nid(old_folio); struct folio *new_folio = NULL; int ret = 0; retry: /* * The old_folio might have been dissolved from under our feet, so make sure * to carefully check the state under the lock. */ spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(old_folio)) { /* * Freed from under us. Drop new_folio too. */ goto free_new; } else if (folio_ref_count(old_folio)) { bool isolated; /* * Someone has grabbed the folio, try to isolate it here. * Fail with -EBUSY if not possible. */ spin_unlock_irq(&hugetlb_lock); isolated = folio_isolate_hugetlb(old_folio, list); ret = isolated ? 0 : -EBUSY; spin_lock_irq(&hugetlb_lock); goto free_new; } else if (!folio_test_hugetlb_freed(old_folio)) { /* * Folio's refcount is 0 but it has not been enqueued in the * freelist yet. Race window is small, so we can succeed here if * we retry. */ spin_unlock_irq(&hugetlb_lock); cond_resched(); goto retry; } else { h = folio_hstate(old_folio); if (!new_folio) { spin_unlock_irq(&hugetlb_lock); gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; new_folio = alloc_fresh_hugetlb_folio(h, gfp_mask, nid, NULL); if (!new_folio) return -ENOMEM; goto retry; } /* * Ok, old_folio is still a genuine free hugepage. Remove it from * the freelist and decrease the counters. These will be * incremented again when calling account_new_hugetlb_folio() * and enqueue_hugetlb_folio() for new_folio. The counters will * remain stable since this happens under the lock. */ remove_hugetlb_folio(h, old_folio, false); /* * Ref count on new_folio is already zero as it was dropped * earlier. It can be directly added to the pool free list. */ account_new_hugetlb_folio(h, new_folio); enqueue_hugetlb_folio(h, new_folio); /* * Folio has been replaced, we can safely free the old one. */ spin_unlock_irq(&hugetlb_lock); update_and_free_hugetlb_folio(h, old_folio, false); } return ret; free_new: spin_unlock_irq(&hugetlb_lock); if (new_folio) update_and_free_hugetlb_folio(h, new_folio, false); return ret; } int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list) { int ret = -EBUSY; /* Not to disrupt normal path by vainly holding hugetlb_lock */ if (!folio_test_hugetlb(folio)) return 0; /* * Fence off gigantic pages as there is a cyclic dependency between * alloc_contig_range and them. Return -ENOMEM as this has the effect * of bailing out right away without further retrying. */ if (order_is_gigantic(folio_order(folio))) return -ENOMEM; if (folio_ref_count(folio) && folio_isolate_hugetlb(folio, list)) ret = 0; else if (!folio_ref_count(folio)) ret = alloc_and_dissolve_hugetlb_folio(folio, list); return ret; } /* * replace_free_hugepage_folios - Replace free hugepage folios in a given pfn * range with new folios. * @start_pfn: start pfn of the given pfn range * @end_pfn: end pfn of the given pfn range * Returns 0 on success, otherwise negated error. */ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) { unsigned long nr = 0; struct page *page; struct hstate *h; LIST_HEAD(list); int ret = 0; /* Avoid pfn iterations if no free non-gigantic huge pages */ for_each_hstate(h) { if (hstate_is_gigantic(h)) continue; nr += h->free_huge_pages; if (nr) break; } if (!nr) return 0; while (start_pfn < end_pfn) { page = pfn_to_page(start_pfn); nr = 1; if (PageHuge(page) || PageCompound(page)) { struct folio *folio = page_folio(page); nr = folio_nr_pages(folio) - folio_page_idx(folio, page); /* * Don't disrupt normal path by vainly holding * hugetlb_lock */ if (folio_test_hugetlb(folio) && !folio_ref_count(folio)) { if (order_is_gigantic(folio_order(folio))) { ret = -ENOMEM; break; } ret = alloc_and_dissolve_hugetlb_folio(folio, &list); if (ret) break; putback_movable_pages(&list); } } else if (PageBuddy(page)) { /* * Buddy order check without zone lock is unsafe and * the order is maybe invalid, but race should be * small, and the worst thing is skipping free hugetlb. */ const unsigned int order = buddy_order_unsafe(page); if (order <= MAX_PAGE_ORDER) nr = 1UL << order; } start_pfn += nr; } return ret; } void wait_for_freed_hugetlb_folios(void) { if (llist_empty(&hpage_freelist)) return; flush_work(&free_hpage_work); } typedef enum { /* * For either 0/1: we checked the per-vma resv map, and one resv * count either can be reused (0), or an extra needed (1). */ MAP_CHG_REUSE = 0, MAP_CHG_NEEDED = 1, /* * Cannot use per-vma resv count can be used, hence a new resv * count is enforced. * * NOTE: This is mostly identical to MAP_CHG_NEEDED, except * that currently vma_needs_reservation() has an unwanted side * effect to either use end() or commit() to complete the * transaction. Hence it needs to differentiate from NEEDED. */ MAP_CHG_ENFORCED = 2, } map_chg_state; /* * NOTE! "cow_from_owner" represents a very hacky usage only used in CoW * faults of hugetlb private mappings on top of a non-page-cache folio (in * which case even if there's a private vma resv map it won't cover such * allocation). New call sites should (probably) never set it to true!! * When it's set, the allocation will bypass all vma level reservations. */ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner) { struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct folio *folio; long retval, gbl_chg, gbl_reserve; map_chg_state map_chg; int ret, idx; struct hugetlb_cgroup *h_cg = NULL; gfp_t gfp = htlb_alloc_mask(h) | __GFP_RETRY_MAYFAIL; idx = hstate_index(h); /* Whether we need a separate per-vma reservation? */ if (cow_from_owner) { /* * Special case! Since it's a CoW on top of a reserved * page, the private resv map doesn't count. So it cannot * consume the per-vma resv map even if it's reserved. */ map_chg = MAP_CHG_ENFORCED; } else { /* * Examine the region/reserve map to determine if the process * has a reservation for the page to be allocated. A return * code of zero indicates a reservation exists (no change). */ retval = vma_needs_reservation(h, vma, addr); if (retval < 0) return ERR_PTR(-ENOMEM); map_chg = retval ? MAP_CHG_NEEDED : MAP_CHG_REUSE; } /* * Whether we need a separate global reservation? * * Processes that did not create the mapping will have no * reserves as indicated by the region/reserve map. Check * that the allocation will not exceed the subpool limit. * Or if it can get one from the pool reservation directly. */ if (map_chg) { gbl_chg = hugepage_subpool_get_pages(spool, 1); if (gbl_chg < 0) goto out_end_reservation; } else { /* * If we have the vma reservation ready, no need for extra * global reservation. */ gbl_chg = 0; } /* * If this allocation is not consuming a per-vma reservation, * charge the hugetlb cgroup now. */ if (map_chg) { ret = hugetlb_cgroup_charge_cgroup_rsvd( idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_subpool_put; } ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg); if (ret) goto out_uncharge_cgroup_reservation; spin_lock_irq(&hugetlb_lock); /* * glb_chg is passed to indicate whether or not a page must be taken * from the global free pool (global change). gbl_chg == 0 indicates * a reservation exists for the allocation. */ folio = dequeue_hugetlb_folio_vma(h, vma, addr, gbl_chg); if (!folio) { spin_unlock_irq(&hugetlb_lock); folio = alloc_buddy_hugetlb_folio_with_mpol(h, vma, addr); if (!folio) goto out_uncharge_cgroup; spin_lock_irq(&hugetlb_lock); list_add(&folio->lru, &h->hugepage_activelist); folio_ref_unfreeze(folio, 1); /* Fall through */ } /* * Either dequeued or buddy-allocated folio needs to add special * mark to the folio when it consumes a global reservation. */ if (!gbl_chg) { folio_set_hugetlb_restore_reserve(folio); h->resv_huge_pages--; } hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio); /* If allocation is not consuming a reservation, also store the * hugetlb_cgroup pointer on the page. */ if (map_chg) { hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h), h_cg, folio); } spin_unlock_irq(&hugetlb_lock); hugetlb_set_folio_subpool(folio, spool); if (map_chg != MAP_CHG_ENFORCED) { /* commit() is only needed if the map_chg is not enforced */ retval = vma_commit_reservation(h, vma, addr); /* * Check for possible race conditions. When it happens.. * The page was added to the reservation map between * vma_needs_reservation and vma_commit_reservation. * This indicates a race with hugetlb_reserve_pages. * Adjust for the subpool count incremented above AND * in hugetlb_reserve_pages for the same page. Also, * the reservation count added in hugetlb_reserve_pages * no longer applies. */ if (unlikely(map_chg == MAP_CHG_NEEDED && retval == 0)) { long rsv_adjust; rsv_adjust = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -rsv_adjust); spin_lock_irq(&hugetlb_lock); hugetlb_cgroup_uncharge_folio_rsvd( hstate_index(h), pages_per_huge_page(h), folio); spin_unlock_irq(&hugetlb_lock); } } ret = mem_cgroup_charge_hugetlb(folio, gfp); /* * Unconditionally increment NR_HUGETLB here. If it turns out that * mem_cgroup_charge_hugetlb failed, then immediately free the page and * decrement NR_HUGETLB. */ lruvec_stat_mod_folio(folio, NR_HUGETLB, pages_per_huge_page(h)); if (ret == -ENOMEM) { free_huge_folio(folio); return ERR_PTR(-ENOMEM); } return folio; out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg); out_uncharge_cgroup_reservation: if (map_chg) hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h), h_cg); out_subpool_put: /* * put page to subpool iff the quota of subpool's rsv_hpages is used * during hugepage_subpool_get_pages. */ if (map_chg && !gbl_chg) { gbl_reserve = hugepage_subpool_put_pages(spool, 1); hugetlb_acct_memory(h, -gbl_reserve); } out_end_reservation: if (map_chg != MAP_CHG_ENFORCED) vma_end_reservation(h, vma, addr); return ERR_PTR(-ENOSPC); } static __init void *alloc_bootmem(struct hstate *h, int nid, bool node_exact) { struct huge_bootmem_page *m; int listnode = nid; if (hugetlb_early_cma(h)) m = hugetlb_cma_alloc_bootmem(h, &listnode, node_exact); else { if (node_exact) m = memblock_alloc_exact_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); else { m = memblock_alloc_try_nid_raw(huge_page_size(h), huge_page_size(h), 0, MEMBLOCK_ALLOC_ACCESSIBLE, nid); /* * For pre-HVO to work correctly, pages need to be on * the list for the node they were actually allocated * from. That node may be different in the case of * fallback by memblock_alloc_try_nid_raw. So, * extract the actual node first. */ if (m) listnode = early_pfn_to_nid(PHYS_PFN(__pa(m))); } if (m) { m->flags = 0; m->cma = NULL; } } if (m) { /* * Use the beginning of the huge page to store the * huge_bootmem_page struct (until gather_bootmem * puts them into the mem_map). * * Put them into a private list first because mem_map * is not up yet. */ INIT_LIST_HEAD(&m->list); list_add(&m->list, &huge_boot_pages[listnode]); m->hstate = h; } return m; } int alloc_bootmem_huge_page(struct hstate *h, int nid) __attribute__ ((weak, alias("__alloc_bootmem_huge_page"))); int __alloc_bootmem_huge_page(struct hstate *h, int nid) { struct huge_bootmem_page *m = NULL; /* initialize for clang */ int nr_nodes, node = nid; /* do node specific alloc */ if (nid != NUMA_NO_NODE) { m = alloc_bootmem(h, node, true); if (!m) return 0; goto found; } /* allocate from next node when distributing huge pages */ for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, &hugetlb_bootmem_nodes) { m = alloc_bootmem(h, node, false); if (!m) return 0; goto found; } found: /* * Only initialize the head struct page in memmap_init_reserved_pages, * rest of the struct pages will be initialized by the HugeTLB * subsystem itself. * The head struct page is used to get folio information by the HugeTLB * subsystem like zone id and node id. */ memblock_reserved_mark_noinit(__pa((void *)m + PAGE_SIZE), huge_page_size(h) - PAGE_SIZE); return 1; } /* Initialize [start_page:end_page_number] tail struct pages of a hugepage */ static void __init hugetlb_folio_init_tail_vmemmap(struct folio *folio, struct hstate *h, unsigned long start_page_number, unsigned long end_page_number) { enum zone_type zone = folio_zonenum(folio); int nid = folio_nid(folio); struct page *page = folio_page(folio, start_page_number); unsigned long head_pfn = folio_pfn(folio); unsigned long pfn, end_pfn = head_pfn + end_page_number; unsigned int order = huge_page_order(h); /* * As we marked all tail pages with memblock_reserved_mark_noinit(), * we must initialize them ourselves here. */ for (pfn = head_pfn + start_page_number; pfn < end_pfn; page++, pfn++) { __init_single_page(page, pfn, zone, nid); prep_compound_tail(page, &folio->page, order); set_page_count(page, 0); } } static void __init hugetlb_folio_init_vmemmap(struct folio *folio, struct hstate *h, unsigned long nr_pages) { int ret; /* * This is an open-coded prep_compound_page() whereby we avoid * walking pages twice by initializing/preparing+freezing them in the * same go. */ __folio_clear_reserved(folio); __folio_set_head(folio); ret = folio_ref_freeze(folio, 1); VM_BUG_ON(!ret); hugetlb_folio_init_tail_vmemmap(folio, h, 1, nr_pages); prep_compound_head(&folio->page, huge_page_order(h)); } static bool __init hugetlb_bootmem_page_prehvo(struct huge_bootmem_page *m) { return m->flags & HUGE_BOOTMEM_HVO; } static bool __init hugetlb_bootmem_page_earlycma(struct huge_bootmem_page *m) { return m->flags & HUGE_BOOTMEM_CMA; } /* * memblock-allocated pageblocks might not have the migrate type set * if marked with the 'noinit' flag. Set it to the default (MIGRATE_MOVABLE) * here, or MIGRATE_CMA if this was a page allocated through an early CMA * reservation. * * In case of vmemmap optimized folios, the tail vmemmap pages are mapped * read-only, but that's ok - for sparse vmemmap this does not write to * the page structure. */ static void __init hugetlb_bootmem_init_migratetype(struct folio *folio, struct hstate *h) { unsigned long nr_pages = pages_per_huge_page(h), i; WARN_ON_ONCE(!pageblock_aligned(folio_pfn(folio))); for (i = 0; i < nr_pages; i += pageblock_nr_pages) { if (folio_test_hugetlb_cma(folio)) init_cma_pageblock(folio_page(folio, i)); else init_pageblock_migratetype(folio_page(folio, i), MIGRATE_MOVABLE, false); } } static void __init prep_and_add_bootmem_folios(struct hstate *h, struct list_head *folio_list) { unsigned long flags; struct folio *folio, *tmp_f; /* Send list for bulk vmemmap optimization processing */ hugetlb_vmemmap_optimize_bootmem_folios(h, folio_list); list_for_each_entry_safe(folio, tmp_f, folio_list, lru) { if (!folio_test_hugetlb_vmemmap_optimized(folio)) { /* * If HVO fails, initialize all tail struct pages * We do not worry about potential long lock hold * time as this is early in boot and there should * be no contention. */ hugetlb_folio_init_tail_vmemmap(folio, h, HUGETLB_VMEMMAP_RESERVE_PAGES, pages_per_huge_page(h)); } hugetlb_bootmem_init_migratetype(folio, h); /* Subdivide locks to achieve better parallel performance */ spin_lock_irqsave(&hugetlb_lock, flags); account_new_hugetlb_folio(h, folio); enqueue_hugetlb_folio(h, folio); spin_unlock_irqrestore(&hugetlb_lock, flags); } } bool __init hugetlb_bootmem_page_zones_valid(int nid, struct huge_bootmem_page *m) { unsigned long start_pfn; bool valid; if (m->flags & HUGE_BOOTMEM_ZONES_VALID) { /* * Already validated, skip check. */ return true; } if (hugetlb_bootmem_page_earlycma(m)) { valid = cma_validate_zones(m->cma); goto out; } start_pfn = virt_to_phys(m) >> PAGE_SHIFT; valid = !pfn_range_intersects_zones(nid, start_pfn, pages_per_huge_page(m->hstate)); out: if (!valid) hstate_boot_nrinvalid[hstate_index(m->hstate)]++; return valid; } /* * Free a bootmem page that was found to be invalid (intersecting with * multiple zones). * * Since it intersects with multiple zones, we can't just do a free * operation on all pages at once, but instead have to walk all * pages, freeing them one by one. */ static void __init hugetlb_bootmem_free_invalid_page(int nid, struct page *page, struct hstate *h) { unsigned long npages = pages_per_huge_page(h); unsigned long pfn; while (npages--) { pfn = page_to_pfn(page); __init_page_from_nid(pfn, nid); free_reserved_page(page); page++; } } /* * Put bootmem huge pages into the standard lists after mem_map is up. * Note: This only applies to gigantic (order > MAX_PAGE_ORDER) pages. */ static void __init gather_bootmem_prealloc_node(unsigned long nid) { LIST_HEAD(folio_list); struct huge_bootmem_page *m, *tm; struct hstate *h = NULL, *prev_h = NULL; list_for_each_entry_safe(m, tm, &huge_boot_pages[nid], list) { struct page *page = virt_to_page(m); struct folio *folio = (void *)page; h = m->hstate; if (!hugetlb_bootmem_page_zones_valid(nid, m)) { /* * Can't use this page. Initialize the * page structures if that hasn't already * been done, and give them to the page * allocator. */ hugetlb_bootmem_free_invalid_page(nid, page, h); continue; } /* * It is possible to have multiple huge page sizes (hstates) * in this list. If so, process each size separately. */ if (h != prev_h && prev_h != NULL) prep_and_add_bootmem_folios(prev_h, &folio_list); prev_h = h; VM_BUG_ON(!hstate_is_gigantic(h)); WARN_ON(folio_ref_count(folio) != 1); hugetlb_folio_init_vmemmap(folio, h, HUGETLB_VMEMMAP_RESERVE_PAGES); init_new_hugetlb_folio(folio); if (hugetlb_bootmem_page_prehvo(m)) /* * If pre-HVO was done, just set the * flag, the HVO code will then skip * this folio. */ folio_set_hugetlb_vmemmap_optimized(folio); if (hugetlb_bootmem_page_earlycma(m)) folio_set_hugetlb_cma(folio); list_add(&folio->lru, &folio_list); /* * We need to restore the 'stolen' pages to totalram_pages * in order to fix confusing memory reports from free(1) and * other side-effects, like CommitLimit going negative. * * For CMA pages, this is done in init_cma_pageblock * (via hugetlb_bootmem_init_migratetype), so skip it here. */ if (!folio_test_hugetlb_cma(folio)) adjust_managed_page_count(page, pages_per_huge_page(h)); cond_resched(); } prep_and_add_bootmem_folios(h, &folio_list); } static void __init gather_bootmem_prealloc_parallel(unsigned long start, unsigned long end, void *arg) { int nid; for (nid = start; nid < end; nid++) gather_bootmem_prealloc_node(nid); } static void __init gather_bootmem_prealloc(void) { struct padata_mt_job job = { .thread_fn = gather_bootmem_prealloc_parallel, .fn_arg = NULL, .start = 0, .size = nr_node_ids, .align = 1, .min_chunk = 1, .max_threads = num_node_state(N_MEMORY), .numa_aware = true, }; padata_do_multithreaded(&job); } static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid) { unsigned long i; char buf[32]; LIST_HEAD(folio_list); for (i = 0; i < h->max_huge_pages_node[nid]; ++i) { if (hstate_is_gigantic(h)) { if (!alloc_bootmem_huge_page(h, nid)) break; } else { struct folio *folio; gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE; folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, &node_states[N_MEMORY], NULL); if (!folio && !list_empty(&folio_list) && hugetlb_vmemmap_optimizable_size(h)) { prep_and_add_allocated_folios(h, &folio_list); INIT_LIST_HEAD(&folio_list); folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, nid, &node_states[N_MEMORY], NULL); } if (!folio) break; list_add(&folio->lru, &folio_list); } cond_resched(); } if (!list_empty(&folio_list)) prep_and_add_allocated_folios(h, &folio_list); if (i == h->max_huge_pages_node[nid]) return; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %u of page size %s failed node%d. Only allocated %lu hugepages.\n", h->max_huge_pages_node[nid], buf, nid, i); h->max_huge_pages -= (h->max_huge_pages_node[nid] - i); h->max_huge_pages_node[nid] = i; } static bool __init hugetlb_hstate_alloc_pages_specific_nodes(struct hstate *h) { int i; bool node_specific_alloc = false; for_each_online_node(i) { if (h->max_huge_pages_node[i] > 0) { hugetlb_hstate_alloc_pages_onenode(h, i); node_specific_alloc = true; } } return node_specific_alloc; } static void __init hugetlb_hstate_alloc_pages_errcheck(unsigned long allocated, struct hstate *h) { if (allocated < h->max_huge_pages) { char buf[32]; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n", h->max_huge_pages, buf, allocated); h->max_huge_pages = allocated; } } static void __init hugetlb_pages_alloc_boot_node(unsigned long start, unsigned long end, void *arg) { struct hstate *h = (struct hstate *)arg; int i, num = end - start; nodemask_t node_alloc_noretry; LIST_HEAD(folio_list); int next_node = first_online_node; /* Bit mask controlling how hard we retry per-node allocations.*/ nodes_clear(node_alloc_noretry); for (i = 0; i < num; ++i) { struct folio *folio; if (hugetlb_vmemmap_optimizable_size(h) && (si_mem_available() == 0) && !list_empty(&folio_list)) { prep_and_add_allocated_folios(h, &folio_list); INIT_LIST_HEAD(&folio_list); } folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY], &node_alloc_noretry, &next_node); if (!folio) break; list_move(&folio->lru, &folio_list); cond_resched(); } prep_and_add_allocated_folios(h, &folio_list); } static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstate *h) { unsigned long i; for (i = 0; i < h->max_huge_pages; ++i) { if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE)) break; cond_resched(); } return i; } static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h) { struct padata_mt_job job = { .fn_arg = h, .align = 1, .numa_aware = true }; unsigned long jiffies_start; unsigned long jiffies_end; unsigned long remaining; job.thread_fn = hugetlb_pages_alloc_boot_node; /* * job.max_threads is 25% of the available cpu threads by default. * * On large servers with terabytes of memory, huge page allocation * can consume a considerably amount of time. * * Tests below show how long it takes to allocate 1 TiB of memory with 2MiB huge pages. * 2MiB huge pages. Using more threads can significantly improve allocation time. * * +-----------------------+-------+-------+-------+-------+-------+ * | threads | 8 | 16 | 32 | 64 | 128 | * +-----------------------+-------+-------+-------+-------+-------+ * | skylake 144 cpus | 44s | 22s | 16s | 19s | 20s | * | cascade lake 192 cpus | 39s | 20s | 11s | 10s | 9s | * +-----------------------+-------+-------+-------+-------+-------+ */ if (hugepage_allocation_threads == 0) { hugepage_allocation_threads = num_online_cpus() / 4; hugepage_allocation_threads = max(hugepage_allocation_threads, 1); } job.max_threads = hugepage_allocation_threads; jiffies_start = jiffies; do { remaining = h->max_huge_pages - h->nr_huge_pages; job.start = h->nr_huge_pages; job.size = remaining; job.min_chunk = remaining / hugepage_allocation_threads; padata_do_multithreaded(&job); if (h->nr_huge_pages == h->max_huge_pages) break; /* * Retry only if the vmemmap optimization might have been able to free * some memory back to the system. */ if (!hugetlb_vmemmap_optimizable(h)) break; /* Continue if progress was made in last iteration */ } while (remaining != (h->max_huge_pages - h->nr_huge_pages)); jiffies_end = jiffies; pr_info("HugeTLB: allocation took %dms with hugepage_allocation_threads=%ld\n", jiffies_to_msecs(jiffies_end - jiffies_start), hugepage_allocation_threads); return h->nr_huge_pages; } /* * NOTE: this routine is called in different contexts for gigantic and * non-gigantic pages. * - For gigantic pages, this is called early in the boot process and * pages are allocated from memblock allocated or something similar. * Gigantic pages are actually added to pools later with the routine * gather_bootmem_prealloc. * - For non-gigantic pages, this is called later in the boot process after * all of mm is up and functional. Pages are allocated from buddy and * then added to hugetlb pools. */ static void __init hugetlb_hstate_alloc_pages(struct hstate *h) { unsigned long allocated; /* * Skip gigantic hugepages allocation if early CMA * reservations are not available. */ if (hstate_is_gigantic(h) && hugetlb_cma_total_size() && !hugetlb_early_cma(h)) { pr_warn_once("HugeTLB: hugetlb_cma is enabled, skip boot time allocation\n"); return; } if (!h->max_huge_pages) return; /* do node specific alloc */ if (hugetlb_hstate_alloc_pages_specific_nodes(h)) return; /* below will do all node balanced alloc */ if (hstate_is_gigantic(h)) allocated = hugetlb_gigantic_pages_alloc_boot(h); else allocated = hugetlb_pages_alloc_boot(h); hugetlb_hstate_alloc_pages_errcheck(allocated, h); } static void __init hugetlb_init_hstates(void) { struct hstate *h, *h2; for_each_hstate(h) { /* * Always reset to first_memory_node here, even if * next_nid_to_alloc was set before - we can't * reference hugetlb_bootmem_nodes after init, and * first_memory_node is right for all further allocations. */ h->next_nid_to_alloc = first_memory_node; h->next_nid_to_free = first_memory_node; /* oversize hugepages were init'ed in early boot */ if (!hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); /* * Set demote order for each hstate. Note that * h->demote_order is initially 0. * - We can not demote gigantic pages if runtime freeing * is not supported, so skip this. * - If CMA allocation is possible, we can not demote * HUGETLB_PAGE_ORDER or smaller size pages. */ if (hstate_is_gigantic_no_runtime(h)) continue; if (hugetlb_cma_total_size() && h->order <= HUGETLB_PAGE_ORDER) continue; for_each_hstate(h2) { if (h2 == h) continue; if (h2->order < h->order && h2->order > h->demote_order) h->demote_order = h2->order; } } } static void __init report_hugepages(void) { struct hstate *h; unsigned long nrinvalid; for_each_hstate(h) { char buf[32]; nrinvalid = hstate_boot_nrinvalid[hstate_index(h)]; h->max_huge_pages -= nrinvalid; string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32); pr_info("HugeTLB: registered %s page size, pre-allocated %ld pages\n", buf, h->nr_huge_pages); if (nrinvalid) pr_info("HugeTLB: %s page size: %lu invalid page%s discarded\n", buf, nrinvalid, str_plural(nrinvalid)); pr_info("HugeTLB: %d KiB vmemmap can be freed for a %s page\n", hugetlb_vmemmap_optimizable_size(h) / SZ_1K, buf); } } #ifdef CONFIG_HIGHMEM static void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { int i; LIST_HEAD(page_list); lockdep_assert_held(&hugetlb_lock); if (hstate_is_gigantic(h)) return; /* * Collect pages to be freed on a list, and free after dropping lock */ for_each_node_mask(i, *nodes_allowed) { struct folio *folio, *next; struct list_head *freel = &h->hugepage_freelists[i]; list_for_each_entry_safe(folio, next, freel, lru) { if (count >= h->nr_huge_pages) goto out; if (folio_test_highmem(folio)) continue; remove_hugetlb_folio(h, folio, false); list_add(&folio->lru, &page_list); } } out: spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); spin_lock_irq(&hugetlb_lock); } #else static inline void try_to_free_low(struct hstate *h, unsigned long count, nodemask_t *nodes_allowed) { } #endif /* * Increment or decrement surplus_huge_pages. Keep node-specific counters * balanced by operating on them in a round-robin fashion. * Returns 1 if an adjustment was made. */ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed, int delta) { int nr_nodes, node; lockdep_assert_held(&hugetlb_lock); VM_BUG_ON(delta != -1 && delta != 1); if (delta < 0) { for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node]) goto found; } } else { for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) { if (h->surplus_huge_pages_node[node] < h->nr_huge_pages_node[node]) goto found; } } return 0; found: h->surplus_huge_pages += delta; h->surplus_huge_pages_node[node] += delta; return 1; } #define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages) static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid, nodemask_t *nodes_allowed) { unsigned long persistent_free_count; unsigned long min_count; unsigned long allocated; struct folio *folio; LIST_HEAD(page_list); NODEMASK_ALLOC(nodemask_t, node_alloc_noretry, GFP_KERNEL); /* * Bit mask controlling how hard we retry per-node allocations. * If we can not allocate the bit mask, do not attempt to allocate * the requested huge pages. */ if (node_alloc_noretry) nodes_clear(*node_alloc_noretry); else return -ENOMEM; /* * resize_lock mutex prevents concurrent adjustments to number of * pages in hstate via the proc/sysfs interfaces. */ mutex_lock(&h->resize_lock); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); /* * Check for a node specific request. * Changing node specific huge page count may require a corresponding * change to the global count. In any case, the passed node mask * (nodes_allowed) will restrict alloc/free to the specified node. */ if (nid != NUMA_NO_NODE) { unsigned long old_count = count; count += persistent_huge_pages(h) - (h->nr_huge_pages_node[nid] - h->surplus_huge_pages_node[nid]); /* * User may have specified a large count value which caused the * above calculation to overflow. In this case, they wanted * to allocate as many huge pages as possible. Set count to * largest possible value to align with their intention. */ if (count < old_count) count = ULONG_MAX; } /* * Gigantic pages runtime allocation depend on the capability for large * page range allocation. * If the system does not provide this feature, return an error when * the user tries to allocate gigantic pages but let the user free the * boottime allocated gigantic pages. */ if (hstate_is_gigantic(h) && !IS_ENABLED(CONFIG_CONTIG_ALLOC)) { if (count > persistent_huge_pages(h)) { spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return -EINVAL; } /* Fall through to decrease pool */ } /* * Increase the pool size * First take pages out of surplus state. Then make up the * remaining difference by allocating fresh huge pages. * * We might race with alloc_surplus_hugetlb_folio() here and be unable * to convert a surplus huge page to a normal huge page. That is * not critical, though, it just means the overall size of the * pool might be one hugepage larger than it needs to be, but * within all the constraints specified by the sysctls. */ while (h->surplus_huge_pages && count > persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, -1)) break; } allocated = 0; while (count > (persistent_huge_pages(h) + allocated)) { /* * If this allocation races such that we no longer need the * page, free_huge_folio will handle it by freeing the page * and reducing the surplus. */ spin_unlock_irq(&hugetlb_lock); /* yield cpu to avoid soft lockup */ cond_resched(); folio = alloc_pool_huge_folio(h, nodes_allowed, node_alloc_noretry, &h->next_nid_to_alloc); if (!folio) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } list_add(&folio->lru, &page_list); allocated++; /* Bail for signals. Probably ctrl-c from user */ if (signal_pending(current)) { prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); goto out; } spin_lock_irq(&hugetlb_lock); } /* Add allocated pages to the pool */ if (!list_empty(&page_list)) { spin_unlock_irq(&hugetlb_lock); prep_and_add_allocated_folios(h, &page_list); spin_lock_irq(&hugetlb_lock); } /* * Decrease the pool size * First return free pages to the buddy allocator (being careful * to keep enough around to satisfy reservations). Then place * pages into surplus state as needed so the pool will shrink * to the desired size as pages become free. * * By placing pages into the surplus state independent of the * overcommit value, we are allowing the surplus pool size to * exceed overcommit. There are few sane options here. Since * alloc_surplus_hugetlb_folio() is checking the global counter, * though, we'll note that we're not allowed to exceed surplus * and won't grow the pool anywhere else. Not until one of the * sysctls are changed, or the surplus pages go out of use. * * min_count is the expected number of persistent pages, we * shouldn't calculate min_count by using * resv_huge_pages + persistent_huge_pages() - free_huge_pages, * because there may exist free surplus huge pages, and this will * lead to subtracting twice. Free surplus huge pages come from HVO * failing to restore vmemmap, see comments in the callers of * hugetlb_vmemmap_restore_folio(). Thus, we should calculate * persistent free count first. */ persistent_free_count = h->free_huge_pages; if (h->free_huge_pages > persistent_huge_pages(h)) { if (h->free_huge_pages > h->surplus_huge_pages) persistent_free_count -= h->surplus_huge_pages; else persistent_free_count = 0; } min_count = h->resv_huge_pages + persistent_huge_pages(h) - persistent_free_count; min_count = max(count, min_count); try_to_free_low(h, min_count, nodes_allowed); /* * Collect pages to be removed on list without dropping lock */ while (min_count < persistent_huge_pages(h)) { folio = remove_pool_hugetlb_folio(h, nodes_allowed, 0); if (!folio) break; list_add(&folio->lru, &page_list); } /* free the pages after dropping lock */ spin_unlock_irq(&hugetlb_lock); update_and_free_pages_bulk(h, &page_list); flush_free_hpage_work(h); spin_lock_irq(&hugetlb_lock); while (count < persistent_huge_pages(h)) { if (!adjust_pool_surplus(h, nodes_allowed, 1)) break; } out: h->max_huge_pages = persistent_huge_pages(h); spin_unlock_irq(&hugetlb_lock); mutex_unlock(&h->resize_lock); NODEMASK_FREE(node_alloc_noretry); return 0; } static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst, struct list_head *src_list) { long rc; struct folio *folio, *next; LIST_HEAD(dst_list); LIST_HEAD(ret_list); rc = hugetlb_vmemmap_restore_folios(src, src_list, &ret_list); list_splice_init(&ret_list, src_list); /* * Taking target hstate mutex synchronizes with set_max_huge_pages. * Without the mutex, pages added to target hstate could be marked * as surplus. * * Note that we already hold src->resize_lock. To prevent deadlock, * use the convention of always taking larger size hstate mutex first. */ mutex_lock(&dst->resize_lock); list_for_each_entry_safe(folio, next, src_list, lru) { int i; bool cma; if (folio_test_hugetlb_vmemmap_optimized(folio)) continue; cma = folio_test_hugetlb_cma(folio); list_del(&folio->lru); split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst)); pgalloc_tag_split(folio, huge_page_order(src), huge_page_order(dst)); for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) { struct page *page = folio_page(folio, i); /* Careful: see __split_huge_page_tail() */ struct folio *new_folio = (struct folio *)page; clear_compound_head(page); prep_compound_page(page, dst->order); new_folio->mapping = NULL; init_new_hugetlb_folio(new_folio); /* Copy the CMA flag so that it is freed correctly */ if (cma) folio_set_hugetlb_cma(new_folio); list_add(&new_folio->lru, &dst_list); } } prep_and_add_allocated_folios(dst, &dst_list); mutex_unlock(&dst->resize_lock); return rc; } long demote_pool_huge_page(struct hstate *src, nodemask_t *nodes_allowed, unsigned long nr_to_demote) __must_hold(&hugetlb_lock) { int nr_nodes, node; struct hstate *dst; long rc = 0; long nr_demoted = 0; lockdep_assert_held(&hugetlb_lock); /* We should never get here if no demote order */ if (!src->demote_order) { pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n"); return -EINVAL; /* internal error */ } dst = size_to_hstate(PAGE_SIZE << src->demote_order); for_each_node_mask_to_free(src, nr_nodes, node, nodes_allowed) { LIST_HEAD(list); struct folio *folio, *next; list_for_each_entry_safe(folio, next, &src->hugepage_freelists[node], lru) { if (folio_test_hwpoison(folio)) continue; remove_hugetlb_folio(src, folio, false); list_add(&folio->lru, &list); if (++nr_demoted == nr_to_demote) break; } spin_unlock_irq(&hugetlb_lock); rc = demote_free_hugetlb_folios(src, dst, &list); spin_lock_irq(&hugetlb_lock); list_for_each_entry_safe(folio, next, &list, lru) { list_del(&folio->lru); add_hugetlb_folio(src, folio, false); nr_demoted--; } if (rc < 0 || nr_demoted == nr_to_demote) break; } /* * Not absolutely necessary, but for consistency update max_huge_pages * based on pool changes for the demoted page. */ src->max_huge_pages -= nr_demoted; dst->max_huge_pages += nr_demoted << (huge_page_order(src) - huge_page_order(dst)); if (rc < 0) return rc; if (nr_demoted) return nr_demoted; /* * Only way to get here is if all pages on free lists are poisoned. * Return -EBUSY so that caller will not retry. */ return -EBUSY; } ssize_t __nr_hugepages_store_common(bool obey_mempolicy, struct hstate *h, int nid, unsigned long count, size_t len) { int err; nodemask_t nodes_allowed, *n_mask; if (hstate_is_gigantic_no_runtime(h)) return -EINVAL; if (nid == NUMA_NO_NODE) { /* * global hstate attribute */ if (!(obey_mempolicy && init_nodemask_of_mempolicy(&nodes_allowed))) n_mask = &node_states[N_MEMORY]; else n_mask = &nodes_allowed; } else { /* * Node specific request. count adjustment happens in * set_max_huge_pages() after acquiring hugetlb_lock. */ init_nodemask_of_node(&nodes_allowed, nid); n_mask = &nodes_allowed; } err = set_max_huge_pages(h, count, nid, n_mask); return err ? err : len; } static int __init hugetlb_init(void) { int i; BUILD_BUG_ON(sizeof_field(struct page, private) * BITS_PER_BYTE < __NR_HPAGEFLAGS); BUILD_BUG_ON_INVALID(HUGETLB_PAGE_ORDER > MAX_FOLIO_ORDER); if (!hugepages_supported()) { if (hugetlb_max_hstate || default_hstate_max_huge_pages) pr_warn("HugeTLB: huge pages not supported, ignoring associated command-line parameters\n"); return 0; } /* * Make sure HPAGE_SIZE (HUGETLB_PAGE_ORDER) hstate exists. Some * architectures depend on setup being done here. */ hugetlb_add_hstate(HUGETLB_PAGE_ORDER); if (!parsed_default_hugepagesz) { /* * If we did not parse a default huge page size, set * default_hstate_idx to HPAGE_SIZE hstate. And, if the * number of huge pages for this default size was implicitly * specified, set that here as well. * Note that the implicit setting will overwrite an explicit * setting. A warning will be printed in this case. */ default_hstate_idx = hstate_index(size_to_hstate(HPAGE_SIZE)); if (default_hstate_max_huge_pages) { if (default_hstate.max_huge_pages) { char buf[32]; string_get_size(huge_page_size(&default_hstate), 1, STRING_UNITS_2, buf, 32); pr_warn("HugeTLB: Ignoring hugepages=%lu associated with %s page size\n", default_hstate.max_huge_pages, buf); pr_warn("HugeTLB: Using hugepages=%lu for number of default huge pages\n", default_hstate_max_huge_pages); } default_hstate.max_huge_pages = default_hstate_max_huge_pages; for_each_online_node(i) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; } } hugetlb_init_hstates(); gather_bootmem_prealloc(); report_hugepages(); hugetlb_sysfs_init(); hugetlb_cgroup_file_init(); hugetlb_sysctl_init(); #ifdef CONFIG_SMP num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus()); #else num_fault_mutexes = 1; #endif hugetlb_fault_mutex_table = kmalloc_objs(struct mutex, num_fault_mutexes); BUG_ON(!hugetlb_fault_mutex_table); for (i = 0; i < num_fault_mutexes; i++) mutex_init(&hugetlb_fault_mutex_table[i]); return 0; } subsys_initcall(hugetlb_init); /* Overwritten by architectures with more huge page sizes */ bool __init __attribute((weak)) arch_hugetlb_valid_size(unsigned long size) { return size == HPAGE_SIZE; } void __init hugetlb_add_hstate(unsigned int order) { struct hstate *h; unsigned long i; if (size_to_hstate(PAGE_SIZE << order)) { return; } BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE); BUG_ON(order < order_base_2(__NR_USED_SUBPAGE)); WARN_ON(order > MAX_FOLIO_ORDER); h = &hstates[hugetlb_max_hstate++]; __mutex_init(&h->resize_lock, "resize mutex", &h->resize_key); h->order = order; h->mask = ~(huge_page_size(h) - 1); for (i = 0; i < MAX_NUMNODES; ++i) INIT_LIST_HEAD(&h->hugepage_freelists[i]); INIT_LIST_HEAD(&h->hugepage_activelist); snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB", huge_page_size(h)/SZ_1K); parsed_hstate = h; } bool __init __weak hugetlb_node_alloc_supported(void) { return true; } static void __init hugepages_clear_pages_in_node(void) { if (!hugetlb_max_hstate) { default_hstate_max_huge_pages = 0; memset(default_hugepages_in_node, 0, sizeof(default_hugepages_in_node)); } else { parsed_hstate->max_huge_pages = 0; memset(parsed_hstate->max_huge_pages_node, 0, sizeof(parsed_hstate->max_huge_pages_node)); } } static __init int hugetlb_add_param(char *s, int (*setup)(char *)) { size_t len; char *p; if (!s) return -EINVAL; if (hugetlb_param_index >= HUGE_MAX_CMDLINE_ARGS) return -EINVAL; len = strlen(s) + 1; if (len + hstate_cmdline_index > sizeof(hstate_cmdline_buf)) return -EINVAL; p = &hstate_cmdline_buf[hstate_cmdline_index]; memcpy(p, s, len); hstate_cmdline_index += len; hugetlb_params[hugetlb_param_index].val = p; hugetlb_params[hugetlb_param_index].setup = setup; hugetlb_param_index++; return 0; } static __init void hugetlb_parse_params(void) { int i; struct hugetlb_cmdline *hcp; for (i = 0; i < hugetlb_param_index; i++) { hcp = &hugetlb_params[i]; hcp->setup(hcp->val); } hugetlb_cma_validate_params(); } /* * hugepages command line processing * hugepages normally follows a valid hugepagsz or default_hugepagsz * specification. If not, ignore the hugepages value. hugepages can also * be the first huge page command line option in which case it implicitly * specifies the number of huge pages for the default size. */ static int __init hugepages_setup(char *s) { unsigned long *mhp; static unsigned long *last_mhp; int node = NUMA_NO_NODE; int count; unsigned long tmp; char *p = s; if (!hugepages_supported()) { pr_warn("HugeTLB: hugepages unsupported, ignoring hugepages=%s cmdline\n", s); return 0; } if (!parsed_valid_hugepagesz) { pr_warn("HugeTLB: hugepages=%s does not follow a valid hugepagesz, ignoring\n", s); parsed_valid_hugepagesz = true; return -EINVAL; } /* * !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter * yet, so this hugepages= parameter goes to the "default hstate". * Otherwise, it goes with the previously parsed hugepagesz or * default_hugepagesz. */ else if (!hugetlb_max_hstate) mhp = &default_hstate_max_huge_pages; else mhp = &parsed_hstate->max_huge_pages; if (mhp == last_mhp) { pr_warn("HugeTLB: hugepages= specified twice without interleaving hugepagesz=, ignoring hugepages=%s\n", s); return 1; } while (*p) { count = 0; if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; /* Parameter is node format */ if (p[count] == ':') { if (!hugetlb_node_alloc_supported()) { pr_warn("HugeTLB: architecture can't support node specific alloc, ignoring!\n"); return 1; } if (tmp >= MAX_NUMNODES || !node_online(tmp)) goto invalid; node = array_index_nospec(tmp, MAX_NUMNODES); p += count + 1; /* Parse hugepages */ if (sscanf(p, "%lu%n", &tmp, &count) != 1) goto invalid; if (!hugetlb_max_hstate) default_hugepages_in_node[node] = tmp; else parsed_hstate->max_huge_pages_node[node] = tmp; *mhp += tmp; /* Go to parse next node*/ if (p[count] == ',') p += count + 1; else break; } else { if (p != s) goto invalid; *mhp = tmp; break; } } last_mhp = mhp; return 0; invalid: pr_warn("HugeTLB: Invalid hugepages parameter %s\n", p); hugepages_clear_pages_in_node(); return -EINVAL; } hugetlb_early_param("hugepages", hugepages_setup); /* * hugepagesz command line processing * A specific huge page size can only be specified once with hugepagesz. * hugepagesz is followed by hugepages on the command line. The global * variable 'parsed_valid_hugepagesz' is used to determine if prior * hugepagesz argument was valid. */ static int __init hugepagesz_setup(char *s) { unsigned long size; struct hstate *h; if (!hugepages_supported()) { pr_warn("HugeTLB: hugepages unsupported, ignoring hugepagesz=%s cmdline\n", s); return 0; } parsed_valid_hugepagesz = false; size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported hugepagesz=%s\n", s); return -EINVAL; } h = size_to_hstate(size); if (h) { /* * hstate for this size already exists. This is normally * an error, but is allowed if the existing hstate is the * default hstate. More specifically, it is only allowed if * the number of huge pages for the default hstate was not * previously specified. */ if (!parsed_default_hugepagesz || h != &default_hstate || default_hstate.max_huge_pages) { pr_warn("HugeTLB: hugepagesz=%s specified twice, ignoring\n", s); return -EINVAL; } /* * No need to call hugetlb_add_hstate() as hstate already * exists. But, do set parsed_hstate so that a following * hugepages= parameter will be applied to this hstate. */ parsed_hstate = h; parsed_valid_hugepagesz = true; return 0; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; return 0; } hugetlb_early_param("hugepagesz", hugepagesz_setup); /* * default_hugepagesz command line input * Only one instance of default_hugepagesz allowed on command line. */ static int __init default_hugepagesz_setup(char *s) { unsigned long size; int i; if (!hugepages_supported()) { pr_warn("HugeTLB: hugepages unsupported, ignoring default_hugepagesz=%s cmdline\n", s); return 0; } parsed_valid_hugepagesz = false; if (parsed_default_hugepagesz) { pr_err("HugeTLB: default_hugepagesz previously specified, ignoring %s\n", s); return -EINVAL; } size = (unsigned long)memparse(s, NULL); if (!arch_hugetlb_valid_size(size)) { pr_err("HugeTLB: unsupported default_hugepagesz=%s\n", s); return -EINVAL; } hugetlb_add_hstate(ilog2(size) - PAGE_SHIFT); parsed_valid_hugepagesz = true; parsed_default_hugepagesz = true; default_hstate_idx = hstate_index(size_to_hstate(size)); /* * The number of default huge pages (for this size) could have been * specified as the first hugetlb parameter: hugepages=X. If so, * then default_hstate_max_huge_pages is set. If the default huge * page size is gigantic (> MAX_PAGE_ORDER), then the pages must be * allocated here from bootmem allocator. */ if (default_hstate_max_huge_pages) { default_hstate.max_huge_pages = default_hstate_max_huge_pages; /* * Since this is an early parameter, we can't check * NUMA node state yet, so loop through MAX_NUMNODES. */ for (i = 0; i < MAX_NUMNODES; i++) { if (default_hugepages_in_node[i] != 0) default_hstate.max_huge_pages_node[i] = default_hugepages_in_node[i]; } default_hstate_max_huge_pages = 0; } return 0; } hugetlb_early_param("default_hugepagesz", default_hugepagesz_setup); void __init hugetlb_bootmem_set_nodes(void) { int i, nid; unsigned long start_pfn, end_pfn; if (!nodes_empty(hugetlb_bootmem_nodes)) return; for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { if (end_pfn > start_pfn) node_set(nid, hugetlb_bootmem_nodes); } } void __init hugetlb_bootmem_alloc(void) { struct hstate *h; int i; hugetlb_bootmem_set_nodes(); for (i = 0; i < MAX_NUMNODES; i++) INIT_LIST_HEAD(&huge_boot_pages[i]); hugetlb_parse_params(); for_each_hstate(h) { h->next_nid_to_alloc = first_online_node; if (hstate_is_gigantic(h)) hugetlb_hstate_alloc_pages(h); } } /* * hugepage_alloc_threads command line parsing. * * When set, use this specific number of threads for the boot * allocation of hugepages. */ static int __init hugepage_alloc_threads_setup(char *s) { unsigned long allocation_threads; if (kstrtoul(s, 0, &allocation_threads) != 0) return 1; if (allocation_threads == 0) return 1; hugepage_allocation_threads = allocation_threads; return 1; } __setup("hugepage_alloc_threads=", hugepage_alloc_threads_setup); static unsigned int allowed_mems_nr(struct hstate *h) { int node; unsigned int nr = 0; nodemask_t *mbind_nodemask; unsigned int *array = h->free_huge_pages_node; gfp_t gfp_mask = htlb_alloc_mask(h); mbind_nodemask = policy_mbind_nodemask(gfp_mask); for_each_node_mask(node, cpuset_current_mems_allowed) { if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) nr += array[node]; } return nr; } void hugetlb_report_meminfo(struct seq_file *m) { struct hstate *h; unsigned long total = 0; if (!hugepages_supported()) return; for_each_hstate(h) { unsigned long count = h->nr_huge_pages; total += huge_page_size(h) * count; if (h == &default_hstate) seq_printf(m, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" "HugePages_Rsvd: %5lu\n" "HugePages_Surp: %5lu\n" "Hugepagesize: %8lu kB\n", count, h->free_huge_pages, h->resv_huge_pages, h->surplus_huge_pages, huge_page_size(h) / SZ_1K); } seq_printf(m, "Hugetlb: %8lu kB\n", total / SZ_1K); } int hugetlb_report_node_meminfo(char *buf, int len, int nid) { struct hstate *h = &default_hstate; if (!hugepages_supported()) return 0; return sysfs_emit_at(buf, len, "Node %d HugePages_Total: %5u\n" "Node %d HugePages_Free: %5u\n" "Node %d HugePages_Surp: %5u\n", nid, h->nr_huge_pages_node[nid], nid, h->free_huge_pages_node[nid], nid, h->surplus_huge_pages_node[nid]); } void hugetlb_show_meminfo_node(int nid) { struct hstate *h; if (!hugepages_supported()) return; for_each_hstate(h) printk("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", nid, h->nr_huge_pages_node[nid], h->free_huge_pages_node[nid], h->surplus_huge_pages_node[nid], huge_page_size(h) / SZ_1K); } void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm) { seq_printf(m, "HugetlbPages:\t%8lu kB\n", K(atomic_long_read(&mm->hugetlb_usage))); } /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { struct hstate *h; unsigned long nr_total_pages = 0; for_each_hstate(h) nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h); return nr_total_pages; } static int hugetlb_acct_memory(struct hstate *h, long delta) { int ret = -ENOMEM; if (!delta) return 0; spin_lock_irq(&hugetlb_lock); /* * When cpuset is configured, it breaks the strict hugetlb page * reservation as the accounting is done on a global variable. Such * reservation is completely rubbish in the presence of cpuset because * the reservation is not checked against page availability for the * current cpuset. Application can still potentially OOM'ed by kernel * with lack of free htlb page in cpuset that the task is in. * Attempt to enforce strict accounting with cpuset is almost * impossible (or too ugly) because cpuset is too fluid that * task or memory node can be dynamically moved between cpusets. * * The change of semantics for shared hugetlb mapping with cpuset is * undesirable. However, in order to preserve some of the semantics, * we fall back to check against current free page availability as * a best attempt and hopefully to minimize the impact of changing * semantics that cpuset has. * * Apart from cpuset, we also have memory policy mechanism that * also determines from which node the kernel will allocate memory * in a NUMA system. So similar to cpuset, we also should consider * the memory policy of the current task. Similar to the description * above. */ if (delta > 0) { if (gather_surplus_pages(h, delta) < 0) goto out; if (delta > allowed_mems_nr(h)) { return_unused_surplus_pages(h, delta); goto out; } } ret = 0; if (delta < 0) return_unused_surplus_pages(h, (unsigned long) -delta); out: spin_unlock_irq(&hugetlb_lock); return ret; } static void hugetlb_vm_op_open(struct vm_area_struct *vma) { struct resv_map *resv = vma_resv_map(vma); /* * HPAGE_RESV_OWNER indicates a private mapping. * This new VMA should share its siblings reservation map if present. * The VMA will only ever have a valid reservation map pointer where * it is being copied for another still existing VMA. As that VMA * has a reference to the reservation map it cannot disappear until * after this open call completes. It is therefore safe to take a * new reference here without additional locking. */ if (resv && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { resv_map_dup_hugetlb_cgroup_uncharge_info(resv); kref_get(&resv->refs); } /* * vma_lock structure for sharable mappings is vma specific. * Clear old pointer (if copied via vm_area_dup) and allocate * new structure. Before clearing, make sure vma_lock is not * for this vma. */ if (vma->vm_flags & VM_MAYSHARE) { struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; if (vma_lock) { if (vma_lock->vma != vma) { vma->vm_private_data = NULL; hugetlb_vma_lock_alloc(vma); } else { pr_warn("HugeTLB: vma_lock already exists in %s.\n", __func__); } } else { hugetlb_vma_lock_alloc(vma); } } } static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *resv; struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve, start, end; long gbl_reserve; hugetlb_vma_lock_free(vma); resv = vma_resv_map(vma); if (!resv || !is_vma_resv_set(vma, HPAGE_RESV_OWNER)) return; start = vma_hugecache_offset(h, vma, vma->vm_start); end = vma_hugecache_offset(h, vma, vma->vm_end); reserve = (end - start) - region_count(resv, start, end); hugetlb_cgroup_uncharge_counter(resv, start, end); if (reserve) { /* * Decrement reserve counts. The global reserve count may be * adjusted if the subpool has a minimum size. */ gbl_reserve = hugepage_subpool_put_pages(spool, reserve); hugetlb_acct_memory(h, -gbl_reserve); } kref_put(&resv->refs, resv_map_release); } static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; return 0; } void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) { /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. * This function is called in the middle of a VMA split operation, with * MM, VMA and rmap all write-locked to prevent concurrent page table * walks (except hardware and gup_fast()). */ vma_assert_write_locked(vma); i_mmap_assert_write_locked(vma->vm_file->f_mapping); if (addr & ~PUD_MASK) { unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; if (floor >= vma->vm_start && ceil <= vma->vm_end) { /* * Locking: * Use take_locks=false here. * The file rmap lock is already held. * The hugetlb VMA lock can't be taken when we already * hold the file rmap lock, and we don't need it because * its purpose is to synchronize against concurrent page * table walks, which are not possible thanks to the * locks held by our caller. */ hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false); } } } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) { return huge_page_size(hstate_vma(vma)); } /* * We cannot handle pagefaults against hugetlb pages at all. They cause * handle_mm_fault() to try to instantiate regular-sized pages in the * hugepage VMA. do_page_fault() is supposed to trap this, so BUG is we get * this far. */ static vm_fault_t hugetlb_vm_op_fault(struct vm_fault *vmf) { BUG(); return 0; } #ifdef CONFIG_USERFAULTFD static bool hugetlb_can_userfault(struct vm_area_struct *vma, vm_flags_t vm_flags) { return true; } static const struct vm_uffd_ops hugetlb_uffd_ops = { .can_userfault = hugetlb_can_userfault, }; #endif /* * When a new function is introduced to vm_operations_struct and added * to hugetlb_vm_ops, please consider adding the function to shm_vm_ops. * This is because under System V memory model, mappings created via * shmget/shmat with "huge page" specified are backed by hugetlbfs files, * their original vm_ops are overwritten with shm_vm_ops. */ const struct vm_operations_struct hugetlb_vm_ops = { .fault = hugetlb_vm_op_fault, .open = hugetlb_vm_op_open, .close = hugetlb_vm_op_close, .may_split = hugetlb_vm_op_split, .pagesize = hugetlb_vm_op_pagesize, #ifdef CONFIG_USERFAULTFD .uffd_ops = &hugetlb_uffd_ops, #endif }; static pte_t make_huge_pte(struct vm_area_struct *vma, struct folio *folio, bool try_mkwrite) { pte_t entry = folio_mk_pte(folio, vma->vm_page_prot); unsigned int shift = huge_page_shift(hstate_vma(vma)); if (try_mkwrite && (vma->vm_flags & VM_WRITE)) { entry = pte_mkwrite_novma(pte_mkdirty(entry)); } else { entry = pte_wrprotect(entry); } entry = pte_mkyoung(entry); entry = arch_make_huge_pte(entry, shift, vma->vm_flags); return entry; } static void set_huge_ptep_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t entry; entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(vma->vm_mm, address, ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); } static void set_huge_ptep_maybe_writable(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { if (vma->vm_flags & VM_WRITE) set_huge_ptep_writable(vma, address, ptep); } static void hugetlb_install_folio(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr, struct folio *new_folio, pte_t old, unsigned long sz) { pte_t newpte = make_huge_pte(vma, new_folio, true); __folio_mark_uptodate(new_folio); hugetlb_add_new_anon_rmap(new_folio, vma, addr); if (userfaultfd_wp(vma) && huge_pte_uffd_wp(old)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(vma->vm_mm, addr, ptep, newpte, sz); hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm); folio_set_hugetlb_migratable(new_folio); } int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { pte_t *src_pte, *dst_pte, entry; struct folio *pte_folio; unsigned long addr; bool cow = is_cow_mapping(src_vma->vm_flags); struct hstate *h = hstate_vma(src_vma); unsigned long sz = huge_page_size(h); unsigned long npages = pages_per_huge_page(h); struct mmu_notifier_range range; unsigned long last_addr_mask; softleaf_t softleaf; int ret = 0; if (cow) { mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, src, src_vma->vm_start, src_vma->vm_end); mmu_notifier_invalidate_range_start(&range); vma_assert_write_locked(src_vma); raw_write_seqcount_begin(&src->write_protect_seq); } else { /* * For shared mappings the vma lock must be held before * calling hugetlb_walk() in the src vma. Otherwise, the * returned ptep could go away if part of a shared pmd and * another thread calls huge_pmd_unshare. */ hugetlb_vma_lock_read(src_vma); } last_addr_mask = hugetlb_mask_last_page(h); for (addr = src_vma->vm_start; addr < src_vma->vm_end; addr += sz) { spinlock_t *src_ptl, *dst_ptl; src_pte = hugetlb_walk(src_vma, addr, sz); if (!src_pte) { addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(dst, dst_vma, addr, sz); if (!dst_pte) { ret = -ENOMEM; break; } #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING /* If the pagetables are shared, there is nothing to do */ if (ptdesc_pmd_is_shared(virt_to_ptdesc(dst_pte))) { addr |= last_addr_mask; continue; } #endif dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); again: if (huge_pte_none(entry)) { /* Skip if src entry none. */ goto next; } softleaf = softleaf_from_pte(entry); if (unlikely(softleaf_is_hwpoison(softleaf))) { if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(softleaf_is_migration(softleaf))) { bool uffd_wp = pte_swp_uffd_wp(entry); if (!softleaf_is_migration_read(softleaf) && cow) { /* * COW mappings require pages in both * parent and child to be set to read. */ softleaf = make_readable_migration_entry( swp_offset(softleaf)); entry = swp_entry_to_pte(softleaf); if (userfaultfd_wp(src_vma) && uffd_wp) entry = pte_swp_mkuffd_wp(entry); set_huge_pte_at(src, addr, src_pte, entry, sz); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); } else if (unlikely(pte_is_marker(entry))) { const pte_marker marker = copy_pte_marker(softleaf, dst_vma); if (marker) set_huge_pte_at(dst, addr, dst_pte, make_pte_marker(marker), sz); } else { entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); pte_folio = page_folio(pte_page(entry)); folio_get(pte_folio); /* * Failing to duplicate the anon rmap is a rare case * where we see pinned hugetlb pages while they're * prone to COW. We need to do the COW earlier during * fork. * * When pre-allocating the page or copying data, we * need to be without the pgtable locks since we could * sleep during the process. */ if (!folio_test_anon(pte_folio)) { hugetlb_add_file_rmap(pte_folio); } else if (hugetlb_try_dup_anon_rmap(pte_folio, src_vma)) { pte_t src_pte_old = entry; struct folio *new_folio; spin_unlock(src_ptl); spin_unlock(dst_ptl); /* Do not use reserve as it's private owned */ new_folio = alloc_hugetlb_folio(dst_vma, addr, false); if (IS_ERR(new_folio)) { folio_put(pte_folio); ret = PTR_ERR(new_folio); break; } ret = copy_user_large_folio(new_folio, pte_folio, addr, dst_vma); folio_put(pte_folio); if (ret) { folio_put(new_folio); break; } /* Install the new hugetlb folio if src pte stable */ dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_vma->vm_mm, addr, src_pte); if (!pte_same(src_pte_old, entry)) { restore_reserve_on_error(h, dst_vma, addr, new_folio); folio_put(new_folio); /* huge_ptep of dst_pte won't change as in child */ goto again; } hugetlb_install_folio(dst_vma, dst_pte, addr, new_folio, src_pte_old, sz); goto next; } if (cow) { /* * No need to notify as we are downgrading page * table protection not changing it to point * to a new page. * * See Documentation/mm/mmu_notifier.rst */ huge_ptep_set_wrprotect(src, addr, src_pte); entry = huge_pte_wrprotect(entry); } if (!userfaultfd_wp(dst_vma)) entry = huge_pte_clear_uffd_wp(entry); set_huge_pte_at(dst, addr, dst_pte, entry, sz); hugetlb_count_add(npages, dst); } next: spin_unlock(src_ptl); spin_unlock(dst_ptl); } if (cow) { raw_write_seqcount_end(&src->write_protect_seq); mmu_notifier_invalidate_range_end(&range); } else { hugetlb_vma_unlock_read(src_vma); } return ret; } static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte, unsigned long sz) { bool need_clear_uffd_wp = vma_has_uffd_without_event_remap(vma); struct hstate *h = hstate_vma(vma); struct mm_struct *mm = vma->vm_mm; spinlock_t *src_ptl, *dst_ptl; pte_t pte; dst_ptl = huge_pte_lock(h, mm, dst_pte); src_ptl = huge_pte_lockptr(h, mm, src_pte); /* * We don't have to worry about the ordering of src and dst ptlocks * because exclusive mmap_lock (or the i_mmap_lock) prevents deadlock. */ if (src_ptl != dst_ptl) spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); pte = huge_ptep_get_and_clear(mm, old_addr, src_pte, sz); if (need_clear_uffd_wp && pte_is_uffd_wp_marker(pte)) { huge_pte_clear(mm, new_addr, dst_pte, sz); } else { if (need_clear_uffd_wp) { if (pte_present(pte)) pte = huge_pte_clear_uffd_wp(pte); else pte = pte_swp_clear_uffd_wp(pte); } set_huge_pte_at(mm, new_addr, dst_pte, pte, sz); } if (src_ptl != dst_ptl) spin_unlock(src_ptl); spin_unlock(dst_ptl); } int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { struct hstate *h = hstate_vma(vma); struct address_space *mapping = vma->vm_file->f_mapping; unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; unsigned long old_end = old_addr + len; unsigned long last_addr_mask; pte_t *src_pte, *dst_pte; struct mmu_notifier_range range; struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, old_addr, old_end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* * In case of shared PMDs, we should cover the maximum possible * range. */ flush_cache_range(vma, range.start, range.end); tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); last_addr_mask = hugetlb_mask_last_page(h); /* Prevent race with file truncation */ hugetlb_vma_lock_write(vma); i_mmap_lock_write(mapping); for (; old_addr < old_end; old_addr += sz, new_addr += sz) { src_pte = hugetlb_walk(vma, old_addr, sz); if (!src_pte) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } if (huge_pte_none(huge_ptep_get(mm, old_addr, src_pte))) continue; if (huge_pmd_unshare(&tlb, vma, old_addr, src_pte)) { old_addr |= last_addr_mask; new_addr |= last_addr_mask; continue; } dst_pte = huge_pte_alloc(mm, new_vma, new_addr, sz); if (!dst_pte) break; move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte, sz); tlb_remove_huge_tlb_entry(h, &tlb, src_pte, old_addr); } tlb_flush_mmu_tlbonly(&tlb); huge_pmd_unshare_flush(&tlb, vma); mmu_notifier_invalidate_range_end(&range); i_mmap_unlock_write(mapping); hugetlb_vma_unlock_write(vma); tlb_finish_mmu(&tlb); return len + old_addr - old_end; } void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct folio *folio, zap_flags_t zap_flags) { struct mm_struct *mm = vma->vm_mm; const bool folio_provided = !!folio; unsigned long address; pte_t *ptep; pte_t pte; spinlock_t *ptl; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); bool adjust_reservation; unsigned long last_addr_mask; WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); BUG_ON(end & ~huge_page_mask(h)); /* * This is a hugetlb vma, all the pte entries should point * to huge page. */ tlb_change_page_size(tlb, sz); tlb_start_vma(tlb, vma); last_addr_mask = hugetlb_mask_last_page(h); address = start; for (; address < end; address += sz) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) { address |= last_addr_mask; continue; } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(tlb, vma, address, ptep)) { spin_unlock(ptl); address |= last_addr_mask; continue; } pte = huge_ptep_get(mm, address, ptep); if (huge_pte_none(pte)) { spin_unlock(ptl); continue; } /* * Migrating hugepage or HWPoisoned hugepage is already * unmapped and its refcount is dropped, so just clear pte here. */ if (unlikely(!pte_present(pte))) { /* * If the pte was wr-protected by uffd-wp in any of the * swap forms, meanwhile the caller does not want to * drop the uffd-wp bit in this zap, then replace the * pte with a marker. */ if (pte_swp_uffd_wp_any(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); else huge_pte_clear(mm, address, ptep, sz); spin_unlock(ptl); continue; } /* * If a folio is supplied, it is because a specific * folio is being unmapped, not a range. Ensure the folio we * are about to unmap is the actual folio of interest. */ if (folio_provided) { if (folio != page_folio(pte_page(pte))) { spin_unlock(ptl); continue; } /* * Mark the VMA as having unmapped its page so that * future faults in this VMA will fail rather than * looking like data was lost */ set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED); } else { folio = page_folio(pte_page(pte)); } pte = huge_ptep_get_and_clear(mm, address, ptep, sz); tlb_remove_huge_tlb_entry(h, tlb, ptep, address); if (huge_pte_dirty(pte)) folio_mark_dirty(folio); /* Leave a uffd-wp pte marker if needed */ if (huge_pte_uffd_wp(pte) && !