| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_NULLS_H #define _LINUX_LIST_NULLS_H #include <linux/poison.h> #include <linux/const.h> /* * Special version of lists, where end of list is not a NULL pointer, * but a 'nulls' marker, which can have many different values. * (up to 2^31 different values guaranteed on all platforms) * * In the standard hlist, termination of a list is the NULL pointer. * In this special 'nulls' variant, we use the fact that objects stored in * a list are aligned on a word (4 or 8 bytes alignment). * We therefore use the last significant bit of 'ptr' : * Set to 1 : This is a 'nulls' end-of-list marker (ptr >> 1) * Set to 0 : This is a pointer to some object (ptr) */ struct hlist_nulls_head { struct hlist_nulls_node *first; }; struct hlist_nulls_node { struct hlist_nulls_node *next, **pprev; }; #define NULLS_MARKER(value) (1UL | (((long)value) << 1)) #define INIT_HLIST_NULLS_HEAD(ptr, nulls) \ ((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls)) #define HLIST_NULLS_HEAD_INIT(nulls) {.first = (struct hlist_nulls_node *)NULLS_MARKER(nulls)} #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member) #define hlist_nulls_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ !is_a_nulls(____ptr) ? hlist_nulls_entry(____ptr, type, member) : NULL; \ }) /** * ptr_is_a_nulls - Test if a ptr is a nulls * @ptr: ptr to be tested * */ static inline int is_a_nulls(const struct hlist_nulls_node *ptr) { return ((unsigned long)ptr & 1); } /** * get_nulls_value - Get the 'nulls' value of the end of chain * @ptr: end of chain * * Should be called only if is_a_nulls(ptr); */ static inline unsigned long get_nulls_value(const struct hlist_nulls_node *ptr) { return ((unsigned long)ptr) >> 1; } /** * hlist_nulls_unhashed - Has node been removed and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed state. * For example, hlist_del_init_rcu() leaves the node in unhashed state, * but hlist_nulls_del() does not. */ static inline int hlist_nulls_unhashed(const struct hlist_nulls_node *h) { return !h->pprev; } /** * hlist_nulls_unhashed_lockless - Has node been removed and reinitialized? * @h: Node to be checked * * Not that not all removal functions will leave a node in unhashed state. * For example, hlist_del_init_rcu() leaves the node in unhashed state, * but hlist_nulls_del() does not. Unlike hlist_nulls_unhashed(), this * function may be used locklessly. */ static inline int hlist_nulls_unhashed_lockless(const struct hlist_nulls_node *h) { return !READ_ONCE(h->pprev); } static inline int hlist_nulls_empty(const struct hlist_nulls_head *h) { return is_a_nulls(READ_ONCE(h->first)); } static inline void hlist_nulls_add_head(struct hlist_nulls_node *n, struct hlist_nulls_head *h) { struct hlist_nulls_node *first = h->first; n->next = first; WRITE_ONCE(n->pprev, &h->first); h->first = n; if (!is_a_nulls(first)) WRITE_ONCE(first->pprev, &n->next); } static inline void __hlist_nulls_del(struct hlist_nulls_node *n) { struct hlist_nulls_node *next = n->next; struct hlist_nulls_node **pprev = n->pprev; WRITE_ONCE(*pprev, next); if (!is_a_nulls(next)) WRITE_ONCE(next->pprev, pprev); } static inline void hlist_nulls_del(struct hlist_nulls_node *n) { __hlist_nulls_del(n); WRITE_ONCE(n->pprev, LIST_POISON2); } /** * hlist_nulls_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_nulls_for_each_entry(tpos, pos, head, member) \ for (pos = (head)->first; \ (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_nulls_for_each_entry_from - iterate over a hlist continuing from current point * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @member: the name of the hlist_node within the struct. * */ #define hlist_nulls_for_each_entry_from(tpos, pos, member) \ for (; (!is_a_nulls(pos)) && \ ({ tpos = hlist_nulls_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) #endif |
| 82 82 620 29 672 63 170 40 18 56 55 113 433 434 427 12 278 36 155 155 15 143 15 142 155 2 13 119 21 136 5 7 64 69 5 8 20 2 117 13 109 338 338 179 849 822 45 5 5 5 25 768 535 234 398 537 538 25 72 271 294 294 286 50 911 911 2 912 611 248 653 751 72 765 894 224 351 4 292 79 218 273 201 200 40 151 236 236 231 190 42 37 73 51 20 48 685 672 210 91 54 663 125 39 101 124 484 89 466 234 486 32 7 482 484 207 484 7 4 3 152 151 153 136 87 152 147 81 96 153 86 151 151 112 31 28 135 85 74 95 88 18 12 14 153 14 31 147 114 1 113 113 81 3 58 105 105 105 64 92 104 105 105 6 21 1 20 26 26 109 109 103 7 4 99 103 84 56 63 81 103 98 1 44 30 30 30 581 564 25 25 25 161 128 102 40 40 102 33 102 102 102 40 5 40 40 101 22 22 22 24 20 24 6 36 36 36 33 24 26 10 4 22 12 22 4 30 14 2 42 43 43 43 42 42 42 42 15 12 4 4 122 122 122 122 122 122 64 78 139 36 76 76 1 46 155 155 155 19 102 152 57 98 78 110 28 25 7 38 2 40 35 33 40 31 20 40 40 40 31 28 76 76 76 16 41 1 37 37 76 76 3 16 22 40 28 24 21 2 23 161 161 161 161 42 20 56 155 155 9 155 155 155 13 155 38 155 154 154 155 40 54 143 143 176 19 150 14 161 76 87 161 161 161 130 102 102 102 35 76 101 102 102 102 128 160 187 11 175 122 114 1 114 43 38 16 41 41 41 35 35 34 26 35 35 2 41 35 24 33 2 24 112 69 43 11 38 2 41 41 53 53 48 6 8 8 5 2 41 41 16 26 68 67 138 138 137 172 172 172 29 69 69 54 27 69 68 67 57 13 21 21 49 49 2 27 36 4 36 36 36 17 36 12 35 61 61 61 61 7 4 36 32 24 55 2 2 54 16 16 14 2 15 11 3 15 25 25 25 432 430 300 133 200 105 123 200 200 98 137 105 94 111 53 159 159 199 200 200 10 127 121 121 3 13 39 84 47 87 122 226 67 6 3 47 47 9 40 1 35 35 29 8 20 20 47 47 11 1 6 30 119 118 32 32 32 10 22 5 3 28 10 21 30 31 1 10 21 31 1 20 10 292 292 289 74 218 289 288 184 111 242 58 160 119 148 95 7 157 118 94 144 176 38 59 179 214 24 289 726 26 8 9 737 735 661 114 68 68 737 737 737 736 12 725 39 38 1 734 12 274 13 443 732 6 292 451 735 1055 6 9 1053 1055 430 1 5 5 30 5 26 5 5 2 256 192 448 449 400 400 5 597 471 4 16 455 778 779 778 645 273 9 371 399 312 25 65 157 631 8 634 1 635 575 1 445 735 733 663 494 427 3 11 45 4 637 19 407 2 241 620 29 649 1 613 9 33 106 541 637 78 4 4 392 253 645 646 205 438 641 239 33 398 641 390 640 400 14 232 43 379 639 4 639 29 549 24 385 175 561 12 344 504 1 10 1 2 7 9 8 4 15 2 632 7 10 626 101 132 51 1 1 1 1 1 132 132 132 132 132 734 9 736 734 9 26 603 132 735 7 7 735 733 735 112 10 2 100 99 99 94 1 1 1 83 8 86 4 89 65 88 18 18 18 43 27 20 30 6 4 40 42 4 10 30 14 14 42 1 13 30 13 34 43 87 87 23 7 74 81 61 5 127 124 4 123 6 2 124 5 125 3 126 2 112 17 125 2 125 3 127 1 106 84 22 106 106 159 255 7 367 366 304 304 50 206 738 13 737 754 51 11 737 92 41 2 23 45 64 90 90 90 2 2 2 2 739 740 61 669 97 721 581 38 562 6 6 6 1 5 5 2 3 13 13 2 7 10 5 7 7 5 3 1 6 3 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/inode.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds * * 64-bit file support on 64-bit platforms by Jakub Jelinek * (jj@sunsite.ms.mff.cuni.cz) * * Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000 */ #include <linux/fs.h> #include <linux/mount.h> #include <linux/time.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/dax.h> #include <linux/quotaops.h> #include <linux/string.h> #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/pagevec.h> #include <linux/mpage.h> #include <linux/rmap.h> #include <linux/namei.h> #include <linux/uio.h> #include <linux/bio.h> #include <linux/workqueue.h> #include <linux/kernel.h> #include <linux/printk.h> #include <linux/slab.h> #include <linux/bitops.h> #include <linux/iomap.h> #include <linux/iversion.h> #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "truncate.h" #include <trace/events/ext4.h> static void ext4_journalled_zero_new_buffers(handle_t *handle, struct inode *inode, struct folio *folio, unsigned from, unsigned to); static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { __u32 csum; __u16 dummy_csum = 0; int offset = offsetof(struct ext4_inode, i_checksum_lo); unsigned int csum_size = sizeof(dummy_csum); csum = ext4_chksum(ei->i_csum_seed, (__u8 *)raw, offset); csum = ext4_chksum(csum, (__u8 *)&dummy_csum, csum_size); offset += csum_size; csum = ext4_chksum(csum, (__u8 *)raw + offset, EXT4_GOOD_OLD_INODE_SIZE - offset); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { offset = offsetof(struct ext4_inode, i_checksum_hi); csum = ext4_chksum(csum, (__u8 *)raw + EXT4_GOOD_OLD_INODE_SIZE, offset - EXT4_GOOD_OLD_INODE_SIZE); if (EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) { csum = ext4_chksum(csum, (__u8 *)&dummy_csum, csum_size); offset += csum_size; } csum = ext4_chksum(csum, (__u8 *)raw + offset, EXT4_INODE_SIZE(inode->i_sb) - offset); } return csum; } static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { __u32 provided, calculated; if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || !ext4_has_feature_metadata_csum(inode->i_sb)) return 1; provided = le16_to_cpu(raw->i_checksum_lo); calculated = ext4_inode_csum(inode, raw, ei); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) provided |= ((__u32)le16_to_cpu(raw->i_checksum_hi)) << 16; else calculated &= 0xFFFF; return provided == calculated; } void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { __u32 csum; if (EXT4_SB(inode->i_sb)->s_es->s_creator_os != cpu_to_le32(EXT4_OS_LINUX) || !ext4_has_feature_metadata_csum(inode->i_sb)) return; csum = ext4_inode_csum(inode, raw, ei); raw->i_checksum_lo = cpu_to_le16(csum & 0xFFFF); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw, ei, i_checksum_hi)) raw->i_checksum_hi = cpu_to_le16(csum >> 16); } static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { trace_ext4_begin_ordered_truncate(inode, new_size); /* * If jinode is zero, then we never opened the file for * writing, so there's no need to call * jbd2_journal_begin_ordered_truncate() since there's no * outstanding writes we need to flush. */ if (!EXT4_I(inode)->jinode) return 0; return jbd2_journal_begin_ordered_truncate(EXT4_JOURNAL(inode), EXT4_I(inode)->jinode, new_size); } /* * Test whether an inode is a fast symlink. * A fast symlink has its symlink data stored in ext4_inode_info->i_data. */ int ext4_inode_is_fast_symlink(struct inode *inode) { if (!ext4_has_feature_ea_inode(inode->i_sb)) { int ea_blocks = EXT4_I(inode)->i_file_acl ? EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0; if (ext4_has_inline_data(inode)) return 0; return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0); } return S_ISLNK(inode->i_mode) && inode->i_size && (inode->i_size < EXT4_N_BLOCKS * 4); } /* * Called at the last iput() if i_nlink is zero. */ void ext4_evict_inode(struct inode *inode) { handle_t *handle; int err; /* * Credits for final inode cleanup and freeing: * sb + inode (ext4_orphan_del()), block bitmap, group descriptor * (xattr block freeing), bitmap, group descriptor (inode freeing) */ int extra_credits = 6; struct ext4_xattr_inode_array *ea_inode_array = NULL; bool freeze_protected = false; trace_ext4_evict_inode(inode); dax_break_layout_final(inode); if (EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL) ext4_evict_ea_inode(inode); if (inode->i_nlink) { truncate_inode_pages_final(&inode->i_data); goto no_delete; } if (is_bad_inode(inode)) goto no_delete; dquot_initialize(inode); if (ext4_should_order_data(inode)) ext4_begin_ordered_truncate(inode, 0); truncate_inode_pages_final(&inode->i_data); /* * For inodes with journalled data, transaction commit could have * dirtied the inode. And for inodes with dioread_nolock, unwritten * extents converting worker could merge extents and also have dirtied * the inode. Flush worker is ignoring it because of I_FREEING flag but * we still need to remove the inode from the writeback lists. */ if (!list_empty_careful(&inode->i_io_list)) inode_io_list_del(inode); /* * Protect us against freezing - iput() caller didn't have to have any * protection against it. When we are in a running transaction though, * we are already protected against freezing and we cannot grab further * protection due to lock ordering constraints. */ if (!ext4_journal_current_handle()) { sb_start_intwrite(inode->i_sb); freeze_protected = true; } if (!IS_NOQUOTA(inode)) extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb); /* * Block bitmap, group descriptor, and inode are accounted in both * ext4_blocks_for_truncate() and extra_credits. So subtract 3. */ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, ext4_blocks_for_truncate(inode) + extra_credits - 3); if (IS_ERR(handle)) { ext4_std_error(inode->i_sb, PTR_ERR(handle)); /* * If we're going to skip the normal cleanup, we still need to * make sure that the in-core orphan linked list is properly * cleaned up. */ ext4_orphan_del(NULL, inode); if (freeze_protected) sb_end_intwrite(inode->i_sb); goto no_delete; } if (IS_SYNC(inode)) ext4_handle_sync(handle); /* * Set inode->i_size to 0 before calling ext4_truncate(). We need * special handling of symlinks here because i_size is used to * determine whether ext4_inode_info->i_data contains symlink data or * block mappings. Setting i_size to 0 will remove its fast symlink * status. Erase i_data so that it becomes a valid empty block map. */ if (ext4_inode_is_fast_symlink(inode)) memset(EXT4_I(inode)->i_data, 0, sizeof(EXT4_I(inode)->i_data)); inode->i_size = 0; err = ext4_mark_inode_dirty(handle, inode); if (err) { ext4_warning(inode->i_sb, "couldn't mark inode dirty (err %d)", err); goto stop_handle; } if (inode->i_blocks) { err = ext4_truncate(inode); if (err) { ext4_error_err(inode->i_sb, -err, "couldn't truncate inode %lu (err %d)", inode->i_ino, err); goto stop_handle; } } /* Remove xattr references. */ err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array, extra_credits); if (err) { ext4_warning(inode->i_sb, "xattr delete (err %d)", err); stop_handle: ext4_journal_stop(handle); ext4_orphan_del(NULL, inode); if (freeze_protected) sb_end_intwrite(inode->i_sb); ext4_xattr_inode_array_free(ea_inode_array); goto no_delete; } /* * Kill off the orphan record which ext4_truncate created. * AKPM: I think this can be inside the above `if'. * Note that ext4_orphan_del() has to be able to cope with the * deletion of a non-existent orphan - this is because we don't * know if ext4_truncate() actually created an orphan record. * (Well, we could do this if we need to, but heck - it works) */ ext4_orphan_del(handle, inode); EXT4_I(inode)->i_dtime = (__u32)ktime_get_real_seconds(); /* * One subtle ordering requirement: if anything has gone wrong * (transaction abort, IO errors, whatever), then we can still * do these next steps (the fs will already have been marked as * having errors), but we can't free the inode if the mark_dirty * fails. */ if (ext4_mark_inode_dirty(handle, inode)) /* If that failed, just do the required in-core inode clear. */ ext4_clear_inode(inode); else ext4_free_inode(handle, inode); ext4_journal_stop(handle); if (freeze_protected) sb_end_intwrite(inode->i_sb); ext4_xattr_inode_array_free(ea_inode_array); return; no_delete: /* * Check out some where else accidentally dirty the evicting inode, * which may probably cause inode use-after-free issues later. */ WARN_ON_ONCE(!list_empty_careful(&inode->i_io_list)); if (!list_empty(&EXT4_I(inode)->i_fc_list)) ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_NOMEM, NULL); ext4_clear_inode(inode); /* We must guarantee clearing of inode... */ } #ifdef CONFIG_QUOTA qsize_t *ext4_get_reserved_space(struct inode *inode) { return &EXT4_I(inode)->i_reserved_quota; } #endif /* * Called with i_data_sem down, which is important since we can call * ext4_discard_preallocations() from here. */ void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); spin_lock(&ei->i_block_reservation_lock); trace_ext4_da_update_reserve_space(inode, used, quota_claim); if (unlikely(used > ei->i_reserved_data_blocks)) { ext4_warning(inode->i_sb, "%s: ino %lu, used %d " "with only %d reserved data blocks", __func__, inode->i_ino, used, ei->i_reserved_data_blocks); WARN_ON(1); used = ei->i_reserved_data_blocks; } /* Update per-inode reservations */ ei->i_reserved_data_blocks -= used; percpu_counter_sub(&sbi->s_dirtyclusters_counter, used); spin_unlock(&ei->i_block_reservation_lock); /* Update quota subsystem for data blocks */ if (quota_claim) dquot_claim_block(inode, EXT4_C2B(sbi, used)); else { /* * We did fallocate with an offset that is already delayed * allocated. So on delayed allocated writeback we should * not re-claim the quota for fallocated blocks. */ dquot_release_reservation_block(inode, EXT4_C2B(sbi, used)); } /* * If we have done all the pending block allocations and if * there aren't any writers on the inode, we can discard the * inode's preallocations. */ if ((ei->i_reserved_data_blocks == 0) && !inode_is_open_for_write(inode)) ext4_discard_preallocations(inode); } static int __check_block_validity(struct inode *inode, const char *func, unsigned int line, struct ext4_map_blocks *map) { journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; if (journal && inode == journal->j_inode) return 0; if (!ext4_inode_block_valid(inode, map->m_pblk, map->m_len)) { ext4_error_inode(inode, func, line, map->m_pblk, "lblock %lu mapped to illegal pblock %llu " "(length %d)", (unsigned long) map->m_lblk, map->m_pblk, map->m_len); return -EFSCORRUPTED; } return 0; } int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, ext4_lblk_t len) { int ret; if (IS_ENCRYPTED(inode) && S_ISREG(inode->i_mode)) return fscrypt_zeroout_range(inode, lblk, pblk, len); ret = sb_issue_zeroout(inode->i_sb, pblk, len, GFP_NOFS); if (ret > 0) ret = 0; return ret; } /* * For generic regular files, when updating the extent tree, Ext4 should * hold the i_rwsem and invalidate_lock exclusively. This ensures * exclusion against concurrent page faults, as well as reads and writes. */ #ifdef CONFIG_EXT4_DEBUG void ext4_check_map_extents_env(struct inode *inode) { if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) return; if (!S_ISREG(inode->i_mode) || IS_NOQUOTA(inode) || IS_VERITY(inode) || is_special_ino(inode->i_sb, inode->i_ino) || (inode->i_state & (I_FREEING | I_WILL_FREE | I_NEW)) || ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE) || ext4_verity_in_progress(inode)) return; WARN_ON_ONCE(!inode_is_locked(inode) && !rwsem_is_locked(&inode->i_mapping->invalidate_lock)); } #else void ext4_check_map_extents_env(struct inode *inode) {} #endif #define check_block_validity(inode, map) \ __check_block_validity((inode), __func__, __LINE__, (map)) #ifdef ES_AGGRESSIVE_TEST static void ext4_map_blocks_es_recheck(handle_t *handle, struct inode *inode, struct ext4_map_blocks *es_map, struct ext4_map_blocks *map, int flags) { int retval; map->m_flags = 0; /* * There is a race window that the result is not the same. * e.g. xfstests #223 when dioread_nolock enables. The reason * is that we lookup a block mapping in extent status tree with * out taking i_data_sem. So at the time the unwritten extent * could be converted. */ down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, 0); } else { retval = ext4_ind_map_blocks(handle, inode, map, 0); } up_read((&EXT4_I(inode)->i_data_sem)); /* * We don't check m_len because extent will be collpased in status * tree. So the m_len might not equal. */ if (es_map->m_lblk != map->m_lblk || es_map->m_flags != map->m_flags || es_map->m_pblk != map->m_pblk) { printk("ES cache assertion failed for inode: %lu " "es_cached ex [%d/%d/%llu/%x] != " "found ex [%d/%d/%llu/%x] retval %d flags %x\n", inode->i_ino, es_map->m_lblk, es_map->m_len, es_map->m_pblk, es_map->m_flags, map->m_lblk, map->m_len, map->m_pblk, map->m_flags, retval, flags); } } #endif /* ES_AGGRESSIVE_TEST */ static int ext4_map_query_blocks_next_in_leaf(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, unsigned int orig_mlen) { struct ext4_map_blocks map2; unsigned int status, status2; int retval; status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; WARN_ON_ONCE(!(map->m_flags & EXT4_MAP_QUERY_LAST_IN_LEAF)); WARN_ON_ONCE(orig_mlen <= map->m_len); /* Prepare map2 for lookup in next leaf block */ map2.m_lblk = map->m_lblk + map->m_len; map2.m_len = orig_mlen - map->m_len; map2.m_flags = 0; retval = ext4_ext_map_blocks(handle, inode, &map2, 0); if (retval <= 0) { ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status, false); return map->m_len; } if (unlikely(retval != map2.m_len)) { ext4_warning(inode->i_sb, "ES len assertion failed for inode " "%lu: retval %d != map->m_len %d", inode->i_ino, retval, map2.m_len); WARN_ON(1); } status2 = map2.m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; /* * If map2 is contiguous with map, then let's insert it as a single * extent in es cache and return the combined length of both the maps. */ if (map->m_pblk + map->m_len == map2.m_pblk && status == status2) { ext4_es_insert_extent(inode, map->m_lblk, map->m_len + map2.m_len, map->m_pblk, status, false); map->m_len += map2.m_len; } else { ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status, false); } return map->m_len; } static int ext4_map_query_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { unsigned int status; int retval; unsigned int orig_mlen = map->m_len; flags &= EXT4_EX_QUERY_FILTER; if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) retval = ext4_ext_map_blocks(handle, inode, map, flags); else retval = ext4_ind_map_blocks(handle, inode, map, flags); if (retval <= 0) return retval; if (unlikely(retval != map->m_len)) { ext4_warning(inode->i_sb, "ES len assertion failed for inode " "%lu: retval %d != map->m_len %d", inode->i_ino, retval, map->m_len); WARN_ON(1); } /* * No need to query next in leaf: * - if returned extent is not last in leaf or * - if the last in leaf is the full requested range */ if (!(map->m_flags & EXT4_MAP_QUERY_LAST_IN_LEAF) || map->m_len == orig_mlen) { status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status, false); return retval; } return ext4_map_query_blocks_next_in_leaf(handle, inode, map, orig_mlen); } static int ext4_map_create_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct extent_status es; unsigned int status; int err, retval = 0; /* * We pass in the magic EXT4_GET_BLOCKS_DELALLOC_RESERVE * indicates that the blocks and quotas has already been * checked when the data was copied into the page cache. */ if (map->m_flags & EXT4_MAP_DELAYED) flags |= EXT4_GET_BLOCKS_DELALLOC_RESERVE; /* * Here we clear m_flags because after allocating an new extent, * it will be set again. */ map->m_flags &= ~EXT4_MAP_FLAGS; /* * We need to check for EXT4 here because migrate could have * changed the inode type in between. */ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, flags); } else { retval = ext4_ind_map_blocks(handle, inode, map, flags); /* * We allocated new blocks which will result in i_data's * format changing. Force the migrate to fail by clearing * migrate flags. */ if (retval > 0 && map->m_flags & EXT4_MAP_NEW) ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE); } if (retval <= 0) return retval; if (unlikely(retval != map->m_len)) { ext4_warning(inode->i_sb, "ES len assertion failed for inode %lu: " "retval %d != map->m_len %d", inode->i_ino, retval, map->m_len); WARN_ON(1); } /* * We have to zeroout blocks before inserting them into extent * status tree. Otherwise someone could look them up there and * use them before they are really zeroed. We also have to * unmap metadata before zeroing as otherwise writeback can * overwrite zeros with stale data from block device. */ if (flags & EXT4_GET_BLOCKS_ZERO && map->m_flags & EXT4_MAP_MAPPED && map->m_flags & EXT4_MAP_NEW) { err = ext4_issue_zeroout(inode, map->m_lblk, map->m_pblk, map->m_len); if (err) return err; } /* * If the extent has been zeroed out, we don't need to update * extent status tree. */ if (flags & EXT4_GET_BLOCKS_PRE_IO && ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) { if (ext4_es_is_written(&es)) return retval; } status = map->m_flags & EXT4_MAP_UNWRITTEN ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN; ext4_es_insert_extent(inode, map->m_lblk, map->m_len, map->m_pblk, status, flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE); return retval; } /* * The ext4_map_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. * * Otherwise it takes the write lock of the i_data_sem and allocate blocks * and store the allocated blocks in the result buffer head and mark it * mapped. * * If file type is extents based, it will call ext4_ext_map_blocks(), * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping * based files * * On success, it returns the number of blocks being mapped or allocated. * If flags doesn't contain EXT4_GET_BLOCKS_CREATE the blocks are * pre-allocated and unwritten, the resulting @map is marked as unwritten. * If the flags contain EXT4_GET_BLOCKS_CREATE, it will mark @map as mapped. * * It returns 0 if plain look up failed (blocks have not been allocated), in * that case, @map is returned as unmapped but we still do fill map->m_len to * indicate the length of a hole starting at map->m_lblk. * * It returns the error in case of allocation failure. */ int ext4_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct extent_status es; int retval; int ret = 0; unsigned int orig_mlen = map->m_len; #ifdef ES_AGGRESSIVE_TEST struct ext4_map_blocks orig_map; memcpy(&orig_map, map, sizeof(*map)); #endif map->m_flags = 0; ext_debug(inode, "flag 0x%x, max_blocks %u, logical block %lu\n", flags, map->m_len, (unsigned long) map->m_lblk); /* * ext4_map_blocks returns an int, and m_len is an unsigned int */ if (unlikely(map->m_len > INT_MAX)) map->m_len = INT_MAX; /* We can handle the block number less than EXT_MAX_BLOCKS */ if (unlikely(map->m_lblk >= EXT_MAX_BLOCKS)) return -EFSCORRUPTED; /* * Callers from the context of data submission are the only exceptions * for regular files that do not hold the i_rwsem or invalidate_lock. * However, caching unrelated ranges is not permitted. */ if (flags & EXT4_GET_BLOCKS_IO_SUBMIT) WARN_ON_ONCE(!(flags & EXT4_EX_NOCACHE)); else ext4_check_map_extents_env(inode); /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) { if (ext4_es_is_written(&es) || ext4_es_is_unwritten(&es)) { map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk; map->m_flags |= ext4_es_is_written(&es) ? EXT4_MAP_MAPPED : EXT4_MAP_UNWRITTEN; retval = es.es_len - (map->m_lblk - es.es_lblk); if (retval > map->m_len) retval = map->m_len; map->m_len = retval; } else if (ext4_es_is_delayed(&es) || ext4_es_is_hole(&es)) { map->m_pblk = 0; map->m_flags |= ext4_es_is_delayed(&es) ? EXT4_MAP_DELAYED : 0; retval = es.es_len - (map->m_lblk - es.es_lblk); if (retval > map->m_len) retval = map->m_len; map->m_len = retval; retval = 0; } else { BUG(); } if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT) return retval; #ifdef ES_AGGRESSIVE_TEST ext4_map_blocks_es_recheck(handle, inode, map, &orig_map, flags); #endif if (!(flags & EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF) || orig_mlen == map->m_len) goto found; map->m_len = orig_mlen; } /* * In the query cache no-wait mode, nothing we can do more if we * cannot find extent in the cache. */ if (flags & EXT4_GET_BLOCKS_CACHED_NOWAIT) return 0; /* * Try to see if we can get the block without requesting a new * file system block. */ down_read(&EXT4_I(inode)->i_data_sem); retval = ext4_map_query_blocks(handle, inode, map, flags); up_read((&EXT4_I(inode)->i_data_sem)); found: if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { ret = check_block_validity(inode, map); if (ret != 0) return ret; } /* If it is only a block(s) look up */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) return retval; /* * Returns if the blocks have already allocated * * Note that if blocks have been preallocated * ext4_ext_map_blocks() returns with buffer head unmapped */ if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) /* * If we need to convert extent to unwritten * we continue and do the actual work in * ext4_ext_map_blocks() */ if (!(flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) return retval; ext4_fc_track_inode(handle, inode); /* * New blocks allocate and/or writing to unwritten extent * will possibly result in updating i_data, so we take * the write lock of i_data_sem, and call get_block() * with create == 1 flag. */ down_write(&EXT4_I(inode)->i_data_sem); retval = ext4_map_create_blocks(handle, inode, map, flags); up_write((&EXT4_I(inode)->i_data_sem)); if (retval > 0 && map->m_flags & EXT4_MAP_MAPPED) { ret = check_block_validity(inode, map); if (ret != 0) return ret; /* * Inodes with freshly allocated blocks where contents will be * visible after transaction commit must be on transaction's * ordered data list. */ if (map->m_flags & EXT4_MAP_NEW && !(map->m_flags & EXT4_MAP_UNWRITTEN) && !