(zap_flags & ZAP_FLAG_DROP_MARKER)) set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), sz); hugetlb_count_sub(pages_per_huge_page(h), mm); hugetlb_remove_rmap(folio); spin_unlock(ptl); /* * Restore the reservation for anonymous page, otherwise the * backing page could be stolen by someone. * If there we are freeing a surplus, do not set the restore * reservation bit. */ adjust_reservation = false; spin_lock_irq(&hugetlb_lock); if (!h->surplus_huge_pages && __vma_private_lock(vma) && folio_test_anon(folio)) { folio_set_hugetlb_restore_reserve(folio); /* Reservation to be adjusted after the spin lock */ adjust_reservation = true; } spin_unlock_irq(&hugetlb_lock); /* * Adjust the reservation for the region that will have the * reserve restored. Keep in mind that vma_needs_reservation() changes * resv->adds_in_progress if it succeeds. If this is not done, * do_exit() will not see it, and will keep the reservation * forever. */ if (adjust_reservation) { int rc = vma_needs_reservation(h, vma, address); if (rc < 0) /* Pressumably allocate_file_region_entries failed * to allocate a file_region struct. Clear * hugetlb_restore_reserve so that global reserve * count will not be incremented by free_huge_folio. * Act as if we consumed the reservation. */ folio_clear_hugetlb_restore_reserve(folio); else if (rc) vma_add_reservation(h, vma, address); } tlb_remove_page_size(tlb, folio_page(folio, 0), folio_size(folio)); /* * If we were instructed to unmap a specific folio, we're done. */ if (folio_provided) break; } tlb_end_vma(tlb, vma); huge_pmd_unshare_flush(tlb, vma); } void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; adjust_range_if_pmd_sharing_possible(vma, start, end); hugetlb_vma_lock_write(vma); if (vma->vm_file) i_mmap_lock_write(vma->vm_file->f_mapping); } void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { zap_flags_t zap_flags = details ? details->zap_flags : 0; if (!vma->vm_file) /* hugetlbfs_file_mmap error */ return; if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */ /* * Unlock and free the vma lock before releasing i_mmap_rwsem. * When the vma_lock is freed, this makes the vma ineligible * for pmd sharing. And, i_mmap_rwsem is required to set up * pmd sharing. This is important as page tables for this * unmapped range will be asynchrously deleted. If the page * tables are shared, there will be issues when accessed by * someone else. */ __hugetlb_vma_unlock_write_free(vma); } else { hugetlb_vma_unlock_write(vma); } if (vma->vm_file) i_mmap_unlock_write(vma->vm_file->f_mapping); } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, struct folio *folio, zap_flags_t zap_flags) { struct mmu_notifier_range range; struct mmu_gather tlb; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); mmu_notifier_invalidate_range_start(&range); tlb_gather_mmu(&tlb, vma->vm_mm); __unmap_hugepage_range(&tlb, vma, start, end, folio, zap_flags); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } /* * This is called when the original mapper is failing to COW a MAP_PRIVATE * mapping it owns the reserve page for. The intention is to unmap the page * from other VMAs and let the children be SIGKILLed if they are faulting the * same region. */ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, struct folio *folio, unsigned long address) { struct hstate *h = hstate_vma(vma); struct vm_area_struct *iter_vma; struct address_space *mapping; pgoff_t pgoff; /* * vm_pgoff is in PAGE_SIZE units, hence the different calculation * from page cache lookup which is in HPAGE_SIZE units. */ address = address & huge_page_mask(h); pgoff = ((address - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; mapping = vma->vm_file->f_mapping; /* * Take the mapping lock for the duration of the table walk. As * this mapping should be shared between all the VMAs, * __unmap_hugepage_range() is called as the lock is already held */ i_mmap_lock_write(mapping); vma_interval_tree_foreach(iter_vma, &mapping->i_mmap, pgoff, pgoff) { /* Do not unmap the current VMA */ if (iter_vma == vma) continue; /* * Shared VMAs have their own reserves and do not affect * MAP_PRIVATE accounting but it is possible that a shared * VMA is using the same page so check and skip such VMAs. */ if (iter_vma->vm_flags & VM_MAYSHARE) continue; /* * Unmap the page from other VMAs without their own reserves. * They get marked to be SIGKILLed if they fault in these * areas. This is because a future no-page fault on this VMA * could insert a zeroed page instead of the data existing * from the time of fork. This would look like data corruption */ if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER)) unmap_hugepage_range(iter_vma, address, address + huge_page_size(h), folio, 0); } i_mmap_unlock_write(mapping); } /* * hugetlb_wp() should be called with page lock of the original hugepage held. * Called with hugetlb_fault_mutex_table held and pte_page locked so we * cannot race with other handlers or page migration. * Keep the pte_same checks anyway to make transition from the mutex easier. */ static vm_fault_t hugetlb_wp(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; pte_t pte = huge_ptep_get(mm, vmf->address, vmf->pte); struct hstate *h = hstate_vma(vma); struct folio *old_folio; struct folio *new_folio; bool cow_from_owner = 0; vm_fault_t ret = 0; struct mmu_notifier_range range; /* * Never handle CoW for uffd-wp protected pages. It should be only * handled when the uffd-wp protection is removed. * * Note that only the CoW optimization path (in hugetlb_no_page()) * can trigger this, because hugetlb_fault() will always resolve * uffd-wp bit first. */ if (!unshare && huge_pte_uffd_wp(pte)) return 0; /* Let's take out MAP_SHARED mappings first. */ if (vma->vm_flags & VM_MAYSHARE) { set_huge_ptep_writable(vma, vmf->address, vmf->pte); return 0; } old_folio = page_folio(pte_page(pte)); delayacct_wpcopy_start(); retry_avoidcopy: /* * If no-one else is actually using this page, we're the exclusive * owner and can reuse this page. * * Note that we don't rely on the (safer) folio refcount here, because * copying the hugetlb folio when there are unexpected (temporary) * folio references could harm simple fork()+exit() users when * we run out of free hugetlb folios: we would have to kill processes * in scenarios that used to work. As a side effect, there can still * be leaks between processes, for example, with FOLL_GET users. */ if (folio_mapcount(old_folio) == 1 && folio_test_anon(old_folio)) { if (!PageAnonExclusive(&old_folio->page)) { folio_move_anon_rmap(old_folio, vma); SetPageAnonExclusive(&old_folio->page); } if (likely(!unshare)) set_huge_ptep_maybe_writable(vma, vmf->address, vmf->pte); delayacct_wpcopy_end(); return 0; } VM_BUG_ON_PAGE(folio_test_anon(old_folio) && PageAnonExclusive(&old_folio->page), &old_folio->page); /* * If the process that created a MAP_PRIVATE mapping is about to perform * a COW due to a shared page count, attempt to satisfy the allocation * without using the existing reserves. * In order to determine where this is a COW on a MAP_PRIVATE mapping it * is enough to check whether the old_folio is anonymous. This means that * the reserve for this address was consumed. If reserves were used, a * partial faulted mapping at the fime of fork() could consume its reserves * on COW instead of the full address range. */ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && folio_test_anon(old_folio)) cow_from_owner = true; folio_get(old_folio); /* * Drop page table lock as buddy allocator may be called. It will * be acquired again before returning to the caller, as expected. */ spin_unlock(vmf->ptl); new_folio = alloc_hugetlb_folio(vma, vmf->address, cow_from_owner); if (IS_ERR(new_folio)) { /* * If a process owning a MAP_PRIVATE mapping fails to COW, * it is due to references held by a child and an insufficient * huge page pool. To guarantee the original mappers * reliability, unmap the page from child processes. The child * may get SIGKILLed if it later faults. */ if (cow_from_owner) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx; u32 hash; folio_put(old_folio); /* * Drop hugetlb_fault_mutex and vma_lock before * unmapping. unmapping needs to hold vma_lock * in write mode. Dropping vma_lock in read mode * here is OK as COW mappings do not interact with * PMD sharing. * * Reacquire both after unmap operation. */ idx = vma_hugecache_offset(h, vma, vmf->address); hash = hugetlb_fault_mutex_hash(mapping, idx); hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); unmap_ref_private(mm, vma, old_folio, vmf->address); mutex_lock(&hugetlb_fault_mutex_table[hash]); hugetlb_vma_lock_read(vma); spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte))) goto retry_avoidcopy; /* * race occurs while re-acquiring page table * lock, and our job is done. */ delayacct_wpcopy_end(); return 0; } ret = vmf_error(PTR_ERR(new_folio)); goto out_release_old; } /* * When the original hugepage is shared one, it does not have * anon_vma prepared. */ ret = __vmf_anon_prepare(vmf); if (unlikely(ret)) goto out_release_all; if (copy_user_large_folio(new_folio, old_folio, vmf->real_address, vma)) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_release_all; } __folio_mark_uptodate(new_folio); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, vmf->address, vmf->address + huge_page_size(h)); mmu_notifier_invalidate_range_start(&range); /* * Retake the page table lock to check for racing updates * before the page tables are altered */ spin_lock(vmf->ptl); vmf->pte = hugetlb_walk(vma, vmf->address, huge_page_size(h)); if (likely(vmf->pte && pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), pte))) { pte_t newpte = make_huge_pte(vma, new_folio, !unshare); /* Break COW or unshare */ huge_ptep_clear_flush(vma, vmf->address, vmf->pte); hugetlb_remove_rmap(old_folio); hugetlb_add_new_anon_rmap(new_folio, vma, vmf->address); if (huge_pte_uffd_wp(pte)) newpte = huge_pte_mkuffd_wp(newpte); set_huge_pte_at(mm, vmf->address, vmf->pte, newpte, huge_page_size(h)); folio_set_hugetlb_migratable(new_folio); /* Make the old page be freed below */ new_folio = old_folio; } spin_unlock(vmf->ptl); mmu_notifier_invalidate_range_end(&range); out_release_all: /* * No restore in case of successful pagetable update (Break COW or * unshare) */ if (new_folio != old_folio) restore_reserve_on_error(h, vma, vmf->address, new_folio); folio_put(new_folio); out_release_old: folio_put(old_folio); spin_lock(vmf->ptl); /* Caller expects lock to be held */ delayacct_wpcopy_end(); return ret; } /* * Return whether there is a pagecache page to back given address within VMA. */ bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = linear_page_index(vma, address); struct folio *folio; folio = filemap_get_folio(mapping, idx); if (IS_ERR(folio)) return false; folio_put(folio); return true; } int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx) { struct inode *inode = mapping->host; struct hstate *h = hstate_inode(inode); int err; idx <<= huge_page_order(h); __folio_set_locked(folio); err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL); if (unlikely(err)) { __folio_clear_locked(folio); return err; } folio_clear_hugetlb_restore_reserve(folio); /* * mark folio dirty so that it will not be removed from cache/file * by non-hugetlbfs specific code paths. */ folio_mark_dirty(folio); spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); return 0; } static inline vm_fault_t hugetlb_handle_userfault(struct vm_fault *vmf, struct address_space *mapping, unsigned long reason) { u32 hash; /* * vma_lock and hugetlb_fault_mutex must be dropped before handling * userfault. Also mmap_lock could be dropped due to handling * userfault, any vma operation should be careful from here. */ hugetlb_vma_unlock_read(vmf->vma); hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(vmf, reason); } /* * Recheck pte with pgtable lock. Returns true if pte didn't change, or * false if pte changed or is changing. */ static bool hugetlb_pte_stable(struct hstate *h, struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t old_pte) { spinlock_t *ptl; bool same; ptl = huge_pte_lock(h, mm, ptep); same = pte_same(huge_ptep_get(mm, addr, ptep), old_pte); spin_unlock(ptl); return same; } static vm_fault_t hugetlb_no_page(struct address_space *mapping, struct vm_fault *vmf) { u32 hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff); bool new_folio, new_anon_folio = false; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; struct hstate *h = hstate_vma(vma); vm_fault_t ret = VM_FAULT_SIGBUS; bool folio_locked = true; struct folio *folio; unsigned long size; pte_t new_pte; /* * Currently, we are forced to kill the process in the event the * original mapper has unmapped pages from the child due to a failed * COW/unsharing. Warn that such a situation has occurred as it may not * be obvious. */ if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) { pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n", current->pid); goto out; } /* * Use page lock to guard against racing truncation * before we get page_table_lock. */ new_folio = false; folio = filemap_lock_hugetlb_folio(h, mapping, vmf->pgoff); if (IS_ERR(folio)) { size = i_size_read(mapping->host) >> huge_page_shift(h); if (vmf->pgoff >= size) goto out; /* Check for page in userfault range */ if (userfaultfd_missing(vma)) { /* * Since hugetlb_no_page() was examining pte * without pgtable lock, we need to re-test under * lock because the pte may not be stable and could * have changed from under us. Try to detect * either changed or during-changing ptes and retry * properly when needed. * * Note that userfaultfd is actually fine with * false positives (e.g. caused by pte changed), * but not wrong logical events (e.g. caused by * reading a pte during changing). The latter can * confuse the userspace, so the strictness is very * much preferred. E.g., MISSING event should * never happen on the page after UFFDIO_COPY has * correctly installed the page and returned. */ if (!hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MISSING); } if (!(vma->vm_flags & VM_MAYSHARE)) { ret = __vmf_anon_prepare(vmf); if (unlikely(ret)) goto out; } folio = alloc_hugetlb_folio(vma, vmf->address, false); if (IS_ERR(folio)) { /* * Returning error will result in faulting task being * sent SIGBUS. The hugetlb fault mutex prevents two * tasks from racing to fault in the same page which * could result in false unable to allocate errors. * Page migration does not take the fault mutex, but * does a clear then write of pte's under page table * lock. Page fault code could race with migration, * notice the clear pte and try to allocate a page * here. Before returning error, get ptl and make * sure there really is no pte entry. */ if (hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) ret = vmf_error(PTR_ERR(folio)); else ret = 0; goto out; } folio_zero_user(folio, vmf->real_address); __folio_mark_uptodate(folio); new_folio = true; if (vma->vm_flags & VM_MAYSHARE) { int err = hugetlb_add_to_page_cache(folio, mapping, vmf->pgoff); if (err) { /* * err can't be -EEXIST which implies someone * else consumed the reservation since hugetlb * fault mutex is held when add a hugetlb page * to the page cache. So it's safe to call * restore_reserve_on_error() here. */ restore_reserve_on_error(h, vma, vmf->address, folio); folio_put(folio); ret = VM_FAULT_SIGBUS; goto out; } } else { new_anon_folio = true; folio_lock(folio); } } else { /* * If memory error occurs between mmap() and fault, some process * don't have hwpoisoned swap entry for errored virtual address. * So we need to block hugepage fault by PG_hwpoison bit check. */ if (unlikely(folio_test_hwpoison(folio))) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto backout_unlocked; } /* Check for page in userfault range. */ if (userfaultfd_minor(vma)) { folio_unlock(folio); folio_put(folio); /* See comment in userfaultfd_missing() block above */ if (!hugetlb_pte_stable(h, mm, vmf->address, vmf->pte, vmf->orig_pte)) { ret = 0; goto out; } return hugetlb_handle_userfault(vmf, mapping, VM_UFFD_MINOR); } } /* * If we are going to COW a private mapping later, we examine the * pending reservations for this page now. This will ensure that * any allocations necessary to record that reservation occur outside * the spinlock. */ if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { if (vma_needs_reservation(h, vma, vmf->address) < 0) { ret = VM_FAULT_OOM; goto backout_unlocked; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf->address); } vmf->ptl = huge_pte_lock(h, mm, vmf->pte); ret = 0; /* If pte changed from under us, retry */ if (!pte_same(huge_ptep_get(mm, vmf->address, vmf->pte), vmf->orig_pte)) goto backout; if (new_anon_folio) hugetlb_add_new_anon_rmap(folio, vma, vmf->address); else hugetlb_add_file_rmap(folio); new_pte = make_huge_pte(vma, folio, vma->vm_flags & VM_SHARED); /* * If this pte was previously wr-protected, keep it wr-protected even * if populated. */ if (unlikely(pte_is_uffd_wp_marker(vmf->orig_pte))) new_pte = huge_pte_mkuffd_wp(new_pte); set_huge_pte_at(mm, vmf->address, vmf->pte, new_pte, huge_page_size(h)); hugetlb_count_add(pages_per_huge_page(h), mm); if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* * No need to keep file folios locked. See comment in * hugetlb_fault(). */ if (!new_anon_folio) { folio_locked = false; folio_unlock(folio); } /* Optimization, do the COW without a second fault */ ret = hugetlb_wp(vmf); } spin_unlock(vmf->ptl); /* * Only set hugetlb_migratable in newly allocated pages. Existing pages * found in the pagecache may not have hugetlb_migratable if they have * been isolated for migration. */ if (new_folio) folio_set_hugetlb_migratable(folio); if (folio_locked) folio_unlock(folio); out: hugetlb_vma_unlock_read(vma); /* * We must check to release the per-VMA lock. __vmf_anon_prepare() is * the only way ret can be set to VM_FAULT_RETRY. */ if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return ret; backout: spin_unlock(vmf->ptl); backout_unlocked: /* We only need to restore reservations for private mappings */ if (new_anon_folio) restore_reserve_on_error(h, vma, vmf->address, folio); folio_unlock(folio); folio_put(folio); goto out; } #ifdef CONFIG_SMP u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { unsigned long key[2]; u32 hash; key[0] = (unsigned long) mapping; key[1] = idx; hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0); return hash & (num_fault_mutexes - 1); } #else /* * For uniprocessor systems we always use a single mutex, so just * return 0 and avoid the hashing overhead. */ u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx) { return 0; } #endif vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { vm_fault_t ret; u32 hash; struct folio *folio = NULL; struct hstate *h = hstate_vma(vma); struct address_space *mapping; bool need_wait_lock = false; struct vm_fault vmf = { .vma = vma, .address = address & huge_page_mask(h), .real_address = address, .flags = flags, .pgoff = vma_hugecache_offset(h, vma, address & huge_page_mask(h)), /* TODO: Track hugetlb faults using vm_fault */ /* * Some fields may not be initialized, be careful as it may * be hard to debug if called functions make assumptions */ }; /* * Serialize hugepage allocation and instantiation, so that we don't * get spurious allocation failures if two CPUs race to instantiate * the same page in the page cache. */ mapping = vma->vm_file->f_mapping; hash = hugetlb_fault_mutex_hash(mapping, vmf.pgoff); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* * Acquire vma lock before calling huge_pte_alloc and hold * until finished with vmf.pte. This prevents huge_pmd_unshare from * being called elsewhere and making the vmf.pte no longer valid. */ hugetlb_vma_lock_read(vma); vmf.pte = huge_pte_alloc(mm, vma, vmf.address, huge_page_size(h)); if (!vmf.pte) { hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return VM_FAULT_OOM; } vmf.orig_pte = huge_ptep_get(mm, vmf.address, vmf.pte); if (huge_pte_none(vmf.orig_pte)) /* * hugetlb_no_page will drop vma lock and hugetlb fault * mutex internally, which make us return immediately. */ return hugetlb_no_page(mapping, &vmf); if (pte_is_marker(vmf.orig_pte)) { const pte_marker marker = softleaf_to_marker(softleaf_from_pte(vmf.orig_pte)); if (marker & PTE_MARKER_POISONED) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); goto out_mutex; } else if (WARN_ON_ONCE(marker & PTE_MARKER_GUARD)) { /* This isn't supported in hugetlb. */ ret = VM_FAULT_SIGSEGV; goto out_mutex; } return hugetlb_no_page(mapping, &vmf); } ret = 0; /* Not present, either a migration or a hwpoisoned entry */ if (!pte_present(vmf.orig_pte) && !huge_pte_none(vmf.orig_pte)) { const softleaf_t softleaf = softleaf_from_pte(vmf.orig_pte); if (softleaf_is_migration(softleaf)) { /* * Release the hugetlb fault lock now, but retain * the vma lock, because it is needed to guard the * huge_pte_lockptr() later in * migration_entry_wait_huge(). The vma lock will * be released there. */ mutex_unlock(&hugetlb_fault_mutex_table[hash]); migration_entry_wait_huge(vma, vmf.address, vmf.pte); return 0; } if (softleaf_is_hwpoison(softleaf)) { ret = VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); } goto out_mutex; } /* * If we are going to COW/unshare the mapping later, we examine the * pending reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the * spinlock. */ if ((flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) && !(vma->vm_flags & VM_MAYSHARE) && !huge_pte_write(vmf.orig_pte)) { if (vma_needs_reservation(h, vma, vmf.address) < 0) { ret = VM_FAULT_OOM; goto out_mutex; } /* Just decrements count, does not deallocate */ vma_end_reservation(h, vma, vmf.address); } vmf.ptl = huge_pte_lock(h, mm, vmf.pte); /* Check for a racing update before calling hugetlb_wp() */ if (unlikely(!pte_same(vmf.orig_pte, huge_ptep_get(mm, vmf.address, vmf.pte)))) goto out_ptl; /* Handle userfault-wp first, before trying to lock more pages */ if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(mm, vmf.address, vmf.pte)) && (flags & FAULT_FLAG_WRITE) && !huge_pte_write(vmf.orig_pte)) { if (!userfaultfd_wp_async(vma)) { spin_unlock(vmf.ptl); hugetlb_vma_unlock_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); return handle_userfault(&vmf, VM_UFFD_WP); } vmf.orig_pte = huge_pte_clear_uffd_wp(vmf.orig_pte); set_huge_pte_at(mm, vmf.address, vmf.pte, vmf.orig_pte, huge_page_size(hstate_vma(vma))); /* Fallthrough to CoW */ } if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!huge_pte_write(vmf.orig_pte)) { /* * Anonymous folios need to be lock since hugetlb_wp() * checks whether we can re-use the folio exclusively * for us in case we are the only user of it. */ folio = page_folio(pte_page(vmf.orig_pte)); if (folio_test_anon(folio) && !folio_trylock(folio)) { need_wait_lock = true; goto out_ptl; } folio_get(folio); ret = hugetlb_wp(&vmf); if (folio_test_anon(folio)) folio_unlock(folio); folio_put(folio); goto out_ptl; } else if (likely(flags & FAULT_FLAG_WRITE)) { vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte); } } vmf.orig_pte = pte_mkyoung(vmf.orig_pte); if (huge_ptep_set_access_flags(vma, vmf.address, vmf.pte, vmf.orig_pte, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, vmf.address, vmf.pte); out_ptl: spin_unlock(vmf.ptl); out_mutex: hugetlb_vma_unlock_read(vma); /* * We must check to release the per-VMA lock. __vmf_anon_prepare() in * hugetlb_wp() is the only way ret can be set to VM_FAULT_RETRY. */ if (unlikely(ret & VM_FAULT_RETRY)) vma_end_read(vma); mutex_unlock(&hugetlb_fault_mutex_table[hash]); /* * hugetlb_wp drops all the locks, but the folio lock, before trying to * unmap the folio from other processes. During that window, if another * process mapping that folio faults in, it will take the mutex and then * it will wait on folio_lock, causing an ABBA deadlock. * Use trylock instead and bail out if we fail. * * Ideally, we should hold a refcount on the folio we wait for, but we do * not want to use the folio after it becomes unlocked, but rather just * wait for it to become unlocked, so hopefully next fault successes on * the trylock. */ if (need_wait_lock) folio_wait_locked(folio); return ret; } #ifdef CONFIG_USERFAULTFD /* * Can probably be eliminated, but still used by hugetlb_mfill_atomic_pte(). */ static struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address) { struct mempolicy *mpol; nodemask_t *nodemask; struct folio *folio; gfp_t gfp_mask; int node; gfp_mask = htlb_alloc_mask(h); node = huge_node(vma, address, gfp_mask, &mpol, &nodemask); /* * This is used to allocate a temporary hugetlb to hold the copied * content, which will then be copied again to the final hugetlb * consuming a reservation. Set the alloc_fallback to false to indicate * that breaking the per-node hugetlb pool is not allowed in this case. */ folio = alloc_hugetlb_folio_nodemask(h, node, nodemask, gfp_mask, false); mpol_cond_put(mpol); return folio; } /* * Used by userfaultfd UFFDIO_* ioctls. Based on userfaultfd's mfill_atomic_pte * with modifications for hugetlb pages. */ int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { struct mm_struct *dst_mm = dst_vma->vm_mm; bool is_continue = uffd_flags_mode_is(flags, MFILL_ATOMIC_CONTINUE); bool wp_enabled = (flags & MFILL_ATOMIC_WP); struct hstate *h = hstate_vma(dst_vma); struct address_space *mapping = dst_vma->vm_file->f_mapping; pgoff_t idx = vma_hugecache_offset(h, dst_vma, dst_addr); unsigned long size = huge_page_size(h); int vm_shared = dst_vma->vm_flags & VM_SHARED; pte_t _dst_pte; spinlock_t *ptl; int ret = -ENOMEM; struct folio *folio; bool folio_in_pagecache = false; pte_t dst_ptep; if (uffd_flags_mode_is(flags, MFILL_ATOMIC_POISON)) { ptl = huge_pte_lock(h, dst_mm, dst_pte); /* Don't overwrite any existing PTEs (even markers) */ if (!huge_pte_none(huge_ptep_get(dst_mm, dst_addr, dst_pte))) { spin_unlock(ptl); return -EEXIST; } _dst_pte = make_pte_marker(PTE_MARKER_POISONED); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, size); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); return 0; } if (is_continue) { ret = -EFAULT; folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) goto out; folio_in_pagecache = true; } else if (!*foliop) { /* If a folio already exists, then it's UFFDIO_COPY for * a non-missing case. Return -EEXIST. */ if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { ret = -EEXIST; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, false); if (IS_ERR(folio)) { pte_t *actual_pte = hugetlb_walk(dst_vma, dst_addr, PMD_SIZE); if (actual_pte) { ret = -EEXIST; goto out; } ret = -ENOMEM; goto out; } ret = copy_folio_from_user(folio, (const void __user *) src_addr, false); /* fallback to copy_from_user outside mmap_lock */ if (unlikely(ret)) { ret = -ENOENT; /* Free the allocated folio which may have * consumed a reservation. */ restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); /* Allocate a temporary folio to hold the copied * contents. */ folio = alloc_hugetlb_folio_vma(h, dst_vma, dst_addr); if (!folio) { ret = -ENOMEM; goto out; } *foliop = folio; /* Set the outparam foliop and return to the caller to * copy the contents outside the lock. Don't free the * folio. */ goto out; } } else { if (vm_shared && hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) { folio_put(*foliop); ret = -EEXIST; *foliop = NULL; goto out; } folio = alloc_hugetlb_folio(dst_vma, dst_addr, false); if (IS_ERR(folio)) { folio_put(*foliop); ret = -ENOMEM; *foliop = NULL; goto out; } ret = copy_user_large_folio(folio, *foliop, dst_addr, dst_vma); folio_put(*foliop); *foliop = NULL; if (ret) { folio_put(folio); goto out; } } /* * If we just allocated a new page, we need a memory barrier to ensure * that preceding stores to the page become visible before the * set_pte_at() write. The memory barrier inside __folio_mark_uptodate * is what we need. * * In the case where we have not allocated a new page (is_continue), * the page must already be uptodate. UFFDIO_CONTINUE already includes * an earlier smp_wmb() to ensure that prior stores will be visible * before the set_pte_at() write. */ if (!is_continue) __folio_mark_uptodate(folio); else WARN_ON_ONCE(!folio_test_uptodate(folio)); /* Add shared, newly allocated pages to the page cache. */ if (vm_shared && !is_continue) { ret = -EFAULT; if (idx >= (i_size_read(mapping->host) >> huge_page_shift(h))) goto out_release_nounlock; /* * Serialization between remove_inode_hugepages() and * hugetlb_add_to_page_cache() below happens through the * hugetlb_fault_mutex_table that here must be hold by * the caller. */ ret = hugetlb_add_to_page_cache(folio, mapping, idx); if (ret) goto out_release_nounlock; folio_in_pagecache = true; } ptl = huge_pte_lock(h, dst_mm, dst_pte); ret = -EIO; if (folio_test_hwpoison(folio)) goto out_release_unlock; ret = -EEXIST; dst_ptep = huge_ptep_get(dst_mm, dst_addr, dst_pte); /* * See comment about UFFD marker overwriting in * mfill_atomic_install_pte(). */ if (!huge_pte_none(dst_ptep) && !pte_is_uffd_marker(dst_ptep)) goto out_release_unlock; if (folio_in_pagecache) hugetlb_add_file_rmap(folio); else hugetlb_add_new_anon_rmap(folio, dst_vma, dst_addr); /* * For either: (1) CONTINUE on a non-shared VMA, or (2) UFFDIO_COPY * with wp flag set, don't set pte write bit. */ _dst_pte = make_huge_pte(dst_vma, folio, !wp_enabled && !(is_continue && !vm_shared)); /* * Always mark UFFDIO_COPY page dirty; note that this may not be * extremely important for hugetlbfs for now since swapping is not * supported, but we should still be clear in that this page cannot be * thrown away at will, even if write bit not set. */ _dst_pte = huge_pte_mkdirty(_dst_pte); _dst_pte = pte_mkyoung(_dst_pte); if (wp_enabled) _dst_pte = huge_pte_mkuffd_wp(_dst_pte); set_huge_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte, size); hugetlb_count_add(pages_per_huge_page(h), dst_mm); /* No need to invalidate - it was non-present before */ update_mmu_cache(dst_vma, dst_addr, dst_pte); spin_unlock(ptl); if (!is_continue) folio_set_hugetlb_migratable(folio); if (vm_shared || is_continue) folio_unlock(folio); ret = 0; out: return ret; out_release_unlock: spin_unlock(ptl); if (vm_shared || is_continue) folio_unlock(folio); out_release_nounlock: if (!folio_in_pagecache) restore_reserve_on_error(h, dst_vma, dst_addr, folio); folio_put(folio); goto out; } #endif /* CONFIG_USERFAULTFD */ long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long start = address; pte_t *ptep; pte_t pte; struct hstate *h = hstate_vma(vma); long pages = 0, psize = huge_page_size(h); struct mmu_notifier_range range; unsigned long last_addr_mask; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; struct mmu_gather tlb; /* * In the case of shared PMDs, the area to flush could be beyond * start/end. Set range.start/range.end to cover the maximum possible * range if PMD sharing is possible. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_VMA, 0, mm, start, end); adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); BUG_ON(address >= end); flush_cache_range(vma, range.start, range.end); tlb_gather_mmu_vma(&tlb, vma); mmu_notifier_invalidate_range_start(&range); hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); last_addr_mask = hugetlb_mask_last_page(h); for (; address < end; address += psize) { softleaf_t entry; spinlock_t *ptl; ptep = hugetlb_walk(vma, address, psize); if (!ptep) { if (!uffd_wp) { address |= last_addr_mask; continue; } /* * Userfaultfd wr-protect requires pgtable * pre-allocations to install pte markers. */ ptep = huge_pte_alloc(mm, vma, address, psize); if (!ptep) { pages = -ENOMEM; break; } } ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(&tlb, vma, address, ptep)) { /* * When uffd-wp is enabled on the vma, unshare * shouldn't happen at all. Warn about it if it * happened due to some reason. */ WARN_ON_ONCE(uffd_wp || uffd_wp_resolve); pages++; spin_unlock(ptl); address |= last_addr_mask; continue; } pte = huge_ptep_get(mm, address, ptep); if (huge_pte_none(pte)) { if (unlikely(uffd_wp)) /* Safe to modify directly (none->non-present). */ set_huge_pte_at(mm, address, ptep, make_pte_marker(PTE_MARKER_UFFD_WP), psize); goto next; } entry = softleaf_from_pte(pte); if (unlikely(softleaf_is_hwpoison(entry))) { /* Nothing to do. */ } else if (unlikely(softleaf_is_migration(entry))) { struct folio *folio = softleaf_to_folio(entry); pte_t newpte = pte; if (softleaf_is_migration_write(entry)) { if (folio_test_anon(folio)) entry = make_readable_exclusive_migration_entry( swp_offset(entry)); else entry = make_readable_migration_entry( swp_offset(entry)); newpte = swp_entry_to_pte(entry); pages++; } if (uffd_wp) newpte = pte_swp_mkuffd_wp(newpte); else if (uffd_wp_resolve) newpte = pte_swp_clear_uffd_wp(newpte); if (!pte_same(pte, newpte)) set_huge_pte_at(mm, address, ptep, newpte, psize); } else if (unlikely(pte_is_marker(pte))) { /* * Do nothing on a poison marker; page is * corrupted, permissions do not apply. Here * pte_marker_uffd_wp()==true implies !poison * because they're mutual exclusive. */ if (pte_is_uffd_wp_marker(pte) && uffd_wp_resolve) /* Safe to modify directly (non-present->none). */ huge_pte_clear(mm, address, ptep, psize); } else { pte_t old_pte; unsigned int shift = huge_page_shift(hstate_vma(vma)); old_pte = huge_ptep_modify_prot_start(vma, address, ptep); pte = huge_pte_modify(old_pte, newprot); pte = arch_make_huge_pte(pte, shift, vma->vm_flags); if (uffd_wp) pte = huge_pte_mkuffd_wp(pte); else if (uffd_wp_resolve) pte = huge_pte_clear_uffd_wp(pte); huge_ptep_modify_prot_commit(vma, address, ptep, old_pte, pte); pages++; tlb_remove_huge_tlb_entry(h, &tlb, ptep, address); } next: spin_unlock(ptl); cond_resched(); } tlb_flush_mmu_tlbonly(&tlb); huge_pmd_unshare_flush(&tlb, vma); /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs() we are * downgrading page table protection not changing it to point to a new * page. * * See Documentation/mm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); return pages > 0 ? (pages << h->order) : pages; } /* * Update the reservation map for the range [from, to]. * * Returns the number of entries that would be added to the reservation map * associated with the range [from, to]. This number is greater or equal to * zero. -EINVAL or -ENOMEM is returned in case of any errors. */ long hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_desc *desc, vma_flags_t vma_flags) { long chg = -1, add = -1, spool_resv, gbl_resv; struct hstate *h = hstate_inode(inode); struct hugepage_subpool *spool = subpool_inode(inode); struct resv_map *resv_map; struct hugetlb_cgroup *h_cg = NULL; long gbl_reserve, regions_needed = 0; int err; /* This should never happen */ if (from > to) { VM_WARN(1, "%s called with a negative range\n", __func__); return -EINVAL; } /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page * without using reserves */ if (vma_flags_test(&vma_flags, VMA_NORESERVE_BIT)) return 0; /* * Shared mappings base their reservation on the number of pages that * are already allocated on behalf of the file. Private mappings need * to reserve the full area even if read-only as mprotect() may be * called to make the mapping read-write. Assume !desc is a shm mapping */ if (!desc || vma_desc_test(desc, VMA_MAYSHARE_BIT)) { /* * resv_map can not be NULL as hugetlb_reserve_pages is only * called for inodes for which resv_maps were created (see * hugetlbfs_get_inode). */ resv_map = inode_resv_map(inode); chg = region_chg(resv_map, from, to, ®ions_needed); } else { /* Private mapping. */ resv_map = resv_map_alloc(); if (!resv_map) { err = -ENOMEM; goto out_err; } chg = to - from; set_vma_desc_resv_map(desc, resv_map); set_vma_desc_resv_flags(desc, HPAGE_RESV_OWNER); } if (chg < 0) { /* region_chg() above can return -ENOMEM */ err = (chg == -ENOMEM) ? -ENOMEM : -EINVAL; goto out_err; } err = hugetlb_cgroup_charge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), &h_cg); if (err < 0) goto out_err; if (desc && !vma_desc_test(desc, VMA_MAYSHARE_BIT) && h_cg) { /* For private mappings, the hugetlb_cgroup uncharge info hangs * of the resv_map. */ resv_map_set_hugetlb_cgroup_uncharge_info(resv_map, h_cg, h); } /* * There must be enough pages in the subpool for the mapping. If * the subpool has a minimum size, there may be some global * reservations already in place (gbl_reserve). */ gbl_reserve = hugepage_subpool_get_pages(spool, chg); if (gbl_reserve < 0) { err = gbl_reserve; goto out_uncharge_cgroup; } /* * Check enough hugepages are available for the reservation. * Hand the pages back to the subpool if there are not */ err = hugetlb_acct_memory(h, gbl_reserve); if (err < 0) goto out_put_pages; /* * Account for the reservations made. Shared mappings record regions * that have reservations as they are shared by multiple VMAs. * When the last VMA disappears, the region map says how much * the reservation was and the page cache tells how much of * the reservation was consumed. Private mappings are per-VMA and * only the consumed reservations are tracked. When the VMA * disappears, the original reservation is the VMA size and the * consumed reservations are stored in the map. Hence, nothing * else has to be done for private mappings here */ if (!desc || vma_desc_test(desc, VMA_MAYSHARE_BIT)) { add = region_add(resv_map, from, to, regions_needed, h, h_cg); if (unlikely(add < 0)) { hugetlb_acct_memory(h, -gbl_reserve); err = add; goto out_put_pages; } else if (unlikely(chg > add)) { /* * pages in this range were added to the reserve * map between region_chg and region_add. This * indicates a race with alloc_hugetlb_folio. Adjust * the subpool and reserve counts modified above * based on the difference. */ long rsv_adjust; /* * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the * reference to h_cg->css. See comment below for detail. */ hugetlb_cgroup_uncharge_cgroup_rsvd( hstate_index(h), (chg - add) * pages_per_huge_page(h), h_cg); rsv_adjust = hugepage_subpool_put_pages(spool, chg - add); hugetlb_acct_memory(h, -rsv_adjust); } else if (h_cg) { /* * The file_regions will hold their own reference to * h_cg->css. So we should release the reference held * via hugetlb_cgroup_charge_cgroup_rsvd() when we are * done. */ hugetlb_cgroup_put_rsvd_cgroup(h_cg); } } return chg; out_put_pages: spool_resv = chg - gbl_reserve; if (spool_resv) { /* put sub pool's reservation back, chg - gbl_reserve */ gbl_resv = hugepage_subpool_put_pages(spool, spool_resv); /* * subpool's reserved pages can not be put back due to race, * return to hstate. */ hugetlb_acct_memory(h, -gbl_resv); } /* Restore used_hpages for pages that failed global reservation */ if (gbl_reserve && spool) { unsigned long flags; spin_lock_irqsave(&spool->lock, flags); if (spool->max_hpages != -1) spool->used_hpages -= gbl_reserve; unlock_or_release_subpool(spool, flags); } out_uncharge_cgroup: hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h), chg * pages_per_huge_page(h), h_cg); out_err: if (!desc || vma_desc_test(desc, VMA_MAYSHARE_BIT)) /* Only call region_abort if the region_chg succeeded but the * region_add failed or didn't run. */ if (chg >= 0 && add < 0) region_abort(resv_map, from, to, regions_needed); if (desc && is_vma_desc_resv_set(desc, HPAGE_RESV_OWNER)) { kref_put(&resv_map->refs, resv_map_release); set_vma_desc_resv_map(desc, NULL); } return err; } long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed) { struct hstate *h = hstate_inode(inode); struct resv_map *resv_map = inode_resv_map(inode); long chg = 0; struct hugepage_subpool *spool = subpool_inode(inode); long gbl_reserve; /* * Since this routine can be called in the evict inode path for all * hugetlbfs inodes, resv_map could be NULL. */ if (resv_map) { chg = region_del(resv_map, start, end); /* * region_del() can fail in the rare case where a region * must be split and another region descriptor can not be * allocated. If end == LONG_MAX, it will not fail. */ if (chg < 0) return chg; } spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); /* * If the subpool has a minimum size, the number of global * reservations to be released may be adjusted. * * Note that !resv_map implies freed == 0. So (chg - freed) * won't go negative. */ gbl_reserve = hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -gbl_reserve); return 0; } #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static unsigned long page_table_shareable(struct vm_area_struct *svma, struct vm_area_struct *vma, unsigned long addr, pgoff_t idx) { unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + svma->vm_start; unsigned long sbase = saddr & PUD_MASK; unsigned long s_end = sbase + PUD_SIZE; /* Allow segments to share if only one is marked locked */ vm_flags_t vm_flags = vma->vm_flags & ~VM_LOCKED_MASK; vm_flags_t svm_flags = svma->vm_flags & ~VM_LOCKED_MASK; /* * match the virtual addresses, permission and the alignment of the * page table page. * * Also, vma_lock (vm_private_data) is required for sharing. */ if (pmd_index(addr) != pmd_index(saddr) || vm_flags != svm_flags || !range_in_vma(svma, sbase, s_end) || !svma->vm_private_data) return 0; return saddr; } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { unsigned long start = addr & PUD_MASK; unsigned long end = start + PUD_SIZE; #ifdef CONFIG_USERFAULTFD if (uffd_disable_huge_pmd_share(vma)) return false; #endif /* * check on proper vm_flags and page table alignment */ if (!(vma->vm_flags & VM_MAYSHARE)) return false; if (!vma->vm_private_data) /* vma lock required for sharing */ return false; if (!range_in_vma(vma, start, end)) return false; return true; } /* * Determine if start,end range within vma could be mapped by shared pmd. * If yes, adjust start and end to cover range associated with possible * shared pmd mappings. */ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE), v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE); /* * vma needs to span at least one aligned PUD size, and the range * must be at least partially within in. */ if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) || (*end <= v_start) || (*start >= v_end)) return; /* Extend the range to be PUD aligned for a worst case scenario */ if (*start > v_start) *start = ALIGN_DOWN(*start, PUD_SIZE); if (*end < v_end) *end = ALIGN(*end, PUD_SIZE); } /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the * !shared pmd case because we can allocate the pmd later as well, it makes the * code much cleaner. pmd allocation is essential for the shared case because * pud has to be populated inside the same i_mmap_rwsem section - otherwise * racing tasks could either miss the sharing (see huge_pte_offset) or select a * bad pmd for sharing. */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { struct address_space *mapping = vma->vm_file->f_mapping; pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; struct vm_area_struct *svma; unsigned long saddr; pte_t *spte = NULL; pte_t *pte; i_mmap_lock_read(mapping); vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { if (svma == vma) continue; saddr = page_table_shareable(svma, vma, addr, idx); if (saddr) { spte = hugetlb_walk(svma, saddr, vma_mmu_pagesize(svma)); if (spte) { ptdesc_pmd_pts_inc(virt_to_ptdesc(spte)); break; } } } if (!spte) goto out; spin_lock(&mm->page_table_lock); if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); mm_inc_nr_pmds(mm); } else { ptdesc_pmd_pts_dec(virt_to_ptdesc(spte)); } spin_unlock(&mm->page_table_lock); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); i_mmap_unlock_read(mapping); return pte; } /** * huge_pmd_unshare - Unmap a pmd table if it is shared by multiple users * @tlb: the current mmu_gather. * @vma: the vma covering the pmd table. * @addr: the address we are trying to unshare. * @ptep: pointer into the (pmd) page table. * * Called with the page table lock held, the i_mmap_rwsem held in write mode * and the hugetlb vma lock held in write mode. * * Note: The caller must call huge_pmd_unshare_flush() before dropping the * i_mmap_rwsem. * * Returns: 1 if it was a shared PMD table and it got unmapped, or 0 if it * was not a shared PMD table. */ int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { unsigned long sz = huge_page_size(hstate_vma(vma)); struct mm_struct *mm = vma->vm_mm; pgd_t *pgd = pgd_offset(mm, addr); p4d_t *p4d = p4d_offset(pgd, addr); pud_t *pud = pud_offset(p4d, addr); if (sz != PMD_SIZE) return 0; if (!ptdesc_pmd_is_shared(virt_to_ptdesc(ptep))) return 0; i_mmap_assert_write_locked(vma->vm_file->f_mapping); hugetlb_vma_assert_locked(vma); pud_clear(pud); tlb_unshare_pmd_ptdesc(tlb, virt_to_ptdesc(ptep), addr); mm_dec_nr_pmds(mm); return 1; } /* * huge_pmd_unshare_flush - Complete a sequence of huge_pmd_unshare() calls * @tlb: the current mmu_gather. * @vma: the vma covering the pmd table. * * Perform necessary TLB flushes or IPI broadcasts to synchronize PMD table * unsharing with concurrent page table walkers. * * This function must be called after a sequence of huge_pmd_unshare() * calls while still holding the i_mmap_rwsem. */ void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) { /* * We must synchronize page table unsharing such that nobody will * try reusing a previously-shared page table while it might still * be in use by previous sharers (TLB, GUP_fast). */ i_mmap_assert_write_locked(vma->vm_file->f_mapping); tlb_flush_unshared_tables(tlb); } #else /* !CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud) { return NULL; } int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) { } void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr) { return false; } #endif /* CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING */ #ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pte_t *pte = NULL; pgd = pgd_offset(mm, addr); p4d = p4d_alloc(mm, pgd, addr); if (!p4d) return NULL; pud = pud_alloc(mm, p4d, addr); if (pud) { if (sz == PUD_SIZE) { pte = (pte_t *)pud; } else { BUG_ON(sz != PMD_SIZE); if (want_pmd_share(vma, addr) && pud_none(*pud)) pte = huge_pmd_share(mm, vma, addr, pud); else pte = (pte_t *)pmd_alloc(mm, pud, addr); } } if (pte) { pte_t pteval = ptep_get_lockless(pte); BUG_ON(pte_present(pteval) && !pte_huge(pteval)); } return pte; } /* * huge_pte_offset() - Walk the page table to resolve the hugepage * entry at address @addr * * Return: Pointer to page table entry (PUD or PMD) for * address @addr, or NULL if a !p*d_present() entry is encountered and the * size @sz doesn't match the hugepage size at this level of the page * table. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pgd = pgd_offset(mm, addr); if (!pgd_present(*pgd)) return NULL; p4d = p4d_offset(pgd, addr); if (!p4d_present(*p4d)) return NULL; pud = pud_offset(p4d, addr); if (sz == PUD_SIZE) /* must be pud huge, non-present or none */ return (pte_t *)pud; if (!pud_present(*pud)) return NULL; /* must have a valid entry and size to go further */ pmd = pmd_offset(pud, addr); /* must be pmd huge, non-present or none */ return (pte_t *)pmd; } /* * Return a mask that can be used to update an address to the last huge * page in a page table page mapping size. Used to skip non-present * page table entries when linearly scanning address ranges. Architectures * with unique huge page to page table relationships can define their own * version of this routine. */ unsigned long hugetlb_mask_last_page(struct hstate *h) { unsigned long hp_size = huge_page_size(h); if (hp_size == PUD_SIZE) return P4D_SIZE - PUD_SIZE; else if (hp_size == PMD_SIZE) return PUD_SIZE - PMD_SIZE; else return 0UL; } #else /* See description above. Architectures can provide their own version. */ __weak unsigned long hugetlb_mask_last_page(struct hstate *h) { #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING if (huge_page_size(h) == PMD_SIZE) return PUD_SIZE - PMD_SIZE; #endif return 0UL; } #endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ /** * folio_isolate_hugetlb - try to isolate an allocated hugetlb folio * @folio: the folio to isolate * @list: the list to add the folio to on success * * Isolate an allocated (refcount > 0) hugetlb folio, marking it as * isolated/non-migratable, and moving it from the active list to the * given list. * * Isolation will fail if @folio is not an allocated hugetlb folio, or if * it is already isolated/non-migratable. * * On success, an additional folio reference is taken that must be dropped * using folio_putback_hugetlb() to undo the isolation. * * Return: True if isolation worked, otherwise False. */ bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list) { bool ret = true; spin_lock_irq(&hugetlb_lock); if (!folio_test_hugetlb(folio) || !folio_test_hugetlb_migratable(folio) || !folio_try_get(folio)) { ret = false; goto unlock; } folio_clear_hugetlb_migratable(folio); list_move_tail(&folio->lru, list); unlock: spin_unlock_irq(&hugetlb_lock); return ret; } int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { int ret = 0; *hugetlb = false; spin_lock_irq(&hugetlb_lock); if (folio_test_hugetlb(folio)) { *hugetlb = true; if (folio_test_hugetlb_freed(folio)) ret = 0; else if (folio_test_hugetlb_migratable(folio) || unpoison) ret = folio_try_get(folio); else ret = -EBUSY; } spin_unlock_irq(&hugetlb_lock); return ret; } int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) { int ret; spin_lock_irq(&hugetlb_lock); ret = __get_huge_page_for_hwpoison(pfn, flags, migratable_cleared); spin_unlock_irq(&hugetlb_lock); return ret; } /** * folio_putback_hugetlb - unisolate a hugetlb folio * @folio: the isolated hugetlb folio * * Putback/un-isolate the hugetlb folio that was previous isolated using * folio_isolate_hugetlb(): marking it non-isolated/migratable and putting it * back onto the active list. * * Will drop the additional folio reference obtained through * folio_isolate_hugetlb(). */ void folio_putback_hugetlb(struct folio *folio) { spin_lock_irq(&hugetlb_lock); folio_set_hugetlb_migratable(folio); list_move_tail(&folio->lru, &(folio_hstate(folio))->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); folio_put(folio); } void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { struct hstate *h = folio_hstate(old_folio); hugetlb_cgroup_migrate(old_folio, new_folio); folio_set_owner_migrate_reason(new_folio, reason); /* * transfer temporary state of the new hugetlb folio. This is * reverse to other transitions because the newpage is going to * be final while the old one will be freed so it takes over * the temporary status. * * Also note that we have to transfer the per-node surplus state * here as well otherwise the global surplus count will not match * the per-node's. */ if (folio_test_hugetlb_temporary(new_folio)) { int old_nid = folio_nid(old_folio); int new_nid = folio_nid(new_folio); folio_set_hugetlb_temporary(old_folio); folio_clear_hugetlb_temporary(new_folio); /* * There is no need to transfer the per-node surplus state * when we do not cross the node. */ if (new_nid == old_nid) return; spin_lock_irq(&hugetlb_lock); if (h->surplus_huge_pages_node[old_nid]) { h->surplus_huge_pages_node[old_nid]--; h->surplus_huge_pages_node[new_nid]++; } spin_unlock_irq(&hugetlb_lock); } /* * Our old folio is isolated and has "migratable" cleared until it * is putback. As migration succeeded, set the new folio "migratable" * and add it to the active list. */ spin_lock_irq(&hugetlb_lock); folio_set_hugetlb_migratable(new_folio); list_move_tail(&new_folio->lru, &(folio_hstate(new_folio))->hugepage_activelist); spin_unlock_irq(&hugetlb_lock); } /* * If @take_locks is false, the caller must ensure that no concurrent page table * access can happen (except for gup_fast() and hardware page walks). * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like * concurrent page fault handling) and the file rmap lock. */ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool take_locks) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); struct mm_struct *mm = vma->vm_mm; struct mmu_notifier_range range; struct mmu_gather tlb; unsigned long address; spinlock_t *ptl; pte_t *ptep; if (!(vma->vm_flags & VM_MAYSHARE)) return; if (start >= end) return; flush_cache_range(vma, start, end); tlb_gather_mmu_vma(&tlb, vma); /* * No need to call adjust_range_if_pmd_sharing_possible(), because * we have already done the PUD_SIZE alignment. */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); if (take_locks) { hugetlb_vma_lock_write(vma); i_mmap_lock_write(vma->vm_file->f_mapping); } else { i_mmap_assert_write_locked(vma->vm_file->f_mapping); } for (address = start; address < end; address += PUD_SIZE) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) continue; ptl = huge_pte_lock(h, mm, ptep); huge_pmd_unshare(&tlb, vma, address, ptep); spin_unlock(ptl); } huge_pmd_unshare_flush(&tlb, vma); if (take_locks) { i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); } /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see * Documentation/mm/mmu_notifier.rst. */ mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); } /* * This function will unconditionally remove all the shared pmd pgtable entries * within the specific vma for a hugetlbfs memory range. */ void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), ALIGN_DOWN(vma->vm_end, PUD_SIZE), /* take_locks = */ true); } /* * For hugetlb, mremap() is an odd edge case - while the VMA copying is * performed, we permit both the old and new VMAs to reference the same * reservation. * * We fix this up after the operation succeeds, or if a newly allocated VMA * is closed as a result of a failure to allocate memory. */ void fixup_hugetlb_reservations(struct vm_area_struct *vma) { if (is_vm_hugetlb_page(vma)) clear_vma_resv_huge_pages(vma); } |
| 169 25 766 169 169 169 168 168 170 602 600 601 600 602 601 600 601 601 602 602 601 601 601 599 602 601 601 25 25 25 25 25 25 25 25 25 24 25 187 2 2 2 2 2 2 12 3 12 2 1 2 7 7 2 3 1 2 7 7 61 62 2 7 6 5 5 5 5 5 5 2 7 2 6 7 7 12 12 12 11 7 6 1785 679 1847 1782 66 66 66 54 54 1782 1783 1784 1787 1 1782 1782 1787 1783 1785 66 66 66 66 66 66 659 658 657 658 659 7 7 6 7 7 7 7 3 7 6 7 6 2 7 7 7 4 5 2 7 2 2 2 2 2 2 5 7 7 7 7 7 7 7 7 7 7 25 25 24 2 2 2 2 2 2 2 2 2 2 2 5 6 6 6 6 6 6 6 6 6 6 6 2 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 | // SPDX-License-Identifier: GPL-2.0 /* * mm/rmap.c - physical to virtual reverse mappings * * Copyright 2001, Rik van Riel <riel@conectiva.com.br> * * Simple, low overhead reverse mapping scheme. * Please try to keep this thing as modular as possible. * * Provides methods for unmapping each kind of mapped page: * the anon methods track anonymous pages, and * the file methods track pages belonging to an inode. * * Original design by Rik van Riel <riel@conectiva.com.br> 2001 * File methods by Dave McCracken <dmccr@us.ibm.com> 2003, 2004 * Anonymous methods by Andrea Arcangeli <andrea@suse.de> 2004 * Contributions by Hugh Dickins 2003, 2004 */ /* * Lock ordering in mm: * * inode->i_rwsem (while writing or truncating, not reading or faulting) * mm->mmap_lock * mapping->invalidate_lock (in filemap_fault) * folio_lock * hugetlbfs_i_mmap_rwsem_key (in huge_pmd_share, see hugetlbfs below) * vma_start_write * mapping->i_mmap_rwsem * anon_vma->rwsem * mm->page_table_lock or pte_lock * swap_lock (in swap_duplicate, swap_info_get) * mmlist_lock (in mmput, drain_mmlist and others) * mapping->private_lock (in block_dirty_folio) * i_pages lock (widely used) * lruvec->lru_lock (in folio_lruvec_lock_irq) * inode->i_lock (in set_page_dirty's __mark_inode_dirty) * bdi.wb->list_lock (in set_page_dirty's __mark_inode_dirty) * sb_lock (within inode_lock in fs/fs-writeback.c) * i_pages lock (widely used, in set_page_dirty, * in arch-dependent flush_dcache_mmap_lock, * within bdi.wb->list_lock in __sync_single_inode) * * anon_vma->rwsem,mapping->i_mmap_rwsem (memory_failure, collect_procs_anon) * ->tasklist_lock * pte map lock * * hugetlbfs PageHuge() take locks in this order: * hugetlb_fault_mutex (hugetlbfs specific page fault mutex) * vma_lock (hugetlb specific lock for pmd_sharing) * mapping->i_mmap_rwsem (also used for hugetlb pmd sharing) * folio_lock */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/swap.h> #include <linux/leafops.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/memcontrol.h> #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> #include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> #include <linux/userfaultfd_k.h> #include <linux/mm_inline.h> #include <linux/oom.h> #include <asm/tlb.h> #define CREATE_TRACE_POINTS #include <trace/events/migrate.h> #include "internal.h" #include "swap.h" static struct kmem_cache *anon_vma_cachep; static struct kmem_cache *anon_vma_chain_cachep; static inline struct anon_vma *anon_vma_alloc(void) { struct anon_vma *anon_vma; anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); anon_vma->num_children = 0; anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. */ anon_vma->root = anon_vma; } return anon_vma; } static inline void anon_vma_free(struct anon_vma *anon_vma) { VM_BUG_ON(atomic_read(&anon_vma->refcount)); /* * Synchronize against folio_lock_anon_vma_read() such that * we can safely hold the lock without the anon_vma getting * freed. * * Relies on the full mb implied by the atomic_dec_and_test() from * put_anon_vma() against the acquire barrier implied by * down_read_trylock() from folio_lock_anon_vma_read(). This orders: * * folio_lock_anon_vma_read() VS put_anon_vma() * down_read_trylock() atomic_dec_and_test() * LOCK MB * atomic_read() rwsem_is_locked() * * LOCK should suffice since the actual taking of the lock must * happen _before_ what follows. */ might_sleep(); if (rwsem_is_locked(&anon_vma->root->rwsem)) { anon_vma_lock_write(anon_vma); anon_vma_unlock_write(anon_vma); } kmem_cache_free(anon_vma_cachep, anon_vma); } static inline struct anon_vma_chain *anon_vma_chain_alloc(gfp_t gfp) { return kmem_cache_alloc(anon_vma_chain_cachep, gfp); } static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) { kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } static void anon_vma_chain_assign(struct vm_area_struct *vma, struct anon_vma_chain *avc, struct anon_vma *anon_vma) { avc->vma = vma; avc->anon_vma = anon_vma; list_add(&avc->same_vma, &vma->anon_vma_chain); } /** * __anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question * * This makes sure the memory mapping described by 'vma' has * an 'anon_vma' attached to it, so that we can associate the * anonymous pages mapped into it with that anon_vma. * * The common case will be that we already have one, which * is handled inline by anon_vma_prepare(). But if * not we either need to find an adjacent mapping that we * can re-use the anon_vma from (very common when the only * reason for splitting a vma has been mprotect()), or we * allocate a new one. * * Anon-vma allocations are very subtle, because we may have * optimistically looked up an anon_vma in folio_lock_anon_vma_read() * and that may actually touch the rwsem even in the newly * allocated vma (it depends on RCU to make sure that the * anon_vma isn't actually destroyed). * * As a result, we need to do proper anon_vma locking even * for the new allocation. At the same time, we do not want * to do any locking for the common case of already having * an anon_vma. */ int __anon_vma_prepare(struct vm_area_struct *vma) { struct mm_struct *mm = vma->vm_mm; struct anon_vma *anon_vma, *allocated; struct anon_vma_chain *avc; mmap_assert_locked(mm); might_sleep(); avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_enomem; anon_vma = find_mergeable_anon_vma(vma); allocated = NULL; if (!anon_vma) { anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } anon_vma_lock_write(anon_vma); /* page_table_lock to protect against threads */ spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_assign(vma, avc, anon_vma); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(anon_vma); if (unlikely(allocated)) put_anon_vma(allocated); if (unlikely(avc)) anon_vma_chain_free(avc); return 0; out_enomem_free_avc: anon_vma_chain_free(avc); out_enomem: return -ENOMEM; } static void check_anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, enum vma_operation operation) { /* The write lock must be held. */ mmap_assert_write_locked(src->vm_mm); /* If not a fork then must be on same mm. */ VM_WARN_ON_ONCE(operation != VMA_OP_FORK && dst->vm_mm != src->vm_mm); /* If we have anything to do src->anon_vma must be provided. */ VM_WARN_ON_ONCE(!src->anon_vma && !list_empty(&src->anon_vma_chain)); VM_WARN_ON_ONCE(!src->anon_vma && dst->anon_vma); /* We are establishing a new anon_vma_chain. */ VM_WARN_ON_ONCE(!list_empty(&dst->anon_vma_chain)); /* * On fork, dst->anon_vma is set NULL (temporarily). Otherwise, anon_vma * must be the same across dst and src. */ VM_WARN_ON_ONCE(dst->anon_vma && dst->anon_vma != src->anon_vma); /* * Essentially equivalent to above - if not a no-op, we should expect * dst->anon_vma to be set for everything except a fork. */ VM_WARN_ON_ONCE(operation != VMA_OP_FORK && src->anon_vma && !dst->anon_vma); /* For the anon_vma to be compatible, it can only be singular. */ VM_WARN_ON_ONCE(operation == VMA_OP_MERGE_UNFAULTED && !list_is_singular(&src->anon_vma_chain)); #ifdef CONFIG_PER_VMA_LOCK /* Only merging an unfaulted VMA leaves the destination attached. */ VM_WARN_ON_ONCE(operation != VMA_OP_MERGE_UNFAULTED && vma_is_attached(dst)); #endif } static void maybe_reuse_anon_vma(struct vm_area_struct *dst, struct anon_vma *anon_vma) { /* If already populated, nothing to do.*/ if (dst->anon_vma) return; /* * We reuse an anon_vma if any linking VMAs were unmapped and it has * only a single child at most. */ if (anon_vma->num_active_vmas > 0) return; if (anon_vma->num_children > 1) return; dst->anon_vma = anon_vma; anon_vma->num_active_vmas++; } static void cleanup_partial_anon_vmas(struct vm_area_struct *vma); /** * anon_vma_clone - Establishes new anon_vma_chain objects in @dst linking to * all of the anon_vma objects contained within @src anon_vma_chain's. * @dst: The destination VMA with an empty anon_vma_chain. * @src: The source VMA we wish to duplicate. * @operation: The type of operation which resulted in the clone. * * This is the heart of the VMA side of the anon_vma implementation - we invoke * this function whenever we need to set up a new VMA's anon_vma state. * * This is invoked for: * * - VMA Merge, but only when @dst is unfaulted and @src is faulted - meaning we * clone @src into @dst. * - VMA split. * - VMA (m)remap. * - Fork of faulted VMA. * * In all cases other than fork this is simply a duplication. Fork additionally * adds a new active anon_vma. * * ONLY in the case of fork do we try to 'reuse' existing anon_vma's in an * anon_vma hierarchy, reusing anon_vma's which have no VMA associated with them * but do have a single child. This is to avoid waste of memory when repeatedly * forking. * * Returns: 0 on success, -ENOMEM on failure. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src, enum vma_operation operation) { struct anon_vma_chain *avc, *pavc; struct anon_vma *active_anon_vma = src->anon_vma; check_anon_vma_clone(dst, src, operation); if (!active_anon_vma) return 0; /* * Allocate AVCs. We don't need an anon_vma lock for this as we * are not updating the anon_vma rbtree nor are we changing * anon_vma statistics. * * Either src, dst have the same mm for which we hold an exclusive mmap * write lock, or we are forking and we hold it on src->vm_mm and dst is * not yet accessible to other threads so there's no possibliity of the * unlinked AVC's being observed yet. */ list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) { avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto enomem_failure; anon_vma_chain_assign(dst, avc, pavc->anon_vma); } /* * Now link the anon_vma's back to the newly inserted AVCs. * Note that all anon_vma's share the same root. */ anon_vma_lock_write(src->anon_vma); list_for_each_entry_reverse(avc, &dst->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); if (operation == VMA_OP_FORK) maybe_reuse_anon_vma(dst, anon_vma); } if (operation != VMA_OP_FORK) dst->anon_vma->num_active_vmas++; anon_vma_unlock_write(active_anon_vma); return 0; enomem_failure: cleanup_partial_anon_vmas(dst); return -ENOMEM; } /* * Attach vma to its own anon_vma, as well as to the anon_vmas that * the corresponding VMA in the parent process is attached to. * Returns 0 on success, non-zero on failure. */ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) { struct anon_vma_chain *avc; struct anon_vma *anon_vma; int rc; /* Don't bother if the parent process has no anon_vma here. */ if (!pvma->anon_vma) return 0; /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ vma->anon_vma = NULL; anon_vma = anon_vma_alloc(); if (!anon_vma) return -ENOMEM; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) { put_anon_vma(anon_vma); return -ENOMEM; } /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. */ rc = anon_vma_clone(vma, pvma, VMA_OP_FORK); /* An error arose or an existing anon_vma was reused, all done then. */ if (rc || vma->anon_vma) { put_anon_vma(anon_vma); anon_vma_chain_free(avc); return rc; } /* * OK no reuse, so add our own anon_vma. * * Since it is not linked anywhere we can safely manipulate anon_vma * fields without a lock. */ anon_vma->num_active_vmas = 1; /* * The root anon_vma's rwsem is the lock actually used when we * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until * this anon_vma is freed, because the lock lives in the root. */ get_anon_vma(anon_vma->root); /* Mark this anon_vma as the one where our new (COWed) pages go. */ vma->anon_vma = anon_vma; anon_vma_chain_assign(vma, avc, anon_vma); /* Now let rmap see it. */ anon_vma_lock_write(anon_vma); anon_vma_interval_tree_insert(avc, &anon_vma->rb_root); anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; } /* * In the unfortunate case of anon_vma_clone() failing to allocate memory we * have to clean things up. * * Since we allocate anon_vma_chain's before we insert them into the interval * trees, we simply have to free up the AVC's and remove the entries from the * VMA's anon_vma_chain. */ static void cleanup_partial_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { list_del(&avc->same_vma); anon_vma_chain_free(avc); } /* * The anon_vma assigned to this VMA is no longer valid, as we were not * able to correctly clone AVC state. Avoid inconsistent anon_vma tree * state by resetting. */ vma->anon_vma = NULL; } /** * unlink_anon_vmas() - remove all links between a VMA and anon_vma's, freeing * anon_vma_chain objects. * @vma: The VMA whose links to anon_vma objects is to be severed. * * As part of the process anon_vma_chain's are freed, * anon_vma->num_children,num_active_vmas is updated as required and, if the * relevant anon_vma references no further VMAs, its reference count is * decremented. */ void unlink_anon_vmas(struct vm_area_struct *vma) { struct anon_vma_chain *avc, *next; struct anon_vma *active_anon_vma = vma->anon_vma; /* Always hold mmap lock, read-lock on unmap possibly. */ mmap_assert_locked(vma->vm_mm); /* Unfaulted is a no-op. */ if (!active_anon_vma) { VM_WARN_ON_ONCE(!list_empty(&vma->anon_vma_chain)); return; } anon_vma_lock_write(active_anon_vma); /* * Unlink each anon_vma chained to the VMA. This list is ordered * from newest to oldest, ensuring the root anon_vma gets freed last. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; anon_vma_interval_tree_remove(avc, &anon_vma->rb_root); /* * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { anon_vma->parent->num_children--; continue; } list_del(&avc->same_vma); anon_vma_chain_free(avc); } active_anon_vma->num_active_vmas--; /* * vma would still be needed after unlink, and anon_vma will be prepared * when handle fault. */ vma->anon_vma = NULL; anon_vma_unlock_write(active_anon_vma); /* * Iterate the list once more, it now only contains empty and unlinked * anon_vmas, destroy them. Could not do before due to __put_anon_vma() * needing to write-acquire the anon_vma->root->rwsem. */ list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; VM_WARN_ON(anon_vma->num_children); VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); anon_vma_chain_free(avc); } } static void anon_vma_ctor(void *data) { struct anon_vma *anon_vma = data; init_rwsem(&anon_vma->rwsem); atomic_set(&anon_vma->refcount, 0); anon_vma->rb_root = RB_ROOT_CACHED; } void __init anon_vma_init(void) { anon_vma_cachep = kmem_cache_create("anon_vma", sizeof(struct anon_vma), 0, SLAB_TYPESAFE_BY_RCU|SLAB_PANIC|SLAB_ACCOUNT, anon_vma_ctor); anon_vma_chain_cachep = KMEM_CACHE(anon_vma_chain, SLAB_PANIC|SLAB_ACCOUNT); } /* * Getting a lock on a stable anon_vma from a page off the LRU is tricky! * * Since there is no serialization what so ever against folio_remove_rmap_*() * the best this function can do is return a refcount increased anon_vma * that might have been relevant to this page. * * The page might have been remapped to a different anon_vma or the anon_vma * returned may already be freed (and even reused). * * In case it was remapped to a different anon_vma, the new anon_vma will be a * child of the old anon_vma, and the anon_vma lifetime rules will therefore * ensure that any anon_vma obtained from the page will still be valid for as * long as we observe page_mapped() [ hence all those page_mapped() tests ]. * * All users of this function must be very careful when walking the anon_vma * chain and verify that the page in question is indeed mapped in it * [ something equivalent to page_mapped_in_vma() ]. * * Since anon_vma's slab is SLAB_TYPESAFE_BY_RCU and we know from * folio_remove_rmap_*() that the anon_vma pointer from page->mapping is valid * if there is a mapcount, we can dereference the anon_vma after observing * those. * * NOTE: the caller should hold folio lock when calling this. */ struct anon_vma *folio_get_anon_vma(const struct folio *folio) { struct anon_vma *anon_vma = NULL; unsigned long anon_mapping; VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON); if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } /* * If this folio is still mapped, then its anon_vma cannot have been * freed. But if it has been unmapped, we have no security against the * anon_vma structure being freed and reused (for another anon_vma: * SLAB_TYPESAFE_BY_RCU guarantees that - so the atomic_inc_not_zero() * above cannot corrupt). */ if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } out: rcu_read_unlock(); return anon_vma; } /* * Similar to folio_get_anon_vma() except it locks the anon_vma. * * Its a little more complex as it tries to keep the fast path to a single * atomic op -- the trylock. If we fail the trylock, we fall back to getting a * reference like with folio_get_anon_vma() and then block on the mutex * on !rwc->try_lock case. */ struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma = NULL; struct anon_vma *root_anon_vma; unsigned long anon_mapping; VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); rcu_read_lock(); anon_mapping = (unsigned long)READ_ONCE(folio->mapping); if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON) goto out; if (!folio_mapped(folio)) goto out; anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON); root_anon_vma = READ_ONCE(anon_vma->root); if (down_read_trylock(&root_anon_vma->rwsem)) { /* * If the folio is still mapped, then this anon_vma is still * its anon_vma, and holding the mutex ensures that it will * not go away, see anon_vma_free(). */ if (!folio_mapped(folio)) { up_read(&root_anon_vma->rwsem); anon_vma = NULL; } goto out; } if (rwc && rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } /* trylock failed, we got to sleep */ if (!atomic_inc_not_zero(&anon_vma->refcount)) { anon_vma = NULL; goto out; } if (!folio_mapped(folio)) { rcu_read_unlock(); put_anon_vma(anon_vma); return NULL; } /* we pinned the anon_vma, its safe to sleep */ rcu_read_unlock(); anon_vma_lock_read(anon_vma); if (atomic_dec_and_test(&anon_vma->refcount)) { /* * Oops, we held the last refcount, release the lock * and bail -- can't simply use put_anon_vma() because * we'll deadlock on the anon_vma_lock_write() recursion. */ anon_vma_unlock_read(anon_vma); __put_anon_vma(anon_vma); anon_vma = NULL; } return anon_vma; out: rcu_read_unlock(); return anon_vma; } #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH /* * Flush TLB entries for recently unmapped pages from remote CPUs. It is * important if a PTE was dirty when it was unmapped that it's flushed * before any IO is initiated on the page to prevent lost writes. Similarly, * it must be flushed before freeing to prevent data leakage. */ void try_to_unmap_flush(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (!tlb_ubc->flush_required) return; arch_tlbbatch_flush(&tlb_ubc->arch); tlb_ubc->flush_required = false; tlb_ubc->writable = false; } /* Flush iff there are potentially writable TLB entries that can race with IO */ void try_to_unmap_flush_dirty(void) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; if (tlb_ubc->writable) try_to_unmap_flush(); } /* * Bits 0-14 of mm->tlb_flush_batched record pending generations. * Bits 16-30 of mm->tlb_flush_batched bit record flushed generations. */ #define TLB_FLUSH_BATCH_FLUSHED_SHIFT 16 #define TLB_FLUSH_BATCH_PENDING_MASK \ ((1 << (TLB_FLUSH_BATCH_FLUSHED_SHIFT - 1)) - 1) #define TLB_FLUSH_BATCH_PENDING_LARGE \ (TLB_FLUSH_BATCH_PENDING_MASK / 2) static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long start, unsigned long end) { struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc; int batch; bool writable = pte_dirty(pteval); if (!pte_accessible(mm, pteval)) return; arch_tlbbatch_add_pending(&tlb_ubc->arch, mm, start, end); tlb_ubc->flush_required = true; /* * Ensure compiler does not re-order the setting of tlb_flush_batched * before the PTE is cleared. */ barrier(); batch = atomic_read(&mm->tlb_flush_batched); retry: if ((batch & TLB_FLUSH_BATCH_PENDING_MASK) > TLB_FLUSH_BATCH_PENDING_LARGE) { /* * Prevent `pending' from catching up with `flushed' because of * overflow. Reset `pending' and `flushed' to be 1 and 0 if * `pending' becomes large. */ if (!atomic_try_cmpxchg(&mm->tlb_flush_batched, &batch, 1)) goto retry; } else { atomic_inc(&mm->tlb_flush_batched); } /* * If the PTE was dirty then it's best to assume it's writable. The * caller must use try_to_unmap_flush_dirty() or try_to_unmap_flush() * before the page is queued for IO. */ if (writable) tlb_ubc->writable = true; } /* * Returns true if the TLB flush should be deferred to the end of a batch of * unmap operations to reduce IPIs. */ static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { if (!(flags & TTU_BATCH_FLUSH)) return false; return arch_tlbbatch_should_defer(mm); } /* * Reclaim unmaps pages under the PTL but do not flush the TLB prior to * releasing the PTL if TLB flushes are batched. It's possible for a parallel * operation such as mprotect or munmap to race between reclaim unmapping * the page and flushing the page. If this race occurs, it potentially allows * access to data via a stale TLB entry. Tracking all mm's that have TLB * batching in flight would be expensive during reclaim so instead track * whether TLB batching occurred in the past and if so then do a flush here * if required. This will cost one additional flush per reclaim cycle paid * by the first operation at risk such as mprotect and mumap. * * This must be called under the PTL so that an access to tlb_flush_batched * that is potentially a "reclaim vs mprotect/munmap/etc" race will synchronise * via the PTL. */ void flush_tlb_batched_pending(struct mm_struct *mm) { int batch = atomic_read(&mm->tlb_flush_batched); int pending = batch & TLB_FLUSH_BATCH_PENDING_MASK; int flushed = batch >> TLB_FLUSH_BATCH_FLUSHED_SHIFT; if (pending != flushed) { flush_tlb_mm(mm); /* * If the new TLB flushing is pending during flushing, leave * mm->tlb_flush_batched as is, to avoid losing flushing. */ atomic_cmpxchg(&mm->tlb_flush_batched, batch, pending | (pending << TLB_FLUSH_BATCH_FLUSHED_SHIFT)); } } #else static void set_tlb_ubc_flush_pending(struct mm_struct *mm, pte_t pteval, unsigned long start, unsigned long end) { } static bool should_defer_flush(struct mm_struct *mm, enum ttu_flags flags) { return false; } #endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ /** * page_address_in_vma - The virtual address of a page in this VMA. * @folio: The folio containing the page. * @page: The page within the folio. * @vma: The VMA we need to know the address in. * * Calculates the user virtual address of this page in the specified VMA. * It is the caller's responsibility to check the page is actually * within the VMA. There may not currently be a PTE pointing at this * page, but if a page fault occurs at this address, this is the page * which will be accessed. * * Context: Caller should hold a reference to the folio. Caller should * hold a lock (eg the i_mmap_lock or the mmap_lock) which keeps the * VMA from being altered. * * Return: The virtual address corresponding to this page in the VMA. */ unsigned long page_address_in_vma(const struct folio *folio, const struct page *page, const struct vm_area_struct *vma) { if (folio_test_anon(folio)) { struct anon_vma *anon_vma = folio_anon_vma(folio); /* * Note: swapoff's unuse_vma() is more efficient with this * check, and needs it to match anon_vma when KSM is active. */ if (!vma->anon_vma || !anon_vma || vma->anon_vma->root != anon_vma->root) return -EFAULT; } else if (!vma->vm_file) { return -EFAULT; } else if (vma->vm_file->f_mapping != folio->mapping) { return -EFAULT; } /* KSM folios don't reach here because of the !anon_vma check */ return vma_address(vma, page_pgoff(folio, page), 1); } /* * Returns the actual pmd_t* where we expect 'address' to be mapped from, or * NULL if it doesn't exist. No guarantees / checks on what the pmd_t* * represents. */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd = NULL; pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) goto out; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) goto out; pud = pud_offset(p4d, address); if (!pud_present(*pud)) goto out; pmd = pmd_offset(pud, address); out: return pmd; } struct folio_referenced_arg { int mapcount; int referenced; vm_flags_t vm_flags; struct mem_cgroup *memcg; }; /* * arg: folio_referenced_arg will be passed */ static bool folio_referenced_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct folio_referenced_arg *pra = arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int ptes = 0, referenced = 0; unsigned int nr; while (page_vma_mapped_walk(&pvmw)) { address = pvmw.address; nr = 1; if (vma->vm_flags & VM_LOCKED) { ptes++; pra->mapcount--; /* Only mlock fully mapped pages */ if (pvmw.pte && ptes != pvmw.nr_pages) continue; /* * All PTEs must be protected by page table lock in * order to mlock the page. * * If page table boundary has been cross, current ptl * only protect part of ptes. */ if (pvmw.flags & PVMW_PGTABLE_CROSSED) continue; /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); page_vma_mapped_walk_done(&pvmw); pra->vm_flags |= VM_LOCKED; return false; /* To break the loop */ } /* * Skip the non-shared swapbacked folio mapped solely by * the exiting or OOM-reaped process. This avoids redundant * swap-out followed by an immediate unmap. */ if ((!atomic_read(&vma->vm_mm->mm_users) || check_stable_address_space(vma->vm_mm)) && folio_test_anon(folio) && folio_test_swapbacked(folio) && !folio_maybe_mapped_shared(folio)) { pra->referenced = -1; page_vma_mapped_walk_done(&pvmw); return false; } if (pvmw.pte && folio_test_large(folio)) { const unsigned long end_addr = pmd_addr_end(address, vma->vm_end); const unsigned int max_nr = (end_addr - address) >> PAGE_SHIFT; pte_t pteval = ptep_get(pvmw.pte); nr = folio_pte_batch(folio, pvmw.pte, pteval, max_nr); } /* * When LRU is switching, we don’t know where the surrounding folios * are. —they could be on active/inactive lists or on MGLRU. So the * simplest approach is to disable this look-around optimization. */ if (lru_gen_enabled() && !lru_gen_switching() && pvmw.pte) { if (lru_gen_look_around(&pvmw, nr)) referenced++; } else if (pvmw.pte) { if (clear_flush_young_ptes_notify(vma, address, pvmw.pte, nr)) referenced++; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) referenced++; } else { /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); } ptes += nr; pra->mapcount -= nr; /* * If we are sure that we batched the entire folio, * we can just optimize and stop right here. */ if (ptes == pvmw.nr_pages) { page_vma_mapped_walk_done(&pvmw); break; } /* Skip the batched PTEs */ pvmw.pte += nr - 1; pvmw.address += (nr - 1) * PAGE_SIZE; } if (referenced) folio_clear_idle(folio); if (folio_test_clear_young(folio)) referenced++; if (referenced) { pra->referenced++; pra->vm_flags |= vma->vm_flags & ~VM_LOCKED; } if (!pra->mapcount) return false; /* To break the loop */ return true; } static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg) { struct folio_referenced_arg *pra = arg; struct mem_cgroup *memcg = pra->memcg; /* * Ignore references from this mapping if it has no recency. If the * folio has been used in another mapping, we will catch it; if this * other mapping is already gone, the unmap path will have set the * referenced flag or activated the folio in zap_pte_range(). */ if (!vma_has_recency(vma)) return true; /* * If we are reclaiming on behalf of a cgroup, skip counting on behalf * of references from different cgroups. */ if (memcg && !mm_match_cgroup(vma->vm_mm, memcg)) return true; return false; } /** * folio_referenced() - Test if the folio was referenced. * @folio: The folio to test. * @is_locked: Caller holds lock on the folio. * @memcg: target memory cgroup * @vm_flags: A combination of all the vma->vm_flags which referenced the folio. * * Quick test_and_clear_referenced for all mappings of a folio, * * Return: The number of mappings which referenced the folio. Return -1 if * the function bailed out due to rmap lock contention. */ int folio_referenced(struct folio *folio, int is_locked, struct mem_cgroup *memcg, vm_flags_t *vm_flags) { bool we_locked = false; struct folio_referenced_arg pra = { .mapcount = folio_mapcount(folio), .memcg = memcg, }; struct rmap_walk_control rwc = { .rmap_one = folio_referenced_one, .arg = (void *)&pra, .anon_lock = folio_lock_anon_vma_read, .try_lock = true, .invalid_vma = invalid_folio_referenced_vma, }; VM_WARN_ON_ONCE_FOLIO(folio_is_zone_device(folio), folio); *vm_flags = 0; if (!pra.mapcount) return 0; if (!folio_raw_mapping(folio)) return 0; if (!is_locked) { we_locked = folio_trylock(folio); if (!we_locked) return 1; } rmap_walk(folio, &rwc); *vm_flags = pra.vm_flags; if (we_locked) folio_unlock(folio); return rwc.contended ? -1 : pra.referenced; } static int page_vma_mkclean_one(struct page_vma_mapped_walk *pvmw) { int cleaned = 0; struct vm_area_struct *vma = pvmw->vma; struct mmu_notifier_range range; unsigned long address = pvmw->address; /* * We have to assume the worse case ie pmd for invalidation. Note that * the folio can not be freed from this function. */ mmu_notifier_range_init(&range, MMU_NOTIFY_PROTECTION_PAGE, 0, vma->vm_mm, address, vma_address_end(pvmw)); mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(pvmw)) { int ret = 0; address = pvmw->address; if (pvmw->pte) { pte_t *pte = pvmw->pte; pte_t entry = ptep_get(pte); /* * PFN swap PTEs, such as device-exclusive ones, that * actually map pages are clean and not writable from a * CPU perspective. The MMU notifier takes care of any * device aspects. */ if (!pte_present(entry)) continue; if (!pte_dirty(entry) && !pte_write(entry)) continue; flush_cache_page(vma, address, pte_pfn(entry)); entry = ptep_clear_flush(vma, address, pte); entry = pte_wrprotect(entry); entry = pte_mkclean(entry); set_pte_at(vma->vm_mm, address, pte, entry); ret = 1; } else { #ifdef CONFIG_TRANSPARENT_HUGEPAGE pmd_t *pmd = pvmw->pmd; pmd_t entry = pmdp_get(pmd); /* * Please see the comment above (!pte_present). * A non present PMD is not writable from a CPU * perspective. */ if (!pmd_present(entry)) continue; if (!pmd_dirty(entry) && !pmd_write(entry)) continue; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); entry = pmdp_invalidate(vma, address, pmd); entry = pmd_wrprotect(entry); entry = pmd_mkclean(entry); set_pmd_at(vma->vm_mm, address, pmd, entry); ret = 1; #else /* unexpected pmd-mapped folio? */ WARN_ON_ONCE(1); #endif } if (ret) cleaned++; } mmu_notifier_invalidate_range_end(&range); return cleaned; } static bool page_mkclean_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, PVMW_SYNC); int *cleaned = arg; *cleaned += page_vma_mkclean_one(&pvmw); return true; } static bool invalid_mkclean_vma(struct vm_area_struct *vma, void *arg) { if (vma->vm_flags & VM_SHARED) return false; return true; } int folio_mkclean(struct folio *folio) { int cleaned = 0; struct address_space *mapping; struct rmap_walk_control rwc = { .arg = (void *)&cleaned, .rmap_one = page_mkclean_one, .invalid_vma = invalid_mkclean_vma, }; BUG_ON(!folio_test_locked(folio)); if (!folio_mapped(folio)) return 0; mapping = folio_mapping(folio); if (!mapping) return 0; rmap_walk(folio, &rwc); return cleaned; } EXPORT_SYMBOL_GPL(folio_mkclean); struct wrprotect_file_state { int cleaned; pgoff_t pgoff; unsigned long pfn; unsigned long nr_pages; }; static bool mapping_wrprotect_range_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct wrprotect_file_state *state = (struct wrprotect_file_state *)arg; struct page_vma_mapped_walk pvmw = { .pfn = state->pfn, .nr_pages = state->nr_pages, .pgoff = state->pgoff, .vma = vma, .address = address, .flags = PVMW_SYNC, }; state->cleaned += page_vma_mkclean_one(&pvmw); return true; } static void __rmap_walk_file(struct folio *folio, struct address_space *mapping, pgoff_t pgoff_start, unsigned long nr_pages, struct rmap_walk_control *rwc, bool locked); /** * mapping_wrprotect_range() - Write-protect all mappings in a specified range. * * @mapping: The mapping whose reverse mapping should be traversed. * @pgoff: The page offset at which @pfn is mapped within @mapping. * @pfn: The PFN of the page mapped in @mapping at @pgoff. * @nr_pages: The number of physically contiguous base pages spanned. * * Traverses the reverse mapping, finding all VMAs which contain a shared * mapping of the pages in the specified range in @mapping, and write-protects * them (that is, updates the page tables to mark the mappings read-only such * that a write protection fault arises when the mappings are written to). * * The @pfn value need not refer to a folio, but rather can reference a kernel * allocation which is mapped into userland. We therefore do not require that * the page maps to a folio with a valid mapping or index field, rather the * caller specifies these in @mapping and @pgoff. * * Return: the number of write-protected PTEs, or an error. */ int mapping_wrprotect_range(struct address_space *mapping, pgoff_t pgoff, unsigned long pfn, unsigned long nr_pages) { struct wrprotect_file_state state = { .cleaned = 0, .pgoff = pgoff, .pfn = pfn, .nr_pages = nr_pages, }; struct rmap_walk_control rwc = { .arg = (void *)&state, .rmap_one = mapping_wrprotect_range_one, .invalid_vma = invalid_mkclean_vma, }; if (!mapping) return 0; __rmap_walk_file(/* folio = */NULL, mapping, pgoff, nr_pages, &rwc, /* locked = */false); return state.cleaned; } EXPORT_SYMBOL_GPL(mapping_wrprotect_range); /** * pfn_mkclean_range - Cleans the PTEs (including PMDs) mapped with range of * [@pfn, @pfn + @nr_pages) at the specific offset (@pgoff) * within the @vma of shared mappings. And since clean PTEs * should also be readonly, write protects them too. * @pfn: start pfn. * @nr_pages: number of physically contiguous pages srarting with @pfn. * @pgoff: page offset that the @pfn mapped with. * @vma: vma that @pfn mapped within. * * Returns the number of cleaned PTEs (including PMDs). */ int pfn_mkclean_range(unsigned long pfn, unsigned long nr_pages, pgoff_t pgoff, struct vm_area_struct *vma) { struct page_vma_mapped_walk pvmw = { .pfn = pfn, .nr_pages = nr_pages, .pgoff = pgoff, .vma = vma, .flags = PVMW_SYNC, }; if (invalid_mkclean_vma(vma, NULL)) return 0; pvmw.address = vma_address(vma, pgoff, nr_pages); VM_BUG_ON_VMA(pvmw.address == -EFAULT, vma); return page_vma_mkclean_one(&pvmw); } static void __folio_mod_stat(struct folio *folio, int nr, int nr_pmdmapped) { int idx; if (nr) { idx = folio_test_anon(folio) ? NR_ANON_MAPPED : NR_FILE_MAPPED; lruvec_stat_mod_folio(folio, idx, nr); } if (nr_pmdmapped) { if (folio_test_anon(folio)) { idx = NR_ANON_THPS; lruvec_stat_mod_folio(folio, idx, nr_pmdmapped); } else { /* NR_*_PMDMAPPED are not maintained per-memcg */ idx = folio_test_swapbacked(folio) ? NR_SHMEM_PMDMAPPED : NR_FILE_PMDMAPPED; __mod_node_page_state(folio_pgdat(folio), idx, nr_pmdmapped); } } } static __always_inline void __folio_add_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; const int orig_nr_pages = nr_pages; int first = 0, nr = 0, nr_pmdmapped = 0; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case PGTABLE_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_inc_and_test(&folio->_mapcount); break; } if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { nr = folio_add_return_large_mapcount(folio, orig_nr_pages, vma); if (nr == orig_nr_pages) /* Was completely unmapped. */ nr = folio_large_nr_pages(folio); else nr = 0; break; } do { first += atomic_inc_and_test(&page->_mapcount); } while (page++, --nr_pages > 0); if (first && atomic_add_return_relaxed(first, mapped) < ENTIRELY_MAPPED) nr = first; folio_add_large_mapcount(folio, orig_nr_pages, vma); break; case PGTABLE_LEVEL_PMD: case PGTABLE_LEVEL_PUD: first = atomic_inc_and_test(&folio->_entire_mapcount); if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { if (level == PGTABLE_LEVEL_PMD && first) nr_pmdmapped = folio_large_nr_pages(folio); nr = folio_inc_return_large_mapcount(folio, vma); if (nr == 1) /* Was completely unmapped. */ nr = folio_large_nr_pages(folio); else nr = 0; break; } if (first) { nr = atomic_add_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED + ENTIRELY_MAPPED)) { nr_pages = folio_large_nr_pages(folio); /* * We only track PMD mappings of PMD-sized * folios separately. */ if (level == PGTABLE_LEVEL_PMD) nr_pmdmapped = nr_pages; nr = nr_pages - (nr & FOLIO_PAGES_MAPPED); /* Raced ahead of a remove and another add? */ if (unlikely(nr < 0)) nr = 0; } else { /* Raced ahead of a remove of ENTIRELY_MAPPED */ nr = 0; } } folio_inc_large_mapcount(folio, vma); break; default: BUILD_BUG(); } __folio_mod_stat(folio, nr, nr_pmdmapped); } /** * folio_move_anon_rmap - move a folio to our anon_vma * @folio: The folio to move to our anon_vma * @vma: The vma the folio belongs to * * When a folio belongs exclusively to one process after a COW event, * that folio can be moved into the anon_vma that belongs to just that * process, so the rmap code will not search the parent or sibling processes. */ void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma) { void *anon_vma = vma->anon_vma; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_VMA(!anon_vma, vma); anon_vma += FOLIO_MAPPING_ANON; /* * Ensure that anon_vma and the FOLIO_MAPPING_ANON bit are written * simultaneously, so a concurrent reader (eg folio_referenced()'s * folio_test_anon()) will not see one without the other. */ WRITE_ONCE(folio->mapping, anon_vma); } /** * __folio_set_anon - set up a new anonymous rmap for a folio * @folio: The folio to set up the new anonymous rmap for. * @vma: VM area to add the folio to. * @address: User virtual address of the mapping * @exclusive: Whether the folio is exclusive to the process. */ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma, unsigned long address, bool exclusive) { struct anon_vma *anon_vma = vma->anon_vma; BUG_ON(!anon_vma); /* * If the folio isn't exclusive to this vma, we must use the _oldest_ * possible anon_vma for the folio mapping! */ if (!exclusive) anon_vma = anon_vma->root; /* * page_idle does a lockless/optimistic rmap scan on folio->mapping. * Make sure the compiler doesn't split the stores of anon_vma and * the FOLIO_MAPPING_ANON type identifier, otherwise the rmap code * could mistake the mapping for a struct address_space and crash. */ anon_vma = (void *) anon_vma + FOLIO_MAPPING_ANON; WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma); folio->index = linear_page_index(vma, address); } /** * __page_check_anon_rmap - sanity check anonymous rmap addition * @folio: The folio containing @page. * @page: the page to check the mapping of * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped */ static void __page_check_anon_rmap(const struct folio *folio, const struct page *page, struct vm_area_struct *vma, unsigned long address) { /* * The page's anon-rmap details (mapping and index) are guaranteed to * be set up correctly at this point. * * We have exclusion against folio_add_anon_rmap_*() because the caller * always holds the page locked. * * We have exclusion against folio_add_new_anon_rmap because those pages * are initially only visible via the pagetables, and the pte is locked * over the call to folio_add_new_anon_rmap. */ VM_BUG_ON_FOLIO(folio_anon_vma(folio)->root != vma->anon_vma->root, folio); VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address), page); } static __always_inline void __folio_add_anon_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags, enum pgtable_level level) { int i; VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); __folio_add_rmap(folio, page, nr_pages, vma, level); if (likely(!folio_test_ksm(folio))) __page_check_anon_rmap(folio, page, vma, address); if (flags & RMAP_EXCLUSIVE) { switch (level) { case PGTABLE_LEVEL_PTE: for (i = 0; i < nr_pages; i++) SetPageAnonExclusive(page + i); break; case PGTABLE_LEVEL_PMD: SetPageAnonExclusive(page); break; case PGTABLE_LEVEL_PUD: /* * Keep the compiler happy, we don't support anonymous * PUD mappings. */ WARN_ON_ONCE(1); break; default: BUILD_BUG(); } } VM_WARN_ON_FOLIO(!folio_test_large(folio) && PageAnonExclusive(page) && atomic_read(&folio->_mapcount) > 0, folio); for (i = 0; i < nr_pages; i++) { struct page *cur_page = page + i; VM_WARN_ON_FOLIO(folio_test_large(folio) && folio_entire_mapcount(folio) > 1 && PageAnonExclusive(cur_page), folio); if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) continue; /* * While PTE-mapping a THP we have a PMD and a PTE * mapping. */ VM_WARN_ON_FOLIO(atomic_read(&cur_page->_mapcount) > 0 && PageAnonExclusive(cur_page), folio); } /* * Only mlock it if the folio is fully mapped to the VMA. * * Partially mapped folios can be split on reclaim and part outside * of mlocked VMA can be evicted or freed. */ if (folio_nr_pages(folio) == nr_pages) mlock_vma_folio(folio, vma); } /** * folio_add_anon_rmap_ptes - add PTE mappings to a page range of an anon folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages which will be mapped * @vma: The vm area in which the mappings are added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + nr_pages) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting, * and to ensure that an anon folio is not being upgraded racily to a KSM folio * (but KSM folios are never downgraded). */ void folio_add_anon_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { __folio_add_anon_rmap(folio, page, nr_pages, vma, address, flags, PGTABLE_LEVEL_PTE); } /** * folio_add_anon_rmap_pmd - add a PMD mapping to a page range of an anon folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * @address: The user virtual address of the first page to map * @flags: The rmap flags * * The page range of folio is defined by [first_page, first_page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock, and the page must be locked in * the anon_vma case: to serialize mapping,index checking after setting. */ void folio_add_anon_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_anon_rmap(folio, page, HPAGE_PMD_NR, vma, address, flags, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_new_anon_rmap - Add mapping to a new anonymous folio. * @folio: The folio to add the mapping to. * @vma: the vm area in which the mapping is added * @address: the user virtual address mapped * @flags: The rmap flags * * Like folio_add_anon_rmap_*() but must only be called on *new* folios. * This means the inc-and-test can be bypassed. * The folio doesn't necessarily need to be locked while it's exclusive * unless two threads map it concurrently. However, the folio must be * locked if it's shared. * * If the folio is pmd-mappable, it is accounted as a THP. */ void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { const bool exclusive = flags & RMAP_EXCLUSIVE; int nr = 1, nr_pmdmapped = 0; VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!exclusive && !folio_test_locked(folio), folio); /* * VM_DROPPABLE mappings don't swap; instead they're just dropped when * under memory pressure. */ if (!folio_test_swapbacked(folio) && !(vma->vm_flags & VM_DROPPABLE)) __folio_set_swapbacked(folio); __folio_set_anon(folio, vma, address, exclusive); if (likely(!folio_test_large(folio))) { /* increment count (starts at -1) */ atomic_set(&folio->_mapcount, 0); if (exclusive) SetPageAnonExclusive(&folio->page); } else if (!folio_test_pmd_mappable(folio)) { int i; nr = folio_large_nr_pages(folio); for (i = 0; i < nr; i++) { struct page *page = folio_page(folio, i); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) /* increment count (starts at -1) */ atomic_set(&page->_mapcount, 0); if (exclusive) SetPageAnonExclusive(page); } folio_set_large_mapcount(folio, nr, vma); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, nr); } else { nr = folio_large_nr_pages(folio); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); folio_set_large_mapcount(folio, 1, vma); if (IS_ENABLED(CONFIG_PAGE_MAPCOUNT)) atomic_set(&folio->_nr_pages_mapped, ENTIRELY_MAPPED); if (exclusive) SetPageAnonExclusive(&folio->page); nr_pmdmapped = nr; } VM_WARN_ON_ONCE(address < vma->vm_start || address + (nr << PAGE_SHIFT) > vma->vm_end); __folio_mod_stat(folio, nr, nr_pmdmapped); mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1); } static __always_inline void __folio_add_file_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { VM_WARN_ON_FOLIO(folio_test_anon(folio), folio); __folio_add_rmap(folio, page, nr_pages, vma, level); /* * Only mlock it if the folio is fully mapped to the VMA. * * Partially mapped folios can be split on reclaim and part outside * of mlocked VMA can be evicted or freed. */ if (folio_nr_pages(folio) == nr_pages) mlock_vma_folio(folio, vma); } /** * folio_add_file_rmap_ptes - add PTE mappings to a page range of a folio * @folio: The folio to add the mappings to * @page: The first page to add * @nr_pages: The number of pages that will be mapped using PTEs * @vma: The vm area in which the mappings are added * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_add_file_rmap(folio, page, nr_pages, vma, PGTABLE_LEVEL_PTE); } /** * folio_add_file_rmap_pmd - add a PMD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_add_file_rmap(folio, page, HPAGE_PMD_NR, vma, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_add_file_rmap_pud - add a PUD mapping to a page range of a folio * @folio: The folio to add the mapping to * @page: The first page to add * @vma: The vm area in which the mapping is added * * The page range of the folio is defined by [page, page + HPAGE_PUD_NR) * * The caller needs to hold the page table lock. */ void folio_add_file_rmap_pud(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) __folio_add_file_rmap(folio, page, HPAGE_PUD_NR, vma, PGTABLE_LEVEL_PUD); #else WARN_ON_ONCE(true); #endif } static __always_inline void __folio_remove_rmap(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma, enum pgtable_level level) { atomic_t *mapped = &folio->_nr_pages_mapped; int last = 0, nr = 0, nr_pmdmapped = 0; bool partially_mapped = false; __folio_rmap_sanity_checks(folio, page, nr_pages, level); switch (level) { case PGTABLE_LEVEL_PTE: if (!folio_test_large(folio)) { nr = atomic_add_negative(-1, &folio->_mapcount); break; } if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { nr = folio_sub_return_large_mapcount(folio, nr_pages, vma); if (!nr) { /* Now completely unmapped. */ nr = folio_large_nr_pages(folio); } else { partially_mapped = nr < folio_large_nr_pages(folio) && !folio_entire_mapcount(folio); nr = 0; } break; } folio_sub_large_mapcount(folio, nr_pages, vma); do { last += atomic_add_negative(-1, &page->_mapcount); } while (page++, --nr_pages > 0); if (last && atomic_sub_return_relaxed(last, mapped) < ENTIRELY_MAPPED) nr = last; partially_mapped = nr && atomic_read(mapped); break; case PGTABLE_LEVEL_PMD: case PGTABLE_LEVEL_PUD: if (IS_ENABLED(CONFIG_NO_PAGE_MAPCOUNT)) { last = atomic_add_negative(-1, &folio->_entire_mapcount); if (level == PGTABLE_LEVEL_PMD && last) nr_pmdmapped = folio_large_nr_pages(folio); nr = folio_dec_return_large_mapcount(folio, vma); if (!nr) { /* Now completely unmapped. */ nr = folio_large_nr_pages(folio); } else { partially_mapped = last && nr < folio_large_nr_pages(folio); nr = 0; } break; } folio_dec_large_mapcount(folio, vma); last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { nr = atomic_sub_return_relaxed(ENTIRELY_MAPPED, mapped); if (likely(nr < ENTIRELY_MAPPED)) { nr_pages = folio_large_nr_pages(folio); if (level == PGTABLE_LEVEL_PMD) nr_pmdmapped = nr_pages; nr = nr_pages - nr; /* Raced ahead of another remove and an add? */ if (unlikely(nr < 0)) nr = 0; } else { /* An add of ENTIRELY_MAPPED raced ahead */ nr = 0; } } partially_mapped = nr && nr < nr_pmdmapped; break; default: BUILD_BUG(); } /* * Queue anon large folio for deferred split if at least one page of * the folio is unmapped and at least one page is still mapped. * * Check partially_mapped first to ensure it is a large folio. * * Device private folios do not support deferred splitting and * shrinker based scanning of the folios to free. */ if (partially_mapped && folio_test_anon(folio) && !folio_test_partially_mapped(folio) && !folio_is_device_private(folio)) deferred_split_folio(folio, true); __folio_mod_stat(folio, -nr, -nr_pmdmapped); /* * It would be tidy to reset folio_test_anon mapping when fully * unmapped, but that might overwrite a racing folio_add_anon_rmap_*() * which increments mapcount after us but sets mapping before us: * so leave the reset to free_pages_prepare, and remember that * it's only reliable while mapped. */ munlock_vma_folio(folio, vma); } /** * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio * @folio: The folio to remove the mappings from * @page: The first page to remove * @nr_pages: The number of pages that will be removed from the mapping * @vma: The vm area from which the mappings are removed * * The page range of the folio is defined by [page, page + nr_pages) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_ptes(struct folio *folio, struct page *page, int nr_pages, struct vm_area_struct *vma) { __folio_remove_rmap(folio, page, nr_pages, vma, PGTABLE_LEVEL_PTE); } /** * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pmd(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE __folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, PGTABLE_LEVEL_PMD); #else WARN_ON_ONCE(true); #endif } /** * folio_remove_rmap_pud - remove a PUD mapping from a page range of a folio * @folio: The folio to remove the mapping from * @page: The first page to remove * @vma: The vm area from which the mapping is removed * * The page range of the folio is defined by [page, page + HPAGE_PUD_NR) * * The caller needs to hold the page table lock. */ void folio_remove_rmap_pud(struct folio *folio, struct page *page, struct vm_area_struct *vma) { #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \ defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) __folio_remove_rmap(folio, page, HPAGE_PUD_NR, vma, PGTABLE_LEVEL_PUD); #else WARN_ON_ONCE(true); #endif } static inline unsigned int folio_unmap_pte_batch(struct folio *folio, struct page_vma_mapped_walk *pvmw, enum ttu_flags flags, pte_t pte) { unsigned long end_addr, addr = pvmw->address; struct vm_area_struct *vma = pvmw->vma; unsigned int max_nr; if (flags & TTU_HWPOISON) return 1; if (!folio_test_large(folio)) return 1; /* We may only batch within a single VMA and a single page table. */ end_addr = pmd_addr_end(addr, vma->vm_end); max_nr = (end_addr - addr) >> PAGE_SHIFT; /* We only support lazyfree or file folios batching for now ... */ if (folio_test_anon(folio) && folio_test_swapbacked(folio)) return 1; if (pte_unused(pte)) return 1; if (userfaultfd_wp(vma)) return 1; /* * If unmap fails, we need to restore the ptes. To avoid accidentally * upgrading write permissions for ptes that were not originally * writable, and to avoid losing the soft-dirty bit, use the * appropriate FPB flags. */ return folio_pte_batch_flags(folio, vma, pvmw->pte, &pte, max_nr, FPB_RESPECT_WRITE | FPB_RESPECT_SOFT_DIRTY); } /* * @arg: enum ttu_flags will be passed to this argument */ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); bool anon_exclusive, ret = true; pte_t pteval; struct page *subpage; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long nr_pages = 1, end_addr; unsigned long pfn; unsigned long hsz = 0; int ptes = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_unmap() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the folio can not be freed in this function as call of * try_to_unmap() must hold a reference on the folio. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* * If the folio is in an mlock()d vma, we must not swap it out. */ if (!(flags & TTU_IGNORE_MLOCK) && (vma->vm_flags & VM_LOCKED)) { ptes++; /* * Set 'ret' to indicate the page cannot be unmapped. * * Do not jump to walk_abort immediately as additional * iteration might be required to detect fully mapped * folio an mlock it. */ ret = false; /* Only mlock fully mapped pages */ if (pvmw.pte && ptes != pvmw.nr_pages) continue; /* * All PTEs must be protected by page table lock in * order to mlock the page. * * If page table boundary has been cross, current ptl * only protect part of ptes. */ if (pvmw.flags & PVMW_PGTABLE_CROSSED) goto walk_done; /* Restore the mlock which got missed */ mlock_vma_folio(folio, vma); goto walk_done; } if (!pvmw.pte) { if (folio_test_lazyfree(folio)) { if (unmap_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, folio)) goto walk_done; /* * unmap_huge_pmd_locked has either already marked * the folio as swap-backed or decided to retain it * due to GUP or speculative references. */ goto walk_abort; } if (flags & TTU_SPLIT_HUGE_PMD) { /* * We temporarily have to drop the PTL and * restart so we can process the PTE-mapped THP. */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, false); flags &= ~TTU_SPLIT_HUGE_PMD; page_vma_mapped_walk_restart(&pvmw); continue; } } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); /* * Handle PFN swap PTEs, such as device-exclusive ones, that * actually map pages. */ pteval = ptep_get(pvmw.pte); if (likely(pte_present(pteval))) { pfn = pte_pfn(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pfn = softleaf_to_pfn(entry); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); } subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * The try_to_unmap() is only passed a hugetlb page * in the case where the hugetlb page is poisoned. */ VM_BUG_ON_PAGE(!PageHWPoison(subpage), subpage); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and fail * if unsuccessful. */ if (!anon) { struct mmu_gather tlb; VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) goto walk_abort; tlb_gather_mmu_vma(&tlb, vma); if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); huge_pmd_unshare_flush(&tlb, vma); tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. */ goto walk_done; } hugetlb_vma_unlock_write(vma); tlb_finish_mmu(&tlb); } pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) folio_mark_dirty(folio); } else if (likely(pte_present(pteval))) { nr_pages = folio_unmap_pte_batch(folio, &pvmw, flags, pteval); end_addr = address + nr_pages * PAGE_SIZE; flush_cache_range(vma, address, end_addr); /* Nuke the page table entry. */ pteval = get_and_clear_ptes(mm, address, pvmw.pte, nr_pages); /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ if (should_defer_flush(mm, flags)) set_tlb_ubc_flush_pending(mm, pteval, address, end_addr); else flush_tlb_range(vma, address, end_addr); if (pte_dirty(pteval)) folio_mark_dirty(folio); } else { pte_clear(mm, address, pvmw.pte); } /* * Now the pte is cleared. If this pte was uffd-wp armed, * we may want to replace a none pte with a marker pte if * it's file-backed, so we don't lose the tracking info. */ pte_install_uffd_wp_if_needed(vma, address, pvmw.pte, pteval); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage) && (flags & TTU_HWPOISON)) { pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (likely(pte_present(pteval)) && pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else if (folio_test_anon(folio)) { swp_entry_t entry = page_swap_entry(subpage); pte_t swp_pte; /* * Store the swap location in the pte. * See handle_pte_fault() ... */ if (unlikely(folio_test_swapbacked(folio) != folio_test_swapcache(folio))) { WARN_ON_ONCE(1); goto walk_abort; } /* MADV_FREE page check */ if (!folio_test_swapbacked(folio)) { int ref_count, map_count; /* * Synchronize with gup_pte_range(): * - clear PTE; barrier; read refcount * - inc refcount; barrier; read PTE */ smp_mb(); ref_count = folio_ref_count(folio); map_count = folio_mapcount(folio); /* * Order reads for page refcount and dirty flag * (see comments in __remove_mapping()). */ smp_rmb(); if (folio_test_dirty(folio) && !(vma->vm_flags & VM_DROPPABLE)) { /* * redirtied either using the page table or a previously * obtained GUP reference. */ set_ptes(mm, address, pvmw.pte, pteval, nr_pages); folio_set_swapbacked(folio); goto walk_abort; } else if (ref_count != 1 + map_count) { /* * Additional reference. Could be a GUP reference or any * speculative reference. GUP users must mark the folio * dirty if there was a modification. This folio cannot be * reclaimed right now either way, so act just like nothing * happened. * We'll come back here later and detect if the folio was * dirtied when the additional reference is gone. */ set_ptes(mm, address, pvmw.pte, pteval, nr_pages); goto walk_abort; } add_mm_counter(mm, MM_ANONPAGES, -nr_pages); goto discard; } if (folio_dup_swap(folio, subpage) < 0) { set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* * arch_unmap_one() is expected to be a NOP on * architectures where we could have PFN swap PTEs, * so we'll not check/care. */ if (arch_unmap_one(mm, vma, address, pteval) < 0) { folio_put_swap(folio, subpage); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } /* See folio_try_share_anon_rmap(): clear PTE first. */ if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { folio_put_swap(folio, subpage); set_pte_at(mm, address, pvmw.pte, pteval); goto walk_abort; } if (list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); if (list_empty(&mm->mmlist)) list_add(&mm->mmlist, &init_mm.mmlist); spin_unlock(&mmlist_lock); } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); swp_pte = swp_entry_to_pte(entry); if (anon_exclusive) swp_pte = pte_swp_mkexclusive(swp_pte); if (likely(pte_present(pteval))) { if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } else { if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } set_pte_at(mm, address, pvmw.pte, swp_pte); } else { /* * This is a locked file-backed folio, * so it cannot be removed from the page * cache and replaced by a new folio before * mmu_notifier_invalidate_range_end, so no * concurrent thread might update its page table * to point at a new folio while a device is * still using this folio. * * See Documentation/mm/mmu_notifier.rst */ add_mm_counter(mm, mm_counter_file(folio), -nr_pages); } discard: if (unlikely(folio_test_hugetlb(folio))) { hugetlb_remove_rmap(folio); } else { folio_remove_rmap_ptes(folio, subpage, nr_pages, vma); } if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put_refs(folio, nr_pages); /* * If we are sure that we batched the entire folio and cleared * all PTEs, we can just optimize and stop right here. */ if (nr_pages == folio_nr_pages(folio)) goto walk_done; continue; walk_abort: ret = false; walk_done: page_vma_mapped_walk_done(&pvmw); break; } mmu_notifier_invalidate_range_end(&range); return ret; } static bool invalid_migration_vma(struct vm_area_struct *vma, void *arg) { return vma_is_temporary_stack(vma); } static int folio_not_mapped(struct folio *folio) { return !folio_mapped(folio); } /** * try_to_unmap - Try to remove all page table mappings to a folio. * @folio: The folio to unmap. * @flags: action and flags * * Tries to remove all the page table entries which are mapping this * folio. It is the caller's responsibility to check if the folio is * still mapped if needed (use TTU_SYNC to prevent accounting races). * * Context: Caller must hold the folio lock. */ void try_to_unmap(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } /* * @arg: enum ttu_flags will be passed to this argument. * * If TTU_SPLIT_HUGE_PMD is specified any PMD mappings will be split into PTEs * containing migration entries. */ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma, unsigned long address, void *arg) { struct mm_struct *mm = vma->vm_mm; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); bool anon_exclusive, writable, ret = true; pte_t pteval; struct page *subpage; struct mmu_notifier_range range; enum ttu_flags flags = (enum ttu_flags)(long)arg; unsigned long pfn; unsigned long hsz = 0; /* * When racing against e.g. zap_pte_range() on another cpu, * in between its ptep_get_and_clear_full() and folio_remove_rmap_*(), * try_to_migrate() may return before page_mapped() has become false, * if page table locking is skipped: use TTU_SYNC to wait for that. */ if (flags & TTU_SYNC) pvmw.flags = PVMW_SYNC; /* * For THP, we have to assume the worse case ie pmd for invalidation. * For hugetlb, it could be much worse if we need to do pud * invalidation in the case of pmd sharing. * * Note that the page can not be free in this function as call of * try_to_unmap() must hold a reference on the page. */ range.end = vma_address_end(&pvmw); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, range.end); if (folio_test_hugetlb(folio)) { /* * If sharing is possible, start and end will be adjusted * accordingly. */ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end); /* We need the huge page size for set_huge_pte_at() */ hsz = huge_page_size(hstate_vma(vma)); } mmu_notifier_invalidate_range_start(&range); while (page_vma_mapped_walk(&pvmw)) { /* PMD-mapped THP migration entry */ if (!pvmw.pte) { __maybe_unused unsigned long pfn; __maybe_unused pmd_t pmdval; if (flags & TTU_SPLIT_HUGE_PMD) { /* * split_huge_pmd_locked() might leave the * folio mapped through PTEs. Retry the walk * so we can detect this scenario and properly * abort the walk. */ split_huge_pmd_locked(vma, pvmw.address, pvmw.pmd, true); flags &= ~TTU_SPLIT_HUGE_PMD; page_vma_mapped_walk_restart(&pvmw); continue; } #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION pmdval = pmdp_get(pvmw.pmd); if (likely(pmd_present(pmdval))) pfn = pmd_pfn(pmdval); else pfn = softleaf_to_pfn(softleaf_from_pmd(pmdval)); subpage = folio_page(folio, pfn - folio_pfn(folio)); VM_BUG_ON_FOLIO(folio_test_hugetlb(folio) || !folio_test_pmd_mappable(folio), folio); if (set_pmd_migration_entry(&pvmw, subpage)) { ret = false; page_vma_mapped_walk_done(&pvmw); break; } continue; #endif } /* Unexpected PMD-mapped THP? */ VM_BUG_ON_FOLIO(!pvmw.pte, folio); /* * Handle PFN swap PTEs, such as device-exclusive ones, that * actually map pages. */ pteval = ptep_get(pvmw.pte); if (likely(pte_present(pteval))) { pfn = pte_pfn(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pfn = softleaf_to_pfn(entry); VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); } subpage = folio_page(folio, pfn - folio_pfn(folio)); address = pvmw.address; anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(subpage); if (folio_test_hugetlb(folio)) { bool anon = folio_test_anon(folio); /* * huge_pmd_unshare may unmap an entire PMD page. * There is no way of knowing exactly which PMDs may * be cached for this mm, so we must flush them all. * start/end were already adjusted above to cover this * range. */ flush_cache_range(vma, range.start, range.end); /* * To call huge_pmd_unshare, i_mmap_rwsem must be * held in write mode. Caller needs to explicitly * do this outside rmap routines. * * We also must hold hugetlb vma_lock in write mode. * Lock order dictates acquiring vma_lock BEFORE * i_mmap_rwsem. We can only try lock here and * fail if unsuccessful. */ if (!anon) { struct mmu_gather tlb; VM_BUG_ON(!(flags & TTU_RMAP_LOCKED)); if (!hugetlb_vma_trylock_write(vma)) { page_vma_mapped_walk_done(&pvmw); ret = false; break; } tlb_gather_mmu_vma(&tlb, vma); if (huge_pmd_unshare(&tlb, vma, address, pvmw.pte)) { hugetlb_vma_unlock_write(vma); huge_pmd_unshare_flush(&tlb, vma); tlb_finish_mmu(&tlb); /* * The PMD table was unmapped, * consequently unmapping the folio. */ page_vma_mapped_walk_done(&pvmw); break; } hugetlb_vma_unlock_write(vma); tlb_finish_mmu(&tlb); } /* Nuke the hugetlb page table entry */ pteval = huge_ptep_clear_flush(vma, address, pvmw.pte); if (pte_dirty(pteval)) folio_mark_dirty(folio); writable = pte_write(pteval); } else if (likely(pte_present(pteval))) { flush_cache_page(vma, address, pfn); /* Nuke the page table entry. */ if (should_defer_flush(mm, flags)) { /* * We clear the PTE but do not flush so potentially * a remote CPU could still be writing to the folio. * If the entry was previously clean then the * architecture must guarantee that a clear->dirty * transition on a cached TLB entry is written through * and traps if the PTE is unmapped. */ pteval = ptep_get_and_clear(mm, address, pvmw.pte); set_tlb_ubc_flush_pending(mm, pteval, address, address + PAGE_SIZE); } else { pteval = ptep_clear_flush(vma, address, pvmw.pte); } if (pte_dirty(pteval)) folio_mark_dirty(folio); writable = pte_write(pteval); } else { const softleaf_t entry = softleaf_from_pte(pteval); pte_clear(mm, address, pvmw.pte); writable = softleaf_is_device_private_write(entry); } VM_WARN_ON_FOLIO(writable && folio_test_anon(folio) && !anon_exclusive, folio); /* Update high watermark before we lower rss */ update_hiwater_rss(mm); if (PageHWPoison(subpage)) { VM_WARN_ON_FOLIO(folio_is_device_private(folio), folio); pteval = swp_entry_to_pte(make_hwpoison_entry(subpage)); if (folio_test_hugetlb(folio)) { hugetlb_count_sub(folio_nr_pages(folio), mm); set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); } else { dec_mm_counter(mm, mm_counter(folio)); set_pte_at(mm, address, pvmw.pte, pteval); } } else if (likely(pte_present(pteval)) && pte_unused(pteval) && !userfaultfd_armed(vma)) { /* * The guest indicated that the page content is of no * interest anymore. Simply discard the pte, vmscan * will take care of the rest. * A future reference will then fault in a new zero * page. When userfaultfd is active, we must not drop * this page though, as its main user (postcopy * migration) will not expect userfaults on already * copied pages. */ dec_mm_counter(mm, mm_counter(folio)); } else { swp_entry_t entry; pte_t swp_pte; /* * arch_unmap_one() is expected to be a NOP on * architectures where we could have PFN swap PTEs, * so we'll not check/care. */ if (arch_unmap_one(mm, vma, address, pteval) < 0) { if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); else set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* See folio_try_share_anon_rmap_pte(): clear PTE first. */ if (folio_test_hugetlb(folio)) { if (anon_exclusive && hugetlb_try_share_anon_rmap(folio)) { set_huge_pte_at(mm, address, pvmw.pte, pteval, hsz); ret = false; page_vma_mapped_walk_done(&pvmw); break; } } else if (anon_exclusive && folio_try_share_anon_rmap_pte(folio, subpage)) { set_pte_at(mm, address, pvmw.pte, pteval); ret = false; page_vma_mapped_walk_done(&pvmw); break; } /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration * pte is removed and then restart fault handling. */ if (writable) entry = make_writable_migration_entry( page_to_pfn(subpage)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry( page_to_pfn(subpage)); else entry = make_readable_migration_entry( page_to_pfn(subpage)); if (likely(pte_present(pteval))) { if (pte_young(pteval)) entry = make_migration_entry_young(entry); if (pte_dirty(pteval)) entry = make_migration_entry_dirty(entry); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } else { swp_pte = swp_entry_to_pte(entry); if (pte_swp_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); if (pte_swp_uffd_wp(pteval)) swp_pte = pte_swp_mkuffd_wp(swp_pte); } if (folio_test_hugetlb(folio)) set_huge_pte_at(mm, address, pvmw.pte, swp_pte, hsz); else set_pte_at(mm, address, pvmw.pte, swp_pte); trace_set_migration_pte(address, pte_val(swp_pte), folio_order(folio)); /* * No need to invalidate here it will synchronize on * against the special swap migration pte. */ } if (unlikely(folio_test_hugetlb(folio))) hugetlb_remove_rmap(folio); else folio_remove_rmap_pte(folio, subpage, vma); if (vma->vm_flags & VM_LOCKED) mlock_drain_local(); folio_put(folio); } mmu_notifier_invalidate_range_end(&range); return ret; } /** * try_to_migrate - try to replace all page table mappings with swap entries * @folio: the folio to replace page table entries for * @flags: action and flags * * Tries to remove all the page table entries which are mapping this folio and * replace them with special swap entries. Caller must hold the folio lock. */ void try_to_migrate(struct folio *folio, enum ttu_flags flags) { struct rmap_walk_control rwc = { .rmap_one = try_to_migrate_one, .arg = (void *)flags, .done = folio_not_mapped, .anon_lock = folio_lock_anon_vma_read, }; /* * Migration always ignores mlock and only supports TTU_RMAP_LOCKED and * TTU_SPLIT_HUGE_PMD, TTU_SYNC, and TTU_BATCH_FLUSH flags. */ if (WARN_ON_ONCE(flags & ~(TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD | TTU_SYNC | TTU_BATCH_FLUSH))) return; if (folio_is_zone_device(folio) && (!folio_is_device_private(folio) && !folio_is_device_coherent(folio))) return; /* * During exec, a temporary VMA is setup and later moved. * The VMA is moved under the anon_vma lock but not the * page tables leading to a race where migration cannot * find the migration ptes. Rather than increasing the * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ if (!folio_test_ksm(folio) && folio_test_anon(folio)) rwc.invalid_vma = invalid_migration_vma; if (flags & TTU_RMAP_LOCKED) rmap_walk_locked(folio, &rwc); else rmap_walk(folio, &rwc); } #ifdef CONFIG_DEVICE_PRIVATE /** * make_device_exclusive() - Mark a page for exclusive use by a device * @mm: mm_struct of associated target process * @addr: the virtual address to mark for exclusive device access * @owner: passed to MMU_NOTIFY_EXCLUSIVE range notifier to allow filtering * @foliop: folio pointer will be stored here on success. * * This function looks up the page mapped at the given address, grabs a * folio reference, locks the folio and replaces the PTE with special * device-exclusive PFN swap entry, preventing access through the process * page tables. The function will return with the folio locked and referenced. * * On fault, the device-exclusive entries are replaced with the original PTE * under folio lock, after calling MMU notifiers. * * Only anonymous non-hugetlb folios are supported and the VMA must have * write permissions such that we can fault in the anonymous page writable * in order to mark it exclusive. The caller must hold the mmap_lock in read * mode. * * A driver using this to program access from a device must use a mmu notifier * critical section to hold a device specific lock during programming. Once * programming is complete it should drop the folio lock and reference after * which point CPU access to the page will revoke the exclusive access. * * Notes: * #. This function always operates on individual PTEs mapping individual * pages. PMD-sized THPs are first remapped to be mapped by PTEs before * the conversion happens on a single PTE corresponding to @addr. * #. While concurrent access through the process page tables is prevented, * concurrent access through other page references (e.g., earlier GUP * invocation) is not handled and not supported. * #. device-exclusive entries are considered "clean" and "old" by core-mm. * Device drivers must update the folio state when informed by MMU * notifiers. * * Returns: pointer to mapped page on success, otherwise a negative error. */ struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr, void *owner, struct folio **foliop) { struct mmu_notifier_range range; struct folio *folio, *fw_folio; struct vm_area_struct *vma; struct folio_walk fw; struct page *page; swp_entry_t entry; pte_t swp_pte; int ret; mmap_assert_locked(mm); addr = PAGE_ALIGN_DOWN(addr); /* * Fault in the page writable and try to lock it; note that if the * address would already be marked for exclusive use by a device, * the GUP call would undo that first by triggering a fault. * * If any other device would already map this page exclusively, the * fault will trigger a conversion to an ordinary * (non-device-exclusive) PTE and issue a MMU_NOTIFY_EXCLUSIVE. */ retry: page = get_user_page_vma_remote(mm, addr, FOLL_GET | FOLL_WRITE | FOLL_SPLIT_PMD, &vma); if (IS_ERR(page)) return page; folio = page_folio(page); if (!folio_test_anon(folio) || folio_test_hugetlb(folio)) { folio_put(folio); return ERR_PTR(-EOPNOTSUPP); } ret = folio_lock_killable(folio); if (ret) { folio_put(folio); return ERR_PTR(ret); } /* * Inform secondary MMUs that we are going to convert this PTE to * device-exclusive, such that they unmap it now. Note that the * caller must filter this event out to prevent livelocks. */ mmu_notifier_range_init_owner(&range, MMU_NOTIFY_EXCLUSIVE, 0, mm, addr, addr + PAGE_SIZE, owner); mmu_notifier_invalidate_range_start(&range); /* * Let's do a second walk and make sure we still find the same page * mapped writable. Note that any page of an anonymous folio can * only be mapped writable using exactly one PTE ("exclusive"), so * there cannot be other mappings. */ fw_folio = folio_walk_start(&fw, vma, addr, 0); if (fw_folio != folio || fw.page != page || fw.level != FW_LEVEL_PTE || !pte_write(fw.pte)) { if (fw_folio) folio_walk_end(&fw, vma); mmu_notifier_invalidate_range_end(&range); folio_unlock(folio); folio_put(folio); goto retry; } /* Nuke the page table entry so we get the uptodate dirty bit. */ flush_cache_page(vma, addr, page_to_pfn(page)); fw.pte = ptep_clear_flush(vma, addr, fw.ptep); /* Set the dirty flag on the folio now the PTE is gone. */ if (pte_dirty(fw.pte)) folio_mark_dirty(folio); /* * Store the pfn of the page in a special device-exclusive PFN swap PTE. * do_swap_page() will trigger the conversion back while holding the * folio lock. */ entry = make_device_exclusive_entry(page_to_pfn(page)); swp_pte = swp_entry_to_pte(entry); if (pte_soft_dirty(fw.pte)) swp_pte = pte_swp_mksoft_dirty(swp_pte); /* The pte is writable, uffd-wp does not apply. */ set_pte_at(mm, addr, fw.ptep, swp_pte); folio_walk_end(&fw, vma); mmu_notifier_invalidate_range_end(&range); *foliop = folio; return page; } EXPORT_SYMBOL_GPL(make_device_exclusive); #endif void __put_anon_vma(struct anon_vma *anon_vma) { struct anon_vma *root = anon_vma->root; anon_vma_free(anon_vma); if (root != anon_vma && atomic_dec_and_test(&root->refcount)) anon_vma_free(root); } static struct anon_vma *rmap_walk_anon_lock(const struct folio *folio, struct rmap_walk_control *rwc) { struct anon_vma *anon_vma; if (rwc->anon_lock) return rwc->anon_lock(folio, rwc); /* * Note: remove_migration_ptes() cannot use folio_lock_anon_vma_read() * because that depends on page_mapped(); but not all its usages * are holding mmap_lock. Users without mmap_lock are required to * take a reference count to prevent the anon_vma disappearing */ anon_vma = folio_anon_vma(folio); if (!anon_vma) return NULL; if (anon_vma_trylock_read(anon_vma)) goto out; if (rwc->try_lock) { anon_vma = NULL; rwc->contended = true; goto out; } anon_vma_lock_read(anon_vma); out: return anon_vma; } /* * rmap_walk_anon - do something to anonymous page using the object-based * rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma * chains contained in the anon_vma struct it points to. */ static void rmap_walk_anon(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { struct anon_vma *anon_vma; pgoff_t pgoff_start, pgoff_end; struct anon_vma_chain *avc; /* * The folio lock ensures that folio->mapping can't be changed under us * to an anon_vma with different root. */ VM_WARN_ON_FOLIO(!folio_test_locked(folio), folio); if (locked) { anon_vma = folio_anon_vma(folio); /* anon_vma disappear under us? */ VM_BUG_ON_FOLIO(!anon_vma, folio); } else { anon_vma = rmap_walk_anon_lock(folio, rwc); } if (!anon_vma) return; pgoff_start = folio_pgoff(folio); pgoff_end = pgoff_start + folio_nr_pages(folio) - 1; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff_start, pgoff_end) { struct vm_area_struct *vma = avc->vma; unsigned long address = vma_address(vma, pgoff_start, folio_nr_pages(folio)); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) break; if (rwc->done && rwc->done(folio)) break; } if (!locked) anon_vma_unlock_read(anon_vma); } /** * __rmap_walk_file() - Traverse the reverse mapping for a file-backed mapping * of a page mapped within a specified page cache object at a specified offset. * * @folio: Either the folio whose mappings to traverse, or if NULL, * the callbacks specified in @rwc will be configured such * as to be able to look up mappings correctly. * @mapping: The page cache object whose mapping VMAs we intend to * traverse. If @folio is non-NULL, this should be equal to * folio_mapping(folio). * @pgoff_start: The offset within @mapping of the page which we are * looking up. If @folio is non-NULL, this should be equal * to folio_pgoff(folio). * @nr_pages: The number of pages mapped by the mapping. If @folio is * non-NULL, this should be equal to folio_nr_pages(folio). * @rwc: The reverse mapping walk control object describing how * the traversal should proceed. * @locked: Is the @mapping already locked? If not, we acquire the * lock. */ static void __rmap_walk_file(struct folio *folio, struct address_space *mapping, pgoff_t pgoff_start, unsigned long nr_pages, struct rmap_walk_control *rwc, bool locked) { pgoff_t pgoff_end = pgoff_start + nr_pages - 1; struct vm_area_struct *vma; VM_WARN_ON_FOLIO(folio && mapping != folio_mapping(folio), folio); VM_WARN_ON_FOLIO(folio && pgoff_start != folio_pgoff(folio), folio); VM_WARN_ON_FOLIO(folio && nr_pages != folio_nr_pages(folio), folio); if (!locked) { if (i_mmap_trylock_read(mapping)) goto lookup; if (rwc->try_lock) { rwc->contended = true; return; } i_mmap_lock_read(mapping); } lookup: vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff_start, pgoff_end) { unsigned long address = vma_address(vma, pgoff_start, nr_pages); VM_BUG_ON_VMA(address == -EFAULT, vma); cond_resched(); if (rwc->invalid_vma && rwc->invalid_vma(vma, rwc->arg)) continue; if (!rwc->rmap_one(folio, vma, address, rwc->arg)) goto done; if (rwc->done && rwc->done(folio)) goto done; } done: if (!locked) i_mmap_unlock_read(mapping); } /* * rmap_walk_file - do something to file page using the object-based rmap method * @folio: the folio to be handled * @rwc: control variable according to each walk type * @locked: caller holds relevant rmap lock * * Find all the mappings of a folio using the mapping pointer and the vma chains * contained in the address_space struct it points to. */ static void rmap_walk_file(struct folio *folio, struct rmap_walk_control *rwc, bool locked) { /* * The folio lock not only makes sure that folio->mapping cannot * suddenly be NULLified by truncation, it makes sure that the structure * at mapping cannot be freed and reused yet, so we can safely take * mapping->i_mmap_rwsem. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); if (!folio->mapping) return; __rmap_walk_file(folio, folio->mapping, folio->index, folio_nr_pages(folio), rwc, locked); } void rmap_walk(struct folio *folio, struct rmap_walk_control *rwc) { if (unlikely(folio_test_ksm(folio))) rmap_walk_ksm(folio, rwc); else if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, false); else rmap_walk_file(folio, rwc, false); } /* Like rmap_walk, but caller holds relevant rmap lock */ void rmap_walk_locked(struct folio *folio, struct rmap_walk_control *rwc) { /* no ksm support for now */ VM_BUG_ON_FOLIO(folio_test_ksm(folio), folio); if (folio_test_anon(folio)) rmap_walk_anon(folio, rwc, true); else rmap_walk_file(folio, rwc, true); } #ifdef CONFIG_HUGETLB_PAGE /* * The following two functions are for anonymous (private mapped) hugepages. * Unlike common anonymous pages, anonymous hugepages have no accounting code * and no lru code, because we handle hugepages differently from common pages. */ void hugetlb_add_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address, rmap_t flags) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); atomic_inc(&folio->_entire_mapcount); atomic_inc(&folio->_large_mapcount); if (flags & RMAP_EXCLUSIVE) SetPageAnonExclusive(&folio->page); VM_WARN_ON_FOLIO(folio_entire_mapcount(folio) > 1 && PageAnonExclusive(&folio->page), folio); } void hugetlb_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma, unsigned long address) { VM_WARN_ON_FOLIO(!folio_test_hugetlb(folio), folio); BUG_ON(address < vma->vm_start || address >= vma->vm_end); /* increment count (starts at -1) */ atomic_set(&folio->_entire_mapcount, 0); atomic_set(&folio->_large_mapcount, 0); folio_clear_hugetlb_restore_reserve(folio); __folio_set_anon(folio, vma, address, true); SetPageAnonExclusive(&folio->page); } #endif /* CONFIG_HUGETLB_PAGE */ |
| 53 31 22 45 2 3 3 3 28 4 39 6 37 8 38 7 1 5 9 1 6 2 6 6 1 3 4 4 1 15 2 2 13 18 18 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2020, Red Hat, Inc. */ #define pr_fmt(fmt) "MPTCP: " fmt #include "protocol.h" #include "mptcp_pm_gen.h" #define MPTCP_PM_CMD_GRP_OFFSET 0 #define MPTCP_PM_EV_GRP_OFFSET 1 static const struct genl_multicast_group mptcp_pm_mcgrps[] = { [MPTCP_PM_CMD_GRP_OFFSET] = { .name = MPTCP_PM_CMD_GRP_NAME, }, [MPTCP_PM_EV_GRP_OFFSET] = { .name = MPTCP_PM_EV_GRP_NAME, .flags = GENL_MCAST_CAP_NET_ADMIN, }, }; static int mptcp_pm_family_to_addr(int family) { #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (family == AF_INET6) return MPTCP_PM_ADDR_ATTR_ADDR6; #endif return MPTCP_PM_ADDR_ATTR_ADDR4; } static int mptcp_pm_parse_pm_addr_attr(struct nlattr *tb[], const struct nlattr *attr, struct genl_info *info, struct mptcp_addr_info *addr, bool require_family) { int err, addr_addr; if (!attr) { GENL_SET_ERR_MSG(info, "missing address info"); return -EINVAL; } /* no validation needed - was already done via nested policy */ err = nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, mptcp_pm_address_nl_policy, info->extack); if (err) return err; if (tb[MPTCP_PM_ADDR_ATTR_ID]) addr->id = nla_get_u8(tb[MPTCP_PM_ADDR_ATTR_ID]); if (!tb[MPTCP_PM_ADDR_ATTR_FAMILY]) { if (!require_family) return 0; NL_SET_ERR_MSG_ATTR(info->extack, attr, "missing family"); return -EINVAL; } addr->family = nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_FAMILY]); if (addr->family != AF_INET #if IS_ENABLED(CONFIG_MPTCP_IPV6) && addr->family != AF_INET6 #endif ) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "unknown address family"); return -EINVAL; } addr_addr = mptcp_pm_family_to_addr(addr->family); if (!tb[addr_addr]) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "missing address data"); return -EINVAL; } #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (addr->family == AF_INET6) addr->addr6 = nla_get_in6_addr(tb[addr_addr]); else #endif addr->addr.s_addr = nla_get_in_addr(tb[addr_addr]); if (tb[MPTCP_PM_ADDR_ATTR_PORT]) addr->port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); return 0; } int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info, struct mptcp_addr_info *addr) { struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; memset(addr, 0, sizeof(*addr)); return mptcp_pm_parse_pm_addr_attr(tb, attr, info, addr, true); } int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info, bool require_family, struct mptcp_pm_addr_entry *entry) { struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; int err; memset(entry, 0, sizeof(*entry)); err = mptcp_pm_parse_pm_addr_attr(tb, attr, info, &entry->addr, require_family); if (err) return err; if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) { s32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]); entry->ifindex = val; } if (tb[MPTCP_PM_ADDR_ATTR_FLAGS]) entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]) & MPTCP_PM_ADDR_FLAGS_MASK; if (tb[MPTCP_PM_ADDR_ATTR_PORT]) entry->addr.port = htons(nla_get_u16(tb[MPTCP_PM_ADDR_ATTR_PORT])); return 0; } static int mptcp_nl_fill_addr(struct sk_buff *skb, struct mptcp_pm_addr_entry *entry) { struct mptcp_addr_info *addr = &entry->addr; struct nlattr *attr; attr = nla_nest_start(skb, MPTCP_PM_ATTR_ADDR); if (!attr) return -EMSGSIZE; if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_FAMILY, addr->family)) goto nla_put_failure; if (nla_put_u16(skb, MPTCP_PM_ADDR_ATTR_PORT, ntohs(addr->port))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_PM_ADDR_ATTR_ID, addr->id)) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->flags)) goto nla_put_failure; if (entry->ifindex && nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->ifindex)) goto nla_put_failure; if (addr->family == AF_INET && nla_put_in_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR4, addr->addr.s_addr)) goto nla_put_failure; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (addr->family == AF_INET6 && nla_put_in6_addr(skb, MPTCP_PM_ADDR_ATTR_ADDR6, &addr->addr6)) goto nla_put_failure; #endif nla_nest_end(skb, attr); return 0; nla_put_failure: nla_nest_cancel(skb, attr); return -EMSGSIZE; } static int mptcp_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr, struct genl_info *info) { if (info->attrs[MPTCP_PM_ATTR_TOKEN]) return mptcp_userspace_pm_get_addr(id, addr, info); return mptcp_pm_nl_get_addr(id, addr, info); } int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct mptcp_pm_addr_entry addr; struct nlattr *attr; struct sk_buff *msg; void *reply; int ret; if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR)) return -EINVAL; attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; ret = mptcp_pm_parse_entry(attr, info, false, &addr); if (ret < 0) return ret; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0, info->genlhdr->cmd); if (!reply) { GENL_SET_ERR_MSG(info, "not enough space in Netlink message"); ret = -EMSGSIZE; goto fail; } ret = mptcp_pm_get_addr(addr.addr.id, &addr, info); if (ret) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found"); goto fail; } ret = mptcp_nl_fill_addr(msg, &addr); if (ret) goto fail; genlmsg_end(msg, reply); ret = genlmsg_reply(msg, info); return ret; fail: nlmsg_free(msg); return ret; } int mptcp_pm_genl_fill_addr(struct sk_buff *msg, struct netlink_callback *cb, struct mptcp_pm_addr_entry *entry) { void *hdr; hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &mptcp_genl_family, NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); if (!hdr) return -EINVAL; if (mptcp_nl_fill_addr(msg, entry) < 0) { genlmsg_cancel(msg, hdr); return -EINVAL; } genlmsg_end(msg, hdr); return 0; } static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb) { const struct genl_info *info = genl_info_dump(cb); if (info->attrs[MPTCP_PM_ATTR_TOKEN]) return mptcp_userspace_pm_dump_addr(msg, cb); return mptcp_pm_nl_dump_addr(msg, cb); } int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { return mptcp_pm_dump_addr(msg, cb); } static int mptcp_pm_set_flags(struct genl_info *info) { struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, }; struct nlattr *attr_loc; int ret = -EINVAL; if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR)) return ret; attr_loc = info->attrs[MPTCP_PM_ATTR_ADDR]; ret = mptcp_pm_parse_entry(attr_loc, info, false, &loc); if (ret < 0) return ret; if (info->attrs[MPTCP_PM_ATTR_TOKEN]) return mptcp_userspace_pm_set_flags(&loc, info); return mptcp_pm_nl_set_flags(&loc, info); } int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info) { return mptcp_pm_set_flags(info); } static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp) { genlmsg_multicast_netns(&mptcp_genl_family, net, nlskb, 0, MPTCP_PM_EV_GRP_OFFSET, gfp); } bool mptcp_userspace_pm_active(const struct mptcp_sock *msk) { return genl_has_listeners(&mptcp_genl_family, sock_net((const struct sock *)msk), MPTCP_PM_EV_GRP_OFFSET); } static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) { const struct inet_sock *issk = inet_sk(ssk); const struct mptcp_subflow_context *sf; if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family)) return -EMSGSIZE; switch (ssk->sk_family) { case AF_INET: if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr)) return -EMSGSIZE; if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, issk->inet_daddr)) return -EMSGSIZE; break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: { if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &issk->pinet6->saddr)) return -EMSGSIZE; if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &ssk->sk_v6_daddr)) return -EMSGSIZE; break; } #endif default: WARN_ON_ONCE(1); return -EMSGSIZE; } if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport)) return -EMSGSIZE; if (nla_put_be16(skb, MPTCP_ATTR_DPORT, issk->inet_dport)) return -EMSGSIZE; sf = mptcp_subflow_ctx(ssk); if (WARN_ON_ONCE(!sf)) return -EINVAL; if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf))) return -EMSGSIZE; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) return -EMSGSIZE; return 0; } static int mptcp_event_put_token_and_ssk(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { const struct sock *sk = (const struct sock *)msk; const struct mptcp_subflow_context *sf; u8 sk_err; if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) return -EMSGSIZE; if (mptcp_event_add_subflow(skb, ssk)) return -EMSGSIZE; sf = mptcp_subflow_ctx(ssk); if (WARN_ON_ONCE(!sf)) return -EINVAL; if (nla_put_u8(skb, MPTCP_ATTR_BACKUP, sf->backup)) return -EMSGSIZE; if (ssk->sk_bound_dev_if && nla_put_s32(skb, MPTCP_ATTR_IF_IDX, ssk->sk_bound_dev_if)) return -EMSGSIZE; sk_err = READ_ONCE(ssk->sk_err); if (sk_err && sk->sk_state == TCP_ESTABLISHED && nla_put_u8(skb, MPTCP_ATTR_ERROR, sk_err)) return -EMSGSIZE; return 0; } static int mptcp_event_sub_established(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { return mptcp_event_put_token_and_ssk(skb, msk, ssk); } static int mptcp_event_sub_closed(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { const struct mptcp_subflow_context *sf; if (mptcp_event_put_token_and_ssk(skb, msk, ssk)) return -EMSGSIZE; sf = mptcp_subflow_ctx(ssk); if (!sf->reset_seen) return 0; if (nla_put_u32(skb, MPTCP_ATTR_RESET_REASON, sf->reset_reason)) return -EMSGSIZE; if (nla_put_u32(skb, MPTCP_ATTR_RESET_FLAGS, sf->reset_transient)) return -EMSGSIZE; return 0; } static int mptcp_event_created(struct sk_buff *skb, const struct mptcp_sock *msk, const struct sock *ssk) { int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)); u16 flags = 0; if (err) return err; if (READ_ONCE(msk->pm.server_side)) { flags |= MPTCP_PM_EV_FLAG_SERVER_SIDE; /* Deprecated, and only set when it is the server side */ if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, 1)) return -EMSGSIZE; } if (READ_ONCE(msk->pm.remote_deny_join_id0)) flags |= MPTCP_PM_EV_FLAG_DENY_JOIN_ID0; if (flags && nla_put_u16(skb, MPTCP_ATTR_FLAGS, flags)) return -EMSGSIZE; return mptcp_event_add_subflow(skb, ssk); } void mptcp_event_addr_removed(const struct mptcp_sock *msk, uint8_t id) { struct net *net = sock_net((const struct sock *)msk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, MPTCP_EVENT_REMOVED); if (!nlh) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, id)) goto nla_put_failure; genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); } void mptcp_event_addr_announced(const struct sock *ssk, const struct mptcp_addr_info *info) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); struct net *net = sock_net(ssk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, MPTCP_EVENT_ANNOUNCED); if (!nlh) goto nla_put_failure; if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token))) goto nla_put_failure; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, info->id)) goto nla_put_failure; if (nla_put_be16(skb, MPTCP_ATTR_DPORT, info->port == 0 ? inet_sk(ssk)->inet_dport : info->port)) goto nla_put_failure; switch (info->family) { case AF_INET: if (nla_put_in_addr(skb, MPTCP_ATTR_DADDR4, info->addr.s_addr)) goto nla_put_failure; break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &info->addr6)) goto nla_put_failure; break; #endif default: WARN_ON_ONCE(1); goto nla_put_failure; } genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, GFP_ATOMIC); return; nla_put_failure: nlmsg_free(skb); } void mptcp_event_pm_listener(const struct sock *ssk, enum mptcp_event_type event) { const struct inet_sock *issk = inet_sk(ssk); struct net *net = sock_net(ssk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, event); if (!nlh) goto nla_put_failure; if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family)) goto nla_put_failure; if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport)) goto nla_put_failure; switch (ssk->sk_family) { case AF_INET: if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr)) goto nla_put_failure; break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: { if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &issk->pinet6->saddr)) goto nla_put_failure; break; } #endif default: WARN_ON_ONCE(1); goto nla_put_failure; } genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, GFP_KERNEL); return; nla_put_failure: nlmsg_free(skb); } void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp) { struct net *net = sock_net((const struct sock *)msk); struct nlmsghdr *nlh; struct sk_buff *skb; if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) return; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, gfp); if (!skb) return; nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, type); if (!nlh) goto nla_put_failure; switch (type) { case MPTCP_EVENT_UNSPEC: WARN_ON_ONCE(1); break; case MPTCP_EVENT_CREATED: case MPTCP_EVENT_ESTABLISHED: if (mptcp_event_created(skb, msk, ssk) < 0) goto nla_put_failure; break; case MPTCP_EVENT_CLOSED: if (nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)) < 0) goto nla_put_failure; break; case MPTCP_EVENT_ANNOUNCED: case MPTCP_EVENT_REMOVED: /* call mptcp_event_addr_announced()/removed instead */ WARN_ON_ONCE(1); break; case MPTCP_EVENT_SUB_ESTABLISHED: case MPTCP_EVENT_SUB_PRIORITY: if (mptcp_event_sub_established(skb, msk, ssk) < 0) goto nla_put_failure; break; case MPTCP_EVENT_SUB_CLOSED: if (mptcp_event_sub_closed(skb, msk, ssk) < 0) goto nla_put_failure; break; case MPTCP_EVENT_LISTENER_CREATED: case MPTCP_EVENT_LISTENER_CLOSED: break; } genlmsg_end(skb, nlh); mptcp_nl_mcast_send(net, skb, gfp); return; nla_put_failure: nlmsg_free(skb); } struct genl_family mptcp_genl_family __ro_after_init = { .name = MPTCP_PM_NAME, .version = MPTCP_PM_VER, .netnsok = true, .module = THIS_MODULE, .ops = mptcp_pm_nl_ops, .n_ops = ARRAY_SIZE(mptcp_pm_nl_ops), .resv_start_op = MPTCP_PM_CMD_SUBFLOW_DESTROY + 1, .mcgrps = mptcp_pm_mcgrps, .n_mcgrps = ARRAY_SIZE(mptcp_pm_mcgrps), }; void __init mptcp_pm_nl_init(void) { if (genl_register_family(&mptcp_genl_family)) panic("Failed to register MPTCP PM netlink family\n"); } |
| 47 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Tick related global functions */ #ifndef _LINUX_TICK_H #define _LINUX_TICK_H #include <linux/clockchips.h> #include <linux/irqflags.h> #include <linux/percpu.h> #include <linux/context_tracking_state.h> #include <linux/cpumask.h> #include <linux/sched.h> #include <linux/rcupdate.h> #include <linux/static_key.h> #ifdef CONFIG_GENERIC_CLOCKEVENTS extern void __init tick_init(void); /* Should be core only, but ARM BL switcher requires it */ extern void tick_suspend_local(void); /* Should be core only, but XEN resume magic and ARM BL switcher require it */ extern void tick_resume_local(void); #else /* CONFIG_GENERIC_CLOCKEVENTS */ static inline void tick_init(void) { } static inline void tick_suspend_local(void) { } static inline void tick_resume_local(void) { } #endif /* !CONFIG_GENERIC_CLOCKEVENTS */ #if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_HOTPLUG_CPU) extern int tick_cpu_dying(unsigned int cpu); extern void tick_assert_timekeeping_handover(void); #else #define tick_cpu_dying NULL static inline void tick_assert_timekeeping_handover(void) { } #endif #if defined(CONFIG_GENERIC_CLOCKEVENTS) && defined(CONFIG_SUSPEND) extern void tick_freeze(void); extern void tick_unfreeze(void); #else static inline void tick_freeze(void) { } static inline void tick_unfreeze(void) { } #endif #ifdef CONFIG_TICK_ONESHOT extern void tick_irq_enter(void); # ifndef arch_needs_cpu # define arch_needs_cpu() (0) # endif # else static inline void tick_irq_enter(void) { } #endif #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern void hotplug_cpu__broadcast_tick_pull(int dead_cpu); #else static inline void hotplug_cpu__broadcast_tick_pull(int dead_cpu) { } #endif enum tick_broadcast_mode { TICK_BROADCAST_OFF, TICK_BROADCAST_ON, TICK_BROADCAST_FORCE, }; enum tick_broadcast_state { TICK_BROADCAST_EXIT, TICK_BROADCAST_ENTER, }; extern struct static_key_false arch_needs_tick_broadcast; #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST extern void tick_broadcast_control(enum tick_broadcast_mode mode); #else static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ #ifdef CONFIG_GENERIC_CLOCKEVENTS extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); #else static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { return 0; } #endif static inline void tick_broadcast_enable(void) { tick_broadcast_control(TICK_BROADCAST_ON); } static inline void tick_broadcast_disable(void) { tick_broadcast_control(TICK_BROADCAST_OFF); } static inline void tick_broadcast_force(void) { tick_broadcast_control(TICK_BROADCAST_FORCE); } static inline int tick_broadcast_enter(void) { return tick_broadcast_oneshot_control(TICK_BROADCAST_ENTER); } static inline void tick_broadcast_exit(void) { tick_broadcast_oneshot_control(TICK_BROADCAST_EXIT); } enum tick_dep_bits { TICK_DEP_BIT_POSIX_TIMER = 0, TICK_DEP_BIT_PERF_EVENTS = 1, TICK_DEP_BIT_SCHED = 2, TICK_DEP_BIT_CLOCK_UNSTABLE = 3, TICK_DEP_BIT_RCU = 4, TICK_DEP_BIT_RCU_EXP = 5 }; #define TICK_DEP_BIT_MAX TICK_DEP_BIT_RCU_EXP #define TICK_DEP_MASK_NONE 0 #define TICK_DEP_MASK_POSIX_TIMER (1 << TICK_DEP_BIT_POSIX_TIMER) #define TICK_DEP_MASK_PERF_EVENTS (1 << TICK_DEP_BIT_PERF_EVENTS) #define TICK_DEP_MASK_SCHED (1 << TICK_DEP_BIT_SCHED) #define TICK_DEP_MASK_CLOCK_UNSTABLE (1 << TICK_DEP_BIT_CLOCK_UNSTABLE) #define TICK_DEP_MASK_RCU (1 << TICK_DEP_BIT_RCU) #define TICK_DEP_MASK_RCU_EXP (1 << TICK_DEP_BIT_RCU_EXP) #ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; extern bool tick_nohz_is_active(void); extern bool tick_nohz_tick_stopped(void); extern bool tick_nohz_tick_stopped_cpu(int cpu); extern void tick_nohz_idle_stop_tick(void); extern void tick_nohz_idle_retain_tick(void); extern void tick_nohz_idle_restart_tick(void); extern void tick_nohz_idle_enter(void); extern void tick_nohz_idle_exit(void); extern void tick_nohz_irq_exit(void); extern bool tick_nohz_idle_got_tick(void); extern ktime_t tick_nohz_get_next_hrtimer(void); extern ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next); extern unsigned long tick_nohz_get_idle_calls_cpu(int cpu); extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time); extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time); #else /* !CONFIG_NO_HZ_COMMON */ #define tick_nohz_enabled (0) static inline bool tick_nohz_is_active(void) { return false; } static inline int tick_nohz_tick_stopped(void) { return 0; } static inline int tick_nohz_tick_stopped_cpu(int cpu) { return 0; } static inline void tick_nohz_idle_stop_tick(void) { } static inline void tick_nohz_idle_retain_tick(void) { } static inline void tick_nohz_idle_restart_tick(void) { } static inline void tick_nohz_idle_enter(void) { } static inline void tick_nohz_idle_exit(void) { } static inline bool tick_nohz_idle_got_tick(void) { return false; } static inline ktime_t tick_nohz_get_next_hrtimer(void) { /* Next wake up is the tick period, assume it starts now */ return ktime_add(ktime_get(), TICK_NSEC); } static inline ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) { *delta_next = TICK_NSEC; return *delta_next; } static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; } static inline u64 get_cpu_iowait_time_us(int cpu, u64 *unused) { return -1; } #endif /* !CONFIG_NO_HZ_COMMON */ /* * Mask of CPUs that are nohz_full. * * Users should be guarded by CONFIG_NO_HZ_FULL or a tick_nohz_full_cpu() * check. */ extern cpumask_var_t tick_nohz_full_mask; #ifdef CONFIG_NO_HZ_FULL extern bool tick_nohz_full_running; static inline bool tick_nohz_full_enabled(void) { if (!context_tracking_enabled()) return false; return tick_nohz_full_running; } /* * Check if a CPU is part of the nohz_full subset. Arrange for evaluating * the cpu expression (typically smp_processor_id()) _after_ the static * key. */ #define tick_nohz_full_cpu(_cpu) ({ \ bool __ret = false; \ if (tick_nohz_full_enabled()) \ __ret = cpumask_test_cpu((_cpu), tick_nohz_full_mask); \ __ret; \ }) extern void tick_nohz_dep_set(enum tick_dep_bits bit); extern void tick_nohz_dep_clear(enum tick_dep_bits bit); extern void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit); extern void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit); extern void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit); extern void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit); extern void tick_nohz_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit); extern void tick_nohz_dep_clear_signal(struct signal_struct *signal, enum tick_dep_bits bit); extern bool tick_nohz_cpu_hotpluggable(unsigned int cpu); /* * The below are tick_nohz_[set,clear]_dep() wrappers that optimize off-cases * on top of static keys. */ static inline void tick_dep_set(enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_set(bit); } static inline void tick_dep_clear(enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_clear(bit); } static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) { if (tick_nohz_full_cpu(cpu)) tick_nohz_dep_set_cpu(cpu, bit); } static inline void tick_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { if (tick_nohz_full_cpu(cpu)) tick_nohz_dep_clear_cpu(cpu, bit); } static inline void tick_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_set_task(tsk, bit); } static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_clear_task(tsk, bit); } static inline void tick_dep_init_task(struct task_struct *tsk) { atomic_set(&tsk->tick_dep_mask, 0); } static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_set_signal(tsk, bit); } static inline void tick_dep_clear_signal(struct signal_struct *signal, enum tick_dep_bits bit) { if (tick_nohz_full_enabled()) tick_nohz_dep_clear_signal(signal, bit); } extern void tick_nohz_full_kick_cpu(int cpu); extern void __tick_nohz_task_switch(void); extern void __init tick_nohz_full_setup(cpumask_var_t cpumask); #else static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } static inline void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { } static inline bool tick_nohz_cpu_hotpluggable(unsigned int cpu) { return true; } static inline void tick_dep_set(enum tick_dep_bits bit) { } static inline void tick_dep_clear(enum tick_dep_bits bit) { } static inline void tick_dep_set_cpu(int cpu, enum tick_dep_bits bit) { } static inline void tick_dep_clear_cpu(int cpu, enum tick_dep_bits bit) { } static inline void tick_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_init_task(struct task_struct *tsk) { } static inline void tick_dep_set_signal(struct task_struct *tsk, enum tick_dep_bits bit) { } static inline void tick_dep_clear_signal(struct signal_struct *signal, enum tick_dep_bits bit) { } static inline void tick_nohz_full_kick_cpu(int cpu) { } static inline void __tick_nohz_task_switch(void) { } static inline void tick_nohz_full_setup(cpumask_var_t cpumask) { } #endif static inline void tick_nohz_task_switch(void) { if (tick_nohz_full_enabled()) __tick_nohz_task_switch(); } static inline void tick_nohz_user_enter_prepare(void) { if (tick_nohz_full_cpu(smp_processor_id())) rcu_nocb_flush_deferred_wakeup(); } #endif |
| 5 5 5 34 2 32 20 3 3 5 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/module.h> #include <linux/netfilter/nf_tables.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_socket.h> #include <net/inet_sock.h> #include <net/tcp.h> struct nft_socket { enum nft_socket_keys key:8; u8 level; /* cgroupv2 level to extract */ u8 level_user; /* cgroupv2 level provided by userspace */ u8 len; union { u8 dreg; }; }; static void nft_socket_wildcard(const struct nft_pktinfo *pkt, struct nft_regs *regs, struct sock *sk, u32 *dest) { switch (nft_pf(pkt)) { case NFPROTO_IPV4: nft_reg_store8(dest, inet_sk(sk)->inet_rcv_saddr == 0); break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: nft_reg_store8(dest, ipv6_addr_any(&sk->sk_v6_rcv_saddr)); break; #endif default: regs->verdict.code = NFT_BREAK; return; } } #ifdef CONFIG_SOCK_CGROUP_DATA static noinline bool nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo *pkt, u32 level) { struct cgroup *cgrp; u64 cgid; if (!sk_fullsock(sk)) return false; cgrp = cgroup_ancestor(sock_cgroup_ptr(&sk->sk_cgrp_data), level); if (!cgrp) return false; cgid = cgroup_id(cgrp); memcpy(dest, &cgid, sizeof(u64)); return true; } /* process context only, uses current->nsproxy. */ static noinline int nft_socket_cgroup_subtree_level(void) { struct cgroup *cgrp = cgroup_get_from_path("/"); int level; if (IS_ERR(cgrp)) return PTR_ERR(cgrp); level = cgrp->level; cgroup_put(cgrp); if (level > 255) return -ERANGE; if (WARN_ON_ONCE(level < 0)) return -EINVAL; return level; } #endif static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt) { const struct net_device *indev = nft_in(pkt); const struct sk_buff *skb = pkt->skb; struct sock *sk = NULL; if (!indev) return NULL; switch (nft_pf(pkt)) { case NFPROTO_IPV4: sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, indev); break; #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, indev); break; #endif default: WARN_ON_ONCE(1); break; } return sk; } static void nft_socket_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_socket *priv = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; struct sock *sk = skb->sk; u32 *dest = ®s->data[priv->dreg]; if (sk && !net_eq(nft_net(pkt), sock_net(sk))) sk = NULL; if (!sk) sk = nft_socket_do_lookup(pkt); if (!sk) { regs->verdict.code = NFT_BREAK; return; } switch(priv->key) { case NFT_SOCKET_TRANSPARENT: nft_reg_store8(dest, inet_sk_transparent(sk)); break; case NFT_SOCKET_MARK: if (sk_fullsock(sk)) { *dest = READ_ONCE(sk->sk_mark); } else { regs->verdict.code = NFT_BREAK; goto out_put_sk; } break; case NFT_SOCKET_WILDCARD: if (!sk_fullsock(sk)) { regs->verdict.code = NFT_BREAK; goto out_put_sk; } nft_socket_wildcard(pkt, regs, sk, dest); break; #ifdef CONFIG_SOCK_CGROUP_DATA case NFT_SOCKET_CGROUPV2: if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) { regs->verdict.code = NFT_BREAK; goto out_put_sk; } break; #endif default: WARN_ON(1); regs->verdict.code = NFT_BREAK; } out_put_sk: if (sk != skb->sk) sock_gen_put(sk); } static const struct nla_policy nft_socket_policy[NFTA_SOCKET_MAX + 1] = { [NFTA_SOCKET_KEY] = NLA_POLICY_MAX(NLA_BE32, 255), [NFTA_SOCKET_DREG] = NLA_POLICY_MAX(NLA_BE32, NFT_REG32_MAX), [NFTA_SOCKET_LEVEL] = NLA_POLICY_MAX(NLA_BE32, 255), }; static int nft_socket_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) { struct nft_socket *priv = nft_expr_priv(expr); unsigned int len; if (!tb[NFTA_SOCKET_DREG] || !tb[NFTA_SOCKET_KEY]) return -EINVAL; switch(ctx->family) { case NFPROTO_IPV4: #if IS_ENABLED(CONFIG_NF_TABLES_IPV6) case NFPROTO_IPV6: #endif case NFPROTO_INET: break; default: return -EOPNOTSUPP; } priv->key = ntohl(nla_get_be32(tb[NFTA_SOCKET_KEY])); switch(priv->key) { case NFT_SOCKET_TRANSPARENT: case NFT_SOCKET_WILDCARD: len = sizeof(u8); break; case NFT_SOCKET_MARK: len = sizeof(u32); break; #ifdef CONFIG_SOCK_CGROUP_DATA case NFT_SOCKET_CGROUPV2: { unsigned int level; int err; if (!tb[NFTA_SOCKET_LEVEL]) return -EINVAL; level = ntohl(nla_get_be32(tb[NFTA_SOCKET_LEVEL])); if (level > 255) return -EOPNOTSUPP; err = nft_socket_cgroup_subtree_level(); if (err < 0) return err; priv->level_user = level; level += err; /* Implies a giant cgroup tree */ if (level > 255) return -EOPNOTSUPP; priv->level = level; len = sizeof(u64); break; } #endif default: return -EOPNOTSUPP; } priv->len = len; return nft_parse_register_store(ctx, tb[NFTA_SOCKET_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, len); } static int nft_socket_dump(struct sk_buff *skb, const struct nft_expr *expr, bool reset) { const struct nft_socket *priv = nft_expr_priv(expr); if (nla_put_be32(skb, NFTA_SOCKET_KEY, htonl(priv->key))) return -1; if (nft_dump_register(skb, NFTA_SOCKET_DREG, priv->dreg)) return -1; if (priv->key == NFT_SOCKET_CGROUPV2 && nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level_user))) return -1; return 0; } static int nft_socket_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { if (ctx->family != NFPROTO_IPV4 && ctx->family != NFPROTO_IPV6 && ctx->family != NFPROTO_INET) return -EOPNOTSUPP; return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT)); } static struct nft_expr_type nft_socket_type; static const struct nft_expr_ops nft_socket_ops = { .type = &nft_socket_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_socket)), .eval = nft_socket_eval, .init = nft_socket_init, .dump = nft_socket_dump, .validate = nft_socket_validate, }; static struct nft_expr_type nft_socket_type __read_mostly = { .name = "socket", .ops = &nft_socket_ops, .policy = nft_socket_policy, .maxattr = NFTA_SOCKET_MAX, .owner = THIS_MODULE, }; static int __init nft_socket_module_init(void) { return nft_register_expr(&nft_socket_type); } static void __exit nft_socket_module_exit(void) { nft_unregister_expr(&nft_socket_type); } module_init(nft_socket_module_init); module_exit(nft_socket_module_exit); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Máté Eckl"); MODULE_DESCRIPTION("nf_tables socket match module"); MODULE_ALIAS_NFT_EXPR("socket"); |
| 2 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2014 Jozsef Kadlecsik <kadlec@netfilter.org> */ /* Kernel module implementing an IP set type: the hash:mac type */ #include <linux/jhash.h> #include <linux/module.h> #include <linux/etherdevice.h> #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/if_arp.h> #include <linux/if_ether.h> #include <net/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/ipset/ip_set.h> #include <linux/netfilter/ipset/ip_set_hash.h> #define IPSET_TYPE_REV_MIN 0 #define IPSET_TYPE_REV_MAX 1 /* bucketsize, initval support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>"); IP_SET_MODULE_DESC("hash:mac", IPSET_TYPE_REV_MIN, IPSET_TYPE_REV_MAX); MODULE_ALIAS("ip_set_hash:mac"); /* Type specific function prefix */ #define HTYPE hash_mac /* Member elements */ struct hash_mac4_elem { /* Zero valued IP addresses cannot be stored */ union { unsigned char ether[ETH_ALEN]; __be32 foo[2]; }; }; /* Common functions */ static bool hash_mac4_data_equal(const struct hash_mac4_elem *e1, const struct hash_mac4_elem *e2, u32 *multi) { return ether_addr_equal(e1->ether, e2->ether); } static bool hash_mac4_data_list(struct sk_buff *skb, const struct hash_mac4_elem *e) { if (nla_put(skb, IPSET_ATTR_ETHER, ETH_ALEN, e->ether)) goto nla_put_failure; return false; nla_put_failure: return true; } static void hash_mac4_data_next(struct hash_mac4_elem *next, const struct hash_mac4_elem *e) { } #define MTYPE hash_mac4 #define HOST_MASK 32 #define IP_SET_EMIT_CREATE #define IP_SET_PROTO_UNDEF #include "ip_set_hash_gen.h" static int hash_mac4_kadt(struct ip_set *set, const struct sk_buff *skb, const struct xt_action_param *par, enum ipset_adt adt, struct ip_set_adt_opt *opt) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_mac4_elem e = { { .foo[0] = 0, .foo[1] = 0 } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); if (!skb->dev || skb->dev->type != ARPHRD_ETHER || !skb_mac_header_was_set(skb) || skb_mac_header_len(skb) < ETH_HLEN) return -EINVAL; if (opt->flags & IPSET_DIM_ONE_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); if (is_zero_ether_addr(e.ether)) return -EINVAL; return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } static int hash_mac4_uadt(struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_mac4_elem e = { { .foo[0] = 0, .foo[1] = 0 } }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); int ret; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); if (unlikely(!tb[IPSET_ATTR_ETHER] || nla_len(tb[IPSET_ATTR_ETHER]) != ETH_ALEN)) return -IPSET_ERR_PROTOCOL; ret = ip_set_get_extensions(set, tb, &ext); if (ret) return ret; ether_addr_copy(e.ether, nla_data(tb[IPSET_ATTR_ETHER])); if (is_zero_ether_addr(e.ether)) return -IPSET_ERR_HASH_ELEM; return adtfn(set, &e, &ext, &ext, flags); } static struct ip_set_type hash_mac_type __read_mostly = { .name = "hash:mac", .protocol = IPSET_PROTOCOL, .features = IPSET_TYPE_MAC, .dimension = IPSET_DIM_ONE, .family = NFPROTO_UNSPEC, .revision_min = IPSET_TYPE_REV_MIN, .revision_max = IPSET_TYPE_REV_MAX, .create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE, .create = hash_mac_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, [IPSET_ATTR_INITVAL] = { .type = NLA_U32 }, [IPSET_ATTR_BUCKETSIZE] = { .type = NLA_U8 }, [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { [IPSET_ATTR_ETHER] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, [IPSET_ATTR_COMMENT] = { .type = NLA_NUL_STRING, .len = IPSET_MAX_COMMENT_SIZE }, [IPSET_ATTR_SKBMARK] = { .type = NLA_U64 }, [IPSET_ATTR_SKBPRIO] = { .type = NLA_U32 }, [IPSET_ATTR_SKBQUEUE] = { .type = NLA_U16 }, }, .me = THIS_MODULE, }; static int __init hash_mac_init(void) { return ip_set_type_register(&hash_mac_type); } static void __exit hash_mac_fini(void) { rcu_barrier(); ip_set_type_unregister(&hash_mac_type); } module_init(hash_mac_init); module_exit(hash_mac_fini); |
| 19418 19417 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 | // SPDX-License-Identifier: GPL-2.0-only /* * x86 APERF/MPERF KHz calculation for * /sys/.../cpufreq/scaling_cur_freq * * Copyright (C) 2017 Intel Corp. * Author: Len Brown <len.brown@intel.com> */ #include <linux/cpufreq.h> #include <linux/delay.h> #include <linux/ktime.h> #include <linux/math64.h> #include <linux/percpu.h> #include <linux/rcupdate.h> #include <linux/sched/isolation.h> #include <linux/sched/topology.h> #include <linux/smp.h> #include <linux/syscore_ops.h> #include <asm/cpu.h> #include <asm/cpu_device_id.h> #include <asm/intel-family.h> #include <asm/msr.h> #include "cpu.h" struct aperfmperf { seqcount_t seq; unsigned long last_update; u64 acnt; u64 mcnt; u64 aperf; u64 mperf; }; static DEFINE_PER_CPU_SHARED_ALIGNED(struct aperfmperf, cpu_samples) = { .seq = SEQCNT_ZERO(cpu_samples.seq) }; static void init_counter_refs(void *data) { u64 aperf, mperf; rdmsrq(MSR_IA32_APERF, aperf); rdmsrq(MSR_IA32_MPERF, mperf); this_cpu_write(cpu_samples.aperf, aperf); this_cpu_write(cpu_samples.mperf, mperf); } #if defined(CONFIG_X86_64) && defined(CONFIG_SMP) /* * APERF/MPERF frequency ratio computation. * * The scheduler wants to do frequency invariant accounting and needs a <1 * ratio to account for the 'current' frequency, corresponding to * freq_curr / freq_max. * * Since the frequency freq_curr on x86 is controlled by micro-controller and * our P-state setting is little more than a request/hint, we need to observe * the effective frequency 'BusyMHz', i.e. the average frequency over a time * interval after discarding idle time. This is given by: * * BusyMHz = delta_APERF / delta_MPERF * freq_base * * where freq_base is the max non-turbo P-state. * * The freq_max term has to be set to a somewhat arbitrary value, because we * can't know which turbo states will be available at a given point in time: * it all depends on the thermal headroom of the entire package. We set it to * the turbo level with 4 cores active. * * Benchmarks show that's a good compromise between the 1C turbo ratio * (freq_curr/freq_max would rarely reach 1) and something close to freq_base, * which would ignore the entire turbo range (a conspicuous part, making * freq_curr/freq_max always maxed out). * * An exception to the heuristic above is the Atom uarch, where we choose the * highest turbo level for freq_max since Atom's are generally oriented towards * power efficiency. * * Setting freq_max to anything less than the 1C turbo ratio makes the ratio * freq_curr / freq_max to eventually grow >1, in which case we clip it to 1. */ DEFINE_STATIC_KEY_FALSE(arch_scale_freq_key); static u64 arch_turbo_freq_ratio = SCHED_CAPACITY_SCALE; static u64 arch_max_freq_ratio = SCHED_CAPACITY_SCALE; void arch_set_max_freq_ratio(bool turbo_disabled) { arch_max_freq_ratio = turbo_disabled ? SCHED_CAPACITY_SCALE : arch_turbo_freq_ratio; } EXPORT_SYMBOL_GPL(arch_set_max_freq_ratio); static bool __init turbo_disabled(void) { u64 misc_en; int err; err = rdmsrq_safe(MSR_IA32_MISC_ENABLE, &misc_en); if (err) return false; return (misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE); } static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) { int err; err = rdmsrq_safe(MSR_ATOM_CORE_RATIOS, base_freq); if (err) return false; err = rdmsrq_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq); if (err) return false; *base_freq = (*base_freq >> 16) & 0x3F; /* max P state */ *turbo_freq = *turbo_freq & 0x3F; /* 1C turbo */ return true; } #define X86_MATCH(vfm) \ X86_MATCH_VFM_FEATURE(vfm, X86_FEATURE_APERFMPERF, NULL) static const struct x86_cpu_id has_knl_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_XEON_PHI_KNL), X86_MATCH(INTEL_XEON_PHI_KNM), {} }; static const struct x86_cpu_id has_skx_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_SKYLAKE_X), {} }; static const struct x86_cpu_id has_glm_turbo_ratio_limits[] __initconst = { X86_MATCH(INTEL_ATOM_GOLDMONT), X86_MATCH(INTEL_ATOM_GOLDMONT_D), X86_MATCH(INTEL_ATOM_GOLDMONT_PLUS), {} }; static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int num_delta_fratio) { int fratio, delta_fratio, found; int err, i; u64 msr; err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &msr); if (err) return false; fratio = (msr >> 8) & 0xFF; i = 16; found = 0; do { if (found >= num_delta_fratio) { *turbo_freq = fratio; return true; } delta_fratio = (msr >> (i + 5)) & 0x7; if (delta_fratio) { found += 1; fratio -= delta_fratio; } i += 8; } while (i < 64); return true; } static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int size) { u64 ratios, counts; u32 group_size; int err, i; err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &ratios); if (err) return false; err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT1, &counts); if (err) return false; for (i = 0; i < 64; i += 8) { group_size = (counts >> i) & 0xFF; if (group_size >= size) { *turbo_freq = (ratios >> i) & 0xFF; return true; } } return false; } static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq) { u64 msr; int err; err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq); if (err) return false; err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &msr); if (err) return false; *base_freq = (*base_freq >> 8) & 0xFF; /* max P state */ *turbo_freq = (msr >> 24) & 0xFF; /* 4C turbo */ /* The CPU may have less than 4 cores */ if (!*turbo_freq) *turbo_freq = msr & 0xFF; /* 1C turbo */ return true; } static bool __init intel_set_max_freq_ratio(void) { u64 base_freq, turbo_freq; u64 turbo_ratio; if (slv_set_max_freq_ratio(&base_freq, &turbo_freq)) goto out; if (x86_match_cpu(has_glm_turbo_ratio_limits) && skx_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; if (x86_match_cpu(has_knl_turbo_ratio_limits) && knl_set_max_freq_ratio(&base_freq, &turbo_freq, 1)) goto out; if (x86_match_cpu(has_skx_turbo_ratio_limits) && skx_set_max_freq_ratio(&base_freq, &turbo_freq, 4)) goto out; if (core_set_max_freq_ratio(&base_freq, &turbo_freq)) goto out; return false; out: /* * Some hypervisors advertise X86_FEATURE_APERFMPERF * but then fill all MSR's with zeroes. * Some CPUs have turbo boost but don't declare any turbo ratio * in MSR_TURBO_RATIO_LIMIT. */ if (!base_freq || !turbo_freq) { pr_debug("Couldn't determine cpu base or turbo frequency, necessary for scale-invariant accounting.\n"); return false; } turbo_ratio = div_u64(turbo_freq * SCHED_CAPACITY_SCALE, base_freq); if (!turbo_ratio) { pr_debug("Non-zero turbo and base frequencies led to a 0 ratio.\n"); return false; } arch_turbo_freq_ratio = turbo_ratio; arch_set_max_freq_ratio(turbo_disabled()); return true; } #ifdef CONFIG_PM_SLEEP static const struct syscore_ops freq_invariance_syscore_ops = { .resume = init_counter_refs, }; static struct syscore freq_invariance_syscore = { .ops = &freq_invariance_syscore_ops, }; static void register_freq_invariance_syscore(void) { register_syscore(&freq_invariance_syscore); } #else static inline void register_freq_invariance_syscore(void) {} #endif static void freq_invariance_enable(void) { if (static_branch_unlikely(&arch_scale_freq_key)) { WARN_ON_ONCE(1); return; } static_branch_enable_cpuslocked(&arch_scale_freq_key); register_freq_invariance_syscore(); pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { arch_turbo_freq_ratio = ratio; arch_set_max_freq_ratio(turbo_disabled); freq_invariance_enable(); } static void __init bp_init_freq_invariance(void) { if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return; if (intel_set_max_freq_ratio()) { guard(cpus_read_lock)(); freq_invariance_enable(); } } static void disable_freq_invariance_workfn(struct work_struct *work) { int cpu; static_branch_disable(&arch_scale_freq_key); /* * Set arch_freq_scale to a default value on all cpus * This negates the effect of scaling */ for_each_possible_cpu(cpu) per_cpu(arch_freq_scale, cpu) = SCHED_CAPACITY_SCALE; } static DECLARE_WORK(disable_freq_invariance_work, disable_freq_invariance_workfn); DEFINE_PER_CPU(unsigned long, arch_freq_scale) = SCHED_CAPACITY_SCALE; EXPORT_PER_CPU_SYMBOL_GPL(arch_freq_scale); static DEFINE_STATIC_KEY_FALSE(arch_hybrid_cap_scale_key); struct arch_hybrid_cpu_scale { unsigned long capacity; unsigned long freq_ratio; }; static struct arch_hybrid_cpu_scale __percpu *arch_cpu_scale; /** * arch_enable_hybrid_capacity_scale() - Enable hybrid CPU capacity scaling * * Allocate memory for per-CPU data used by hybrid CPU capacity scaling, * initialize it and set the static key controlling its code paths. * * Must be called before arch_set_cpu_capacity(). */ bool arch_enable_hybrid_capacity_scale(void) { int cpu; if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) { WARN_ONCE(1, "Hybrid CPU capacity scaling already enabled"); return true; } arch_cpu_scale = alloc_percpu(struct arch_hybrid_cpu_scale); if (!arch_cpu_scale) return false; for_each_possible_cpu(cpu) { per_cpu_ptr(arch_cpu_scale, cpu)->capacity = SCHED_CAPACITY_SCALE; per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio = arch_max_freq_ratio; } static_branch_enable(&arch_hybrid_cap_scale_key); pr_info("Hybrid CPU capacity scaling enabled\n"); return true; } /** * arch_set_cpu_capacity() - Set scale-invariance parameters for a CPU * @cpu: Target CPU. * @cap: Capacity of @cpu at its maximum frequency, relative to @max_cap. * @max_cap: System-wide maximum CPU capacity. * @cap_freq: Frequency of @cpu corresponding to @cap. * @base_freq: Frequency of @cpu at which MPERF counts. * * The units in which @cap and @max_cap are expressed do not matter, so long * as they are consistent, because the former is effectively divided by the * latter. Analogously for @cap_freq and @base_freq. * * After calling this function for all CPUs, call arch_rebuild_sched_domains() * to let the scheduler know that capacity-aware scheduling can be used going * forward. */ void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long max_cap, unsigned long cap_freq, unsigned long base_freq) { if (static_branch_likely(&arch_hybrid_cap_scale_key)) { WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity, div_u64(cap << SCHED_CAPACITY_SHIFT, max_cap)); WRITE_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->freq_ratio, div_u64(cap_freq << SCHED_CAPACITY_SHIFT, base_freq)); } else { WARN_ONCE(1, "Hybrid CPU capacity scaling not enabled"); } } unsigned long arch_scale_cpu_capacity(int cpu) { if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) return READ_ONCE(per_cpu_ptr(arch_cpu_scale, cpu)->capacity); return SCHED_CAPACITY_SCALE; } EXPORT_SYMBOL_GPL(arch_scale_cpu_capacity); static void scale_freq_tick(u64 acnt, u64 mcnt) { u64 freq_scale, freq_ratio; if (!arch_scale_freq_invariant()) return; if (check_shl_overflow(acnt, 2*SCHED_CAPACITY_SHIFT, &acnt)) goto error; if (static_branch_unlikely(&arch_hybrid_cap_scale_key)) freq_ratio = READ_ONCE(this_cpu_ptr(arch_cpu_scale)->freq_ratio); else freq_ratio = arch_max_freq_ratio; if (check_mul_overflow(mcnt, freq_ratio, &mcnt) || !mcnt) goto error; freq_scale = div64_u64(acnt, mcnt); if (!freq_scale) goto error; if (freq_scale > SCHED_CAPACITY_SCALE) freq_scale = SCHED_CAPACITY_SCALE; this_cpu_write(arch_freq_scale, freq_scale); return; error: pr_warn("Scheduler frequency invariance went wobbly, disabling!\n"); schedule_work(&disable_freq_invariance_work); } #else static inline void bp_init_freq_invariance(void) { } static inline void scale_freq_tick(u64 acnt, u64 mcnt) { } #endif /* CONFIG_X86_64 && CONFIG_SMP */ void arch_scale_freq_tick(void) { struct aperfmperf *s = this_cpu_ptr(&cpu_samples); u64 acnt, mcnt, aperf, mperf; if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) return; rdmsrq(MSR_IA32_APERF, aperf); rdmsrq(MSR_IA32_MPERF, mperf); acnt = aperf - s->aperf; mcnt = mperf - s->mperf; s->aperf = aperf; s->mperf = mperf; raw_write_seqcount_begin(&s->seq); s->last_update = jiffies; s->acnt = acnt; s->mcnt = mcnt; raw_write_seqcount_end(&s->seq); scale_freq_tick(acnt, mcnt); } /* * Discard samples older than the define maximum sample age of 20ms. There * is no point in sending IPIs in such a case. If the scheduler tick was * not running then the CPU is either idle or isolated. */ #define MAX_SAMPLE_AGE ((unsigned long)HZ / 50) int arch_freq_get_on_cpu(int cpu) { struct aperfmperf *s = per_cpu_ptr(&cpu_samples, cpu); unsigned int seq, freq; unsigned long last; u64 acnt, mcnt; if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) goto fallback; do { seq = raw_read_seqcount_begin(&s->seq); last = s->last_update; acnt = s->acnt; mcnt = s->mcnt; } while (read_seqcount_retry(&s->seq, seq)); /* * Bail on invalid count and when the last update was too long ago, * which covers idle and NOHZ full CPUs. */ if (!mcnt || (jiffies - last) > MAX_SAMPLE_AGE) goto fallback; return div64_u64((cpu_khz * acnt), mcnt); fallback: freq = cpufreq_quick_get(cpu); return freq ? freq : cpu_khz; } static int __init bp_init_aperfmperf(void) { if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF)) return 0; init_counter_refs(NULL); bp_init_freq_invariance(); return 0; } early_initcall(bp_init_aperfmperf); void ap_init_aperfmperf(void) { if (cpu_feature_enabled(X86_FEATURE_APERFMPERF)) init_counter_refs(NULL); } |
| 26 26 26 16 11 6 8 8 8 18 5 7 2 4 10 2 1 1 9 7 2 9 9 5 5 1 3 2 1 1 2 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 | // SPDX-License-Identifier: GPL-2.0 /* * cfg80211 wext compat for managed mode. * * Copyright 2009 Johannes Berg <johannes@sipsolutions.net> * Copyright (C) 2009, 2020-2023 Intel Corporation */ #include <linux/export.h> #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <net/cfg80211.h> #include <net/cfg80211-wext.h> #include "wext-compat.h" #include "nl80211.h" int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { struct cfg80211_cached_keys *ck = NULL; const u8 *prev_bssid = NULL; int err, i; ASSERT_RTNL(); lockdep_assert_wiphy(wdev->wiphy); if (!netif_running(wdev->netdev)) return 0; wdev->wext.connect.ie = wdev->wext.ie; wdev->wext.connect.ie_len = wdev->wext.ie_len; /* Use default background scan period */ wdev->wext.connect.bg_scan_period = -1; if (wdev->wext.keys) { wdev->wext.keys->def = wdev->wext.default_key; if (wdev->wext.default_key != -1) wdev->wext.connect.privacy = true; } if (!wdev->wext.connect.ssid_len) return 0; if (wdev->wext.keys && wdev->wext.keys->def != -1) { ck = kmemdup(wdev->wext.keys, sizeof(*ck), GFP_KERNEL); if (!ck) return -ENOMEM; for (i = 0; i < 4; i++) ck->params[i].key = ck->data[i]; } if (wdev->wext.prev_bssid_valid) prev_bssid = wdev->wext.prev_bssid; err = cfg80211_connect(rdev, wdev->netdev, &wdev->wext.connect, ck, prev_bssid); if (err) kfree_sensitive(ck); return err; } int cfg80211_mgd_wext_siwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *wextfreq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct ieee80211_channel *chan = NULL; int err, freq; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; freq = cfg80211_wext_freq(wextfreq); if (freq < 0) return freq; if (freq) { chan = ieee80211_get_channel(wdev->wiphy, freq); if (!chan) return -EINVAL; if (chan->flags & IEEE80211_CHAN_DISABLED) return -EINVAL; } if (wdev->conn) { bool event = true; if (wdev->wext.connect.channel == chan) return 0; /* if SSID set, we'll try right again, avoid event */ if (wdev->wext.connect.ssid_len) event = false; err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, event); if (err) return err; } wdev->wext.connect.channel = chan; return cfg80211_mgd_wext_connect(rdev, wdev); } int cfg80211_mgd_wext_giwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *freq, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct ieee80211_channel *chan = NULL; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; if (wdev->valid_links) return -EOPNOTSUPP; if (wdev->links[0].client.current_bss) chan = wdev->links[0].client.current_bss->pub.channel; else if (wdev->wext.connect.channel) chan = wdev->wext.connect.channel; if (chan) { freq->m = chan->center_freq; freq->e = 6; return 0; } /* no channel if not joining */ return -EINVAL; } int cfg80211_mgd_wext_siwessid(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); size_t len = data->length; int err; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; if (!data->flags) len = 0; /* iwconfig uses nul termination in SSID.. */ if (len > 0 && ssid[len - 1] == '\0') len--; if (wdev->conn) { bool event = true; if (wdev->wext.connect.ssid && len && len == wdev->wext.connect.ssid_len && memcmp(wdev->wext.connect.ssid, ssid, len) == 0) return 0; /* if SSID set now, we'll try to connect, avoid event */ if (len) event = false; err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, event); if (err) return err; } wdev->wext.prev_bssid_valid = false; wdev->wext.connect.ssid = wdev->wext.ssid; memcpy(wdev->wext.ssid, ssid, len); wdev->wext.connect.ssid_len = len; wdev->wext.connect.crypto.control_port = false; wdev->wext.connect.crypto.control_port_ethertype = cpu_to_be16(ETH_P_PAE); return cfg80211_mgd_wext_connect(rdev, wdev); } int cfg80211_mgd_wext_giwessid(struct net_device *dev, struct iw_request_info *info, struct iw_point *data, char *ssid) { struct wireless_dev *wdev = dev->ieee80211_ptr; int ret = 0; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; if (wdev->valid_links) return -EINVAL; data->flags = 0; if (wdev->links[0].client.current_bss) { const struct element *ssid_elem; rcu_read_lock(); ssid_elem = ieee80211_bss_get_elem( &wdev->links[0].client.current_bss->pub, WLAN_EID_SSID); if (ssid_elem) { data->flags = 1; data->length = ssid_elem->datalen; if (data->length > IW_ESSID_MAX_SIZE) ret = -EINVAL; else memcpy(ssid, ssid_elem->data, data->length); } rcu_read_unlock(); } else if (wdev->wext.connect.ssid && wdev->wext.connect.ssid_len) { data->flags = 1; data->length = wdev->wext.connect.ssid_len; memcpy(ssid, wdev->wext.connect.ssid, data->length); } return ret; } int cfg80211_mgd_wext_siwap(struct net_device *dev, struct iw_request_info *info, struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); u8 *bssid = ap_addr->sa_data; int err; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; if (ap_addr->sa_family != ARPHRD_ETHER) return -EINVAL; /* automatic mode */ if (is_zero_ether_addr(bssid) || is_broadcast_ether_addr(bssid)) bssid = NULL; if (wdev->conn) { /* both automatic */ if (!bssid && !wdev->wext.connect.bssid) return 0; /* fixed already - and no change */ if (wdev->wext.connect.bssid && bssid && ether_addr_equal(bssid, wdev->wext.connect.bssid)) return 0; err = cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, false); if (err) return err; } if (bssid) { memcpy(wdev->wext.bssid, bssid, ETH_ALEN); wdev->wext.connect.bssid = wdev->wext.bssid; } else wdev->wext.connect.bssid = NULL; return cfg80211_mgd_wext_connect(rdev, wdev); } int cfg80211_mgd_wext_giwap(struct net_device *dev, struct iw_request_info *info, struct sockaddr *ap_addr, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; /* call only for station! */ if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) return -EINVAL; ap_addr->sa_family = ARPHRD_ETHER; if (wdev->valid_links) return -EOPNOTSUPP; if (wdev->links[0].client.current_bss) memcpy(ap_addr->sa_data, wdev->links[0].client.current_bss->pub.bssid, ETH_ALEN); else eth_zero_addr(ap_addr->sa_data); return 0; } int cfg80211_wext_siwgenie(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct iw_point *data = &wrqu->data; struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); int ie_len = data->length; u8 *ie = extra; if (wdev->iftype != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!ie_len) ie = NULL; guard(wiphy)(wdev->wiphy); /* no change */ if (wdev->wext.ie_len == ie_len && memcmp(wdev->wext.ie, ie, ie_len) == 0) return 0; if (ie_len) { ie = kmemdup(extra, ie_len, GFP_KERNEL); if (!ie) return -ENOMEM; } else { ie = NULL; } kfree(wdev->wext.ie); wdev->wext.ie = ie; wdev->wext.ie_len = ie_len; if (wdev->conn) return cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, false); /* userspace better not think we'll reconnect */ return 0; } int cfg80211_wext_siwmlme(struct net_device *dev, struct iw_request_info *info, union iwreq_data *wrqu, char *extra) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct iw_mlme *mlme = (struct iw_mlme *)extra; struct cfg80211_registered_device *rdev; if (!wdev) return -EOPNOTSUPP; rdev = wiphy_to_rdev(wdev->wiphy); if (wdev->iftype != NL80211_IFTYPE_STATION) return -EINVAL; if (mlme->addr.sa_family != ARPHRD_ETHER) return -EINVAL; guard(wiphy)(&rdev->wiphy); switch (mlme->cmd) { case IW_MLME_DEAUTH: case IW_MLME_DISASSOC: return cfg80211_disconnect(rdev, dev, mlme->reason_code, true); default: return -EOPNOTSUPP; } } |
| 4421 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM printk #if !defined(_TRACE_PRINTK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PRINTK_H #include <linux/tracepoint.h> TRACE_EVENT(console, TP_PROTO(const char *text, size_t len), TP_ARGS(text, len), TP_STRUCT__entry( __dynamic_array(char, msg, len + 1) ), TP_fast_assign( /* * Each trace entry is printed in a new line. * If the msg finishes with '\n', cut it off * to avoid blank lines in the trace. */ if ((len > 0) && (text[len-1] == '\n')) len -= 1; memcpy(__get_str(msg), text, len); __get_str(msg)[len] = 0; ), TP_printk("%s", __get_str(msg)) ); #endif /* _TRACE_PRINTK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ #include "main.h" #include <linux/byteorder/generic.h> #include <linux/container_of.h> #include <linux/etherdevice.h> #include <linux/gfp.h> #include <linux/if_ether.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/lockdep.h> #include <linux/netdevice.h> #include <linux/pkt_sched.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> #include <linux/types.h> #include <uapi/linux/batadv_packet.h> #include "originator.h" #include "send.h" #include "tvlv.h" /** * batadv_tvlv_handler_release() - release tvlv handler from lists and queue for * free after rcu grace period * @ref: kref pointer of the tvlv */ static void batadv_tvlv_handler_release(struct kref *ref) { struct batadv_tvlv_handler *tvlv_handler; tvlv_handler = container_of(ref, struct batadv_tvlv_handler, refcount); kfree_rcu(tvlv_handler, rcu); } /** * batadv_tvlv_handler_put() - decrement the tvlv container refcounter and * possibly release it * @tvlv_handler: the tvlv handler to free */ static void batadv_tvlv_handler_put(struct batadv_tvlv_handler *tvlv_handler) { if (!tvlv_handler) return; kref_put(&tvlv_handler->refcount, batadv_tvlv_handler_release); } /** * batadv_tvlv_handler_get() - retrieve tvlv handler from the tvlv handler list * based on the provided type and version (both need to match) * @bat_priv: the bat priv with all the mesh interface information * @type: tvlv handler type to look for * @version: tvlv handler version to look for * * Return: tvlv handler if found or NULL otherwise. */ static struct batadv_tvlv_handler * batadv_tvlv_handler_get(struct batadv_priv *bat_priv, u8 type, u8 version) { struct batadv_tvlv_handler *tvlv_handler_tmp, *tvlv_handler = NULL; rcu_read_lock(); hlist_for_each_entry_rcu(tvlv_handler_tmp, &bat_priv->tvlv.handler_list, list) { if (tvlv_handler_tmp->type != type) continue; if (tvlv_handler_tmp->version != version) continue; if (!kref_get_unless_zero(&tvlv_handler_tmp->refcount)) continue; tvlv_handler = tvlv_handler_tmp; break; } rcu_read_unlock(); return tvlv_handler; } /** * batadv_tvlv_container_release() - release tvlv from lists and free * @ref: kref pointer of the tvlv */ static void batadv_tvlv_container_release(struct kref *ref) { struct batadv_tvlv_container *tvlv; tvlv = container_of(ref, struct batadv_tvlv_container, refcount); kfree(tvlv); } /** * batadv_tvlv_container_put() - decrement the tvlv container refcounter and * possibly release it * @tvlv: the tvlv container to free */ static void batadv_tvlv_container_put(struct batadv_tvlv_container *tvlv) { if (!tvlv) return; kref_put(&tvlv->refcount, batadv_tvlv_container_release); } /** * batadv_tvlv_container_get() - retrieve tvlv container from the tvlv container * list based on the provided type and version (both need to match) * @bat_priv: the bat priv with all the mesh interface information * @type: tvlv container type to look for * @version: tvlv container version to look for * * Has to be called with the appropriate locks being acquired * (tvlv.container_list_lock). * * Return: tvlv container if found or NULL otherwise. */ static struct batadv_tvlv_container * batadv_tvlv_container_get(struct batadv_priv *bat_priv, u8 type, u8 version) { struct batadv_tvlv_container *tvlv_tmp, *tvlv = NULL; lockdep_assert_held(&bat_priv->tvlv.container_list_lock); hlist_for_each_entry(tvlv_tmp, &bat_priv->tvlv.container_list, list) { if (tvlv_tmp->tvlv_hdr.type != type) continue; if (tvlv_tmp->tvlv_hdr.version != version) continue; kref_get(&tvlv_tmp->refcount); tvlv = tvlv_tmp; break; } return tvlv; } /** * batadv_tvlv_container_list_size() - calculate the size of the tvlv container * list entries * @bat_priv: the bat priv with all the mesh interface information * * Has to be called with the appropriate locks being acquired * (tvlv.container_list_lock). * * Return: size of all currently registered tvlv containers in bytes. */ static u16 batadv_tvlv_container_list_size(struct batadv_priv *bat_priv) { struct batadv_tvlv_container *tvlv; u16 tvlv_len = 0; lockdep_assert_held(&bat_priv->tvlv.container_list_lock); hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) { tvlv_len += sizeof(struct batadv_tvlv_hdr); tvlv_len += ntohs(tvlv->tvlv_hdr.len); } return tvlv_len; } /** * batadv_tvlv_container_remove() - remove tvlv container from the tvlv * container list * @bat_priv: the bat priv with all the mesh interface information * @tvlv: the to be removed tvlv container * * Has to be called with the appropriate locks being acquired * (tvlv.container_list_lock). */ static void batadv_tvlv_container_remove(struct batadv_priv *bat_priv, struct batadv_tvlv_container *tvlv) { lockdep_assert_held(&bat_priv->tvlv.container_list_lock); if (!tvlv) return; hlist_del(&tvlv->list); /* first call to decrement the counter, second call to free */ batadv_tvlv_container_put(tvlv); batadv_tvlv_container_put(tvlv); } /** * batadv_tvlv_container_unregister() - unregister tvlv container based on the * provided type and version (both need to match) * @bat_priv: the bat priv with all the mesh interface information * @type: tvlv container type to unregister * @version: tvlv container type to unregister */ void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv, u8 type, u8 version) { struct batadv_tvlv_container *tvlv; spin_lock_bh(&bat_priv->tvlv.container_list_lock); tvlv = batadv_tvlv_container_get(bat_priv, type, version); batadv_tvlv_container_remove(bat_priv, tvlv); spin_unlock_bh(&bat_priv->tvlv.container_list_lock); } /** * batadv_tvlv_container_register() - register tvlv type, version and content * to be propagated with each (primary interface) OGM * @bat_priv: the bat priv with all the mesh interface information * @type: tvlv container type * @version: tvlv container version * @tvlv_value: tvlv container content * @tvlv_value_len: tvlv container content length * * If a container of the same type and version was already registered the new * content is going to replace the old one. */ void batadv_tvlv_container_register(struct batadv_priv *bat_priv, u8 type, u8 version, void *tvlv_value, u16 tvlv_value_len) { struct batadv_tvlv_container *tvlv_old, *tvlv_new; if (!tvlv_value) tvlv_value_len = 0; tvlv_new = kzalloc(sizeof(*tvlv_new) + tvlv_value_len, GFP_ATOMIC); if (!tvlv_new) return; tvlv_new->tvlv_hdr.version = version; tvlv_new->tvlv_hdr.type = type; tvlv_new->tvlv_hdr.len = htons(tvlv_value_len); memcpy(tvlv_new + 1, tvlv_value, ntohs(tvlv_new->tvlv_hdr.len)); INIT_HLIST_NODE(&tvlv_new->list); kref_init(&tvlv_new->refcount); spin_lock_bh(&bat_priv->tvlv.container_list_lock); tvlv_old = batadv_tvlv_container_get(bat_priv, type, version); batadv_tvlv_container_remove(bat_priv, tvlv_old); kref_get(&tvlv_new->refcount); hlist_add_head(&tvlv_new->list, &bat_priv->tvlv.container_list); spin_unlock_bh(&bat_priv->tvlv.container_list_lock); /* don't return reference to new tvlv_container */ batadv_tvlv_container_put(tvlv_new); } /** * batadv_tvlv_realloc_packet_buff() - reallocate packet buffer to accommodate * requested packet size * @packet_buff: packet buffer * @packet_buff_len: packet buffer size * @min_packet_len: requested packet minimum size * @additional_packet_len: requested additional packet size on top of minimum * size * * Return: true of the packet buffer could be changed to the requested size, * false otherwise. */ static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff, int *packet_buff_len, int min_packet_len, int additional_packet_len) { unsigned char *new_buff; new_buff = kmalloc(min_packet_len + additional_packet_len, GFP_ATOMIC); /* keep old buffer if kmalloc should fail */ if (!new_buff) return false; memcpy(new_buff, *packet_buff, min_packet_len); kfree(*packet_buff); *packet_buff = new_buff; *packet_buff_len = min_packet_len + additional_packet_len; return true; } /** * batadv_tvlv_container_ogm_append() - append tvlv container content to given * OGM packet buffer * @bat_priv: the bat priv with all the mesh interface information * @packet_buff: ogm packet buffer * @packet_buff_len: ogm packet buffer size including ogm header and tvlv * content * @packet_min_len: ogm header size to be preserved for the OGM itself * * The ogm packet might be enlarged or shrunk depending on the current size * and the size of the to-be-appended tvlv containers. * * Return: size of all appended tvlv containers in bytes. */ u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv, unsigned char **packet_buff, int *packet_buff_len, int packet_min_len) { struct batadv_tvlv_container *tvlv; struct batadv_tvlv_hdr *tvlv_hdr; u16 tvlv_value_len; void *tvlv_value; bool ret; spin_lock_bh(&bat_priv->tvlv.container_list_lock); tvlv_value_len = batadv_tvlv_container_list_size(bat_priv); ret = batadv_tvlv_realloc_packet_buff(packet_buff, packet_buff_len, packet_min_len, tvlv_value_len); if (!ret) goto end; if (!tvlv_value_len) goto end; tvlv_value = (*packet_buff) + packet_min_len; hlist_for_each_entry(tvlv, &bat_priv->tvlv.container_list, list) { tvlv_hdr = tvlv_value; tvlv_hdr->type = tvlv->tvlv_hdr.type; tvlv_hdr->version = tvlv->tvlv_hdr.version; tvlv_hdr->len = tvlv->tvlv_hdr.len; tvlv_value = tvlv_hdr + 1; memcpy(tvlv_value, tvlv + 1, ntohs(tvlv->tvlv_hdr.len)); tvlv_value = (u8 *)tvlv_value + ntohs(tvlv->tvlv_hdr.len); } end: spin_unlock_bh(&bat_priv->tvlv.container_list_lock); return tvlv_value_len; } /** * batadv_tvlv_call_handler() - parse the given tvlv buffer to call the * appropriate handlers * @bat_priv: the bat priv with all the mesh interface information * @tvlv_handler: tvlv callback function handling the tvlv content * @packet_type: indicates for which packet type the TVLV handler is called * @orig_node: orig node emitting the ogm packet * @skb: the skb the TVLV handler is called for * @tvlv_value: tvlv content * @tvlv_value_len: tvlv content length * * Return: success if the handler was not found or the return value of the * handler callback. */ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv, struct batadv_tvlv_handler *tvlv_handler, u8 packet_type, struct batadv_orig_node *orig_node, struct sk_buff *skb, void *tvlv_value, u16 tvlv_value_len) { unsigned int tvlv_offset; u8 *src, *dst; if (!tvlv_handler) return NET_RX_SUCCESS; switch (packet_type) { case BATADV_IV_OGM: case BATADV_OGM2: if (!tvlv_handler->ogm_handler) return NET_RX_SUCCESS; if (!orig_node) return NET_RX_SUCCESS; tvlv_handler->ogm_handler(bat_priv, orig_node, BATADV_NO_FLAGS, tvlv_value, tvlv_value_len); tvlv_handler->flags |= BATADV_TVLV_HANDLER_OGM_CALLED; break; case BATADV_UNICAST_TVLV: if (!skb) return NET_RX_SUCCESS; if (!tvlv_handler->unicast_handler) return NET_RX_SUCCESS; src = ((struct batadv_unicast_tvlv_packet *)skb->data)->src; dst = ((struct batadv_unicast_tvlv_packet *)skb->data)->dst; return tvlv_handler->unicast_handler(bat_priv, src, dst, tvlv_value, tvlv_value_len); case BATADV_MCAST: if (!skb) return NET_RX_SUCCESS; if (!tvlv_handler->mcast_handler) return NET_RX_SUCCESS; tvlv_offset = (unsigned char *)tvlv_value - skb->data; skb_set_network_header(skb, tvlv_offset); skb_set_transport_header(skb, tvlv_offset + tvlv_value_len); return tvlv_handler->mcast_handler(bat_priv, skb); } return NET_RX_SUCCESS; } /** * batadv_tvlv_containers_process() - parse the given tvlv buffer to call the * appropriate handlers * @bat_priv: the bat priv with all the mesh interface information * @packet_type: indicates for which packet type the TVLV handler is called * @orig_node: orig node emitting the ogm packet * @skb: the skb the TVLV handler is called for * @tvlv_value: tvlv content * @tvlv_value_len: tvlv content length * * Return: success when processing an OGM or the return value of all called * handler callbacks. */ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv, u8 packet_type, struct batadv_orig_node *orig_node, struct sk_buff *skb, void *tvlv_value, u16 tvlv_value_len) { struct batadv_tvlv_handler *tvlv_handler; struct batadv_tvlv_hdr *tvlv_hdr; u16 tvlv_value_cont_len; u8 cifnotfound = BATADV_TVLV_HANDLER_OGM_CIFNOTFND; int ret = NET_RX_SUCCESS; while (tvlv_value_len >= sizeof(*tvlv_hdr)) { tvlv_hdr = tvlv_value; tvlv_value_cont_len = ntohs(tvlv_hdr->len); tvlv_value = tvlv_hdr + 1; tvlv_value_len -= sizeof(*tvlv_hdr); if (tvlv_value_cont_len > tvlv_value_len) break; tvlv_handler = batadv_tvlv_handler_get(bat_priv, tvlv_hdr->type, tvlv_hdr->version); ret |= batadv_tvlv_call_handler(bat_priv, tvlv_handler, packet_type, orig_node, skb, tvlv_value, tvlv_value_cont_len); batadv_tvlv_handler_put(tvlv_handler); tvlv_value = (u8 *)tvlv_value + tvlv_value_cont_len; tvlv_value_len -= tvlv_value_cont_len; } if (packet_type != BATADV_IV_OGM && packet_type != BATADV_OGM2) return ret; rcu_read_lock(); hlist_for_each_entry_rcu(tvlv_handler, &bat_priv->tvlv.handler_list, list) { if (!tvlv_handler->ogm_handler) continue; if ((tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND) && !(tvlv_handler->flags & BATADV_TVLV_HANDLER_OGM_CALLED)) tvlv_handler->ogm_handler(bat_priv, orig_node, cifnotfound, NULL, 0); tvlv_handler->flags &= ~BATADV_TVLV_HANDLER_OGM_CALLED; } rcu_read_unlock(); return NET_RX_SUCCESS; } /** * batadv_tvlv_ogm_receive() - process an incoming ogm and call the appropriate * handlers * @bat_priv: the bat priv with all the mesh interface information * @batadv_ogm_packet: ogm packet containing the tvlv containers * @orig_node: orig node emitting the ogm packet */ void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv, struct batadv_ogm_packet *batadv_ogm_packet, struct batadv_orig_node *orig_node) { void *tvlv_value; u16 tvlv_value_len; if (!batadv_ogm_packet) return; tvlv_value_len = ntohs(batadv_ogm_packet->tvlv_len); if (!tvlv_value_len) return; tvlv_value = batadv_ogm_packet + 1; batadv_tvlv_containers_process(bat_priv, BATADV_IV_OGM, orig_node, NULL, tvlv_value, tvlv_value_len); } /** * batadv_tvlv_handler_register() - register tvlv handler based on the provided * type and version (both need to match) for ogm tvlv payload and/or unicast * payload * @bat_priv: the bat priv with all the mesh interface information * @optr: ogm tvlv handler callback function. This function receives the orig * node, flags and the tvlv content as argument to process. * @uptr: unicast tvlv handler callback function. This function receives the * source & destination of the unicast packet as well as the tvlv content * to process. * @mptr: multicast packet tvlv handler callback function. This function * receives the full skb to process, with the skb network header pointing * to the current tvlv and the skb transport header pointing to the first * byte after the current tvlv. * @type: tvlv handler type to be registered * @version: tvlv handler version to be registered * @flags: flags to enable or disable TVLV API behavior */ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv, void (*optr)(struct batadv_priv *bat_priv, struct batadv_orig_node *orig, u8 flags, void *tvlv_value, u16 tvlv_value_len), int (*uptr)(struct batadv_priv *bat_priv, u8 *src, u8 *dst, void *tvlv_value, u16 tvlv_value_len), int (*mptr)(struct batadv_priv *bat_priv, struct sk_buff *skb), u8 type, u8 version, u8 flags) { struct batadv_tvlv_handler *tvlv_handler; spin_lock_bh(&bat_priv->tvlv.handler_list_lock); tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version); if (tvlv_handler) { spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); batadv_tvlv_handler_put(tvlv_handler); return; } tvlv_handler = kzalloc_obj(*tvlv_handler, GFP_ATOMIC); if (!tvlv_handler) { spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); return; } tvlv_handler->ogm_handler = optr; tvlv_handler->unicast_handler = uptr; tvlv_handler->mcast_handler = mptr; tvlv_handler->type = type; tvlv_handler->version = version; tvlv_handler->flags = flags; kref_init(&tvlv_handler->refcount); INIT_HLIST_NODE(&tvlv_handler->list); kref_get(&tvlv_handler->refcount); hlist_add_head_rcu(&tvlv_handler->list, &bat_priv->tvlv.handler_list); spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); /* don't return reference to new tvlv_handler */ batadv_tvlv_handler_put(tvlv_handler); } /** * batadv_tvlv_handler_unregister() - unregister tvlv handler based on the * provided type and version (both need to match) * @bat_priv: the bat priv with all the mesh interface information * @type: tvlv handler type to be unregistered * @version: tvlv handler version to be unregistered */ void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv, u8 type, u8 version) { struct batadv_tvlv_handler *tvlv_handler; tvlv_handler = batadv_tvlv_handler_get(bat_priv, type, version); if (!tvlv_handler) return; batadv_tvlv_handler_put(tvlv_handler); spin_lock_bh(&bat_priv->tvlv.handler_list_lock); hlist_del_rcu(&tvlv_handler->list); spin_unlock_bh(&bat_priv->tvlv.handler_list_lock); batadv_tvlv_handler_put(tvlv_handler); } /** * batadv_tvlv_unicast_send() - send a unicast packet with tvlv payload to the * specified host * @bat_priv: the bat priv with all the mesh interface information * @src: source mac address of the unicast packet * @dst: destination mac address of the unicast packet * @type: tvlv type * @version: tvlv version * @tvlv_value: tvlv content * @tvlv_value_len: tvlv content length */ void batadv_tvlv_unicast_send(struct batadv_priv *bat_priv, const u8 *src, const u8 *dst, u8 type, u8 version, void *tvlv_value, u16 tvlv_value_len) { struct batadv_unicast_tvlv_packet *unicast_tvlv_packet; struct batadv_tvlv_hdr *tvlv_hdr; struct batadv_orig_node *orig_node; struct sk_buff *skb; unsigned char *tvlv_buff; unsigned int tvlv_len; ssize_t hdr_len = sizeof(*unicast_tvlv_packet); orig_node = batadv_orig_hash_find(bat_priv, dst); if (!orig_node) return; tvlv_len = sizeof(*tvlv_hdr) + tvlv_value_len; skb = netdev_alloc_skb_ip_align(NULL, ETH_HLEN + hdr_len + tvlv_len); if (!skb) goto out; skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, ETH_HLEN); tvlv_buff = skb_put(skb, sizeof(*unicast_tvlv_packet) + tvlv_len); unicast_tvlv_packet = (struct batadv_unicast_tvlv_packet *)tvlv_buff; unicast_tvlv_packet->packet_type = BATADV_UNICAST_TVLV; unicast_tvlv_packet->version = BATADV_COMPAT_VERSION; unicast_tvlv_packet->ttl = BATADV_TTL; unicast_tvlv_packet->reserved = 0; unicast_tvlv_packet->tvlv_len = htons(tvlv_len); unicast_tvlv_packet->align = 0; ether_addr_copy(unicast_tvlv_packet->src, src); ether_addr_copy(unicast_tvlv_packet->dst, dst); tvlv_buff = (unsigned char *)(unicast_tvlv_packet + 1); tvlv_hdr = (struct batadv_tvlv_hdr *)tvlv_buff; tvlv_hdr->version = version; tvlv_hdr->type = type; tvlv_hdr->len = htons(tvlv_value_len); tvlv_buff += sizeof(*tvlv_hdr); memcpy(tvlv_buff, tvlv_value, tvlv_value_len); batadv_send_skb_to_orig(skb, orig_node, NULL); out: batadv_orig_node_put(orig_node); } |