(flags & EXT4_GET_BLOCKS_ZERO) && !ext4_is_quota_file(inode) && ext4_should_order_data(inode)) { loff_t start_byte = (loff_t)map->m_lblk << inode->i_blkbits; loff_t length = (loff_t)map->m_len << inode->i_blkbits; if (flags & EXT4_GET_BLOCKS_IO_SUBMIT) ret = ext4_jbd2_inode_add_wait(handle, inode, start_byte, length); else ret = ext4_jbd2_inode_add_write(handle, inode, start_byte, length); if (ret) return ret; } } if (retval > 0 && (map->m_flags & EXT4_MAP_UNWRITTEN || map->m_flags & EXT4_MAP_MAPPED)) ext4_fc_track_range(handle, inode, map->m_lblk, map->m_lblk + map->m_len - 1); if (retval < 0) ext_debug(inode, "failed with err %d\n", retval); return retval; } /* * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages * we have to be careful as someone else may be manipulating b_state as well. */ static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags) { unsigned long old_state; unsigned long new_state; flags &= EXT4_MAP_FLAGS; /* Dummy buffer_head? Set non-atomically. */ if (!bh->b_folio) { bh->b_state = (bh->b_state & ~EXT4_MAP_FLAGS) | flags; return; } /* * Someone else may be modifying b_state. Be careful! This is ugly but * once we get rid of using bh as a container for mapping information * to pass to / from get_block functions, this can go away. */ old_state = READ_ONCE(bh->b_state); do { new_state = (old_state & ~EXT4_MAP_FLAGS) | flags; } while (unlikely(!try_cmpxchg(&bh->b_state, &old_state, new_state))); } /* * Make sure that the current journal transaction has enough credits to map * one extent. Return -EAGAIN if it cannot extend the current running * transaction. */ static inline int ext4_journal_ensure_extent_credits(handle_t *handle, struct inode *inode) { int credits; int ret; /* Called from ext4_da_write_begin() which has no handle started? */ if (!handle) return 0; credits = ext4_chunk_trans_blocks(inode, 1); ret = __ext4_journal_ensure_credits(handle, credits, credits, 0); return ret <= 0 ? ret : -EAGAIN; } static int _ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int flags) { struct ext4_map_blocks map; int ret = 0; if (ext4_has_inline_data(inode)) return -ERANGE; map.m_lblk = iblock; map.m_len = bh->b_size >> inode->i_blkbits; ret = ext4_map_blocks(ext4_journal_current_handle(), inode, &map, flags); if (ret > 0) { map_bh(bh, inode->i_sb, map.m_pblk); ext4_update_bh_state(bh, map.m_flags); bh->b_size = inode->i_sb->s_blocksize * map.m_len; ret = 0; } else if (ret == 0) { /* hole case, need to fill in bh->b_size */ bh->b_size = inode->i_sb->s_blocksize * map.m_len; } return ret; } int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { return _ext4_get_block(inode, iblock, bh, create ? EXT4_GET_BLOCKS_CREATE : 0); } /* * Get block function used when preparing for buffered write if we require * creating an unwritten extent if blocks haven't been allocated. The extent * will be converted to written after the IO is complete. */ int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { int ret = 0; ext4_debug("ext4_get_block_unwritten: inode %lu, create flag %d\n", inode->i_ino, create); ret = _ext4_get_block(inode, iblock, bh_result, EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); /* * If the buffer is marked unwritten, mark it as new to make sure it is * zeroed out correctly in case of partial writes. Otherwise, there is * a chance of stale data getting exposed. */ if (ret == 0 && buffer_unwritten(bh_result)) set_buffer_new(bh_result); return ret; } /* Maximum number of blocks we map for direct IO at once. */ #define DIO_MAX_BLOCKS 4096 /* * `handle' can be NULL if create is zero */ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, ext4_lblk_t block, int map_flags) { struct ext4_map_blocks map; struct buffer_head *bh; int create = map_flags & EXT4_GET_BLOCKS_CREATE; bool nowait = map_flags & EXT4_GET_BLOCKS_CACHED_NOWAIT; int err; ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) || handle != NULL || create == 0); ASSERT(create == 0 || !nowait); map.m_lblk = block; map.m_len = 1; err = ext4_map_blocks(handle, inode, &map, map_flags); if (err == 0) return create ? ERR_PTR(-ENOSPC) : NULL; if (err < 0) return ERR_PTR(err); if (nowait) return sb_find_get_block(inode->i_sb, map.m_pblk); /* * Since bh could introduce extra ref count such as referred by * journal_head etc. Try to avoid using __GFP_MOVABLE here * as it may fail the migration when journal_head remains. */ bh = getblk_unmovable(inode->i_sb->s_bdev, map.m_pblk, inode->i_sb->s_blocksize); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); if (map.m_flags & EXT4_MAP_NEW) { ASSERT(create != 0); ASSERT((EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY) || (handle != NULL)); /* * Now that we do not always journal data, we should * keep in mind whether this should always journal the * new buffer as metadata. For now, regular file * writes use ext4_get_block instead, so it's not a * problem. */ lock_buffer(bh); BUFFER_TRACE(bh, "call get_create_access"); err = ext4_journal_get_create_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (unlikely(err)) { unlock_buffer(bh); goto errout; } if (!buffer_uptodate(bh)) { memset(bh->b_data, 0, inode->i_sb->s_blocksize); set_buffer_uptodate(bh); } unlock_buffer(bh); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, inode, bh); if (unlikely(err)) goto errout; } else BUFFER_TRACE(bh, "not a new buffer"); return bh; errout: brelse(bh); return ERR_PTR(err); } struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, ext4_lblk_t block, int map_flags) { struct buffer_head *bh; int ret; bh = ext4_getblk(handle, inode, block, map_flags); if (IS_ERR(bh)) return bh; if (!bh || ext4_buffer_uptodate(bh)) return bh; ret = ext4_read_bh_lock(bh, REQ_META | REQ_PRIO, true); if (ret) { put_bh(bh); return ERR_PTR(ret); } return bh; } /* Read a contiguous batch of blocks. */ int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count, bool wait, struct buffer_head **bhs) { int i, err; for (i = 0; i < bh_count; i++) { bhs[i] = ext4_getblk(NULL, inode, block + i, 0 /* map_flags */); if (IS_ERR(bhs[i])) { err = PTR_ERR(bhs[i]); bh_count = i; goto out_brelse; } } for (i = 0; i < bh_count; i++) /* Note that NULL bhs[i] is valid because of holes. */ if (bhs[i] && !ext4_buffer_uptodate(bhs[i])) ext4_read_bh_lock(bhs[i], REQ_META | REQ_PRIO, false); if (!wait) return 0; for (i = 0; i < bh_count; i++) if (bhs[i]) wait_on_buffer(bhs[i]); for (i = 0; i < bh_count; i++) { if (bhs[i] && !buffer_uptodate(bhs[i])) { err = -EIO; goto out_brelse; } } return 0; out_brelse: for (i = 0; i < bh_count; i++) { brelse(bhs[i]); bhs[i] = NULL; } return err; } int ext4_walk_page_buffers(handle_t *handle, struct inode *inode, struct buffer_head *head, unsigned from, unsigned to, int *partial, int (*fn)(handle_t *handle, struct inode *inode, struct buffer_head *bh)) { struct buffer_head *bh; unsigned block_start, block_end; unsigned blocksize = head->b_size; int err, ret = 0; struct buffer_head *next; for (bh = head, block_start = 0; ret == 0 && (bh != head || !block_start); block_start = block_end, bh = next) { next = bh->b_this_page; block_end = block_start + blocksize; if (block_end <= from || block_start >= to) { if (partial && !buffer_uptodate(bh)) *partial = 1; continue; } err = (*fn)(handle, inode, bh); if (!ret) ret = err; } return ret; } /* * Helper for handling dirtying of journalled data. We also mark the folio as * dirty so that writeback code knows about this page (and inode) contains * dirty data. ext4_writepages() then commits appropriate transaction to * make data stable. */ static int ext4_dirty_journalled_data(handle_t *handle, struct buffer_head *bh) { struct folio *folio = bh->b_folio; struct inode *inode = folio->mapping->host; /* only regular files have a_ops */ if (S_ISREG(inode->i_mode)) folio_mark_dirty(folio); return ext4_handle_dirty_metadata(handle, NULL, bh); } int do_journal_get_write_access(handle_t *handle, struct inode *inode, struct buffer_head *bh) { if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; BUFFER_TRACE(bh, "get write access"); return ext4_journal_get_write_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); } int ext4_block_write_begin(handle_t *handle, struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block) { unsigned int from = offset_in_folio(folio, pos); unsigned to = from + len; struct inode *inode = folio->mapping->host; unsigned block_start, block_end; sector_t block; int err = 0; unsigned blocksize = inode->i_sb->s_blocksize; unsigned bbits; struct buffer_head *bh, *head, *wait[2]; int nr_wait = 0; int i; bool should_journal_data = ext4_should_journal_data(inode); BUG_ON(!folio_test_locked(folio)); BUG_ON(to > folio_size(folio)); BUG_ON(from > to); head = folio_buffers(folio); if (!head) head = create_empty_buffers(folio, blocksize, 0); bbits = ilog2(blocksize); block = (sector_t)folio->index << (PAGE_SHIFT - bbits); 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)) { set_buffer_uptodate(bh); } continue; } if (WARN_ON_ONCE(buffer_new(bh))) clear_buffer_new(bh); if (!buffer_mapped(bh)) { WARN_ON(bh->b_size != blocksize); err = ext4_journal_ensure_extent_credits(handle, inode); if (!err) err = get_block(inode, block, bh, 1); if (err) break; if (buffer_new(bh)) { /* * We may be zeroing partial buffers or all new * buffers in case of failure. Prepare JBD2 for * that. */ if (should_journal_data) do_journal_get_write_access(handle, inode, bh); if (folio_test_uptodate(folio)) { /* * Unlike __block_write_begin() we leave * dirtying of new uptodate buffers to * ->write_end() time or * folio_zero_new_buffers(). */ set_buffer_uptodate(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)) { set_buffer_uptodate(bh); continue; } if (!buffer_uptodate(bh) && !buffer_delay(bh) && !buffer_unwritten(bh) && (block_start < from || block_end > to)) { ext4_read_bh_lock(bh, 0, false); wait[nr_wait++] = bh; } } /* * If we issued read requests, let them complete. */ for (i = 0; i < nr_wait; i++) { wait_on_buffer(wait[i]); if (!buffer_uptodate(wait[i])) err = -EIO; } if (unlikely(err)) { if (should_journal_data) ext4_journalled_zero_new_buffers(handle, inode, folio, from, to); else folio_zero_new_buffers(folio, from, to); } else if (fscrypt_inode_uses_fs_layer_crypto(inode)) { for (i = 0; i < nr_wait; i++) { int err2; err2 = fscrypt_decrypt_pagecache_blocks(folio, blocksize, bh_offset(wait[i])); if (err2) { clear_buffer_uptodate(wait[i]); err = err2; } } } return err; } /* * To preserve ordering, it is essential that the hole instantiation and * the data write be encapsulated in a single transaction. We cannot * close off a transaction and start a new one between the ext4_get_block() * and the ext4_write_end(). So doing the jbd2_journal_start at the start of * ext4_write_begin() is the right place. */ static int ext4_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { struct inode *inode = mapping->host; int ret, needed_blocks; handle_t *handle; int retries = 0; struct folio *folio; pgoff_t index; unsigned from, to; ret = ext4_emergency_state(inode->i_sb); if (unlikely(ret)) return ret; trace_ext4_write_begin(inode, pos, len); /* * Reserve one block more for addition to orphan list in case * we allocate blocks but write fails for some reason */ needed_blocks = ext4_chunk_trans_extent(inode, ext4_journal_blocks_per_folio(inode)) + 1; index = pos >> PAGE_SHIFT; if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_try_to_write_inline_data(mapping, inode, pos, len, foliop); if (ret < 0) return ret; if (ret == 1) return 0; } /* * write_begin_get_folio() can take a long time if the * system is thrashing due to memory pressure, or if the folio * is being written back. So grab it first before we start * the transaction handle. This also allows us to allocate * the folio (if needed) without using GFP_NOFS. */ retry_grab: folio = write_begin_get_folio(iocb, mapping, index, len); if (IS_ERR(folio)) return PTR_ERR(folio); if (pos + len > folio_pos(folio) + folio_size(folio)) len = folio_pos(folio) + folio_size(folio) - pos; from = offset_in_folio(folio, pos); to = from + len; /* * The same as page allocation, we prealloc buffer heads before * starting the handle. */ if (!folio_buffers(folio)) create_empty_buffers(folio, inode->i_sb->s_blocksize, 0); folio_unlock(folio); retry_journal: handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks); if (IS_ERR(handle)) { folio_put(folio); return PTR_ERR(handle); } folio_lock(folio); if (folio->mapping != mapping) { /* The folio got truncated from under us */ folio_unlock(folio); folio_put(folio); ext4_journal_stop(handle); goto retry_grab; } /* In case writeback began while the folio was unlocked */ folio_wait_stable(folio); if (ext4_should_dioread_nolock(inode)) ret = ext4_block_write_begin(handle, folio, pos, len, ext4_get_block_unwritten); else ret = ext4_block_write_begin(handle, folio, pos, len, ext4_get_block); if (!ret && ext4_should_journal_data(inode)) { ret = ext4_walk_page_buffers(handle, inode, folio_buffers(folio), from, to, NULL, do_journal_get_write_access); } if (ret) { bool extended = (pos + len > inode->i_size) && !ext4_verity_in_progress(inode); folio_unlock(folio); /* * ext4_block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need * i_size_read because we hold i_rwsem. * * Add inode to orphan list in case we crash before * truncate finishes */ if (extended && ext4_can_truncate(inode)) ext4_orphan_add(handle, inode); ext4_journal_stop(handle); if (extended) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might * still be on the orphan list; we need to * make sure the inode is removed from the * orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } if (ret == -EAGAIN || (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))) goto retry_journal; folio_put(folio); return ret; } *foliop = folio; return ret; } /* For write_end() in data=journal mode */ static int write_end_fn(handle_t *handle, struct inode *inode, struct buffer_head *bh) { int ret; if (!buffer_mapped(bh) || buffer_freed(bh)) return 0; set_buffer_uptodate(bh); ret = ext4_dirty_journalled_data(handle, bh); clear_buffer_meta(bh); clear_buffer_prio(bh); clear_buffer_new(bh); return ret; } /* * We need to pick up the new inode size which generic_commit_write gave us * `iocb` can be NULL - eg, when called from page_symlink(). * * ext4 never places buffers on inode->i_mapping->i_private_list. metadata * buffers are managed internally. */ static int ext4_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; loff_t old_size = inode->i_size; int ret = 0, ret2; int i_size_changed = 0; bool verity = ext4_verity_in_progress(inode); trace_ext4_write_end(inode, pos, len, copied); if (ext4_has_inline_data(inode) && ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) return ext4_write_inline_data_end(inode, pos, len, copied, folio); copied = block_write_end(pos, len, copied, folio); /* * it's important to update i_size while still holding folio lock: * page writeout could otherwise come in and zero beyond i_size. * * If FS_IOC_ENABLE_VERITY is running on this inode, then Merkle tree * blocks are being written past EOF, so skip the i_size update. */ if (!verity) i_size_changed = ext4_update_inode_size(inode, pos + copied); folio_unlock(folio); folio_put(folio); if (old_size < pos && !verity) { pagecache_isize_extended(inode, old_size, pos); ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size); } /* * Don't mark the inode dirty under folio lock. First, it unnecessarily * makes the holding time of folio lock longer. Second, it forces lock * ordering of folio lock and transaction start for journaling * filesystems. */ if (i_size_changed) ret = ext4_mark_inode_dirty(handle, inode); if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; if (pos + len > inode->i_size && !verity) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } return ret ? ret : copied; } /* * This is a private version of folio_zero_new_buffers() which doesn't * set the buffer to be dirty, since in data=journalled mode we need * to call ext4_dirty_journalled_data() instead. */ static void ext4_journalled_zero_new_buffers(handle_t *handle, struct inode *inode, struct folio *folio, unsigned from, unsigned to) { unsigned int block_start = 0, block_end; struct buffer_head *head, *bh; bh = head = folio_buffers(folio); do { block_end = block_start + bh->b_size; if (buffer_new(bh)) { if (block_end > from && block_start < to) { if (!folio_test_uptodate(folio)) { unsigned start, size; start = max(from, block_start); size = min(to, block_end) - start; folio_zero_range(folio, start, size); } clear_buffer_new(bh); write_end_fn(handle, inode, bh); } } block_start = block_end; bh = bh->b_this_page; } while (bh != head); } static int ext4_journalled_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio, void *fsdata) { handle_t *handle = ext4_journal_current_handle(); struct inode *inode = mapping->host; loff_t old_size = inode->i_size; int ret = 0, ret2; int partial = 0; unsigned from, to; int size_changed = 0; bool verity = ext4_verity_in_progress(inode); trace_ext4_journalled_write_end(inode, pos, len, copied); from = pos & (PAGE_SIZE - 1); to = from + len; BUG_ON(!ext4_handle_valid(handle)); if (ext4_has_inline_data(inode)) return ext4_write_inline_data_end(inode, pos, len, copied, folio); if (unlikely(copied < len) && !folio_test_uptodate(folio)) { copied = 0; ext4_journalled_zero_new_buffers(handle, inode, folio, from, to); } else { if (unlikely(copied < len)) ext4_journalled_zero_new_buffers(handle, inode, folio, from + copied, to); ret = ext4_walk_page_buffers(handle, inode, folio_buffers(folio), from, from + copied, &partial, write_end_fn); if (!partial) folio_mark_uptodate(folio); } if (!verity) size_changed = ext4_update_inode_size(inode, pos + copied); EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; folio_unlock(folio); folio_put(folio); if (old_size < pos && !verity) { pagecache_isize_extended(inode, old_size, pos); ext4_zero_partial_blocks(handle, inode, old_size, pos - old_size); } if (size_changed) { ret2 = ext4_mark_inode_dirty(handle, inode); if (!ret) ret = ret2; } if (pos + len > inode->i_size && !verity && ext4_can_truncate(inode)) /* if we have allocated more blocks and copied * less. We will have blocks allocated outside * inode->i_size. So truncate them */ ext4_orphan_add(handle, inode); ret2 = ext4_journal_stop(handle); if (!ret) ret = ret2; if (pos + len > inode->i_size && !verity) { ext4_truncate_failed_write(inode); /* * If truncate failed early the inode might still be * on the orphan list; we need to make sure the inode * is removed from the orphan list in that case. */ if (inode->i_nlink) ext4_orphan_del(NULL, inode); } return ret ? ret : copied; } /* * Reserve space for 'nr_resv' clusters */ static int ext4_da_reserve_space(struct inode *inode, int nr_resv) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); int ret; /* * We will charge metadata quota at writeout time; this saves * us from metadata over-estimation, though we may go over by * a small amount in the end. Here we just reserve for data. */ ret = dquot_reserve_block(inode, EXT4_C2B(sbi, nr_resv)); if (ret) return ret; spin_lock(&ei->i_block_reservation_lock); if (ext4_claim_free_clusters(sbi, nr_resv, 0)) { spin_unlock(&ei->i_block_reservation_lock); dquot_release_reservation_block(inode, EXT4_C2B(sbi, nr_resv)); return -ENOSPC; } ei->i_reserved_data_blocks += nr_resv; trace_ext4_da_reserve_space(inode, nr_resv); spin_unlock(&ei->i_block_reservation_lock); return 0; /* success */ } void ext4_da_release_space(struct inode *inode, int to_free) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); if (!to_free) return; /* Nothing to release, exit */ spin_lock(&EXT4_I(inode)->i_block_reservation_lock); trace_ext4_da_release_space(inode, to_free); if (unlikely(to_free > ei->i_reserved_data_blocks)) { /* * if there aren't enough reserved blocks, then the * counter is messed up somewhere. Since this * function is called from invalidate page, it's * harmless to return without any action. */ ext4_warning(inode->i_sb, "ext4_da_release_space: " "ino %lu, to_free %d with only %d reserved " "data blocks", inode->i_ino, to_free, ei->i_reserved_data_blocks); WARN_ON(1); to_free = ei->i_reserved_data_blocks; } ei->i_reserved_data_blocks -= to_free; /* update fs dirty data blocks counter */ percpu_counter_sub(&sbi->s_dirtyclusters_counter, to_free); spin_unlock(&EXT4_I(inode)->i_block_reservation_lock); dquot_release_reservation_block(inode, EXT4_C2B(sbi, to_free)); } /* * Delayed allocation stuff */ struct mpage_da_data { /* These are input fields for ext4_do_writepages() */ struct inode *inode; struct writeback_control *wbc; unsigned int can_map:1; /* Can writepages call map blocks? */ /* These are internal state of ext4_do_writepages() */ loff_t start_pos; /* The start pos to write */ loff_t next_pos; /* Current pos to examine */ loff_t end_pos; /* Last pos to examine */ /* * Extent to map - this can be after start_pos because that can be * fully mapped. We somewhat abuse m_flags to store whether the extent * is delalloc or unwritten. */ struct ext4_map_blocks map; struct ext4_io_submit io_submit; /* IO submission data */ unsigned int do_map:1; unsigned int scanned_until_end:1; unsigned int journalled_more_data:1; }; static void mpage_release_unused_pages(struct mpage_da_data *mpd, bool invalidate) { unsigned nr, i; pgoff_t index, end; struct folio_batch fbatch; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; /* This is necessary when next_pos == 0. */ if (mpd->start_pos >= mpd->next_pos) return; mpd->scanned_until_end = 0; if (invalidate) { ext4_lblk_t start, last; start = EXT4_B_TO_LBLK(inode, mpd->start_pos); last = mpd->next_pos >> inode->i_blkbits; /* * avoid racing with extent status tree scans made by * ext4_insert_delayed_block() */ down_write(&EXT4_I(inode)->i_data_sem); ext4_es_remove_extent(inode, start, last - start); up_write(&EXT4_I(inode)->i_data_sem); } folio_batch_init(&fbatch); index = mpd->start_pos >> PAGE_SHIFT; end = mpd->next_pos >> PAGE_SHIFT; while (index < end) { nr = filemap_get_folios(mapping, &index, end - 1, &fbatch); if (nr == 0) break; for (i = 0; i < nr; i++) { struct folio *folio = fbatch.folios[i]; if (folio_pos(folio) < mpd->start_pos) continue; if (folio_next_index(folio) > end) continue; BUG_ON(!folio_test_locked(folio)); BUG_ON(folio_test_writeback(folio)); if (invalidate) { if (folio_mapped(folio)) folio_clear_dirty_for_io(folio); block_invalidate_folio(folio, 0, folio_size(folio)); folio_clear_uptodate(folio); } folio_unlock(folio); } folio_batch_release(&fbatch); } } static void ext4_print_free_blocks(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct super_block *sb = inode->i_sb; struct ext4_inode_info *ei = EXT4_I(inode); ext4_msg(sb, KERN_CRIT, "Total free blocks count %lld", EXT4_C2B(EXT4_SB(inode->i_sb), ext4_count_free_clusters(sb))); ext4_msg(sb, KERN_CRIT, "Free/Dirty block details"); ext4_msg(sb, KERN_CRIT, "free_blocks=%lld", (long long) EXT4_C2B(EXT4_SB(sb), percpu_counter_sum(&sbi->s_freeclusters_counter))); ext4_msg(sb, KERN_CRIT, "dirty_blocks=%lld", (long long) EXT4_C2B(EXT4_SB(sb), percpu_counter_sum(&sbi->s_dirtyclusters_counter))); ext4_msg(sb, KERN_CRIT, "Block reservation details"); ext4_msg(sb, KERN_CRIT, "i_reserved_data_blocks=%u", ei->i_reserved_data_blocks); return; } /* * Check whether the cluster containing lblk has been allocated or has * delalloc reservation. * * Returns 0 if the cluster doesn't have either, 1 if it has delalloc * reservation, 2 if it's already been allocated, negative error code on * failure. */ static int ext4_clu_alloc_state(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int ret; /* Has delalloc reservation? */ if (ext4_es_scan_clu(inode, &ext4_es_is_delayed, lblk)) return 1; /* Already been allocated? */ if (ext4_es_scan_clu(inode, &ext4_es_is_mapped, lblk)) return 2; ret = ext4_clu_mapped(inode, EXT4_B2C(sbi, lblk)); if (ret < 0) return ret; if (ret > 0) return 2; return 0; } /* * ext4_insert_delayed_blocks - adds a multiple delayed blocks to the extents * status tree, incrementing the reserved * cluster/block count or making pending * reservations where needed * * @inode - file containing the newly added block * @lblk - start logical block to be added * @len - length of blocks to be added * * Returns 0 on success, negative error code on failure. */ static int ext4_insert_delayed_blocks(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int ret; bool lclu_allocated = false; bool end_allocated = false; ext4_lblk_t resv_clu; ext4_lblk_t end = lblk + len - 1; /* * If the cluster containing lblk or end is shared with a delayed, * written, or unwritten extent in a bigalloc file system, it's * already been accounted for and does not need to be reserved. * A pending reservation must be made for the cluster if it's * shared with a written or unwritten extent and doesn't already * have one. Written and unwritten extents can be purged from the * extents status tree if the system is under memory pressure, so * it's necessary to examine the extent tree if a search of the * extents status tree doesn't get a match. */ if (sbi->s_cluster_ratio == 1) { ret = ext4_da_reserve_space(inode, len); if (ret != 0) /* ENOSPC */ return ret; } else { /* bigalloc */ resv_clu = EXT4_B2C(sbi, end) - EXT4_B2C(sbi, lblk) + 1; ret = ext4_clu_alloc_state(inode, lblk); if (ret < 0) return ret; if (ret > 0) { resv_clu--; lclu_allocated = (ret == 2); } if (EXT4_B2C(sbi, lblk) != EXT4_B2C(sbi, end)) { ret = ext4_clu_alloc_state(inode, end); if (ret < 0) return ret; if (ret > 0) { resv_clu--; end_allocated = (ret == 2); } } if (resv_clu) { ret = ext4_da_reserve_space(inode, resv_clu); if (ret != 0) /* ENOSPC */ return ret; } } ext4_es_insert_delayed_extent(inode, lblk, len, lclu_allocated, end_allocated); return 0; } /* * Looks up the requested blocks and sets the delalloc extent map. * First try to look up for the extent entry that contains the requested * blocks in the extent status tree without i_data_sem, then try to look * up for the ondisk extent mapping with i_data_sem in read mode, * finally hold i_data_sem in write mode, looks up again and add a * delalloc extent entry if it still couldn't find any extent. Pass out * the mapped extent through @map and return 0 on success. */ static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map) { struct extent_status es; int retval; #ifdef ES_AGGRESSIVE_TEST struct ext4_map_blocks orig_map; memcpy(&orig_map, map, sizeof(*map)); #endif map->m_flags = 0; ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len, (unsigned long) map->m_lblk); ext4_check_map_extents_env(inode); /* Lookup extent status tree firstly */ if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) { map->m_len = min_t(unsigned int, map->m_len, es.es_len - (map->m_lblk - es.es_lblk)); if (ext4_es_is_hole(&es)) goto add_delayed; found: /* * Delayed extent could be allocated by fallocate. * So we need to check it. */ if (ext4_es_is_delayed(&es)) { map->m_flags |= EXT4_MAP_DELAYED; return 0; } map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk; if (ext4_es_is_written(&es)) map->m_flags |= EXT4_MAP_MAPPED; else if (ext4_es_is_unwritten(&es)) map->m_flags |= EXT4_MAP_UNWRITTEN; else BUG(); #ifdef ES_AGGRESSIVE_TEST ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0); #endif return 0; } /* * Try to see if we can get the block without requesting a new * file system block. */ down_read(&EXT4_I(inode)->i_data_sem); if (ext4_has_inline_data(inode)) retval = 0; else retval = ext4_map_query_blocks(NULL, inode, map, 0); up_read(&EXT4_I(inode)->i_data_sem); if (retval) return retval < 0 ? retval : 0; add_delayed: down_write(&EXT4_I(inode)->i_data_sem); /* * Page fault path (ext4_page_mkwrite does not take i_rwsem) * and fallocate path (no folio lock) can race. Make sure we * lookup the extent status tree here again while i_data_sem * is held in write mode, before inserting a new da entry in * the extent status tree. */ if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) { map->m_len = min_t(unsigned int, map->m_len, es.es_len - (map->m_lblk - es.es_lblk)); if (!ext4_es_is_hole(&es)) { up_write(&EXT4_I(inode)->i_data_sem); goto found; } } else if (!ext4_has_inline_data(inode)) { retval = ext4_map_query_blocks(NULL, inode, map, 0); if (retval) { up_write(&EXT4_I(inode)->i_data_sem); return retval < 0 ? retval : 0; } } map->m_flags |= EXT4_MAP_DELAYED; retval = ext4_insert_delayed_blocks(inode, map->m_lblk, map->m_len); up_write(&EXT4_I(inode)->i_data_sem); return retval; } /* * This is a special get_block_t callback which is used by * ext4_da_write_begin(). It will either return mapped block or * reserve space for a single block. * * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set. * We also have b_blocknr = -1 and b_bdev initialized properly * * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set. * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev * initialized properly. */ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { struct ext4_map_blocks map; sector_t invalid_block = ~((sector_t) 0xffff); int ret = 0; BUG_ON(create == 0); BUG_ON(bh->b_size != inode->i_sb->s_blocksize); if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es)) invalid_block = ~0; map.m_lblk = iblock; map.m_len = 1; /* * first, we need to know whether the block is allocated already * preallocated blocks are unmapped but should treated * the same as allocated blocks. */ ret = ext4_da_map_blocks(inode, &map); if (ret < 0) return ret; if (map.m_flags & EXT4_MAP_DELAYED) { map_bh(bh, inode->i_sb, invalid_block); set_buffer_new(bh); set_buffer_delay(bh); return 0; } map_bh(bh, inode->i_sb, map.m_pblk); ext4_update_bh_state(bh, map.m_flags); if (buffer_unwritten(bh)) { /* A delayed write to unwritten bh should be marked * new and mapped. Mapped ensures that we don't do * get_block multiple times when we write to the same * offset and new ensures that we do proper zero out * for partial write. */ set_buffer_new(bh); set_buffer_mapped(bh); } return 0; } static void mpage_folio_done(struct mpage_da_data *mpd, struct folio *folio) { mpd->start_pos += folio_size(folio); mpd->wbc->nr_to_write -= folio_nr_pages(folio); folio_unlock(folio); } static int mpage_submit_folio(struct mpage_da_data *mpd, struct folio *folio) { size_t len; loff_t size; int err; WARN_ON_ONCE(folio_pos(folio) != mpd->start_pos); folio_clear_dirty_for_io(folio); /* * We have to be very careful here! Nothing protects writeback path * against i_size changes and the page can be writeably mapped into * page tables. So an application can be growing i_size and writing * data through mmap while writeback runs. folio_clear_dirty_for_io() * write-protects our page in page tables and the page cannot get * written to again until we release folio lock. So only after * folio_clear_dirty_for_io() we are safe to sample i_size for * ext4_bio_write_folio() to zero-out tail of the written page. We rely * on the barrier provided by folio_test_clear_dirty() in * folio_clear_dirty_for_io() to make sure i_size is really sampled only * after page tables are updated. */ size = i_size_read(mpd->inode); len = folio_size(folio); if (folio_pos(folio) + len > size && !ext4_verity_in_progress(mpd->inode)) len = size & (len - 1); err = ext4_bio_write_folio(&mpd->io_submit, folio, len); return err; } #define BH_FLAGS (BIT(BH_Unwritten) | BIT(BH_Delay)) /* * mballoc gives us at most this number of blocks... * XXX: That seems to be only a limitation of ext4_mb_normalize_request(). * The rest of mballoc seems to handle chunks up to full group size. */ #define MAX_WRITEPAGES_EXTENT_LEN 2048 /* * mpage_add_bh_to_extent - try to add bh to extent of blocks to map * * @mpd - extent of blocks * @lblk - logical number of the block in the file * @bh - buffer head we want to add to the extent * * The function is used to collect contig. blocks in the same state. If the * buffer doesn't require mapping for writeback and we haven't started the * extent of buffers to map yet, the function returns 'true' immediately - the * caller can write the buffer right away. Otherwise the function returns true * if the block has been added to the extent, false