| 8 8 8 8 8 8 8 8 8 8 8 8 8 8 4 8 8 8 4 8 8 8 8 8 8 8 8 8 8 8 2 2 2 2 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 8 57 58 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler, * for the blk-mq scheduling framework * * Copyright (C) 2016 Jens Axboe <axboe@kernel.dk> */ #include <linux/kernel.h> #include <linux/fs.h> #include <linux/blkdev.h> #include <linux/bio.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/sbitmap.h> #include <trace/events/block.h> #include "elevator.h" #include "blk.h" #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-mq-sched.h" /* * See Documentation/block/deadline-iosched.rst */ static const int read_expire = HZ / 2; /* max time before a read is submitted. */ static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */ /* * Time after which to dispatch lower priority requests even if higher * priority requests are pending. */ static const int prio_aging_expire = 10 * HZ; static const int writes_starved = 2; /* max times reads can starve a write */ static const int fifo_batch = 16; /* # of sequential requests treated as one by the above parameters. For throughput. */ enum dd_data_dir { DD_READ = READ, DD_WRITE = WRITE, }; enum { DD_DIR_COUNT = 2 }; enum dd_prio { DD_RT_PRIO = 0, DD_BE_PRIO = 1, DD_IDLE_PRIO = 2, DD_PRIO_MAX = 2, }; enum { DD_PRIO_COUNT = 3 }; /* * I/O statistics per I/O priority. It is fine if these counters overflow. * What matters is that these counters are at least as wide as * log2(max_outstanding_requests). */ struct io_stats_per_prio { uint32_t inserted; uint32_t merged; uint32_t dispatched; atomic_t completed; }; /* * Deadline scheduler data per I/O priority (enum dd_prio). Requests are * present on both sort_list[] and fifo_list[]. */ struct dd_per_prio { struct rb_root sort_list[DD_DIR_COUNT]; struct list_head fifo_list[DD_DIR_COUNT]; /* Position of the most recently dispatched request. */ sector_t latest_pos[DD_DIR_COUNT]; struct io_stats_per_prio stats; }; struct deadline_data { /* * run time data */ struct list_head dispatch; struct dd_per_prio per_prio[DD_PRIO_COUNT]; /* Data direction of latest dispatched request. */ enum dd_data_dir last_dir; unsigned int batching; /* number of sequential requests made */ unsigned int starved; /* times reads have starved writes */ /* * settings that change how the i/o scheduler behaves */ int fifo_expire[DD_DIR_COUNT]; int fifo_batch; int writes_starved; int front_merges; int prio_aging_expire; spinlock_t lock; }; /* Maps an I/O priority class to a deadline scheduler priority. */ static const enum dd_prio ioprio_class_to_prio[] = { [IOPRIO_CLASS_NONE] = DD_BE_PRIO, [IOPRIO_CLASS_RT] = DD_RT_PRIO, [IOPRIO_CLASS_BE] = DD_BE_PRIO, [IOPRIO_CLASS_IDLE] = DD_IDLE_PRIO, }; static inline struct rb_root * deadline_rb_root(struct dd_per_prio *per_prio, struct request *rq) { return &per_prio->sort_list[rq_data_dir(rq)]; } /* * Returns the I/O priority class (IOPRIO_CLASS_*) that has been assigned to a * request. */ static u8 dd_rq_ioclass(struct request *rq) { return IOPRIO_PRIO_CLASS(req_get_ioprio(rq)); } /* * Return the first request for which blk_rq_pos() >= @pos. */ static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio, enum dd_data_dir data_dir, sector_t pos) { struct rb_node *node = per_prio->sort_list[data_dir].rb_node; struct request *rq, *res = NULL; while (node) { rq = rb_entry_rq(node); if (blk_rq_pos(rq) >= pos) { res = rq; node = node->rb_left; } else { node = node->rb_right; } } return res; } static void deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq) { struct rb_root *root = deadline_rb_root(per_prio, rq); elv_rb_add(root, rq); } static inline void deadline_del_rq_rb(struct dd_per_prio *per_prio, struct request *rq) { elv_rb_del(deadline_rb_root(per_prio, rq), rq); } /* * remove rq from rbtree and fifo. */ static void deadline_remove_request(struct request_queue *q, struct dd_per_prio *per_prio, struct request *rq) { list_del_init(&rq->queuelist); /* * We might not be on the rbtree, if we are doing an insert merge */ if (!RB_EMPTY_NODE(&rq->rb_node)) deadline_del_rq_rb(per_prio, rq); elv_rqhash_del(q, rq); if (q->last_merge == rq) q->last_merge = NULL; } static void dd_request_merged(struct request_queue *q, struct request *req, enum elv_merge type) { struct deadline_data *dd = q->elevator->elevator_data; const u8 ioprio_class = dd_rq_ioclass(req); const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; struct dd_per_prio *per_prio = &dd->per_prio[prio]; /* * if the merge was a front merge, we need to reposition request */ if (type == ELEVATOR_FRONT_MERGE) { elv_rb_del(deadline_rb_root(per_prio, req), req); deadline_add_rq_rb(per_prio, req); } } /* * Callback function that is invoked after @next has been merged into @req. */ static void dd_merged_requests(struct request_queue *q, struct request *req, struct request *next) { struct deadline_data *dd = q->elevator->elevator_data; const u8 ioprio_class = dd_rq_ioclass(next); const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; lockdep_assert_held(&dd->lock); dd->per_prio[prio].stats.merged++; /* * if next expires before rq, assign its expire time to rq * and move into next position (next will be deleted) in fifo */ if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) { if (time_before((unsigned long)next->fifo_time, (unsigned long)req->fifo_time)) { list_move(&req->queuelist, &next->queuelist); req->fifo_time = next->fifo_time; } } /* * kill knowledge of next, this one is a goner */ deadline_remove_request(q, &dd->per_prio[prio], next); } /* * move an entry to dispatch queue */ static void deadline_move_request(struct deadline_data *dd, struct dd_per_prio *per_prio, struct request *rq) { /* * take it off the sort and fifo list */ deadline_remove_request(rq->q, per_prio, rq); } /* Number of requests queued for a given priority level. */ static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio) { const struct io_stats_per_prio *stats = &dd->per_prio[prio].stats; lockdep_assert_held(&dd->lock); return stats->inserted - atomic_read(&stats->completed); } /* * deadline_check_fifo returns true if and only if there are expired requests * in the FIFO list. Requires !list_empty(&dd->fifo_list[data_dir]). */ static inline bool deadline_check_fifo(struct dd_per_prio *per_prio, enum dd_data_dir data_dir) { struct request *rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next); return time_is_before_eq_jiffies((unsigned long)rq->fifo_time); } /* * For the specified data direction, return the next request to * dispatch using arrival ordered lists. */ static struct request * deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio, enum dd_data_dir data_dir) { if (list_empty(&per_prio->fifo_list[data_dir])) return NULL; return rq_entry_fifo(per_prio->fifo_list[data_dir].next); } /* * For the specified data direction, return the next request to * dispatch using sector position sorted lists. */ static struct request * deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio, enum dd_data_dir data_dir) { return deadline_from_pos(per_prio, data_dir, per_prio->latest_pos[data_dir]); } /* * Returns true if and only if @rq started after @latest_start where * @latest_start is in jiffies. */ static bool started_after(struct deadline_data *dd, struct request *rq, unsigned long latest_start) { unsigned long start_time = (unsigned long)rq->fifo_time; start_time -= dd->fifo_expire[rq_data_dir(rq)]; return time_after(start_time, latest_start); } static struct request *dd_start_request(struct deadline_data *dd, enum dd_data_dir data_dir, struct request *rq) { u8 ioprio_class = dd_rq_ioclass(rq); enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; dd->per_prio[prio].latest_pos[data_dir] = blk_rq_pos(rq); dd->per_prio[prio].stats.dispatched++; rq->rq_flags |= RQF_STARTED; return rq; } /* * deadline_dispatch_requests selects the best request according to * read/write expire, fifo_batch, etc and with a start time <= @latest_start. */ static struct request *__dd_dispatch_request(struct deadline_data *dd, struct dd_per_prio *per_prio, unsigned long latest_start) { struct request *rq, *next_rq; enum dd_data_dir data_dir; lockdep_assert_held(&dd->lock); /* * batches are currently reads XOR writes */ rq = deadline_next_request(dd, per_prio, dd->last_dir); if (rq && dd->batching < dd->fifo_batch) { /* we have a next request and are still entitled to batch */ data_dir = rq_data_dir(rq); goto dispatch_request; } /* * at this point we are not running a batch. select the appropriate * data direction (read / write) */ if (!list_empty(&per_prio->fifo_list[DD_READ])) { BUG_ON(RB_EMPTY_ROOT(&per_prio->sort_list[DD_READ])); if (deadline_fifo_request(dd, per_prio, DD_WRITE) && (dd->starved++ >= dd->writes_starved)) goto dispatch_writes; data_dir = DD_READ; goto dispatch_find_request; } /* * there are either no reads or writes have been starved */ if (!list_empty(&per_prio->fifo_list[DD_WRITE])) { dispatch_writes: BUG_ON(RB_EMPTY_ROOT(&per_prio->sort_list[DD_WRITE])); dd->starved = 0; data_dir = DD_WRITE; goto dispatch_find_request; } return NULL; dispatch_find_request: /* * we are not running a batch, find best request for selected data_dir */ next_rq = deadline_next_request(dd, per_prio, data_dir); if (deadline_check_fifo(per_prio, data_dir) || !next_rq) { /* * A deadline has expired, the last request was in the other * direction, or we have run out of higher-sectored requests. * Start again from the request with the earliest expiry time. */ rq = deadline_fifo_request(dd, per_prio, data_dir); } else { /* * The last req was the same dir and we have a next request in * sort order. No expired requests so continue on from here. */ rq = next_rq; } if (!rq) return NULL; dd->last_dir = data_dir; dd->batching = 0; dispatch_request: if (started_after(dd, rq, latest_start)) return NULL; /* * rq is the selected appropriate request. */ dd->batching++; deadline_move_request(dd, per_prio, rq); return dd_start_request(dd, data_dir, rq); } /* * Check whether there are any requests with priority other than DD_RT_PRIO * that were inserted more than prio_aging_expire jiffies ago. */ static struct request *dd_dispatch_prio_aged_requests(struct deadline_data *dd, unsigned long now) { struct request *rq; enum dd_prio prio; int prio_cnt; lockdep_assert_held(&dd->lock); prio_cnt = !!dd_queued(dd, DD_RT_PRIO) + !!dd_queued(dd, DD_BE_PRIO) + !!dd_queued(dd, DD_IDLE_PRIO); if (prio_cnt < 2) return NULL; for (prio = DD_BE_PRIO; prio <= DD_PRIO_MAX; prio++) { rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now - dd->prio_aging_expire); if (rq) return rq; } return NULL; } /* * Called from blk_mq_run_hw_queue() -> __blk_mq_sched_dispatch_requests(). * * One confusing aspect here is that we get called for a specific * hardware queue, but we may return a request that is for a * different hardware queue. This is because mq-deadline has shared * state for all hardware queues, in terms of sorting, FIFOs, etc. */ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx) { struct deadline_data *dd = hctx->queue->elevator->elevator_data; const unsigned long now = jiffies; struct request *rq; enum dd_prio prio; spin_lock(&dd->lock); if (!list_empty(&dd->dispatch)) { rq = list_first_entry(&dd->dispatch, struct request, queuelist); list_del_init(&rq->queuelist); dd_start_request(dd, rq_data_dir(rq), rq); goto unlock; } rq = dd_dispatch_prio_aged_requests(dd, now); if (rq) goto unlock; /* * Next, dispatch requests in priority order. Ignore lower priority * requests if any higher priority requests are pending. */ for (prio = 0; prio <= DD_PRIO_MAX; prio++) { rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now); if (rq || dd_queued(dd, prio)) break; } unlock: spin_unlock(&dd->lock); return rq; } static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) { if (!blk_mq_is_sync_read(opf)) data->shallow_depth = data->q->async_depth; } /* Called by blk_mq_init_sched() and blk_mq_update_nr_requests(). */ static void dd_depth_updated(struct request_queue *q) { blk_mq_set_min_shallow_depth(q, q->async_depth); } static void dd_exit_sched(struct elevator_queue *e) { struct deadline_data *dd = e->elevator_data; enum dd_prio prio; for (prio = 0; prio <= DD_PRIO_MAX; prio++) { struct dd_per_prio *per_prio = &dd->per_prio[prio]; const struct io_stats_per_prio *stats = &per_prio->stats; uint32_t queued; WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_READ])); WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_WRITE])); spin_lock(&dd->lock); queued = dd_queued(dd, prio); spin_unlock(&dd->lock); WARN_ONCE(queued != 0, "statistics for priority %d: i %u m %u d %u c %u\n", prio, stats->inserted, stats->merged, stats->dispatched, atomic_read(&stats->completed)); } kfree(dd); } /* * initialize elevator private data (deadline_data). */ static int dd_init_sched(struct request_queue *q, struct elevator_queue *eq) { struct deadline_data *dd; enum dd_prio prio; dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node); if (!dd) return -ENOMEM; eq->elevator_data = dd; INIT_LIST_HEAD(&dd->dispatch); for (prio = 0; prio <= DD_PRIO_MAX; prio++) { struct dd_per_prio *per_prio = &dd->per_prio[prio]; INIT_LIST_HEAD(&per_prio->fifo_list[DD_READ]); INIT_LIST_HEAD(&per_prio->fifo_list[DD_WRITE]); per_prio->sort_list[DD_READ] = RB_ROOT; per_prio->sort_list[DD_WRITE] = RB_ROOT; } dd->fifo_expire[DD_READ] = read_expire; dd->fifo_expire[DD_WRITE] = write_expire; dd->writes_starved = writes_starved; dd->front_merges = 1; dd->last_dir = DD_WRITE; dd->fifo_batch = fifo_batch; dd->prio_aging_expire = prio_aging_expire; spin_lock_init(&dd->lock); /* We dispatch from request queue wide instead of hw queue */ blk_queue_flag_set(QUEUE_FLAG_SQ_SCHED, q); q->elevator = eq; q->async_depth = q->nr_requests; dd_depth_updated(q); return 0; } /* * Try to merge @bio into an existing request. If @bio has been merged into * an existing request, store the pointer to that request into *@rq. */ static int dd_request_merge(struct request_queue *q, struct request **rq, struct bio *bio) { struct deadline_data *dd = q->elevator->elevator_data; const u8 ioprio_class = IOPRIO_PRIO_CLASS(bio->bi_ioprio); const enum dd_prio prio = ioprio_class_to_prio[ioprio_class]; struct dd_per_prio *per_prio = &dd->per_prio[prio]; sector_t sector = bio_end_sector(bio); struct request *__rq; if (!dd->front_merges) return ELEVATOR_NO_MERGE; __rq = elv_rb_find(&per_prio->sort_list[bio_data_dir(bio)], sector); if (__rq) { BUG_ON(sector != blk_rq_pos(__rq)); if (elv_bio_merge_ok(__rq, bio)) { *rq = __rq; if (blk_discard_mergable(__rq)) return ELEVATOR_DISCARD_MERGE; return ELEVATOR_FRONT_MERGE; } } return ELEVATOR_NO_MERGE; } /* * Attempt to merge a bio into an existing request. This function is called * before @bio is associated with a request. */ static bool dd_bio_merge(struct request_queue *q, struct bio *bio, unsigned int nr_segs) { struct deadline_data *dd = q->elevator->elevator_data; struct request *free = NULL; bool ret; spin_lock(&dd->lock); ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free); spin_unlock(&dd->lock); if (free) blk_mq_free_request(free); return ret; } /* * add rq to rbtree and fifo */ static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, blk_insert_t flags, struct list_head *free) { struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; const enum dd_data_dir data_dir = rq_data_dir(rq); u16 ioprio = req_get_ioprio(rq); u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio); struct dd_per_prio *per_prio; enum dd_prio prio; lockdep_assert_held(&dd->lock); prio = ioprio_class_to_prio[ioprio_class]; per_prio = &dd->per_prio[prio]; if (!rq->elv.priv[0]) per_prio->stats.inserted++; rq->elv.priv[0] = per_prio; if (blk_mq_sched_try_insert_merge(q, rq, free)) return; trace_block_rq_insert(rq); if (flags & BLK_MQ_INSERT_AT_HEAD) { list_add(&rq->queuelist, &dd->dispatch); rq->fifo_time = jiffies; } else { deadline_add_rq_rb(per_prio, rq); if (rq_mergeable(rq)) { elv_rqhash_add(q, rq); if (!q->last_merge) q->last_merge = rq; } /* * set expire time and add to fifo list */ rq->fifo_time = jiffies + dd->fifo_expire[data_dir]; list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]); } } /* * Called from blk_mq_insert_request() or blk_mq_dispatch_list(). */ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, struct list_head *list, blk_insert_t flags) { struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; LIST_HEAD(free); spin_lock(&dd->lock); while (!list_empty(list)) { struct request *rq; rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); dd_insert_request(hctx, rq, flags, &free); } spin_unlock(&dd->lock); blk_mq_free_requests(&free); } /* Callback from inside blk_mq_rq_ctx_init(). */ static void dd_prepare_request(struct request *rq) { rq->elv.priv[0] = NULL; } /* * Callback from inside blk_mq_free_request(). */ static void dd_finish_request(struct request *rq) { struct dd_per_prio *per_prio = rq->elv.priv[0]; /* * The block layer core may call dd_finish_request() without having * called dd_insert_requests(). Skip requests that bypassed I/O * scheduling. See also blk_mq_request_bypass_insert(). */ if (per_prio) atomic_inc(&per_prio->stats.completed); } static bool dd_has_work_for_prio(struct dd_per_prio *per_prio) { return !list_empty_careful(&per_prio->fifo_list[DD_READ]) || !list_empty_careful(&per_prio->fifo_list[DD_WRITE]); } static bool dd_has_work(struct blk_mq_hw_ctx *hctx) { struct deadline_data *dd = hctx->queue->elevator->elevator_data; enum dd_prio prio; if (!list_empty_careful(&dd->dispatch)) return true; for (prio = 0; prio <= DD_PRIO_MAX; prio++) if (dd_has_work_for_prio(&dd->per_prio[prio])) return true; return false; } /* * sysfs parts below */ #define SHOW_INT(__FUNC, __VAR) \ static ssize_t __FUNC(struct elevator_queue *e, char *page) \ { \ struct deadline_data *dd = e->elevator_data; \ \ return sysfs_emit(page, "%d\n", __VAR); \ } #define SHOW_JIFFIES(__FUNC, __VAR) SHOW_INT(__FUNC, jiffies_to_msecs(__VAR)) SHOW_JIFFIES(deadline_read_expire_show, dd->fifo_expire[DD_READ]); SHOW_JIFFIES(deadline_write_expire_show, dd->fifo_expire[DD_WRITE]); SHOW_JIFFIES(deadline_prio_aging_expire_show, dd->prio_aging_expire); SHOW_INT(deadline_writes_starved_show, dd->writes_starved); SHOW_INT(deadline_front_merges_show, dd->front_merges); SHOW_INT(deadline_fifo_batch_show, dd->fifo_batch); #undef SHOW_INT #undef SHOW_JIFFIES #define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV) \ static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count) \ { \ struct deadline_data *dd = e->elevator_data; \ int __data, __ret; \ \ __ret = kstrtoint(page, 0, &__data); \ if (__ret < 0) \ return __ret; \ if (__data < (MIN)) \ __data = (MIN); \ else if (__data > (MAX)) \ __data = (MAX); \ *(__PTR) = __CONV(__data); \ return count; \ } #define STORE_INT(__FUNC, __PTR, MIN, MAX) \ STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, ) #define STORE_JIFFIES(__FUNC, __PTR, MIN, MAX) \ STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, msecs_to_jiffies) STORE_JIFFIES(deadline_read_expire_store, &dd->fifo_expire[DD_READ], 0, INT_MAX); STORE_JIFFIES(deadline_write_expire_store, &dd->fifo_expire[DD_WRITE], 0, INT_MAX); STORE_JIFFIES(deadline_prio_aging_expire_store, &dd->prio_aging_expire, 0, INT_MAX); STORE_INT(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX); STORE_INT(deadline_front_merges_store, &dd->front_merges, 0, 1); STORE_INT(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX); #undef STORE_FUNCTION #undef STORE_INT #undef STORE_JIFFIES #define DD_ATTR(name) \ __ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store) static const struct elv_fs_entry deadline_attrs[] = { DD_ATTR(read_expire), DD_ATTR(write_expire), DD_ATTR(writes_starved), DD_ATTR(front_merges), DD_ATTR(fifo_batch), DD_ATTR(prio_aging_expire), __ATTR_NULL }; #ifdef CONFIG_BLK_DEBUG_FS #define DEADLINE_DEBUGFS_DDIR_ATTRS(prio, data_dir, name) \ static void *deadline_##name##_fifo_start(struct seq_file *m, \ loff_t *pos) \ __acquires(&dd->lock) \ { \ struct request_queue *q = m->private; \ struct deadline_data *dd = q->elevator->elevator_data; \ struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ \ spin_lock(&dd->lock); \ return seq_list_start(&per_prio->fifo_list[data_dir], *pos); \ } \ \ static void *deadline_##name##_fifo_next(struct seq_file *m, void *v, \ loff_t *pos) \ { \ struct request_queue *q = m->private; \ struct deadline_data *dd = q->elevator->elevator_data; \ struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ \ return seq_list_next(v, &per_prio->fifo_list[data_dir], pos); \ } \ \ static void deadline_##name##_fifo_stop(struct seq_file *m, void *v) \ __releases(&dd->lock) \ { \ struct request_queue *q = m->private; \ struct deadline_data *dd = q->elevator->elevator_data; \ \ spin_unlock(&dd->lock); \ } \ \ static const struct seq_operations deadline_##name##_fifo_seq_ops = { \ .start = deadline_##name##_fifo_start, \ .next = deadline_##name##_fifo_next, \ .stop = deadline_##name##_fifo_stop, \ .show = blk_mq_debugfs_rq_show, \ }; \ \ static int deadline_##name##_next_rq_show(void *data, \ struct seq_file *m) \ { \ struct request_queue *q = data; \ struct deadline_data *dd = q->elevator->elevator_data; \ struct dd_per_prio *per_prio = &dd->per_prio[prio]; \ struct request *rq; \ \ rq = deadline_from_pos(per_prio, data_dir, \ per_prio->latest_pos[data_dir]); \ if (rq) \ __blk_mq_debugfs_rq_show(m, rq); \ return 0; \ } DEADLINE_DEBUGFS_DDIR_ATTRS(DD_RT_PRIO, DD_READ, read0); DEADLINE_DEBUGFS_DDIR_ATTRS(DD_RT_PRIO, DD_WRITE, write0); DEADLINE_DEBUGFS_DDIR_ATTRS(DD_BE_PRIO, DD_READ, read1); DEADLINE_DEBUGFS_DDIR_ATTRS(DD_BE_PRIO, DD_WRITE, write1); DEADLINE_DEBUGFS_DDIR_ATTRS(DD_IDLE_PRIO, DD_READ, read2); DEADLINE_DEBUGFS_DDIR_ATTRS(DD_IDLE_PRIO, DD_WRITE, write2); #undef DEADLINE_DEBUGFS_DDIR_ATTRS static int deadline_batching_show(void *data, struct seq_file *m) { struct request_queue *q = data; struct deadline_data *dd = q->elevator->elevator_data; seq_printf(m, "%u\n", dd->batching); return 0; } static int deadline_starved_show(void *data, struct seq_file *m) { struct request_queue *q = data; struct deadline_data *dd = q->elevator->elevator_data; seq_printf(m, "%u\n", dd->starved); return 0; } static int dd_queued_show(void *data, struct seq_file *m) { struct request_queue *q = data; struct deadline_data *dd = q->elevator->elevator_data; u32 rt, be, idle; spin_lock(&dd->lock); rt = dd_queued(dd, DD_RT_PRIO); be = dd_queued(dd, DD_BE_PRIO); idle = dd_queued(dd, DD_IDLE_PRIO); spin_unlock(&dd->lock); seq_printf(m, "%u %u %u\n", rt, be, idle); return 0; } /* Number of requests owned by the block driver for a given priority. */ static u32 dd_owned_by_driver(struct deadline_data *dd, enum dd_prio prio) { const struct io_stats_per_prio *stats = &dd->per_prio[prio].stats; lockdep_assert_held(&dd->lock); return stats->dispatched + stats->merged - atomic_read(&stats->completed); } static int dd_owned_by_driver_show(void *data, struct seq_file *m) { struct request_queue *q = data; struct deadline_data *dd = q->elevator->elevator_data; u32 rt, be, idle; spin_lock(&dd->lock); rt = dd_owned_by_driver(dd, DD_RT_PRIO); be = dd_owned_by_driver(dd, DD_BE_PRIO); idle = dd_owned_by_driver(dd, DD_IDLE_PRIO); spin_unlock(&dd->lock); seq_printf(m, "%u %u %u\n", rt, be, idle); return 0; } static void *deadline_dispatch_start(struct seq_file *m, loff_t *pos) __acquires(&dd->lock) { struct request_queue *q = m->private; struct deadline_data *dd = q->elevator->elevator_data; spin_lock(&dd->lock); return seq_list_start(&dd->dispatch, *pos); } static void *deadline_dispatch_next(struct seq_file *m, void *v, loff_t *pos) { struct request_queue *q = m->private; struct deadline_data *dd = q->elevator->elevator_data; return seq_list_next(v, &dd->dispatch, pos); } static void deadline_dispatch_stop(struct seq_file *m, void *v) __releases(&dd->lock) { struct request_queue *q = m->private; struct deadline_data *dd = q->elevator->elevator_data; spin_unlock(&dd->lock); } static const struct seq_operations deadline_dispatch_seq_ops = { .start = deadline_dispatch_start, .next = deadline_dispatch_next, .stop = deadline_dispatch_stop, .show = blk_mq_debugfs_rq_show, }; #define DEADLINE_QUEUE_DDIR_ATTRS(name) \ {#name "_fifo_list", 0400, \ .seq_ops = &deadline_##name##_fifo_seq_ops} #define DEADLINE_NEXT_RQ_ATTR(name) \ {#name "_next_rq", 0400, deadline_##name##_next_rq_show} static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = { DEADLINE_QUEUE_DDIR_ATTRS(read0), DEADLINE_QUEUE_DDIR_ATTRS(write0), DEADLINE_QUEUE_DDIR_ATTRS(read1), DEADLINE_QUEUE_DDIR_ATTRS(write1), DEADLINE_QUEUE_DDIR_ATTRS(read2), DEADLINE_QUEUE_DDIR_ATTRS(write2), DEADLINE_NEXT_RQ_ATTR(read0), DEADLINE_NEXT_RQ_ATTR(write0), DEADLINE_NEXT_RQ_ATTR(read1), DEADLINE_NEXT_RQ_ATTR(write1), DEADLINE_NEXT_RQ_ATTR(read2), DEADLINE_NEXT_RQ_ATTR(write2), {"batching", 0400, deadline_batching_show}, {"starved", 0400, deadline_starved_show}, {"dispatch", 0400, .seq_ops = &deadline_dispatch_seq_ops}, {"owned_by_driver", 0400, dd_owned_by_driver_show}, {"queued", 0400, dd_queued_show}, {}, }; #undef DEADLINE_QUEUE_DDIR_ATTRS #endif static struct elevator_type mq_deadline = { .ops = { .depth_updated = dd_depth_updated, .limit_depth = dd_limit_depth, .insert_requests = dd_insert_requests, .dispatch_request = dd_dispatch_request, .prepare_request = dd_prepare_request, .finish_request = dd_finish_request, .next_request = elv_rb_latter_request, .former_request = elv_rb_former_request, .bio_merge = dd_bio_merge, .request_merge = dd_request_merge, .requests_merged = dd_merged_requests, .request_merged = dd_request_merged, .has_work = dd_has_work, .init_sched = dd_init_sched, .exit_sched = dd_exit_sched, }, #ifdef CONFIG_BLK_DEBUG_FS .queue_debugfs_attrs = deadline_queue_debugfs_attrs, #endif .elevator_attrs = deadline_attrs, .elevator_name = "mq-deadline", .elevator_alias = "deadline", .elevator_owner = THIS_MODULE, }; MODULE_ALIAS("mq-deadline-iosched"); static int __init deadline_init(void) { return elv_register(&mq_deadline); } static void __exit deadline_exit(void) { elv_unregister(&mq_deadline); } module_init(deadline_init); module_exit(deadline_exit); MODULE_AUTHOR("Jens Axboe, Damien Le Moal and Bart Van Assche"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("MQ deadline IO scheduler"); |
| 5708 20589 18608 18614 1421 20482 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * AppArmor security module * * This file contains AppArmor label definitions * * Copyright 2017 Canonical Ltd. */ #ifndef __AA_LABEL_H #define __AA_LABEL_H #include <linux/atomic.h> #include <linux/audit.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> #include "apparmor.h" #include "lib.h" struct aa_ns; struct aa_ruleset; #define LOCAL_VEC_ENTRIES 8 #define DEFINE_VEC(T, V) \ struct aa_ ## T *(_ ## V ## _localtmp)[LOCAL_VEC_ENTRIES]; \ struct aa_ ## T **(V) #define vec_setup(T, V, N, GFP) \ ({ \ if ((N) <= LOCAL_VEC_ENTRIES) { \ typeof(N) i; \ (V) = (_ ## V ## _localtmp); \ for (i = 0; i < (N); i++) \ (V)[i] = NULL; \ } else \ (V) = kzalloc(sizeof(struct aa_ ## T *) * (N), (GFP)); \ (V) ? 0 : -ENOMEM; \ }) #define vec_cleanup(T, V, N) \ do { \ int i; \ for (i = 0; i < (N); i++) { \ if (!IS_ERR_OR_NULL((V)[i])) \ aa_put_ ## T((V)[i]); \ } \ if ((V) != _ ## V ## _localtmp) \ kfree(V); \ } while (0) #define vec_last(VEC, SIZE) ((VEC)[(SIZE) - 1]) #define vec_ns(VEC, SIZE) (vec_last((VEC), (SIZE))->ns) #define vec_labelset(VEC, SIZE) (&vec_ns((VEC), (SIZE))->labels) #define cleanup_domain_vec(V, L) cleanup_label_vec((V), (L)->size) struct aa_profile; #define VEC_FLAG_TERMINATE 1 int aa_vec_unique(struct aa_profile **vec, int n, int flags); struct aa_label *aa_vec_find_or_create_label(struct aa_profile **vec, int len, gfp_t gfp); #define aa_sort_and_merge_vec(N, V) \ aa_sort_and_merge_profiles((N), (struct aa_profile **)(V)) /* struct aa_labelset - set of labels for a namespace * * Labels are reference counted; aa_labelset does not contribute to label * reference counts. Once a label's last refcount is put it is removed from * the set. */ struct aa_labelset { rwlock_t lock; struct rb_root root; }; #define __labelset_for_each(LS, N) \ for ((N) = rb_first(&(LS)->root); (N); (N) = rb_next(N)) enum label_flags { FLAG_HAT = 1, /* profile is a hat */ FLAG_UNCONFINED = 2, /* label unconfined only if all */ FLAG_NULL = 4, /* profile is null learning profile */ FLAG_IX_ON_NAME_ERROR = 8, /* fallback to ix on name lookup fail */ FLAG_IMMUTIBLE = 0x10, /* don't allow changes/replacement */ FLAG_USER_DEFINED = 0x20, /* user based profile - lower privs */ FLAG_NO_LIST_REF = 0x40, /* list doesn't keep profile ref */ FLAG_NS_COUNT = 0x80, /* carries NS ref count */ FLAG_IN_TREE = 0x100, /* label is in tree */ FLAG_PROFILE = 0x200, /* label is a profile */ FLAG_EXPLICIT = 0x400, /* explicit static label */ FLAG_STALE = 0x800, /* replaced/removed */ FLAG_RENAMED = 0x1000, /* label has renaming in it */ FLAG_REVOKED = 0x2000, /* label has revocation in it */ FLAG_DEBUG1 = 0x4000, FLAG_DEBUG2 = 0x8000, /* These flags must correspond with PATH_flags */ /* TODO: add new path flags */ }; struct aa_label; struct aa_proxy { struct aa_common_ref count; struct aa_label __rcu *label; }; struct label_it { int i, j; }; /* struct aa_label_base - base info of label * @count: ref count of active users * @node: rbtree position * @rcu: rcu callback struct * @proxy: is set to the label that replaced this label * @hname: text representation of the label (MAYBE_NULL) * @flags: stale and other flags - values may change under label set lock * @secid: secid that references this label * @size: number of entries in @ent[] * @mediates: bitmask for label_mediates * profile: label vec when embedded in a profile FLAG_PROFILE is set * rules: variable length rules in a profile FLAG_PROFILE is set * vec: vector of profiles comprising the compound label */ struct aa_label { struct aa_common_ref count; struct rb_node node; struct rcu_head rcu; struct aa_proxy *proxy; __counted char *hname; long flags; u32 secid; int size; u64 mediates; union { struct { /* only used is the label is a profile, size of * rules[] is determined by the profile * profile[1] is poison or null as guard */ struct aa_profile *profile[2]; DECLARE_FLEX_ARRAY(struct aa_ruleset *, rules); }; DECLARE_FLEX_ARRAY(struct aa_profile *, vec); }; }; #define last_error(E, FN) \ do { \ int __subE = (FN); \ if (__subE) \ (E) = __subE; \ } while (0) #define label_isprofile(X) ((X)->flags & FLAG_PROFILE) #define label_unconfined(X) ((X)->flags & FLAG_UNCONFINED) #define unconfined(X) label_unconfined(X) #define label_is_stale(X) ((X)->flags & FLAG_STALE) #define __label_make_stale(X) ((X)->flags |= FLAG_STALE) #define labels_ns(X) (vec_ns(&((X)->vec[0]), (X)->size)) #define labels_set(X) (&labels_ns(X)->labels) #define labels_view(X) labels_ns(X) #define labels_profile(X) ((X)->vec[(X)->size - 1]) int aa_label_next_confined(struct aa_label *l, int i); /* for each profile in a label */ #define label_for_each(I, L, P) \ for ((I).i = 0; ((P) = (L)->vec[(I).i]); ++((I).i)) /* assumes break/goto ended label_for_each */ #define label_for_each_cont(I, L, P) \ for (++((I).i); ((P) = (L)->vec[(I).i]); ++((I).i)) /* for each profile that is enforcing confinement in a label */ #define label_for_each_confined(I, L, P) \ for ((I).i = aa_label_next_confined((L), 0); \ ((P) = (L)->vec[(I).i]); \ (I).i = aa_label_next_confined((L), (I).i + 1)) #define label_for_each_in_merge(I, A, B, P) \ for ((I).i = (I).j = 0; \ ((P) = aa_label_next_in_merge(&(I), (A), (B))); \ ) #define label_for_each_not_in_set(I, SET, SUB, P) \ for ((I).i = (I).j = 0; \ ((P) = __aa_label_next_not_in_set(&(I), (SET), (SUB))); \ ) #define next_in_ns(i, NS, L) \ ({ \ typeof(i) ___i = (i); \ while ((L)->vec[___i] && (L)->vec[___i]->ns != (NS)) \ (___i)++; \ (___i); \ }) #define label_for_each_in_ns(I, NS, L, P) \ for ((I).i = next_in_ns(0, (NS), (L)); \ ((P) = (L)->vec[(I).i]); \ (I).i = next_in_ns((I).i + 1, (NS), (L))) #define fn_for_each_in_ns(L, P, FN) \ ({ \ struct label_it __i; \ struct aa_ns *__ns = labels_ns(L); \ int __E = 0; \ label_for_each_in_ns(__i, __ns, (L), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each_XXX(L, P, FN, ...) \ ({ \ struct label_it i; \ int __E = 0; \ label_for_each ## __VA_ARGS__(i, (L), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each(L, P, FN) fn_for_each_XXX(L, P, FN) #define fn_for_each_confined(L, P, FN) fn_for_each_XXX(L, P, FN, _confined) #define fn_for_each2_XXX(L1, L2, P, FN, ...) \ ({ \ struct label_it i; \ int __E = 0; \ label_for_each ## __VA_ARGS__(i, (L1), (L2), (P)) { \ last_error(__E, (FN)); \ } \ __E; \ }) #define fn_for_each_in_merge(L1, L2, P, FN) \ fn_for_each2_XXX((L1), (L2), P, FN, _in_merge) #define fn_for_each_not_in_set(L1, L2, P, FN) \ fn_for_each2_XXX((L1), (L2), P, FN, _not_in_set) static inline bool label_mediates(struct aa_label *L, unsigned char C) { return (L)->mediates & (((u64) 1) << (C)); } static inline bool label_mediates_safe(struct aa_label *L, unsigned char C) { if (C > AA_CLASS_LAST) return false; return label_mediates(L, C); } void aa_labelset_destroy(struct aa_labelset *ls); void aa_labelset_init(struct aa_labelset *ls); void __aa_labelset_update_subtree(struct aa_ns *ns); void aa_label_destroy(struct aa_label *label); void aa_label_free(struct aa_label *label); void aa_label_kref(struct kref *kref); bool aa_label_init(struct aa_label *label, int size, gfp_t gfp); struct aa_label *aa_label_alloc(int size, struct aa_proxy *proxy, gfp_t gfp); bool aa_label_is_subset(struct aa_label *set, struct aa_label *sub); bool aa_label_is_unconfined_subset(struct aa_label *set, struct aa_label *sub); struct aa_profile *__aa_label_next_not_in_set(struct label_it *I, struct aa_label *set, struct aa_label *sub); bool aa_label_remove(struct aa_label *label); struct aa_label *aa_label_insert(struct aa_labelset *ls, struct aa_label *l); bool aa_label_replace(struct aa_label *old, struct aa_label *new); bool aa_label_make_newest(struct aa_labelset *ls, struct aa_label *old, struct aa_label *new); struct aa_profile *aa_label_next_in_merge(struct label_it *I, struct aa_label *a, struct aa_label *b); struct aa_label *aa_label_find_merge(struct aa_label *a, struct aa_label *b); struct aa_label *aa_label_merge(struct aa_label *a, struct aa_label *b, gfp_t gfp); bool aa_update_label_name(struct aa_ns *ns, struct aa_label *label, gfp_t gfp); #define FLAGS_NONE 0 #define FLAG_SHOW_MODE 1 #define FLAG_VIEW_SUBNS 2 #define FLAG_HIDDEN_UNCONFINED 4 #define FLAG_ABS_ROOT 8 int aa_label_snxprint(char *str, size_t size, struct aa_ns *view, struct aa_label *label, int flags); int aa_label_asxprint(char **strp, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); int aa_label_acntsxprint(char __counted **strp, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_xaudit(struct audit_buffer *ab, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_seq_xprint(struct seq_file *f, struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_xprintk(struct aa_ns *ns, struct aa_label *label, int flags, gfp_t gfp); void aa_label_printk(struct aa_label *label, gfp_t gfp); struct aa_label *aa_label_strn_parse(struct aa_label *base, const char *str, size_t n, gfp_t gfp, bool create, bool force_stack); struct aa_label *aa_label_parse(struct aa_label *base, const char *str, gfp_t gfp, bool create, bool force_stack); static inline const char *aa_label_strn_split(const char *str, int n) { const char *pos; aa_state_t state; state = aa_dfa_matchn_until(stacksplitdfa, DFA_START, str, n, &pos); if (!ACCEPT_TABLE(stacksplitdfa)[state]) return NULL; return pos - 3; } static inline const char *aa_label_str_split(const char *str) { const char *pos; aa_state_t state; state = aa_dfa_match_until(stacksplitdfa, DFA_START, str, &pos); if (!ACCEPT_TABLE(stacksplitdfa)[state]) return NULL; return pos - 3; } struct aa_perms; struct aa_ruleset; int aa_label_match(struct aa_profile *profile, struct aa_ruleset *rules, struct aa_label *label, aa_state_t state, bool subns, u32 request, struct aa_perms *perms); /** * __aa_get_label - get a reference count to uncounted label reference * @l: reference to get a count on * * Returns: pointer to reference OR NULL if race is lost and reference is * being repeated. * Requires: lock held, and the return code MUST be checked */ static inline struct aa_label *__aa_get_label(struct aa_label *l) { if (l && kref_get_unless_zero(&l->count.count)) return l; return NULL; } static inline struct aa_label *aa_get_label(struct aa_label *l) { if (l) kref_get(&(l->count.count)); return l; } /** * aa_get_label_rcu - increment refcount on a label that can be replaced * @l: pointer to label that can be replaced (NOT NULL) * * Returns: pointer to a refcounted label. * else NULL if no label */ static inline struct aa_label *aa_get_label_rcu(struct aa_label __rcu **l) { struct aa_label *c; rcu_read_lock(); do { c = rcu_dereference(*l); } while (c && !kref_get_unless_zero(&c->count.count)); rcu_read_unlock(); return c; } /** * aa_get_newest_label - find the newest version of @l * @l: the label to check for newer versions of * * Returns: refcounted newest version of @l taking into account * replacement, renames and removals * return @l. */ static inline struct aa_label *aa_get_newest_label(struct aa_label *l) { if (!l) return NULL; if (label_is_stale(l)) { struct aa_label *tmp; AA_BUG(!l->proxy); AA_BUG(!l->proxy->label); /* BUG: only way this can happen is @l ref count and its * replacement count have gone to 0 and are on their way * to destruction. ie. we have a refcounting error */ tmp = aa_get_label_rcu(&l->proxy->label); AA_BUG(!tmp); return tmp; } return aa_get_label(l); } static inline void aa_put_label(struct aa_label *l) { if (l) kref_put(&l->count.count, aa_label_kref); } /* wrapper fn to indicate semantics of the check */ static inline bool __aa_subj_label_is_cached(struct aa_label *subj_label, struct aa_label *obj_label) { return aa_label_is_subset(obj_label, subj_label); } struct aa_proxy *aa_alloc_proxy(struct aa_label *l, gfp_t gfp); void aa_proxy_kref(struct kref *kref); static inline struct aa_proxy *aa_get_proxy(struct aa_proxy *proxy) { if (proxy) kref_get(&(proxy->count.count)); return proxy; } static inline void aa_put_proxy(struct aa_proxy *proxy) { if (proxy) kref_put(&proxy->count.count, aa_proxy_kref); } void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new); #endif /* __AA_LABEL_H */ |
| 2 2 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 | // SPDX-License-Identifier: GPL-2.0-only /* * debugfs code for HSR & PRP * Copyright (C) 2019 Texas Instruments Incorporated * * Author(s): * Murali Karicheri <m-karicheri2@ti.com> */ #include <linux/module.h> #include <linux/errno.h> #include <linux/debugfs.h> #include "hsr_main.h" #include "hsr_framereg.h" static struct dentry *hsr_debugfs_root_dir; /* hsr_node_table_show - Formats and prints node_table entries */ static int hsr_node_table_show(struct seq_file *sfp, void *data) { struct hsr_priv *priv = (struct hsr_priv *)sfp->private; struct hsr_node *node; seq_printf(sfp, "Node Table entries for (%s) device\n", (priv->prot_version == PRP_V1 ? "PRP" : "HSR")); seq_puts(sfp, "MAC-Address-A, MAC-Address-B, time_in[A], "); seq_puts(sfp, "time_in[B], Address-B port, "); if (priv->prot_version == PRP_V1) seq_puts(sfp, "SAN-A, SAN-B, DAN-P\n"); else seq_puts(sfp, "DAN-H\n"); rcu_read_lock(); list_for_each_entry_rcu(node, &priv->node_db, mac_list) { /* skip self node */ if (hsr_addr_is_self(priv, node->macaddress_A)) continue; seq_printf(sfp, "%pM ", &node->macaddress_A[0]); seq_printf(sfp, "%pM ", &node->macaddress_B[0]); seq_printf(sfp, "%10lx, ", node->time_in[HSR_PT_SLAVE_A]); seq_printf(sfp, "%10lx, ", node->time_in[HSR_PT_SLAVE_B]); seq_printf(sfp, "%14x, ", node->addr_B_port); if (priv->prot_version == PRP_V1) seq_printf(sfp, "%5x, %5x, %5x\n", node->san_a, node->san_b, (node->san_a == 0 && node->san_b == 0)); else seq_printf(sfp, "%5x\n", 1); } rcu_read_unlock(); return 0; } DEFINE_SHOW_ATTRIBUTE(hsr_node_table); void hsr_debugfs_rename(struct net_device *dev) { struct hsr_priv *priv = netdev_priv(dev); int err; err = debugfs_change_name(priv->node_tbl_root, "%s", dev->name); if (err) netdev_warn(dev, "failed to rename\n"); } /* hsr_debugfs_init - create hsr node_table file for dumping * the node table * * Description: * When debugfs is configured this routine sets up the node_table file per * hsr device for dumping the node_table entries */ void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) { struct dentry *de = NULL; de = debugfs_create_dir(hsr_dev->name, hsr_debugfs_root_dir); if (IS_ERR(de)) { pr_err("Cannot create hsr debugfs directory\n"); return; } priv->node_tbl_root = de; de = debugfs_create_file("node_table", S_IFREG | 0444, priv->node_tbl_root, priv, &hsr_node_table_fops); if (IS_ERR(de)) { pr_err("Cannot create hsr node_table file\n"); debugfs_remove(priv->node_tbl_root); priv->node_tbl_root = NULL; return; } } /* hsr_debugfs_term - Tear down debugfs intrastructure * * Description: * When Debugfs is configured this routine removes debugfs file system * elements that are specific to hsr */ void hsr_debugfs_term(struct hsr_priv *priv) { debugfs_remove_recursive(priv->node_tbl_root); priv->node_tbl_root = NULL; } void hsr_debugfs_create_root(void) { hsr_debugfs_root_dir = debugfs_create_dir("hsr", NULL); if (IS_ERR(hsr_debugfs_root_dir)) { pr_err("Cannot create hsr debugfs root directory\n"); hsr_debugfs_root_dir = NULL; } } void hsr_debugfs_remove_root(void) { /* debugfs_remove() internally checks NULL and ERROR */ debugfs_remove(hsr_debugfs_root_dir); } |
| 99 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 | // SPDX-License-Identifier: GPL-2.0-only /* * Software WEP encryption implementation * Copyright 2002, Jouni Malinen <jkmaline@cc.hut.fi> * Copyright 2003, Instant802 Networks, Inc. * Copyright (C) 2023 Intel Corporation */ #include <linux/netdevice.h> #include <linux/types.h> #include <linux/random.h> #include <linux/compiler.h> #include <linux/crc32.h> #include <linux/crypto.h> #include <linux/err.h> #include <linux/mm.h> #include <linux/scatterlist.h> #include <linux/slab.h> #include <linux/unaligned.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "wep.h" void ieee80211_wep_init(struct ieee80211_local *local) { /* start WEP IV from a random value */ get_random_bytes(&local->wep_iv, IEEE80211_WEP_IV_LEN); } static inline bool ieee80211_wep_weak_iv(u32 iv, int keylen) { /* * Fluhrer, Mantin, and Shamir have reported weaknesses in the * key scheduling algorithm of RC4. At least IVs (KeyByte + 3, * 0xff, N) can be used to speedup attacks, so avoid using them. */ if ((iv & 0xff00) == 0xff00) { u8 B = (iv >> 16) & 0xff; if (B >= 3 && B < 3 + keylen) return true; } return false; } static void ieee80211_wep_get_iv(struct ieee80211_local *local, int keylen, int keyidx, u8 *iv) { local->wep_iv++; if (ieee80211_wep_weak_iv(local->wep_iv, keylen)) local->wep_iv += 0x0100; if (!iv) return; *iv++ = (local->wep_iv >> 16) & 0xff; *iv++ = (local->wep_iv >> 8) & 0xff; *iv++ = local->wep_iv & 0xff; *iv++ = keyidx << 6; } static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local, struct sk_buff *skb, int keylen, int keyidx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); unsigned int hdrlen; u8 *newhdr; hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); if (WARN_ON(skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) return NULL; hdrlen = ieee80211_hdrlen(hdr->frame_control); newhdr = skb_push(skb, IEEE80211_WEP_IV_LEN); memmove(newhdr, newhdr + IEEE80211_WEP_IV_LEN, hdrlen); /* the HW only needs room for the IV, but not the actual IV */ if (info->control.hw_key && (info->control.hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) return newhdr + hdrlen; ieee80211_wep_get_iv(local, keylen, keyidx, newhdr + hdrlen); return newhdr + hdrlen; } static void ieee80211_wep_remove_iv(struct ieee80211_local *local, struct sk_buff *skb, struct ieee80211_key *key) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; unsigned int hdrlen; hdrlen = ieee80211_hdrlen(hdr->frame_control); memmove(skb->data + IEEE80211_WEP_IV_LEN, skb->data, hdrlen); skb_pull(skb, IEEE80211_WEP_IV_LEN); } /* Perform WEP encryption using given key. data buffer must have tailroom * for 4-byte ICV. data_len must not include this ICV. Note: this function * does _not_ add IV. data = RC4(data | CRC32(data)) */ int ieee80211_wep_encrypt_data(struct arc4_ctx *ctx, u8 *rc4key, size_t klen, u8 *data, size_t data_len) { __le32 icv; icv = cpu_to_le32(~crc32_le(~0, data, data_len)); put_unaligned(icv, (__le32 *)(data + data_len)); arc4_setkey(ctx, rc4key, klen); arc4_crypt(ctx, data, data, data_len + IEEE80211_WEP_ICV_LEN); memzero_explicit(ctx, sizeof(*ctx)); return 0; } /* Perform WEP encryption on given skb. 4 bytes of extra space (IV) in the * beginning of the buffer 4 bytes of extra space (ICV) in the end of the * buffer will be added. Both IV and ICV will be transmitted, so the * payload length increases with 8 bytes. * * WEP frame payload: IV + TX key idx, RC4(data), ICV = RC4(CRC32(data)) */ int ieee80211_wep_encrypt(struct ieee80211_local *local, struct sk_buff *skb, const u8 *key, int keylen, int keyidx) { u8 *iv; size_t len; u8 rc4key[3 + WLAN_KEY_LEN_WEP104]; if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN)) return -1; iv = ieee80211_wep_add_iv(local, skb, keylen, keyidx); if (!iv) return -1; len = skb->len - (iv + IEEE80211_WEP_IV_LEN - skb->data); /* Prepend 24-bit IV to RC4 key */ memcpy(rc4key, iv, 3); /* Copy rest of the WEP key (the secret part) */ memcpy(rc4key + 3, key, keylen); /* Add room for ICV */ skb_put(skb, IEEE80211_WEP_ICV_LEN); return ieee80211_wep_encrypt_data(&local->wep_tx_ctx, rc4key, keylen + 3, iv + IEEE80211_WEP_IV_LEN, len); } /* Perform WEP decryption using given key. data buffer includes encrypted * payload, including 4-byte ICV, but _not_ IV. data_len must not include ICV. * Return 0 on success and -1 on ICV mismatch. */ int ieee80211_wep_decrypt_data(struct arc4_ctx *ctx, u8 *rc4key, size_t klen, u8 *data, size_t data_len) { __le32 crc; arc4_setkey(ctx, rc4key, klen); arc4_crypt(ctx, data, data, data_len + IEEE80211_WEP_ICV_LEN); memzero_explicit(ctx, sizeof(*ctx)); crc = cpu_to_le32(~crc32_le(~0, data, data_len)); if (memcmp(&crc, data + data_len, IEEE80211_WEP_ICV_LEN) != 0) /* ICV mismatch */ return -1; return 0; } /* Perform WEP decryption on given skb. Buffer includes whole WEP part of * the frame: IV (4 bytes), encrypted payload (including SNAP header), * ICV (4 bytes). skb->len includes both IV and ICV. * * Returns 0 if frame was decrypted successfully and ICV was correct and -1 on * failure. If frame is OK, IV and ICV will be removed, i.e., decrypted payload * is moved to the beginning of the skb and skb length will be reduced. */ static int ieee80211_wep_decrypt(struct ieee80211_local *local, struct sk_buff *skb, struct ieee80211_key *key) { u32 klen; u8 rc4key[3 + WLAN_KEY_LEN_WEP104]; u8 keyidx; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; unsigned int hdrlen; size_t len; int ret = 0; if (!ieee80211_has_protected(hdr->frame_control)) return -1; hdrlen = ieee80211_hdrlen(hdr->frame_control); if (skb->len < hdrlen + IEEE80211_WEP_IV_LEN + IEEE80211_WEP_ICV_LEN) return -1; len = skb->len - hdrlen - IEEE80211_WEP_IV_LEN - IEEE80211_WEP_ICV_LEN; keyidx = skb->data[hdrlen + 3] >> 6; if (!key || keyidx != key->conf.keyidx) return -1; klen = 3 + key->conf.keylen; /* Prepend 24-bit IV to RC4 key */ memcpy(rc4key, skb->data + hdrlen, 3); /* Copy rest of the WEP key (the secret part) */ memcpy(rc4key + 3, key->conf.key, key->conf.keylen); if (ieee80211_wep_decrypt_data(&local->wep_rx_ctx, rc4key, klen, skb->data + hdrlen + IEEE80211_WEP_IV_LEN, len)) ret = -1; /* Trim ICV */ skb_trim(skb, skb->len - IEEE80211_WEP_ICV_LEN); /* Remove IV */ memmove(skb->data + IEEE80211_WEP_IV_LEN, skb->data, hdrlen); skb_pull(skb, IEEE80211_WEP_IV_LEN); return ret; } ieee80211_rx_result ieee80211_crypto_wep_decrypt(struct ieee80211_rx_data *rx) { struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; __le16 fc = hdr->frame_control; if (!ieee80211_is_data(fc) && !ieee80211_is_auth(fc)) return RX_CONTINUE; if (!(status->flag & RX_FLAG_DECRYPTED)) { if (skb_linearize(rx->skb)) return RX_DROP_U_OOM; if (ieee80211_wep_decrypt(rx->local, rx->skb, rx->key)) return RX_DROP_U_WEP_DEC_FAIL; } else if (!(status->flag & RX_FLAG_IV_STRIPPED)) { if (!pskb_may_pull(rx->skb, ieee80211_hdrlen(fc) + IEEE80211_WEP_IV_LEN)) return RX_DROP_U_NO_IV; ieee80211_wep_remove_iv(rx->local, rx->skb, rx->key); /* remove ICV */ if (!(status->flag & RX_FLAG_ICV_STRIPPED) && pskb_trim(rx->skb, rx->skb->len - IEEE80211_WEP_ICV_LEN)) return RX_DROP_U_NO_ICV; } return RX_CONTINUE; } static int wep_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_key_conf *hw_key = info->control.hw_key; if (!hw_key) { if (ieee80211_wep_encrypt(tx->local, skb, tx->key->conf.key, tx->key->conf.keylen, tx->key->conf.keyidx)) return -1; } else if ((hw_key->flags & IEEE80211_KEY_FLAG_GENERATE_IV) || (hw_key->flags & IEEE80211_KEY_FLAG_PUT_IV_SPACE)) { if (!ieee80211_wep_add_iv(tx->local, skb, tx->key->conf.keylen, tx->key->conf.keyidx)) return -1; } return 0; } ieee80211_tx_result ieee80211_crypto_wep_encrypt(struct ieee80211_tx_data *tx) { struct sk_buff *skb; ieee80211_tx_set_protected(tx); skb_queue_walk(&tx->skbs, skb) { if (wep_encrypt_skb(tx, skb) < 0) { I802_DEBUG_INC(tx->local->tx_handlers_drop_wep); return TX_DROP; } } return TX_CONTINUE; } |
| 5 17 1 1 1 2 1 1 4 1 5 1 61 47 13 2 58 301 304 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 | /* SPDX-License-Identifier: GPL-2.0-or-later */ #ifndef TUN_VNET_H #define TUN_VNET_H /* High bits in flags field are unused. */ #define TUN_VNET_LE 0x80000000 #define TUN_VNET_BE 0x40000000 #define TUN_VNET_TNL_SIZE sizeof(struct virtio_net_hdr_v1_hash_tunnel) static inline bool tun_vnet_legacy_is_little_endian(unsigned int flags) { bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) && (flags & TUN_VNET_BE); return !be && virtio_legacy_is_little_endian(); } static inline long tun_get_vnet_be(unsigned int flags, int __user *argp) { int be = !!(flags & TUN_VNET_BE); if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE)) return -EINVAL; if (put_user(be, argp)) return -EFAULT; return 0; } static inline long tun_set_vnet_be(unsigned int *flags, int __user *argp) { int be; if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE)) return -EINVAL; if (get_user(be, argp)) return -EFAULT; if (be) *flags |= TUN_VNET_BE; else *flags &= ~TUN_VNET_BE; return 0; } static inline bool tun_vnet_is_little_endian(unsigned int flags) { return flags & TUN_VNET_LE || tun_vnet_legacy_is_little_endian(flags); } static inline u16 tun_vnet16_to_cpu(unsigned int flags, __virtio16 val) { return __virtio16_to_cpu(tun_vnet_is_little_endian(flags), val); } static inline __virtio16 cpu_to_tun_vnet16(unsigned int flags, u16 val) { return __cpu_to_virtio16(tun_vnet_is_little_endian(flags), val); } static inline long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags, unsigned int cmd, int __user *sp) { int s; switch (cmd) { case TUNGETVNETHDRSZ: s = *vnet_hdr_sz; if (put_user(s, sp)) return -EFAULT; return 0; case TUNSETVNETHDRSZ: if (get_user(s, sp)) return -EFAULT; if (s < (int)sizeof(struct virtio_net_hdr)) return -EINVAL; *vnet_hdr_sz = s; return 0; case TUNGETVNETLE: s = !!(*flags & TUN_VNET_LE); if (put_user(s, sp)) return -EFAULT; return 0; case TUNSETVNETLE: if (get_user(s, sp)) return -EFAULT; if (s) *flags |= TUN_VNET_LE; else *flags &= ~TUN_VNET_LE; return 0; case TUNGETVNETBE: return tun_get_vnet_be(*flags, sp); case TUNSETVNETBE: return tun_set_vnet_be(flags, sp); default: return -EINVAL; } } static inline unsigned int tun_vnet_parse_size(netdev_features_t features) { if (!(features & NETIF_F_GSO_UDP_TUNNEL)) return sizeof(struct virtio_net_hdr); return TUN_VNET_TNL_SIZE; } static inline int __tun_vnet_hdr_get(int sz, unsigned int flags, netdev_features_t features, struct iov_iter *from, struct virtio_net_hdr *hdr) { unsigned int parsed_size = tun_vnet_parse_size(features); u16 hdr_len; if (iov_iter_count(from) < sz) return -EINVAL; if (!copy_from_iter_full(hdr, parsed_size, from)) return -EFAULT; hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len); if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { hdr_len = max(tun_vnet16_to_cpu(flags, hdr->csum_start) + tun_vnet16_to_cpu(flags, hdr->csum_offset) + 2, hdr_len); hdr->hdr_len = cpu_to_tun_vnet16(flags, hdr_len); } if (hdr_len > iov_iter_count(from)) return -EINVAL; iov_iter_advance(from, sz - parsed_size); return hdr_len; } static inline int tun_vnet_hdr_get(int sz, unsigned int flags, struct iov_iter *from, struct virtio_net_hdr *hdr) { return __tun_vnet_hdr_get(sz, flags, 0, from, hdr); } static inline int __tun_vnet_hdr_put(int sz, netdev_features_t features, struct iov_iter *iter, const struct virtio_net_hdr *hdr) { unsigned int parsed_size = tun_vnet_parse_size(features); if (unlikely(iov_iter_count(iter) < sz)) return -EINVAL; if (unlikely(copy_to_iter(hdr, parsed_size, iter) != parsed_size)) return -EFAULT; if (iov_iter_zero(sz - parsed_size, iter) != sz - parsed_size) return -EFAULT; return 0; } static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter, const struct virtio_net_hdr *hdr) { return __tun_vnet_hdr_put(sz, 0, iter, hdr); } static inline int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb, const struct virtio_net_hdr *hdr) { return virtio_net_hdr_to_skb(skb, hdr, tun_vnet_is_little_endian(flags)); } /* * Tun is not aware of the negotiated guest features, guess them from the * virtio net hdr size */ static inline netdev_features_t tun_vnet_hdr_guest_features(int vnet_hdr_sz) { if (vnet_hdr_sz >= TUN_VNET_TNL_SIZE) return NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM; return 0; } static inline int tun_vnet_hdr_tnl_to_skb(unsigned int flags, netdev_features_t features, struct sk_buff *skb, const struct virtio_net_hdr_v1_hash_tunnel *hdr) { return virtio_net_hdr_tnl_to_skb(skb, hdr, features & NETIF_F_GSO_UDP_TUNNEL, features & NETIF_F_GSO_UDP_TUNNEL_CSUM, tun_vnet_is_little_endian(flags)); } static inline int tun_vnet_hdr_from_skb(unsigned int flags, const struct net_device *dev, const struct sk_buff *skb, struct virtio_net_hdr *hdr) { int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0; if (virtio_net_hdr_from_skb(skb, hdr, tun_vnet_is_little_endian(flags), true, vlan_hlen)) { struct skb_shared_info *sinfo = skb_shinfo(skb); if (net_ratelimit()) { netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size), tun_vnet16_to_cpu(flags, hdr->hdr_len)); print_hex_dump(KERN_ERR, "tun: ", DUMP_PREFIX_NONE, 16, 1, skb->head, min(tun_vnet16_to_cpu(flags, hdr->hdr_len), 64), true); } WARN_ON_ONCE(1); return -EINVAL; } return 0; } static inline int tun_vnet_hdr_tnl_from_skb(unsigned int flags, const struct net_device *dev, const struct sk_buff *skb, struct virtio_net_hdr_v1_hash_tunnel *tnl_hdr) { bool has_tnl_offload = !!(dev->features & NETIF_F_GSO_UDP_TUNNEL); int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0; if (virtio_net_hdr_tnl_from_skb(skb, tnl_hdr, has_tnl_offload, tun_vnet_is_little_endian(flags), vlan_hlen, true, false)) { struct virtio_net_hdr_v1 *hdr = &tnl_hdr->hash_hdr.hdr; struct skb_shared_info *sinfo = skb_shinfo(skb); if (net_ratelimit()) { int hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len); netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n", sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size), tun_vnet16_to_cpu(flags, hdr->hdr_len)); print_hex_dump(KERN_ERR, "tun: ", DUMP_PREFIX_NONE, 16, 1, skb->head, min(hdr_len, 64), true); } WARN_ON_ONCE(1); return -EINVAL; } return 0; } #endif /* TUN_VNET_H */ |
| 33 55 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 | /* 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. * * This file is part of the SCTP kernel implementation * * These are definitions needed by the state machine. * * Please send any bug reports or fixes you make to the * email addresses: * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Xingang Guo <xingang.guo@intel.com> * Jon Grimm <jgrimm@us.ibm.com> * Dajiang Zhang <dajiang.zhang@nokia.com> * Sridhar Samudrala <sri@us.ibm.com> * Daisy Chang <daisyc@us.ibm.com> * Ardelle Fan <ardelle.fan@intel.com> * Kevin Gao <kevin.gao@intel.com> */ #include <linux/types.h> #include <linux/compiler.h> #include <linux/slab.h> #include <linux/in.h> #include <net/sctp/command.h> #include <net/sctp/sctp.h> #ifndef __sctp_sm_h__ #define __sctp_sm_h__ /* * Possible values for the disposition are: */ enum sctp_disposition { SCTP_DISPOSITION_DISCARD, /* No further processing. */ SCTP_DISPOSITION_CONSUME, /* Process return values normally. */ SCTP_DISPOSITION_NOMEM, /* We ran out of memory--recover. */ SCTP_DISPOSITION_DELETE_TCB, /* Close the association. */ SCTP_DISPOSITION_ABORT, /* Close the association NOW. */ SCTP_DISPOSITION_VIOLATION, /* The peer is misbehaving. */ SCTP_DISPOSITION_NOT_IMPL, /* This entry is not implemented. */ SCTP_DISPOSITION_ERROR, /* This is plain old user error. */ SCTP_DISPOSITION_BUG, /* This is a bug. */ }; typedef enum sctp_disposition (sctp_state_fn_t) ( struct net *net, const struct sctp_endpoint *ep, const struct sctp_association *asoc, const union sctp_subtype type, void *arg, struct sctp_cmd_seq *commands); typedef void (sctp_timer_event_t) (struct timer_list *); struct sctp_sm_table_entry { sctp_state_fn_t *fn; const char *name; }; /* A naming convention of "sctp_sf_xxx" applies to all the state functions * currently in use. */ /* Prototypes for generic state functions. */ sctp_state_fn_t sctp_sf_not_impl; sctp_state_fn_t sctp_sf_bug; /* Prototypes for gener timer state functions. */ sctp_state_fn_t sctp_sf_timer_ignore; /* Prototypes for chunk state functions. */ sctp_state_fn_t sctp_sf_do_9_1_abort; sctp_state_fn_t sctp_sf_cookie_wait_abort; sctp_state_fn_t sctp_sf_cookie_echoed_abort; sctp_state_fn_t sctp_sf_shutdown_pending_abort; sctp_state_fn_t sctp_sf_shutdown_sent_abort; sctp_state_fn_t sctp_sf_shutdown_ack_sent_abort; sctp_state_fn_t sctp_sf_do_5_1B_init; sctp_state_fn_t sctp_sf_do_5_1C_ack; sctp_state_fn_t sctp_sf_do_5_1D_ce; sctp_state_fn_t sctp_sf_do_5_1E_ca; sctp_state_fn_t sctp_sf_do_4_C; sctp_state_fn_t sctp_sf_eat_data_6_2; sctp_state_fn_t sctp_sf_eat_data_fast_4_4; sctp_state_fn_t sctp_sf_eat_sack_6_2; sctp_state_fn_t sctp_sf_operr_notify; sctp_state_fn_t sctp_sf_t1_init_timer_expire; sctp_state_fn_t sctp_sf_t1_cookie_timer_expire; sctp_state_fn_t sctp_sf_t2_timer_expire; sctp_state_fn_t sctp_sf_t4_timer_expire; sctp_state_fn_t sctp_sf_t5_timer_expire; sctp_state_fn_t sctp_sf_sendbeat_8_3; sctp_state_fn_t sctp_sf_beat_8_3; sctp_state_fn_t sctp_sf_backbeat_8_3; sctp_state_fn_t sctp_sf_do_9_2_final; sctp_state_fn_t sctp_sf_do_9_2_shutdown; sctp_state_fn_t sctp_sf_do_9_2_shut_ctsn; sctp_state_fn_t sctp_sf_do_ecn_cwr; sctp_state_fn_t sctp_sf_do_ecne; sctp_state_fn_t sctp_sf_ootb; sctp_state_fn_t sctp_sf_pdiscard; sctp_state_fn_t sctp_sf_violation; sctp_state_fn_t sctp_sf_discard_chunk; sctp_state_fn_t sctp_sf_do_5_2_1_siminit; sctp_state_fn_t sctp_sf_do_5_2_2_dupinit; sctp_state_fn_t sctp_sf_do_5_2_3_initack; sctp_state_fn_t sctp_sf_do_5_2_4_dupcook; sctp_state_fn_t sctp_sf_unk_chunk; sctp_state_fn_t sctp_sf_do_8_5_1_E_sa; sctp_state_fn_t sctp_sf_cookie_echoed_err; sctp_state_fn_t sctp_sf_do_asconf; sctp_state_fn_t sctp_sf_do_asconf_ack; sctp_state_fn_t sctp_sf_do_reconf; sctp_state_fn_t sctp_sf_do_9_2_reshutack; sctp_state_fn_t sctp_sf_eat_fwd_tsn; sctp_state_fn_t sctp_sf_eat_fwd_tsn_fast; sctp_state_fn_t sctp_sf_eat_auth; /* Prototypes for primitive event state functions. */ sctp_state_fn_t sctp_sf_do_prm_asoc; sctp_state_fn_t sctp_sf_do_prm_send; sctp_state_fn_t sctp_sf_do_9_2_prm_shutdown; sctp_state_fn_t sctp_sf_cookie_wait_prm_shutdown; sctp_state_fn_t sctp_sf_cookie_echoed_prm_shutdown; sctp_state_fn_t sctp_sf_do_9_1_prm_abort; sctp_state_fn_t sctp_sf_cookie_wait_prm_abort; sctp_state_fn_t sctp_sf_cookie_echoed_prm_abort; sctp_state_fn_t sctp_sf_shutdown_pending_prm_abort; sctp_state_fn_t sctp_sf_shutdown_sent_prm_abort; sctp_state_fn_t sctp_sf_shutdown_ack_sent_prm_abort; sctp_state_fn_t sctp_sf_error_closed; sctp_state_fn_t sctp_sf_error_shutdown; sctp_state_fn_t sctp_sf_ignore_primitive; sctp_state_fn_t sctp_sf_do_prm_requestheartbeat; sctp_state_fn_t sctp_sf_do_prm_asconf; sctp_state_fn_t sctp_sf_do_prm_reconf; /* Prototypes for other event state functions. */ sctp_state_fn_t sctp_sf_do_no_pending_tsn; sctp_state_fn_t sctp_sf_do_9_2_start_shutdown; sctp_state_fn_t sctp_sf_do_9_2_shutdown_ack; sctp_state_fn_t sctp_sf_ignore_other; sctp_state_fn_t sctp_sf_cookie_wait_icmp_abort; /* Prototypes for timeout event state functions. */ sctp_state_fn_t sctp_sf_do_6_3_3_rtx; sctp_state_fn_t sctp_sf_send_reconf; sctp_state_fn_t sctp_sf_send_probe; sctp_state_fn_t sctp_sf_do_6_2_sack; sctp_state_fn_t sctp_sf_autoclose_timer_expire; /* Prototypes for utility support functions. */ const struct sctp_sm_table_entry *sctp_sm_lookup_event( struct net *net, enum sctp_event_type event_type, enum sctp_state state, union sctp_subtype event_subtype); struct sctp_association *sctp_make_temp_asoc(const struct sctp_endpoint *, struct sctp_chunk *, gfp_t gfp); /* Prototypes for chunk-building functions. */ struct sctp_chunk *sctp_make_init(const struct sctp_association *asoc, const struct sctp_bind_addr *bp, gfp_t gfp, int vparam_len); struct sctp_chunk *sctp_make_init_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const gfp_t gfp, const int unkparam_len); struct sctp_chunk *sctp_make_cookie_echo(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_cookie_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_cwr(const struct sctp_association *asoc, const __u32 lowest_tsn, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_idata(const struct sctp_association *asoc, __u8 flags, int paylen, gfp_t gfp); struct sctp_chunk *sctp_make_ifwdtsn(const struct sctp_association *asoc, __u32 new_cum_tsn, size_t nstreams, struct sctp_ifwdtsn_skip *skiplist); struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc, const struct sctp_sndrcvinfo *sinfo, int len, __u8 flags, gfp_t gfp); struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc, const __u32 lowest_tsn); struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc); struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_shutdown_complete( const struct sctp_association *asoc, const struct sctp_chunk *chunk); int sctp_init_cause(struct sctp_chunk *chunk, __be16 cause, size_t paylen); struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const size_t hint); struct sctp_chunk *sctp_make_abort_no_data(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __u32 tsn); struct sctp_chunk *sctp_make_abort_user(const struct sctp_association *asoc, struct msghdr *msg, size_t msg_len); struct sctp_chunk *sctp_make_abort_violation( const struct sctp_association *asoc, const struct sctp_chunk *chunk, const __u8 *payload, const size_t paylen); struct sctp_chunk *sctp_make_violation_paramlen( const struct sctp_association *asoc, const struct sctp_chunk *chunk, struct sctp_paramhdr *param); struct sctp_chunk *sctp_make_violation_max_retrans( const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_new_encap_port( const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc, const struct sctp_transport *transport, __u32 probe_size); struct sctp_chunk *sctp_make_heartbeat_ack(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const void *payload, const size_t paylen); struct sctp_chunk *sctp_make_pad(const struct sctp_association *asoc, int len); struct sctp_chunk *sctp_make_op_error(const struct sctp_association *asoc, const struct sctp_chunk *chunk, __be16 cause_code, const void *payload, size_t paylen, size_t reserve_tail); struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, union sctp_addr *laddr, struct sockaddr *addrs, int addrcnt, __be16 flags); struct sctp_chunk *sctp_make_asconf_set_prim(struct sctp_association *asoc, union sctp_addr *addr); bool sctp_verify_asconf(const struct sctp_association *asoc, struct sctp_chunk *chunk, bool addr_param_needed, struct sctp_paramhdr **errp); struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, struct sctp_chunk *asconf); int sctp_process_asconf_ack(struct sctp_association *asoc, struct sctp_chunk *asconf_ack); struct sctp_chunk *sctp_make_fwdtsn(const struct sctp_association *asoc, __u32 new_cum_tsn, size_t nstreams, struct sctp_fwdtsn_skip *skiplist); struct sctp_chunk *sctp_make_auth(const struct sctp_association *asoc, __u16 key_id); struct sctp_chunk *sctp_make_strreset_req(const struct sctp_association *asoc, __u16 stream_num, __be16 *stream_list, bool out, bool in); struct sctp_chunk *sctp_make_strreset_tsnreq( const struct sctp_association *asoc); struct sctp_chunk *sctp_make_strreset_addstrm( const struct sctp_association *asoc, __u16 out, __u16 in); struct sctp_chunk *sctp_make_strreset_resp(const struct sctp_association *asoc, __u32 result, __u32 sn); struct sctp_chunk *sctp_make_strreset_tsnresp(struct sctp_association *asoc, __u32 result, __u32 sn, __u32 sender_tsn, __u32 receiver_tsn); bool sctp_verify_reconf(const struct sctp_association *asoc, struct sctp_chunk *chunk, struct sctp_paramhdr **errp); void sctp_chunk_assign_tsn(struct sctp_chunk *chunk); void sctp_chunk_assign_ssn(struct sctp_chunk *chunk); /* Prototypes for stream-processing functions. */ struct sctp_chunk *sctp_process_strreset_outreq( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); struct sctp_chunk *sctp_process_strreset_inreq( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); struct sctp_chunk *sctp_process_strreset_tsnreq( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); struct sctp_chunk *sctp_process_strreset_addstrm_out( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); struct sctp_chunk *sctp_process_strreset_addstrm_in( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); struct sctp_chunk *sctp_process_strreset_resp( struct sctp_association *asoc, union sctp_params param, struct sctp_ulpevent **evp); /* Prototypes for statetable processing. */ int sctp_do_sm(struct net *net, enum sctp_event_type event_type, union sctp_subtype subtype, enum sctp_state state, struct sctp_endpoint *ep, struct sctp_association *asoc, void *event_arg, gfp_t gfp); /* 2nd level prototypes */ void sctp_generate_t3_rtx_event(struct timer_list *t); void sctp_generate_heartbeat_event(struct timer_list *t); void sctp_generate_reconf_event(struct timer_list *t); void sctp_generate_probe_event(struct timer_list *t); void sctp_generate_proto_unreach_event(struct timer_list *t); void sctp_ootb_pkt_free(struct sctp_packet *packet); struct sctp_association *sctp_unpack_cookie( const struct sctp_endpoint *ep, const struct sctp_association *asoc, struct sctp_chunk *chunk, gfp_t gfp, int *err, struct sctp_chunk **err_chk_p); /* 3rd level prototypes */ __u32 sctp_generate_tag(const struct sctp_endpoint *ep); __u32 sctp_generate_tsn(const struct sctp_endpoint *ep); /* Extern declarations for major data structures. */ extern sctp_timer_event_t *sctp_timer_events[SCTP_NUM_TIMEOUT_TYPES]; /* Get the size of a DATA chunk payload. */ static inline __u16 sctp_data_size(struct sctp_chunk *chunk) { __u16 size; size = ntohs(chunk->chunk_hdr->length); size -= sctp_datachk_len(&chunk->asoc->stream); return size; } /* Compare two TSNs */ #define TSN_lt(a,b) \ (typecheck(__u32, a) && \ typecheck(__u32, b) && \ ((__s32)((a) - (b)) < 0)) #define TSN_lte(a,b) \ (typecheck(__u32, a) && \ typecheck(__u32, b) && \ ((__s32)((a) - (b)) <= 0)) /* Compare two MIDs */ #define MID_lt(a, b) \ (typecheck(__u32, a) && \ typecheck(__u32, b) && \ ((__s32)((a) - (b)) < 0)) /* Compare two SSNs */ #define SSN_lt(a,b) \ (typecheck(__u16, a) && \ typecheck(__u16, b) && \ ((__s16)((a) - (b)) < 0)) /* ADDIP 3.1.1 */ #define ADDIP_SERIAL_gte(a,b) \ (typecheck(__u32, a) && \ typecheck(__u32, b) && \ ((__s32)((b) - (a)) <= 0)) /* Check VTAG of the packet matches the sender's own tag. */ static inline int sctp_vtag_verify(const struct sctp_chunk *chunk, const struct sctp_association *asoc) { /* RFC 2960 Sec 8.5 When receiving an SCTP packet, the endpoint * MUST ensure that the value in the Verification Tag field of * the received SCTP packet matches its own Tag. If the received * Verification Tag value does not match the receiver's own * tag value, the receiver shall silently discard the packet... */ if (ntohl(chunk->sctp_hdr->vtag) != asoc->c.my_vtag) return 0; chunk->transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port; return 1; } /* Check VTAG of the packet matches the sender's own tag and the T bit is * not set, OR its peer's tag and the T bit is set in the Chunk Flags. */ static inline int sctp_vtag_verify_either(const struct sctp_chunk *chunk, const struct sctp_association *asoc) { /* RFC 2960 Section 8.5.1, sctpimpguide Section 2.41 * * B) The receiver of a ABORT MUST accept the packet * if the Verification Tag field of the packet matches its own tag * and the T bit is not set * OR * it is set to its peer's tag and the T bit is set in the Chunk * Flags. * Otherwise, the receiver MUST silently discard the packet * and take no further action. * * C) The receiver of a SHUTDOWN COMPLETE shall accept the packet * if the Verification Tag field of the packet matches its own tag * and the T bit is not set * OR * it is set to its peer's tag and the T bit is set in the Chunk * Flags. * Otherwise, the receiver MUST silently discard the packet * and take no further action. An endpoint MUST ignore the * SHUTDOWN COMPLETE if it is not in the SHUTDOWN-ACK-SENT state. */ if ((!sctp_test_T_bit(chunk) && (ntohl(chunk->sctp_hdr->vtag) == asoc->c.my_vtag)) || (sctp_test_T_bit(chunk) && asoc->c.peer_vtag && (ntohl(chunk->sctp_hdr->vtag) == asoc->c.peer_vtag))) { return 1; } return 0; } #endif /* __sctp_sm_h__ */ |
| 163 162 163 1 1 1 1 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/file.h> #include <linux/net.h> #include <linux/rcupdate.h> #include <linux/tcp.h> #include <net/ip.h> #include <net/psp.h> #include "psp.h" struct psp_dev *psp_dev_get_for_sock(struct sock *sk) { struct psp_dev *psd = NULL; struct dst_entry *dst; rcu_read_lock(); dst = __sk_dst_get(sk); if (dst) { psd = rcu_dereference(dst_dev_rcu(dst)->psp_dev); if (psd && !psp_dev_tryget(psd)) psd = NULL; } rcu_read_unlock(); return psd; } static struct sk_buff * psp_validate_xmit(struct sock *sk, struct net_device *dev, struct sk_buff *skb) { struct psp_assoc *pas; bool good; rcu_read_lock(); pas = psp_skb_get_assoc_rcu(skb); good = !pas || rcu_access_pointer(dev->psp_dev) == pas->psd; rcu_read_unlock(); if (!good) { sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_PSP_OUTPUT); return NULL; } return skb; } struct psp_assoc *psp_assoc_create(struct psp_dev *psd) { struct psp_assoc *pas; lockdep_assert_held(&psd->lock); pas = kzalloc_flex(*pas, drv_data, psd->caps->assoc_drv_spc, GFP_KERNEL_ACCOUNT); if (!pas) return NULL; pas->psd = psd; pas->dev_id = psd->id; pas->generation = psd->generation; psp_dev_get(psd); refcount_set(&pas->refcnt, 1); list_add_tail(&pas->assocs_list, &psd->active_assocs); return pas; } static struct psp_assoc *psp_assoc_dummy(struct psp_assoc *pas) { struct psp_dev *psd = pas->psd; size_t sz; lockdep_assert_held(&psd->lock); sz = struct_size(pas, drv_data, psd->caps->assoc_drv_spc); return kmemdup(pas, sz, GFP_KERNEL); } static int psp_dev_tx_key_add(struct psp_dev *psd, struct psp_assoc *pas, struct netlink_ext_ack *extack) { return psd->ops->tx_key_add(psd, pas, extack); } void psp_dev_tx_key_del(struct psp_dev *psd, struct psp_assoc *pas) { if (pas->tx.spi) psd->ops->tx_key_del(psd, pas); list_del(&pas->assocs_list); } static void psp_assoc_free(struct work_struct *work) { struct psp_assoc *pas = container_of(work, struct psp_assoc, work); struct psp_dev *psd = pas->psd; mutex_lock(&psd->lock); if (psd->ops) psp_dev_tx_key_del(psd, pas); mutex_unlock(&psd->lock); psp_dev_put(psd); kfree(pas); } static void psp_assoc_free_queue(struct rcu_head *head) { struct psp_assoc *pas = container_of(head, struct psp_assoc, rcu); INIT_WORK(&pas->work, psp_assoc_free); schedule_work(&pas->work); } /** * psp_assoc_put() - release a reference on a PSP association * @pas: association to release */ void psp_assoc_put(struct psp_assoc *pas) { if (pas && refcount_dec_and_test(&pas->refcnt)) call_rcu(&pas->rcu, psp_assoc_free_queue); } void psp_sk_assoc_free(struct sock *sk) { struct psp_assoc *pas = rcu_dereference_protected(sk->psp_assoc, 1); rcu_assign_pointer(sk->psp_assoc, NULL); psp_assoc_put(pas); } int psp_sock_assoc_set_rx(struct sock *sk, struct psp_assoc *pas, struct psp_key_parsed *key, struct netlink_ext_ack *extack) { int err; memcpy(&pas->rx, key, sizeof(*key)); lock_sock(sk); if (psp_sk_assoc(sk)) { NL_SET_ERR_MSG(extack, "Socket already has PSP state"); err = -EBUSY; goto exit_unlock; } refcount_inc(&pas->refcnt); rcu_assign_pointer(sk->psp_assoc, pas); err = 0; exit_unlock: release_sock(sk); return err; } static int psp_sock_recv_queue_check(struct sock *sk, struct psp_assoc *pas) { struct psp_skb_ext *pse; struct sk_buff *skb; skb_rbtree_walk(skb, &tcp_sk(sk)->out_of_order_queue) { pse = skb_ext_find(skb, SKB_EXT_PSP); if (!psp_pse_matches_pas(pse, pas)) return -EBUSY; } skb_queue_walk(&sk->sk_receive_queue, skb) { pse = skb_ext_find(skb, SKB_EXT_PSP); if (!psp_pse_matches_pas(pse, pas)) return -EBUSY; } return 0; } int psp_sock_assoc_set_tx(struct sock *sk, struct psp_dev *psd, u32 version, struct psp_key_parsed *key, struct netlink_ext_ack *extack) { struct inet_connection_sock *icsk; struct psp_assoc *pas, *dummy; int err; lock_sock(sk); pas = psp_sk_assoc(sk); if (!pas) { NL_SET_ERR_MSG(extack, "Socket has no Rx key"); err = -EINVAL; goto exit_unlock; } if (pas->psd != psd) { NL_SET_ERR_MSG(extack, "Rx key from different device"); err = -EINVAL; goto exit_unlock; } if (pas->version != version) { NL_SET_ERR_MSG(extack, "PSP version mismatch with existing state"); err = -EINVAL; goto exit_unlock; } if (pas->tx.spi) { NL_SET_ERR_MSG(extack, "Tx key already set"); err = -EBUSY; goto exit_unlock; } err = psp_sock_recv_queue_check(sk, pas); if (err) { NL_SET_ERR_MSG(extack, "Socket has incompatible segments already in the recv queue"); goto exit_unlock; } /* Pass a fake association to drivers to make sure they don't * try to store pointers to it. For re-keying we'll need to * re-allocate the assoc structures. */ dummy = psp_assoc_dummy(pas); if (!dummy) { err = -ENOMEM; goto exit_unlock; } memcpy(&dummy->tx, key, sizeof(*key)); err = psp_dev_tx_key_add(psd, dummy, extack); if (err) goto exit_free_dummy; memcpy(pas->drv_data, dummy->drv_data, psd->caps->assoc_drv_spc); memcpy(&pas->tx, key, sizeof(*key)); WRITE_ONCE(sk->sk_validate_xmit_skb, psp_validate_xmit); tcp_write_collapse_fence(sk); pas->upgrade_seq = tcp_sk(sk)->rcv_nxt; icsk = inet_csk(sk); icsk->icsk_ext_hdr_len += psp_sk_overhead(sk); icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); exit_free_dummy: kfree(dummy); exit_unlock: release_sock(sk); return err; } void psp_assocs_key_rotated(struct psp_dev *psd) { struct psp_assoc *pas, *next; /* Mark the stale associations as invalid, they will no longer * be able to Rx any traffic. */ list_for_each_entry_safe(pas, next, &psd->prev_assocs, assocs_list) { pas->generation |= ~PSP_GEN_VALID_MASK; psd->stats.stales++; } list_splice_init(&psd->prev_assocs, &psd->stale_assocs); list_splice_init(&psd->active_assocs, &psd->prev_assocs); /* TODO: we should inform the sockets that got shut down */ } void psp_twsk_init(struct inet_timewait_sock *tw, const struct sock *sk) { struct psp_assoc *pas = psp_sk_assoc(sk); if (pas) refcount_inc(&pas->refcnt); rcu_assign_pointer(tw->psp_assoc, pas); tw->tw_validate_xmit_skb = psp_validate_xmit; } void psp_twsk_assoc_free(struct inet_timewait_sock *tw) { struct psp_assoc *pas = rcu_dereference_protected(tw->psp_assoc, 1); rcu_assign_pointer(tw->psp_assoc, NULL); psp_assoc_put(pas); } void psp_reply_set_decrypted(const struct sock *sk, struct sk_buff *skb) { struct psp_assoc *pas; rcu_read_lock(); pas = psp_sk_get_assoc_rcu(sk); if (pas && pas->tx.spi) skb->decrypted = 1; rcu_read_unlock(); } |
| 6384 2506 4 6382 6377 6381 2507 6331 6333 6333 106 106 106 106 106 1038 1043 1043 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra * * Provides a framework for enqueueing and running callbacks from hardirq * context. The enqueueing is NMI-safe. */ #include <linux/bug.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/irq_work.h> #include <linux/percpu.h> #include <linux/hardirq.h> #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/tick.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/smp.h> #include <linux/smpboot.h> #include <asm/processor.h> #include <linux/kasan.h> #include <trace/events/ipi.h> static DEFINE_PER_CPU(struct llist_head, raised_list); static DEFINE_PER_CPU(struct llist_head, lazy_list); static DEFINE_PER_CPU(struct task_struct *, irq_workd); static void wake_irq_workd(void) { struct task_struct *tsk = __this_cpu_read(irq_workd); if (!llist_empty(this_cpu_ptr(&lazy_list)) && tsk) wake_up_process(tsk); } #ifdef CONFIG_SMP static void irq_work_wake(struct irq_work *entry) { wake_irq_workd(); } static DEFINE_PER_CPU(struct irq_work, irq_work_wakeup) = IRQ_WORK_INIT_HARD(irq_work_wake); #endif static int irq_workd_should_run(unsigned int cpu) { return !llist_empty(this_cpu_ptr(&lazy_list)); } /* * Claim the entry so that no one else will poke at it. */ static bool irq_work_claim(struct irq_work *work) { int oflags; oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->node.a_flags); /* * If the work is already pending, no need to raise the IPI. * The pairing smp_mb() in irq_work_single() makes sure * everything we did before is visible. */ if (oflags & IRQ_WORK_PENDING) return false; return true; } void __weak arch_irq_work_raise(void) { /* * Lame architectures will get the timer tick callback */ } static __always_inline void irq_work_raise(struct irq_work *work) { if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt()) trace_call__ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func); arch_irq_work_raise(); } /* Enqueue on current CPU, work must already be claimed and preempt disabled */ static void __irq_work_queue_local(struct irq_work *work) { struct llist_head *list; bool rt_lazy_work = false; bool lazy_work = false; int work_flags; work_flags = atomic_read(&work->node.a_flags); if (work_flags & IRQ_WORK_LAZY) lazy_work = true; else if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(work_flags & IRQ_WORK_HARD_IRQ)) rt_lazy_work = true; if (lazy_work || rt_lazy_work) list = this_cpu_ptr(&lazy_list); else list = this_cpu_ptr(&raised_list); if (!llist_add(&work->node.llist, list)) return; /* If the work is "lazy", handle it from next tick if any */ if (!lazy_work || tick_nohz_tick_stopped()) irq_work_raise(work); } /* Enqueue the irq work @work on the current CPU */ bool irq_work_queue(struct irq_work *work) { /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; /* Queue the entry and raise the IPI if needed. */ preempt_disable(); __irq_work_queue_local(work); preempt_enable(); return true; } EXPORT_SYMBOL_GPL(irq_work_queue); /* * Enqueue the irq_work @work on @cpu unless it's already pending * somewhere. * * Can be re-enqueued while the callback is still in progress. */ bool irq_work_queue_on(struct irq_work *work, int cpu) { #ifndef CONFIG_SMP return irq_work_queue(work); #else /* CONFIG_SMP: */ /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(cpu)); /* Only queue if not already pending */ if (!irq_work_claim(work)) return false; kasan_record_aux_stack(work); preempt_disable(); if (cpu != smp_processor_id()) { /* Arch remote IPI send/receive backend aren't NMI safe */ WARN_ON_ONCE(in_nmi()); /* * On PREEMPT_RT the items which are not marked as * IRQ_WORK_HARD_IRQ are added to the lazy list and a HARD work * item is used on the remote CPU to wake the thread. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(atomic_read(&work->node.a_flags) & IRQ_WORK_HARD_IRQ)) { if (!llist_add(&work->node.llist, &per_cpu(lazy_list, cpu))) goto out; work = &per_cpu(irq_work_wakeup, cpu); if (!irq_work_claim(work)) goto out; } __smp_call_single_queue(cpu, &work->node.llist); } else { __irq_work_queue_local(work); } out: preempt_enable(); return true; #endif /* CONFIG_SMP */ } bool irq_work_needs_cpu(void) { struct llist_head *raised, *lazy; raised = this_cpu_ptr(&raised_list); lazy = this_cpu_ptr(&lazy_list); if (llist_empty(raised) || arch_irq_work_has_interrupt()) if (llist_empty(lazy)) return false; /* All work should have been flushed before going offline */ WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); return true; } void irq_work_single(void *arg) { struct irq_work *work = arg; int flags; /* * Clear the PENDING bit, after this point the @work can be re-used. * The PENDING bit acts as a lock, and we own it, so we can clear it * without atomic ops. */ flags = atomic_read(&work->node.a_flags); flags &= ~IRQ_WORK_PENDING; atomic_set(&work->node.a_flags, flags); /* * See irq_work_claim(). */ smp_mb(); lockdep_irq_work_enter(flags); work->func(work); lockdep_irq_work_exit(flags); /* * Clear the BUSY bit, if set, and return to the free state if no-one * else claimed it meanwhile. */ (void)atomic_cmpxchg(&work->node.a_flags, flags, flags & ~IRQ_WORK_BUSY); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) rcuwait_wake_up(&work->irqwait); } static void irq_work_run_list(struct llist_head *list) { struct irq_work *work, *tmp; struct llist_node *llnode; /* * On PREEMPT_RT IRQ-work which is not marked as HARD will be processed * in a per-CPU thread in preemptible context. Only the items which are * marked as IRQ_WORK_HARD_IRQ will be processed in hardirq context. */ BUG_ON(!irqs_disabled() && !IS_ENABLED(CONFIG_PREEMPT_RT)); if (llist_empty(list)) return; llnode = llist_del_all(list); llist_for_each_entry_safe(work, tmp, llnode, node.llist) irq_work_single(work); } /* * hotplug calls this through: * hotplug_cfd() -> flush_smp_call_function_queue() */ void irq_work_run(void) { irq_work_run_list(this_cpu_ptr(&raised_list)); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } EXPORT_SYMBOL_GPL(irq_work_run); void irq_work_tick(void) { struct llist_head *raised = this_cpu_ptr(&raised_list); if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) irq_work_run_list(raised); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) irq_work_run_list(this_cpu_ptr(&lazy_list)); else wake_irq_workd(); } /* * Synchronize against the irq_work @entry, ensures the entry is not * currently in use. */ void irq_work_sync(struct irq_work *work) { lockdep_assert_irqs_enabled(); might_sleep(); if ((IS_ENABLED(CONFIG_PREEMPT_RT) && !irq_work_is_hard(work)) || !arch_irq_work_has_interrupt()) { rcuwait_wait_event(&work->irqwait, !irq_work_is_busy(work), TASK_UNINTERRUPTIBLE); return; } while (irq_work_is_busy(work)) cpu_relax(); } EXPORT_SYMBOL_GPL(irq_work_sync); static void run_irq_workd(unsigned int cpu) { irq_work_run_list(this_cpu_ptr(&lazy_list)); } static void irq_workd_setup(unsigned int cpu) { sched_set_fifo_low(current); } static struct smp_hotplug_thread irqwork_threads = { .store = &irq_workd, .setup = irq_workd_setup, .thread_should_run = irq_workd_should_run, .thread_fn = run_irq_workd, .thread_comm = "irq_work/%u", }; static __init int irq_work_init_threads(void) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) BUG_ON(smpboot_register_percpu_thread(&irqwork_threads)); return 0; } early_initcall(irq_work_init_threads); |
| 4 11 6 6 2 3 6 7 2 2 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * IEEE 802.11 UHR definitions * * Copyright (c) 2025-2026 Intel Corporation */ #ifndef LINUX_IEEE80211_UHR_H #define LINUX_IEEE80211_UHR_H #include <linux/types.h> #include <linux/if_ether.h> #define IEEE80211_UHR_OPER_PARAMS_DPS_ENA 0x0001 #define IEEE80211_UHR_OPER_PARAMS_NPCA_ENA 0x0002 #define IEEE80211_UHR_OPER_PARAMS_PEDCA_ENA 0x0004 #define IEEE80211_UHR_OPER_PARAMS_DBE_ENA 0x0008 struct ieee80211_uhr_operation { __le16 params; u8 basic_mcs_nss_set[4]; u8 variable[]; } __packed; #define IEEE80211_UHR_NPCA_PARAMS_PRIMARY_CHAN_OFFS 0x0000000F #define IEEE80211_UHR_NPCA_PARAMS_MIN_DUR_THRESH 0x000000F0 #define IEEE80211_UHR_NPCA_PARAMS_SWITCH_DELAY 0x00003F00 #define IEEE80211_UHR_NPCA_PARAMS_SWITCH_BACK_DELAY 0x000FC000 #define IEEE80211_UHR_NPCA_PARAMS_INIT_QSRC 0x00300000 #define IEEE80211_UHR_NPCA_PARAMS_MOPLEN 0x00400000 #define IEEE80211_UHR_NPCA_PARAMS_DIS_SUBCH_BMAP_PRES 0x00800000 /** * struct ieee80211_uhr_npca_info - npca operation information * * This structure is the "NPCA Operation Parameters field format" of "UHR * Operation Element" fields as described in P802.11bn_D1.3 * subclause 9.4.2.353. See Figure 9-aa4. * * Refer to IEEE80211_UHR_NPCA* * @params: * NPCA Primary Channel - NPCA primary channel * NPCA_Min Duration Threshold - Minimum duration of inter-BSS activity * NPCA Switching Delay - * Time needed by an NPCA AP to switch from the * BSS primary channel to the NPCA primary channel * in the unit of 4 µs. * NPCA Switching Back Delay - * Time to switch from the NPCA primary channel * to the BSS primary channel in the unit of 4 µs. * NPCA Initial QSRC - * Initialize the EDCAF QSRC[AC] variables * when an NPCA STA in the BSS * switches to NPCA operation. * NPCA MOPLEN - * Indicates which conditions can be used to * initiate an NPCA operation, * 1 -> both PHYLEN NPCA operation and MOPLEN * NPCA operation are * permitted in the BSS * 0 -> only PHYLEN NPCA operation is allowed in the BSS. * NPCA Disabled Subchannel Bitmap Present - * Indicates whether the NPCA Disabled Subchannel * Bitmap field is present. A 1 in this field indicates that * the NPCA Disabled Subchannel Bitmap field is present * @dis_subch_bmap: * A bit in the bitmap that lies within the BSS bandwidth is set * to 1 to indicate that the corresponding 20 MHz subchannel is * punctured and is set to 0 to indicate that the corresponding * 20 MHz subchannel is not punctured. A bit in the bitmap that * falls outside of the BSS bandwidth is reserved. This field is * present when the value of the NPCA Disabled Subchannel Bitmap * Field Present field is equal to 1, and not present, otherwise */ struct ieee80211_uhr_npca_info { __le32 params; __le16 dis_subch_bmap[]; } __packed; #define IEEE80211_UHR_DPS_PADDING_DELAY 0x0000003F #define IEEE80211_UHR_DPS_TRANSITION_DELAY 0x00003F00 #define IEEE80211_UHR_DPS_ICF_REQUIRED 0x00010000 #define IEEE80211_UHR_DPS_PARAMETERIZED_FLAG 0x00020000 #define IEEE80211_UHR_DPS_LC_MODE_BW 0x001C0000 #define IEEE80211_UHR_DPS_LC_MODE_NSS 0x01E00000 #define IEEE80211_UHR_DPS_LC_MODE_MCS 0x1E000000 #define IEEE80211_UHR_DPS_MOBILE_AP_DPS_STATIC_HCM 0x20000000 /** * struct ieee80211_uhr_dps_info - DPS operation information * * This structure is the "DPS Operation Parameter field" of "UHR * Operation Element" fields as described in P802.11bn_D1.3 * subclause 9.4.1.87. See Figure 9-207u. * * Refer to IEEE80211_UHR_DPS* * @params: * DPS Padding Delay - * Indicates the minimum MAC padding * duration that is required by a DPS STA * in an ICF to cause the STA to transition * from the lower capability mode to the * higher capability mode. The DPS Padding * Delay field is in units of 4 µs. * DPS Transition Delay - * Indicates the amount of time required by a * DPS STA to transition from the higher * capability mode to the lower capability * mode. The DPS Transition Delay field is in * units of 4 µs. * ICF Required - * Indicates when the DPS assisting STA needs * to transmit an ICF frame to the peer DPS STA * before performing the frame exchanges with * the peer DPS STA in a TXOP. * 1 -> indicates that the transmission of the * ICF frame to the peer DPS STA prior to * any frame exchange is needed. * 0 -> ICF transmission before the frame * exchanges with the peer DPS STA is only * needed if the frame exchange is performed * in the HC mode. * Parameterized Flag - * 0 -> indicates that only 20 MHz, 1 SS, * non-HT PPDU format with the data * rate of 6, 12, and 24 Mb/s as the * default mode are supported by the * DPS STA in the LC mode * 1 -> indicates that a bandwidth up to the * bandwidth indicated in the LC Mode * Bandwidth field, a number of spatial * streams up to the NSS indicated in * the LC Mode Nss field, and an MCS up * to the MCS indicated in the LC Mode * MCS fields are supported by the DPS * STA in the LC mode as the * parameterized mode. * LC Mode Bandwidth - * Indicates the maximum bandwidth supported * by the STA in the LC mode. * LC Mode NSS - * Indicates the maximum number of the spatial * streams supported by the STA in the LC mode. * LC Mode MCS - * Indicates the highest MCS supported by the STA * in the LC mode. * Mobile AP DPS Static HCM - * 1 -> indicates that it will remain in the DPS high * capability mode until the next TBTT on that * link. * 0 -> otherwise. */ struct ieee80211_uhr_dps_info { __le32 params; } __packed; #define IEEE80211_UHR_DBE_OPER_BANDWIDTH 0x07 #define IEEE80211_UHR_DBE_OPER_DIS_SUBCHANNEL_BITMAP_PRES 0x08 /** * enum ieee80211_uhr_dbe_oper_bw - DBE Operational Bandwidth * * Encoding for the DBE Operational Bandwidth field in the UHR Operation * element (DBE Operation Parameters). * * @IEEE80211_UHR_DBE_OPER_BW_40: 40 MHz operational DBE bandwidth * @IEEE80211_UHR_DBE_OPER_BW_80: 80 MHz operational DBE bandwidth * @IEEE80211_UHR_DBE_OPER_BW_160: 160 MHz operational DBE bandwidth * @IEEE80211_UHR_DBE_OPER_BW_320_1: 320-1 MHz operational DBE bandwidth * @IEEE80211_UHR_DBE_OPER_BW_320_2: 320-2 MHz operational DBE bandwidth */ enum ieee80211_uhr_dbe_oper_bw { IEEE80211_UHR_DBE_OPER_BW_40 = 1, IEEE80211_UHR_DBE_OPER_BW_80 = 2, IEEE80211_UHR_DBE_OPER_BW_160 = 3, IEEE80211_UHR_DBE_OPER_BW_320_1 = 4, IEEE80211_UHR_DBE_OPER_BW_320_2 = 5, }; /** * struct ieee80211_uhr_dbe_info - DBE operation information * * This structure is the "DBE Operation Parameters field" of * "UHR Operation Element" fields as described in P802.11bn_D1.3 * subclause 9.4.2.353. See Figure 9-aa6. * * Refer to IEEE80211_UHR_DBE_OPER* * @params: * B0-B2 - DBE Operational Bandwidth field, see * "enum ieee80211_uhr_dbe_oper_bw" for values. * Value 0 is reserved. * Value 1 indicates 40 MHz operational DBE bandwidth. * Value 2 indicates 80 MHz operational DBE bandwidth. * Value 3 indicates 160 MHz operational DBE bandwidth. * Value 4 indicates 320-1 MHz operational DBE bandwidth. * Value 5 indicates 320-2 MHz operational DBE bandwidth. * Values 6 to 7 are reserved. * B3 - DBE Disabled Subchannel Bitmap Present. * @dis_subch_bmap: DBE Disabled Subchannel Bitmap field is set to indicate * disabled 20 MHz subchannels within the DBE Bandwidth. */ struct ieee80211_uhr_dbe_info { u8 params; __le16 dis_subch_bmap[]; } __packed; #define IEEE80211_UHR_P_EDCA_ECWMIN 0x0F #define IEEE80211_UHR_P_EDCA_ECWMAX 0xF0 #define IEEE80211_UHR_P_EDCA_AIFSN 0x000F #define IEEE80211_UHR_P_EDCA_CW_DS 0x0030 #define IEEE80211_UHR_P_EDCA_PSRC_THRESHOLD 0x01C0 #define IEEE80211_UHR_P_EDCA_QSRC_THRESHOLD 0x0600 /** * struct ieee80211_uhr_p_edca_info - P-EDCA operation information * * This structure is the "P-EDCA Operation Parameters field" of * "UHR Operation Element" fields as described in P802.11bn_D1.3 * subclause 9.4.2.353. See Figure 9-aa5. * * Refer to IEEE80211_UHR_P_EDCA* * @p_edca_ec: P-EDCA ECWmin and ECWmax. * These fields indicate the CWmin and CWmax values used by a * P-EDCA STA during P-EDCA contention. * @params: AIFSN, CW DS, PSRC threshold, and QSRC threshold. * - The AIFSN field indicates the AIFSN value used by a P-EDCA STA * during P-EDCA contention. * - The CW DS field indicates the value used for randomization of the * transmission slot of the DS-CTS frame. The value 3 is reserved. * The value 0 indicates that randomization is not enabled. * - The P-EDCA PSRC threshold field indicates the maximum number of * allowed consecutive DS-CTS transmissions. The value 0 and values * greater than 4 are reserved. * - The P-EDCA QSRC threshold field indicates the value of the * QSRC[AC_VO] counter required to start P-EDCA contention. The * value 0 is reserved. */ struct ieee80211_uhr_p_edca_info { u8 p_edca_ec; __le16 params; } __packed; static inline bool ieee80211_uhr_oper_size_ok(const u8 *data, u8 len, bool beacon) { const struct ieee80211_uhr_operation *oper = (const void *)data; u8 needed = sizeof(*oper); if (len < needed) return false; /* nothing else present in beacons */ if (beacon) return true; /* DPS Operation Parameters (fixed 4 bytes) */ if (oper->params & cpu_to_le16(IEEE80211_UHR_OPER_PARAMS_DPS_ENA)) { needed += sizeof(struct ieee80211_uhr_dps_info); if (len < needed) return false; } /* NPCA Operation Parameters (fixed 4 bytes + optional 2 bytes) */ if (oper->params & cpu_to_le16(IEEE80211_UHR_OPER_PARAMS_NPCA_ENA)) { const struct ieee80211_uhr_npca_info *npca = (const void *)(data + needed); needed += sizeof(*npca); if (len < needed) return false; if (npca->params & cpu_to_le32(IEEE80211_UHR_NPCA_PARAMS_DIS_SUBCH_BMAP_PRES)) { needed += sizeof(npca->dis_subch_bmap[0]); if (len < needed) return false; } } /* P-EDCA Operation Parameters (fixed 3 bytes) */ if (oper->params & cpu_to_le16(IEEE80211_UHR_OPER_PARAMS_PEDCA_ENA)) { needed += sizeof(struct ieee80211_uhr_p_edca_info); if (len < needed) return false; } /* DBE Operation Parameters (fixed 1 byte + optional 2 bytes) */ if (oper->params & cpu_to_le16(IEEE80211_UHR_OPER_PARAMS_DBE_ENA)) { const struct ieee80211_uhr_dbe_info *dbe = (const void *)(data + needed); needed += sizeof(*dbe); if (len < needed) return false; if (dbe->params & IEEE80211_UHR_DBE_OPER_DIS_SUBCHANNEL_BITMAP_PRES) { needed += sizeof(dbe->dis_subch_bmap[0]); if (len < needed) return false; } } return len >= needed; } /* * Note: cannot call this on the element coming from a beacon, * must ensure ieee80211_uhr_oper_size_ok(..., false) first */ static inline const struct ieee80211_uhr_npca_info * ieee80211_uhr_npca_info(const struct ieee80211_uhr_operation *oper) { const u8 *pos = oper->variable; if (!(oper->params & cpu_to_le16(IEEE80211_UHR_OPER_PARAMS_NPCA_ENA))) return NULL; if (oper->params & cpu_to_le16(IEEE80211_UHR_OPER_PARAMS_DPS_ENA)) pos += sizeof(struct ieee80211_uhr_dps_info); return (const void *)pos; } static inline const __le16 * ieee80211_uhr_npca_dis_subch_bitmap(const struct ieee80211_uhr_operation *oper) { const struct ieee80211_uhr_npca_info *npca; npca = ieee80211_uhr_npca_info(oper); if (!npca) return NULL; if (!(npca->params & cpu_to_le32(IEEE80211_UHR_NPCA_PARAMS_DIS_SUBCH_BMAP_PRES))) return NULL; return npca->dis_subch_bmap; } #define IEEE80211_UHR_MAC_CAP0_DPS_SUPP 0x01 #define IEEE80211_UHR_MAC_CAP0_DPS_ASSIST_SUPP 0x02 #define IEEE80211_UHR_MAC_CAP0_DPS_AP_STATIC_HCM_SUPP 0x04 #define IEEE80211_UHR_MAC_CAP0_NPCA_SUPP 0x10 #define IEEE80211_UHR_MAC_CAP0_ENH_BSR_SUPP 0x20 #define IEEE80211_UHR_MAC_CAP0_ADD_MAP_TID_SUPP 0x40 #define IEEE80211_UHR_MAC_CAP0_EOTSP_SUPP 0x80 #define IEEE80211_UHR_MAC_CAP1_DSO_SUPP 0x01 #define IEEE80211_UHR_MAC_CAP1_PEDCA_SUPP 0x02 #define IEEE80211_UHR_MAC_CAP1_DBE_SUPP 0x04 #define IEEE80211_UHR_MAC_CAP1_UL_LLI_SUPP 0x08 #define IEEE80211_UHR_MAC_CAP1_P2P_LLI_SUPP 0x10 #define IEEE80211_UHR_MAC_CAP1_PUO_SUPP 0x20 #define IEEE80211_UHR_MAC_CAP1_AP_PUO_SUPP 0x40 #define IEEE80211_UHR_MAC_CAP1_DUO_SUPP 0x80 #define IEEE80211_UHR_MAC_CAP2_OMC_UL_MU_DIS_RX_SUPP 0x01 #define IEEE80211_UHR_MAC_CAP2_AOM_SUPP 0x02 #define IEEE80211_UHR_MAC_CAP2_IFCS_LOC_SUPP 0x04 #define IEEE80211_UHR_MAC_CAP2_UHR_TRS_SUPP 0x08 #define IEEE80211_UHR_MAC_CAP2_TXSPG_SUPP 0x10 #define IEEE80211_UHR_MAC_CAP2_TXOP_RET_IN_TXSPG 0x20 #define IEEE80211_UHR_MAC_CAP2_UHR_OM_PU_TO_LOW 0xC0 #define IEEE80211_UHR_MAC_CAP3_UHR_OM_PU_TO_HIGH 0x03 #define IEEE80211_UHR_MAC_CAP3_PARAM_UPD_ADV_NOTIF_INTV 0x1C #define IEEE80211_UHR_MAC_CAP3_UPD_IND_TIM_INTV_LOW 0xE0 #define IEEE80211_UHR_MAC_CAP4_UPD_IND_TIM_INTV_HIGH 0x03 #define IEEE80211_UHR_MAC_CAP4_BOUNDED_ESS 0x04 #define IEEE80211_UHR_MAC_CAP4_BTM_ASSURANCE 0x08 #define IEEE80211_UHR_MAC_CAP4_CO_BF_SUPP 0x10 #define IEEE80211_UHR_MAC_CAP_DBE_MAX_BW 0x07 #define IEEE80211_UHR_MAC_CAP_DBE_EHT_MCS_MAP_160_PRES 0x08 #define IEEE80211_UHR_MAC_CAP_DBE_EHT_MCS_MAP_320_PRES 0x10 /** * enum ieee80211_uhr_dbe_max_supported_bw - DBE Maximum Supported Bandwidth * * As per spec P802.11bn_D1.3 "Table 9-bb5—Encoding of the DBE Maximum * Supported Bandwidth field". * * @IEEE80211_UHR_DBE_MAX_BW_40: Indicates 40 MHz DBE max supported bw * @IEEE80211_UHR_DBE_MAX_BW_80: Indicates 80 MHz DBE max supported bw * @IEEE80211_UHR_DBE_MAX_BW_160: Indicates 160 MHz DBE max supported bw * @IEEE80211_UHR_DBE_MAX_BW_320: Indicates 320 MHz DBE max supported bw */ enum ieee80211_uhr_dbe_max_supported_bw { IEEE80211_UHR_DBE_MAX_BW_40 = 1, IEEE80211_UHR_DBE_MAX_BW_80 = 2, IEEE80211_UHR_DBE_MAX_BW_160 = 3, IEEE80211_UHR_DBE_MAX_BW_320 = 4, }; struct ieee80211_uhr_cap_mac { u8 mac_cap[5]; } __packed; struct ieee80211_uhr_cap { struct ieee80211_uhr_cap_mac mac; /* DBE, PHY capabilities */ u8 variable[]; } __packed; #define IEEE80211_UHR_PHY_CAP_MAX_NSS_RX_SND_NDP_LE80 0x01 #define IEEE80211_UHR_PHY_CAP_MAX_NSS_RX_DL_MU_LE80 0x02 #define IEEE80211_UHR_PHY_CAP_MAX_NSS_RX_SND_NDP_160 0x04 #define IEEE80211_UHR_PHY_CAP_MAX_NSS_RX_DL_MU_160 0x08 #define IEEE80211_UHR_PHY_CAP_MAX_NSS_RX_SND_NDP_320 0x10 #define IEEE80211_UHR_PHY_CAP_MAX_NSS_RX_DL_MU_320 0x20 #define IEEE80211_UHR_PHY_CAP_ELR_RX 0x40 #define IEEE80211_UHR_PHY_CAP_ELR_TX 0x80 struct ieee80211_uhr_cap_phy { u8 cap; } __packed; static inline bool ieee80211_uhr_capa_size_ok(const u8 *data, u8 len, bool from_ap) { const struct ieee80211_uhr_cap *cap = (const void *)data; size_t needed = sizeof(*cap) + sizeof(struct ieee80211_uhr_cap_phy); if (len < needed) return false; /* * A non-AP STA does not include the DBE Capability Parameters field * in the UHR MAC Capabilities Information field. */ if (from_ap && cap->mac.mac_cap[1] & IEEE80211_UHR_MAC_CAP1_DBE_SUPP) { u8 dbe; needed += 1; if (len < needed) return false; dbe = cap->variable[0]; if (dbe & IEEE80211_UHR_MAC_CAP_DBE_EHT_MCS_MAP_160_PRES) needed += 3; if (dbe & IEEE80211_UHR_MAC_CAP_DBE_EHT_MCS_MAP_320_PRES) needed += 3; } return len >= needed; } static inline const struct ieee80211_uhr_cap_phy * ieee80211_uhr_phy_cap(const struct ieee80211_uhr_cap *cap, bool from_ap) { u8 offs = 0; if (from_ap && cap->mac.mac_cap[1] & IEEE80211_UHR_MAC_CAP1_DBE_SUPP) { u8 dbe = cap->variable[0]; offs += 1; if (dbe & IEEE80211_UHR_MAC_CAP_DBE_EHT_MCS_MAP_160_PRES) offs += 3; if (dbe & IEEE80211_UHR_MAC_CAP_DBE_EHT_MCS_MAP_320_PRES) offs += 3; } return (const void *)&cap->variable[offs]; } #define IEEE80211_SMD_INFO_CAPA_DL_DATA_FWD 0x01 #define IEEE80211_SMD_INFO_CAPA_MAX_NUM_PREP 0x0E #define IEEE80211_SMD_INFO_CAPA_TYPE 0x10 #define IEEE80211_SMD_INFO_CAPA_PTK_PER_AP_MLD 0x20 struct ieee80211_smd_info { u8 id[ETH_ALEN]; u8 capa; __le16 timeout; } __packed; #endif /* LINUX_IEEE80211_UHR_H */ |
| 7 7 7 6 7 7 7 7 7 7 5 5 5 5 5 5 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/xattr.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> * * Fix by Harrison Xing <harrison@mountainviewdata.com>. * Ext4 code with a lot of help from Eric Jarman <ejarman@acm.org>. * Extended attributes for symlinks and special files added per * suggestion of Luka Renko <luka.renko@hermes.si>. * xattr consolidation Copyright (c) 2004 James Morris <jmorris@redhat.com>, * Red Hat Inc. * ea-in-inode support by Alex Tomas <alex@clusterfs.com> aka bzzz * and Andreas Gruenbacher <agruen@suse.de>. */ /* * Extended attributes are stored directly in inodes (on file systems with * inodes bigger than 128 bytes) and on additional disk blocks. The i_file_acl * field contains the block number if an inode uses an additional block. All * attributes must fit in the inode and one additional block. Blocks that * contain the identical set of attributes may be shared among several inodes. * Identical blocks are detected by keeping a cache of blocks that have * recently been accessed. * * The attributes in inodes and on blocks have a different header; the entries * are stored in the same format: * * +------------------+ * | header | * | entry 1 | | * | entry 2 | | growing downwards * | entry 3 | v * | four null bytes | * | . . . | * | value 1 | ^ * | value 3 | | growing upwards * | value 2 | | * +------------------+ * * The header is followed by multiple entry descriptors. In disk blocks, the * entry descriptors are kept sorted. In inodes, they are unsorted. The * attribute values are aligned to the end of the block in no specific order. * * Locking strategy * ---------------- * EXT4_I(inode)->i_file_acl is protected by EXT4_I(inode)->xattr_sem. * EA blocks are only changed if they are exclusive to an inode, so * holding xattr_sem also means that nothing but the EA block's reference * count can change. Multiple writers to the same block are synchronized * by the buffer lock. */ #include <linux/init.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/mbcache.h> #include <linux/quotaops.h> #include <linux/iversion.h> #include "ext4_jbd2.h" #include "ext4.h" #include "xattr.h" #include "acl.h" #ifdef EXT4_XATTR_DEBUG # define ea_idebug(inode, fmt, ...) \ printk(KERN_DEBUG "inode %s:%llu: " fmt "\n", \ inode->i_sb->s_id, inode->i_ino, ##__VA_ARGS__) # define ea_bdebug(bh, fmt, ...) \ printk(KERN_DEBUG "block %pg:%lu: " fmt "\n", \ bh->b_bdev, (unsigned long)bh->b_blocknr, ##__VA_ARGS__) #else # define ea_idebug(inode, fmt, ...) no_printk(fmt, ##__VA_ARGS__) # define ea_bdebug(bh, fmt, ...) no_printk(fmt, ##__VA_ARGS__) #endif static void ext4_xattr_block_cache_insert(struct mb_cache *, struct buffer_head *); static struct buffer_head * ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *, struct mb_cache_entry **); static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, size_t value_count); static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value, size_t value_count); static void ext4_xattr_rehash(struct ext4_xattr_header *); static const struct xattr_handler * const ext4_xattr_handler_map[] = { [EXT4_XATTR_INDEX_USER] = &ext4_xattr_user_handler, #ifdef CONFIG_EXT4_FS_POSIX_ACL [EXT4_XATTR_INDEX_POSIX_ACL_ACCESS] = &nop_posix_acl_access, [EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT] = &nop_posix_acl_default, #endif [EXT4_XATTR_INDEX_TRUSTED] = &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY [EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler, #endif [EXT4_XATTR_INDEX_HURD] = &ext4_xattr_hurd_handler, }; const struct xattr_handler * const ext4_xattr_handlers[] = { &ext4_xattr_user_handler, &ext4_xattr_trusted_handler, #ifdef CONFIG_EXT4_FS_SECURITY &ext4_xattr_security_handler, #endif &ext4_xattr_hurd_handler, NULL }; #define EA_BLOCK_CACHE(inode) (((struct ext4_sb_info *) \ inode->i_sb->s_fs_info)->s_ea_block_cache) #define EA_INODE_CACHE(inode) (((struct ext4_sb_info *) \ inode->i_sb->s_fs_info)->s_ea_inode_cache) static int ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, struct inode *inode); #ifdef CONFIG_LOCKDEP void ext4_xattr_inode_set_class(struct inode *ea_inode) { struct ext4_inode_info *ei = EXT4_I(ea_inode); lockdep_set_subclass(&ea_inode->i_rwsem, 1); (void) ei; /* shut up clang warning if !CONFIG_LOCKDEP */ lockdep_set_subclass(&ei->i_data_sem, I_DATA_SEM_EA); } #endif static __le32 ext4_xattr_block_csum(struct inode *inode, sector_t block_nr, struct ext4_xattr_header *hdr) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le64 dsk_block_nr = cpu_to_le64(block_nr); __u32 dummy_csum = 0; int offset = offsetof(struct ext4_xattr_header, h_checksum); csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)&dsk_block_nr, sizeof(dsk_block_nr)); csum = ext4_chksum(csum, (__u8 *)hdr, offset); csum = ext4_chksum(csum, (__u8 *)&dummy_csum, sizeof(dummy_csum)); offset += sizeof(dummy_csum); csum = ext4_chksum(csum, (__u8 *)hdr + offset, EXT4_BLOCK_SIZE(inode->i_sb) - offset); return cpu_to_le32(csum); } static int ext4_xattr_block_csum_verify(struct inode *inode, struct buffer_head *bh) { struct ext4_xattr_header *hdr = BHDR(bh); int ret = 1; if (ext4_has_feature_metadata_csum(inode->i_sb)) { lock_buffer(bh); ret = (hdr->h_checksum == ext4_xattr_block_csum(inode, bh->b_blocknr, hdr)); unlock_buffer(bh); } return ret; } static void ext4_xattr_block_csum_set(struct inode *inode, struct buffer_head *bh) { if (ext4_has_feature_metadata_csum(inode->i_sb)) BHDR(bh)->h_checksum = ext4_xattr_block_csum(inode, bh->b_blocknr, BHDR(bh)); } static inline const char *ext4_xattr_prefix(int name_index, struct dentry *dentry) { const struct xattr_handler *handler = NULL; if (name_index > 0 && name_index < ARRAY_SIZE(ext4_xattr_handler_map)) handler = ext4_xattr_handler_map[name_index]; if (!xattr_handler_can_list(handler, dentry)) return NULL; return xattr_prefix(handler); } static int check_xattrs(struct inode *inode, struct buffer_head *bh, struct ext4_xattr_entry *entry, void *end, void *value_start, const char *function, unsigned int line) { struct ext4_xattr_entry *e = entry; int err = -EFSCORRUPTED; char *err_str; if (bh) { if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) || BHDR(bh)->h_blocks != cpu_to_le32(1)) { err_str = "invalid header"; goto errout; } if (buffer_verified(bh)) return 0; if (!ext4_xattr_block_csum_verify(inode, bh)) { err = -EFSBADCRC; err_str = "invalid checksum"; goto errout; } } else { struct ext4_xattr_ibody_header *header = value_start; header -= 1; if (end - (void *)header < sizeof(*header) + sizeof(u32)) { err_str = "in-inode xattr block too small"; goto errout; } if (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) { err_str = "bad magic number in in-inode xattr"; goto errout; } } /* Find the end of the names list */ while (!IS_LAST_ENTRY(e)) { struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e); if ((void *)next + sizeof(u32) > end) { err_str = "e_name out of bounds"; goto errout; } if (strnlen(e->e_name, e->e_name_len) != e->e_name_len) { err_str = "bad e_name length"; goto errout; } e = next; } /* Check the values */ while (!IS_LAST_ENTRY(entry)) { u32 size = le32_to_cpu(entry->e_value_size); unsigned long ea_ino = le32_to_cpu(entry->e_value_inum); if (!ext4_has_feature_ea_inode(inode->i_sb) && ea_ino) { err_str = "ea_inode specified without ea_inode feature enabled"; goto errout; } if (ea_ino && ((ea_ino == EXT4_ROOT_INO) || !ext4_valid_inum(inode->i_sb, ea_ino))) { err_str = "invalid ea_ino"; goto errout; } if (ea_ino && !size) { err_str = "invalid size in ea xattr"; goto errout; } if (size > EXT4_XATTR_SIZE_MAX) { err_str = "e_value size too large"; goto errout; } if (size != 0 && entry->e_value_inum == 0) { u16 offs = le16_to_cpu(entry->e_value_offs); void *value; /* * The value cannot overlap the names, and the value * with padding cannot extend beyond 'end'. Check both * the padded and unpadded sizes, since the size may * overflow to 0 when adding padding. */ if (offs > end - value_start) { err_str = "e_value out of bounds"; goto errout; } value = value_start + offs; if (value < (void *)e + sizeof(u32) || size > end - value || EXT4_XATTR_SIZE(size) > end - value) { err_str = "overlapping e_value "; goto errout; } } entry = EXT4_XATTR_NEXT(entry); } if (bh) set_buffer_verified(bh); return 0; errout: if (bh) __ext4_error_inode(inode, function, line, 0, -err, "corrupted xattr block %llu: %s", (unsigned long long) bh->b_blocknr, err_str); else __ext4_error_inode(inode, function, line, 0, -err, "corrupted in-inode xattr: %s", err_str); return err; } static inline int __ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh, const char *function, unsigned int line) { return check_xattrs(inode, bh, BFIRST(bh), bh->b_data + bh->b_size, bh->b_data, function, line); } #define ext4_xattr_check_block(inode, bh) \ __ext4_xattr_check_block((inode), (bh), __func__, __LINE__) int __xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header, void *end, const char *function, unsigned int line) { return check_xattrs(inode, NULL, IFIRST(header), end, IFIRST(header), function, line); } static int xattr_find_entry(struct inode *inode, struct ext4_xattr_entry **pentry, void *end, int name_index, const char *name, int sorted) { struct ext4_xattr_entry *entry, *next; size_t name_len; int cmp = 1; if (name == NULL) return -EINVAL; name_len = strlen(name); for (entry = *pentry; !IS_LAST_ENTRY(entry); entry = next) { next = EXT4_XATTR_NEXT(entry); if ((void *) next >= end) { EXT4_ERROR_INODE(inode, "corrupted xattr entries"); return -EFSCORRUPTED; } cmp = name_index - entry->e_name_index; if (!cmp) cmp = name_len - entry->e_name_len; if (!cmp) cmp = memcmp(name, entry->e_name, name_len); if (!cmp || (cmp < 0 && sorted)) break; } *pentry = entry; return cmp ? -ENODATA : 0; } static u32 ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size) { return ext4_chksum(sbi->s_csum_seed, buffer, size); } static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode) { return ((u64) inode_get_ctime_sec(ea_inode) << 32) | (u32) inode_peek_iversion_raw(ea_inode); } static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count) { inode_set_ctime(ea_inode, (u32)(ref_count >> 32), 0); inode_set_iversion_raw(ea_inode, ref_count & 0xffffffff); } static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode) { return (u32) inode_get_atime_sec(ea_inode); } static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash) { inode_set_atime(ea_inode, hash, 0); } /* * Read the EA value from an inode. */ static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size) { int blocksize = 1 << ea_inode->i_blkbits; int bh_count = (size + blocksize - 1) >> ea_inode->i_blkbits; int tail_size = (size % blocksize) ?: blocksize; struct buffer_head *bhs_inline[8]; struct buffer_head **bhs = bhs_inline; int i, ret; if (bh_count > ARRAY_SIZE(bhs_inline)) { bhs = kmalloc_objs(*bhs, bh_count, GFP_NOFS); if (!bhs) return -ENOMEM; } ret = ext4_bread_batch(ea_inode, 0 /* block */, bh_count, true /* wait */, bhs); if (ret) goto free_bhs; for (i = 0; i < bh_count; i++) { /* There shouldn't be any holes in ea_inode. */ if (!bhs[i]) { ret = -EFSCORRUPTED; goto put_bhs; } memcpy((char *)buf + blocksize * i, bhs[i]->b_data, i < bh_count - 1 ? blocksize : tail_size); } ret = 0; put_bhs: for (i = 0; i < bh_count; i++) brelse(bhs[i]); free_bhs: if (bhs != bhs_inline) kfree(bhs); return ret; } #define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode_get_mtime_sec(inode))) static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino, u32 ea_inode_hash, struct inode **ea_inode) { struct inode *inode; int err; /* * We have to check for this corruption early as otherwise * iget_locked() could wait indefinitely for the state of our * parent inode. */ if (parent->i_ino == ea_ino) { ext4_error(parent->i_sb, "Parent and EA inode have the same ino %lu", ea_ino); return -EFSCORRUPTED; } inode = ext4_iget(parent->i_sb, ea_ino, EXT4_IGET_EA_INODE); if (IS_ERR(inode)) { err = PTR_ERR(inode); ext4_error(parent->i_sb, "error while reading EA inode %lu err=%d", ea_ino, err); return err; } ext4_xattr_inode_set_class(inode); /* * Check whether this is an old Lustre-style xattr inode. Lustre * implementation does not have hash validation, rather it has a * backpointer from ea_inode to the parent inode. */ if (ea_inode_hash != ext4_xattr_inode_get_hash(inode) && EXT4_XATTR_INODE_GET_PARENT(inode) == parent->i_ino && inode->i_generation == parent->i_generation) { ext4_set_inode_state(inode, EXT4_STATE_LUSTRE_EA_INODE); ext4_xattr_inode_set_ref(inode, 1); } else { inode_lock_nested(inode, I_MUTEX_XATTR); inode->i_flags |= S_NOQUOTA; inode_unlock(inode); } *ea_inode = inode; return 0; } /* Remove entry from mbcache when EA inode is getting evicted */ void ext4_evict_ea_inode(struct inode *inode) { struct mb_cache_entry *oe; if (!EA_INODE_CACHE(inode)) return; /* Wait for entry to get unused so that we can remove it */ while ((oe = mb_cache_entry_delete_or_get(EA_INODE_CACHE(inode), ext4_xattr_inode_get_hash(inode), inode->i_ino))) { mb_cache_entry_wait_unused(oe); mb_cache_entry_put(EA_INODE_CACHE(inode), oe); } } static int ext4_xattr_inode_verify_hashes(struct inode *ea_inode, struct ext4_xattr_entry *entry, void *buffer, size_t size) { u32 hash; /* Verify stored hash matches calculated hash. */ hash = ext4_xattr_inode_hash(EXT4_SB(ea_inode->i_sb), buffer, size); if (hash != ext4_xattr_inode_get_hash(ea_inode)) return -EFSCORRUPTED; if (entry) { __le32 e_hash, tmp_data; /* Verify entry hash. */ tmp_data = cpu_to_le32(hash); e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len, &tmp_data, 1); /* All good? */ if (e_hash == entry->e_hash) return 0; /* * Not good. Maybe the entry hash was calculated * using the buggy signed char version? */ e_hash = ext4_xattr_hash_entry_signed(entry->e_name, entry->e_name_len, &tmp_data, 1); /* Still no match - bad */ if (e_hash != entry->e_hash) return -EFSCORRUPTED; /* Let people know about old hash */ pr_warn_once("ext4: filesystem with signed xattr name hash"); } return 0; } /* * Read xattr value from the EA inode. */ static int ext4_xattr_inode_get(struct inode *inode, struct ext4_xattr_entry *entry, void *buffer, size_t size) { struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); struct inode *ea_inode; int err; err = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum), le32_to_cpu(entry->e_hash), &ea_inode); if (err) { ea_inode = NULL; goto out; } if (i_size_read(ea_inode) != size) { ext4_warning_inode(ea_inode, "ea_inode file size=%llu entry size=%zu", i_size_read(ea_inode), size); err = -EFSCORRUPTED; goto out; } err = ext4_xattr_inode_read(ea_inode, buffer, size); if (err) goto out; if (!ext4_test_inode_state(ea_inode, EXT4_STATE_LUSTRE_EA_INODE)) { err = ext4_xattr_inode_verify_hashes(ea_inode, entry, buffer, size); if (err) { ext4_warning_inode(ea_inode, "EA inode hash validation failed"); goto out; } if (ea_inode_cache) mb_cache_entry_create(ea_inode_cache, GFP_NOFS, ext4_xattr_inode_get_hash(ea_inode), ea_inode->i_ino, true /* reusable */); } out: iput(ea_inode); return err; } static int ext4_xattr_block_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { struct buffer_head *bh = NULL; struct ext4_xattr_entry *entry; size_t size; void *end; int error; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld", name_index, name, buffer, (long)buffer_size); if (!EXT4_I(inode)->i_file_acl) return -ENODATA; ea_idebug(inode, "reading block %llu", (unsigned long long)EXT4_I(inode)->i_file_acl); bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return PTR_ERR(bh); ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; ext4_xattr_block_cache_insert(ea_block_cache, bh); entry = BFIRST(bh); end = bh->b_data + bh->b_size; error = xattr_find_entry(inode, &entry, end, name_index, name, 1); if (error) goto cleanup; size = le32_to_cpu(entry->e_value_size); error = -ERANGE; if (unlikely(size > EXT4_XATTR_SIZE_MAX)) goto cleanup; if (buffer) { if (size > buffer_size) goto cleanup; if (entry->e_value_inum) { error = ext4_xattr_inode_get(inode, entry, buffer, size); if (error) goto cleanup; } else { u16 offset = le16_to_cpu(entry->e_value_offs); void *p = bh->b_data + offset; if (unlikely(p + size > end)) goto cleanup; memcpy(buffer, p, size); } } error = size; cleanup: brelse(bh); return error; } int ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; struct ext4_inode *raw_inode; struct ext4_iloc iloc; size_t size; void *end; int error; if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return -ENODATA; error = ext4_get_inode_loc(inode, &iloc); if (error) return error; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); end = ITAIL(inode, raw_inode); entry = IFIRST(header); error = xattr_find_entry(inode, &entry, end, name_index, name, 0); if (error) goto cleanup; size = le32_to_cpu(entry->e_value_size); error = -ERANGE; if (unlikely(size > EXT4_XATTR_SIZE_MAX)) goto cleanup; if (buffer) { if (size > buffer_size) goto cleanup; if (entry->e_value_inum) { error = ext4_xattr_inode_get(inode, entry, buffer, size); if (error) goto cleanup; } else { u16 offset = le16_to_cpu(entry->e_value_offs); void *p = (void *)IFIRST(header) + offset; if (unlikely(p + size > end)) goto cleanup; memcpy(buffer, p, size); } } error = size; cleanup: brelse(iloc.bh); return error; } /* * ext4_xattr_get() * * Copy an extended attribute into the buffer * provided, or compute the buffer size required. * Buffer is NULL to compute the size of the buffer required. * * Returns a negative error number on failure, or the number of bytes * used / required on success. */ int ext4_xattr_get(struct inode *inode, int name_index, const char *name, void *buffer, size_t buffer_size) { int error; if (unlikely(ext4_forced_shutdown(inode->i_sb))) return -EIO; if (strlen(name) > 255) return -ERANGE; down_read(&EXT4_I(inode)->xattr_sem); error = ext4_xattr_ibody_get(inode, name_index, name, buffer, buffer_size); if (error == -ENODATA) error = ext4_xattr_block_get(inode, name_index, name, buffer, buffer_size); up_read(&EXT4_I(inode)->xattr_sem); return error; } static int ext4_xattr_list_entries(struct dentry *dentry, struct ext4_xattr_entry *entry, char *buffer, size_t buffer_size) { size_t rest = buffer_size; for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { const char *prefix; prefix = ext4_xattr_prefix(entry->e_name_index, dentry); if (prefix) { size_t prefix_len = strlen(prefix); size_t size = prefix_len + entry->e_name_len + 1; if (buffer) { if (size > rest) return -ERANGE; memcpy(buffer, prefix, prefix_len); buffer += prefix_len; memcpy(buffer, entry->e_name, entry->e_name_len); buffer += entry->e_name_len; *buffer++ = 0; } rest -= size; } } return buffer_size - rest; /* total size */ } static int ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = d_inode(dentry); struct buffer_head *bh = NULL; int error; ea_idebug(inode, "buffer=%p, buffer_size=%ld", buffer, (long)buffer_size); if (!EXT4_I(inode)->i_file_acl) return 0; ea_idebug(inode, "reading block %llu", (unsigned long long)EXT4_I(inode)->i_file_acl); bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return PTR_ERR(bh); ea_bdebug(bh, "b_count=%d, refcount=%d", atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount)); error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; ext4_xattr_block_cache_insert(EA_BLOCK_CACHE(inode), bh); error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size); cleanup: brelse(bh); return error; } static int ext4_xattr_ibody_list(struct dentry *dentry, char *buffer, size_t buffer_size) { struct inode *inode = d_inode(dentry); struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; struct ext4_iloc iloc; int error; if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR)) return 0; error = ext4_get_inode_loc(inode, &iloc); if (error) return error; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); error = ext4_xattr_list_entries(dentry, IFIRST(header), buffer, buffer_size); brelse(iloc.bh); return error; } /* * Inode operation listxattr() * * d_inode(dentry)->i_rwsem: don't care * * Copy a list of attribute names into the buffer * provided, or compute the buffer size required. * Buffer is NULL to compute the size of the buffer required. * * Returns a negative error number on failure, or the number of bytes * used / required on success. */ ssize_t ext4_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size) { int ret, ret2; down_read(&EXT4_I(d_inode(dentry))->xattr_sem); ret = ret2 = ext4_xattr_ibody_list(dentry, buffer, buffer_size); if (ret < 0) goto errout; if (buffer) { buffer += ret; buffer_size -= ret; } ret = ext4_xattr_block_list(dentry, buffer, buffer_size); if (ret < 0) goto errout; ret += ret2; errout: up_read(&EXT4_I(d_inode(dentry))->xattr_sem); return ret; } /* * If the EXT4_FEATURE_COMPAT_EXT_ATTR feature of this file system is * not set, set it. */ static void ext4_xattr_update_super_block(handle_t *handle, struct super_block *sb) { if (ext4_has_feature_xattr(sb)) return; BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get_write_access"); if (ext4_journal_get_write_access(handle, sb, EXT4_SB(sb)->s_sbh, EXT4_JTR_NONE) == 0) { lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_xattr(sb); ext4_superblock_csum_set(sb); unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); } } int ext4_get_inode_usage(struct inode *inode, qsize_t *usage) { struct ext4_iloc iloc = { .bh = NULL }; struct buffer_head *bh = NULL; struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; struct ext4_xattr_entry *entry; qsize_t ea_inode_refs = 0; int ret; lockdep_assert_held_read(&EXT4_I(inode)->xattr_sem); if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { ret = ext4_get_inode_loc(inode, &iloc); if (ret) goto out; raw_inode = ext4_raw_inode(&iloc); header = IHDR(inode, raw_inode); for (entry = IFIRST(header); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) ea_inode_refs++; } if (EXT4_I(inode)->i_file_acl) { bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { ret = PTR_ERR(bh); bh = NULL; goto out; } ret = ext4_xattr_check_block(inode, bh); if (ret) goto out; for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) ea_inode_refs++; } *usage = ea_inode_refs + 1; ret = 0; out: brelse(iloc.bh); brelse(bh); return ret; } static inline size_t round_up_cluster(struct inode *inode, size_t length) { struct super_block *sb = inode->i_sb; size_t cluster_size = 1 << (EXT4_SB(sb)->s_cluster_bits + inode->i_blkbits); size_t mask = ~(cluster_size - 1); return (length + cluster_size - 1) & mask; } static int ext4_xattr_inode_alloc_quota(struct inode *inode, size_t len) { int err; err = dquot_alloc_inode(inode); if (err) return err; err = dquot_alloc_space_nodirty(inode, round_up_cluster(inode, len)); if (err) dquot_free_inode(inode); return err; } static void ext4_xattr_inode_free_quota(struct inode *parent, struct inode *ea_inode, size_t len) { if (ea_inode && ext4_test_inode_state(ea_inode, EXT4_STATE_LUSTRE_EA_INODE)) return; dquot_free_space_nodirty(parent, round_up_cluster(parent, len)); dquot_free_inode(parent); } int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode, struct buffer_head *block_bh, size_t value_len, bool is_create) { int credits; int blocks; /* * 1) Owner inode update * 2) Ref count update on old xattr block * 3) new xattr block * 4) block bitmap update for new xattr block * 5) group descriptor for new xattr block * 6) block bitmap update for old xattr block * 7) group descriptor for old block * * 6 & 7 can happen if we have two racing threads T_a and T_b * which are each trying to set an xattr on inodes I_a and I_b * which were both initially sharing an xattr block. */ credits = 7; /* Quota updates. */ credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(sb); /* * In case of inline data, we may push out the data to a block, * so we need to reserve credits for this eventuality */ if (inode && ext4_has_inline_data(inode)) credits += ext4_chunk_trans_extent(inode, 1) + 1; /* We are done if ea_inode feature is not enabled. */ if (!ext4_has_feature_ea_inode(sb)) return credits; /* New ea_inode, inode map, block bitmap, group descriptor. */ credits += 4; /* Data blocks. */ blocks = (value_len + sb->s_blocksize - 1) >> sb->s_blocksize_bits; /* Indirection block or one level of extent tree. */ blocks += 1; /* Block bitmap and group descriptor updates for each block. */ credits += blocks * 2; /* Blocks themselves. */ credits += blocks; if (!is_create) { /* Dereference ea_inode holding old xattr value. * Old ea_inode, inode map, block bitmap, group descriptor. */ credits += 4; /* Data blocks for old ea_inode. */ blocks = XATTR_SIZE_MAX >> sb->s_blocksize_bits; /* Indirection block or one level of extent tree for old * ea_inode. */ blocks += 1; /* Block bitmap and group descriptor updates for each block. */ credits += blocks * 2; } /* We may need to clone the existing xattr block in which case we need * to increment ref counts for existing ea_inodes referenced by it. */ if (block_bh) { struct ext4_xattr_entry *entry = BFIRST(block_bh); for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) if (entry->e_value_inum) /* Ref count update on ea_inode. */ credits += 1; } return credits; } static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode, int ref_change) { struct ext4_iloc iloc; u64 ref_count; int ret; inode_lock_nested(ea_inode, I_MUTEX_XATTR); ret = ext4_reserve_inode_write(handle, ea_inode, &iloc); if (ret) goto out; ref_count = ext4_xattr_inode_get_ref(ea_inode); if ((ref_count == 0 && ref_change < 0) || (ref_count == U64_MAX && ref_change > 0)) { ext4_error_inode(ea_inode, __func__, __LINE__, 0, "EA inode %llu ref wraparound: ref_count=%lld ref_change=%d", ea_inode->i_ino, ref_count, ref_change); brelse(iloc.bh); ret = -EFSCORRUPTED; goto out; } ref_count += ref_change; ext4_xattr_inode_set_ref(ea_inode, ref_count); if (ref_change > 0) { if (ref_count == 1) { WARN_ONCE(ea_inode->i_nlink, "EA inode %llu i_nlink=%u", ea_inode->i_ino, ea_inode->i_nlink); set_nlink(ea_inode, 1); ext4_orphan_del(handle, ea_inode); } } else { if (ref_count == 0) { WARN_ONCE(ea_inode->i_nlink != 1, "EA inode %llu i_nlink=%u", ea_inode->i_ino, ea_inode->i_nlink); clear_nlink(ea_inode); ext4_orphan_add(handle, ea_inode); } } ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc); if (ret) ext4_warning_inode(ea_inode, "ext4_mark_iloc_dirty() failed ret=%d", ret); out: inode_unlock(ea_inode); return ret; } static int ext4_xattr_inode_inc_ref(handle_t *handle, struct inode *ea_inode) { return ext4_xattr_inode_update_ref(handle, ea_inode, 1); } static int ext4_xattr_inode_dec_ref(handle_t *handle, struct inode *ea_inode) { return ext4_xattr_inode_update_ref(handle, ea_inode, -1); } static int ext4_xattr_inode_inc_ref_all(handle_t *handle, struct inode *parent, struct ext4_xattr_entry *first) { struct inode *ea_inode; struct ext4_xattr_entry *entry; struct ext4_xattr_entry *failed_entry; unsigned int ea_ino; int err, saved_err; for (entry = first; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) goto cleanup; err = ext4_xattr_inode_inc_ref(handle, ea_inode); if (err) { ext4_warning_inode(ea_inode, "inc ref error %d", err); iput(ea_inode); goto cleanup; } iput(ea_inode); } return 0; cleanup: saved_err = err; failed_entry = entry; for (entry = first; entry != failed_entry; entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) { ext4_warning(parent->i_sb, "cleanup ea_ino %u iget error %d", ea_ino, err); continue; } err = ext4_xattr_inode_dec_ref(handle, ea_inode); if (err) ext4_warning_inode(ea_inode, "cleanup dec ref error %d", err); iput(ea_inode); } return saved_err; } static int ext4_xattr_restart_fn(handle_t *handle, struct inode *inode, struct buffer_head *bh, bool block_csum, bool dirty) { int error; if (bh && dirty) { if (block_csum) ext4_xattr_block_csum_set(inode, bh); error = ext4_handle_dirty_metadata(handle, NULL, bh); if (error) { ext4_warning(inode->i_sb, "Handle metadata (error %d)", error); return error; } } return 0; } static void ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent, struct buffer_head *bh, struct ext4_xattr_entry *first, bool block_csum, struct ext4_xattr_inode_array **ea_inode_array, int extra_credits, bool skip_quota) { struct inode *ea_inode; struct ext4_xattr_entry *entry; struct ext4_iloc iloc = { .bh = NULL }; bool dirty = false; unsigned int ea_ino; int err; int credits; void *end; if (block_csum) end = (void *)bh->b_data + bh->b_size; else { err = ext4_get_inode_loc(parent, &iloc); if (err) { EXT4_ERROR_INODE(parent, "parent inode loc (error %d)", err); return; } end = (void *)ext4_raw_inode(&iloc) + EXT4_SB(parent->i_sb)->s_inode_size; } /* One credit for dec ref on ea_inode, one for orphan list addition, */ credits = 2 + extra_credits; for (entry = first; (void *)entry < end && !