if the block couldn't be * added. */ static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk, struct buffer_head *bh) { struct ext4_map_blocks *map = &mpd->map; /* Buffer that doesn't need mapping for writeback? */ if (!buffer_dirty(bh) || !buffer_mapped(bh) || (!buffer_delay(bh) && !buffer_unwritten(bh))) { /* So far no extent to map => we write the buffer right away */ if (map->m_len == 0) return true; return false; } /* First block in the extent? */ if (map->m_len == 0) { /* We cannot map unless handle is started... */ if (!mpd->do_map) return false; map->m_lblk = lblk; map->m_len = 1; map->m_flags = bh->b_state & BH_FLAGS; return true; } /* Don't go larger than mballoc is willing to allocate */ if (map->m_len >= MAX_WRITEPAGES_EXTENT_LEN) return false; /* Can we merge the block to our big extent? */ if (lblk == map->m_lblk + map->m_len && (bh->b_state & BH_FLAGS) == map->m_flags) { map->m_len++; return true; } return false; } /* * mpage_process_page_bufs - submit page buffers for IO or add them to extent * * @mpd - extent of blocks for mapping * @head - the first buffer in the page * @bh - buffer we should start processing from * @lblk - logical number of the block in the file corresponding to @bh * * Walk through page buffers from @bh upto @head (exclusive) and either submit * the page for IO if all buffers in this page were mapped and there's no * accumulated extent of buffers to map or add buffers in the page to the * extent of buffers to map. The function returns 1 if the caller can continue * by processing the next page, 0 if it should stop adding buffers to the * extent to map because we cannot extend it anymore. It can also return value * < 0 in case of error during IO submission. */ static int mpage_process_page_bufs(struct mpage_da_data *mpd, struct buffer_head *head, struct buffer_head *bh, ext4_lblk_t lblk) { struct inode *inode = mpd->inode; int err; ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1) >> inode->i_blkbits; if (ext4_verity_in_progress(inode)) blocks = EXT_MAX_BLOCKS; do { BUG_ON(buffer_locked(bh)); if (lblk >= blocks || !mpage_add_bh_to_extent(mpd, lblk, bh)) { /* Found extent to map? */ if (mpd->map.m_len) return 0; /* Buffer needs mapping and handle is not started? */ if (!mpd->do_map) return 0; /* Everything mapped so far and we hit EOF */ break; } } while (lblk++, (bh = bh->b_this_page) != head); /* So far everything mapped? Submit the page for IO. */ if (mpd->map.m_len == 0) { err = mpage_submit_folio(mpd, head->b_folio); if (err < 0) return err; mpage_folio_done(mpd, head->b_folio); } if (lblk >= blocks) { mpd->scanned_until_end = 1; return 0; } return 1; } /* * mpage_process_folio - update folio buffers corresponding to changed extent * and may submit fully mapped page for IO * @mpd: description of extent to map, on return next extent to map * @folio: Contains these buffers. * @m_lblk: logical block mapping. * @m_pblk: corresponding physical mapping. * @map_bh: determines on return whether this page requires any further * mapping or not. * * Scan given folio buffers corresponding to changed extent and update buffer * state according to new extent state. * We map delalloc buffers to their physical location, clear unwritten bits. * If the given folio is not fully mapped, we update @mpd to the next extent in * the given folio that needs mapping & return @map_bh as true. */ static int mpage_process_folio(struct mpage_da_data *mpd, struct folio *folio, ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk, bool *map_bh) { struct buffer_head *head, *bh; ext4_io_end_t *io_end = mpd->io_submit.io_end; ext4_lblk_t lblk = *m_lblk; ext4_fsblk_t pblock = *m_pblk; int err = 0; int blkbits = mpd->inode->i_blkbits; ssize_t io_end_size = 0; struct ext4_io_end_vec *io_end_vec = ext4_last_io_end_vec(io_end); bh = head = folio_buffers(folio); do { if (lblk < mpd->map.m_lblk) continue; if (lblk >= mpd->map.m_lblk + mpd->map.m_len) { /* * Buffer after end of mapped extent. * Find next buffer in the folio to map. */ mpd->map.m_len = 0; mpd->map.m_flags = 0; io_end_vec->size += io_end_size; err = mpage_process_page_bufs(mpd, head, bh, lblk); if (err > 0) err = 0; if (!err && mpd->map.m_len && mpd->map.m_lblk > lblk) { io_end_vec = ext4_alloc_io_end_vec(io_end); if (IS_ERR(io_end_vec)) { err = PTR_ERR(io_end_vec); goto out; } io_end_vec->offset = (loff_t)mpd->map.m_lblk << blkbits; } *map_bh = true; goto out; } if (buffer_delay(bh)) { clear_buffer_delay(bh); bh->b_blocknr = pblock++; } clear_buffer_unwritten(bh); io_end_size += (1 << blkbits); } while (lblk++, (bh = bh->b_this_page) != head); io_end_vec->size += io_end_size; *map_bh = false; out: *m_lblk = lblk; *m_pblk = pblock; return err; } /* * mpage_map_buffers - update buffers corresponding to changed extent and * submit fully mapped pages for IO * * @mpd - description of extent to map, on return next extent to map * * Scan buffers corresponding to changed extent (we expect corresponding pages * to be already locked) and update buffer state according to new extent state. * We map delalloc buffers to their physical location, clear unwritten bits, * and mark buffers as uninit when we perform writes to unwritten extents * and do extent conversion after IO is finished. If the last page is not fully * mapped, we update @map to the next extent in the last page that needs * mapping. Otherwise we submit the page for IO. */ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) { struct folio_batch fbatch; unsigned nr, i; struct inode *inode = mpd->inode; int bpp_bits = PAGE_SHIFT - inode->i_blkbits; pgoff_t start, end; ext4_lblk_t lblk; ext4_fsblk_t pblock; int err; bool map_bh = false; start = mpd->map.m_lblk >> bpp_bits; end = (mpd->map.m_lblk + mpd->map.m_len - 1) >> bpp_bits; pblock = mpd->map.m_pblk; folio_batch_init(&fbatch); while (start <= end) { nr = filemap_get_folios(inode->i_mapping, &start, end, &fbatch); if (nr == 0) break; for (i = 0; i < nr; i++) { struct folio *folio = fbatch.folios[i]; lblk = folio->index << bpp_bits; err = mpage_process_folio(mpd, folio, &lblk, &pblock, &map_bh); /* * If map_bh is true, means page may require further bh * mapping, or maybe the page was submitted for IO. * So we return to call further extent mapping. */ if (err < 0 || map_bh) goto out; /* Page fully mapped - let IO run! */ err = mpage_submit_folio(mpd, folio); if (err < 0) goto out; mpage_folio_done(mpd, folio); } folio_batch_release(&fbatch); } /* Extent fully mapped and matches with page boundary. We are done. */ mpd->map.m_len = 0; mpd->map.m_flags = 0; return 0; out: folio_batch_release(&fbatch); return err; } static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd) { struct inode *inode = mpd->inode; struct ext4_map_blocks *map = &mpd->map; int get_blocks_flags; int err, dioread_nolock; /* Make sure transaction has enough credits for this extent */ err = ext4_journal_ensure_extent_credits(handle, inode); if (err < 0) return err; trace_ext4_da_write_pages_extent(inode, map); /* * Call ext4_map_blocks() to allocate any delayed allocation blocks, or * to convert an unwritten extent to be initialized (in the case * where we have written into one or more preallocated blocks). It is * possible that we're going to need more metadata blocks than * previously reserved. However we must not fail because we're in * writeback and there is nothing we can do about it so it might result * in data loss. So use reserved blocks to allocate metadata if * possible. In addition, do not cache any unrelated extents, as it * only holds the folio lock but does not hold the i_rwsem or * invalidate_lock, which could corrupt the extent status tree. */ get_blocks_flags = EXT4_GET_BLOCKS_CREATE | EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_GET_BLOCKS_IO_SUBMIT | EXT4_EX_NOCACHE; dioread_nolock = ext4_should_dioread_nolock(inode); if (dioread_nolock) get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT; err = ext4_map_blocks(handle, inode, map, get_blocks_flags); if (err < 0) return err; if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) { if (!mpd->io_submit.io_end->handle && ext4_handle_valid(handle)) { mpd->io_submit.io_end->handle = handle->h_rsv_handle; handle->h_rsv_handle = NULL; } ext4_set_io_unwritten_flag(mpd->io_submit.io_end); } BUG_ON(map->m_len == 0); return 0; } /* * This is used to submit mapped buffers in a single folio that is not fully * mapped for various reasons, such as insufficient space or journal credits. */ static int mpage_submit_partial_folio(struct mpage_da_data *mpd) { struct inode *inode = mpd->inode; struct folio *folio; loff_t pos; int ret; folio = filemap_get_folio(inode->i_mapping, mpd->start_pos >> PAGE_SHIFT); if (IS_ERR(folio)) return PTR_ERR(folio); /* * The mapped position should be within the current processing folio * but must not be the folio start position. */ pos = ((loff_t)mpd->map.m_lblk) << inode->i_blkbits; if (WARN_ON_ONCE((folio_pos(folio) == pos) || !folio_contains(folio, pos >> PAGE_SHIFT))) return -EINVAL; ret = mpage_submit_folio(mpd, folio); if (ret) goto out; /* * Update start_pos to prevent this folio from being released in * mpage_release_unused_pages(), it will be reset to the aligned folio * pos when this folio is written again in the next round. Additionally, * do not update wbc->nr_to_write here, as it will be updated once the * entire folio has finished processing. */ mpd->start_pos = pos; out: folio_unlock(folio); folio_put(folio); return ret; } /* * mpage_map_and_submit_extent - map extent starting at mpd->lblk of length * mpd->len and submit pages underlying it for IO * * @handle - handle for journal operations * @mpd - extent to map * @give_up_on_write - we set this to true iff there is a fatal error and there * is no hope of writing the data. The caller should discard * dirty pages to avoid infinite loops. * * The function maps extent starting at mpd->lblk of length mpd->len. If it is * delayed, blocks are allocated, if it is unwritten, we may need to convert * them to initialized or split the described range from larger unwritten * extent. Note that we need not map all the described range since allocation * can return less blocks or the range is covered by more unwritten extents. We * cannot map more because we are limited by reserved transaction credits. On * the other hand we always make sure that the last touched page is fully * mapped so that it can be written out (and thus forward progress is * guaranteed). After mapping we submit all mapped pages for IO. */ static int mpage_map_and_submit_extent(handle_t *handle, struct mpage_da_data *mpd, bool *give_up_on_write) { struct inode *inode = mpd->inode; struct ext4_map_blocks *map = &mpd->map; int err; loff_t disksize; int progress = 0; ext4_io_end_t *io_end = mpd->io_submit.io_end; struct ext4_io_end_vec *io_end_vec; io_end_vec = ext4_alloc_io_end_vec(io_end); if (IS_ERR(io_end_vec)) return PTR_ERR(io_end_vec); io_end_vec->offset = ((loff_t)map->m_lblk) << inode->i_blkbits; do { err = mpage_map_one_extent(handle, mpd); if (err < 0) { struct super_block *sb = inode->i_sb; if (ext4_emergency_state(sb)) goto invalidate_dirty_pages; /* * Let the uper layers retry transient errors. * In the case of ENOSPC, if ext4_count_free_blocks() * is non-zero, a commit should free up blocks. */ if ((err == -ENOMEM) || (err == -EAGAIN) || (err == -ENOSPC && ext4_count_free_clusters(sb))) { /* * We may have already allocated extents for * some bhs inside the folio, issue the * corresponding data to prevent stale data. */ if (progress) { if (mpage_submit_partial_folio(mpd)) goto invalidate_dirty_pages; goto update_disksize; } return err; } ext4_msg(sb, KERN_CRIT, "Delayed block allocation failed for " "inode %lu at logical offset %llu with" " max blocks %u with error %d", inode->i_ino, (unsigned long long)map->m_lblk, (unsigned)map->m_len, -err); ext4_msg(sb, KERN_CRIT, "This should not happen!! Data will " "be lost\n"); if (err == -ENOSPC) ext4_print_free_blocks(inode); invalidate_dirty_pages: *give_up_on_write = true; return err; } progress = 1; /* * Update buffer state, submit mapped pages, and get us new * extent to map */ err = mpage_map_and_submit_buffers(mpd); if (err < 0) goto update_disksize; } while (map->m_len); update_disksize: /* * Update on-disk size after IO is submitted. Races with * truncate are avoided by checking i_size under i_data_sem. */ disksize = mpd->start_pos; if (disksize > READ_ONCE(EXT4_I(inode)->i_disksize)) { int err2; loff_t i_size; down_write(&EXT4_I(inode)->i_data_sem); i_size = i_size_read(inode); if (disksize > i_size) disksize = i_size; if (disksize > EXT4_I(inode)->i_disksize) EXT4_I(inode)->i_disksize = disksize; up_write(&EXT4_I(inode)->i_data_sem); err2 = ext4_mark_inode_dirty(handle, inode); if (err2) { ext4_error_err(inode->i_sb, -err2, "Failed to mark inode %lu dirty", inode->i_ino); } if (!err) err = err2; } return err; } static int ext4_journal_folio_buffers(handle_t *handle, struct folio *folio, size_t len) { struct buffer_head *page_bufs = folio_buffers(folio); struct inode *inode = folio->mapping->host; int ret, err; ret = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len, NULL, do_journal_get_write_access); err = ext4_walk_page_buffers(handle, inode, page_bufs, 0, len, NULL, write_end_fn); if (ret == 0) ret = err; err = ext4_jbd2_inode_add_write(handle, inode, folio_pos(folio), len); if (ret == 0) ret = err; EXT4_I(inode)->i_datasync_tid = handle->h_transaction->t_tid; return ret; } static int mpage_journal_page_buffers(handle_t *handle, struct mpage_da_data *mpd, struct folio *folio) { struct inode *inode = mpd->inode; loff_t size = i_size_read(inode); size_t len = folio_size(folio); folio_clear_checked(folio); mpd->wbc->nr_to_write -= folio_nr_pages(folio); if (folio_pos(folio) + len > size && !ext4_verity_in_progress(inode)) len = size & (len - 1); return ext4_journal_folio_buffers(handle, folio, len); } /* * mpage_prepare_extent_to_map - find & lock contiguous range of dirty pages * needing mapping, submit mapped pages * * @mpd - where to look for pages * * Walk dirty pages in the mapping. If they are fully mapped, submit them for * IO immediately. If we cannot map blocks, we submit just already mapped * buffers in the page for IO and keep page dirty. When we can map blocks and * we find a page which isn't mapped we start accumulating extent of buffers * underlying these pages that needs mapping (formed by either delayed or * unwritten buffers). We also lock the pages containing these buffers. The * extent found is returned in @mpd structure (starting at mpd->lblk with * length mpd->len blocks). * * Note that this function can attach bios to one io_end structure which are * neither logically nor physically contiguous. Although it may seem as an * unnecessary complication, it is actually inevitable in blocksize < pagesize * case as we need to track IO to all buffers underlying a page in one io_end. */ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) { struct address_space *mapping = mpd->inode->i_mapping; struct folio_batch fbatch; unsigned int nr_folios; pgoff_t index = mpd->start_pos >> PAGE_SHIFT; pgoff_t end = mpd->end_pos >> PAGE_SHIFT; xa_mark_t tag; int i, err = 0; int blkbits = mpd->inode->i_blkbits; ext4_lblk_t lblk; struct buffer_head *head; handle_t *handle = NULL; int bpp = ext4_journal_blocks_per_folio(mpd->inode); if (mpd->wbc->sync_mode == WB_SYNC_ALL || mpd->wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; mpd->map.m_len = 0; mpd->next_pos = mpd->start_pos; if (ext4_should_journal_data(mpd->inode)) { handle = ext4_journal_start(mpd->inode, EXT4_HT_WRITE_PAGE, bpp); if (IS_ERR(handle)) return PTR_ERR(handle); } folio_batch_init(&fbatch); while (index <= end) { nr_folios = filemap_get_folios_tag(mapping, &index, end, tag, &fbatch); if (nr_folios == 0) break; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; /* * Accumulated enough dirty pages? This doesn't apply * to WB_SYNC_ALL mode. For integrity sync we have to * keep going because someone may be concurrently * dirtying pages, and we might have synced a lot of * newly appeared dirty pages, but have not synced all * of the old dirty pages. */ if (mpd->wbc->sync_mode == WB_SYNC_NONE && mpd->wbc->nr_to_write <= mpd->map.m_len >> (PAGE_SHIFT - blkbits)) goto out; /* If we can't merge this page, we are done. */ if (mpd->map.m_len > 0 && mpd->next_pos != folio_pos(folio)) goto out; if (handle) { err = ext4_journal_ensure_credits(handle, bpp, 0); if (err < 0) goto out; } folio_lock(folio); /* * If the page is no longer dirty, or its mapping no * longer corresponds to inode we are writing (which * means it has been truncated or invalidated), or the * page is already under writeback and we are not doing * a data integrity writeback, skip the page */ if (!folio_test_dirty(folio) || (folio_test_writeback(folio) && (mpd->wbc->sync_mode == WB_SYNC_NONE)) || unlikely(folio->mapping != mapping)) { folio_unlock(folio); continue; } folio_wait_writeback(folio); BUG_ON(folio_test_writeback(folio)); /* * Should never happen but for buggy code in * other subsystems that call * set_page_dirty() without properly warning * the file system first. See [1] for more * information. * * [1] https://lore.kernel.org/linux-mm/20180103100430.GE4911@quack2.suse.cz */ if (!folio_buffers(folio)) { ext4_warning_inode(mpd->inode, "page %lu does not have buffers attached", folio->index); folio_clear_dirty(folio); folio_unlock(folio); continue; } if (mpd->map.m_len == 0) mpd->start_pos = folio_pos(folio); mpd->next_pos = folio_pos(folio) + folio_size(folio); /* * Writeout when we cannot modify metadata is simple. * Just submit the page. For data=journal mode we * first handle writeout of the page for checkpoint and * only after that handle delayed page dirtying. This * makes sure current data is checkpointed to the final * location before possibly journalling it again which * is desirable when the page is frequently dirtied * through a pin. */ if (!mpd->can_map) { err = mpage_submit_folio(mpd, folio); if (err < 0) goto out; /* Pending dirtying of journalled data? */ if (folio_test_checked(folio)) { err = mpage_journal_page_buffers(handle, mpd, folio); if (err < 0) goto out; mpd->journalled_more_data = 1; } mpage_folio_done(mpd, folio); } else { /* Add all dirty buffers to mpd */ lblk = ((ext4_lblk_t)folio->index) << (PAGE_SHIFT - blkbits); head = folio_buffers(folio); err = mpage_process_page_bufs(mpd, head, head, lblk); if (err <= 0) goto out; err = 0; } } folio_batch_release(&fbatch); cond_resched(); } mpd->scanned_until_end = 1; if (handle) ext4_journal_stop(handle); return 0; out: folio_batch_release(&fbatch); if (handle) ext4_journal_stop(handle); return err; } static int ext4_do_writepages(struct mpage_da_data *mpd) { struct writeback_control *wbc = mpd->wbc; pgoff_t writeback_index = 0; long nr_to_write = wbc->nr_to_write; int range_whole = 0; int cycled = 1; handle_t *handle = NULL; struct inode *inode = mpd->inode; struct address_space *mapping = inode->i_mapping; int needed_blocks, rsv_blocks = 0, ret = 0; struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb); struct blk_plug plug; bool give_up_on_write = false; trace_ext4_writepages(inode, wbc); /* * No pages to write? This is mainly a kludge to avoid starting * a transaction for special inodes like journal inode on last iput() * because that could violate lock ordering on umount */ if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) goto out_writepages; /* * If the filesystem has aborted, it is read-only, so return * right away instead of dumping stack traces later on that * will obscure the real source of the problem. We test * fs shutdown state instead of sb->s_flag's SB_RDONLY because * the latter could be true if the filesystem is mounted * read-only, and in that case, ext4_writepages should * *never* be called, so if that ever happens, we would want * the stack trace. */ ret = ext4_emergency_state(mapping->host->i_sb); if (unlikely(ret)) goto out_writepages; /* * If we have inline data and arrive here, it means that * we will soon create the block for the 1st page, so * we'd better clear the inline data here. */ if (ext4_has_inline_data(inode)) { /* Just inode will be modified... */ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); goto out_writepages; } BUG_ON(ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)); ext4_destroy_inline_data(handle, inode); ext4_journal_stop(handle); } /* * data=journal mode does not do delalloc so we just need to writeout / * journal already mapped buffers. On the other hand we need to commit * transaction to make data stable. We expect all the data to be * already in the journal (the only exception are DMA pinned pages * dirtied behind our back) so we commit transaction here and run the * writeback loop to checkpoint them. The checkpointing is not actually * necessary to make data persistent *but* quite a few places (extent * shifting operations, fsverity, ...) depend on being able to drop * pagecache pages after calling filemap_write_and_wait() and for that * checkpointing needs to happen. */ if (ext4_should_journal_data(inode)) { mpd->can_map = 0; if (wbc->sync_mode == WB_SYNC_ALL) ext4_fc_commit(sbi->s_journal, EXT4_I(inode)->i_datasync_tid); } mpd->journalled_more_data = 0; if (ext4_should_dioread_nolock(inode)) { int bpf = ext4_journal_blocks_per_folio(inode); /* * We may need to convert up to one extent per block in * the folio and we may dirty the inode. */ rsv_blocks = 1 + ext4_ext_index_trans_blocks(inode, bpf); } if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; if (writeback_index) cycled = 0; mpd->start_pos = writeback_index << PAGE_SHIFT; mpd->end_pos = LLONG_MAX; } else { mpd->start_pos = wbc->range_start; mpd->end_pos = wbc->range_end; } ext4_io_submit_init(&mpd->io_submit, wbc); retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, mpd->start_pos >> PAGE_SHIFT, mpd->end_pos >> PAGE_SHIFT); blk_start_plug(&plug); /* * First writeback pages that don't need mapping - we can avoid * starting a transaction unnecessarily and also avoid being blocked * in the block layer on device congestion while having transaction * started. */ mpd->do_map = 0; mpd->scanned_until_end = 0; mpd->io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL); if (!mpd->io_submit.io_end) { ret = -ENOMEM; goto unplug; } ret = mpage_prepare_extent_to_map(mpd); /* Unlock pages we didn't use */ mpage_release_unused_pages(mpd, false); /* Submit prepared bio */ ext4_io_submit(&mpd->io_submit); ext4_put_io_end_defer(mpd->io_submit.io_end); mpd->io_submit.io_end = NULL; if (ret < 0) goto unplug; while (!mpd->scanned_until_end && wbc->nr_to_write > 0) { /* For each extent of pages we use new io_end */ mpd->io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL); if (!mpd->io_submit.io_end) { ret = -ENOMEM; break; } WARN_ON_ONCE(!mpd->can_map); /* * We have two constraints: We find one extent to map and we * must always write out whole page (makes a difference when * blocksize < pagesize) so that we don't block on IO when we * try to write out the rest of the page. Journalled mode is * not supported by delalloc. */ BUG_ON(ext4_should_journal_data(inode)); /* * Calculate the number of credits needed to reserve for one * extent of up to MAX_WRITEPAGES_EXTENT_LEN blocks. It will * attempt to extend the transaction or start a new iteration * if the reserved credits are insufficient. */ needed_blocks = ext4_chunk_trans_blocks(inode, MAX_WRITEPAGES_EXTENT_LEN); /* start a new transaction */ handle = ext4_journal_start_with_reserve(inode, EXT4_HT_WRITE_PAGE, needed_blocks, rsv_blocks); if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_msg(inode->i_sb, KERN_CRIT, "%s: jbd2_start: " "%ld pages, ino %lu; err %d", __func__, wbc->nr_to_write, inode->i_ino, ret); /* Release allocated io_end */ ext4_put_io_end(mpd->io_submit.io_end); mpd->io_submit.io_end = NULL; break; } mpd->do_map = 1; trace_ext4_da_write_folios_start(inode, mpd->start_pos, mpd->next_pos, wbc); ret = mpage_prepare_extent_to_map(mpd); if (!ret && mpd->map.m_len) ret = mpage_map_and_submit_extent(handle, mpd, &give_up_on_write); /* * Caution: If the handle is synchronous, * ext4_journal_stop() can wait for transaction commit * to finish which may depend on writeback of pages to * complete or on page lock to be released. In that * case, we have to wait until after we have * submitted all the IO, released page locks we hold, * and dropped io_end reference (for extent conversion * to be able to complete) before stopping the handle. */ if (!ext4_handle_valid(handle) || handle->h_sync == 0) { ext4_journal_stop(handle); handle = NULL; mpd->do_map = 0; } /* Unlock pages we didn't use */ mpage_release_unused_pages(mpd, give_up_on_write); /* Submit prepared bio */ ext4_io_submit(&mpd->io_submit); /* * Drop our io_end reference we got from init. We have * to be careful and use deferred io_end finishing if * we are still holding the transaction as we can * release the last reference to io_end which may end * up doing unwritten extent conversion. */ if (handle) { ext4_put_io_end_defer(mpd->io_submit.io_end); ext4_journal_stop(handle); } else ext4_put_io_end(mpd->io_submit.io_end); mpd->io_submit.io_end = NULL; trace_ext4_da_write_folios_end(inode, mpd->start_pos, mpd->next_pos, wbc, ret); if (ret == -ENOSPC && sbi->s_journal) { /* * Commit the transaction which would * free blocks released in the transaction * and try again */ jbd2_journal_force_commit_nested(sbi->s_journal); ret = 0; continue; } if (ret == -EAGAIN) ret = 0; /* Fatal error - ENOMEM, EIO... */ if (ret) break; } unplug: blk_finish_plug(&plug); if (!ret && !cycled && wbc->nr_to_write > 0) { cycled = 1; mpd->end_pos = (writeback_index << PAGE_SHIFT) - 1; mpd->start_pos = 0; goto retry; } /* Update index */ if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) /* * Set the writeback_index so that range_cyclic * mode will write it back later */ mapping->writeback_index = mpd->start_pos >> PAGE_SHIFT; out_writepages: trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); return ret; } static int ext4_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct super_block *sb = mapping->host->i_sb; struct mpage_da_data mpd = { .inode = mapping->host, .wbc = wbc, .can_map = 1, }; int ret; int alloc_ctx; ret = ext4_emergency_state(sb); if (unlikely(ret)) return ret; alloc_ctx = ext4_writepages_down_read(sb); ret = ext4_do_writepages(&mpd); /* * For data=journal writeback we could have come across pages marked * for delayed dirtying (PageChecked) which were just added to the * running transaction. Try once more to get them to stable storage. */ if (!ret && mpd.journalled_more_data) ret = ext4_do_writepages(&mpd); ext4_writepages_up_read(sb, alloc_ctx); return ret; } int ext4_normal_submit_inode_data_buffers(struct jbd2_inode *jinode) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = LONG_MAX, .range_start = jinode->i_dirty_start, .range_end = jinode->i_dirty_end, }; struct mpage_da_data mpd = { .inode = jinode->i_vfs_inode, .wbc = &wbc, .can_map = 0, }; return ext4_do_writepages(&mpd); } static int ext4_dax_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; long nr_to_write = wbc->nr_to_write; struct inode *inode = mapping->host; int alloc_ctx; ret = ext4_emergency_state(inode->i_sb); if (unlikely(ret)) return ret; alloc_ctx = ext4_writepages_down_read(inode->i_sb); trace_ext4_writepages(inode, wbc); ret = dax_writeback_mapping_range(mapping, EXT4_SB(inode->i_sb)->s_daxdev, wbc); trace_ext4_writepages_result(inode, wbc, ret, nr_to_write - wbc->nr_to_write); ext4_writepages_up_read(inode->i_sb, alloc_ctx); return ret; } static int ext4_nonda_switch(struct super_block *sb) { s64 free_clusters, dirty_clusters; struct ext4_sb_info *sbi = EXT4_SB(sb); /* * switch to non delalloc mode if we are running low * on free block. The free block accounting via percpu * counters can get slightly wrong with percpu_counter_batch getting * accumulated on each CPU without updating global counters * Delalloc need an accurate free block accounting. So switch * to non delalloc when we are near to error range. */ free_clusters = percpu_counter_read_positive(&sbi->s_freeclusters_counter); dirty_clusters = percpu_counter_read_positive(&sbi->s_dirtyclusters_counter); /* * Start pushing delalloc when 1/2 of free blocks are dirty. */ if (dirty_clusters && (free_clusters < 2 * dirty_clusters)) try_to_writeback_inodes_sb(sb, WB_REASON_FS_FREE_SPACE); if (2 * free_clusters < 3 * dirty_clusters || free_clusters < (dirty_clusters + EXT4_FREECLUSTERS_WATERMARK)) { /* * free block count is less than 150% of dirty blocks * or free blocks is less than watermark */ return 1; } return 0; } static int ext4_da_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, unsigned len, struct folio **foliop, void **fsdata) { int ret, retries = 0; struct folio *folio; pgoff_t index; struct inode *inode = mapping->host; ret = ext4_emergency_state(inode->i_sb); if (unlikely(ret)) return ret; index = pos >> PAGE_SHIFT; if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) { *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; return ext4_write_begin(iocb, mapping, pos, len, foliop, fsdata); } *fsdata = (void *)0; trace_ext4_da_write_begin(inode, pos, len); if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { ret = ext4_generic_write_inline_data(mapping, inode, pos, len, foliop, fsdata, true); if (ret < 0) return ret; if (ret == 1) return 0; } retry: folio = write_begin_get_folio(iocb, mapping, index, len); if (IS_ERR(folio)) return PTR_ERR(folio); if (pos + len > folio_pos(folio) + folio_size(folio)) len = folio_pos(folio) + folio_size(folio) - pos; ret = ext4_block_write_begin(NULL, folio, pos, len, ext4_da_get_block_prep); if (ret < 0) { folio_unlock(folio); folio_put(folio); /* * ext4_block_write_begin may have instantiated a few blocks * outside i_size. Trim these off again. Don't need * i_size_read because we hold inode lock. */ if (pos + len > inode->i_size) ext4_truncate_failed_write(inode); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; return ret; } *foliop = folio; return ret; } /* * Check if we should update i_disksize * when write to the end of file but not require block allocation */ static int ext4_da_should_update_i_disksize(struct folio *folio, unsigned long offset) { struct buffer_head *bh; struct inode *inode = folio->mapping->host; unsigned int idx; int