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; ea_ino = le32_to_cpu(entry->e_value_inum); err = ext4_xattr_inode_iget(parent, ea_ino, le32_to_cpu(entry->e_hash), &ea_inode); if (err) continue; err = ext4_expand_inode_array(ea_inode_array, ea_inode); if (err) { ext4_warning_inode(ea_inode, "Expand inode array err=%d", err); iput(ea_inode); continue; } err = ext4_journal_ensure_credits_fn(handle, credits, credits, ext4_free_metadata_revoke_credits(parent->i_sb, 1), ext4_xattr_restart_fn(handle, parent, bh, block_csum, dirty)); if (err < 0) { ext4_warning_inode(ea_inode, "Ensure credits err=%d", err); continue; } if (err > 0) { err = ext4_journal_get_write_access(handle, parent->i_sb, bh, EXT4_JTR_NONE); if (err) { ext4_warning_inode(ea_inode, "Re-get write access err=%d", err); continue; } } err = ext4_xattr_inode_dec_ref(handle, ea_inode); if (err) { ext4_warning_inode(ea_inode, "ea_inode dec ref err=%d", err); continue; } if (!skip_quota) ext4_xattr_inode_free_quota(parent, ea_inode, le32_to_cpu(entry->e_value_size)); /* * Forget about ea_inode within the same transaction that * decrements the ref count. This avoids duplicate decrements in * case the rest of the work spills over to subsequent * transactions. */ entry->e_value_inum = 0; entry->e_value_size = 0; dirty = true; } if (dirty) { /* * Note that we are deliberately skipping csum calculation for * the final update because we do not expect any journal * restarts until xattr block is freed. */ err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) ext4_warning_inode(parent, "handle dirty metadata err=%d", err); } brelse(iloc.bh); } /* * Release the xattr block BH: If the reference count is > 1, decrement it; * otherwise free the block. */ static void ext4_xattr_release_block(handle_t *handle, struct inode *inode, struct buffer_head *bh, struct ext4_xattr_inode_array **ea_inode_array, int extra_credits) { struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); u32 hash, ref; int error = 0; BUFFER_TRACE(bh, "get_write_access"); error = ext4_journal_get_write_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (error) goto out; retry_ref: lock_buffer(bh); hash = le32_to_cpu(BHDR(bh)->h_hash); ref = le32_to_cpu(BHDR(bh)->h_refcount); if (ref == 1) { ea_bdebug(bh, "refcount now=0; freeing"); /* * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect freed block */ if (ea_block_cache) { struct mb_cache_entry *oe; oe = mb_cache_entry_delete_or_get(ea_block_cache, hash, bh->b_blocknr); if (oe) { unlock_buffer(bh); mb_cache_entry_wait_unused(oe); mb_cache_entry_put(ea_block_cache, oe); goto retry_ref; } } get_bh(bh); unlock_buffer(bh); if (ext4_has_feature_ea_inode(inode->i_sb)) ext4_xattr_inode_dec_ref_all(handle, inode, bh, BFIRST(bh), true /* block_csum */, ea_inode_array, extra_credits, true /* skip_quota */); ext4_free_blocks(handle, inode, bh, 0, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); } else { ref--; BHDR(bh)->h_refcount = cpu_to_le32(ref); if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) { struct mb_cache_entry *ce; if (ea_block_cache) { ce = mb_cache_entry_get(ea_block_cache, hash, bh->b_blocknr); if (ce) { set_bit(MBE_REUSABLE_B, &ce->e_flags); mb_cache_entry_put(ea_block_cache, ce); } } } ext4_xattr_block_csum_set(inode, bh); /* * Beware of this ugliness: Releasing of xattr block references * from different inodes can race and so we have to protect * from a race where someone else frees the block (and releases * its journal_head) before we are done dirtying the buffer. In * nojournal mode this race is harmless and we actually cannot * call ext4_handle_dirty_metadata() with locked buffer as * that function can call sync_dirty_buffer() so for that case * we handle the dirtying after unlocking the buffer. */ if (ext4_handle_valid(handle)) error = ext4_handle_dirty_metadata(handle, inode, bh); unlock_buffer(bh); if (!ext4_handle_valid(handle)) error = ext4_handle_dirty_metadata(handle, inode, bh); if (IS_SYNC(inode)) ext4_handle_sync(handle); dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1)); ea_bdebug(bh, "refcount now=%d; releasing", le32_to_cpu(BHDR(bh)->h_refcount)); } out: ext4_std_error(inode->i_sb, error); return; } /* * Find the available free space for EAs. This also returns the total number of * bytes used by EA entries. */ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last, size_t *min_offs, void *base, int *total) { for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < *min_offs) *min_offs = offs; } if (total) *total += EXT4_XATTR_LEN(last->e_name_len); } return (*min_offs - ((void *)last - base) - sizeof(__u32)); } /* * Write the value of the EA in an inode. */ static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode, const void *buf, int bufsize) { struct buffer_head *bh = NULL; unsigned long block = 0; int blocksize = ea_inode->i_sb->s_blocksize; int max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits; int csize, wsize = 0; int ret = 0, ret2 = 0; int retries = 0; retry: while (ret >= 0 && ret < max_blocks) { struct ext4_map_blocks map; map.m_lblk = block += ret; map.m_len = max_blocks -= ret; ret = ext4_map_blocks(handle, ea_inode, &map, EXT4_GET_BLOCKS_CREATE); if (ret <= 0) { ext4_mark_inode_dirty(handle, ea_inode); if (ret == -ENOSPC && ext4_should_retry_alloc(ea_inode->i_sb, &retries)) { ret = 0; goto retry; } break; } } if (ret < 0) return ret; block = 0; while (wsize < bufsize) { brelse(bh); csize = (bufsize - wsize) > blocksize ? blocksize : bufsize - wsize; bh = ext4_getblk(handle, ea_inode, block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); if (!bh) { WARN_ON_ONCE(1); EXT4_ERROR_INODE(ea_inode, "ext4_getblk() return bh = NULL"); return -EFSCORRUPTED; } ret = ext4_journal_get_write_access(handle, ea_inode->i_sb, bh, EXT4_JTR_NONE); if (ret) goto out; memcpy(bh->b_data, buf, csize); /* * Zero out block tail to avoid writing uninitialized memory * to disk. */ if (csize < blocksize) memset(bh->b_data + csize, 0, blocksize - csize); set_buffer_uptodate(bh); ext4_handle_dirty_metadata(handle, ea_inode, bh); buf += csize; wsize += csize; block += 1; } inode_lock(ea_inode); i_size_write(ea_inode, wsize); ext4_update_i_disksize(ea_inode, wsize); inode_unlock(ea_inode); ret2 = ext4_mark_inode_dirty(handle, ea_inode); if (unlikely(ret2 && !ret)) ret = ret2; out: brelse(bh); return ret; } /* * Create an inode to store the value of a large EA. */ static struct inode *ext4_xattr_inode_create(handle_t *handle, struct inode *inode, u32 hash) { struct inode *ea_inode = NULL; uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) }; int err; if (inode->i_sb->s_root == NULL) { ext4_warning(inode->i_sb, "refuse to create EA inode when umounting"); WARN_ON(1); return ERR_PTR(-EINVAL); } /* * Let the next inode be the goal, so we try and allocate the EA inode * in the same group, or nearby one. */ ea_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode, S_IFREG | 0600, NULL, inode->i_ino + 1, owner, EXT4_EA_INODE_FL); if (!IS_ERR(ea_inode)) { ea_inode->i_op = &ext4_file_inode_operations; ea_inode->i_fop = &ext4_file_operations; ext4_set_aops(ea_inode); ext4_xattr_inode_set_class(ea_inode); unlock_new_inode(ea_inode); ext4_xattr_inode_set_ref(ea_inode, 1); ext4_xattr_inode_set_hash(ea_inode, hash); err = ext4_mark_inode_dirty(handle, ea_inode); if (!err) err = ext4_inode_attach_jinode(ea_inode); if (err) { if (ext4_xattr_inode_dec_ref(handle, ea_inode)) ext4_warning_inode(ea_inode, "cleanup dec ref error %d", err); iput(ea_inode); return ERR_PTR(err); } /* * Xattr inodes are shared therefore quota charging is performed * at a higher level. */ dquot_free_inode(ea_inode); dquot_drop(ea_inode); inode_lock(ea_inode); ea_inode->i_flags |= S_NOQUOTA; inode_unlock(ea_inode); } return ea_inode; } static struct inode * ext4_xattr_inode_cache_find(struct inode *inode, const void *value, size_t value_len, u32 hash) { struct inode *ea_inode; struct mb_cache_entry *ce; struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode); void *ea_data; if (!ea_inode_cache) return NULL; ce = mb_cache_entry_find_first(ea_inode_cache, hash); if (!ce) return NULL; WARN_ON_ONCE(ext4_handle_valid(journal_current_handle()) && !(current->flags & PF_MEMALLOC_NOFS)); ea_data = kvmalloc(value_len, GFP_NOFS); if (!ea_data) { mb_cache_entry_put(ea_inode_cache, ce); return NULL; } while (ce) { ea_inode = ext4_iget(inode->i_sb, ce->e_value, EXT4_IGET_EA_INODE); if (IS_ERR(ea_inode)) goto next_entry; ext4_xattr_inode_set_class(ea_inode); if (i_size_read(ea_inode) == value_len && !ext4_xattr_inode_read(ea_inode, ea_data, value_len) && !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data, value_len) && !memcmp(value, ea_data, value_len)) { mb_cache_entry_touch(ea_inode_cache, ce); mb_cache_entry_put(ea_inode_cache, ce); kvfree(ea_data); return ea_inode; } iput(ea_inode); next_entry: ce = mb_cache_entry_find_next(ea_inode_cache, ce); } kvfree(ea_data); return NULL; } /* * Add value of the EA in an inode. */ static struct inode *ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode, const void *value, size_t value_len) { struct inode *ea_inode; u32 hash; int err; /* Account inode & space to quota even if sharing... */ err = ext4_xattr_inode_alloc_quota(inode, value_len); if (err) return ERR_PTR(err); hash = ext4_xattr_inode_hash(EXT4_SB(inode->i_sb), value, value_len); ea_inode = ext4_xattr_inode_cache_find(inode, value, value_len, hash); if (ea_inode) { err = ext4_xattr_inode_inc_ref(handle, ea_inode); if (err) goto out_err; return ea_inode; } /* Create an inode for the EA value */ ea_inode = ext4_xattr_inode_create(handle, inode, hash); if (IS_ERR(ea_inode)) { ext4_xattr_inode_free_quota(inode, NULL, value_len); return ea_inode; } err = ext4_xattr_inode_write(handle, ea_inode, value, value_len); if (err) { if (ext4_xattr_inode_dec_ref(handle, ea_inode)) ext4_warning_inode(ea_inode, "cleanup dec ref error %d", err); goto out_err; } if (EA_INODE_CACHE(inode)) mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash, ea_inode->i_ino, true /* reusable */); return ea_inode; out_err: iput(ea_inode); ext4_xattr_inode_free_quota(inode, NULL, value_len); return ERR_PTR(err); } /* * Reserve min(block_size/8, 1024) bytes for xattr entries/names if ea_inode * feature is enabled. */ #define EXT4_XATTR_BLOCK_RESERVE(inode) min(i_blocksize(inode)/8, 1024U) static int ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s, handle_t *handle, struct inode *inode, struct inode *new_ea_inode, bool is_block) { struct ext4_xattr_entry *last, *next; struct ext4_xattr_entry *here = s->here; size_t min_offs = s->end - s->base, name_len = strlen(i->name); int in_inode = i->in_inode; struct inode *old_ea_inode = NULL; size_t old_size, new_size; int ret; /* Space used by old and new values. */ old_size = (!s->not_found && !here->e_value_inum) ? EXT4_XATTR_SIZE(le32_to_cpu(here->e_value_size)) : 0; new_size = (i->value && !in_inode) ? EXT4_XATTR_SIZE(i->value_len) : 0; /* * Optimization for the simple case when old and new values have the * same padded sizes. Not applicable if external inodes are involved. */ if (new_size && new_size == old_size) { size_t offs = le16_to_cpu(here->e_value_offs); void *val = s->base + offs; here->e_value_size = cpu_to_le32(i->value_len); if (i->value == EXT4_ZERO_XATTR_VALUE) { memset(val, 0, new_size); } else { memcpy(val, i->value, i->value_len); /* Clear padding bytes. */ memset(val + i->value_len, 0, new_size - i->value_len); } goto update_hash; } /* Compute min_offs and last. */ last = s->first; for (; !IS_LAST_ENTRY(last); last = next) { next = EXT4_XATTR_NEXT(last); if ((void *)next >= s->end) { EXT4_ERROR_INODE(inode, "corrupted xattr entries"); ret = -EFSCORRUPTED; goto out; } if (!last->e_value_inum && last->e_value_size) { size_t offs = le16_to_cpu(last->e_value_offs); if (offs < min_offs) min_offs = offs; } } /* Check whether we have enough space. */ if (i->value) { size_t free; free = min_offs - ((void *)last - s->base) - sizeof(__u32); if (!s->not_found) free += EXT4_XATTR_LEN(name_len) + old_size; if (free < EXT4_XATTR_LEN(name_len) + new_size) { ret = -ENOSPC; goto out; } /* * If storing the value in an external inode is an option, * reserve space for xattr entries/names in the external * attribute block so that a long value does not occupy the * whole space and prevent further entries being added. */ if (ext4_has_feature_ea_inode(inode->i_sb) && new_size && is_block && (min_offs + old_size - new_size) < EXT4_XATTR_BLOCK_RESERVE(inode)) { ret = -ENOSPC; goto out; } } /* * Getting access to old and new ea inodes is subject to failures. * Finish that work before doing any modifications to the xattr data. */ if (!s->not_found && here->e_value_inum) { ret = ext4_xattr_inode_iget(inode, le32_to_cpu(here->e_value_inum), le32_to_cpu(here->e_hash), &old_ea_inode); if (ret) { old_ea_inode = NULL; goto out; } /* We are ready to release ref count on the old_ea_inode. */ ret = ext4_xattr_inode_dec_ref(handle, old_ea_inode); if (ret) goto out; ext4_xattr_inode_free_quota(inode, old_ea_inode, le32_to_cpu(here->e_value_size)); } /* No failures allowed past this point. */ if (!s->not_found && here->e_value_size && !here->e_value_inum) { /* Remove the old value. */ void *first_val = s->base + min_offs; size_t offs = le16_to_cpu(here->e_value_offs); void *val = s->base + offs; memmove(first_val + old_size, first_val, val - first_val); memset(first_val, 0, old_size); min_offs += old_size; /* Adjust all value offsets. */ last = s->first; while (!IS_LAST_ENTRY(last)) { size_t o = le16_to_cpu(last->e_value_offs); if (!last->e_value_inum && last->e_value_size && o < offs) last->e_value_offs = cpu_to_le16(o + old_size); last = EXT4_XATTR_NEXT(last); } } if (!i->value) { /* Remove old name. */ size_t size = EXT4_XATTR_LEN(name_len); last = ENTRY((void *)last - size); memmove(here, (void *)here + size, (void *)last - (void *)here + sizeof(__u32)); memset(last, 0, size); /* * Update i_inline_off - moved ibody region might contain * system.data attribute. Handling a failure here won't * cause other complications for setting an xattr. */ if (!is_block && ext4_has_inline_data(inode)) { ret = ext4_find_inline_data_nolock(inode); if (ret) { ext4_warning_inode(inode, "unable to update i_inline_off"); goto out; } } } else if (s->not_found) { /* Insert new name. */ size_t size = EXT4_XATTR_LEN(name_len); size_t rest = (void *)last - (void *)here + sizeof(__u32); memmove((void *)here + size, here, rest); memset(here, 0, size); here->e_name_index = i->name_index; here->e_name_len = name_len; memcpy(here->e_name, i->name, name_len); } else { /* This is an update, reset value info. */ here->e_value_inum = 0; here->e_value_offs = 0; here->e_value_size = 0; } if (i->value) { /* Insert new value. */ if (in_inode) { here->e_value_inum = cpu_to_le32(new_ea_inode->i_ino); } else if (i->value_len) { void *val = s->base + min_offs - new_size; here->e_value_offs = cpu_to_le16(min_offs - new_size); if (i->value == EXT4_ZERO_XATTR_VALUE) { memset(val, 0, new_size); } else { memcpy(val, i->value, i->value_len); /* Clear padding bytes. */ memset(val + i->value_len, 0, new_size - i->value_len); } } here->e_value_size = cpu_to_le32(i->value_len); } update_hash: if (i->value) { __le32 hash = 0; /* Entry hash calculation. */ if (in_inode) { __le32 crc32c_hash; /* * Feed crc32c hash instead of the raw value for entry * hash calculation. This is to avoid walking * potentially long value buffer again. */ crc32c_hash = cpu_to_le32( ext4_xattr_inode_get_hash(new_ea_inode)); hash = ext4_xattr_hash_entry(here->e_name, here->e_name_len, &crc32c_hash, 1); } else if (is_block) { __le32 *value = s->base + le16_to_cpu( here->e_value_offs); hash = ext4_xattr_hash_entry(here->e_name, here->e_name_len, value, new_size >> 2); } here->e_hash = hash; } if (is_block) ext4_xattr_rehash((struct ext4_xattr_header *)s->base); ret = 0; out: iput(old_ea_inode); return ret; } struct ext4_xattr_block_find { struct ext4_xattr_search s; struct buffer_head *bh; }; static int ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_block_find *bs) { struct super_block *sb = inode->i_sb; int error; ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld", i->name_index, i->name, i->value, (long)i->value_len); if (EXT4_I(inode)->i_file_acl) { /* The inode already has an extended attribute block. */ bs->bh = ext4_sb_bread(sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bs->bh)) { error = PTR_ERR(bs->bh); bs->bh = NULL; return error; } ea_bdebug(bs->bh, "b_count=%d, refcount=%d", atomic_read(&(bs->bh->b_count)), le32_to_cpu(BHDR(bs->bh)->h_refcount)); error = ext4_xattr_check_block(inode, bs->bh); if (error) return error; /* Find the named attribute. */ bs->s.base = BHDR(bs->bh); bs->s.first = BFIRST(bs->bh); bs->s.end = bs->bh->b_data + bs->bh->b_size; bs->s.here = bs->s.first; error = xattr_find_entry(inode, &bs->s.here, bs->s.end, i->name_index, i->name, 1); if (error && error != -ENODATA) return error; bs->s.not_found = error; } return 0; } static int ext4_xattr_block_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_block_find *bs) { struct super_block *sb = inode->i_sb; struct buffer_head *new_bh = NULL; struct ext4_xattr_search s_copy = bs->s; struct ext4_xattr_search *s = &s_copy; struct mb_cache_entry *ce = NULL; int error = 0; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); struct inode *ea_inode = NULL, *tmp_inode; size_t old_ea_inode_quota = 0; unsigned int ea_ino; #define header(x) ((struct ext4_xattr_header *)(x)) /* If we need EA inode, prepare it before locking the buffer */ if (i->value && i->in_inode) { WARN_ON_ONCE(!i->value_len); ea_inode = ext4_xattr_inode_lookup_create(handle, inode, i->value, i->value_len); if (IS_ERR(ea_inode)) { error = PTR_ERR(ea_inode); ea_inode = NULL; goto cleanup; } } if (s->base) { int offset = (char *)s->here - bs->bh->b_data; BUFFER_TRACE(bs->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, sb, bs->bh, EXT4_JTR_NONE); if (error) goto cleanup; lock_buffer(bs->bh); if (header(s->base)->h_refcount == cpu_to_le32(1)) { __u32 hash = le32_to_cpu(BHDR(bs->bh)->h_hash); /* * This must happen under buffer lock for * ext4_xattr_block_set() to reliably detect modified * block */ if (ea_block_cache) { struct mb_cache_entry *oe; oe = mb_cache_entry_delete_or_get(ea_block_cache, hash, bs->bh->b_blocknr); if (oe) { /* * Xattr block is getting reused. Leave * it alone. */ mb_cache_entry_put(ea_block_cache, oe); goto clone_block; } } ea_bdebug(bs->bh, "modifying in-place"); error = ext4_xattr_set_entry(i, s, handle, inode, ea_inode, true /* is_block */); ext4_xattr_block_csum_set(inode, bs->bh); unlock_buffer(bs->bh); if (error == -EFSCORRUPTED) goto bad_block; if (!error) error = ext4_handle_dirty_metadata(handle, inode, bs->bh); if (error) goto cleanup; goto inserted; } clone_block: unlock_buffer(bs->bh); ea_bdebug(bs->bh, "cloning"); s->base = kmemdup(BHDR(bs->bh), bs->bh->b_size, GFP_NOFS); error = -ENOMEM; if (s->base == NULL) goto cleanup; s->first = ENTRY(header(s->base)+1); header(s->base)->h_refcount = cpu_to_le32(1); s->here = ENTRY(s->base + offset); s->end = s->base + bs->bh->b_size; /* * If existing entry points to an xattr inode, we need * to prevent ext4_xattr_set_entry() from decrementing * ref count on it because the reference belongs to the * original block. In this case, make the entry look * like it has an empty value. */ if (!s->not_found && s->here->e_value_inum) { ea_ino = le32_to_cpu(s->here->e_value_inum); error = ext4_xattr_inode_iget(inode, ea_ino, le32_to_cpu(s->here->e_hash), &tmp_inode); if (error) goto cleanup; if (!ext4_test_inode_state(tmp_inode, EXT4_STATE_LUSTRE_EA_INODE)) { /* * Defer quota free call for previous * inode until success is guaranteed. */ old_ea_inode_quota = le32_to_cpu( s->here->e_value_size); } iput(tmp_inode); s->here->e_value_inum = 0; s->here->e_value_size = 0; } } else { /* Allocate a buffer where we construct the new block. */ s->base = kzalloc(sb->s_blocksize, GFP_NOFS); error = -ENOMEM; if (s->base == NULL) goto cleanup; header(s->base)->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); header(s->base)->h_blocks = cpu_to_le32(1); header(s->base)->h_refcount = cpu_to_le32(1); s->first = ENTRY(header(s->base)+1); s->here = ENTRY(header(s->base)+1); s->end = s->base + sb->s_blocksize; } error = ext4_xattr_set_entry(i, s, handle, inode, ea_inode, true /* is_block */); if (error == -EFSCORRUPTED) goto bad_block; if (error) goto cleanup; inserted: if (!IS_LAST_ENTRY(s->first)) { new_bh = ext4_xattr_block_cache_find(inode, header(s->base), &ce); if (IS_ERR(new_bh)) { error = PTR_ERR(new_bh); new_bh = NULL; goto cleanup; } if (new_bh) { /* We found an identical block in the cache. */ if (new_bh == bs->bh) ea_bdebug(new_bh, "keeping"); else { u32 ref; #ifdef EXT4_XATTR_DEBUG WARN_ON_ONCE(dquot_initialize_needed(inode)); #endif /* The old block is released after updating the inode. */ error = dquot_alloc_block(inode, EXT4_C2B(EXT4_SB(sb), 1)); if (error) goto cleanup; BUFFER_TRACE(new_bh, "get_write_access"); error = ext4_journal_get_write_access( handle, sb, new_bh, EXT4_JTR_NONE); if (error) goto cleanup_dquot; lock_buffer(new_bh); /* * We have to be careful about races with * adding references to xattr block. Once we * hold buffer lock xattr block's state is * stable so we can check the additional * reference fits. */ ref = le32_to_cpu(BHDR(new_bh)->h_refcount) + 1; if (ref > EXT4_XATTR_REFCOUNT_MAX) { /* * Undo everything and check mbcache * again. */ unlock_buffer(new_bh); dquot_free_block(inode, EXT4_C2B(EXT4_SB(sb), 1)); brelse(new_bh); mb_cache_entry_put(ea_block_cache, ce); ce = NULL; new_bh = NULL; goto inserted; } BHDR(new_bh)->h_refcount = cpu_to_le32(ref); if (ref == EXT4_XATTR_REFCOUNT_MAX) clear_bit(MBE_REUSABLE_B, &ce->e_flags); ea_bdebug(new_bh, "reusing; refcount now=%d", ref); ext4_xattr_block_csum_set(inode, new_bh); unlock_buffer(new_bh); error = ext4_handle_dirty_metadata(handle, inode, new_bh); if (error) goto cleanup_dquot; } mb_cache_entry_touch(ea_block_cache, ce); mb_cache_entry_put(ea_block_cache, ce); ce = NULL; } else if (bs->bh && s->base == bs->bh->b_data) { /* We were modifying this block in-place. */ ea_bdebug(bs->bh, "keeping this block"); ext4_xattr_block_cache_insert(ea_block_cache, bs->bh); new_bh = bs->bh; get_bh(new_bh); } else { /* We need to allocate a new block */ ext4_fsblk_t goal, block; #ifdef EXT4_XATTR_DEBUG WARN_ON_ONCE(dquot_initialize_needed(inode)); #endif goal = ext4_group_first_block_no(sb, EXT4_I(inode)->i_block_group); block = ext4_new_meta_blocks(handle, inode, goal, 0, NULL, &error); if (error) goto cleanup; ea_idebug(inode, "creating block %llu", (unsigned long long)block); new_bh = sb_getblk(sb, block); if (unlikely(!new_bh)) { error = -ENOMEM; getblk_failed: ext4_free_blocks(handle, inode, NULL, block, 1, EXT4_FREE_BLOCKS_METADATA); goto cleanup; } error = ext4_xattr_inode_inc_ref_all(handle, inode, ENTRY(header(s->base)+1)); if (error) goto getblk_failed; if (ea_inode) { /* Drop the extra ref on ea_inode. */ error = ext4_xattr_inode_dec_ref(handle, ea_inode); if (error) ext4_warning_inode(ea_inode, "dec ref error=%d", error); iput(ea_inode); ea_inode = NULL; } lock_buffer(new_bh); error = ext4_journal_get_create_access(handle, sb, new_bh, EXT4_JTR_NONE); if (error) { unlock_buffer(new_bh); error = -EIO; goto getblk_failed; } memcpy(new_bh->b_data, s->base, new_bh->b_size); ext4_xattr_block_csum_set(inode, new_bh); set_buffer_uptodate(new_bh); unlock_buffer(new_bh); ext4_xattr_block_cache_insert(ea_block_cache, new_bh); error = ext4_handle_dirty_metadata(handle, inode, new_bh); if (error) goto cleanup; } } if (old_ea_inode_quota) ext4_xattr_inode_free_quota(inode, NULL, old_ea_inode_quota); /* Update the inode. */ EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0; /* Drop the previous xattr block. */ if (bs->bh && bs->bh != new_bh) { struct ext4_xattr_inode_array *ea_inode_array = NULL; ext4_xattr_release_block(handle, inode, bs->bh, &ea_inode_array, 0 /* extra_credits */); ext4_xattr_inode_array_free(ea_inode_array); } error = 0; cleanup: if (ea_inode) { if (error) { int error2; error2 = ext4_xattr_inode_dec_ref(handle, ea_inode); if (error2) ext4_warning_inode(ea_inode, "dec ref error=%d", error2); ext4_xattr_inode_free_quota(inode, ea_inode, i_size_read(ea_inode)); } iput(ea_inode); } if (ce) mb_cache_entry_put(ea_block_cache, ce); brelse(new_bh); if (!(bs->bh && s->base == bs->bh->b_data)) kfree(s->base); return error; cleanup_dquot: dquot_free_block(inode, EXT4_C2B(EXT4_SB(sb), 1)); goto cleanup; bad_block: EXT4_ERROR_INODE(inode, "bad block %llu", EXT4_I(inode)->i_file_acl); goto cleanup; #undef header } int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { struct ext4_xattr_ibody_header *header; struct ext4_inode *raw_inode; int error; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return 0; raw_inode = ext4_raw_inode(&is->iloc); header = IHDR(inode, raw_inode); is->s.base = is->s.first = IFIRST(header); is->s.here = is->s.first; is->s.end = ITAIL(inode, raw_inode); if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { /* Find the named attribute. */ error = xattr_find_entry(inode, &is->s.here, is->s.end, i->name_index, i->name, 0); if (error && error != -ENODATA) return error; is->s.not_found = error; } return 0; } int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode, struct ext4_xattr_info *i, struct ext4_xattr_ibody_find *is) { struct ext4_xattr_ibody_header *header; struct ext4_xattr_search *s = &is->s; struct inode *ea_inode = NULL; int error; if (!EXT4_INODE_HAS_XATTR_SPACE(inode)) return -ENOSPC; /* If we need EA inode, prepare it before locking the buffer */ if (i->value && i->in_inode) { WARN_ON_ONCE(!i->value_len); ea_inode = ext4_xattr_inode_lookup_create(handle, inode, i->value, i->value_len); if (IS_ERR(ea_inode)) return PTR_ERR(ea_inode); } error = ext4_xattr_set_entry(i, s, handle, inode, ea_inode, false /* is_block */); if (error) { if (ea_inode) { int error2; error2 = ext4_xattr_inode_dec_ref(handle, ea_inode); if (error2) ext4_warning_inode(ea_inode, "dec ref error=%d", error2); ext4_xattr_inode_free_quota(inode, ea_inode, i_size_read(ea_inode)); iput(ea_inode); } return error; } header = IHDR(inode, ext4_raw_inode(&is->iloc)); if (!IS_LAST_ENTRY(s->first)) { header->h_magic = cpu_to_le32(EXT4_XATTR_MAGIC); ext4_set_inode_state(inode, EXT4_STATE_XATTR); } else { header->h_magic = cpu_to_le32(0); ext4_clear_inode_state(inode, EXT4_STATE_XATTR); } iput(ea_inode); return 0; } static int ext4_xattr_value_same(struct ext4_xattr_search *s, struct ext4_xattr_info *i) { void *value; /* When e_value_inum is set the value is stored externally. */ if (s->here->e_value_inum) return 0; if (le32_to_cpu(s->here->e_value_size) != i->value_len) return 0; value = ((void *)s->base) + le16_to_cpu(s->here->e_value_offs); return !memcmp(value, i->value, i->value_len); } static struct buffer_head *ext4_xattr_get_block(struct inode *inode) { struct buffer_head *bh; int error; if (!EXT4_I(inode)->i_file_acl) return NULL; bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) return bh; error = ext4_xattr_check_block(inode, bh); if (error) { brelse(bh); return ERR_PTR(error); } return bh; } /* * ext4_xattr_set_handle() * * Create, replace or remove an extended attribute for this inode. Value * is NULL to remove an existing extended attribute, and non-NULL to * either replace an existing extended attribute, or create a new extended * attribute. The flags XATTR_REPLACE and XATTR_CREATE * specify that an extended attribute must exist and must not exist * previous to the call, respectively. * * Returns 0, or a negative error number on failure. */ int ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index, const char *name, const void *value, size_t value_len, int flags) { struct ext4_xattr_info i = { .name_index = name_index, .name = name, .value = value, .value_len = value_len, .in_inode = 0, }; struct ext4_xattr_ibody_find is = { .s = { .not_found = -ENODATA, }, }; struct ext4_xattr_block_find bs = { .s = { .not_found = -ENODATA, }, }; int no_expand; int error; if (!name) return -EINVAL; if (strlen(name) > 255) return -ERANGE; ext4_write_lock_xattr(inode, &no_expand); /* Check journal credits under write lock. */ if (ext4_handle_valid(handle)) { struct buffer_head *bh; int credits; bh = ext4_xattr_get_block(inode); if (IS_ERR(bh)) { error = PTR_ERR(bh); goto cleanup; } credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh, value_len, flags & XATTR_CREATE); brelse(bh); if (jbd2_handle_buffer_credits(handle) < credits) { error = -ENOSPC; goto cleanup; } WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } error = ext4_reserve_inode_write(handle, inode, &is.iloc); if (error) goto cleanup; if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) { struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc); memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); ext4_clear_inode_state(inode, EXT4_STATE_NEW); } error = ext4_xattr_ibody_find(inode, &i, &is); if (error) goto cleanup; if (is.s.not_found) error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; if (is.s.not_found && bs.s.not_found) { error = -ENODATA; if (flags & XATTR_REPLACE) goto cleanup; error = 0; if (!value) goto cleanup; } else { error = -EEXIST; if (flags & XATTR_CREATE) goto cleanup; } if (!value) { if (!is.s.not_found) error = ext4_xattr_ibody_set(handle, inode, &i, &is); else if (!bs.s.not_found) error = ext4_xattr_block_set(handle, inode, &i, &bs); } else { error = 0; /* Xattr value did not change? Save us some work and bail out */ if (!is.s.not_found && ext4_xattr_value_same(&is.s, &i)) goto cleanup; if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i)) goto cleanup; if (ext4_has_feature_ea_inode(inode->i_sb) && (EXT4_XATTR_SIZE(i.value_len) > EXT4_XATTR_MIN_LARGE_EA_SIZE(inode->i_sb->s_blocksize))) i.in_inode = 1; retry_inode: error = ext4_xattr_ibody_set(handle, inode, &i, &is); if (!error && !bs.s.not_found) { i.value = NULL; error = ext4_xattr_block_set(handle, inode, &i, &bs); } else if (error == -ENOSPC) { if (EXT4_I(inode)->i_file_acl && !bs.s.base) { brelse(bs.bh); bs.bh = NULL; error = ext4_xattr_block_find(inode, &i, &bs); if (error) goto cleanup; } error = ext4_xattr_block_set(handle, inode, &i, &bs); if (!error && !is.s.not_found) { i.value = NULL; error = ext4_xattr_ibody_set(handle, inode, &i, &is); } else if (error == -ENOSPC) { /* * Xattr does not fit in the block, store at * external inode if possible. */ if (ext4_has_feature_ea_inode(inode->i_sb) && i.value_len && !i.in_inode) { i.in_inode = 1; goto retry_inode; } } } } if (!error) { ext4_xattr_update_super_block(handle, inode->i_sb); inode_set_ctime_current(inode); inode_inc_iversion(inode); if (!value) no_expand = 0; error = ext4_mark_iloc_dirty(handle, inode, &is.iloc); /* * The bh is consumed by ext4_mark_iloc_dirty, even with * error != 0. */ is.iloc.bh = NULL; if (IS_SYNC(inode)) ext4_handle_sync(handle); } ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); cleanup: brelse(is.iloc.bh); brelse(bs.bh); ext4_write_unlock_xattr(inode, &no_expand); return error; } int ext4_xattr_set_credits(struct inode *inode, size_t value_len, bool is_create, int *credits) { struct buffer_head *bh; int err; *credits = 0; if (!EXT4_SB(inode->i_sb)->s_journal) return 0; down_read(&EXT4_I(inode)->xattr_sem); bh = ext4_xattr_get_block(inode); if (IS_ERR(bh)) { err = PTR_ERR(bh); } else { *credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh, value_len, is_create); brelse(bh); err = 0; } up_read(&EXT4_I(inode)->xattr_sem); return err; } /* * ext4_xattr_set() * * Like ext4_xattr_set_handle, but start from an inode. This extended * attribute modification is a filesystem transaction by itself. * * Returns 0, or a negative error number on failure. */ int ext4_xattr_set(struct inode *inode, int name_index, const char *name, const void *value, size_t value_len, int flags) { handle_t *handle; struct super_block *sb = inode->i_sb; int error, retries = 0; int credits; error = dquot_initialize(inode); if (error) return error; retry: error = ext4_xattr_set_credits(inode, value_len, flags & XATTR_CREATE, &credits); if (error) return error; handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits); if (IS_ERR(handle)) { error = PTR_ERR(handle); } else { int error2; error = ext4_xattr_set_handle(handle, inode, name_index, name, value, value_len, flags); ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); error2 = ext4_journal_stop(handle); if (error == -ENOSPC && ext4_should_retry_alloc(sb, &retries)) goto retry; if (error == 0) error = error2; } return error; } /* * Shift the EA entries in the inode to create space for the increased * i_extra_isize. */ static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry, int value_offs_shift, void *to, void *from, size_t n) { struct ext4_xattr_entry *last = entry; int new_offs; /* We always shift xattr headers further thus offsets get lower */ BUG_ON(value_offs_shift > 0); /* Adjust the value offsets of the entries */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { if (!last->e_value_inum && last->e_value_size) { new_offs = le16_to_cpu(last->e_value_offs) + value_offs_shift; last->e_value_offs = cpu_to_le16(new_offs); } } /* Shift the entries by n bytes */ memmove(to, from, n); } /* * Move xattr pointed to by 'entry' from inode into external xattr block */ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode, struct ext4_inode *raw_inode, struct ext4_xattr_entry *entry) { struct ext4_xattr_ibody_find *is = NULL; struct ext4_xattr_block_find *bs = NULL; char *buffer = NULL, *b_entry_name = NULL; size_t value_size = le32_to_cpu(entry->e_value_size); struct ext4_xattr_info i = { .value = NULL, .value_len = 0, .name_index = entry->e_name_index, .in_inode = !!entry->e_value_inum, }; struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); int needs_kvfree = 0; int error; is = kzalloc_obj(struct ext4_xattr_ibody_find, GFP_NOFS); bs = kzalloc_obj(struct ext4_xattr_block_find, GFP_NOFS); b_entry_name = kmalloc(entry->e_name_len + 1, GFP_NOFS); if (!is || !bs || !b_entry_name) { error = -ENOMEM; goto out; } is->s.not_found = -ENODATA; bs->s.not_found = -ENODATA; is->iloc.bh = NULL; bs->bh = NULL; /* Save the entry name and the entry value */ if (entry->e_value_inum) { buffer = kvmalloc(value_size, GFP_NOFS); if (!buffer) { error = -ENOMEM; goto out; } needs_kvfree = 1; error = ext4_xattr_inode_get(inode, entry, buffer, value_size); if (error) goto out; } else { size_t value_offs = le16_to_cpu(entry->e_value_offs); buffer = (void *)IFIRST(header) + value_offs; } memcpy(b_entry_name, entry->e_name, entry->e_name_len); b_entry_name[entry->e_name_len] = '\0'; i.name = b_entry_name; error = ext4_get_inode_loc(inode, &is->iloc); if (error) goto out; error = ext4_xattr_ibody_find(inode, &i, is); if (error) goto out; i.value = buffer; i.value_len = value_size; error = ext4_xattr_block_find(inode, &i, bs); if (error) goto out; /* Move ea entry from the inode into the block */ error = ext4_xattr_block_set(handle, inode, &i, bs); if (error) goto out; /* Remove the chosen entry from the inode */ i.value = NULL; i.value_len = 0; error = ext4_xattr_ibody_set(handle, inode, &i, is); out: kfree(b_entry_name); if (needs_kvfree && buffer) kvfree(buffer); if (is) brelse(is->iloc.bh); if (bs) brelse(bs->bh); kfree(is); kfree(bs); return error; } static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode, struct ext4_inode *raw_inode, int isize_diff, size_t ifree, size_t bfree, int *total_ino) { struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode); struct ext4_xattr_entry *small_entry; struct ext4_xattr_entry *entry; struct ext4_xattr_entry *last; unsigned int entry_size; /* EA entry size */ unsigned int total_size; /* EA entry size + value size */ unsigned int min_total_size; int error; while (isize_diff > ifree) { entry = NULL; small_entry = NULL; min_total_size = ~0U; last = IFIRST(header); /* Find the entry best suited to be pushed into EA block */ for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) { /* never move system.data out of the inode */ if ((last->e_name_len == 4) && (last->e_name_index == EXT4_XATTR_INDEX_SYSTEM) && !memcmp(last->e_name, "data", 4)) continue; total_size = EXT4_XATTR_LEN(last->e_name_len); if (!last->e_value_inum) total_size += EXT4_XATTR_SIZE( le32_to_cpu(last->e_value_size)); if (total_size <= bfree && total_size < min_total_size) { if (total_size + ifree < isize_diff) { small_entry = last; } else { entry = last; min_total_size = total_size; } } } if (entry == NULL) { if (small_entry == NULL) return -ENOSPC; entry = small_entry; } entry_size = EXT4_XATTR_LEN(entry->e_name_len); total_size = entry_size; if (!entry->e_value_inum) total_size += EXT4_XATTR_SIZE( le32_to_cpu(entry->e_value_size)); error = ext4_xattr_move_to_block(handle, inode, raw_inode, entry); if (error) return error; *total_ino -= entry_size; ifree += total_size; bfree -= total_size; } return 0; } /* * Expand an inode by new_extra_isize bytes when EAs are present. * Returns 0 on success or negative error number on failure. */ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize, struct ext4_inode *raw_inode, handle_t *handle) { struct ext4_xattr_ibody_header *header; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); static unsigned int mnt_count; size_t min_offs; size_t ifree, bfree; int total_ino; void *base, *end; int error = 0, tried_min_extra_isize = 0; int s_min_extra_isize = le16_to_cpu(sbi->s_es->s_min_extra_isize); int isize_diff; /* How much do we need to grow i_extra_isize */ retry: isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize; if (EXT4_I(inode)->i_extra_isize >= new_extra_isize) return 0; header = IHDR(inode, raw_inode); /* * Check if enough free space is available in the inode to shift the * entries ahead by new_extra_isize. */ base = IFIRST(header); end = ITAIL(inode, raw_inode); min_offs = end - base; total_ino = sizeof(struct ext4_xattr_ibody_header) + sizeof(u32); ifree = ext4_xattr_free_space(base, &min_offs, base, &total_ino); if (ifree >= isize_diff) goto shift; /* * Enough free space isn't available in the inode, check if * EA block can hold new_extra_isize bytes. */ if (EXT4_I(inode)->i_file_acl) { struct buffer_head *bh; bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { error = PTR_ERR(bh); goto cleanup; } error = ext4_xattr_check_block(inode, bh); if (error) { brelse(bh); goto cleanup; } base = BHDR(bh); end = bh->b_data + bh->b_size; min_offs = end - base; bfree = ext4_xattr_free_space(BFIRST(bh), &min_offs, base, NULL); brelse(bh); if (bfree + ifree < isize_diff) { if (!tried_min_extra_isize && s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; goto retry; } error = -ENOSPC; goto cleanup; } } else { bfree = inode->i_sb->s_blocksize; } error = ext4_xattr_make_inode_space(handle, inode, raw_inode, isize_diff, ifree, bfree, &total_ino); if (error) { if (error == -ENOSPC && !tried_min_extra_isize && s_min_extra_isize) { tried_min_extra_isize++; new_extra_isize = s_min_extra_isize; goto retry; } goto cleanup; } shift: /* Adjust the offsets and shift the remaining entries ahead */ ext4_xattr_shift_entries(IFIRST(header), EXT4_I(inode)->i_extra_isize - new_extra_isize, (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + new_extra_isize, (void *)header, total_ino); EXT4_I(inode)->i_extra_isize = new_extra_isize; if (ext4_has_inline_data(inode)) error = ext4_find_inline_data_nolock(inode); cleanup: if (error && (mnt_count != le16_to_cpu(sbi->s_es->s_mnt_count))) { ext4_warning(inode->i_sb, "Unable to expand inode %llu. Delete some EAs or run e2fsck.", inode->i_ino); mnt_count = le16_to_cpu(sbi->s_es->s_mnt_count); } return error; } #define EIA_INCR 16 /* must be 2^n */ #define EIA_MASK (EIA_INCR - 1) /* Add the large xattr @inode into @ea_inode_array for deferred iput(). * If @ea_inode_array is new or full it will be grown and the old * contents copied over. */ static int ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array, struct inode *inode) { if (*ea_inode_array == NULL) { /* * Start with 15 inodes, so it fits into a power-of-two size. */ (*ea_inode_array) = kmalloc_flex(**ea_inode_array, inodes, EIA_MASK, GFP_NOFS); if (*ea_inode_array == NULL) return -ENOMEM; (*ea_inode_array)->count = 0; } else if (((*ea_inode_array)->count & EIA_MASK) == EIA_MASK) { /* expand the array once all 15 + n * 16 slots are full */ struct ext4_xattr_inode_array *new_array = NULL; new_array = kmalloc_flex(**ea_inode_array, inodes, (*ea_inode_array)->count + EIA_INCR, GFP_NOFS); if (new_array == NULL) return -ENOMEM; memcpy(new_array, *ea_inode_array, struct_size(*ea_inode_array, inodes, (*ea_inode_array)->count)); kfree(*ea_inode_array); *ea_inode_array = new_array; } (*ea_inode_array)->count++; (*ea_inode_array)->inodes[(*ea_inode_array)->count - 1] = inode; return 0; } /* * ext4_xattr_delete_inode() * * Free extended attribute resources associated with this inode. Traverse * all entries and decrement reference on any xattr inodes associated with this * inode. This is called immediately before an inode is freed. We have exclusive * access to the inode. If an orphan inode is deleted it will also release its * references on xattr block and xattr inodes. */ int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode, struct ext4_xattr_inode_array **ea_inode_array, int extra_credits) { struct buffer_head *bh = NULL; struct ext4_xattr_ibody_header *header; struct ext4_iloc iloc = { .bh = NULL }; struct ext4_xattr_entry *entry; struct inode *ea_inode; int error; error = ext4_journal_ensure_credits(handle, extra_credits, ext4_free_metadata_revoke_credits(inode->i_sb, 1)); if (error < 0) { EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error); goto cleanup; } if (ext4_has_feature_ea_inode(inode->i_sb) && ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { error = ext4_get_inode_loc(inode, &iloc); if (error) { EXT4_ERROR_INODE(inode, "inode loc (error %d)", error); goto cleanup; } error = ext4_journal_get_write_access(handle, inode->i_sb, iloc.bh, EXT4_JTR_NONE); if (error) { EXT4_ERROR_INODE(inode, "write access (error %d)", error); goto cleanup; } header = IHDR(inode, ext4_raw_inode(&iloc)); if (header->h_magic == cpu_to_le32(EXT4_XATTR_MAGIC)) ext4_xattr_inode_dec_ref_all(handle, inode, iloc.bh, IFIRST(header), false /* block_csum */, ea_inode_array, extra_credits, false /* skip_quota */); } if (EXT4_I(inode)->i_file_acl) { bh = ext4_sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl, REQ_PRIO); if (IS_ERR(bh)) { error = PTR_ERR(bh); if (error == -EIO) { EXT4_ERROR_INODE_ERR(inode, EIO, "block %llu read error", EXT4_I(inode)->i_file_acl); } bh = NULL; goto cleanup; } error = ext4_xattr_check_block(inode, bh); if (error) goto cleanup; if (ext4_has_feature_ea_inode(inode->i_sb)) { for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) { if (!entry->e_value_inum) continue; error = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum), le32_to_cpu(entry->e_hash), &ea_inode); if (error) continue; ext4_xattr_inode_free_quota(inode, ea_inode, le32_to_cpu(entry->e_value_size)); iput(ea_inode); } } ext4_xattr_release_block(handle, inode, bh, ea_inode_array, extra_credits); /* * Update i_file_acl value in the same transaction that releases * block. */ EXT4_I(inode)->i_file_acl = 0; error = ext4_mark_inode_dirty(handle, inode); if (error) { EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)", error); goto cleanup; } ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR, handle); } error = 0; cleanup: brelse(iloc.bh); brelse(bh); return error; } void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *ea_inode_array) { int idx; if (ea_inode_array == NULL) return; for (idx = 0; idx < ea_inode_array->count; ++idx) iput(ea_inode_array->inodes[idx]); kfree(ea_inode_array); } /* * ext4_xattr_block_cache_insert() * * Create a new entry in the extended attribute block cache, and insert * it unless such an entry is already in the cache. */ static void ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache, struct buffer_head *bh) { struct ext4_xattr_header *header = BHDR(bh); __u32 hash = le32_to_cpu(header->h_hash); int reusable = le32_to_cpu(header->h_refcount) < EXT4_XATTR_REFCOUNT_MAX; int error; if (!ea_block_cache) return; error = mb_cache_entry_create(ea_block_cache, GFP_NOFS, hash, bh->b_blocknr, reusable); if (error) { if (error == -EBUSY) ea_bdebug(bh, "already in cache"); } else ea_bdebug(bh, "inserting [%x]", (int)hash); } /* * ext4_xattr_cmp() * * Compare two extended attribute blocks for equality. * * Returns 0 if the blocks are equal, 1 if they differ. */ static int ext4_xattr_cmp(struct ext4_xattr_header *header1, struct ext4_xattr_header *header2) { struct ext4_xattr_entry *entry1, *entry2; entry1 = ENTRY(header1+1); entry2 = ENTRY(header2+1); while (!IS_LAST_ENTRY(entry1)) { if (IS_LAST_ENTRY(entry2)) return 1; if (entry1->e_hash != entry2->e_hash || entry1->e_name_index != entry2->e_name_index || entry1->e_name_len != entry2->e_name_len || entry1->e_value_size != entry2->e_value_size || entry1->e_value_inum != entry2->e_value_inum || memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len)) return 1; if (!entry1->e_value_inum && memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs), (char *)header2 + le16_to_cpu(entry2->e_value_offs), le32_to_cpu(entry1->e_value_size))) return 1; entry1 = EXT4_XATTR_NEXT(entry1); entry2 = EXT4_XATTR_NEXT(entry2); } if (!IS_LAST_ENTRY(entry2)) return 1; return 0; } /* * ext4_xattr_block_cache_find() * * Find an identical extended attribute block. * * Returns a pointer to the block found, or NULL if such a block was not * found, or an error pointer if an error occurred while reading ea block. */ static struct buffer_head * ext4_xattr_block_cache_find(struct inode *inode, struct ext4_xattr_header *header, struct mb_cache_entry **pce) { __u32 hash = le32_to_cpu(header->h_hash); struct mb_cache_entry *ce; struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode); if (!ea_block_cache) return NULL; if (!header->h_hash) return NULL; /* never share */ ea_idebug(inode, "looking for cached blocks [%x]", (int)hash); ce = mb_cache_entry_find_first(ea_block_cache, hash); while (ce) { struct buffer_head *bh; bh = ext4_sb_bread(inode->i_sb, ce->e_value, REQ_PRIO); if (IS_ERR(bh)) { if (PTR_ERR(bh) != -ENOMEM) EXT4_ERROR_INODE(inode, "block %lu read error", (unsigned long)ce->e_value); mb_cache_entry_put(ea_block_cache, ce); return bh; } else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) { *pce = ce; return bh; } brelse(bh); ce = mb_cache_entry_find_next(ea_block_cache, ce); } return NULL; } #define NAME_HASH_SHIFT 5 #define VALUE_HASH_SHIFT 16 /* * ext4_xattr_hash_entry() * * Compute the hash of an extended attribute. */ static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value, size_t value_count) { __u32 hash = 0; while (name_len--) { hash = (hash << NAME_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ (unsigned char)*name++; } while (value_count--) { hash = (hash << VALUE_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ le32_to_cpu(*value++); } return cpu_to_le32(hash); } /* * ext4_xattr_hash_entry_signed() * * Compute the hash of an extended attribute incorrectly. */ static __le32 ext4_xattr_hash_entry_signed(char *name, size_t name_len, __le32 *value, size_t value_count) { __u32 hash = 0; while (name_len--) { hash = (hash << NAME_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^ (signed char)*name++; } while (value_count--) { hash = (hash << VALUE_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^ le32_to_cpu(*value++); } return cpu_to_le32(hash); } #undef NAME_HASH_SHIFT #undef VALUE_HASH_SHIFT #define BLOCK_HASH_SHIFT 16 /* * ext4_xattr_rehash() * * Re-compute the extended attribute hash value after an entry has changed. */ static void ext4_xattr_rehash(struct ext4_xattr_header *header) { struct ext4_xattr_entry *here; __u32 hash = 0; here = ENTRY(header+1); while (!IS_LAST_ENTRY(here)) { if (!here->e_hash) { /* Block is not shared if an entry's hash value == 0 */ hash = 0; break; } hash = (hash << BLOCK_HASH_SHIFT) ^ (hash >> (8*sizeof(hash) - BLOCK_HASH_SHIFT)) ^ le32_to_cpu(here->e_hash); here = EXT4_XATTR_NEXT(here); } header->h_hash = cpu_to_le32(hash); } #undef BLOCK_HASH_SHIFT #define HASH_BUCKET_BITS 10 struct mb_cache * ext4_xattr_create_cache(void) { return mb_cache_create(HASH_BUCKET_BITS); } void ext4_xattr_destroy_cache(struct mb_cache *cache) { if (cache) mb_cache_destroy(cache); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2011 Nokia Corporation and/or its subsidiary(-ies). This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR 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. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ #ifndef __SMP_H #define __SMP_H struct smp_command_hdr { __u8 code; } __packed; #define SMP_CMD_PAIRING_REQ 0x01 #define SMP_CMD_PAIRING_RSP 0x02 struct smp_cmd_pairing { __u8 io_capability; __u8 oob_flag; __u8 auth_req; __u8 max_key_size; __u8 init_key_dist; __u8 resp_key_dist; } __packed; #define SMP_IO_DISPLAY_ONLY 0x00 #define SMP_IO_DISPLAY_YESNO 0x01 #define SMP_IO_KEYBOARD_ONLY 0x02 #define SMP_IO_NO_INPUT_OUTPUT 0x03 #define SMP_IO_KEYBOARD_DISPLAY 0x04 #define SMP_OOB_NOT_PRESENT 0x00 #define SMP_OOB_PRESENT 0x01 #define SMP_DIST_ENC_KEY 0x01 #define SMP_DIST_ID_KEY 0x02 #define SMP_DIST_SIGN 0x04 #define SMP_DIST_LINK_KEY 0x08 #define SMP_AUTH_NONE 0x00 #define SMP_AUTH_BONDING 0x01 #define SMP_AUTH_MITM 0x04 #define SMP_AUTH_SC 0x08 #define SMP_AUTH_KEYPRESS 0x10 #define SMP_AUTH_CT2 0x20 #define SMP_CMD_PAIRING_CONFIRM 0x03 struct smp_cmd_pairing_confirm { __u8 confirm_val[16]; } __packed; #define SMP_CMD_PAIRING_RANDOM 0x04 struct smp_cmd_pairing_random { __u8 rand_val[16]; } __packed; #define SMP_CMD_PAIRING_FAIL 0x05 struct smp_cmd_pairing_fail { __u8 reason; } __packed; #define SMP_CMD_ENCRYPT_INFO 0x06 struct smp_cmd_encrypt_info { __u8 ltk[16]; } __packed; #define SMP_CMD_INITIATOR_IDENT 0x07 struct smp_cmd_initiator_ident { __le16 ediv; __le64 rand; } __packed; #define SMP_CMD_IDENT_INFO 0x08 struct smp_cmd_ident_info { __u8 irk[16]; } __packed; #define SMP_CMD_IDENT_ADDR_INFO 0x09 struct smp_cmd_ident_addr_info { __u8 addr_type; bdaddr_t bdaddr; } __packed; #define SMP_CMD_SIGN_INFO 0x0a struct smp_cmd_sign_info { __u8 csrk[16]; } __packed; #define SMP_CMD_SECURITY_REQ 0x0b struct smp_cmd_security_req { __u8 auth_req; } __packed; #define SMP_CMD_PUBLIC_KEY 0x0c struct smp_cmd_public_key { __u8 x[32]; __u8 y[32]; } __packed; #define SMP_CMD_DHKEY_CHECK 0x0d struct smp_cmd_dhkey_check { __u8 e[16]; } __packed; #define SMP_CMD_KEYPRESS_NOTIFY 0x0e struct smp_cmd_keypress_notify { __u8 value; } __packed; #define SMP_CMD_MAX 0x0e #define SMP_PASSKEY_ENTRY_FAILED 0x01 #define SMP_OOB_NOT_AVAIL 0x02 #define SMP_AUTH_REQUIREMENTS 0x03 #define SMP_CONFIRM_FAILED 0x04 #define SMP_PAIRING_NOTSUPP 0x05 #define SMP_ENC_KEY_SIZE 0x06 #define SMP_CMD_NOTSUPP 0x07 #define SMP_UNSPECIFIED 0x08 #define SMP_REPEATED_ATTEMPTS 0x09 #define SMP_INVALID_PARAMS 0x0a #define SMP_DHKEY_CHECK_FAILED 0x0b #define SMP_NUMERIC_COMP_FAILED 0x0c #define SMP_BREDR_PAIRING_IN_PROGRESS 0x0d #define SMP_CROSS_TRANSP_NOT_ALLOWED 0x0e #define SMP_KEY_REJECTED 0x0f #define SMP_MIN_ENC_KEY_SIZE 7 #define SMP_MAX_ENC_KEY_SIZE 16 /* LTK types used in internal storage (struct smp_ltk) */ enum { SMP_STK, SMP_LTK, SMP_LTK_RESPONDER, SMP_LTK_P256, SMP_LTK_P256_DEBUG, }; static inline bool smp_ltk_is_sc(struct smp_ltk *key) { switch (key->type) { case SMP_LTK_P256: case SMP_LTK_P256_DEBUG: return true; } return false; } static inline u8 smp_ltk_sec_level(struct smp_ltk *key) { if (key->authenticated) { if (smp_ltk_is_sc(key)) return BT_SECURITY_FIPS; else return BT_SECURITY_HIGH; } return BT_SECURITY_MEDIUM; } /* Key preferences for smp_sufficient security */ enum smp_key_pref { SMP_ALLOW_STK, SMP_USE_LTK, }; /* SMP Commands */ int smp_cancel_and_remove_pairing(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 addr_type); bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level, enum smp_key_pref key_pref); int smp_conn_security(struct hci_conn *hcon, __u8 sec_level); int smp_user_confirm_reply(struct hci_conn *conn, u16 mgmt_op, __le32 passkey); bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16], const bdaddr_t *bdaddr); int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa); int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]); int smp_force_bredr(struct hci_dev *hdev, bool enable); int smp_register(struct hci_dev *hdev); void smp_unregister(struct hci_dev *hdev); #if IS_ENABLED(CONFIG_BT_SELFTEST_SMP) int bt_selftest_smp(void); #else static inline int bt_selftest_smp(void) { return 0; } #endif #endif /* __SMP_H */ |
| 29 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_UIDGID_H #define _LINUX_UIDGID_H /* * A set of types for the internal kernel types representing uids and gids. * * The types defined in this header allow distinguishing which uids and gids in * the kernel are values used by userspace and which uid and gid values are * the internal kernel values. With the addition of user namespaces the values * can be different. Using the type system makes it possible for the compiler * to detect when we overlook these differences. * */ #include <linux/uidgid_types.h> #include <linux/highuid.h> struct user_namespace; extern struct user_namespace init_user_ns; struct uid_gid_map; #define KUIDT_INIT(value) (kuid_t){ value } #define KGIDT_INIT(value) (kgid_t){ value } #ifdef CONFIG_MULTIUSER static inline uid_t __kuid_val(kuid_t uid) { return uid.val; } static inline gid_t __kgid_val(kgid_t gid) { return gid.val; } #else static inline uid_t __kuid_val(kuid_t uid) { return 0; } static inline gid_t __kgid_val(kgid_t gid) { return 0; } #endif #define GLOBAL_ROOT_UID KUIDT_INIT(0) #define GLOBAL_ROOT_GID KGIDT_INIT(0) #define INVALID_UID KUIDT_INIT(-1) #define INVALID_GID KGIDT_INIT(-1) static inline bool uid_eq(kuid_t left, kuid_t right) { return __kuid_val(left) == __kuid_val(right); } static inline bool gid_eq(kgid_t left, kgid_t right) { return __kgid_val(left) == __kgid_val(right); } static inline bool uid_gt(kuid_t left, kuid_t right) { return __kuid_val(left) > __kuid_val(right); } static inline bool gid_gt(kgid_t left, kgid_t right) { return __kgid_val(left) > __kgid_val(right); } static inline bool uid_gte(kuid_t left, kuid_t right) { return __kuid_val(left) >= __kuid_val(right); } static inline bool gid_gte(kgid_t left, kgid_t right) { return __kgid_val(left) >= __kgid_val(right); } static inline bool uid_lt(kuid_t left, kuid_t right) { return __kuid_val(left) < __kuid_val(right); } static inline bool gid_lt(kgid_t left, kgid_t right) { return __kgid_val(left) < __kgid_val(right); } static inline bool uid_lte(kuid_t left, kuid_t right) { return __kuid_val(left) <= __kuid_val(right); } static inline bool gid_lte(kgid_t left, kgid_t right) { return __kgid_val(left) <= __kgid_val(right); } static inline bool uid_valid(kuid_t uid) { return __kuid_val(uid) != (uid_t) -1; } static inline bool gid_valid(kgid_t gid) { return __kgid_val(gid) != (gid_t) -1; } #ifdef CONFIG_USER_NS extern kuid_t make_kuid(struct user_namespace *from, uid_t uid); extern kgid_t make_kgid(struct user_namespace *from, gid_t gid); extern uid_t from_kuid(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid(struct user_namespace *to, kgid_t gid); extern uid_t from_kuid_munged(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid_munged(struct user_namespace *to, kgid_t gid); static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return from_kuid(ns, uid) != (uid_t) -1; } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return from_kgid(ns, gid) != (gid_t) -1; } u32 map_id_down(struct uid_gid_map *map, u32 id); u32 map_id_up(struct uid_gid_map *map, u32 id); u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count); #else static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid) { return KUIDT_INIT(uid); } static inline kgid_t make_kgid(struct user_namespace *from, gid_t gid) { return KGIDT_INIT(gid); } static inline uid_t from_kuid(struct user_namespace *to, kuid_t kuid) { return __kuid_val(kuid); } static inline gid_t from_kgid(struct user_namespace *to, kgid_t kgid) { return __kgid_val(kgid); } static inline uid_t from_kuid_munged(struct user_namespace *to, kuid_t kuid) { uid_t uid = from_kuid(to, kuid); if (uid == (uid_t)-1) uid = overflowuid; return uid; } static inline gid_t from_kgid_munged(struct user_namespace *to, kgid_t kgid) { gid_t gid = from_kgid(to, kgid); if (gid == (gid_t)-1) gid = overflowgid; return gid; } static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return uid_valid(uid); } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return gid_valid(gid); } static inline u32 map_id_down(struct uid_gid_map *map, u32 id) { return id; } static inline u32 map_id_range_up(struct uid_gid_map *map, u32 id, u32 count) { return id; } static inline u32 map_id_up(struct uid_gid_map *map, u32 id) { return id; } #endif /* CONFIG_USER_NS */ #endif /* _LINUX_UIDGID_H */ |
| 3 10 8 2 7 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 | // SPDX-License-Identifier: GPL-2.0-or-later /* * CALIPSO - Common Architecture Label IPv6 Security Option * * This is an implementation of the CALIPSO protocol as specified in * RFC 5570. * * Authors: Paul Moore <paul.moore@hp.com> * Huw Davies <huw@codeweavers.com> */ /* (c) Copyright Hewlett-Packard Development Company, L.P., 2006, 2008 * (c) Copyright Huw Davies <huw@codeweavers.com>, 2015 */ #include <linux/init.h> #include <linux/types.h> #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/jhash.h> #include <linux/audit.h> #include <linux/slab.h> #include <net/ip.h> #include <net/icmp.h> #include <net/tcp.h> #include <net/netlabel.h> #include <net/calipso.h> #include <linux/atomic.h> #include <linux/bug.h> #include <linux/unaligned.h> #include <linux/crc-ccitt.h> /* Maximum size of the calipso option including * the two-byte TLV header. */ #define CALIPSO_OPT_LEN_MAX (2 + 252) /* Size of the minimum calipso option including * the two-byte TLV header. */ #define CALIPSO_HDR_LEN (2 + 8) /* Maximum size of the calipso option including * the two-byte TLV header and upto 3 bytes of * leading pad and 7 bytes of trailing pad. */ #define CALIPSO_OPT_LEN_MAX_WITH_PAD (3 + CALIPSO_OPT_LEN_MAX + 7) /* Maximum size of u32 aligned buffer required to hold calipso * option. Max of 3 initial pad bytes starting from buffer + 3. * i.e. the worst case is when the previous tlv finishes on 4n + 3. */ #define CALIPSO_MAX_BUFFER (6 + CALIPSO_OPT_LEN_MAX) /* List of available DOI definitions */ static DEFINE_SPINLOCK(calipso_doi_list_lock); static LIST_HEAD(calipso_doi_list); /* Label mapping cache */ int calipso_cache_enabled = 1; int calipso_cache_bucketsize = 10; #define CALIPSO_CACHE_BUCKETBITS 7 #define CALIPSO_CACHE_BUCKETS BIT(CALIPSO_CACHE_BUCKETBITS) #define CALIPSO_CACHE_REORDERLIMIT 10 struct calipso_map_cache_bkt { spinlock_t lock; u32 size; struct list_head list; }; struct calipso_map_cache_entry { u32 hash; unsigned char *key; size_t key_len; struct netlbl_lsm_cache *lsm_data; u32 activity; struct list_head list; }; static struct calipso_map_cache_bkt *calipso_cache; static void calipso_cache_invalidate(void); static void calipso_doi_putdef(struct calipso_doi *doi_def); /* Label Mapping Cache Functions */ /** * calipso_cache_entry_free - Frees a cache entry * @entry: the entry to free * * Description: * This function frees the memory associated with a cache entry including the * LSM cache data if there are no longer any users, i.e. reference count == 0. * */ static void calipso_cache_entry_free(struct calipso_map_cache_entry *entry) { if (entry->lsm_data) netlbl_secattr_cache_free(entry->lsm_data); kfree(entry->key); kfree(entry); } /** * calipso_map_cache_hash - Hashing function for the CALIPSO cache * @key: the hash key * @key_len: the length of the key in bytes * * Description: * The CALIPSO tag hashing function. Returns a 32-bit hash value. * */ static u32 calipso_map_cache_hash(const unsigned char *key, u32 key_len) { return jhash(key, key_len, 0); } /** * calipso_cache_init - Initialize the CALIPSO cache * * Description: * Initializes the CALIPSO label mapping cache, this function should be called * before any of the other functions defined in this file. Returns zero on * success, negative values on error. * */ static int __init calipso_cache_init(void) { u32 iter; calipso_cache = kzalloc_objs(struct calipso_map_cache_bkt, CALIPSO_CACHE_BUCKETS); if (!calipso_cache) return -ENOMEM; for (iter = 0; iter < CALIPSO_CACHE_BUCKETS; iter++) { spin_lock_init(&calipso_cache[iter].lock); calipso_cache[iter].size = 0; INIT_LIST_HEAD(&calipso_cache[iter].list); } return 0; } /** * calipso_cache_invalidate - Invalidates the current CALIPSO cache * * Description: * Invalidates and frees any entries in the CALIPSO cache. Returns zero on * success and negative values on failure. * */ static void calipso_cache_invalidate(void) { struct calipso_map_cache_entry *entry, *tmp_entry; u32 iter; for (iter = 0; iter < CALIPSO_CACHE_BUCKETS; iter++) { spin_lock_bh(&calipso_cache[iter].lock); list_for_each_entry_safe(entry, tmp_entry, &calipso_cache[iter].list, list) { list_del(&entry->list); calipso_cache_entry_free(entry); } calipso_cache[iter].size = 0; spin_unlock_bh(&calipso_cache[iter].lock); } } /** * calipso_cache_check - Check the CALIPSO cache for a label mapping * @key: the buffer to check * @key_len: buffer length in bytes * @secattr: the security attribute struct to use * * Description: * This function checks the cache to see if a label mapping already exists for * the given key. If there is a match then the cache is adjusted and the * @secattr struct is populated with the correct LSM security attributes. The * cache is adjusted in the following manner if the entry is not already the * first in the cache bucket: * * 1. The cache entry's activity counter is incremented * 2. The previous (higher ranking) entry's activity counter is decremented * 3. If the difference between the two activity counters is geater than * CALIPSO_CACHE_REORDERLIMIT the two entries are swapped * * Returns zero on success, -ENOENT for a cache miss, and other negative values * on error. * */ static int calipso_cache_check(const unsigned char *key, u32 key_len, struct netlbl_lsm_secattr *secattr) { u32 bkt; struct calipso_map_cache_entry *entry; struct calipso_map_cache_entry *prev_entry = NULL; u32 hash; if (!calipso_cache_enabled) return -ENOENT; hash = calipso_map_cache_hash(key, key_len); bkt = hash & (CALIPSO_CACHE_BUCKETS - 1); spin_lock_bh(&calipso_cache[bkt].lock); list_for_each_entry(entry, &calipso_cache[bkt].list, list) { if (entry->hash == hash && entry->key_len == key_len && memcmp(entry->key, key, key_len) == 0) { entry->activity += 1; refcount_inc(&entry->lsm_data->refcount); secattr->cache = entry->lsm_data; secattr->flags |= NETLBL_SECATTR_CACHE; secattr->type = NETLBL_NLTYPE_CALIPSO; if (!prev_entry) { spin_unlock_bh(&calipso_cache[bkt].lock); return 0; } if (prev_entry->activity > 0) prev_entry->activity -= 1; if (entry->activity > prev_entry->activity && entry->activity - prev_entry->activity > CALIPSO_CACHE_REORDERLIMIT) { __list_del(entry->list.prev, entry->list.next); __list_add(&entry->list, prev_entry->list.prev, &prev_entry->list); } spin_unlock_bh(&calipso_cache[bkt].lock); return 0; } prev_entry = entry; } spin_unlock_bh(&calipso_cache[bkt].lock); return -ENOENT; } /** * calipso_cache_add - Add an entry to the CALIPSO cache * @calipso_ptr: the CALIPSO option * @secattr: the packet's security attributes * * Description: * Add a new entry into the CALIPSO label mapping cache. Add the new entry to * head of the cache bucket's list, if the cache bucket is out of room remove * the last entry in the list first. It is important to note that there is * currently no checking for duplicate keys. Returns zero on success, * negative values on failure. The key stored starts at calipso_ptr + 2, * i.e. the type and length bytes are not stored, this corresponds to * calipso_ptr[1] bytes of data. * */ static int calipso_cache_add(const unsigned char *calipso_ptr, const struct netlbl_lsm_secattr *secattr) { int ret_val = -EPERM; u32 bkt; struct calipso_map_cache_entry *entry = NULL; struct calipso_map_cache_entry *old_entry = NULL; u32 calipso_ptr_len; if (!calipso_cache_enabled || calipso_cache_bucketsize <= 0) return 0; calipso_ptr_len = calipso_ptr[1]; entry = kzalloc_obj(*entry, GFP_ATOMIC); if (!entry) return -ENOMEM; entry->key = kmemdup(calipso_ptr + 2, calipso_ptr_len, GFP_ATOMIC); if (!entry->key) { ret_val = -ENOMEM; goto cache_add_failure; } entry->key_len = calipso_ptr_len; entry->hash = calipso_map_cache_hash(calipso_ptr, calipso_ptr_len); refcount_inc(&secattr->cache->refcount); entry->lsm_data = secattr->cache; bkt = entry->hash & (CALIPSO_CACHE_BUCKETS - 1); spin_lock_bh(&calipso_cache[bkt].lock); if (calipso_cache[bkt].size < calipso_cache_bucketsize) { list_add(&entry->list, &calipso_cache[bkt].list); calipso_cache[bkt].size += 1; } else { old_entry = list_entry(calipso_cache[bkt].list.prev, struct calipso_map_cache_entry, list); list_del(&old_entry->list); list_add(&entry->list, &calipso_cache[bkt].list); calipso_cache_entry_free(old_entry); } spin_unlock_bh(&calipso_cache[bkt].lock); return 0; cache_add_failure: if (entry) calipso_cache_entry_free(entry); return ret_val; } /* DOI List Functions */ /** * calipso_doi_search - Searches for a DOI definition * @doi: the DOI to search for * * Description: * Search the DOI definition list for a DOI definition with a DOI value that * matches @doi. The caller is responsible for calling rcu_read_[un]lock(). * Returns a pointer to the DOI definition on success and NULL on failure. */ static struct calipso_doi *calipso_doi_search(u32 doi) { struct calipso_doi *iter; list_for_each_entry_rcu(iter, &calipso_doi_list, list) if (iter->doi == doi && refcount_read(&iter->refcount)) return iter; return NULL; } /** * calipso_doi_add - Add a new DOI to the CALIPSO protocol engine * @doi_def: the DOI structure * @audit_info: NetLabel audit information * * Description: * The caller defines a new DOI for use by the CALIPSO engine and calls this * function to add it to the list of acceptable domains. The caller must * ensure that the mapping table specified in @doi_def->map meets all of the * requirements of the mapping type (see calipso.h for details). Returns * zero on success and non-zero on failure. * */ static int calipso_doi_add(struct calipso_doi *doi_def, struct netlbl_audit *audit_info) { int ret_val = -EINVAL; u32 doi; u32 doi_type; struct audit_buffer *audit_buf; doi = doi_def->doi; doi_type = doi_def->type; if (doi_def->doi == CALIPSO_DOI_UNKNOWN) goto doi_add_return; refcount_set(&doi_def->refcount, 1); spin_lock(&calipso_doi_list_lock); if (calipso_doi_search(doi_def->doi)) { spin_unlock(&calipso_doi_list_lock); ret_val = -EEXIST; goto doi_add_return; } list_add_tail_rcu(&doi_def->list, &calipso_doi_list); spin_unlock(&calipso_doi_list_lock); ret_val = 0; doi_add_return: audit_buf = netlbl_audit_start(AUDIT_MAC_CALIPSO_ADD, audit_info); if (audit_buf) { const char *type_str; switch (doi_type) { case CALIPSO_MAP_PASS: type_str = "pass"; break; default: type_str = "(unknown)"; } audit_log_format(audit_buf, " calipso_doi=%u calipso_type=%s res=%u", doi, type_str, ret_val == 0 ? 1 : 0); audit_log_end(audit_buf); } return ret_val; } /** * calipso_doi_free - Frees a DOI definition * @doi_def: the DOI definition * * Description: * This function frees all of the memory associated with a DOI definition. * */ static void calipso_doi_free(struct calipso_doi *doi_def) { kfree(doi_def); } /** * calipso_doi_free_rcu - Frees a DOI definition via the RCU pointer * @entry: the entry's RCU field * * Description: * This function is designed to be used as a callback to the call_rcu() * function so that the memory allocated to the DOI definition can be released * safely. * */ static void calipso_doi_free_rcu(struct rcu_head *entry) { struct calipso_doi *doi_def; doi_def = container_of(entry, struct calipso_doi, rcu); calipso_doi_free(doi_def); } /** * calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine * @doi: the DOI value * @audit_info: NetLabel audit information * * Description: * Removes a DOI definition from the CALIPSO engine. The NetLabel routines will * be called to release their own LSM domain mappings as well as our own * domain list. Returns zero on success and negative values on failure. * */ static int calipso_doi_remove(u32 doi, struct netlbl_audit *audit_info) { int ret_val; struct calipso_doi *doi_def; struct audit_buffer *audit_buf; spin_lock(&calipso_doi_list_lock); doi_def = calipso_doi_search(doi); if (!doi_def) { spin_unlock(&calipso_doi_list_lock); ret_val = -ENOENT; goto doi_remove_return; } list_del_rcu(&doi_def->list); spin_unlock(&calipso_doi_list_lock); calipso_doi_putdef(doi_def); ret_val = 0; doi_remove_return: audit_buf = netlbl_audit_start(AUDIT_MAC_CALIPSO_DEL, audit_info); if (audit_buf) { audit_log_format(audit_buf, " calipso_doi=%u res=%u", doi, ret_val == 0 ? 1 : 0); audit_log_end(audit_buf); } return ret_val; } /** * calipso_doi_getdef - Returns a reference to a valid DOI definition * @doi: the DOI value * * Description: * Searches for a valid DOI definition and if one is found it is returned to * the caller. Otherwise NULL is returned. The caller must ensure that * calipso_doi_putdef() is called when the caller is done. * */ static struct calipso_doi *calipso_doi_getdef(u32 doi) { struct calipso_doi *doi_def; rcu_read_lock(); doi_def = calipso_doi_search(doi); if (!doi_def) goto doi_getdef_return; if (!refcount_inc_not_zero(&doi_def->refcount)) doi_def = NULL; doi_getdef_return: rcu_read_unlock(); return doi_def; } /** * calipso_doi_putdef - Releases a reference for the given DOI definition * @doi_def: the DOI definition * * Description: * Releases a DOI definition reference obtained from calipso_doi_getdef(). * */ static void calipso_doi_putdef(struct calipso_doi *doi_def) { if (!doi_def) return; if (!refcount_dec_and_test(&doi_def->refcount)) return; calipso_cache_invalidate(); call_rcu(&doi_def->rcu, calipso_doi_free_rcu); } /** * calipso_doi_walk - Iterate through the DOI definitions * @skip_cnt: skip past this number of DOI definitions, updated * @callback: callback for each DOI definition * @cb_arg: argument for the callback function * * Description: * Iterate over the DOI definition list, skipping the first @skip_cnt entries. * For each entry call @callback, if @callback returns a negative value stop * 'walking' through the list and return. Updates the value in @skip_cnt upon * return. Returns zero on success, negative values on failure. * */ static int calipso_doi_walk(u32 *skip_cnt, int (*callback)(struct calipso_doi *doi_def, void *arg), void *cb_arg) { int ret_val = -ENOENT; u32 doi_cnt = 0; struct calipso_doi *iter_doi; rcu_read_lock(); list_for_each_entry_rcu(iter_doi, &calipso_doi_list, list) if (refcount_read(&iter_doi->refcount) > 0) { if (doi_cnt++ < *skip_cnt) continue; ret_val = callback(iter_doi, cb_arg); if (ret_val < 0) { doi_cnt--; goto doi_walk_return; } } doi_walk_return: rcu_read_unlock(); *skip_cnt = doi_cnt; return ret_val; } /** * calipso_validate - Validate a CALIPSO option * @skb: the packet * @option: the start of the option * * Description: * This routine is called to validate a CALIPSO option. * If the option is valid then %true is returned, otherwise * %false is returned. * * The caller should have already checked that the length of the * option (including the TLV header) is >= 10 and that the catmap * length is consistent with the option length. * * We leave checks on the level and categories to the socket layer. */ bool calipso_validate(const struct sk_buff *skb, const unsigned char *option) { struct calipso_doi *doi_def; bool ret_val; u16 crc, len = option[1] + 2; static const u8 zero[2]; /* The original CRC runs over the option including the TLV header * with the CRC-16 field (at offset 8) zeroed out. */ crc = crc_ccitt(0xffff, option, 8); crc = crc_ccitt(crc, zero, sizeof(zero)); if (len > 10) crc = crc_ccitt(crc, option + 10, len - 10); crc = ~crc; if (option[8] != (crc & 0xff) || option[9] != ((crc >> 8) & 0xff)) return false; rcu_read_lock(); doi_def = calipso_doi_search(get_unaligned_be32(option + 2)); ret_val = !!doi_def; rcu_read_unlock(); return ret_val; } /** * calipso_map_cat_hton - Perform a category mapping from host to network * @doi_def: the DOI definition * @secattr: the security attributes * @net_cat: the zero'd out category bitmap in network/CALIPSO format * @net_cat_len: the length of the CALIPSO bitmap in bytes * * Description: * Perform a label mapping to translate a local MLS category bitmap to the * correct CALIPSO bitmap using the given DOI definition. Returns the minimum * size in bytes of the network bitmap on success, negative values otherwise. * */ static int calipso_map_cat_hton(const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr, unsigned char *net_cat, u32 net_cat_len) { int spot = -1; u32 net_spot_max = 0; u32 net_clen_bits = net_cat_len * 8; for (;;) { spot = netlbl_catmap_walk(secattr->attr.mls.cat, spot + 1); if (spot < 0) break; if (spot >= net_clen_bits) return -ENOSPC; netlbl_bitmap_setbit(net_cat, spot, 1); if (spot > net_spot_max) net_spot_max = spot; } return (net_spot_max / 32 + 1) * 4; } /** * calipso_map_cat_ntoh - Perform a category mapping from network to host * @doi_def: the DOI definition * @net_cat: the category bitmap in network/CALIPSO format * @net_cat_len: the length of the CALIPSO bitmap in bytes * @secattr: the security attributes * * Description: * Perform a label mapping to translate a CALIPSO bitmap to the correct local * MLS category bitmap using the given DOI definition. Returns zero on * success, negative values on failure. * */ static int calipso_map_cat_ntoh(const struct calipso_doi *doi_def, const unsigned char *net_cat, u32 net_cat_len, struct netlbl_lsm_secattr *secattr) { int ret_val; int spot = -1; u32 net_clen_bits = net_cat_len * 8; for (;;) { spot = netlbl_bitmap_walk(net_cat, net_clen_bits, spot + 1, 1); if (spot < 0) return 0; ret_val = netlbl_catmap_setbit(&secattr->attr.mls.cat, spot, GFP_ATOMIC); if (ret_val != 0) return ret_val; } return -EINVAL; } /** * calipso_pad_write - Writes pad bytes in TLV format * @buf: the buffer * @offset: offset from start of buffer to write padding * @count: number of pad bytes to write * * Description: * Write @count bytes of TLV padding into @buffer starting at offset @offset. * @count should be less than 8 - see RFC 4942. * */ static int calipso_pad_write(unsigned char *buf, unsigned int offset, unsigned int count) { if (WARN_ON_ONCE(count >= 8)) return -EINVAL; switch (count) { case 0: break; case 1: buf[offset] = IPV6_TLV_PAD1; break; default: buf[offset] = IPV6_TLV_PADN; buf[offset + 1] = count - 2; if (count > 2) memset(buf + offset + 2, 0, count - 2); break; } return 0; } /** * calipso_genopt - Generate a CALIPSO option * @buf: the option buffer * @start: offset from which to write * @buf_len: the size of opt_buf * @doi_def: the CALIPSO DOI to use * @secattr: the security attributes * * Description: * Generate a CALIPSO option using the DOI definition and security attributes * passed to the function. This also generates upto three bytes of leading * padding that ensures that the option is 4n + 2 aligned. It returns the * number of bytes written (including any initial padding). */ static int calipso_genopt(unsigned char *buf, u32 start, u32 buf_len, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val; u32 len, pad; u16 crc; static const unsigned char padding[4] = {2, 1, 0, 3}; unsigned char *calipso; /* CALIPSO has 4n + 2 alignment */ pad = padding[start & 3]; if (buf_len <= start + pad + CALIPSO_HDR_LEN) return -ENOSPC; if ((secattr->flags & NETLBL_SECATTR_MLS_LVL) == 0) return -EPERM; len = CALIPSO_HDR_LEN; if (secattr->flags & NETLBL_SECATTR_MLS_CAT) { ret_val = calipso_map_cat_hton(doi_def, secattr, buf + start + pad + len, buf_len - start - pad - len); if (ret_val < 0) return ret_val; len += ret_val; } calipso_pad_write(buf, start, pad); calipso = buf + start + pad; calipso[0] = IPV6_TLV_CALIPSO; calipso[1] = len - 2; *(__be32 *)(calipso + 2) = htonl(doi_def->doi); calipso[6] = (len - CALIPSO_HDR_LEN) / 4; calipso[7] = secattr->attr.mls.lvl; crc = ~crc_ccitt(0xffff, calipso, len); calipso[8] = crc & 0xff; calipso[9] = (crc >> 8) & 0xff; return pad + len; } /* Hop-by-hop hdr helper functions */ /** * calipso_opt_update - Replaces socket's hop options with a new set * @sk: the socket * @hop: new hop options * * Description: * Replaces @sk's hop options with @hop. @hop may be NULL to leave * the socket with no hop options. * */ static int calipso_opt_update(struct sock *sk, struct ipv6_opt_hdr *hop) { struct ipv6_txoptions *old = txopt_get(inet6_sk(sk)), *txopts; txopts = ipv6_renew_options(sk, old, IPV6_HOPOPTS, hop); txopt_put(old); if (IS_ERR(txopts)) return PTR_ERR(txopts); txopts = ipv6_update_options(sk, txopts); if (txopts) { atomic_sub(txopts->tot_len, &sk->sk_omem_alloc); txopt_put(txopts); } return 0; } /** * calipso_tlv_len - Returns the length of the TLV * @opt: the option header * @offset: offset of the TLV within the header * * Description: * Returns the length of the TLV option at offset @offset within * the option header @opt. Checks that the entire TLV fits inside * the option header, returns a negative value if this is not the case. */ static int calipso_tlv_len(struct ipv6_opt_hdr *opt, unsigned int offset) { unsigned char *tlv = (unsigned char *)opt; unsigned int opt_len = ipv6_optlen(opt), tlv_len; if (offset < sizeof(*opt) || offset >= opt_len) return -EINVAL; if (tlv[offset] == IPV6_TLV_PAD1) return 1; if (offset + 1 >= opt_len) return -EINVAL; tlv_len = tlv[offset + 1] + 2; if (offset + tlv_len > opt_len) return -EINVAL; return tlv_len; } /** * calipso_opt_find - Finds the CALIPSO option in an IPv6 hop options header * @hop: the hop options header * @start: on return holds the offset of any leading padding * @end: on return holds the offset of the first non-pad TLV after CALIPSO * * Description: * Finds the space occupied by a CALIPSO option (including any leading and * trailing padding). * * If a CALIPSO option exists set @start and @end to the * offsets within @hop of the start of padding before the first * CALIPSO option and the end of padding after the first CALIPSO * option. In this case the function returns 0. * * In the absence of a CALIPSO option, @start and @end will be * set to the start and end of any trailing padding in the header. * This is useful when appending a new option, as the caller may want * to overwrite some of this padding. In this case the function will * return -ENOENT. */ static int calipso_opt_find(struct ipv6_opt_hdr *hop, unsigned int *start, unsigned int *end) { int ret_val = -ENOENT, tlv_len; unsigned int opt_len, offset, offset_s = 0, offset_e = 0; unsigned char *opt = (unsigned char *)hop; opt_len = ipv6_optlen(hop); offset = sizeof(*hop); while (offset < opt_len) { tlv_len = calipso_tlv_len(hop, offset); if (tlv_len < 0) return tlv_len; switch (opt[offset]) { case IPV6_TLV_PAD1: case IPV6_TLV_PADN: if (offset_e) offset_e = offset; break; case IPV6_TLV_CALIPSO: ret_val = 0; offset_e = offset; break; default: if (offset_e == 0) offset_s = offset; else goto out; } offset += tlv_len; } out: if (offset_s) *start = offset_s + calipso_tlv_len(hop, offset_s); else *start = sizeof(*hop); if (offset_e) *end = offset_e + calipso_tlv_len(hop, offset_e); else *end = opt_len; return ret_val; } /** * calipso_opt_insert - Inserts a CALIPSO option into an IPv6 hop opt hdr * @hop: the original hop options header * @doi_def: the CALIPSO DOI to use * @secattr: the specific security attributes of the socket * * Description: * Creates a new hop options header based on @hop with a * CALIPSO option added to it. If @hop already contains a CALIPSO * option this is overwritten, otherwise the new option is appended * after any existing options. If @hop is NULL then the new header * will contain just the CALIPSO option and any needed padding. * */ static struct ipv6_opt_hdr * calipso_opt_insert(struct ipv6_opt_hdr *hop, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { unsigned int start, end, buf_len, pad, hop_len; struct ipv6_opt_hdr *new; int ret_val; if (hop) { hop_len = ipv6_optlen(hop); ret_val = calipso_opt_find(hop, &start, &end); if (ret_val && ret_val != -ENOENT) return ERR_PTR(ret_val); } else { hop_len = 0; start = sizeof(*hop); end = 0; } buf_len = hop_len + start - end + CALIPSO_OPT_LEN_MAX_WITH_PAD; new = kzalloc(buf_len, GFP_ATOMIC); if (!new) return ERR_PTR(-ENOMEM); if (start > sizeof(*hop)) memcpy(new, hop, start); ret_val = calipso_genopt((unsigned char *)new, start, buf_len, doi_def, secattr); if (ret_val < 0) { kfree(new); return ERR_PTR(ret_val); } buf_len = start + ret_val; /* At this point buf_len aligns to 4n, so (buf_len & 4) pads to 8n */ pad = ((buf_len & 4) + (end & 7)) & 7; calipso_pad_write((unsigned char *)new, buf_len, pad); buf_len += pad; if (end != hop_len) { memcpy((char *)new + buf_len, (char *)hop + end, hop_len - end); buf_len += hop_len - end; } new->nexthdr = 0; new->hdrlen = buf_len / 8 - 1; return new; } /** * calipso_opt_del - Removes the CALIPSO option from an option header * @hop: the original header * @new: the new header * * Description: * Creates a new header based on @hop without any CALIPSO option. If @hop * doesn't contain a CALIPSO option it returns -ENOENT. If @hop contains * no other non-padding options, it returns zero with @new set to NULL. * Otherwise it returns zero, creates a new header without the CALIPSO * option (and removing as much padding as possible) and returns with * @new set to that header. * */ static int calipso_opt_del(struct ipv6_opt_hdr *hop, struct ipv6_opt_hdr **new) { int ret_val; unsigned int start, end, delta, pad, hop_len; ret_val = calipso_opt_find(hop, &start, &end); if (ret_val) return ret_val; hop_len = ipv6_optlen(hop); if (start == sizeof(*hop) && end == hop_len) { /* There's no other option in the header so return NULL */ *new = NULL; return 0; } delta = (end - start) & ~7; *new = kzalloc(hop_len - delta, GFP_ATOMIC); if (!*new) return -ENOMEM; memcpy(*new, hop, start); (*new)->hdrlen -= delta / 8; pad = (end - start) & 7; calipso_pad_write((unsigned char *)*new, start, pad); if (end != hop_len) memcpy((char *)*new + start + pad, (char *)hop + end, hop_len - end); return 0; } /** * calipso_opt_getattr - Get the security attributes from a memory block * @calipso: the CALIPSO option * @secattr: the security attributes * * Description: * Inspect @calipso and return the security attributes in @secattr. * Returns zero on success and negative values on failure. * */ static int calipso_opt_getattr(const unsigned char *calipso, struct netlbl_lsm_secattr *secattr) { int ret_val = -ENOMSG; u32 doi, len = calipso[1], cat_len = calipso[6] * 4; struct calipso_doi *doi_def; if (cat_len + 8 > len) return -EINVAL; if (calipso_cache_check(calipso + 2, calipso[1], secattr) == 0) return 0; doi = get_unaligned_be32(calipso + 2); rcu_read_lock(); doi_def = calipso_doi_search(doi); if (!doi_def) goto getattr_return; secattr->attr.mls.lvl = calipso[7]; secattr->flags |= NETLBL_SECATTR_MLS_LVL; if (cat_len) { ret_val = calipso_map_cat_ntoh(doi_def, calipso + 10, cat_len, secattr); if (ret_val != 0) { netlbl_catmap_free(secattr->attr.mls.cat); goto getattr_return; } if (secattr->attr.mls.cat) secattr->flags |= NETLBL_SECATTR_MLS_CAT; } secattr->type = NETLBL_NLTYPE_CALIPSO; getattr_return: rcu_read_unlock(); return ret_val; } /* sock functions. */ /** * calipso_sock_getattr - Get the security attributes from a sock * @sk: the sock * @secattr: the security attributes * * Description: * Query @sk to see if there is a CALIPSO option attached to the sock and if * there is return the CALIPSO security attributes in @secattr. This function * requires that @sk be locked, or privately held, but it does not do any * locking itself. Returns zero on success and negative values on failure. * */ static int calipso_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) { struct ipv6_opt_hdr *hop; int opt_len, len, ret_val = -ENOMSG, offset; unsigned char *opt; struct ipv6_pinfo *pinfo = inet6_sk(sk); struct ipv6_txoptions *txopts; if (!pinfo) return -EAFNOSUPPORT; txopts = txopt_get(pinfo); if (!txopts || !txopts->hopopt) goto done; hop = txopts->hopopt; opt = (unsigned char *)hop; opt_len = ipv6_optlen(hop); offset = sizeof(*hop); while (offset < opt_len) { len = calipso_tlv_len(hop, offset); if (len < 0) { ret_val = len; goto done; } switch (opt[offset]) { case IPV6_TLV_CALIPSO: if (len < CALIPSO_HDR_LEN) ret_val = -EINVAL; else ret_val = calipso_opt_getattr(&opt[offset], secattr); goto done; default: offset += len; break; } } done: txopt_put(txopts); return ret_val; } /** * calipso_sock_setattr - Add a CALIPSO option to a socket * @sk: the socket * @doi_def: the CALIPSO DOI to use * @secattr: the specific security attributes of the socket * * Description: * Set the CALIPSO option on the given socket using the DOI definition and * security attributes passed to the function. This function requires * exclusive access to @sk, which means it either needs to be in the * process of being created or locked. Returns zero on success and negative * values on failure. * */ static int calipso_sock_setattr(struct sock *sk, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val; struct ipv6_opt_hdr *old, *new; struct ipv6_pinfo *pinfo = inet6_sk(sk); struct ipv6_txoptions *txopts; if (!pinfo) return -EAFNOSUPPORT; txopts = txopt_get(pinfo); old = NULL; if (txopts) old = txopts->hopopt; new = calipso_opt_insert(old, doi_def, secattr); txopt_put(txopts); if (IS_ERR(new)) return PTR_ERR(new); ret_val = calipso_opt_update(sk, new); kfree(new); return ret_val; } /** * calipso_sock_delattr - Delete the CALIPSO option from a socket * @sk: the socket * * Description: * Removes the CALIPSO option from a socket, if present. * */ static void calipso_sock_delattr(struct sock *sk) { struct ipv6_opt_hdr *new_hop; struct ipv6_pinfo *pinfo = inet6_sk(sk); struct ipv6_txoptions *txopts; if (!pinfo) return; txopts = txopt_get(pinfo); if (!txopts || !txopts->hopopt) goto done; if (calipso_opt_del(txopts->hopopt, &new_hop)) goto done; calipso_opt_update(sk, new_hop); kfree(new_hop); done: txopt_put(txopts); } /* request sock functions. */ /** * calipso_req_setattr - Add a CALIPSO option to a connection request socket * @req: the connection request socket * @doi_def: the CALIPSO DOI to use * @secattr: the specific security attributes of the socket * * Description: * Set the CALIPSO option on the given socket using the DOI definition and * security attributes passed to the function. Returns zero on success and * negative values on failure. * */ static int calipso_req_setattr(struct request_sock *req, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { struct ipv6_txoptions *txopts; struct inet_request_sock *req_inet = inet_rsk(req); struct ipv6_opt_hdr *old, *new; struct sock *sk = sk_to_full_sk(req_to_sk(req)); /* sk is NULL for SYN+ACK w/ SYN Cookie */ if (!sk) return -ENOMEM; if (req_inet->ipv6_opt && req_inet->ipv6_opt->hopopt) old = req_inet->ipv6_opt->hopopt; else old = NULL; new = calipso_opt_insert(old, doi_def, secattr); if (IS_ERR(new)) return PTR_ERR(new); txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new); kfree(new); if (IS_ERR(txopts)) return PTR_ERR(txopts); txopts = xchg(&req_inet->ipv6_opt, txopts); if (txopts) { atomic_sub(txopts->tot_len, &sk->sk_omem_alloc); txopt_put(txopts); } return 0; } /** * calipso_req_delattr - Delete the CALIPSO option from a request socket * @req: the request socket * * Description: * Removes the CALIPSO option from a request socket, if present. * */ static void calipso_req_delattr(struct request_sock *req) { struct inet_request_sock *req_inet = inet_rsk(req); struct ipv6_opt_hdr *new; struct ipv6_txoptions *txopts; struct sock *sk = sk_to_full_sk(req_to_sk(req)); /* sk is NULL for SYN+ACK w/ SYN Cookie */ if (!sk) return; if (!req_inet->ipv6_opt || !req_inet->ipv6_opt->hopopt) return; if (calipso_opt_del(req_inet->ipv6_opt->hopopt, &new)) return; /* Nothing to do */ txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new); if (!IS_ERR(txopts)) { txopts = xchg(&req_inet->ipv6_opt, txopts); if (txopts) { atomic_sub(txopts->tot_len, &sk->sk_omem_alloc); txopt_put(txopts); } } kfree(new); } /* skbuff functions. */ /** * calipso_skbuff_optptr - Find the CALIPSO option in the packet * @skb: the packet * * Description: * Parse the packet's IP header looking for a CALIPSO option. Returns a pointer * to the start of the CALIPSO option on success, NULL if one if not found. * */ static unsigned char *calipso_skbuff_optptr(const struct sk_buff *skb) { const struct ipv6hdr *ip6_hdr = ipv6_hdr(skb); int offset; if (ip6_hdr->nexthdr != NEXTHDR_HOP) return NULL; offset = ipv6_find_tlv(skb, sizeof(*ip6_hdr), IPV6_TLV_CALIPSO); if (offset >= 0) return (unsigned char *)ip6_hdr + offset; return NULL; } /** * calipso_skbuff_setattr - Set the CALIPSO option on a packet * @skb: the packet * @doi_def: the CALIPSO DOI to use * @secattr: the security attributes * * Description: * Set the CALIPSO option on the given packet based on the security attributes. * Returns a pointer to the IP header on success and NULL on failure. * */ static int calipso_skbuff_setattr(struct sk_buff *skb, const struct calipso_doi *doi_def, const struct netlbl_lsm_secattr *secattr) { int ret_val; struct ipv6hdr *ip6_hdr; struct ipv6_opt_hdr *hop; unsigned char buf[CALIPSO_MAX_BUFFER]; int len_delta, new_end, pad, payload; unsigned int start, end; ip6_hdr = ipv6_hdr(skb); if (ip6_hdr->nexthdr == NEXTHDR_HOP) { hop = (struct ipv6_opt_hdr *)(ip6_hdr + 1); ret_val = calipso_opt_find(hop, &start, &end); if (ret_val && ret_val != -ENOENT) return ret_val; } else { start = 0; end = 0; } memset(buf, 0, sizeof(buf)); ret_val = calipso_genopt(buf, start & 3, sizeof(buf), doi_def, secattr); if (ret_val < 0) return ret_val; new_end = start + ret_val; /* At this point new_end aligns to 4n, so (new_end & 4) pads to 8n */ pad = ((new_end & 4) + (end & 7)) & 7; len_delta = new_end - (int)end + pad; ret_val = skb_cow(skb, skb_headroom(skb) + (len_delta > 0 ? len_delta : 0)); if (ret_val < 0) return ret_val; ip6_hdr = ipv6_hdr(skb); /* Reset as skb_cow() may have moved it */ if (len_delta) { if (len_delta > 0) skb_push(skb, len_delta); else skb_pull(skb, -len_delta); memmove((char *)ip6_hdr - len_delta, ip6_hdr, sizeof(*ip6_hdr) + start); skb_reset_network_header(skb); ip6_hdr = ipv6_hdr(skb); payload = ntohs(ip6_hdr->payload_len); ip6_hdr->payload_len = htons(payload + len_delta); } hop = (struct ipv6_opt_hdr *)(ip6_hdr + 1); if (start == 0) { struct ipv6_opt_hdr *new_hop = (struct ipv6_opt_hdr *)buf; new_hop->nexthdr = ip6_hdr->nexthdr; new_hop->hdrlen = len_delta / 8 - 1; ip6_hdr->nexthdr = NEXTHDR_HOP; } else { hop->hdrlen += len_delta / 8; } memcpy((char *)hop + start, buf + (start & 3), new_end - start); calipso_pad_write((unsigned char *)hop, new_end, pad); return 0; } /** * calipso_skbuff_delattr - Delete any CALIPSO options from a packet * @skb: the packet * * Description: * Removes any and all CALIPSO options from the given packet. Returns zero on * success, negative values on failure. * */ static int calipso_skbuff_delattr(struct sk_buff *skb) { int ret_val; struct ipv6hdr *ip6_hdr; struct ipv6_opt_hdr *old_hop; u32 old_hop_len, start = 0, end = 0, delta, size, pad; if (!calipso_skbuff_optptr(skb)) return 0; /* since we are changing the packet we should make a copy */ ret_val = skb_cow(skb, skb_headroom(skb)); if (ret_val < 0) return ret_val; ip6_hdr = ipv6_hdr(skb); old_hop = (struct ipv6_opt_hdr *)(ip6_hdr + 1); old_hop_len = ipv6_optlen(old_hop); ret_val = calipso_opt_find(old_hop, &start, &end); if (ret_val) return ret_val; if (start == sizeof(*old_hop) && end == old_hop_len) { /* There's no other option in the header so we delete * the whole thing. */ delta = old_hop_len; size = sizeof(*ip6_hdr); ip6_hdr->nexthdr = old_hop->nexthdr; } else { delta = (end - start) & ~7; if (delta) old_hop->hdrlen -= delta / 8; pad = (end - start) & 7; size = sizeof(*ip6_hdr) + start + pad; calipso_pad_write((unsigned char *)old_hop, start, pad); } if (delta) { skb_pull(skb, delta); memmove((char *)ip6_hdr + delta, ip6_hdr, size); skb_reset_network_header(skb); } return 0; } static const struct netlbl_calipso_ops ops = { .doi_add = calipso_doi_add, .doi_free = calipso_doi_free, .doi_remove = calipso_doi_remove, .doi_getdef = calipso_doi_getdef, .doi_putdef = calipso_doi_putdef, .doi_walk = calipso_doi_walk, .sock_getattr = calipso_sock_getattr, .sock_setattr = calipso_sock_setattr, .sock_delattr = calipso_sock_delattr, .req_setattr = calipso_req_setattr, .req_delattr = calipso_req_delattr, .opt_getattr = calipso_opt_getattr, .skbuff_optptr = calipso_skbuff_optptr, .skbuff_setattr = calipso_skbuff_setattr, .skbuff_delattr = calipso_skbuff_delattr, .cache_invalidate = calipso_cache_invalidate, .cache_add = calipso_cache_add }; /** * calipso_init - Initialize the CALIPSO module * * Description: * Initialize the CALIPSO module and prepare it for use. Returns zero on * success and negative values on failure. * */ int __init calipso_init(void) { int ret_val; ret_val = calipso_cache_init(); if (!ret_val) netlbl_calipso_ops_register(&ops); return ret_val; } void calipso_exit(void) { netlbl_calipso_ops_register(NULL); calipso_cache_invalidate(); kfree(calipso_cache); } |
| 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 | // SPDX-License-Identifier: GPL-2.0-only /* * Creates audit record for dropped/accepted packets * * (C) 2010-2011 Thomas Graf <tgraf@redhat.com> * (C) 2010-2011 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/audit.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_AUDIT.h> #include <linux/netfilter_bridge/ebtables.h> #include <net/ipv6.h> #include <net/ip.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Thomas Graf <tgraf@redhat.com>"); MODULE_DESCRIPTION("Xtables: creates audit records for dropped/accepted packets"); MODULE_ALIAS("ipt_AUDIT"); MODULE_ALIAS("ip6t_AUDIT"); MODULE_ALIAS("ebt_AUDIT"); MODULE_ALIAS("arpt_AUDIT"); static unsigned int audit_tg(struct sk_buff *skb, const struct xt_action_param *par) { struct audit_buffer *ab; if (audit_enabled == AUDIT_OFF) goto errout; ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT); if (ab == NULL) goto errout; audit_log_format(ab, "mark=%#x", skb->mark); audit_log_nf_skb(ab, skb, xt_family(par)); audit_log_end(ab); errout: return XT_CONTINUE; } static unsigned int audit_tg_ebt(struct sk_buff *skb, const struct xt_action_param *par) { audit_tg(skb, par); return EBT_CONTINUE; } static int audit_tg_check(const struct xt_tgchk_param *par) { const struct xt_audit_info *info = par->targinfo; if (info->type > XT_AUDIT_TYPE_MAX) { pr_info_ratelimited("Audit type out of range (valid range: 0..%u)\n", XT_AUDIT_TYPE_MAX); return -ERANGE; } return 0; } static struct xt_target audit_tg_reg[] __read_mostly = { { .name = "AUDIT", .family = NFPROTO_UNSPEC, .target = audit_tg, .targetsize = sizeof(struct xt_audit_info), .checkentry = audit_tg_check, .me = THIS_MODULE, }, { .name = "AUDIT", .family = NFPROTO_BRIDGE, .target = audit_tg_ebt, .targetsize = sizeof(struct xt_audit_info), .checkentry = audit_tg_check, .me = THIS_MODULE, }, }; static int __init audit_tg_init(void) { return xt_register_targets(audit_tg_reg, ARRAY_SIZE(audit_tg_reg)); } static void __exit audit_tg_exit(void) { xt_unregister_targets(audit_tg_reg, ARRAY_SIZE(audit_tg_reg)); } module_init(audit_tg_init); module_exit(audit_tg_exit); |
| 243 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_U64_STATS_SYNC_H #define _LINUX_U64_STATS_SYNC_H /* * Protect against 64-bit values tearing on 32-bit architectures. This is * typically used for statistics read/update in different subsystems. * * Key points : * * - Use a seqcount on 32-bit * - The whole thing is a no-op on 64-bit architectures. * * Usage constraints: * * 1) Write side must ensure mutual exclusion, or one seqcount update could * be lost, thus blocking readers forever. * * 2) Write side must disable preemption, or a seqcount reader can preempt the * writer and also spin forever. * * 3) Write side must use the _irqsave() variant if other writers, or a reader, * can be invoked from an IRQ context. On 64bit systems this variant does not * disable interrupts. * * 4) If reader fetches several counters, there is no guarantee the whole values * are consistent w.r.t. each other (remember point #2: seqcounts are not * used for 64bit architectures). * * 5) Readers are allowed to sleep or be preempted/interrupted: they perform * pure reads. * * Usage : * * Stats producer (writer) should use following template granted it already got * an exclusive access to counters (a lock is already taken, or per cpu * data is used [in a non preemptable context]) * * spin_lock_bh(...) or other synchronization to get exclusive access * ... * u64_stats_update_begin(&stats->syncp); * u64_stats_add(&stats->bytes64, len); // non atomic operation * u64_stats_inc(&stats->packets64); // non atomic operation * u64_stats_update_end(&stats->syncp); * * While a consumer (reader) should use following template to get consistent * snapshot for each variable (but no guarantee on several ones) * * u64 tbytes, tpackets; * unsigned int start; * * do { * start = u64_stats_fetch_begin(&stats->syncp); * tbytes = u64_stats_read(&stats->bytes64); // non atomic operation * tpackets = u64_stats_read(&stats->packets64); // non atomic operation * } while (u64_stats_fetch_retry(&stats->syncp, start)); * * * Example of use in drivers/net/loopback.c, using per_cpu containers, * in BH disabled context. */ #include <linux/seqlock.h> struct u64_stats_sync { #if BITS_PER_LONG == 32 seqcount_t seq; #endif }; #if BITS_PER_LONG == 64 #include <asm/local64.h> typedef struct { local64_t v; } u64_stats_t ; static inline u64 u64_stats_read(const u64_stats_t *p) { return local64_read(&p->v); } static inline void *u64_stats_copy(void *dst, const void *src, size_t len) { BUILD_BUG_ON(len % sizeof(u64_stats_t)); for (size_t i = 0; i < len / sizeof(u64_stats_t); i++) ((u64 *)dst)[i] = local64_read(&((local64_t *)src)[i]); return dst; } static inline void u64_stats_set(u64_stats_t *p, u64 val) { local64_set(&p->v, val); } static inline void u64_stats_add(u64_stats_t *p, unsigned long val) { local64_add(val, &p->v); } static inline void u64_stats_sub(u64_stats_t *p, s64 val) { local64_sub(val, &p->v); } static inline void u64_stats_inc(u64_stats_t *p) { local64_inc(&p->v); } static inline void u64_stats_init(struct u64_stats_sync *syncp) { } static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { } static inline void __u64_stats_update_end(struct u64_stats_sync *syncp) { } static inline unsigned long __u64_stats_irqsave(void) { return 0; } static inline void __u64_stats_irqrestore(unsigned long flags) { } static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { return 0; } static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { return false; } #else /* 64 bit */ #include <linux/string.h> typedef struct { u64 v; } u64_stats_t; static inline u64 u64_stats_read(const u64_stats_t *p) { return p->v; } static inline void *u64_stats_copy(void *dst, const void *src, size_t len) { BUILD_BUG_ON(len % sizeof(u64_stats_t)); return memcpy(dst, src, len); } static inline void u64_stats_set(u64_stats_t *p, u64 val) { p->v = val; } static inline void u64_stats_add(u64_stats_t *p, unsigned long val) { p->v += val; } static inline void u64_stats_sub(u64_stats_t *p, s64 val) { p->v -= val; } static inline void u64_stats_inc(u64_stats_t *p) { p->v++; } #define u64_stats_init(syncp) \ do { \ struct u64_stats_sync *__s = (syncp); \ seqcount_init(&__s->seq); \ } while (0) static inline void __u64_stats_update_begin(struct u64_stats_sync *syncp) { preempt_disable_nested(); write_seqcount_begin(&syncp->seq); } static inline void __u64_stats_update_end(struct u64_stats_sync *syncp) { write_seqcount_end(&syncp->seq); preempt_enable_nested(); } static inline unsigned long __u64_stats_irqsave(void) { unsigned long flags; local_irq_save(flags); return flags; } static inline void __u64_stats_irqrestore(unsigned long flags) { local_irq_restore(flags); } static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { return read_seqcount_begin(&syncp->seq); } static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { return read_seqcount_retry(&syncp->seq, start); } #endif /* !64 bit */ static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { __u64_stats_update_begin(syncp); } static inline void u64_stats_update_end(struct u64_stats_sync *syncp) { __u64_stats_update_end(syncp); } static inline unsigned long u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) { unsigned long flags = __u64_stats_irqsave(); __u64_stats_update_begin(syncp); return flags; } static inline void u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, unsigned long flags) { __u64_stats_update_end(syncp); __u64_stats_irqrestore(flags); } static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { return __u64_stats_fetch_begin(syncp); } static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { return __u64_stats_fetch_retry(syncp, start); } #endif /* _LINUX_U64_STATS_SYNC_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __NET_SCHED_PIE_H #define __NET_SCHED_PIE_H #include <linux/ktime.h> #include <linux/skbuff.h> #include <linux/types.h> #include <net/inet_ecn.h> #include <net/pkt_sched.h> #define MAX_PROB (U64_MAX >> BITS_PER_BYTE) #define DTIME_INVALID U64_MAX #define QUEUE_THRESHOLD 16384 #define DQCOUNT_INVALID -1 #define PIE_SCALE 8 /** * struct pie_params - contains pie parameters * @target: target delay in pschedtime * @tupdate: interval at which drop probability is calculated * @limit: total number of packets that can be in the queue * @alpha: parameter to control drop probability * @beta: parameter to control drop probability * @ecn: is ECN marking of packets enabled * @bytemode: is drop probability scaled based on pkt size * @dq_rate_estimator: is Little's law used for qdelay calculation */ struct pie_params { psched_time_t target; u32 tupdate; u32 limit; u32 alpha; u32 beta; u8 ecn; u8 bytemode; u8 dq_rate_estimator; }; /** * struct pie_vars - contains pie variables * @qdelay: current queue delay * @qdelay_old: queue delay in previous qdelay calculation * @burst_time: burst time allowance * @dq_tstamp: timestamp at which dq rate was last calculated * @prob: drop probability * @accu_prob: accumulated drop probability * @dq_count: number of bytes dequeued in a measurement cycle * @avg_dq_rate: calculated average dq rate * @backlog_old: queue backlog during previous qdelay calculation */ struct pie_vars { psched_time_t qdelay; psched_time_t qdelay_old; psched_time_t burst_time; psched_time_t dq_tstamp; u64 prob; u64 accu_prob; u64 dq_count; u32 avg_dq_rate; u32 backlog_old; }; /** * struct pie_stats - contains pie stats * @packets_in: total number of packets enqueued * @dropped: packets dropped due to pie action * @overlimit: packets dropped due to lack of space in queue * @ecn_mark: packets marked with ECN * @maxq: maximum queue size */ struct pie_stats { u32 packets_in; u32 dropped; u32 overlimit; u32 ecn_mark; u32 maxq; }; /** * struct pie_skb_cb - contains private skb vars * @enqueue_time: timestamp when the packet is enqueued * @mem_usage: size of the skb during enqueue */ struct pie_skb_cb { psched_time_t enqueue_time; u32 mem_usage; }; static inline void pie_params_init(struct pie_params *params) { params->target = PSCHED_NS2TICKS(15 * NSEC_PER_MSEC); /* 15 ms */ params->tupdate = usecs_to_jiffies(15 * USEC_PER_MSEC); /* 15 ms */ params->limit = 1000; params->alpha = 2; params->beta = 20; params->ecn = false; params->bytemode = false; params->dq_rate_estimator = false; } static inline void pie_vars_init(struct pie_vars *vars) { vars->burst_time = PSCHED_NS2TICKS(150 * NSEC_PER_MSEC); /* 150 ms */ vars->dq_tstamp = DTIME_INVALID; vars->accu_prob = 0; vars->dq_count = DQCOUNT_INVALID; WRITE_ONCE(vars->avg_dq_rate, 0); } static inline struct pie_skb_cb *get_pie_cb(const struct sk_buff *skb) { qdisc_cb_private_validate(skb, sizeof(struct pie_skb_cb)); return (struct pie_skb_cb *)qdisc_skb_cb(skb)->data; } static inline psched_time_t pie_get_enqueue_time(const struct sk_buff *skb) { return get_pie_cb(skb)->enqueue_time; } static inline void pie_set_enqueue_time(struct sk_buff *skb) { get_pie_cb(skb)->enqueue_time = psched_get_time(); } bool pie_drop_early(struct Qdisc *sch, struct pie_params *params, struct pie_vars *vars, u32 backlog, u32 packet_size); void pie_process_dequeue(struct sk_buff *skb, struct pie_params *params, struct pie_vars *vars, u32 backlog); void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars, u32 backlog); #endif |
| 490 614 7 7 906 935 397 334 63 6 60 63 363 362 178 231 220 8 8 737 736 595 9 176 175 558 46 736 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/l3mdev/l3mdev.c - L3 master device implementation * Copyright (c) 2015 Cumulus Networks * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com> */ #include <linux/netdevice.h> #include <net/fib_rules.h> #include <net/l3mdev.h> static DEFINE_SPINLOCK(l3mdev_lock); struct l3mdev_handler { lookup_by_table_id_t dev_lookup; }; static struct l3mdev_handler l3mdev_handlers[L3MDEV_TYPE_MAX + 1]; static int l3mdev_check_type(enum l3mdev_type l3type) { if (l3type <= L3MDEV_TYPE_UNSPEC || l3type > L3MDEV_TYPE_MAX) return -EINVAL; return 0; } int l3mdev_table_lookup_register(enum l3mdev_type l3type, lookup_by_table_id_t fn) { struct l3mdev_handler *hdlr; int res; res = l3mdev_check_type(l3type); if (res) return res; hdlr = &l3mdev_handlers[l3type]; spin_lock(&l3mdev_lock); if (hdlr->dev_lookup) { res = -EBUSY; goto unlock; } hdlr->dev_lookup = fn; res = 0; unlock: spin_unlock(&l3mdev_lock); return res; } EXPORT_SYMBOL_GPL(l3mdev_table_lookup_register); void l3mdev_table_lookup_unregister(enum l3mdev_type l3type, lookup_by_table_id_t fn) { struct l3mdev_handler *hdlr; if (l3mdev_check_type(l3type)) return; hdlr = &l3mdev_handlers[l3type]; spin_lock(&l3mdev_lock); if (hdlr->dev_lookup == fn) hdlr->dev_lookup = NULL; spin_unlock(&l3mdev_lock); } EXPORT_SYMBOL_GPL(l3mdev_table_lookup_unregister); int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net, u32 table_id) { lookup_by_table_id_t lookup; struct l3mdev_handler *hdlr; int ifindex = -EINVAL; int res; res = l3mdev_check_type(l3type); if (res) return res; hdlr = &l3mdev_handlers[l3type]; spin_lock(&l3mdev_lock); lookup = hdlr->dev_lookup; if (!lookup) goto unlock; ifindex = lookup(net, table_id); unlock: spin_unlock(&l3mdev_lock); return ifindex; } EXPORT_SYMBOL_GPL(l3mdev_ifindex_lookup_by_table_id); /** * l3mdev_master_ifindex_rcu - get index of L3 master device * @dev: targeted interface */ int l3mdev_master_ifindex_rcu(const struct net_device *dev) { int ifindex = 0; if (!dev) return 0; if (netif_is_l3_master(dev)) { ifindex = dev->ifindex; } else if (netif_is_l3_slave(dev)) { struct net_device *master; struct net_device *_dev = (struct net_device *)dev; /* netdev_master_upper_dev_get_rcu calls * list_first_or_null_rcu to walk the upper dev list. * list_first_or_null_rcu does not handle a const arg. We aren't * making changes, just want the master device from that list so * typecast to remove the const */ master = netdev_master_upper_dev_get_rcu(_dev); if (master) ifindex = master->ifindex; } return ifindex; } EXPORT_SYMBOL_GPL(l3mdev_master_ifindex_rcu); /** * l3mdev_master_upper_ifindex_by_index_rcu - get index of upper l3 master * device * @net: network namespace for device index lookup * @ifindex: targeted interface */ int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex) { struct net_device *dev; dev = dev_get_by_index_rcu(net, ifindex); while (dev && !netif_is_l3_master(dev)) dev = netdev_master_upper_dev_get_rcu(dev); return dev ? dev->ifindex : 0; } EXPORT_SYMBOL_GPL(l3mdev_master_upper_ifindex_by_index_rcu); /** * l3mdev_fib_table_rcu - get FIB table id associated with an L3 * master interface * @dev: targeted interface */ u32 l3mdev_fib_table_rcu(const struct net_device *dev) { u32 tb_id = 0; if (!dev) return 0; if (netif_is_l3_master(dev)) { if (dev->l3mdev_ops->l3mdev_fib_table) tb_id = dev->l3mdev_ops->l3mdev_fib_table(dev); } else if (netif_is_l3_slave(dev)) { /* Users of netdev_master_upper_dev_get_rcu need non-const, * but current inet_*type functions take a const */ struct net_device *_dev = (struct net_device *) dev; const struct net_device *master; master = netdev_master_upper_dev_get_rcu(_dev); if (master && master->l3mdev_ops->l3mdev_fib_table) tb_id = master->l3mdev_ops->l3mdev_fib_table(master); } return tb_id; } EXPORT_SYMBOL_GPL(l3mdev_fib_table_rcu); u32 l3mdev_fib_table_by_index(struct net *net, int ifindex) { struct net_device *dev; u32 tb_id = 0; if (!ifindex) return 0; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) tb_id = l3mdev_fib_table_rcu(dev); rcu_read_unlock(); return tb_id; } EXPORT_SYMBOL_GPL(l3mdev_fib_table_by_index); /** * l3mdev_link_scope_lookup - IPv6 route lookup based on flow for link * local and multicast addresses * @net: network namespace for device index lookup * @fl6: IPv6 flow struct for lookup * This function does not hold refcnt on the returned dst. * Caller must hold rcu_read_lock(). */ struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6) { struct dst_entry *dst = NULL; struct net_device *dev; WARN_ON_ONCE(!rcu_read_lock_held()); if (fl6->flowi6_oif) { dev = dev_get_by_index_rcu(net, fl6->flowi6_oif); if (dev && netif_is_l3_slave(dev)) dev = netdev_master_upper_dev_get_rcu(dev); if (dev && netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_link_scope_lookup) dst = dev->l3mdev_ops->l3mdev_link_scope_lookup(dev, fl6); } return dst; } EXPORT_SYMBOL_GPL(l3mdev_link_scope_lookup); /** * l3mdev_fib_rule_match - Determine if flowi references an * L3 master device * @net: network namespace for device index lookup * @fl: flow struct * @arg: store the table the rule matched with here */ int l3mdev_fib_rule_match(struct net *net, struct flowi *fl, struct fib_lookup_arg *arg) { struct net_device *dev; int rc = 0; /* update flow ensures flowi_l3mdev is set when relevant */ if (!fl->flowi_l3mdev) return 0; rcu_read_lock(); dev = dev_get_by_index_rcu(net, fl->flowi_l3mdev); if (dev && netif_is_l3_master(dev) && dev->l3mdev_ops->l3mdev_fib_table) { arg->table = dev->l3mdev_ops->l3mdev_fib_table(dev); rc = 1; } rcu_read_unlock(); return rc; } void l3mdev_update_flow(struct net *net, struct flowi *fl) { struct net_device *dev; rcu_read_lock(); if (fl->flowi_oif) { dev = dev_get_by_index_rcu(net, fl->flowi_oif); if (dev) { if (!fl->flowi_l3mdev) { fl->flowi_l3mdev = l3mdev_master_ifindex_rcu(dev); fl->flowi_flags |= FLOWI_FLAG_L3MDEV_OIF; } /* oif set to L3mdev directs lookup to its table; * reset to avoid oif match in fib_lookup */ if (netif_is_l3_master(dev)) fl->flowi_oif = 0; goto out; } } if (fl->flowi_iif > LOOPBACK_IFINDEX && !fl->flowi_l3mdev) { dev = dev_get_by_index_rcu(net, fl->flowi_iif); if (dev) fl->flowi_l3mdev = l3mdev_master_ifindex_rcu(dev); } out: rcu_read_unlock(); } EXPORT_SYMBOL_GPL(l3mdev_update_flow); |
| 11 11 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM readahead #if !defined(_TRACE_FILEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_READAHEAD_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/fs.h> #include <linux/pagemap.h> TRACE_EVENT(page_cache_ra_unbounded, TP_PROTO(struct inode *inode, pgoff_t index, unsigned long nr_to_read, unsigned long lookahead_size), TP_ARGS(inode, index, nr_to_read, lookahead_size), TP_STRUCT__entry( __field(u64, i_ino) __field(dev_t, s_dev) __field(pgoff_t, index) __field(unsigned long, nr_to_read) __field(unsigned long, lookahead_size) ), TP_fast_assign( __entry->i_ino = inode->i_ino; __entry->s_dev = inode->i_sb->s_dev; __entry->index = index; __entry->nr_to_read = nr_to_read; __entry->lookahead_size = lookahead_size; ), TP_printk( "dev=%d:%d ino=%llx index=%lu nr_to_read=%lu lookahead_size=%lu", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->index, __entry->nr_to_read, __entry->lookahead_size ) ); TRACE_EVENT(page_cache_ra_order, TP_PROTO(struct inode *inode, pgoff_t index, struct file_ra_state *ra), TP_ARGS(inode, index, ra), TP_STRUCT__entry( __field(u64, i_ino) __field(dev_t, s_dev) __field(pgoff_t, index) __field(unsigned int, order) __field(unsigned int, size) __field(unsigned int, async_size) __field(unsigned int, ra_pages) ), TP_fast_assign( __entry->i_ino = inode->i_ino; __entry->s_dev = inode->i_sb->s_dev; __entry->index = index; __entry->order = ra->order; __entry->size = ra->size; __entry->async_size = ra->async_size; __entry->ra_pages = ra->ra_pages; ), TP_printk( "dev=%d:%d ino=%llx index=%lu order=%u size=%u async_size=%u ra_pages=%u", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->index, __entry->order, __entry->size, __entry->async_size, __entry->ra_pages ) ); DECLARE_EVENT_CLASS(page_cache_ra_op, TP_PROTO(struct inode *inode, pgoff_t index, struct file_ra_state *ra, unsigned long req_count), TP_ARGS(inode, index, ra, req_count), TP_STRUCT__entry( __field(u64, i_ino) __field(loff_t, prev_pos) __field(pgoff_t, index) __field(unsigned long, req_count) __field(dev_t, s_dev) __field(unsigned int, order) __field(unsigned int, size) __field(unsigned int, async_size) __field(unsigned int, ra_pages) __field(unsigned int, mmap_miss) ), TP_fast_assign( __entry->i_ino = inode->i_ino; __entry->s_dev = inode->i_sb->s_dev; __entry->index = index; __entry->order = ra->order; __entry->size = ra->size; __entry->async_size = ra->async_size; __entry->ra_pages = ra->ra_pages; __entry->mmap_miss = ra->mmap_miss; __entry->prev_pos = ra->prev_pos; __entry->req_count = req_count; ), TP_printk( "dev=%d:%d ino=%llx index=%lu req_count=%lu order=%u size=%u async_size=%u ra_pages=%u mmap_miss=%u prev_pos=%lld", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->index, __entry->req_count, __entry->order, __entry->size, __entry->async_size, __entry->ra_pages, __entry->mmap_miss, __entry->prev_pos ) ); DEFINE_EVENT(page_cache_ra_op, page_cache_sync_ra, TP_PROTO(struct inode *inode, pgoff_t index, struct file_ra_state *ra, unsigned long req_count), TP_ARGS(inode, index, ra, req_count) ); DEFINE_EVENT(page_cache_ra_op, page_cache_async_ra, TP_PROTO(struct inode *inode, pgoff_t index, struct file_ra_state *ra, unsigned long req_count), TP_ARGS(inode, index, ra, req_count) ); #endif /* _TRACE_FILEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 486 459 103 79 23 103 462 100 916 26 26 32 14 26 26 26 250 251 250 982 341 189 543 125 193 474 475 543 444 12 583 584 10 10 10 10 10 10 7 10 5 16 2 17 8 20 23 4 15 1 2 1 1 2 2 8 3 5 17 3 14 5 8 6 3 4 3 4 4 3 37 37 8 7 18 29 2 3 6 2 14 2 203 2 2 2 2 190 10 4 13 4 27 14 17 11 13 2 41 13 52 89 104 11 2 180 2 170 3 8 6 1 165 8 19 12 5 2 2 4 184 17 166 1 27 27 6 21 5 22 22 5 22 21 22 27 296 296 157 166 157 157 1 33 135 17 32 119 8 122 6 124 2 2 166 6 165 4 166 135 31 31 5 5 31 31 4 165 166 136 109 9 2 1 8 1 9 11 1 1 9 9 398 267 251 201 61 166 30 1235 176 1235 725 1158 200 284 178 49 71 119 31 31 31 31 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket * interface as the means of communication with the user level. * * IPv4 Forwarding Information Base: FIB frontend. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/module.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/capability.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> #include <linux/if_addr.h> #include <linux/if_arp.h> #include <linux/skbuff.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/list.h> #include <linux/slab.h> #include <net/flow.h> #include <net/inet_dscp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/tcp.h> #include <net/sock.h> #include <net/arp.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/rtnetlink.h> #include <net/xfrm.h> #include <net/l3mdev.h> #include <net/lwtunnel.h> #include <trace/events/fib.h> #ifndef CONFIG_IP_MULTIPLE_TABLES static int __net_init fib4_rules_init(struct net *net) { struct fib_table *local_table, *main_table; main_table = fib_trie_table(RT_TABLE_MAIN, NULL); if (!main_table) return -ENOMEM; local_table = fib_trie_table(RT_TABLE_LOCAL, main_table); if (!local_table) goto fail; hlist_add_head_rcu(&local_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]); hlist_add_head_rcu(&main_table->tb_hlist, &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]); return 0; fail: fib_free_table(main_table); return -ENOMEM; } #else struct fib_table *fib_new_table(struct net *net, u32 id) { struct fib_table *tb, *alias = NULL; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; tb = fib_get_table(net, id); if (tb) return tb; if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules) alias = fib_new_table(net, RT_TABLE_MAIN); tb = fib_trie_table(id, alias); if (!tb) return NULL; switch (id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, tb); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, tb); break; default: break; } h = id & (FIB_TABLE_HASHSZ - 1); hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]); return tb; } EXPORT_SYMBOL_GPL(fib_new_table); /* caller must hold either rtnl or rcu read lock */ struct fib_table *fib_get_table(struct net *net, u32 id) { struct fib_table *tb; struct hlist_head *head; unsigned int h; if (id == 0) id = RT_TABLE_MAIN; h = id & (FIB_TABLE_HASHSZ - 1); head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry_rcu(tb, head, tb_hlist, lockdep_rtnl_is_held()) { if (tb->tb_id == id) return tb; } return NULL; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ static void fib_replace_table(struct net *net, struct fib_table *old, struct fib_table *new) { #ifdef CONFIG_IP_MULTIPLE_TABLES switch (new->tb_id) { case RT_TABLE_MAIN: rcu_assign_pointer(net->ipv4.fib_main, new); break; case RT_TABLE_DEFAULT: rcu_assign_pointer(net->ipv4.fib_default, new); break; default: break; } #endif /* replace the old table in the hlist */ hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist); } int fib_unmerge(struct net *net) { struct fib_table *old, *new, *main_table; /* attempt to fetch local table if it has been allocated */ old = fib_get_table(net, RT_TABLE_LOCAL); if (!old) return 0; new = fib_trie_unmerge(old); if (!new) return -ENOMEM; /* table is already unmerged */ if (new == old) return 0; /* replace merged table with clean table */ fib_replace_table(net, old, new); fib_free_table(old); /* attempt to fetch main table if it has been allocated */ main_table = fib_get_table(net, RT_TABLE_MAIN); if (!main_table) return 0; /* flush local entries from main table */ fib_table_flush_external(main_table); return 0; } void fib_flush(struct net *net) { int flushed = 0; unsigned int h; for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct hlist_node *tmp; struct fib_table *tb; hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) flushed += fib_table_flush(net, tb, false); } if (flushed) rt_cache_flush(net); } /* * Find address type as if only "dev" was present in the system. If * on_dev is NULL then all interfaces are taken into consideration. */ static inline unsigned int __inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr, u32 tb_id) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; unsigned int ret = RTN_BROADCAST; struct fib_table *table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; if (ipv4_is_multicast(addr)) return RTN_MULTICAST; rcu_read_lock(); table = fib_get_table(net, tb_id); if (table) { ret = RTN_UNICAST; if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { struct fib_nh_common *nhc = fib_info_nhc(res.fi, 0); if (!dev || dev == nhc->nhc_dev) ret = res.type; } } rcu_read_unlock(); return ret; } unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id) { return __inet_dev_addr_type(net, NULL, addr, tb_id); } EXPORT_SYMBOL(inet_addr_type_table); unsigned int inet_addr_type(struct net *net, __be32 addr) { return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL); } EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, dev, addr, rt_table); } EXPORT_SYMBOL(inet_dev_addr_type); /* inet_addr_type with dev == NULL but using the table from a dev * if one is associated */ unsigned int inet_addr_type_dev_table(struct net *net, const struct net_device *dev, __be32 addr) { u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL; return __inet_dev_addr_type(net, NULL, addr, rt_table); } EXPORT_SYMBOL(inet_addr_type_dev_table); __be32 fib_compute_spec_dst(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct rtable *rt; struct net *net; int scope; rt = skb_rtable(skb); if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) == RTCF_LOCAL) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, .flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_dscp = ip4h_dscp(ip_hdr(skb)), .flowi4_scope = scope, .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return fib_result_prefsrc(net, &res); } else { scope = RT_SCOPE_LINK; } return inet_select_addr(dev, ip_hdr(skb)->saddr, scope); } bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev) { bool dev_match = false; #ifdef CONFIG_IP_ROUTE_MULTIPATH if (unlikely(fi->nh)) { dev_match = nexthop_uses_dev(fi->nh, dev); } else { int ret; for (ret = 0; ret < fib_info_num_path(fi); ret++) { const struct fib_nh_common *nhc = fib_info_nhc(fi, ret); if (nhc_l3mdev_matches_dev(nhc, dev)) { dev_match = true; break; } } } #else if (fib_info_nhc(fi, 0)->nhc_dev == dev) dev_match = true; #endif return dev_match; } EXPORT_SYMBOL_GPL(fib_info_nh_uses_dev); /* Given (packet source, input interface) and optional (dst, oif, tos): * - (main) check, that source is valid i.e. not broadcast or our local * address. * - figure out what "logical" interface this packet arrived * and calculate "specific destination" address. * - check, that packet arrived from expected physical interface. * called with rcu_read_lock() */ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, int rpf, struct in_device *idev, u32 *itag) { struct net *net = dev_net(dev); enum skb_drop_reason reason; struct flow_keys flkeys; int ret, no_addr; struct fib_result res; struct flowi4 fl4; bool dev_match; fl4.flowi4_oif = 0; fl4.flowi4_l3mdev = l3mdev_master_ifindex_rcu(dev); fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_dscp = dscp; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_tun_key.tun_id = 0; fl4.flowi4_flags = 0; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } else { swap(fl4.fl4_sport, fl4.fl4_dport); } if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; if (res.type != RTN_UNICAST) { if (res.type != RTN_LOCAL) { reason = SKB_DROP_REASON_IP_INVALID_SOURCE; goto e_inval; } else if (!IN_DEV_ACCEPT_LOCAL(idev)) { reason = SKB_DROP_REASON_IP_LOCAL_SOURCE; goto e_inval; } } fib_combine_itag(itag, &res); dev_match = fib_info_nh_uses_dev(res.fi, dev); /* This is not common, loopback packets retain skb_dst so normally they * would not even hit this slow path. */ dev_match = dev_match || (res.type == RTN_LOCAL && dev == net->loopback_dev); if (dev_match) { ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; return ret; } if (no_addr) goto last_resort; if (rpf == 1) goto e_rpf; fl4.flowi4_oif = dev->ifindex; ret = 0; if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) { if (res.type == RTN_UNICAST) ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST; } return ret; last_resort: if (rpf) goto e_rpf; *itag = 0; return 0; e_inval: return -reason; e_rpf: return -SKB_DROP_REASON_IP_RPFILTER; } /* Ignore rp_filter for packets protected by IPsec. */ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, dscp_t dscp, int oif, struct net_device *dev, struct in_device *idev, u32 *itag) { int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev); struct net *net = dev_net(dev); if (!r && !fib_num_tclassid_users(net) && (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) { if (IN_DEV_ACCEPT_LOCAL(idev)) goto ok; /* with custom local routes in place, checking local addresses * only will be too optimistic, with custom rules, checking * local addresses only can be too strict, e.g. due to vrf */ if (net->ipv4.fib_has_custom_local_routes || fib4_has_custom_rules(net)) goto full_check; /* Within the same container, it is regarded as a martian source, * and the same host but different containers are not. */ if (inet_lookup_ifaddr_rcu(net, src)) return -SKB_DROP_REASON_IP_LOCAL_SOURCE; ok: *itag = 0; return 0; } full_check: return __fib_validate_source(skb, src, dst, dscp, oif, dev, r, idev, itag); } static inline __be32 sk_extract_addr(struct sockaddr *addr) { return ((struct sockaddr_in *) addr)->sin_addr.s_addr; } static int put_rtax(struct nlattr *mx, int len, int type, u32 value) { struct nlattr *nla; nla = (struct nlattr *) ((char *) mx + len); nla->nla_type = type; nla->nla_len = nla_attr_size(4); *(u32 *) nla_data(nla) = value; return len + nla_total_size(4); } static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, struct fib_config *cfg) { __be32 addr; int plen; memset(cfg, 0, sizeof(*cfg)); cfg->fc_nlinfo.nl_net = net; if (rt->rt_dst.sa_family != AF_INET) return -EAFNOSUPPORT; /* * Check mask for validity: * a) it must be contiguous. * b) destination must have all host bits clear. * c) if application forgot to set correct family (AF_INET), * reject request unless it is absolutely clear i.e. * both family and mask are zero. */ plen = 32; addr = sk_extract_addr(&rt->rt_dst); if (!(rt->rt_flags & RTF_HOST)) { __be32 mask = sk_extract_addr(&rt->rt_genmask); if (rt->rt_genmask.sa_family != AF_INET) { if (mask || rt->rt_genmask.sa_family) return -EAFNOSUPPORT; } if (bad_mask(mask, addr)) return -EINVAL; plen = inet_mask_len(mask); } cfg->fc_dst_len = plen; cfg->fc_dst = addr; if (cmd != SIOCDELRT) { cfg->fc_nlflags = NLM_F_CREATE; cfg->fc_protocol = RTPROT_BOOT; } if (rt->rt_metric) cfg->fc_priority = rt->rt_metric - 1; if (rt->rt_flags & RTF_REJECT) { cfg->fc_scope = RT_SCOPE_HOST; cfg->fc_type = RTN_UNREACHABLE; return 0; } cfg->fc_scope = RT_SCOPE_NOWHERE; cfg->fc_type = RTN_UNICAST; if (rt->rt_dev) { char *colon; struct net_device *dev; char devname[IFNAMSIZ]; if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1)) return -EFAULT; devname[IFNAMSIZ-1] = 0; colon = strchr(devname, ':'); if (colon) *colon = 0; dev = __dev_get_by_name(net, devname); if (!dev) return -ENODEV; cfg->fc_oif = dev->ifindex; cfg->fc_table = l3mdev_fib_table(dev); if (colon) { const struct in_ifaddr *ifa; struct in_device *in_dev; in_dev = __in_dev_get_rtnl_net(dev); if (!in_dev) return -ENODEV; *colon = ':'; in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) { if (strcmp(ifa->ifa_label, devname) == 0) break; } if (!ifa) return -ENODEV; cfg->fc_prefsrc = ifa->ifa_local; } } addr = sk_extract_addr(&rt->rt_gateway); if (rt->rt_gateway.sa_family == AF_INET && addr) { unsigned int addr_type; cfg->fc_gw4 = addr; cfg->fc_gw_family = AF_INET; addr_type = inet_addr_type_table(net, addr, cfg->fc_table); if (rt->rt_flags & RTF_GATEWAY && addr_type == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } if (!cfg->fc_table) cfg->fc_table = RT_TABLE_MAIN; if (cmd == SIOCDELRT) return 0; if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family) return -EINVAL; if (cfg->fc_scope == RT_SCOPE_NOWHERE) cfg->fc_scope = RT_SCOPE_LINK; if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) { struct nlattr *mx; int len = 0; mx = kcalloc(3, nla_total_size(4), GFP_KERNEL); if (!mx) return -ENOMEM; if (rt->rt_flags & RTF_MTU) len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40); if (rt->rt_flags & RTF_WINDOW) len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window); if (rt->rt_flags & RTF_IRTT) len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3); cfg->fc_mx = mx; cfg->fc_mx_len = len; } return 0; } /* * Handle IP routing ioctl calls. * These are used to manipulate the routing tables */ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt) { struct fib_config cfg; int err; |