i; bh = folio_buffers(folio); idx = offset >> inode->i_blkbits; for (i = 0; i < idx; i++) bh = bh->b_this_page; if (!buffer_mapped(bh) || (buffer_delay(bh)) || buffer_unwritten(bh)) return 0; return 1; } static int ext4_da_do_write_end(struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio) { struct inode *inode = mapping->host; loff_t old_size = inode->i_size; bool disksize_changed = false; loff_t new_i_size, zero_len = 0; handle_t *handle; if (unlikely(!folio_buffers(folio))) { folio_unlock(folio); folio_put(folio); return -EIO; } /* * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES * flag, which all that's needed to trigger page writeback. */ copied = block_write_end(pos, len, copied, folio); new_i_size = pos + copied; /* * It's important to update i_size while still holding folio lock, * because folio writeout could otherwise come in and zero beyond * i_size. * * Since we are holding inode lock, we are sure i_disksize <= * i_size. We also know that if i_disksize < i_size, there are * delalloc writes pending in the range up to i_size. If the end of * the current write is <= i_size, there's no need to touch * i_disksize since writeback will push i_disksize up to i_size * eventually. If the end of the current write is > i_size and * inside an allocated block which ext4_da_should_update_i_disksize() * checked, we need to update i_disksize here as certain * ext4_writepages() paths not allocating blocks and update i_disksize. */ if (new_i_size > inode->i_size) { unsigned long end; i_size_write(inode, new_i_size); end = offset_in_folio(folio, new_i_size - 1); if (copied && ext4_da_should_update_i_disksize(folio, end)) { ext4_update_i_disksize(inode, new_i_size); disksize_changed = true; } } folio_unlock(folio); folio_put(folio); if (pos > old_size) { pagecache_isize_extended(inode, old_size, pos); zero_len = pos - old_size; } if (!disksize_changed && !zero_len) return copied; handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) return PTR_ERR(handle); if (zero_len) ext4_zero_partial_blocks(handle, inode, old_size, zero_len); ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); return copied; } static int ext4_da_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; int write_mode = (int)(unsigned long)fsdata; if (write_mode == FALL_BACK_TO_NONDELALLOC) return ext4_write_end(iocb, mapping, pos, len, copied, folio, fsdata); trace_ext4_da_write_end(inode, pos, len, copied); if (write_mode != CONVERT_INLINE_DATA && ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) && ext4_has_inline_data(inode)) return ext4_write_inline_data_end(inode, pos, len, copied, folio); if (unlikely(copied < len) && !folio_test_uptodate(folio)) copied = 0; return ext4_da_do_write_end(mapping, pos, len, copied, folio); } /* * Force all delayed allocation blocks to be allocated for a given inode. */ int ext4_alloc_da_blocks(struct inode *inode) { trace_ext4_alloc_da_blocks(inode); if (!EXT4_I(inode)->i_reserved_data_blocks) return 0; /* * We do something simple for now. The filemap_flush() will * also start triggering a write of the data blocks, which is * not strictly speaking necessary (and for users of * laptop_mode, not even desirable). However, to do otherwise * would require replicating code paths in: * * ext4_writepages() -> * write_cache_pages() ---> (via passed in callback function) * __mpage_da_writepage() --> * mpage_add_bh_to_extent() * mpage_da_map_blocks() * * The problem is that write_cache_pages(), located in * mm/page-writeback.c, marks pages clean in preparation for * doing I/O, which is not desirable if we're not planning on * doing I/O at all. * * We could call write_cache_pages(), and then redirty all of * the pages by calling redirty_page_for_writepage() but that * would be ugly in the extreme. So instead we would need to * replicate parts of the code in the above functions, * simplifying them because we wouldn't actually intend to * write out the pages, but rather only collect contiguous * logical block extents, call the multi-block allocator, and * then update the buffer heads with the block allocations. * * For now, though, we'll cheat by calling filemap_flush(), * which will map the blocks, and start the I/O, but not * actually wait for the I/O to complete. */ return filemap_flush(inode->i_mapping); } /* * bmap() is special. It gets used by applications such as lilo and by * the swapper to find the on-disk block of a specific piece of data. * * Naturally, this is dangerous if the block concerned is still in the * journal. If somebody makes a swapfile on an ext4 data-journaling * filesystem and enables swap, then they may get a nasty shock when the * data getting swapped to that swapfile suddenly gets overwritten by * the original zero's written out previously to the journal and * awaiting writeback in the kernel's buffer cache. * * So, if we see any bmap calls here on a modified, data-journaled file, * take extra steps to flush any blocks which might be in the cache. */ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) { struct inode *inode = mapping->host; sector_t ret = 0; inode_lock_shared(inode); /* * We can get here for an inline file via the FIBMAP ioctl */ if (ext4_has_inline_data(inode)) goto out; if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && (test_opt(inode->i_sb, DELALLOC) || ext4_should_journal_data(inode))) { /* * With delalloc or journalled data we want to sync the file so * that we can make sure we allocate blocks for file and data * is in place for the user to see it */ filemap_write_and_wait(mapping); } ret = iomap_bmap(mapping, block, &ext4_iomap_ops); out: inode_unlock_shared(inode); return ret; } static int ext4_read_folio(struct file *file, struct folio *folio) { int ret = -EAGAIN; struct inode *inode = folio->mapping->host; trace_ext4_read_folio(inode, folio); if (ext4_has_inline_data(inode)) ret = ext4_readpage_inline(inode, folio); if (ret == -EAGAIN) return ext4_mpage_readpages(inode, NULL, folio); return ret; } static void ext4_readahead(struct readahead_control *rac) { struct inode *inode = rac->mapping->host; /* If the file has inline data, no need to do readahead. */ if (ext4_has_inline_data(inode)) return; ext4_mpage_readpages(inode, rac, NULL); } static void ext4_invalidate_folio(struct folio *folio, size_t offset, size_t length) { trace_ext4_invalidate_folio(folio, offset, length); /* No journalling happens on data buffers when this function is used */ WARN_ON(folio_buffers(folio) && buffer_jbd(folio_buffers(folio))); block_invalidate_folio(folio, offset, length); } static int __ext4_journalled_invalidate_folio(struct folio *folio, size_t offset, size_t length) { journal_t *journal = EXT4_JOURNAL(folio->mapping->host); trace_ext4_journalled_invalidate_folio(folio, offset, length); /* * If it's a full truncate we just forget about the pending dirtying */ if (offset == 0 && length == folio_size(folio)) folio_clear_checked(folio); return jbd2_journal_invalidate_folio(journal, folio, offset, length); } /* Wrapper for aops... */ static void ext4_journalled_invalidate_folio(struct folio *folio, size_t offset, size_t length) { WARN_ON(__ext4_journalled_invalidate_folio(folio, offset, length) < 0); } static bool ext4_release_folio(struct folio *folio, gfp_t wait) { struct inode *inode = folio->mapping->host; journal_t *journal = EXT4_JOURNAL(inode); trace_ext4_release_folio(inode, folio); /* Page has dirty journalled data -> cannot release */ if (folio_test_checked(folio)) return false; if (journal) return jbd2_journal_try_to_free_buffers(journal, folio); else return try_to_free_buffers(folio); } static bool ext4_inode_datasync_dirty(struct inode *inode) { journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; if (journal) { if (jbd2_transaction_committed(journal, EXT4_I(inode)->i_datasync_tid)) return false; if (test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT)) return !list_empty(&EXT4_I(inode)->i_fc_list); return true; } /* Any metadata buffers to write? */ if (!list_empty(&inode->i_mapping->i_private_list)) return true; return inode->i_state & I_DIRTY_DATASYNC; } static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, struct ext4_map_blocks *map, loff_t offset, loff_t length, unsigned int flags) { u8 blkbits = inode->i_blkbits; /* * Writes that span EOF might trigger an I/O size update on completion, * so consider them to be dirty for the purpose of O_DSYNC, even if * there is no other metadata changes being made or are pending. */ iomap->flags = 0; if (ext4_inode_datasync_dirty(inode) || offset + length > i_size_read(inode)) iomap->flags |= IOMAP_F_DIRTY; if (map->m_flags & EXT4_MAP_NEW) iomap->flags |= IOMAP_F_NEW; /* HW-offload atomics are always used */ if (flags & IOMAP_ATOMIC) iomap->flags |= IOMAP_F_ATOMIC_BIO; if (flags & IOMAP_DAX) iomap->dax_dev = EXT4_SB(inode->i_sb)->s_daxdev; else iomap->bdev = inode->i_sb->s_bdev; iomap->offset = (u64) map->m_lblk << blkbits; iomap->length = (u64) map->m_len << blkbits; if ((map->m_flags & EXT4_MAP_MAPPED) && !ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) iomap->flags |= IOMAP_F_MERGED; /* * Flags passed to ext4_map_blocks() for direct I/O writes can result * in m_flags having both EXT4_MAP_MAPPED and EXT4_MAP_UNWRITTEN bits * set. In order for any allocated unwritten extents to be converted * into written extents correctly within the ->end_io() handler, we * need to ensure that the iomap->type is set appropriately. Hence, the * reason why we need to check whether the EXT4_MAP_UNWRITTEN bit has * been set first. */ if (map->m_flags & EXT4_MAP_UNWRITTEN) { iomap->type = IOMAP_UNWRITTEN; iomap->addr = (u64) map->m_pblk << blkbits; if (flags & IOMAP_DAX) iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off; } else if (map->m_flags & EXT4_MAP_MAPPED) { iomap->type = IOMAP_MAPPED; iomap->addr = (u64) map->m_pblk << blkbits; if (flags & IOMAP_DAX) iomap->addr += EXT4_SB(inode->i_sb)->s_dax_part_off; } else if (map->m_flags & EXT4_MAP_DELAYED) { iomap->type = IOMAP_DELALLOC; iomap->addr = IOMAP_NULL_ADDR; } else { iomap->type = IOMAP_HOLE; iomap->addr = IOMAP_NULL_ADDR; } } static int ext4_map_blocks_atomic_write_slow(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map) { ext4_lblk_t m_lblk = map->m_lblk; unsigned int m_len = map->m_len; unsigned int mapped_len = 0, m_flags = 0; ext4_fsblk_t next_pblk; bool check_next_pblk = false; int ret = 0; WARN_ON_ONCE(!ext4_has_feature_bigalloc(inode->i_sb)); /* * This is a slow path in case of mixed mapping. We use * EXT4_GET_BLOCKS_CREATE_ZERO flag here to make sure we get a single * contiguous mapped mapping. This will ensure any unwritten or hole * regions within the requested range is zeroed out and we return * a single contiguous mapped extent. */ m_flags = EXT4_GET_BLOCKS_CREATE_ZERO; do { ret = ext4_map_blocks(handle, inode, map, m_flags); if (ret < 0 && ret != -ENOSPC) goto out_err; /* * This should never happen, but let's return an error code to * avoid an infinite loop in here. */ if (ret == 0) { ret = -EFSCORRUPTED; ext4_warning_inode(inode, "ext4_map_blocks() couldn't allocate blocks m_flags: 0x%x, ret:%d", m_flags, ret); goto out_err; } /* * With bigalloc we should never get ENOSPC nor discontiguous * physical extents. */ if ((check_next_pblk && next_pblk != map->m_pblk) || ret == -ENOSPC) { ext4_warning_inode(inode, "Non-contiguous allocation detected: expected %llu, got %llu, " "or ext4_map_blocks() returned out of space ret: %d", next_pblk, map->m_pblk, ret); ret = -EFSCORRUPTED; goto out_err; } next_pblk = map->m_pblk + map->m_len; check_next_pblk = true; mapped_len += map->m_len; map->m_lblk += map->m_len; map->m_len = m_len - mapped_len; } while (mapped_len < m_len); /* * We might have done some work in above loop, so we need to query the * start of the physical extent, based on the origin m_lblk and m_len. * Let's also ensure we were able to allocate the required range for * mixed mapping case. */ map->m_lblk = m_lblk; map->m_len = m_len; map->m_flags = 0; ret = ext4_map_blocks(handle, inode, map, EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF); if (ret != m_len) { ext4_warning_inode(inode, "allocation failed for atomic write request m_lblk:%u, m_len:%u, ret:%d\n", m_lblk, m_len, ret); ret = -EINVAL; } return ret; out_err: /* reset map before returning an error */ map->m_lblk = m_lblk; map->m_len = m_len; map->m_flags = 0; return ret; } /* * ext4_map_blocks_atomic: Helper routine to ensure the entire requested * range in @map [lblk, lblk + len) is one single contiguous extent with no * mixed mappings. * * We first use m_flags passed to us by our caller (ext4_iomap_alloc()). * We only call EXT4_GET_BLOCKS_ZERO in the slow path, when the underlying * physical extent for the requested range does not have a single contiguous * mapping type i.e. (Hole, Mapped, or Unwritten) throughout. * In that case we will loop over the requested range to allocate and zero out * the unwritten / holes in between, to get a single mapped extent from * [m_lblk, m_lblk + m_len). Note that this is only possible because we know * this can be called only with bigalloc enabled filesystem where the underlying * cluster is already allocated. This avoids allocating discontiguous extents * in the slow path due to multiple calls to ext4_map_blocks(). * The slow path is mostly non-performance critical path, so it should be ok to * loop using ext4_map_blocks() with appropriate flags to allocate & zero the * underlying short holes/unwritten extents within the requested range. */ static int ext4_map_blocks_atomic_write(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int m_flags, bool *force_commit) { ext4_lblk_t m_lblk = map->m_lblk; unsigned int m_len = map->m_len; int ret = 0; WARN_ON_ONCE(m_len > 1 && !ext4_has_feature_bigalloc(inode->i_sb)); ret = ext4_map_blocks(handle, inode, map, m_flags); if (ret < 0 || ret == m_len) goto out; /* * This is a mixed mapping case where we were not able to allocate * a single contiguous extent. In that case let's reset requested * mapping and call the slow path. */ map->m_lblk = m_lblk; map->m_len = m_len; map->m_flags = 0; /* * slow path means we have mixed mapping, that means we will need * to force txn commit. */ *force_commit = true; return ext4_map_blocks_atomic_write_slow(handle, inode, map); out: return ret; } static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map, unsigned int flags) { handle_t *handle; u8 blkbits = inode->i_blkbits; int ret, dio_credits, m_flags = 0, retries = 0; bool force_commit = false; /* * Trim the mapping request to the maximum value that we can map at * once for direct I/O. */ if (map->m_len > DIO_MAX_BLOCKS) map->m_len = DIO_MAX_BLOCKS; /* * journal credits estimation for atomic writes. We call * ext4_map_blocks(), to find if there could be a mixed mapping. If yes, * then let's assume the no. of pextents required can be m_len i.e. * every alternate block can be unwritten and hole. */ if (flags & IOMAP_ATOMIC) { unsigned int orig_mlen = map->m_len; ret = ext4_map_blocks(NULL, inode, map, 0); if (ret < 0) return ret; if (map->m_len < orig_mlen) { map->m_len = orig_mlen; dio_credits = ext4_meta_trans_blocks(inode, orig_mlen, map->m_len); } else { dio_credits = ext4_chunk_trans_blocks(inode, map->m_len); } } else { dio_credits = ext4_chunk_trans_blocks(inode, map->m_len); } retry: /* * Either we allocate blocks and then don't get an unwritten extent, so * in that case we have reserved enough credits. Or, the blocks are * already allocated and unwritten. In that case, the extent conversion * fits into the credits as well. */ handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, dio_credits); if (IS_ERR(handle)) return PTR_ERR(handle); /* * DAX and direct I/O are the only two operations that are currently * supported with IOMAP_WRITE. */ WARN_ON(!(flags & (IOMAP_DAX | IOMAP_DIRECT))); if (flags & IOMAP_DAX) m_flags = EXT4_GET_BLOCKS_CREATE_ZERO; /* * We use i_size instead of i_disksize here because delalloc writeback * can complete at any point during the I/O and subsequently push the * i_disksize out to i_size. This could be beyond where direct I/O is * happening and thus expose allocated blocks to direct I/O reads. */ else if (((loff_t)map->m_lblk << blkbits) >= i_size_read(inode)) m_flags = EXT4_GET_BLOCKS_CREATE; else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) m_flags = EXT4_GET_BLOCKS_IO_CREATE_EXT; if (flags & IOMAP_ATOMIC) ret = ext4_map_blocks_atomic_write(handle, inode, map, m_flags, &force_commit); else ret = ext4_map_blocks(handle, inode, map, m_flags); /* * We cannot fill holes in indirect tree based inodes as that could * expose stale data in the case of a crash. Use the magic error code * to fallback to buffered I/O. */ if (!m_flags && !ret) ret = -ENOTBLK; ext4_journal_stop(handle); if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; /* * Force commit the current transaction if the allocation spans a mixed * mapping range. This ensures any pending metadata updates (like * unwritten to written extents conversion) in this range are in * consistent state with the file data blocks, before performing the * actual write I/O. If the commit fails, the whole I/O must be aborted * to prevent any possible torn writes. */ if (ret > 0 && force_commit) { int ret2; ret2 = ext4_force_commit(inode->i_sb); if (ret2) return ret2; } return ret; } static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap, struct iomap *srcmap) { int ret; struct ext4_map_blocks map; u8 blkbits = inode->i_blkbits; unsigned int orig_mlen; if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK) return -EINVAL; if (WARN_ON_ONCE(ext4_has_inline_data(inode))) return -ERANGE; /* * Calculate the first and last logical blocks respectively. */ map.m_lblk = offset >> blkbits; map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits, EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1; orig_mlen = map.m_len; if (flags & IOMAP_WRITE) { /* * We check here if the blocks are already allocated, then we * don't need to start a journal txn and we can directly return * the mapping information. This could boost performance * especially in multi-threaded overwrite requests. */ if (offset + length <= i_size_read(inode)) { ret = ext4_map_blocks(NULL, inode, &map, 0); /* * For atomic writes the entire requested length should * be mapped. */ if (map.m_flags & EXT4_MAP_MAPPED) { if ((!(flags & IOMAP_ATOMIC) && ret > 0) || (flags & IOMAP_ATOMIC && ret >= orig_mlen)) goto out; } map.m_len = orig_mlen; } ret = ext4_iomap_alloc(inode, &map, flags); } else { /* * This can be called for overwrites path from * ext4_iomap_overwrite_begin(). */ ret = ext4_map_blocks(NULL, inode, &map, 0); } if (ret < 0) return ret; out: /* * When inline encryption is enabled, sometimes I/O to an encrypted file * has to be broken up to guarantee DUN contiguity. Handle this by * limiting the length of the mapping returned. */ map.m_len = fscrypt_limit_io_blocks(inode, map.m_lblk, map.m_len); /* * Before returning to iomap, let's ensure the allocated mapping * covers the entire requested length for atomic writes. */ if (flags & IOMAP_ATOMIC) { if (map.m_len < (length >> blkbits)) { WARN_ON_ONCE(1); return -EINVAL; } } ext4_set_iomap(inode, iomap, &map, offset, length, flags); return 0; } static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap, struct iomap *srcmap) { int ret; /* * Even for writes we don't need to allocate blocks, so just pretend * we are reading to save overhead of starting a transaction. */ flags &= ~IOMAP_WRITE; ret = ext4_iomap_begin(inode, offset, length, flags, iomap, srcmap); WARN_ON_ONCE(!ret && iomap->type != IOMAP_MAPPED); return ret; } static inline bool ext4_want_directio_fallback(unsigned flags, ssize_t written) { /* must be a directio to fall back to buffered */ if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) != (IOMAP_WRITE | IOMAP_DIRECT)) return false; /* atomic writes are all-or-nothing */ if (flags & IOMAP_ATOMIC) return false; /* can only try again if we wrote nothing */ return written == 0; } static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length, ssize_t written, unsigned flags, struct iomap *iomap) { /* * Check to see whether an error occurred while writing out the data to * the allocated blocks. If so, return the magic error code for * non-atomic write so that we fallback to buffered I/O and attempt to * complete the remainder of the I/O. * For non-atomic writes, any blocks that may have been * allocated in preparation for the direct I/O will be reused during * buffered I/O. For atomic write, we never fallback to buffered-io. */ if (ext4_want_directio_fallback(flags, written)) return -ENOTBLK; return 0; } const struct iomap_ops ext4_iomap_ops = { .iomap_begin = ext4_iomap_begin, .iomap_end = ext4_iomap_end, }; const struct iomap_ops ext4_iomap_overwrite_ops = { .iomap_begin = ext4_iomap_overwrite_begin, .iomap_end = ext4_iomap_end, }; static int ext4_iomap_begin_report(struct inode *inode, loff_t offset, loff_t length, unsigned int flags, struct iomap *iomap, struct iomap *srcmap) { int ret; struct ext4_map_blocks map; u8 blkbits = inode->i_blkbits; if ((offset >> blkbits) > EXT4_MAX_LOGICAL_BLOCK) return -EINVAL; if (ext4_has_inline_data(inode)) { ret = ext4_inline_data_iomap(inode, iomap); if (ret != -EAGAIN) { if (ret == 0 && offset >= iomap->length) ret = -ENOENT; return ret; } } /* * Calculate the first and last logical block respectively. */ map.m_lblk = offset >> blkbits; map.m_len = min_t(loff_t, (offset + length - 1) >> blkbits, EXT4_MAX_LOGICAL_BLOCK) - map.m_lblk + 1; /* * Fiemap callers may call for offset beyond s_bitmap_maxbytes. * So handle it here itself instead of querying ext4_map_blocks(). * Since ext4_map_blocks() will warn about it and will return * -EIO error. */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (offset >= sbi->s_bitmap_maxbytes) { map.m_flags = 0; goto set_iomap; } } ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) return ret; set_iomap: ext4_set_iomap(inode, iomap, &map, offset, length, flags); return 0; } const struct iomap_ops ext4_iomap_report_ops = { .iomap_begin = ext4_iomap_begin_report, }; /* * For data=journal mode, folio should be marked dirty only when it was * writeably mapped. When that happens, it was already attached to the * transaction and marked as jbddirty (we take care of this in * ext4_page_mkwrite()). On transaction commit, we writeprotect page mappings * so we should have nothing to do here, except for the case when someone * had the page pinned and dirtied the page through this pin (e.g. by doing * direct IO to it). In that case we'd need to attach buffers here to the * transaction but we cannot due to lock ordering. We cannot just dirty the * folio and leave attached buffers clean, because the buffers' dirty state is * "definitive". We cannot just set the buffers dirty or jbddirty because all * the journalling code will explode. So what we do is to mark the folio * "pending dirty" and next time ext4_writepages() is called, attach buffers * to the transaction appropriately. */ static bool ext4_journalled_dirty_folio(struct address_space *mapping, struct folio *folio) { WARN_ON_ONCE(!folio_buffers(folio)); if (folio_maybe_dma_pinned(folio)) folio_set_checked(folio); return filemap_dirty_folio(mapping, folio); } static bool ext4_dirty_folio(struct address_space *mapping, struct folio *folio) { WARN_ON_ONCE(!folio_test_locked(folio) && !folio_test_dirty(folio)); WARN_ON_ONCE(!folio_buffers(folio)); return block_dirty_folio(mapping, folio); } static int ext4_iomap_swap_activate(struct swap_info_struct *sis, struct file *file, sector_t *span) { return iomap_swapfile_activate(sis, file, span, &ext4_iomap_report_ops); } static const struct address_space_operations ext4_aops = { .read_folio = ext4_read_folio, .readahead = ext4_readahead, .writepages = ext4_writepages, .write_begin = ext4_write_begin, .write_end = ext4_write_end, .dirty_folio = ext4_dirty_folio, .bmap = ext4_bmap, .invalidate_folio = ext4_invalidate_folio, .release_folio = ext4_release_folio, .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, .swap_activate = ext4_iomap_swap_activate, }; static const struct address_space_operations ext4_journalled_aops = { .read_folio = ext4_read_folio, .readahead = ext4_readahead, .writepages = ext4_writepages, .write_begin = ext4_write_begin, .write_end = ext4_journalled_write_end, .dirty_folio = ext4_journalled_dirty_folio, .bmap = ext4_bmap, .invalidate_folio = ext4_journalled_invalidate_folio, .release_folio = ext4_release_folio, .migrate_folio = buffer_migrate_folio_norefs, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, .swap_activate = ext4_iomap_swap_activate, }; static const struct address_space_operations ext4_da_aops = { .read_folio = ext4_read_folio, .readahead = ext4_readahead, .writepages = ext4_writepages, .write_begin = ext4_da_write_begin, .write_end = ext4_da_write_end, .dirty_folio = ext4_dirty_folio, .bmap = ext4_bmap, .invalidate_folio = ext4_invalidate_folio, .release_folio = ext4_release_folio, .migrate_folio = buffer_migrate_folio, .is_partially_uptodate = block_is_partially_uptodate, .error_remove_folio = generic_error_remove_folio, .swap_activate = ext4_iomap_swap_activate, }; static const struct address_space_operations ext4_dax_aops = { .writepages = ext4_dax_writepages, .dirty_folio = noop_dirty_folio, .bmap = ext4_bmap, .swap_activate = ext4_iomap_swap_activate, }; void ext4_set_aops(struct inode *inode) { switch (ext4_inode_journal_mode(inode)) { case EXT4_INODE_ORDERED_DATA_MODE: case EXT4_INODE_WRITEBACK_DATA_MODE: break; case EXT4_INODE_JOURNAL_DATA_MODE: inode->i_mapping->a_ops = &ext4_journalled_aops; return; default: BUG(); } if (IS_DAX(inode)) inode->i_mapping->a_ops = &ext4_dax_aops; else if (test_opt(inode->i_sb, DELALLOC)) inode->i_mapping->a_ops = &ext4_da_aops; else inode->i_mapping->a_ops = &ext4_aops; } /* * Here we can't skip an unwritten buffer even though it usually reads zero * because it might have data in pagecache (eg, if called from ext4_zero_range, * ext4_punch_hole, etc) which needs to be properly zeroed out. Otherwise a * racing writeback can come later and flush the stale pagecache to disk. */ static int __ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) { unsigned int offset, blocksize, pos; ext4_lblk_t iblock; struct inode *inode = mapping->host; struct buffer_head *bh; struct folio *folio; int err = 0; folio = __filemap_get_folio(mapping, from >> PAGE_SHIFT, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mapping_gfp_constraint(mapping, ~__GFP_FS)); if (IS_ERR(folio)) return PTR_ERR(folio); blocksize = inode->i_sb->s_blocksize; iblock = folio->index << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits); 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_freed(bh)) { BUFFER_TRACE(bh, "freed: skip"); goto unlock; } if (!buffer_mapped(bh)) { BUFFER_TRACE(bh, "unmapped"); ext4_get_block(inode, iblock, bh, 0); /* unmapped? It's a hole - nothing to do */ if (!buffer_mapped(bh)) { BUFFER_TRACE(bh, "still unmapped"); 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)) { err = ext4_read_bh_lock(bh, 0, true); if (err) goto unlock; if (fscrypt_inode_uses_fs_layer_crypto(inode)) { /* We expect the key to be set. */ BUG_ON(!fscrypt_has_encryption_key(inode)); err = fscrypt_decrypt_pagecache_blocks(folio, blocksize, bh_offset(bh)); if (err) { clear_buffer_uptodate(bh); goto unlock; } } } if (ext4_should_journal_data(inode)) { BUFFER_TRACE(bh, "get write access"); err = ext4_journal_get_write_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (err) goto unlock; } folio_zero_range(folio, offset, length); BUFFER_TRACE(bh, "zeroed end of block"); if (ext4_should_journal_data(inode)) { err = ext4_dirty_journalled_data(handle, bh); } else { err = 0; mark_buffer_dirty(bh); if (ext4_should_order_data(inode)) err = ext4_jbd2_inode_add_write(handle, inode, from, length); } unlock: folio_unlock(folio); folio_put(folio); return err; } /* * ext4_block_zero_page_range() zeros out a mapping of length 'length' * starting from file offset 'from'. The range to be zero'd must * be contained with in one block. If the specified range exceeds * the end of the block it will be shortened to end of the block * that corresponds to 'from' */ static int ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) { struct inode *inode = mapping->host; unsigned offset = from & (PAGE_SIZE-1); unsigned blocksize = inode->i_sb->s_blocksize; unsigned max = blocksize - (offset & (blocksize - 1)); /* * correct length if it does not fall between * 'from' and the end of the block */ if (length > max || length < 0) length = max; if (IS_DAX(inode)) { return dax_zero_range(inode, from, length, NULL, &ext4_iomap_ops); } return __ext4_block_zero_page_range(handle, mapping, from, length); } /* * ext4_block_truncate_page() zeroes out a mapping from file offset `from' * up to the end of the block which corresponds to `from'. * This required during truncate. We need to physically zero the tail end * of that block so it doesn't yield old data if the file is later grown. */ static int ext4_block_truncate_page(handle_t *handle, struct address_space *mapping, loff_t from) { unsigned offset = from & (PAGE_SIZE-1); unsigned length; unsigned blocksize; struct inode *inode = mapping->host; /* If we are processing an encrypted inode during orphan list handling */ if (IS_ENCRYPTED(inode) && !fscrypt_has_encryption_key(inode)) return 0; blocksize = inode->i_sb->s_blocksize; length = blocksize - (offset & (blocksize - 1)); return ext4_block_zero_page_range(handle, mapping, from, length); } int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t length) { struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; unsigned partial_start, partial_end; ext4_fsblk_t start, end; loff_t byte_end = (lstart + length - 1); int err = 0; partial_start = lstart & (sb->s_blocksize - 1); partial_end = byte_end & (sb->s_blocksize - 1); start = lstart >> sb->s_blocksize_bits; end = byte_end >> sb->s_blocksize_bits; /* Handle partial zero within the single block */ if (start == end && (partial_start || (partial_end != sb->s_blocksize - 1))) { err = ext4_block_zero_page_range(handle, mapping, lstart, length); return err; } /* Handle partial zero out on the start of the range */ if (partial_start) { err = ext4_block_zero_page_range(handle, mapping, lstart, sb->s_blocksize); if (err) return err; } /* Handle partial zero out on the end of the range */ if (partial_end != sb->s_blocksize - 1) err = ext4_block_zero_page_range(handle, mapping, byte_end - partial_end, partial_end + 1); return err; } int ext4_can_truncate(struct inode *inode) { if (S_ISREG(inode->i_mode)) return 1; if (S_ISDIR(inode->i_mode)) return 1; if (S_ISLNK(inode->i_mode)) return !ext4_inode_is_fast_symlink(inode); return 0; } /* * We have to make sure i_disksize gets properly updated before we truncate * page cache due to hole punching or zero range. Otherwise i_disksize update * can get lost as it may have been postponed to submission of writeback but * that will never happen after we truncate page cache. */ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, loff_t len) { handle_t *handle; int ret; loff_t size = i_size_read(inode); WARN_ON(!inode_is_locked(inode)); if (offset > size || offset + len < size) return 0; if (EXT4_I(inode)->i_disksize >= size) return 0; handle = ext4_journal_start(inode, EXT4_HT_MISC, 1); if (IS_ERR(handle)) return PTR_ERR(handle); ext4_update_i_disksize(inode, size); ret = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); return ret; } static inline void ext4_truncate_folio(struct inode *inode, loff_t start, loff_t end) { unsigned long blocksize = i_blocksize(inode); struct folio *folio; /* Nothing to be done if no complete block needs to be truncated. */ if (round_up(start, blocksize) >= round_down(end, blocksize)) return; folio = filemap_lock_folio(inode->i_mapping, start >> PAGE_SHIFT); if (IS_ERR(folio)) return; if (folio_mkclean(folio)) folio_mark_dirty(folio); folio_unlock(folio); folio_put(folio); } int ext4_truncate_page_cache_block_range(struct inode *inode, loff_t start, loff_t end) { unsigned long blocksize = i_blocksize(inode); int ret; /* * For journalled data we need to write (and checkpoint) pages * before discarding page cache to avoid inconsitent data on disk * in case of crash before freeing or unwritten converting trans * is committed. */ if (ext4_should_journal_data(inode)) { ret = filemap_write_and_wait_range(inode->i_mapping, start, end - 1); if (ret) return ret; goto truncate_pagecache; } /* * If the block size is less than the page size, the file's mapped * blocks within one page could be freed or converted to unwritten. * So it's necessary to remove writable userspace mappings, and then * ext4_page_mkwrite() can be called during subsequent write access * to these partial folios. */ if (!IS_ALIGNED(start | end, PAGE_SIZE) && blocksize < PAGE_SIZE && start < inode->i_size) { loff_t page_boundary = round_up(start, PAGE_SIZE); ext4_truncate_folio(inode, start, min(page_boundary, end)); if (end > page_boundary) ext4_truncate_folio(inode, round_down(end, PAGE_SIZE), end); } truncate_pagecache: truncate_pagecache_range(inode, start, end - 1); return 0; } static void ext4_wait_dax_page(struct inode *inode) { filemap_invalidate_unlock(inode->i_mapping); schedule(); filemap_invalidate_lock(inode->i_mapping); } int ext4_break_layouts(struct inode *inode) { if (WARN_ON_ONCE(!rwsem_is_locked(&inode->i_mapping->invalidate_lock))) return -EINVAL; return dax_break_layout_inode(inode, ext4_wait_dax_page); } /* * ext4_punch_hole: punches a hole in a file by releasing the blocks * associated with the given offset and length * * @inode: File inode * @offset: The offset where the hole will begin * @len: The length of the hole * * Returns: 0 on success or negative on failure */ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; ext4_lblk_t start_lblk, end_lblk; loff_t max_end = sb->s_maxbytes; loff_t end = offset + length; handle_t *handle; unsigned int credits; int ret; trace_ext4_punch_hole(inode, offset, length, 0); WARN_ON_ONCE(!inode_is_locked(inode)); /* * For indirect-block based inodes, make sure that the hole within * one block before last range. */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) max_end = EXT4_SB(sb)->s_bitmap_maxbytes - sb->s_blocksize; /* No need to punch hole beyond i_size */ if (offset >= inode->i_size || offset >= max_end) return 0; /* * If the hole extends beyond i_size, set the hole to end after * the page that contains i_size. */ if (end > inode->i_size) end = round_up(inode->i_size, PAGE_SIZE); if (end > max_end) end = max_end; length = end - offset; /* * Attach jinode to inode for jbd2 if we do any zeroing of partial * block. */ if (!IS_ALIGNED(offset | end, sb->s_blocksize)) { ret = ext4_inode_attach_jinode(inode); if (ret < 0) return ret; } ret = ext4_update_disksize_before_punch(inode, offset, length); if (ret) return ret; /* Now release the pages and zero block aligned part of pages*/ ret = ext4_truncate_page_cache_block_range(inode, offset, end); if (ret) return ret; if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_chunk_trans_extent(inode, 2); else credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(sb, ret); return ret; } ret = ext4_zero_partial_blocks(handle, inode, offset, length); if (ret) goto out_handle; /* If there are blocks to remove, do it */ start_lblk = EXT4_B_TO_LBLK(inode, offset); end_lblk = end >> inode->i_blkbits; if (end_lblk > start_lblk) { ext4_lblk_t hole_len = end_lblk - start_lblk; ext4_fc_track_inode(handle, inode); ext4_check_map_extents_env(inode); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, start_lblk, hole_len); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ret = ext4_ext_remove_space(inode, start_lblk, end_lblk - 1); else ret = ext4_ind_remove_space(handle, inode, start_lblk, end_lblk); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_handle; } ext4_es_insert_extent(inode, start_lblk, hole_len, ~0, EXTENT_STATUS_HOLE, 0); up_write(&EXT4_I(inode)->i_data_sem); } ext4_fc_track_range(handle, inode, start_lblk, end_lblk); ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) goto out_handle; ext4_update_inode_fsync_trans(handle, inode, 1); if (IS_SYNC(inode)) ext4_handle_sync(handle); out_handle: ext4_journal_stop(handle); return ret; } int ext4_inode_attach_jinode(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct jbd2_inode *jinode; if (ei->jinode || !EXT4_SB(inode->i_sb)->s_journal) return 0; jinode = jbd2_alloc_inode(GFP_KERNEL); spin_lock(&inode->i_lock); if (!ei->jinode) { if (!jinode) { spin_unlock(&inode->i_lock); return -ENOMEM; } ei->jinode = jinode; jbd2_journal_init_jbd_inode(ei->jinode, inode); jinode = NULL; } spin_unlock(&inode->i_lock); if (unlikely(jinode != NULL)) jbd2_free_inode(jinode); return 0; } /* * ext4_truncate() * * We block out ext4_get_block() block instantiations across the entire * transaction, and VFS/VM ensures that ext4_truncate() cannot run * simultaneously on behalf of the same inode. * * As we work through the truncate and commit bits of it to the journal there * is one core, guiding principle: the file's tree must always be consistent on * disk. We must be able to restart the truncate after a crash. * * The file's tree may be transiently inconsistent in memory (although it * probably isn't), but whenever we close off and commit a journal transaction, * the contents of (the filesystem + the journal) must be consistent and * restartable. It's pretty simple, really: bottom up, right to left (although * left-to-right works OK too). * * Note that at recovery time, journal replay occurs *before* the restart of * truncate against the orphan inode list. * * The committed inode has the new, desired i_size (which is the same as * i_disksize in this case). After a crash, ext4_orphan_cleanup() will see * that this inode's truncate did not complete and it will again call * ext4_truncate() to have another go. So there will be instantiated blocks * to the right of the truncation point in a crashed ext4 filesystem. But * that's fine - as long as they are linked from the inode, the post-crash * ext4_truncate() run will find them and release them. */ int ext4_truncate(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); unsigned int credits; int err = 0, err2; handle_t *handle; struct address_space *mapping = inode->i_mapping; /* * There is a possibility that we're either freeing the inode * or it's a completely new inode. In those cases we might not * have i_rwsem locked because it's not necessary. */ if (!(inode->i_state & (I_NEW|I_FREEING))) WARN_ON(!inode_is_locked(inode)); trace_ext4_truncate_enter(inode); if (!ext4_can_truncate(inode)) goto out_trace; if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC)) ext4_set_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE); if (ext4_has_inline_data(inode)) { int has_inline = 1; err = ext4_inline_data_truncate(inode, &has_inline); if (err || has_inline) goto out_trace; } /* If we zero-out tail of the page, we have to create jinode for jbd2 */ if (inode->i_size & (inode->i_sb->s_blocksize - 1)) { err = ext4_inode_attach_jinode(inode); if (err) goto out_trace; } if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) credits = ext4_chunk_trans_extent(inode, 1); else credits = ext4_blocks_for_truncate(inode); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto out_trace; } if (inode->i_size & (inode->i_sb->s_blocksize - 1)) ext4_block_truncate_page(handle, mapping, inode->i_size); /* * We add the inode to the orphan list, so that if this * truncate spans multiple transactions, and we crash, we will * resume the truncate when the filesystem recovers. It also * marks the inode dirty, to catch the new size. * * Implication: the file must always be in a sane, consistent * truncatable state while each transaction commits. */ err = ext4_orphan_add(handle, inode); if (err) goto out_stop; ext4_fc_track_inode(handle, inode); ext4_check_map_extents_env(inode); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) err = ext4_ext_truncate(handle, inode); else ext4_ind_truncate(handle, inode); up_write(&ei->i_data_sem); if (err) goto out_stop; if (IS_SYNC(inode)) ext4_handle_sync(handle); out_stop: /* * If this was a simple ftruncate() and the file will remain alive, * then we need to clear up the orphan record which we created above. * However, if this was a real unlink then we were called by * ext4_evict_inode(), and we allow that function to clean up the * orphan info for us. */ if (inode->i_nlink) ext4_orphan_del(handle, inode); inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); err2 = ext4_mark_inode_dirty(handle, inode); if (unlikely(err2 && !err)) err = err2; ext4_journal_stop(handle); out_trace: trace_ext4_truncate_exit(inode); return err; } static inline u64 ext4_inode_peek_iversion(const struct inode *inode) { if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) return inode_peek_iversion_raw(inode); else return inode_peek_iversion(inode); } static int ext4_inode_blocks_set(struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { struct inode *inode = &(ei->vfs_inode); u64 i_blocks = READ_ONCE(inode->i_blocks); struct super_block *sb = inode->i_sb; if (i_blocks <= ~0U) { /* * i_blocks can be represented in a 32 bit variable * as multiple of 512 bytes */ raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); raw_inode->i_blocks_high = 0; ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); return 0; } /* * This should never happen since sb->s_maxbytes should not have * allowed this, sb->s_maxbytes was set according to the huge_file * feature in ext4_fill_super(). */ if (!ext4_has_feature_huge_file(sb)) return -EFSCORRUPTED; if (i_blocks <= 0xffffffffffffULL) { /* * i_blocks can be represented in a 48 bit variable * as multiple of 512 bytes */ raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); ext4_clear_inode_flag(inode, EXT4_INODE_HUGE_FILE); } else { ext4_set_inode_flag(inode, EXT4_INODE_HUGE_FILE); /* i_block is stored in file system block size */ i_blocks = i_blocks >> (inode->i_blkbits - 9); raw_inode->i_blocks_lo = cpu_to_le32(i_blocks); raw_inode->i_blocks_high = cpu_to_le16(i_blocks >> 32); } return 0; } static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode) { struct ext4_inode_info *ei = EXT4_I(inode); uid_t i_uid; gid_t i_gid; projid_t i_projid; int block; int err; err = ext4_inode_blocks_set(raw_inode, ei); raw_inode->i_mode = cpu_to_le16(inode->i_mode); i_uid = i_uid_read(inode); i_gid = i_gid_read(inode); i_projid = from_kprojid(&init_user_ns, ei->i_projid); if (!(test_opt(inode->i_sb, NO_UID32))) { raw_inode->i_uid_low = cpu_to_le16(low_16_bits(i_uid)); raw_inode->i_gid_low = cpu_to_le16(low_16_bits(i_gid)); /* * Fix up interoperability with old kernels. Otherwise, * old inodes get re-used with the upper 16 bits of the * uid/gid intact. */ if (ei->i_dtime && list_empty(&ei->i_orphan)) { raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } else { raw_inode->i_uid_high = cpu_to_le16(high_16_bits(i_uid)); raw_inode->i_gid_high = cpu_to_le16(high_16_bits(i_gid)); } } else { raw_inode->i_uid_low = cpu_to_le16(fs_high2lowuid(i_uid)); raw_inode->i_gid_low = cpu_to_le16(fs_high2lowgid(i_gid)); raw_inode->i_uid_high = 0; raw_inode->i_gid_high = 0; } raw_inode->i_links_count = cpu_to_le16(inode->i_nlink); EXT4_INODE_SET_CTIME(inode, raw_inode); EXT4_INODE_SET_MTIME(inode, raw_inode); EXT4_INODE_SET_ATIME(inode, raw_inode); EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode); raw_inode->i_dtime = cpu_to_le32(ei->i_dtime); raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF); if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) raw_inode->i_file_acl_high = cpu_to_le16(ei->i_file_acl >> 32); raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl); ext4_isize_set(raw_inode, ei->i_disksize); raw_inode->i_generation = cpu_to_le32(inode->i_generation); if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) { if (old_valid_dev(inode->i_rdev)) { raw_inode->i_block[0] = cpu_to_le32(old_encode_dev(inode->i_rdev)); raw_inode->i_block[1] = 0; } else { raw_inode->i_block[0] = 0; raw_inode->i_block[1] = cpu_to_le32(new_encode_dev(inode->i_rdev)); raw_inode->i_block[2] = 0; } } else if (!ext4_has_inline_data(inode)) { for (block = 0; block < EXT4_N_BLOCKS; block++) raw_inode->i_block[block] = ei->i_data[block]; } if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { u64 ivers = ext4_inode_peek_iversion(inode); raw_inode->i_disk_version = cpu_to_le32(ivers); if (ei->i_extra_isize) { if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) raw_inode->i_version_hi = cpu_to_le32(ivers >> 32); raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize); } } if (i_projid != EXT4_DEF_PROJID && !ext4_has_feature_project(inode->i_sb)) err = err ?: -EFSCORRUPTED; if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) raw_inode->i_projid = cpu_to_le32(i_projid); ext4_inode_csum_set(inode, raw_inode, ei); return err; } /* * ext4_get_inode_loc returns with an extra refcount against the inode's * underlying buffer_head on success. If we pass 'inode' and it does not * have in-inode xattr, we have all inode data in memory that is needed * to recreate the on-disk version of this inode. */ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, struct inode *inode, struct ext4_iloc *iloc, ext4_fsblk_t *ret_block) { struct ext4_group_desc *gdp; struct buffer_head *bh; ext4_fsblk_t block; struct blk_plug plug; int inodes_per_block, inode_offset; iloc->bh = NULL; if (ino < EXT4_ROOT_INO || ino > le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count)) return -EFSCORRUPTED; iloc->block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb); gdp = ext4_get_group_desc(sb, iloc->block_group, NULL); if (!gdp) return -EIO; /* * Figure out the offset within the block group inode table */ inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; inode_offset = ((ino - 1) % EXT4_INODES_PER_GROUP(sb)); iloc->offset = (inode_offset % inodes_per_block) * EXT4_INODE_SIZE(sb); block = ext4_inode_table(sb, gdp); if ((block <= le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block)) || (block >= ext4_blocks_count(EXT4_SB(sb)->s_es))) { ext4_error(sb, "Invalid inode table block %llu in " "block_group %u", block, iloc->block_group); return -EFSCORRUPTED; } block += (inode_offset / inodes_per_block); bh = sb_getblk(sb, block); if (unlikely(!bh)) return -ENOMEM; if (ext4_buffer_uptodate(bh)) goto has_buffer; lock_buffer(bh); if (ext4_buffer_uptodate(bh)) { /* Someone brought it uptodate while we waited */ unlock_buffer(bh); goto has_buffer; } /* * If we have all information of the inode in memory and this * is the only valid inode in the block, we need not read the * block. */ if (inode && !ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { struct buffer_head *bitmap_bh; int i, start; start = inode_offset & ~(inodes_per_block - 1); /* Is the inode bitmap in cache? */ bitmap_bh = sb_getblk(sb, ext4_inode_bitmap(sb, gdp)); if (unlikely(!bitmap_bh)) goto make_io; /* * If the inode bitmap isn't in cache then the * optimisation may end up performing two reads instead * of one, so skip it. */ if (!buffer_uptodate(bitmap_bh)) { brelse(bitmap_bh); goto make_io; } for (i = start; i < start + inodes_per_block; i++) { if (i == inode_offset) continue; if (ext4_test_bit(i, bitmap_bh->b_data)) break; } brelse(bitmap_bh); if (i == start + inodes_per_block) { struct ext4_inode *raw_inode = (struct ext4_inode *) (bh->b_data + iloc->offset); /* all other inodes are free, so skip I/O */ memset(bh->b_data, 0, bh->b_size); if (!ext4_test_inode_state(inode, EXT4_STATE_NEW)) ext4_fill_raw_inode(inode, raw_inode); set_buffer_uptodate(bh); unlock_buffer(bh); goto has_buffer; } } make_io: /* * If we need to do any I/O, try to pre-readahead extra * blocks from the inode table. */ blk_start_plug(&plug); if (EXT4_SB(sb)->s_inode_readahead_blks) { ext4_fsblk_t b, end, table; unsigned num; __u32 ra_blks = EXT4_SB(sb)->s_inode_readahead_blks; table = ext4_inode_table(sb, gdp); /* s_inode_readahead_blks is always a power of 2 */ b = block & ~((ext4_fsblk_t) ra_blks - 1); if (table > b) b = table; end = b + ra_blks; num = EXT4_INODES_PER_GROUP(sb); if (ext4_has_group_desc_csum(sb)) num -= ext4_itable_unused_count(sb, gdp); table += num / inodes_per_block; if (end > table) end = table; while (b <= end) ext4_sb_breadahead_unmovable(sb, b++); } /* * There are other valid inodes in the buffer, this inode * has in-inode xattrs, or we don't have this inode in memory. * Read the block from disk. */ trace_ext4_load_inode(sb, ino); ext4_read_bh_nowait(bh, REQ_META | REQ_PRIO, NULL, ext4_simulate_fail(sb, EXT4_SIM_INODE_EIO)); blk_finish_plug(&plug); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { if (ret_block) *ret_block = block; brelse(bh); return -EIO; } has_buffer: iloc->bh = bh; return 0; } static int __ext4_get_inode_loc_noinmem(struct inode *inode, struct ext4_iloc *iloc) { ext4_fsblk_t err_blk = 0; int ret; ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, NULL, iloc, &err_blk); if (ret == -EIO) ext4_error_inode_block(inode, err_blk, EIO, "unable to read itable block"); return ret; } int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) { ext4_fsblk_t err_blk = 0; int ret; ret = __ext4_get_inode_loc(inode->i_sb, inode->i_ino, inode, iloc, &err_blk); if (ret == -EIO) ext4_error_inode_block(inode, err_blk, EIO, "unable to read itable block"); return ret; } int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino, struct ext4_iloc *iloc) { return __ext4_get_inode_loc(sb, ino, NULL, iloc, NULL); } static bool ext4_should_enable_dax(struct inode *inode) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (test_opt2(inode->i_sb, DAX_NEVER)) return false; if (!S_ISREG(inode->i_mode)) return false; if (ext4_should_journal_data(inode)) return false; if (ext4_has_inline_data(inode)) return false; if (ext4_test_inode_flag(inode, EXT4_INODE_ENCRYPT)) return false; if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY)) return false; if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) return false; if (test_opt(inode->i_sb, DAX_ALWAYS)) return true; return ext4_test_inode_flag(inode, EXT4_INODE_DAX); } void ext4_set_inode_flags(struct inode *inode, bool init) { unsigned int flags = EXT4_I(inode)->i_flags; unsigned int new_fl = 0; WARN_ON_ONCE(IS_DAX(inode) && init); if (flags & EXT4_SYNC_FL) new_fl |= S_SYNC; if (flags & EXT4_APPEND_FL) new_fl |= S_APPEND; if (flags & EXT4_IMMUTABLE_FL) new_fl |= S_IMMUTABLE; if (flags & EXT4_NOATIME_FL) new_fl |= S_NOATIME; if (flags & EXT4_DIRSYNC_FL) new_fl |= S_DIRSYNC; /* Because of the way inode_set_flags() works we must preserve S_DAX * here if already set. */ new_fl |= (inode->i_flags & S_DAX); if (init && ext4_should_enable_dax(inode)) new_fl |= S_DAX; if (flags & EXT4_ENCRYPT_FL) new_fl |= S_ENCRYPTED; if (flags & EXT4_CASEFOLD_FL) new_fl |= S_CASEFOLD; if (flags & EXT4_VERITY_FL) new_fl |= S_VERITY; inode_set_flags(inode, new_fl, S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX| S_ENCRYPTED|S_CASEFOLD|S_VERITY); } static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { blkcnt_t i_blocks ; struct inode *inode = &(ei->vfs_inode); struct super_block *sb = inode->i_sb; if (ext4_has_feature_huge_file(sb)) { /* we are using combined 48 bit field */ i_blocks = ((u64)le16_to_cpu(raw_inode->i_blocks_high)) << 32 | le32_to_cpu(raw_inode->i_blocks_lo); if (ext4_test_inode_flag(inode, EXT4_INODE_HUGE_FILE)) { /* i_blocks represent file system block size */ return i_blocks << (inode->i_blkbits - 9); } else { return i_blocks; } } else { return le32_to_cpu(raw_inode->i_blocks_lo); } } static inline int ext4_iget_extra_inode(struct inode *inode, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { __le32 *magic = (void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize; if (EXT4_INODE_HAS_XATTR_SPACE(inode) && *magic == cpu_to_le32(EXT4_XATTR_MAGIC)) { int err; err = xattr_check_inode(inode, IHDR(inode, raw_inode), ITAIL(inode, raw_inode)); if (err) return err; ext4_set_inode_state(inode, EXT4_STATE_XATTR); err = ext4_find_inline_data_nolock(inode); if (!err && ext4_has_inline_data(inode)) ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); return err; } else EXT4_I(inode)->i_inline_off = 0; return 0; } int ext4_get_projid(struct inode *inode, kprojid_t *projid) { if (!ext4_has_feature_project(inode->i_sb)) return -EOPNOTSUPP; *projid = EXT4_I(inode)->i_projid; return 0; } /* * ext4 has self-managed i_version for ea inodes, it stores the lower 32bit of * refcount in i_version, so use raw values if inode has EXT4_EA_INODE_FL flag * set. */ static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val) { if (unlikely(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) inode_set_iversion_raw(inode, val); else inode_set_iversion_queried(inode, val); } static int check_igot_inode(struct inode *inode, ext4_iget_flags flags, const char *function, unsigned int line) { const char *err_str; if (flags & EXT4_IGET_EA_INODE) { if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { err_str = "missing EA_INODE flag"; goto error; } if (ext4_test_inode_state(inode, EXT4_STATE_XATTR) || EXT4_I(inode)->i_file_acl) { err_str = "ea_inode with extended attributes"; goto error; } } else { if ((EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) { /* * open_by_handle_at() could provide an old inode number * that has since been reused for an ea_inode; this does * not indicate filesystem corruption */ if (flags & EXT4_IGET_HANDLE) return -ESTALE; err_str = "unexpected EA_INODE flag"; goto error; } } if (is_bad_inode(inode) && !(flags & EXT4_IGET_BAD)) { err_str = "unexpected bad inode w/o EXT4_IGET_BAD"; goto error; } return 0; error: ext4_error_inode(inode, function, line, 0, "%s", err_str); return -EFSCORRUPTED; } static bool ext4_should_enable_large_folio(struct inode *inode) { struct super_block *sb = inode->i_sb; if (!S_ISREG(inode->i_mode)) return false; if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA || ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA)) return false; if (ext4_has_feature_verity(sb)) return false; if (ext4_has_feature_encrypt(sb)) return false; return true; } /* * Limit the maximum folio order to 2048 blocks to prevent overestimation * of reserve handle credits during the folio writeback in environments * where the PAGE_SIZE exceeds 4KB. */ #define EXT4_MAX_PAGECACHE_ORDER(i) \ umin(MAX_PAGECACHE_ORDER, (11 + (i)->i_blkbits - PAGE_SHIFT)) void ext4_set_inode_mapping_order(struct inode *inode) { if (!ext4_should_enable_large_folio(inode)) return; mapping_set_folio_order_range(inode->i_mapping, 0, EXT4_MAX_PAGECACHE_ORDER(inode)); } struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ext4_iget_flags flags, const char *function, unsigned int line) { struct ext4_iloc iloc; struct ext4_inode *raw_inode; struct ext4_inode_info *ei; struct ext4_super_block *es = EXT4_SB(sb)->s_es; struct inode *inode; journal_t *journal = EXT4_SB(sb)->s_journal; long ret; loff_t size; int block; uid_t i_uid; gid_t i_gid; projid_t i_projid; if ((!(flags & EXT4_IGET_SPECIAL) && is_special_ino(sb, ino)) || (ino < EXT4_ROOT_INO) || (ino > le32_to_cpu(es->s_inodes_count))) { if (flags & EXT4_IGET_HANDLE) return ERR_PTR(-ESTALE); __ext4_error(sb, function, line, false, EFSCORRUPTED, 0, "inode #%lu: comm %s: iget: illegal inode #", ino, current->comm); return ERR_PTR(-EFSCORRUPTED); } inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) { ret = check_igot_inode(inode, flags, function, line); if (ret) { iput(inode); return ERR_PTR(ret); } return inode; } ei = EXT4_I(inode); iloc.bh = NULL; ret = __ext4_get_inode_loc_noinmem(inode, &iloc); if (ret < 0) goto bad_inode; raw_inode = ext4_raw_inode(&iloc); if ((flags & EXT4_IGET_HANDLE) && (raw_inode->i_links_count == 0) && (raw_inode->i_mode == 0)) { ret = -ESTALE; goto bad_inode; } if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize); if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > EXT4_INODE_SIZE(inode->i_sb) || (ei->i_extra_isize & 3)) { ext4_error_inode(inode, function, line, 0, "iget: bad extra_isize %u " "(inode size %u)", ei->i_extra_isize, EXT4_INODE_SIZE(inode->i_sb)); ret = -EFSCORRUPTED; goto bad_inode; } } else ei->i_extra_isize = 0; /* Precompute checksum seed for inode metadata */ if (ext4_has_feature_metadata_csum(sb)) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __u32 csum; __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = raw_inode->i_generation; csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum)); ei->i_csum_seed = ext4_chksum(csum, (__u8 *)&gen, sizeof(gen)); } if ((!ext4_inode_csum_verify(inode, raw_inode, ei) || ext4_simulate_fail(sb, EXT4_SIM_INODE_CRC)) && (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY))) { ext4_error_inode_err(inode, function, line, 0, EFSBADCRC, "iget: checksum invalid"); ret = -EFSBADCRC; goto bad_inode; } inode->i_mode = le16_to_cpu(raw_inode->i_mode); i_uid = (uid_t)le16_to_cpu(raw_inode->i_uid_low); i_gid = (gid_t)le16_to_cpu(raw_inode->i_gid_low); if (ext4_has_feature_project(sb) && EXT4_INODE_SIZE(sb) > EXT4_GOOD_OLD_INODE_SIZE && EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) i_projid = (projid_t)le32_to_cpu(raw_inode->i_projid); else i_projid = EXT4_DEF_PROJID; if (!(test_opt(inode->i_sb, NO_UID32))) { i_uid |= le16_to_cpu(raw_inode->i_uid_high) << 16; i_gid |= le16_to_cpu(raw_inode->i_gid_high) << 16; } i_uid_write(inode, i_uid); i_gid_write(inode, i_gid); ei->i_projid = make_kprojid(&init_user_ns, i_projid); set_nlink(inode, le16_to_cpu(raw_inode->i_links_count)); ext4_clear_state_flags(ei); /* Only relevant on 32-bit archs */ ei->i_inline_off = 0; ei->i_dir_start_lookup = 0; ei->i_dtime = le32_to_cpu(raw_inode->i_dtime); /* We now have enough fields to check if the inode was active or not. * This is needed because nfsd might try to access dead inodes * the test is that same one that e2fsck uses * NeilBrown 1999oct15 */ if (inode->i_nlink == 0) { if ((inode->i_mode == 0 || flags & EXT4_IGET_SPECIAL || !(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_ORPHAN_FS)) && ino != EXT4_BOOT_LOADER_INO) { /* this inode is deleted or unallocated */ if (flags & EXT4_IGET_SPECIAL) { ext4_error_inode(inode, function, line, 0, "iget: special inode unallocated"); ret = -EFSCORRUPTED; } else ret = -ESTALE; goto bad_inode; } /* The only unlinked inodes we let through here have * valid i_mode and are being read by the orphan * recovery code: that's fine, we're about to complete * the process of deleting those. * OR it is the EXT4_BOOT_LOADER_INO which is * not initialized on a new filesystem. */ } ei->i_flags = le32_to_cpu(raw_inode->i_flags); ext4_set_inode_flags(inode, true); inode->i_blocks = ext4_inode_blocks(raw_inode, ei); ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo); if (ext4_has_feature_64bit(sb)) ei->i_file_acl |= ((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32; inode->i_size = ext4_isize(sb, raw_inode); size = i_size_read(inode); if (size < 0 || size > ext4_get_maxbytes(inode)) { ext4_error_inode(inode, function, line, 0, "iget: bad i_size value: %lld", size); ret = -EFSCORRUPTED; goto bad_inode; } /* * If dir_index is not enabled but there's dir with INDEX flag set, * we'd normally treat htree data as empty space. But with metadata * checksumming that corrupts checksums so forbid that. */ if (!ext4_has_feature_dir_index(sb) && ext4_has_feature_metadata_csum(sb) && ext4_test_inode_flag(inode, EXT4_INODE_INDEX)) { ext4_error_inode(inode, function, line, 0, "iget: Dir with htree data on filesystem without dir_index feature."); ret = -EFSCORRUPTED; goto bad_inode; } ei->i_disksize = inode->i_size; #ifdef CONFIG_QUOTA ei->i_reserved_quota = 0; #endif inode->i_generation = le32_to_cpu(raw_inode->i_generation); ei->i_block_group = iloc.block_group; ei->i_last_alloc_group = ~0; /* * NOTE! The in-memory inode i_data array is in little-endian order * even on big-endian machines: we do NOT byteswap the block numbers! */ for (block = 0; block < EXT4_N_BLOCKS; block++) ei->i_data[block] = raw_inode->i_block[block]; INIT_LIST_HEAD(&ei->i_orphan); ext4_fc_init_inode(&ei->vfs_inode); /* * Set transaction id's of transactions that have to be committed * to finish f[data]sync. We set them to currently running transaction * as we cannot be sure that the inode or some of its metadata isn't * part of the transaction - the inode could have been reclaimed and * now it is reread from disk. */ if (journal) { transaction_t *transaction; tid_t tid; read_lock(&journal->j_state_lock); if (journal->j_running_transaction) transaction = journal->j_running_transaction; else transaction = journal->j_committing_transaction; if (transaction) tid = transaction->t_tid; else tid = journal->j_commit_sequence; read_unlock(&journal->j_state_lock); ei->i_sync_tid = tid; ei->i_datasync_tid = tid; } if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { if (ei->i_extra_isize == 0) { /* The extra space is currently unused. Use it. */ BUILD_BUG_ON(sizeof(struct ext4_inode) & 3); ei->i_extra_isize = sizeof(struct ext4_inode) - EXT4_GOOD_OLD_INODE_SIZE; } else { ret = ext4_iget_extra_inode(inode, raw_inode, ei); if (ret) goto bad_inode; } } EXT4_INODE_GET_CTIME(inode, raw_inode); EXT4_INODE_GET_ATIME(inode, raw_inode); EXT4_INODE_GET_MTIME(inode, raw_inode); EXT4_EINODE_GET_XTIME(i_crtime, ei, raw_inode); if (likely(!test_opt2(inode->i_sb, HURD_COMPAT))) { u64 ivers = le32_to_cpu(raw_inode->i_disk_version); if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) { if (EXT4_FITS_IN_INODE(raw_inode, ei, i_version_hi)) ivers |= (__u64)(le32_to_cpu(raw_inode->i_version_hi)) << 32; } ext4_inode_set_iversion_queried(inode, ivers); } ret = 0; if (ei->i_file_acl && !ext4_inode_block_valid(inode, ei->i_file_acl, 1)) { ext4_error_inode(inode, function, line, 0, "iget: bad extended attribute block %llu", ei->i_file_acl); ret = -EFSCORRUPTED; goto bad_inode; } else if (!ext4_has_inline_data(inode)) { /* validate the block references in the inode */ if (!(EXT4_SB(sb)->s_mount_state & EXT4_FC_REPLAY) && (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || (S_ISLNK(inode->i_mode) && !ext4_inode_is_fast_symlink(inode)))) { if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) ret = ext4_ext_check_inode(inode); else ret = ext4_ind_check_inode(inode); } } if (ret) goto bad_inode; if (S_ISREG(inode->i_mode)) { inode->i_op = &ext4_file_inode_operations; inode->i_fop = &ext4_file_operations; ext4_set_aops(inode); } else if (S_ISDIR(inode->i_mode)) { inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; } else if (S_ISLNK(inode->i_mode)) { /* VFS does not allow setting these so must be corruption */ if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) { ext4_error_inode(inode, function, line, 0, "iget: immutable or append flags " "not allowed on symlinks"); ret = -EFSCORRUPTED; goto bad_inode; } if (IS_ENCRYPTED(inode)) { inode->i_op = &ext4_encrypted_symlink_inode_operations; } else if (ext4_inode_is_fast_symlink(inode)) { inode->i_op = &ext4_fast_symlink_inode_operations; if (inode->i_size == 0 || inode->i_size >= sizeof(ei->i_data) || strnlen((char *)ei->i_data, inode->i_size + 1) != inode->i_size) { ext4_error_inode(inode, function, line, 0, "invalid fast symlink length %llu", (unsigned long long)inode->i_size); ret = -EFSCORRUPTED; goto bad_inode; } inode_set_cached_link(inode, (char *)ei->i_data, inode->i_size); } else { inode->i_op = &ext4_symlink_inode_operations; } } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) || S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { inode->i_op = &ext4_special_inode_operations; if (raw_inode->i_block[0]) init_special_inode(inode, inode->i_mode, old_decode_dev(le32_to_cpu(raw_inode->i_block[0]))); else init_special_inode(inode, inode->i_mode, new_decode_dev(le32_to_cpu(raw_inode->i_block[1]))); } else if (ino == EXT4_BOOT_LOADER_INO) { make_bad_inode(inode); } else { ret = -EFSCORRUPTED; ext4_error_inode(inode, function, line, 0, "iget: bogus i_mode (%o)", inode->i_mode); goto bad_inode; } if (IS_CASEFOLDED(inode) && !ext4_has_feature_casefold(inode->i_sb)) { ext4_error_inode(inode, function, line, 0, "casefold flag without casefold feature"); ret = -EFSCORRUPTED; goto bad_inode; } ext4_set_inode_mapping_order(inode); ret = check_igot_inode(inode, flags, function, line); /* * -ESTALE here means there is nothing inherently wrong with the inode, * it's just not an inode we can return for an fhandle lookup. */ if (ret == -ESTALE) { brelse(iloc.bh); unlock_new_inode(inode); iput(inode); return ERR_PTR(-ESTALE); } if (ret) goto bad_inode; brelse(iloc.bh); unlock_new_inode(inode); return inode; bad_inode: brelse(iloc.bh); iget_failed(inode); return ERR_PTR(ret); } static void __ext4_update_other_inode_time(struct super_block *sb, unsigned long orig_ino, unsigned long ino, struct ext4_inode *raw_inode) { struct inode *inode; inode = find_inode_by_ino_rcu(sb, ino); if (!inode) return; if (!inode_is_dirtytime_only(inode)) return; spin_lock(&inode->i_lock); if (inode_is_dirtytime_only(inode)) { struct ext4_inode_info *ei = EXT4_I(inode); inode->i_state &= ~I_DIRTY_TIME; spin_unlock(&inode->i_lock); spin_lock(&ei->i_raw_lock); EXT4_INODE_SET_CTIME(inode, raw_inode); EXT4_INODE_SET_MTIME(inode, raw_inode); EXT4_INODE_SET_ATIME(inode, raw_inode); ext4_inode_csum_set(inode, raw_inode, ei); spin_unlock(&ei->i_raw_lock); trace_ext4_other_inode_update_time(inode, orig_ino); return; } spin_unlock(&inode->i_lock); } /* * Opportunistically update the other time fields for other inodes in * the same inode table block. */ static void ext4_update_other_inodes_time(struct super_block *sb, unsigned long orig_ino, char *buf) { unsigned long ino; int i, inodes_per_block = EXT4_SB(sb)->s_inodes_per_block; int inode_size = EXT4_INODE_SIZE(sb); /* * Calculate the first inode in the inode table block. Inode * numbers are one-based. That is, the first inode in a block * (assuming 4k blocks and 256 byte inodes) is (n*16 + 1). */ ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1; rcu_read_lock(); for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) { if (ino == orig_ino) continue; __ext4_update_other_inode_time(sb, orig_ino, ino, (struct ext4_inode *)buf); } rcu_read_unlock(); } /* * Post the struct inode info into an on-disk inode location in the * buffer-cache. This gobbles the caller's reference to the * buffer_head in the inode location struct. * * The caller must have write access to iloc->bh. */ static int ext4_do_update_inode(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { struct ext4_inode *raw_inode = ext4_raw_inode(iloc); struct ext4_inode_info *ei = EXT4_I(inode); struct buffer_head *bh = iloc->bh; struct super_block *sb = inode->i_sb; int err; int need_datasync = 0, set_large_file = 0; spin_lock(&ei->i_raw_lock); /* * For fields not tracked in the in-memory inode, initialise them * to zero for new inodes. */ if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size); if (READ_ONCE(ei->i_disksize) != ext4_isize(inode->i_sb, raw_inode)) need_datasync = 1; if (ei->i_disksize > 0x7fffffffULL) { if (!ext4_has_feature_large_file(sb) || EXT4_SB(sb)->s_es->s_rev_level == cpu_to_le32(EXT4_GOOD_OLD_REV)) set_large_file = 1; } err = ext4_fill_raw_inode(inode, raw_inode); spin_unlock(&ei->i_raw_lock); if (err) { EXT4_ERROR_INODE(inode, "corrupted inode contents"); goto out_brelse; } if (inode->i_sb->s_flags & SB_LAZYTIME) ext4_update_other_inodes_time(inode->i_sb, inode->i_ino, bh->b_data); BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata"); err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) goto out_error; ext4_clear_inode_state(inode, EXT4_STATE_NEW); if (set_large_file) { BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "get write access"); err = ext4_journal_get_write_access(handle, sb, EXT4_SB(sb)->s_sbh, EXT4_JTR_NONE); if (err) goto out_error; lock_buffer(EXT4_SB(sb)->s_sbh); ext4_set_feature_large_file(sb); ext4_superblock_csum_set(sb); unlock_buffer(EXT4_SB(sb)->s_sbh); ext4_handle_sync(handle); err = ext4_handle_dirty_metadata(handle, NULL, EXT4_SB(sb)->s_sbh); } ext4_update_inode_fsync_trans(handle, inode, need_datasync); out_error: ext4_std_error(inode->i_sb, err); out_brelse: brelse(bh); return err; } /* * ext4_write_inode() * * We are called from a few places: * * - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files. * Here, there will be no transaction running. We wait for any running * transaction to commit. * * - Within flush work (sys_sync(), kupdate and such). * We wait on commit, if told to. * * - Within iput_final() -> write_inode_now() * We wait on commit, if told to. * * In all cases it is actually safe for us to return without doing anything, * because the inode has been copied into a raw inode buffer in * ext4_mark_inode_dirty(). This is a correctness thing for WB_SYNC_ALL * writeback. * * Note that we are absolutely dependent upon all inode dirtiers doing the * right thing: they *must* call mark_inode_dirty() after dirtying info in * which we are interested. * * It would be a bug for them to not do this. The code: * * mark_inode_dirty(inode) * stuff(); * inode->i_size = expr; * * is in error because write_inode() could occur while `stuff()' is running, * and the new i_size will be lost. Plus the inode will no longer be on the * superblock's dirty inode list. */ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) { int err; if (WARN_ON_ONCE(current->flags & PF_MEMALLOC)) return 0; err = ext4_emergency_state(inode->i_sb); if (unlikely(err)) return err; if (EXT4_SB(inode->i_sb)->s_journal) { if (ext4_journal_current_handle()) { ext4_debug("called recursively, non-PF_MEMALLOC!\n"); dump_stack(); return -EIO; } /* * No need to force transaction in WB_SYNC_NONE mode. Also * ext4_sync_fs() will force the commit after everything is * written. */ if (wbc->sync_mode != WB_SYNC_ALL || wbc->for_sync) return 0; err = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal, EXT4_I(inode)->i_sync_tid); } else { struct ext4_iloc iloc; err = __ext4_get_inode_loc_noinmem(inode, &iloc); if (err) return err; /* * sync(2) will flush the whole buffer cache. No need to do * it here separately for each inode. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) sync_dirty_buffer(iloc.bh); if (buffer_req(iloc.bh) && !buffer_uptodate(iloc.bh)) { ext4_error_inode_block(inode, iloc.bh->b_blocknr, EIO, "IO error syncing inode"); err = -EIO; } brelse(iloc.bh); } return err; } /* * In data=journal mode ext4_journalled_invalidate_folio() may fail to invalidate * buffers that are attached to a folio straddling i_size and are undergoing * commit. In that case we have to wait for commit to finish and try again. */ static void ext4_wait_for_tail_page_commit(struct inode *inode) { unsigned offset; journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; tid_t commit_tid; int ret; bool has_transaction; offset = inode->i_size & (PAGE_SIZE - 1); /* * If the folio is fully truncated, we don't need to wait for any commit * (and we even should not as __ext4_journalled_invalidate_folio() may * strip all buffers from the folio but keep the folio dirty which can then * confuse e.g. concurrent ext4_writepages() seeing dirty folio without * buffers). Also we don't need to wait for any commit if all buffers in * the folio remain valid. This is most beneficial for the common case of * blocksize == PAGESIZE. */ if (!offset || offset > (PAGE_SIZE - i_blocksize(inode))) return; while (1) { struct folio *folio = filemap_lock_folio(inode->i_mapping, inode->i_size >> PAGE_SHIFT); if (IS_ERR(folio)) return; ret = __ext4_journalled_invalidate_folio(folio, offset, folio_size(folio) - offset); folio_unlock(folio); folio_put(folio); if (ret != -EBUSY) return; has_transaction = false; read_lock(&journal->j_state_lock); if (journal->j_committing_transaction) { commit_tid = journal->j_committing_transaction->t_tid; has_transaction = true; } read_unlock(&journal->j_state_lock); if (has_transaction) jbd2_log_wait_commit(journal, commit_tid); } } /* * ext4_setattr() * * Called from notify_change. * * We want to trap VFS attempts to truncate the file as soon as * possible. In particular, we want to make sure that when the VFS * shrinks i_size, we put the inode on the orphan list and modify * i_disksize immediately, so that during the subsequent flushing of * dirty pages and freeing of disk blocks, we can guarantee that any * commit will leave the blocks being flushed in an unused state on * disk. (On recovery, the inode will get truncated and the blocks will * be freed, so we have a strong guarantee that no future commit will * leave these blocks visible to the user.) * * Another thing we have to assure is that if we are in ordered mode * and inode is still attached to the committing transaction, we must * we start writeout of all the dirty pages which are being truncated. * This way we are sure that all the data written in the previous * transaction are already on disk (truncate waits for pages under * writeback). * * Called with inode->i_rwsem down. */ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); int error, rc = 0; int orphan = 0; const unsigned int ia_valid = attr->ia_valid; bool inc_ivers = true; error = ext4_emergency_state(inode->i_sb); if (unlikely(error)) return error; if (unlikely(IS_IMMUTABLE(inode))) return -EPERM; if (unlikely(IS_APPEND(inode) && (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)))) return -EPERM; error = setattr_prepare(idmap, dentry, attr); if (error) return error; error = fscrypt_prepare_setattr(dentry, attr); if (error) return error; error = fsverity_prepare_setattr(dentry, attr); if (error) return error; if (is_quota_modification(idmap, inode, attr)) { error = dquot_initialize(inode); if (error) return error; } if (i_uid_needs_update(idmap, attr, inode) || i_gid_needs_update(idmap, attr, inode)) { handle_t *handle; /* (user+group)*(old+new) structure, inode write (sb, * inode block, ? - but truncate inode update has it) */ handle = ext4_journal_start(inode, EXT4_HT_QUOTA, (EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb) + EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb)) + 3); if (IS_ERR(handle)) { error = PTR_ERR(handle); goto err_out; } /* dquot_transfer() calls back ext4_get_inode_usage() which * counts xattr inode references. */ down_read(&EXT4_I(inode)->xattr_sem); error = dquot_transfer(idmap, inode, attr); up_read(&EXT4_I(inode)->xattr_sem); if (error) { ext4_journal_stop(handle); return error; } /* Update corresponding info in inode so that everything is in * one transaction */ i_uid_update(idmap, attr, inode); i_gid_update(idmap, attr, inode); error = ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); if (unlikely(error)) { return error; } } if (attr->ia_valid & ATTR_SIZE) { handle_t *handle; loff_t oldsize = inode->i_size; loff_t old_disksize; int shrink = (attr->ia_size < inode->i_size); if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); if (attr->ia_size > sbi->s_bitmap_maxbytes) { return -EFBIG; } } if (!S_ISREG(inode->i_mode)) { return -EINVAL; } if (attr->ia_size == inode->i_size) inc_ivers = false; if (shrink) { if (ext4_should_order_data(inode)) { error = ext4_begin_ordered_truncate(inode, attr->ia_size); if (error) goto err_out; } /* * Blocks are going to be removed from the inode. Wait * for dio in flight. */ inode_dio_wait(inode); } filemap_invalidate_lock(inode->i_mapping); rc = ext4_break_layouts(inode); if (rc) { filemap_invalidate_unlock(inode->i_mapping); goto err_out; } if (attr->ia_size != inode->i_size) { /* attach jbd2 jinode for EOF folio tail zeroing */ if (attr->ia_size & (inode->i_sb->s_blocksize - 1) || oldsize & (inode->i_sb->s_blocksize - 1)) { error = ext4_inode_attach_jinode(inode); if (error) goto out_mmap_sem; } handle = ext4_journal_start(inode, EXT4_HT_INODE, 3); if (IS_ERR(handle)) { error = PTR_ERR(handle); goto out_mmap_sem; } if (ext4_handle_valid(handle) && shrink) { error = ext4_orphan_add(handle, inode); orphan = 1; } /* * Update c/mtime and tail zero the EOF folio on * truncate up. ext4_truncate() handles the shrink case * below. */ if (!shrink) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); if (oldsize & (inode->i_sb->s_blocksize - 1)) ext4_block_truncate_page(handle, inode->i_mapping, oldsize); } if (shrink) ext4_fc_track_range(handle, inode, (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> inode->i_sb->s_blocksize_bits, EXT_MAX_BLOCKS - 1); else ext4_fc_track_range( handle, inode, (oldsize > 0 ? oldsize - 1 : oldsize) >> inode->i_sb->s_blocksize_bits, (attr->ia_size > 0 ? attr->ia_size - 1 : 0) >> inode->i_sb->s_blocksize_bits); down_write(&EXT4_I(inode)->i_data_sem); old_disksize = EXT4_I(inode)->i_disksize; EXT4_I(inode)->i_disksize = attr->ia_size; /* * We have to update i_size under i_data_sem together * with i_disksize to avoid races with writeback code * running ext4_wb_update_i_disksize(). */ if (!error) i_size_write(inode, attr->ia_size); else EXT4_I(inode)->i_disksize = old_disksize; up_write(&EXT4_I(inode)->i_data_sem); rc = ext4_mark_inode_dirty(handle, inode); if (!error) error = rc; ext4_journal_stop(handle); if (error) goto out_mmap_sem; if (!shrink) { pagecache_isize_extended(inode, oldsize, inode->i_size); } else if (ext4_should_journal_data(inode)) { ext4_wait_for_tail_page_commit(inode); } } /* * Truncate pagecache after we've waited for commit * in data=journal mode to make pages freeable. */ truncate_pagecache(inode, inode->i_size); /* * Call ext4_truncate() even if i_size didn't change to * truncate possible preallocated blocks. */ if (attr->ia_size <= oldsize) { rc = ext4_truncate(inode); if (rc) error = rc; } out_mmap_sem: filemap_invalidate_unlock(inode->i_mapping); } if (!error) { if (inc_ivers) inode_inc_iversion(inode); setattr_copy(idmap, inode, attr); mark_inode_dirty(inode); } /* * If the call to ext4_truncate failed to get a transaction handle at * all, we need to clean up the in-core orphan list manually. */ if (orphan && inode->i_nlink) ext4_orphan_del(NULL, inode); if (!error && (ia_valid & ATTR_MODE)) rc = posix_acl_chmod(idmap, dentry, inode->i_mode); err_out: if (error) ext4_std_error(inode->i_sb, error); if (!error) error = rc; return error; } u32 ext4_dio_alignment(struct inode *inode) { if (fsverity_active(inode)) return 0; if (ext4_should_journal_data(inode)) return 0; if (ext4_has_inline_data(inode)) return 0; if (IS_ENCRYPTED(inode)) { if (!fscrypt_dio_supported(inode)) return 0; return i_blocksize(inode); } return 1; /* use the iomap defaults */ } int ext4_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); struct ext4_inode *raw_inode; struct ext4_inode_info *ei = EXT4_I(inode); unsigned int flags; if ((request_mask & STATX_BTIME) && EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) { stat->result_mask |= STATX_BTIME; stat->btime.tv_sec = ei->i_crtime.tv_sec; stat->btime.tv_nsec = ei->i_crtime.tv_nsec; } /* * Return the DIO alignment restrictions if requested. We only return * this information when requested, since on encrypted files it might * take a fair bit of work to get if the file wasn't opened recently. */ if ((request_mask & STATX_DIOALIGN) && S_ISREG(inode->i_mode)) { u32 dio_align = ext4_dio_alignment(inode); stat->result_mask |= STATX_DIOALIGN; if (dio_align == 1) { struct block_device *bdev = inode->i_sb->s_bdev; /* iomap defaults */ stat->dio_mem_align = bdev_dma_alignment(bdev) + 1; stat->dio_offset_align = bdev_logical_block_size(bdev); } else { stat->dio_mem_align = dio_align; stat->dio_offset_align = dio_align; } } if ((request_mask & STATX_WRITE_ATOMIC) && S_ISREG(inode->i_mode)) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned int awu_min = 0, awu_max = 0; if (ext4_inode_can_atomic_write(inode)) { awu_min = sbi->s_awu_min; awu_max = sbi->s_awu_max; } generic_fill_statx_atomic_writes(stat, awu_min, awu_max, 0); } flags = ei->i_flags & EXT4_FL_USER_VISIBLE; if (flags & EXT4_APPEND_FL) stat->attributes |= STATX_ATTR_APPEND; if (flags & EXT4_COMPR_FL) stat->attributes |= STATX_ATTR_COMPRESSED; if (flags & EXT4_ENCRYPT_FL) stat->attributes |= STATX_ATTR_ENCRYPTED; if (flags & EXT4_IMMUTABLE_FL) stat->attributes |= STATX_ATTR_IMMUTABLE; if (flags & EXT4_NODUMP_FL) stat->attributes |= STATX_ATTR_NODUMP; if (flags & EXT4_VERITY_FL) stat->attributes |= STATX_ATTR_VERITY; stat->attributes_mask |= (STATX_ATTR_APPEND | STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED | STATX_ATTR_IMMUTABLE | STATX_ATTR_NODUMP | STATX_ATTR_VERITY); generic_fillattr(idmap, request_mask, inode, stat); return 0; } int ext4_file_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { struct inode *inode = d_inode(path->dentry); u64 delalloc_blocks; ext4_getattr(idmap, path, stat, request_mask, query_flags); /* * If there is inline data in the inode, the inode will normally not * have data blocks allocated (it may have an external xattr block). * Report at least one sector for such files, so tools like tar, rsync, * others don't incorrectly think the file is completely sparse. */ if (unlikely(ext4_has_inline_data(inode))) stat->blocks += (stat->size + 511) >> 9; /* * We can't update i_blocks if the block allocation is delayed * otherwise in the case of system crash before the real block * allocation is done, we will have i_blocks inconsistent with * on-disk file blocks. * We always keep i_blocks updated together with real * allocation. But to not confuse with user, stat * will return the blocks that include the delayed allocation * blocks for this file. */ delalloc_blocks = EXT4_C2B(EXT4_SB(inode->i_sb), EXT4_I(inode)->i_reserved_data_blocks); stat->blocks += delalloc_blocks << (inode->i_sb->s_blocksize_bits - 9); return 0; } static int ext4_index_trans_blocks(struct inode *inode, int lblocks, int pextents) { if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return ext4_ind_trans_blocks(inode, lblocks); return ext4_ext_index_trans_blocks(inode, pextents); } /* * Account for index blocks, block groups bitmaps and block group * descriptor blocks if modify datablocks and index blocks * worse case, the indexs blocks spread over different block groups * * If datablocks are discontiguous, they are possible to spread over * different block groups too. If they are contiguous, with flexbg, * they could still across block group boundary. * * Also account for superblock, inode, quota and xattr blocks */ int ext4_meta_trans_blocks(struct inode *inode, int lblocks, int pextents) { ext4_group_t groups, ngroups = ext4_get_groups_count(inode->i_sb); int gdpblocks; int idxblocks; int ret; /* * How many index and leaf blocks need to touch to map @lblocks * logical blocks to @pextents physical extents? */ idxblocks = ext4_index_trans_blocks(inode, lblocks, pextents); /* * Now let's see how many group bitmaps and group descriptors need * to account */ groups = idxblocks + pextents; gdpblocks = groups; if (groups > ngroups) groups = ngroups; if (groups > EXT4_SB(inode->i_sb)->s_gdb_count) gdpblocks = EXT4_SB(inode->i_sb)->s_gdb_count; /* bitmaps and block group descriptor blocks */ ret = idxblocks + groups + gdpblocks; /* Blocks for super block, inode, quota and xattr blocks */ ret += EXT4_META_TRANS_BLOCKS(inode->i_sb); return ret; } /* * Calculate the journal credits for modifying the number of blocks * in a single extent within one transaction. 'nrblocks' is used only * for non-extent inodes. For extent type inodes, 'nrblocks' can be * zero if the exact number of blocks is unknown. */ int ext4_chunk_trans_extent(struct inode *inode, int nrblocks) { int ret; ret = ext4_meta_trans_blocks(inode, nrblocks, 1); /* Account for data blocks for journalled mode */ if (ext4_should_journal_data(inode)) ret += nrblocks; return ret; } /* * Calculate the journal credits for a chunk of data modification. * * This is called from DIO, fallocate or whoever calling * ext4_map_blocks() to map/allocate a chunk of contiguous disk blocks. * * journal buffers for data blocks are not included here, as DIO * and fallocate do no need to journal data buffers. */ int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks) { return ext4_meta_trans_blocks(inode, nrblocks, 1); } /* * The caller must have previously called ext4_reserve_inode_write(). * Give this, we know that the caller already has write access to iloc->bh. */ int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { int err = 0; err = ext4_emergency_state(inode->i_sb); if (unlikely(err)) { put_bh(iloc->bh); return err; } ext4_fc_track_inode(handle, inode); /* the do_update_inode consumes one bh->b_count */ get_bh(iloc->bh); /* ext4_do_update_inode() does jbd2_journal_dirty_metadata */ err = ext4_do_update_inode(handle, inode, iloc); put_bh(iloc->bh); return err; } /* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { int err; err = ext4_emergency_state(inode->i_sb); if (unlikely(err)) return err; err = ext4_get_inode_loc(inode, iloc); if (!err) { BUFFER_TRACE(iloc->bh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode->i_sb, iloc->bh, EXT4_JTR_NONE); if (err) { brelse(iloc->bh); iloc->bh = NULL; } ext4_fc_track_inode(handle, inode); } ext4_std_error(inode->i_sb, err); return err; } static int __ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc, handle_t *handle, int *no_expand) { struct ext4_inode *raw_inode; struct ext4_xattr_ibody_header *header; unsigned int inode_size = EXT4_INODE_SIZE(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); int error; /* this was checked at iget time, but double check for good measure */ if ((EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize > inode_size) || (ei->i_extra_isize & 3)) { EXT4_ERROR_INODE(inode, "bad extra_isize %u (inode size %u)", ei->i_extra_isize, EXT4_INODE_SIZE(inode->i_sb)); return -EFSCORRUPTED; } if ((new_extra_isize < ei->i_extra_isize) || (new_extra_isize < 4) || (new_extra_isize > inode_size - EXT4_GOOD_OLD_INODE_SIZE)) return -EINVAL; /* Should never happen */ raw_inode = ext4_raw_inode(iloc); header = IHDR(inode, raw_inode); /* No extended attributes present */ if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) || header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) { memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize, 0, new_extra_isize - EXT4_I(inode)->i_extra_isize); EXT4_I(inode)->i_extra_isize = new_extra_isize; return 0; } /* * We may need to allocate external xattr block so we need quotas * initialized. Here we can be called with various locks held so we * cannot affort to initialize quotas ourselves. So just bail. */ if (dquot_initialize_needed(inode)) return -EAGAIN; /* try to expand with EAs present */ error = ext4_expand_extra_isize_ea(inode, new_extra_isize, raw_inode, handle); if (error) { /* * Inode size expansion failed; don't try again */ *no_expand = 1; } return error; } /* * Expand an inode by new_extra_isize bytes. * Returns 0 on success or negative error number on failure. */ static int ext4_try_to_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc iloc, handle_t *handle) { int no_expand; int error; if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) return -EOVERFLOW; /* * In nojournal mode, we can immediately attempt to expand * the inode. When journaled, we first need to obtain extra * buffer credits since we may write into the EA block * with this same handle. If journal_extend fails, then it will * only result in a minor loss of functionality for that inode. * If this is felt to be critical, then e2fsck should be run to * force a large enough s_min_extra_isize. */ if (ext4_journal_extend(handle, EXT4_DATA_TRANS_BLOCKS(inode->i_sb), 0) != 0) return -ENOSPC; if (ext4_write_trylock_xattr(inode, &no_expand) == 0) return -EBUSY; error = __ext4_expand_extra_isize(inode, new_extra_isize, &iloc, handle, &no_expand); ext4_write_unlock_xattr(inode, &no_expand); return error; } int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc) { handle_t *handle; int no_expand; int error, rc; if (ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND)) { brelse(iloc->bh); return -EOVERFLOW; } handle = ext4_journal_start(inode, EXT4_HT_INODE, EXT4_DATA_TRANS_BLOCKS(inode->i_sb)); if (IS_ERR(handle)) { error = PTR_ERR(handle); brelse(iloc->bh); return error; } ext4_write_lock_xattr(inode, &no_expand); BUFFER_TRACE(iloc->bh, "get_write_access"); error = ext4_journal_get_write_access(handle, inode->i_sb, iloc->bh, EXT4_JTR_NONE); if (error) { brelse(iloc->bh); goto out_unlock; } error = __ext4_expand_extra_isize(inode, new_extra_isize, iloc, handle, &no_expand); rc = ext4_mark_iloc_dirty(handle, inode, iloc); if (!error) error = rc; out_unlock: ext4_write_unlock_xattr(inode, &no_expand); ext4_journal_stop(handle); return error; } /* * What we do here is to mark the in-core inode as clean with respect to inode * dirtiness (it may still be data-dirty). * This means that the in-core inode may be reaped by prune_icache * without having to perform any I/O. This is a very good thing, * because *any* task may call prune_icache - even ones which * have a transaction open against a different journal. * * Is this cheating? Not really. Sure, we haven't written the * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. */ int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, const char *func, unsigned int line) { struct ext4_iloc iloc; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int err; might_sleep(); trace_ext4_mark_inode_dirty(inode, _RET_IP_); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto out; if (EXT4_I(inode)->i_extra_isize < sbi->s_want_extra_isize) ext4_try_to_expand_extra_isize(inode, sbi->s_want_extra_isize, iloc, handle); err = ext4_mark_iloc_dirty(handle, inode, &iloc); out: if (unlikely(err)) ext4_error_inode_err(inode, func, line, 0, err, "mark_inode_dirty error"); return err; } /* * ext4_dirty_inode() is called from __mark_inode_dirty() * * We're really interested in the case where a file is being extended. * i_size has been changed by generic_commit_write() and we thus need * to include the updated inode in the current transaction. * * Also, dquot_alloc_block() will always dirty the inode when blocks * are allocated to the file. * * If the inode is marked synchronous, we don't honour that here - doing * so would cause a commit on atime updates, which we don't bother doing. * We handle synchronous inodes at the highest possible level. */ void ext4_dirty_inode(struct inode *inode, int flags) { handle_t *handle; handle = ext4_journal_start(inode, EXT4_HT_INODE, 2); if (IS_ERR(handle)) return; ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); } int ext4_change_inode_journal_flag(struct inode *inode, int val) { journal_t *journal; handle_t *handle; int err; int alloc_ctx; /* * We have to be very careful here: changing a data block's * journaling status dynamically is dangerous. If we write a * data block to the journal, change the status and then delete * that block, we risk forgetting to revoke the old log record * from the journal and so a subsequent replay can corrupt data. * So, first we make sure that the journal is empty and that * nobody is changing anything. */ journal = EXT4_JOURNAL(inode); if (!journal) return 0; if (is_journal_aborted(journal)) return -EROFS; /* Wait for all existing dio workers */ inode_dio_wait(inode); /* * Before flushing the journal and switching inode's aops, we have * to flush all dirty data the inode has. There can be outstanding * delayed allocations, there can be unwritten extents created by * fallocate or buffered writes in dioread_nolock mode covered by * dirty data which can be converted only after flushing the dirty * data (and journalled aops don't know how to handle these cases). */ if (val) { filemap_invalidate_lock(inode->i_mapping); err = filemap_write_and_wait(inode->i_mapping); if (err < 0) { filemap_invalidate_unlock(inode->i_mapping); return err; } } alloc_ctx = ext4_writepages_down_write(inode->i_sb); jbd2_journal_lock_updates(journal); /* * OK, there are no updates running now, and all cached data is * synced to disk. We are now in a completely consistent state * which doesn't have anything in the journal, and we know that * no filesystem updates are running, so it is safe to modify * the inode's in-core data-journaling state flag now. */ if (val) ext4_set_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); else { err = jbd2_journal_flush(journal, 0); if (err < 0) { jbd2_journal_unlock_updates(journal); ext4_writepages_up_write(inode->i_sb, alloc_ctx); return err; } ext4_clear_inode_flag(inode, EXT4_INODE_JOURNAL_DATA); } ext4_set_aops(inode); jbd2_journal_unlock_updates(journal); ext4_writepages_up_write(inode->i_sb, alloc_ctx); if (val) filemap_invalidate_unlock(inode->i_mapping); /* Finally we can mark the inode as dirty. */ handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) return PTR_ERR(handle); ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_JOURNAL_FLAG_CHANGE, handle); err = ext4_mark_inode_dirty(handle, inode); ext4_handle_sync(handle); ext4_journal_stop(handle); ext4_std_error(inode->i_sb, err); return err; } static int ext4_bh_unmapped(handle_t *handle, struct inode *inode, struct buffer_head *bh) { return !buffer_mapped(bh); } static int ext4_block_page_mkwrite(struct inode *inode, struct folio *folio, get_block_t get_block) { handle_t *handle; loff_t size; unsigned long len; int credits; int ret; credits = ext4_chunk_trans_extent(inode, ext4_journal_blocks_per_folio(inode)); handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, credits); if (IS_ERR(handle)) return PTR_ERR(handle); folio_lock(folio); size = i_size_read(inode); /* Page got truncated from under us? */ if (folio->mapping != inode->i_mapping || folio_pos(folio) > size) { ret = -EFAULT; goto out_error; } len = folio_size(folio); if (folio_pos(folio) + len > size) len = size - folio_pos(folio); ret = ext4_block_write_begin(handle, folio, 0, len, get_block); if (ret) goto out_error; if (!ext4_should_journal_data(inode)) { block_commit_write(folio, 0, len); folio_mark_dirty(folio); } else { ret = ext4_journal_folio_buffers(handle, folio, len); if (ret) goto out_error; } ext4_journal_stop(handle); folio_wait_stable(folio); return ret; out_error: folio_unlock(folio); ext4_journal_stop(handle); return ret; } vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; struct folio *folio = page_folio(vmf->page); loff_t size; unsigned long len; int err; vm_fault_t ret; struct file *file = vma->vm_file; struct inode *inode = file_inode(file); struct address_space *mapping = inode->i_mapping; get_block_t *get_block = ext4_get_block; int retries = 0; if (unlikely(IS_IMMUTABLE(inode))) return VM_FAULT_SIGBUS; sb_start_pagefault(inode->i_sb); file_update_time(vma->vm_file); filemap_invalidate_lock_shared(mapping); err = ext4_convert_inline_data(inode); if (err) goto out_ret; /* * On data journalling we skip straight to the transaction handle: * there's no delalloc; page truncated will be checked later; the * early return w/ all buffers mapped (calculates size/len) can't * be used; and there's no dioread_nolock, so only ext4_get_block. */ if (ext4_should_journal_data(inode)) goto retry_alloc; /* Delalloc case is easy... */ if (test_opt(inode->i_sb, DELALLOC) && !ext4_nonda_switch(inode->i_sb)) { do { err = block_page_mkwrite(vma, vmf, ext4_da_get_block_prep); } while (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)); goto out_ret; } folio_lock(folio); size = i_size_read(inode); /* Page got truncated from under us? */ if (folio->mapping != mapping || folio_pos(folio) > size) { folio_unlock(folio); ret = VM_FAULT_NOPAGE; goto out; } len = folio_size(folio); if (folio_pos(folio) + len > size) len = size - folio_pos(folio); /* * Return if we have all the buffers mapped. This avoids the need to do * journal_start/journal_stop which can block and take a long time * * This cannot be done for data journalling, as we have to add the * inode to the transaction's list to writeprotect pages on commit. */ if (folio_buffers(folio)) { if (!ext4_walk_page_buffers(NULL, inode, folio_buffers(folio), 0, len, NULL, ext4_bh_unmapped)) { /* Wait so that we don't change page under IO */ folio_wait_stable(folio); ret = VM_FAULT_LOCKED; goto out; } } folio_unlock(folio); /* OK, we need to fill the hole... */ if (ext4_should_dioread_nolock(inode)) get_block = ext4_get_block_unwritten; retry_alloc: /* Start journal and allocate blocks */ err = ext4_block_page_mkwrite(inode, folio, get_block); if (err == -EAGAIN || (err == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))) goto retry_alloc; out_ret: ret = vmf_fs_error(err); out: filemap_invalidate_unlock_shared(mapping); sb_end_pagefault(inode->i_sb); return ret; } |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 | // SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause /* ****************************************************************** * huff0 huffman decoder, * part of Finite State Entropy library * Copyright (c) Meta Platforms, Inc. and affiliates. * * You can contact the author at : * - FSE+HUF source repository : https://github.com/Cyan4973/FiniteStateEntropy * * This source code is licensed under both the BSD-style license (found in the * LICENSE file in the root directory of this source tree) and the GPLv2 (found * in the COPYING file in the root directory of this source tree). * You may select, at your option, one of the above-listed licenses. ****************************************************************** */ /* ************************************************************** * Dependencies ****************************************************************/ #include "../common/zstd_deps.h" /* ZSTD_memcpy, ZSTD_memset */ #include "../common/compiler.h" #include "../common/bitstream.h" /* BIT_* */ #include "../common/fse.h" /* to compress headers */ #include "../common/huf.h" #include "../common/error_private.h" #include "../common/zstd_internal.h" #include "../common/bits.h" /* ZSTD_highbit32, ZSTD_countTrailingZeros64 */ /* ************************************************************** * Constants ****************************************************************/ #define HUF_DECODER_FAST_TABLELOG 11 /* ************************************************************** * Macros ****************************************************************/ #ifdef HUF_DISABLE_FAST_DECODE # define HUF_ENABLE_FAST_DECODE 0 #else # define HUF_ENABLE_FAST_DECODE 1 #endif /* These two optional macros force the use one way or another of the two * Huffman decompression implementations. You can't force in both directions * at the same time. */ #if defined(HUF_FORCE_DECOMPRESS_X1) && \ defined(HUF_FORCE_DECOMPRESS_X2) #error "Cannot force the use of the X1 and X2 decoders at the same time!" #endif /* When DYNAMIC_BMI2 is enabled, fast decoders are only called when bmi2 is * supported at runtime, so we can add the BMI2 target attribute. * When it is disabled, we will still get BMI2 if it is enabled statically. */ #if DYNAMIC_BMI2 # define HUF_FAST_BMI2_ATTRS BMI2_TARGET_ATTRIBUTE #else # define HUF_FAST_BMI2_ATTRS #endif #define HUF_EXTERN_C #define HUF_ASM_DECL HUF_EXTERN_C #if DYNAMIC_BMI2 # define HUF_NEED_BMI2_FUNCTION 1 #else # define HUF_NEED_BMI2_FUNCTION 0 #endif /* ************************************************************** * Error Management ****************************************************************/ #define HUF_isError ERR_isError /* ************************************************************** * Byte alignment for workSpace management ****************************************************************/ #define HUF_ALIGN(x, a) HUF_ALIGN_MASK((x), (a) - 1) #define HUF_ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask)) /* ************************************************************** * BMI2 Variant Wrappers ****************************************************************/ typedef size_t (*HUF_DecompressUsingDTableFn)(void *dst, size_t dstSize, const void *cSrc, size_t cSrcSize, const HUF_DTable *DTable); #if DYNAMIC_BMI2 #define HUF_DGEN(fn) \ \ static size_t fn##_default( \ void* dst, size_t dstSize, \ const void* cSrc, size_t cSrcSize, \ const HUF_DTable* DTable) \ { \ return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable); \ } \ \ static BMI2_TARGET_ATTRIBUTE size_t fn##_bmi2( \ void* dst, size_t dstSize, \ const void* cSrc, size_t cSrcSize, \ const HUF_DTable* DTable) \ { \ return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable); \ } \ \ static size_t fn(void* dst, size_t dstSize, void const* cSrc, \ size_t cSrcSize, HUF_DTable const* DTable, int flags) \ { \ if (flags & HUF_flags_bmi2) { \ return fn##_bmi2(dst, dstSize, cSrc, cSrcSize, DTable); \ } \ return fn##_default(dst, dstSize, cSrc, cSrcSize, DTable); \ } #else #define HUF_DGEN(fn) \ static size_t fn(void* dst, size_t dstSize, void const* cSrc, \ size_t cSrcSize, HUF_DTable const* DTable, int flags) \ { \ (void)flags; \ return fn##_body(dst, dstSize, cSrc, cSrcSize, DTable); \ } #endif /*-***************************/ /* generic DTableDesc */ /*-***************************/ typedef struct { BYTE maxTableLog; BYTE tableType; BYTE tableLog; BYTE reserved; } DTableDesc; static DTableDesc HUF_getDTableDesc(const HUF_DTable* table) { DTableDesc dtd; ZSTD_memcpy(&dtd, table, sizeof(dtd)); return dtd; } static size_t HUF_initFastDStream(BYTE const* ip) { BYTE const lastByte = ip[7]; size_t const bitsConsumed = lastByte ? 8 - ZSTD_highbit32(lastByte) : 0; size_t const value = MEM_readLEST(ip) | 1; assert(bitsConsumed <= 8); assert(sizeof(size_t) == 8); return value << bitsConsumed; } /* * The input/output arguments to the Huffman fast decoding loop: * * ip [in/out] - The input pointers, must be updated to reflect what is consumed. * op [in/out] - The output pointers, must be updated to reflect what is written. * bits [in/out] - The bitstream containers, must be updated to reflect the current state. * dt [in] - The decoding table. * ilowest [in] - The beginning of the valid range of the input. Decoders may read * down to this pointer. It may be below iend[0]. * oend [in] - The end of the output stream. op[3] must not cross oend. * iend [in] - The end of each input stream. ip[i] may cross iend[i], * as long as it is above ilowest, but that indicates corruption. */ typedef struct { BYTE const* ip[4]; BYTE* op[4]; U64 bits[4]; void const* dt; BYTE const* ilowest; BYTE* oend; BYTE const* iend[4]; } HUF_DecompressFastArgs; typedef void (*HUF_DecompressFastLoopFn)(HUF_DecompressFastArgs*); /* * Initializes args for the fast decoding loop. * @returns 1 on success * 0 if the fallback implementation should be used. * Or an error code on failure. */ static size_t HUF_DecompressFastArgs_init(HUF_DecompressFastArgs* args, void* dst, size_t dstSize, void const* src, size_t srcSize, const HUF_DTable* DTable) { void const* dt = DTable + 1; U32 const dtLog = HUF_getDTableDesc(DTable).tableLog; const BYTE* const istart = (const BYTE*)src; BYTE* const oend = ZSTD_maybeNullPtrAdd((BYTE*)dst, dstSize); /* The fast decoding loop assumes 64-bit little-endian. * This condition is false on x32. */ if (!MEM_isLittleEndian() || MEM_32bits()) return 0; /* Avoid nullptr addition */ if (dstSize == 0) return 0; assert(dst != NULL); /* strict minimum : jump table + 1 byte per stream */ if (srcSize < 10) return ERROR(corruption_detected); /* Must have at least 8 bytes per stream because we don't handle initializing smaller bit containers. * If table log is not correct at this point, fallback to the old decoder. * On small inputs we don't have enough data to trigger the fast loop, so use the old decoder. */ if (dtLog != HUF_DECODER_FAST_TABLELOG) return 0; /* Read the jump table. */ { size_t const length1 = MEM_readLE16(istart); size_t const length2 = MEM_readLE16(istart+2); size_t const length3 = MEM_readLE16(istart+4); size_t const length4 = srcSize - (length1 + length2 + length3 + 6); args->iend[0] = istart + 6; /* jumpTable */ args->iend[1] = args->iend[0] + length1; args->iend[2] = args->iend[1] + length2; args->iend[3] = args->iend[2] + length3; /* HUF_initFastDStream() requires this, and this small of an input * won't benefit from the ASM loop anyways. */ if (length1 < 8 || length2 < 8 || length3 < 8 || length4 < 8) return 0; if (length4 > srcSize) return ERROR(corruption_detected); /* overflow */ } /* ip[] contains the position that is currently loaded into bits[]. */ args->ip[0] = args->iend[1] - sizeof(U64); args->ip[1] = args->iend[2] - sizeof(U64); args->ip[2] = args->iend[3] - sizeof(U64); args->ip[3] = (BYTE const*)src + srcSize - sizeof(U64); /* op[] contains the output pointers. */ args->op[0] = (BYTE*)dst; args->op[1] = args->op[0] + (dstSize+3)/4; args->op[2] = args->op[1] + (dstSize+3)/4; args->op[3] = args->op[2] + (dstSize+3)/4; /* No point to call the ASM loop for tiny outputs. */ if (args->op[3] >= oend) return 0; /* bits[] is the bit container. * It is read from the MSB down to the LSB. * It is shifted left as it is read, and zeros are * shifted in. After the lowest valid bit a 1 is * set, so that CountTrailingZeros(bits[]) can be used * to count how many bits we've consumed. */ args->bits[0] = HUF_initFastDStream(args->ip[0]); args->bits[1] = HUF_initFastDStream(args->ip[1]); args->bits[2] = HUF_initFastDStream(args->ip[2]); args->bits[3] = HUF_initFastDStream(args->ip[3]); /* The decoders must be sure to never read beyond ilowest. * This is lower than iend[0], but allowing decoders to read * down to ilowest can allow an extra iteration or two in the * fast loop. */ args->ilowest = istart; args->oend = oend; args->dt = dt; return 1; } static size_t HUF_initRemainingDStream(BIT_DStream_t* bit, HUF_DecompressFastArgs const* args, int stream, BYTE* segmentEnd) { /* Validate that we haven't overwritten. */ if (args->op[stream] > segmentEnd) return ERROR(corruption_detected); /* Validate that we haven't read beyond iend[]. * Note that ip[] may be < iend[] because the MSB is * the next bit to read, and we may have consumed 100% * of the stream, so down to iend[i] - 8 is valid. */ if (args->ip[stream] < args->iend[stream] - 8) return ERROR(corruption_detected); /* Construct the BIT_DStream_t. */ assert(sizeof(size_t) == 8); bit->bitContainer = MEM_readLEST(args->ip[stream]); bit->bitsConsumed = ZSTD_countTrailingZeros64(args->bits[stream]); bit->start = (const char*)args->ilowest; bit->limitPtr = bit->start + sizeof(size_t); bit->ptr = (const char*)args->ip[stream]; return 0; } /* Calls X(N) for each stream 0, 1, 2, 3. */ #define HUF_4X_FOR_EACH_STREAM(X) \ do { \ X(0); \ X(1); \ X(2); \ X(3); \ } while (0) /* Calls X(N, var) for each stream 0, 1, 2, 3. */ #define HUF_4X_FOR_EACH_STREAM_WITH_VAR(X, var) \ do { \ X(0, (var)); \ X(1, (var)); \ X(2, (var)); \ X(3, (var)); \ } while (0) #ifndef HUF_FORCE_DECOMPRESS_X2 /*-***************************/ /* single-symbol decoding */ /*-***************************/ typedef struct { BYTE nbBits; BYTE byte; } HUF_DEltX1; /* single-symbol decoding */ /* * Packs 4 HUF_DEltX1 structs into a U64. This is used to lay down 4 entries at * a time. */ static U64 HUF_DEltX1_set4(BYTE symbol, BYTE nbBits) { U64 D4; if (MEM_isLittleEndian()) { D4 = (U64)((symbol << 8) + nbBits); } else { D4 = (U64)(symbol + (nbBits << 8)); } assert(D4 < (1U << 16)); D4 *= 0x0001000100010001ULL; return D4; } /* * Increase the tableLog to targetTableLog and rescales the stats. * If tableLog > targetTableLog this is a no-op. * @returns New tableLog */ static U32 HUF_rescaleStats(BYTE* huffWeight, U32* rankVal, U32 nbSymbols, U32 tableLog, U32 targetTableLog) { if (tableLog > targetTableLog) return tableLog; if (tableLog < targetTableLog) { U32 const scale = targetTableLog - tableLog; U32 s; /* Increase the weight for all non-zero probability symbols by scale. */ for (s = 0; s < nbSymbols; ++s) { huffWeight[s] += (BYTE)((huffWeight[s] == 0) ? 0 : scale); } /* Update rankVal to reflect the new weights. * All weights except 0 get moved to weight + scale. * Weights [1, scale] are empty. */ for (s = targetTableLog; s > scale; --s) { rankVal[s] = rankVal[s - scale]; } for (s = scale; s > 0; --s) { rankVal[s] = 0; } } return targetTableLog; } typedef struct { U32 rankVal[HUF_TABLELOG_ABSOLUTEMAX + 1]; U32 rankStart[HUF_TABLELOG_ABSOLUTEMAX + 1]; U32 statsWksp[HUF_READ_STATS_WORKSPACE_SIZE_U32]; BYTE symbols[HUF_SYMBOLVALUE_MAX + 1]; BYTE huffWeight[HUF_SYMBOLVALUE_MAX + 1]; } HUF_ReadDTableX1_Workspace; size_t HUF_readDTableX1_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int flags) { U32 tableLog = 0; U32 nbSymbols = 0; size_t iSize; void* const dtPtr = DTable + 1; HUF_DEltX1* const dt = (HUF_DEltX1*)dtPtr; HUF_ReadDTableX1_Workspace* wksp = (HUF_ReadDTableX1_Workspace*)workSpace; DEBUG_STATIC_ASSERT(HUF_DECOMPRESS_WORKSPACE_SIZE >= sizeof(*wksp)); if (sizeof(*wksp) > wkspSize) return ERROR(tableLog_tooLarge); DEBUG_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable)); /* ZSTD_memset(huffWeight, 0, sizeof(huffWeight)); */ /* is not necessary, even though some analyzer complain ... */ iSize = HUF_readStats_wksp(wksp->huffWeight, HUF_SYMBOLVALUE_MAX + 1, wksp->rankVal, &nbSymbols, &tableLog, src, srcSize, wksp->statsWksp, sizeof(wksp->statsWksp), flags); if (HUF_isError(iSize)) return iSize; /* Table header */ { DTableDesc dtd = HUF_getDTableDesc(DTable); U32 const maxTableLog = dtd.maxTableLog + 1; U32 const targetTableLog = MIN(maxTableLog, HUF_DECODER_FAST_TABLELOG); tableLog = HUF_rescaleStats(wksp->huffWeight, wksp->rankVal, nbSymbols, tableLog, targetTableLog); if (tableLog > (U32)(dtd.maxTableLog+1)) return ERROR(tableLog_tooLarge); /* DTable too small, Huffman tree cannot fit in */ dtd.tableType = 0; dtd.tableLog = (BYTE)tableLog; ZSTD_memcpy(DTable, &dtd, sizeof(dtd)); } /* Compute symbols and rankStart given rankVal: * * rankVal already contains the number of values of each weight. * * symbols contains the symbols ordered by weight. First are the rankVal[0] * weight 0 symbols, followed by the rankVal[1] weight 1 symbols, and so on. * symbols[0] is filled (but unused) to avoid a branch. * * rankStart contains the offset where each rank belongs in the DTable. * rankStart[0] is not filled because there are no entries in the table for * weight 0. */ { int n; U32 nextRankStart = 0; int const unroll = 4; int const nLimit = (int)nbSymbols - unroll + 1; for (n=0; n<(int)tableLog+1; n++) { U32 const curr = nextRankStart; nextRankStart += wksp->rankVal[n]; wksp->rankStart[n] = curr; } for (n=0; n < nLimit; n += unroll) { int u; for (u=0; u < unroll; ++u) { size_t const w = wksp->huffWeight[n+u]; wksp->symbols[wksp->rankStart[w]++] = (BYTE)(n+u); } } for (; n < (int)nbSymbols; ++n) { size_t const w = wksp->huffWeight[n]; wksp->symbols[wksp->rankStart[w]++] = (BYTE)n; } } /* fill DTable * We fill all entries of each weight in order. * That way length is a constant for each iteration of the outer loop. * We can switch based on the length to a different inner loop which is * optimized for that particular case. */ { U32 w; int symbol = wksp->rankVal[0]; int rankStart = 0; for (w=1; w<tableLog+1; ++w) { int const symbolCount = wksp->rankVal[w]; int const length = (1 << w) >> 1; int uStart = rankStart; BYTE const nbBits = (BYTE)(tableLog + 1 - w); int s; int u; switch (length) { case 1: for (s=0; s<symbolCount; ++s) { HUF_DEltX1 D; D.byte = wksp->symbols[symbol + s]; D.nbBits = nbBits; dt[uStart] = D; uStart += 1; } break; case 2: for (s=0; s<symbolCount; ++s) { HUF_DEltX1 D; D.byte = wksp->symbols[symbol + s]; D.nbBits = nbBits; dt[uStart+0] = D; dt[uStart+1] = D; uStart += 2; } break; case 4: for (s=0; s<symbolCount; ++s) { U64 const D4 = HUF_DEltX1_set4(wksp->symbols[symbol + s], nbBits); MEM_write64(dt + uStart, D4); uStart += 4; } break; case 8: for (s=0; s<symbolCount; ++s) { U64 const D4 = HUF_DEltX1_set4(wksp->symbols[symbol + s], nbBits); MEM_write64(dt + uStart, D4); MEM_write64(dt + uStart + 4, D4); uStart += 8; } break; default: for (s=0; s<symbolCount; ++s) { U64 const D4 = HUF_DEltX1_set4(wksp->symbols[symbol + s], nbBits); for (u=0; u < length; u += 16) { MEM_write64(dt + uStart + u + 0, D4); MEM_write64(dt + uStart + u + 4, D4); MEM_write64(dt + uStart + u + 8, D4); MEM_write64(dt + uStart + u + 12, D4); } assert(u == length); uStart += length; } break; } symbol += symbolCount; rankStart += symbolCount * length; } } return iSize; } FORCE_INLINE_TEMPLATE BYTE HUF_decodeSymbolX1(BIT_DStream_t* Dstream, const HUF_DEltX1* dt, const U32 dtLog) { size_t const val = BIT_lookBitsFast(Dstream, dtLog); /* note : dtLog >= 1 */ BYTE const c = dt[val].byte; BIT_skipBits(Dstream, dt[val].nbBits); return c; } #define HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr) \ do { *ptr++ = HUF_decodeSymbolX1(DStreamPtr, dt, dtLog); } while (0) #define HUF_DECODE_SYMBOLX1_1(ptr, DStreamPtr) \ do { \ if (MEM_64bits() || (HUF_TABLELOG_MAX<=12)) \ HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr); \ } while (0) #define HUF_DECODE_SYMBOLX1_2(ptr, DStreamPtr) \ do { \ if (MEM_64bits()) \ HUF_DECODE_SYMBOLX1_0(ptr, DStreamPtr); \ } while (0) HINT_INLINE size_t HUF_decodeStreamX1(BYTE* p, BIT_DStream_t* const bitDPtr, BYTE* const pEnd, const HUF_DEltX1* const dt, const U32 dtLog) { BYTE* const pStart = p; /* up to 4 symbols at a time */ if ((pEnd - p) > 3) { while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd-3)) { HUF_DECODE_SYMBOLX1_2(p, bitDPtr); HUF_DECODE_SYMBOLX1_1(p, bitDPtr); HUF_DECODE_SYMBOLX1_2(p, bitDPtr); HUF_DECODE_SYMBOLX1_0(p, bitDPtr); } } else { BIT_reloadDStream(bitDPtr); } /* [0-3] symbols remaining */ if (MEM_32bits()) while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd)) HUF_DECODE_SYMBOLX1_0(p, bitDPtr); /* no more data to retrieve from bitstream, no need to reload */ while (p < pEnd) HUF_DECODE_SYMBOLX1_0(p, bitDPtr); return (size_t)(pEnd-pStart); } FORCE_INLINE_TEMPLATE size_t HUF_decompress1X1_usingDTable_internal_body( void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable) { BYTE* op = (BYTE*)dst; BYTE* const oend = ZSTD_maybeNullPtrAdd(op, dstSize); const void* dtPtr = DTable + 1; const HUF_DEltX1* const dt = (const HUF_DEltX1*)dtPtr; BIT_DStream_t bitD; DTableDesc const dtd = HUF_getDTableDesc(DTable); U32 const dtLog = dtd.tableLog; CHECK_F( BIT_initDStream(&bitD, cSrc, cSrcSize) ); HUF_decodeStreamX1(op, &bitD, oend, dt, dtLog); if (!BIT_endOfDStream(&bitD)) return ERROR(corruption_detected); return dstSize; } /* HUF_decompress4X1_usingDTable_internal_body(): * Conditions : * @dstSize >= 6 */ FORCE_INLINE_TEMPLATE size_t HUF_decompress4X1_usingDTable_internal_body( void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable) { /* Check */ if (cSrcSize < 10) return ERROR(corruption_detected); /* strict minimum : jump table + 1 byte per stream */ if (dstSize < 6) return ERROR(corruption_detected); /* stream 4-split doesn't work */ { const BYTE* const istart = (const BYTE*) cSrc; BYTE* const ostart = (BYTE*) dst; BYTE* const oend = ostart + dstSize; BYTE* const olimit = oend - 3; const void* const dtPtr = DTable + 1; const HUF_DEltX1* const dt = (const HUF_DEltX1*)dtPtr; /* Init */ BIT_DStream_t bitD1; BIT_DStream_t bitD2; BIT_DStream_t bitD3; BIT_DStream_t bitD4; size_t const length1 = MEM_readLE16(istart); size_t const length2 = MEM_readLE16(istart+2); size_t const length3 = MEM_readLE16(istart+4); size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6); const BYTE* const istart1 = istart + 6; /* jumpTable */ const BYTE* const istart2 = istart1 + length1; const BYTE* const istart3 = istart2 + length2; const BYTE* const istart4 = istart3 + length3; const size_t segmentSize = (dstSize+3) / 4; BYTE* const opStart2 = ostart + segmentSize; BYTE* const opStart3 = opStart2 + segmentSize; BYTE* const opStart4 = opStart3 + segmentSize; BYTE* op1 = ostart; BYTE* op2 = opStart2; BYTE* op3 = opStart3; BYTE* op4 = opStart4; DTableDesc const dtd = HUF_getDTableDesc(DTable); U32 const dtLog = dtd.tableLog; U32 endSignal = 1; if (length4 > cSrcSize) return ERROR(corruption_detected); /* overflow */ if (opStart4 > oend) return ERROR(corruption_detected); /* overflow */ assert(dstSize >= 6); /* validated above */ CHECK_F( BIT_initDStream(&bitD1, istart1, length1) ); CHECK_F( BIT_initDStream(&bitD2, istart2, length2) ); CHECK_F( BIT_initDStream(&bitD3, istart3, length3) ); CHECK_F( BIT_initDStream(&bitD4, istart4, length4) ); /* up to 16 symbols per loop (4 symbols per stream) in 64-bit mode */ if ((size_t)(oend - op4) >= sizeof(size_t)) { for ( ; (endSignal) & (op4 < olimit) ; ) { HUF_DECODE_SYMBOLX1_2(op1, &bitD1); HUF_DECODE_SYMBOLX1_2(op2, &bitD2); HUF_DECODE_SYMBOLX1_2(op3, &bitD3); HUF_DECODE_SYMBOLX1_2(op4, &bitD4); HUF_DECODE_SYMBOLX1_1(op1, &bitD1); HUF_DECODE_SYMBOLX1_1(op2, &bitD2); HUF_DECODE_SYMBOLX1_1(op3, &bitD3); HUF_DECODE_SYMBOLX1_1(op4, &bitD4); HUF_DECODE_SYMBOLX1_2(op1, &bitD1); HUF_DECODE_SYMBOLX1_2(op2, &bitD2); HUF_DECODE_SYMBOLX1_2(op3, &bitD3); HUF_DECODE_SYMBOLX1_2(op4, &bitD4); HUF_DECODE_SYMBOLX1_0(op1, &bitD1); HUF_DECODE_SYMBOLX1_0(op2, &bitD2); HUF_DECODE_SYMBOLX1_0(op3, &bitD3); HUF_DECODE_SYMBOLX1_0(op4, &bitD4); endSignal &= BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished; endSignal &= BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished; endSignal &= BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished; endSignal &= BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished; } } /* check corruption */ /* note : should not be necessary : op# advance in lock step, and we control op4. * but curiously, binary generated by gcc 7.2 & 7.3 with -mbmi2 runs faster when >=1 test is present */ if (op1 > opStart2) return ERROR(corruption_detected); if (op2 > opStart3) return ERROR(corruption_detected); if (op3 > opStart4) return ERROR(corruption_detected); /* note : op4 supposed already verified within main loop */ /* finish bitStreams one by one */ HUF_decodeStreamX1(op1, &bitD1, opStart2, dt, dtLog); HUF_decodeStreamX1(op2, &bitD2, opStart3, dt, dtLog); HUF_decodeStreamX1(op3, &bitD3, opStart4, dt, dtLog); HUF_decodeStreamX1(op4, &bitD4, oend, dt, dtLog); /* check */ { U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4); if (!endCheck) return ERROR(corruption_detected); } /* decoded size */ return dstSize; } } #if HUF_NEED_BMI2_FUNCTION static BMI2_TARGET_ATTRIBUTE size_t HUF_decompress4X1_usingDTable_internal_bmi2(void* dst, size_t dstSize, void const* cSrc, size_t cSrcSize, HUF_DTable const* DTable) { return HUF_decompress4X1_usingDTable_internal_body(dst, dstSize, cSrc, cSrcSize, DTable); } #endif static size_t HUF_decompress4X1_usingDTable_internal_default(void* dst, size_t dstSize, void const* cSrc, size_t cSrcSize, HUF_DTable const* DTable) { return HUF_decompress4X1_usingDTable_internal_body(dst, dstSize, cSrc, cSrcSize, DTable); } #if ZSTD_ENABLE_ASM_X86_64_BMI2 HUF_ASM_DECL void HUF_decompress4X1_usingDTable_internal_fast_asm_loop(HUF_DecompressFastArgs* args) ZSTDLIB_HIDDEN; #endif static HUF_FAST_BMI2_ATTRS void HUF_decompress4X1_usingDTable_internal_fast_c_loop(HUF_DecompressFastArgs* args) { U64 bits[4]; BYTE const* ip[4]; BYTE* op[4]; U16 const* const dtable = (U16 const*)args->dt; BYTE* const oend = args->oend; BYTE const* const ilowest = args->ilowest; /* Copy the arguments to local variables */ ZSTD_memcpy(&bits, &args->bits, sizeof(bits)); ZSTD_memcpy((void*)(&ip), &args->ip, sizeof(ip)); ZSTD_memcpy(&op, &args->op, sizeof(op)); assert(MEM_isLittleEndian()); assert(!MEM_32bits()); for (;;) { BYTE* olimit; int stream; /* Assert loop preconditions */ #ifndef NDEBUG for (stream = 0; stream < 4; ++stream) { assert(op[stream] <= (stream == 3 ? oend : op[stream + 1])); assert(ip[stream] >= ilowest); } #endif /* Compute olimit */ { /* Each iteration produces 5 output symbols per stream */ size_t const oiters = (size_t)(oend - op[3]) / 5; /* Each iteration consumes up to 11 bits * 5 = 55 bits < 7 bytes * per stream. */ size_t const iiters = (size_t)(ip[0] - ilowest) / 7; /* We can safely run iters iterations before running bounds checks */ size_t const iters = MIN(oiters, iiters); size_t const symbols = iters * 5; /* We can simply check that op[3] < olimit, instead of checking all * of our bounds, since we can't hit the other bounds until we've run * iters iterations, which only happens when op[3] == olimit. */ olimit = op[3] + symbols; /* Exit fast decoding loop once we reach the end. */ if (op[3] == olimit) break; /* Exit the decoding loop if any input pointer has crossed the * previous one. This indicates corruption, and a precondition * to our loop is that ip[i] >= ip[0]. */ for (stream = 1; stream < 4; ++stream) { if (ip[stream] < ip[stream - 1]) goto _out; } } #ifndef NDEBUG for (stream = 1; stream < 4; ++stream) { assert(ip[stream] >= ip[stream - 1]); } #endif #define HUF_4X1_DECODE_SYMBOL(_stream, _symbol) \ do { \ int const index = (int)(bits[(_stream)] >> 53); \ int const entry = (int)dtable[index]; \ bits[(_stream)] <<= (entry & 0x3F); \ op[(_stream)][(_symbol)] = (BYTE)((entry >> 8) & 0xFF); \ } while (0) #define HUF_4X1_RELOAD_STREAM(_stream) \ do { \ int const ctz = ZSTD_countTrailingZeros64(bits[(_stream)]); \ int const nbBits = ctz & 7; \ int const nbBytes = ctz >> 3; \ op[(_stream)] += 5; \ ip[(_stream)] -= nbBytes; \ bits[(_stream)] = MEM_read64(ip[(_stream)]) | 1; \ bits[(_stream)] <<= nbBits; \ } while (0) /* Manually unroll the loop because compilers don't consistently * unroll the inner loops, which destroys performance. */ do { /* Decode 5 symbols in each of the 4 streams */ HUF_4X_FOR_EACH_STREAM_WITH_VAR(HUF_4X1_DECODE_SYMBOL, 0); HUF_4X_FOR_EACH_STREAM_WITH_VAR(HUF_4X1_DECODE_SYMBOL, 1); HUF_4X_FOR_EACH_STREAM_WITH_VAR(HUF_4X1_DECODE_SYMBOL, 2); HUF_4X_FOR_EACH_STREAM_WITH_VAR(HUF_4X1_DECODE_SYMBOL, 3); HUF_4X_FOR_EACH_STREAM_WITH_VAR(HUF_4X1_DECODE_SYMBOL, 4); /* Reload each of the 4 the bitstreams */ HUF_4X_FOR_EACH_STREAM(HUF_4X1_RELOAD_STREAM); } while (op[3] < olimit); #undef HUF_4X1_DECODE_SYMBOL #undef HUF_4X1_RELOAD_STREAM } _out: /* Save the final values of each of the state variables back to args. */ ZSTD_memcpy(&args->bits, &bits, sizeof(bits)); ZSTD_memcpy((void*)(&args->ip), &ip, sizeof(ip)); ZSTD_memcpy(&args->op, &op, sizeof(op)); } /* * @returns @p dstSize on success (>= 6) * 0 if the fallback implementation should be used * An error if an error occurred */ static HUF_FAST_BMI2_ATTRS size_t HUF_decompress4X1_usingDTable_internal_fast( void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, HUF_DecompressFastLoopFn loopFn) { void const* dt = DTable + 1; BYTE const* const ilowest = (BYTE const*)cSrc; BYTE* const oend = ZSTD_maybeNullPtrAdd((BYTE*)dst, dstSize); HUF_DecompressFastArgs args; { size_t const ret = HUF_DecompressFastArgs_init(&args, dst, dstSize, cSrc, cSrcSize, DTable); FORWARD_IF_ERROR(ret, "Failed to init fast loop args"); if (ret == 0) return 0; } assert(args.ip[0] >= args.ilowest); loopFn(&args); /* Our loop guarantees that ip[] >= ilowest and that we haven't * overwritten any op[]. */ assert(args.ip[0] >= ilowest); assert(args.ip[0] >= ilowest); assert(args.ip[1] >= ilowest); assert(args.ip[2] >= ilowest); assert(args.ip[3] >= ilowest); assert(args.op[3] <= oend); assert(ilowest == args.ilowest); assert(ilowest + 6 == args.iend[0]); (void)ilowest; /* finish bit streams one by one. */ { size_t const segmentSize = (dstSize+3) / 4; BYTE* segmentEnd = (BYTE*)dst; int i; for (i = 0; i < 4; ++i) { BIT_DStream_t bit; if (segmentSize <= (size_t)(oend - segmentEnd)) segmentEnd += segmentSize; else segmentEnd = oend; FORWARD_IF_ERROR(HUF_initRemainingDStream(&bit, &args, i, segmentEnd), "corruption"); /* Decompress and validate that we've produced exactly the expected length. */ args.op[i] += HUF_decodeStreamX1(args.op[i], &bit, segmentEnd, (HUF_DEltX1 const*)dt, HUF_DECODER_FAST_TABLELOG); if (args.op[i] != segmentEnd) return ERROR(corruption_detected); } } /* decoded size */ assert(dstSize != 0); return dstSize; } HUF_DGEN(HUF_decompress1X1_usingDTable_internal) static size_t HUF_decompress4X1_usingDTable_internal(void* dst, size_t dstSize, void const* cSrc, size_t cSrcSize, HUF_DTable const* DTable, int flags) { HUF_DecompressUsingDTableFn fallbackFn = HUF_decompress4X1_usingDTable_internal_default; HUF_DecompressFastLoopFn loopFn = HUF_decompress4X1_usingDTable_internal_fast_c_loop; #if DYNAMIC_BMI2 if (flags & HUF_flags_bmi2) { fallbackFn = HUF_decompress4X1_usingDTable_internal_bmi2; # if ZSTD_ENABLE_ASM_X86_64_BMI2 if (!(flags & HUF_flags_disableAsm)) { loopFn = HUF_decompress4X1_usingDTable_internal_fast_asm_loop; } # endif } else { return fallbackFn(dst, dstSize, cSrc, cSrcSize, DTable); } #endif #if ZSTD_ENABLE_ASM_X86_64_BMI2 && defined(__BMI2__) if (!(flags & HUF_flags_disableAsm)) { loopFn = HUF_decompress4X1_usingDTable_internal_fast_asm_loop; } #endif if (HUF_ENABLE_FAST_DECODE && !(flags & HUF_flags_disableFast)) { size_t const ret = HUF_decompress4X1_usingDTable_internal_fast(dst, dstSize, cSrc, cSrcSize, DTable, loopFn); if (ret != 0) return ret; } return fallbackFn(dst, dstSize, cSrc, cSrcSize, DTable); } static size_t HUF_decompress4X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags) { const BYTE* ip = (const BYTE*) cSrc; size_t const hSize = HUF_readDTableX1_wksp(dctx, cSrc, cSrcSize, workSpace, wkspSize, flags); if (HUF_isError(hSize)) return hSize; if (hSize >= cSrcSize) return ERROR(srcSize_wrong); ip += hSize; cSrcSize -= hSize; return HUF_decompress4X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, flags); } #endif /* HUF_FORCE_DECOMPRESS_X2 */ #ifndef HUF_FORCE_DECOMPRESS_X1 /* *************************/ /* double-symbols decoding */ /* *************************/ typedef struct { U16 sequence; BYTE nbBits; BYTE length; } HUF_DEltX2; /* double-symbols decoding */ typedef struct { BYTE symbol; } sortedSymbol_t; typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1]; typedef rankValCol_t rankVal_t[HUF_TABLELOG_MAX]; /* * Constructs a HUF_DEltX2 in a U32. */ static U32 HUF_buildDEltX2U32(U32 symbol, U32 nbBits, U32 baseSeq, int level) { U32 seq; DEBUG_STATIC_ASSERT(offsetof(HUF_DEltX2, sequence) == 0); DEBUG_STATIC_ASSERT(offsetof(HUF_DEltX2, nbBits) == 2); DEBUG_STATIC_ASSERT(offsetof(HUF_DEltX2, length) == 3); DEBUG_STATIC_ASSERT(sizeof(HUF_DEltX2) == sizeof(U32)); if (MEM_isLittleEndian()) { seq = level == 1 ? symbol : (baseSeq + (symbol << 8)); return seq + (nbBits << 16) + ((U32)level << 24); } else { seq = level == 1 ? (symbol << 8) : ((baseSeq << 8) + symbol); return (seq << 16) + (nbBits << 8) + (U32)level; } } /* * Constructs a HUF_DEltX2. */ static HUF_DEltX2 HUF_buildDEltX2(U32 symbol, U32 nbBits, U32 baseSeq, int level) { HUF_DEltX2 DElt; U32 const val = HUF_buildDEltX2U32(symbol, nbBits, baseSeq, level); DEBUG_STATIC_ASSERT(sizeof(DElt) == sizeof(val)); ZSTD_memcpy(&DElt, &val, sizeof(val)); return DElt; } /* * Constructs 2 HUF_DEltX2s and packs them into a U64. */ static U64 HUF_buildDEltX2U64(U32 symbol, U32 nbBits, U16 baseSeq, int level) { U32 DElt = HUF_buildDEltX2U32(symbol, nbBits, baseSeq, level); return (U64)DElt + ((U64)DElt << 32); } /* * Fills the DTable rank with all the symbols from [begin, end) that are each * nbBits long. * * @param DTableRank The start of the rank in the DTable. * @param begin The first symbol to fill (inclusive). * @param end The last symbol to fill (exclusive). * @param nbBits Each symbol is nbBits long. * @param tableLog The table log. * @param baseSeq If level == 1 { 0 } else { the first level symbol } * @param level The level in the table. Must be 1 or 2. */ static void HUF_fillDTableX2ForWeight( HUF_DEltX2* DTableRank, sortedSymbol_t const* begin, sortedSymbol_t const* end, U32 nbBits, U32 tableLog, U16 baseSeq, int const level) { U32 const length = 1U << ((tableLog - nbBits) & 0x1F /* quiet static-analyzer */); const sortedSymbol_t* ptr; assert(level >= 1 && level <= 2); switch (length) { case 1: for (ptr = begin; ptr != end; ++ptr) { HUF_DEltX2 const DElt = HUF_buildDEltX2(ptr->symbol, nbBits, baseSeq, level); *DTableRank++ = DElt; } break; case 2: for (ptr = begin; ptr != end; ++ptr) { HUF_DEltX2 const DElt = HUF_buildDEltX2(ptr->symbol, nbBits, baseSeq, level); DTableRank[0] = DElt; DTableRank[1] = DElt; DTableRank += 2; } break; case 4: for (ptr = begin; ptr != end; ++ptr) { U64 const DEltX2 = HUF_buildDEltX2U64(ptr->symbol, nbBits, baseSeq, level); ZSTD_memcpy(DTableRank + 0, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTableRank + 2, &DEltX2, sizeof(DEltX2)); DTableRank += 4; } break; case 8: for (ptr = begin; ptr != end; ++ptr) { U64 const DEltX2 = HUF_buildDEltX2U64(ptr->symbol, nbBits, baseSeq, level); ZSTD_memcpy(DTableRank + 0, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTableRank + 2, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTableRank + 4, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTableRank + 6, &DEltX2, sizeof(DEltX2)); DTableRank += 8; } break; default: for (ptr = begin; ptr != end; ++ptr) { U64 const DEltX2 = HUF_buildDEltX2U64(ptr->symbol, nbBits, baseSeq, level); HUF_DEltX2* const DTableRankEnd = DTableRank + length; for (; DTableRank != DTableRankEnd; DTableRank += 8) { ZSTD_memcpy(DTableRank + 0, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTableRank + 2, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTableRank + 4, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTableRank + 6, &DEltX2, sizeof(DEltX2)); } } break; } } /* HUF_fillDTableX2Level2() : * `rankValOrigin` must be a table of at least (HUF_TABLELOG_MAX + 1) U32 */ static void HUF_fillDTableX2Level2(HUF_DEltX2* DTable, U32 targetLog, const U32 consumedBits, const U32* rankVal, const int minWeight, const int maxWeight1, const sortedSymbol_t* sortedSymbols, U32 const* rankStart, U32 nbBitsBaseline, U16 baseSeq) { /* Fill skipped values (all positions up to rankVal[minWeight]). * These are positions only get a single symbol because the combined weight * is too large. */ if (minWeight>1) { U32 const length = 1U << ((targetLog - consumedBits) & 0x1F /* quiet static-analyzer */); U64 const DEltX2 = HUF_buildDEltX2U64(baseSeq, consumedBits, /* baseSeq */ 0, /* level */ 1); int const skipSize = rankVal[minWeight]; assert(length > 1); assert((U32)skipSize < length); switch (length) { case 2: assert(skipSize == 1); ZSTD_memcpy(DTable, &DEltX2, sizeof(DEltX2)); break; case 4: assert(skipSize <= 4); ZSTD_memcpy(DTable + 0, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTable + 2, &DEltX2, sizeof(DEltX2)); break; default: { int i; for (i = 0; i < skipSize; i += 8) { ZSTD_memcpy(DTable + i + 0, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTable + i + 2, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTable + i + 4, &DEltX2, sizeof(DEltX2)); ZSTD_memcpy(DTable + i + 6, &DEltX2, sizeof(DEltX2)); } } } } /* Fill each of the second level symbols by weight. */ { int w; for (w = minWeight; w < maxWeight1; ++w) { int const begin = rankStart[w]; int const end = rankStart[w+1]; U32 const nbBits = nbBitsBaseline - w; U32 const totalBits = nbBits + consumedBits; HUF_fillDTableX2ForWeight( DTable + rankVal[w], sortedSymbols + begin, sortedSymbols + end, totalBits, targetLog, baseSeq, /* level */ 2); } } } static void HUF_fillDTableX2(HUF_DEltX2* DTable, const U32 targetLog, const sortedSymbol_t* sortedList, const U32* rankStart, rankValCol_t* rankValOrigin, const U32 maxWeight, const U32 nbBitsBaseline) { U32* const rankVal = rankValOrigin[0]; const int scaleLog = nbBitsBaseline - targetLog; /* note : targetLog >= srcLog, hence scaleLog <= 1 */ const U32 minBits = nbBitsBaseline - maxWeight; int w; int const wEnd = (int)maxWeight + 1; /* Fill DTable in order of weight. */ for (w = 1; w < wEnd; ++w) { int const begin = (int)rankStart[w]; int const end = (int)rankStart[w+1]; U32 const nbBits = nbBitsBaseline - w; if (targetLog-nbBits >= minBits) { /* Enough room for a second symbol. */ int start = rankVal[w]; U32 const length = 1U << ((targetLog - nbBits) & 0x1F /* quiet static-analyzer */); int minWeight = nbBits + scaleLog; int s; if (minWeight < 1) minWeight = 1; /* Fill the DTable for every symbol of weight w. * These symbols get at least 1 second symbol. */ for (s = begin; s != end; ++s) { HUF_fillDTableX2Level2( DTable + start, targetLog, nbBits, rankValOrigin[nbBits], minWeight, wEnd, sortedList, rankStart, nbBitsBaseline, sortedList[s].symbol); start += length; } } else { /* Only a single symbol. */ HUF_fillDTableX2ForWeight( DTable + rankVal[w], sortedList + begin, sortedList + end, nbBits, targetLog, /* baseSeq */ 0, /* level */ 1); } } } typedef struct { rankValCol_t rankVal[HUF_TABLELOG_MAX]; U32 rankStats[HUF_TABLELOG_MAX + 1]; U32 rankStart0[HUF_TABLELOG_MAX + 3]; sortedSymbol_t sortedSymbol[HUF_SYMBOLVALUE_MAX + 1]; BYTE weightList[HUF_SYMBOLVALUE_MAX + 1]; U32 calleeWksp[HUF_READ_STATS_WORKSPACE_SIZE_U32]; } HUF_ReadDTableX2_Workspace; size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize, int flags) { U32 tableLog, maxW, nbSymbols; DTableDesc dtd = HUF_getDTableDesc(DTable); U32 maxTableLog = dtd.maxTableLog; size_t iSize; void* dtPtr = DTable+1; /* force compiler to avoid strict-aliasing */ HUF_DEltX2* const dt = (HUF_DEltX2*)dtPtr; U32 *rankStart; HUF_ReadDTableX2_Workspace* const wksp = (HUF_ReadDTableX2_Workspace*)workSpace; if (sizeof(*wksp) > wkspSize) return ERROR(GENERIC); rankStart = wksp->rankStart0 + 1; ZSTD_memset(wksp->rankStats, 0, sizeof(wksp->rankStats)); ZSTD_memset(wksp->rankStart0, 0, sizeof(wksp->rankStart0)); DEBUG_STATIC_ASSERT(sizeof(HUF_DEltX2) == sizeof(HUF_DTable)); /* if compiler fails here, assertion is wrong */ if (maxTableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge); /* ZSTD_memset(weightList, 0, sizeof(weightList)); */ /* is not necessary, even though some analyzer complain ... */ iSize = HUF_readStats_wksp(wksp->weightList, HUF_SYMBOLVALUE_MAX + 1, wksp->rankStats, &nbSymbols, &tableLog, src, srcSize, wksp->calleeWksp, sizeof(wksp->calleeWksp), flags); if (HUF_isError(iSize)) return iSize; /* check result */ if (tableLog > maxTableLog) return ERROR(tableLog_tooLarge); /* DTable can't fit code depth */ if (tableLog <= HUF_DECODER_FAST_TABLELOG && maxTableLog > HUF_DECODER_FAST_TABLELOG) maxTableLog = HUF_DECODER_FAST_TABLELOG; /* find maxWeight */ for (maxW = tableLog; wksp->rankStats[maxW]==0; maxW--) {} /* necessarily finds a solution before 0 */ /* Get start index of each weight */ { U32 w, nextRankStart = 0; for (w=1; w<maxW+1; w++) { U32 curr = nextRankStart; nextRankStart += wksp->rankStats[w]; rankStart[w] = curr; } rankStart[0] = nextRankStart; /* put all 0w symbols at the end of sorted list*/ rankStart[maxW+1] = nextRankStart; } /* sort symbols by weight */ { U32 s; for (s=0; s<nbSymbols; s++) { U32 const w = wksp->weightList[s]; U32 const r = rankStart[w]++; wksp->sortedSymbol[r].symbol = (BYTE)s; } rankStart[0] = 0; /* forget 0w symbols; this is beginning of weight(1) */ } /* Build rankVal */ { U32* const rankVal0 = wksp->rankVal[0]; { int const rescale = (maxTableLog-tableLog) - 1; /* tableLog <= maxTableLog */ U32 nextRankVal = 0; U32 w; for (w=1; w<maxW+1; w++) { U32 curr = nextRankVal; nextRankVal += wksp->rankStats[w] << (w+rescale); rankVal0[w] = curr; } } { U32 const minBits = tableLog+1 - maxW; U32 consumed; for (consumed = minBits; consumed < maxTableLog - minBits + 1; consumed++) { U32* const rankValPtr = wksp->rankVal[consumed]; U32 w; for (w = 1; w < maxW+1; w++) { rankValPtr[w] = rankVal0[w] >> consumed; } } } } HUF_fillDTableX2(dt, maxTableLog, wksp->sortedSymbol, wksp->rankStart0, wksp->rankVal, maxW, tableLog+1); dtd.tableLog = (BYTE)maxTableLog; dtd.tableType = 1; ZSTD_memcpy(DTable, &dtd, sizeof(dtd)); return iSize; } FORCE_INLINE_TEMPLATE U32 HUF_decodeSymbolX2(void* op, BIT_DStream_t* DStream, const HUF_DEltX2* dt, const U32 dtLog) { size_t const val = BIT_lookBitsFast(DStream, dtLog); /* note : dtLog >= 1 */ ZSTD_memcpy(op, &dt[val].sequence, 2); BIT_skipBits(DStream, dt[val].nbBits); return dt[val].length; } FORCE_INLINE_TEMPLATE U32 HUF_decodeLastSymbolX2(void* op, BIT_DStream_t* DStream, const HUF_DEltX2* dt, const U32 dtLog) { size_t const val = BIT_lookBitsFast(DStream, dtLog); /* note : dtLog >= 1 */ ZSTD_memcpy(op, &dt[val].sequence, 1); if (dt[val].length==1) { BIT_skipBits(DStream, dt[val].nbBits); } else { if (DStream->bitsConsumed < (sizeof(DStream->bitContainer)*8)) { BIT_skipBits(DStream, dt[val].nbBits); if (DStream->bitsConsumed > (sizeof(DStream->bitContainer)*8)) /* ugly hack; works only because it's the last symbol. Note : can't easily extract nbBits from just this symbol */ DStream->bitsConsumed = (sizeof(DStream->bitContainer)*8); } } return 1; } #define HUF_DECODE_SYMBOLX2_0(ptr, DStreamPtr) \ do { ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog); } while (0) #define HUF_DECODE_SYMBOLX2_1(ptr, DStreamPtr) \ do { \ if (MEM_64bits() || (HUF_TABLELOG_MAX<=12)) \ ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog); \ } while (0) #define HUF_DECODE_SYMBOLX2_2(ptr, DStreamPtr) \ do { \ if (MEM_64bits()) \ ptr += HUF_decodeSymbolX2(ptr, DStreamPtr, dt, dtLog); \ } while (0) HINT_INLINE size_t HUF_decodeStreamX2(BYTE* p, BIT_DStream_t* bitDPtr, BYTE* const pEnd, const HUF_DEltX2* const dt, const U32 dtLog) { BYTE* const pStart = p; /* up to 8 symbols at a time */ if ((size_t)(pEnd - p) >= sizeof(bitDPtr->bitContainer)) { if (dtLog <= 11 && MEM_64bits()) { /* up to 10 symbols at a time */ while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd-9)) { HUF_DECODE_SYMBOLX2_0(p, bitDPtr); HUF_DECODE_SYMBOLX2_0(p, bitDPtr); HUF_DECODE_SYMBOLX2_0(p, bitDPtr); HUF_DECODE_SYMBOLX2_0(p, bitDPtr); HUF_DECODE_SYMBOLX2_0(p, bitDPtr); } } else { /* up to 8 symbols at a time */ while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p < pEnd-(sizeof(bitDPtr->bitContainer)-1))) { HUF_DECODE_SYMBOLX2_2(p, bitDPtr); HUF_DECODE_SYMBOLX2_1(p, bitDPtr); HUF_DECODE_SYMBOLX2_2(p, bitDPtr); HUF_DECODE_SYMBOLX2_0(p, bitDPtr); } } } else { BIT_reloadDStream(bitDPtr); } /* closer to end : up to 2 symbols at a time */ if ((size_t)(pEnd - p) >= 2) { while ((BIT_reloadDStream(bitDPtr) == BIT_DStream_unfinished) & (p <= pEnd-2)) HUF_DECODE_SYMBOLX2_0(p, bitDPtr); while (p <= pEnd-2) HUF_DECODE_SYMBOLX2_0(p, bitDPtr); /* no need to reload : reached the end of DStream */ } if (p < pEnd) p += HUF_decodeLastSymbolX2(p, bitDPtr, dt, dtLog); return p-pStart; } FORCE_INLINE_TEMPLATE size_t HUF_decompress1X2_usingDTable_internal_body( void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable) { BIT_DStream_t bitD; /* Init */ CHECK_F( BIT_initDStream(&bitD, cSrc, cSrcSize) ); /* decode */ { BYTE* const ostart = (BYTE*) dst; BYTE* const oend = ZSTD_maybeNullPtrAdd(ostart, dstSize); const void* const dtPtr = DTable+1; /* force compiler to not use strict-aliasing */ const HUF_DEltX2* const dt = (const HUF_DEltX2*)dtPtr; DTableDesc const dtd = HUF_getDTableDesc(DTable); HUF_decodeStreamX2(ostart, &bitD, oend, dt, dtd.tableLog); } /* check */ if (!BIT_endOfDStream(&bitD)) return ERROR(corruption_detected); /* decoded size */ return dstSize; } /* HUF_decompress4X2_usingDTable_internal_body(): * Conditions: * @dstSize >= 6 */ FORCE_INLINE_TEMPLATE size_t HUF_decompress4X2_usingDTable_internal_body( void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable) { if (cSrcSize < 10) return ERROR(corruption_detected); /* strict minimum : jump table + 1 byte per stream */ if (dstSize < 6) return ERROR(corruption_detected); /* stream 4-split doesn't work */ { const BYTE* const istart = (const BYTE*) cSrc; BYTE* const ostart = (BYTE*) dst; BYTE* const oend = ostart + dstSize; BYTE* const olimit = oend - (sizeof(size_t)-1); const void* const dtPtr = DTable+1; const HUF_DEltX2* const dt = (const HUF_DEltX2*)dtPtr; /* Init */ BIT_DStream_t bitD1; BIT_DStream_t bitD2; BIT_DStream_t bitD3; BIT_DStream_t bitD4; size_t const length1 = MEM_readLE16(istart); size_t const length2 = MEM_readLE16(istart+2); size_t const length3 = MEM_readLE16(istart+4); size_t const length4 = cSrcSize - (length1 + length2 + length3 + 6); const BYTE* const istart1 = istart + 6; /* jumpTable */ const BYTE* const istart2 = istart1 + length1; const BYTE* const istart3 = istart2 + length2; const BYTE* const istart4 = istart3 + length3; size_t const segmentSize = (dstSize+3) / 4; BYTE* const opStart2 = ostart + segmentSize; BYTE* const opStart3 = opStart2 + segmentSize; BYTE* const opStart4 = opStart3 + segmentSize; BYTE* op1 = ostart; BYTE* op2 = opStart2; BYTE* op3 = opStart3; BYTE* op4 = opStart4; U32 endSignal = 1; DTableDesc const dtd = HUF_getDTableDesc(DTable); U32 const dtLog = dtd.tableLog; if (length4 > cSrcSize) return ERROR(corruption_detected); /* overflow */ if (opStart4 > oend) return ERROR(corruption_detected); /* overflow */ assert(dstSize >= 6 /* validated above */); CHECK_F( BIT_initDStream(&bitD1, istart1, length1) ); CHECK_F( BIT_initDStream(&bitD2, istart2, length2) ); CHECK_F( BIT_initDStream(&bitD3, istart3, length3) ); CHECK_F( BIT_initDStream(&bitD4, istart4, length4) ); /* 16-32 symbols per loop (4-8 symbols per stream) */ if ((size_t)(oend - op4) >= sizeof(size_t)) { for ( ; (endSignal) & (op4 < olimit); ) { #if defined(__clang__) && (defined(__x86_64__) || defined(__i386__)) HUF_DECODE_SYMBOLX2_2(op1, &bitD1); HUF_DECODE_SYMBOLX2_1(op1, &bitD1); HUF_DECODE_SYMBOLX2_2(op1, &bitD1); HUF_DECODE_SYMBOLX2_0(op1, &bitD1); HUF_DECODE_SYMBOLX2_2(op2, &bitD2); HUF_DECODE_SYMBOLX2_1(op2, &bitD2); HUF_DECODE_SYMBOLX2_2(op2, &bitD2); HUF_DECODE_SYMBOLX2_0(op2, &bitD2); endSignal &= BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished; endSignal &= BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished; HUF_DECODE_SYMBOLX2_2(op3, &bitD3); HUF_DECODE_SYMBOLX2_1(op3, &bitD3); HUF_DECODE_SYMBOLX2_2(op3, &bitD3); HUF_DECODE_SYMBOLX2_0(op3, &bitD3); HUF_DECODE_SYMBOLX2_2(op4, &bitD4); HUF_DECODE_SYMBOLX2_1(op4, &bitD4); HUF_DECODE_SYMBOLX2_2(op4, &bitD4); HUF_DECODE_SYMBOLX2_0(op4, &bitD4); endSignal &= BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished; endSignal &= BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished; #else HUF_DECODE_SYMBOLX2_2(op1, &bitD1); HUF_DECODE_SYMBOLX2_2(op2, &bitD2); HUF_DECODE_SYMBOLX2_2(op3, &bitD3); HUF_DECODE_SYMBOLX2_2(op4, &bitD4); HUF_DECODE_SYMBOLX2_1(op1, &bitD1); HUF_DECODE_SYMBOLX2_1(op2, &bitD2); HUF_DECODE_SYMBOLX2_1(op3, &bitD3); HUF_DECODE_SYMBOLX2_1(op4, &bitD4); HUF_DECODE_SYMBOLX2_2(op1, &bitD1); HUF_DECODE_SYMBOLX2_2(op2, &bitD2); HUF_DECODE_SYMBOLX2_2(op3, &bitD3); HUF_DECODE_SYMBOLX2_2(op4, &bitD4); HUF_DECODE_SYMBOLX2_0(op1, &bitD1); HUF_DECODE_SYMBOLX2_0(op2, &bitD2); HUF_DECODE_SYMBOLX2_0(op3, &bitD3); HUF_DECODE_SYMBOLX2_0(op4, &bitD4); endSignal = (U32)LIKELY((U32) (BIT_reloadDStreamFast(&bitD1) == BIT_DStream_unfinished) & (BIT_reloadDStreamFast(&bitD2) == BIT_DStream_unfinished) & (BIT_reloadDStreamFast(&bitD3) == BIT_DStream_unfinished) & (BIT_reloadDStreamFast(&bitD4) == BIT_DStream_unfinished)); #endif } } /* check corruption */ if (op1 > opStart2) return ERROR(corruption_detected); if (op2 > opStart3) return ERROR(corruption_detected); if (op3 > opStart4) return ERROR(corruption_detected); /* note : op4 already verified within main loop */ /* finish bitStreams one by one */ HUF_decodeStreamX2(op1, &bitD1, opStart2, dt, dtLog); HUF_decodeStreamX2(op2, &bitD2, opStart3, dt, dtLog); HUF_decodeStreamX2(op3, &bitD3, opStart4, dt, dtLog); HUF_decodeStreamX2(op4, &bitD4, oend, dt, dtLog); /* check */ { U32 const endCheck = BIT_endOfDStream(&bitD1) & BIT_endOfDStream(&bitD2) & BIT_endOfDStream(&bitD3) & BIT_endOfDStream(&bitD4); if (!endCheck) return ERROR(corruption_detected); } /* decoded size */ return dstSize; } } #if HUF_NEED_BMI2_FUNCTION static BMI2_TARGET_ATTRIBUTE size_t HUF_decompress4X2_usingDTable_internal_bmi2(void* dst, size_t dstSize, void const* cSrc, size_t cSrcSize, HUF_DTable const* DTable) { return HUF_decompress4X2_usingDTable_internal_body(dst, dstSize, cSrc, cSrcSize, DTable); } #endif static size_t HUF_decompress4X2_usingDTable_internal_default(void* dst, size_t dstSize, void const* cSrc, size_t cSrcSize, HUF_DTable const* DTable) { return HUF_decompress4X2_usingDTable_internal_body(dst, dstSize, cSrc, cSrcSize, DTable); } #if ZSTD_ENABLE_ASM_X86_64_BMI2 HUF_ASM_DECL void HUF_decompress4X2_usingDTable_internal_fast_asm_loop(HUF_DecompressFastArgs* args) ZSTDLIB_HIDDEN; #endif static HUF_FAST_BMI2_ATTRS void HUF_decompress4X2_usingDTable_internal_fast_c_loop(HUF_DecompressFastArgs* args) { U64 bits[4]; BYTE const* ip[4]; BYTE* op[4]; BYTE* oend[4]; HUF_DEltX2 const* const dtable = (HUF_DEltX2 const*)args->dt; BYTE const* const ilowest = args->ilowest; /* Copy the arguments to local registers. */ ZSTD_memcpy(&bits, &args->bits, sizeof(bits)); ZSTD_memcpy((void*)(&ip), &args->ip, sizeof(ip)); ZSTD_memcpy(&op, &args->op, sizeof(op)); oend[0] = op[1]; oend[1] = op[2]; oend[2] = op[3]; oend[3] = args->oend; assert(MEM_isLittleEndian()); assert(!MEM_32bits()); for (;;) { BYTE* olimit; int stream; /* Assert loop preconditions */ #ifndef NDEBUG for (stream = 0; stream < 4; ++stream) { assert(op[stream] <= oend[stream]); assert(ip[stream] >= ilowest); } #endif /* Compute olimit */ { /* Each loop does 5 table lookups for each of the 4 streams. * Each table lookup consumes up to 11 bits of input, and produces * up to 2 bytes of output. */ /* We can consume up to 7 bytes of input per iteration per stream. * We also know that each input pointer is >= ip[0]. So we can run * iters loops before running out of input. */ size_t iters = (size_t)(ip[0] - ilowest) / 7; /* Each iteration can produce up to 10 bytes of output per stream. * Each output stream my advance at different rates. So take the * minimum number of safe iterations among all the output streams. */ for (stream = 0; stream < 4; ++stream) { size_t const oiters = (size_t)(oend[stream] - op[stream]) / 10; iters = MIN(iters, oiters); } /* Each iteration produces at least 5 output symbols. So until * op[3] crosses olimit, we know we haven't executed iters * iterations yet. This saves us maintaining an iters counter, * at the expense of computing the remaining # of iterations * more frequently. */ olimit = op[3] + (iters * 5); /* Exit the fast decoding loop once we reach the end. */ if (op[3] == olimit) break; /* Exit the decoding loop if any input pointer has crossed the * previous one. This indicates corruption, and a precondition * to our loop is that ip[i] >= ip[0]. */ for (stream = 1; stream < 4; ++stream) { if (ip[stream] < ip[stream - 1]) goto _out; } } #ifndef NDEBUG for (stream = 1; stream < 4; ++stream) { assert(ip[stream] >= ip[stream - 1]); } #endif #define HUF_4X2_DECODE_SYMBOL(_stream, _decode3) \ do { \ if ((_decode3) || (_stream) != 3) { \ int const index = (int)(bits[(_stream)] >> 53); \ HUF_DEltX2 const entry = dtable[index]; \ MEM_write16(op[(_stream)], entry.sequence); \ bits[(_stream)] <<= (entry.nbBits) & 0x3F; \ op[(_stream)] += (entry.length); \ } \ } while (0) #define HUF_4X2_RELOAD_STREAM(_stream) \ do { \ HUF_4X2_DECODE_SYMBOL(3, 1); \ { \ int const ctz = ZSTD_countTrailingZeros64(bits[(_stream)]); \ int const nbBits = ctz & 7; \ int const nbBytes = ctz >> 3; \ ip[(_stream)] -= nbBytes; \ bits[(_stream)] = MEM_read64(ip[(_stream)]) | 1; \ bits[(_stream)] <<= nbBits; \ } \ } while (0) /* Manually unroll the loop because compilers don't consistently * unroll the inner loops, which destroys performance. */ do { /* Decode 5 symbols from each of the first 3 streams. * The final stream will be decoded during the reload phase * to reduce register pressure. */ HUF_4X_FOR_EACH_STREAM_WITH_VAR(HUF_4X2_DECODE_SYMBOL, 0); HUF_4X_FOR_EACH_STREAM_WITH_VAR(HUF_4X2_DECODE_SYMBOL, 0); HUF_4X_FOR_EACH_STREAM_WITH_VAR(HUF_4X2_DECODE_SYMBOL, 0); HUF_4X_FOR_EACH_STREAM_WITH_VAR(HUF_4X2_DECODE_SYMBOL, 0); HUF_4X_FOR_EACH_STREAM_WITH_VAR(HUF_4X2_DECODE_SYMBOL, 0); /* Decode one symbol from the final stream */ HUF_4X2_DECODE_SYMBOL(3, 1); /* Decode 4 symbols from the final stream & reload bitstreams. * The final stream is reloaded last, meaning that all 5 symbols * are decoded from the final stream before it is reloaded. */ HUF_4X_FOR_EACH_STREAM(HUF_4X2_RELOAD_STREAM); } while (op[3] < olimit); } #undef HUF_4X2_DECODE_SYMBOL #undef HUF_4X2_RELOAD_STREAM _out: /* Save the final values of each of the state variables back to args. */ ZSTD_memcpy(&args->bits, &bits, sizeof(bits)); ZSTD_memcpy((void*)(&args->ip), &ip, sizeof(ip)); ZSTD_memcpy(&args->op, &op, sizeof(op)); } static HUF_FAST_BMI2_ATTRS size_t HUF_decompress4X2_usingDTable_internal_fast( void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, HUF_DecompressFastLoopFn loopFn) { void const* dt = DTable + 1; const BYTE* const ilowest = (const BYTE*)cSrc; BYTE* const oend = ZSTD_maybeNullPtrAdd((BYTE*)dst, dstSize); HUF_DecompressFastArgs args; { size_t const ret = HUF_DecompressFastArgs_init(&args, dst, dstSize, cSrc, cSrcSize, DTable); FORWARD_IF_ERROR(ret, "Failed to init asm args"); if (ret == 0) return 0; } assert(args.ip[0] >= args.ilowest); loopFn(&args); /* note : op4 already verified within main loop */ assert(args.ip[0] >= ilowest); assert(args.ip[1] >= ilowest); assert(args.ip[2] >= ilowest); assert(args.ip[3] >= ilowest); assert(args.op[3] <= oend); assert(ilowest == args.ilowest); assert(ilowest + 6 == args.iend[0]); (void)ilowest; /* finish bitStreams one by one */ { size_t const segmentSize = (dstSize+3) / 4; BYTE* segmentEnd = (BYTE*)dst; int i; for (i = 0; i < 4; ++i) { BIT_DStream_t bit; if (segmentSize <= (size_t)(oend - segmentEnd)) segmentEnd += segmentSize; else segmentEnd = oend; FORWARD_IF_ERROR(HUF_initRemainingDStream(&bit, &args, i, segmentEnd), "corruption"); args.op[i] += HUF_decodeStreamX2(args.op[i], &bit, segmentEnd, (HUF_DEltX2 const*)dt, HUF_DECODER_FAST_TABLELOG); if (args.op[i] != segmentEnd) return ERROR(corruption_detected); } } /* decoded size */ return dstSize; } static size_t HUF_decompress4X2_usingDTable_internal(void* dst, size_t dstSize, void const* cSrc, size_t cSrcSize, HUF_DTable const* DTable, int flags) { HUF_DecompressUsingDTableFn fallbackFn = HUF_decompress4X2_usingDTable_internal_default; HUF_DecompressFastLoopFn loopFn = HUF_decompress4X2_usingDTable_internal_fast_c_loop; #if DYNAMIC_BMI2 if (flags & HUF_flags_bmi2) { fallbackFn = HUF_decompress4X2_usingDTable_internal_bmi2; # if ZSTD_ENABLE_ASM_X86_64_BMI2 if (!(flags & HUF_flags_disableAsm)) { loopFn = HUF_decompress4X2_usingDTable_internal_fast_asm_loop; } # endif } else { return fallbackFn(dst, dstSize, cSrc, cSrcSize, DTable); } #endif #if ZSTD_ENABLE_ASM_X86_64_BMI2 && defined(__BMI2__) if (!(flags & HUF_flags_disableAsm)) { loopFn = HUF_decompress4X2_usingDTable_internal_fast_asm_loop; } #endif if (HUF_ENABLE_FAST_DECODE && !(flags & HUF_flags_disableFast)) { size_t const ret = HUF_decompress4X2_usingDTable_internal_fast(dst, dstSize, cSrc, cSrcSize, DTable, loopFn); if (ret != 0) return ret; } return fallbackFn(dst, dstSize, cSrc, cSrcSize, DTable); } HUF_DGEN(HUF_decompress1X2_usingDTable_internal) size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags) { const BYTE* ip = (const BYTE*) cSrc; size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize, workSpace, wkspSize, flags); if (HUF_isError(hSize)) return hSize; if (hSize >= cSrcSize) return ERROR(srcSize_wrong); ip += hSize; cSrcSize -= hSize; return HUF_decompress1X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, DCtx, flags); } static size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags) { const BYTE* ip = (const BYTE*) cSrc; size_t hSize = HUF_readDTableX2_wksp(dctx, cSrc, cSrcSize, workSpace, wkspSize, flags); if (HUF_isError(hSize)) return hSize; if (hSize >= cSrcSize) return ERROR(srcSize_wrong); ip += hSize; cSrcSize -= hSize; return HUF_decompress4X2_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, flags); } #endif /* HUF_FORCE_DECOMPRESS_X1 */ /* ***********************************/ /* Universal decompression selectors */ /* ***********************************/ #if !defined(HUF_FORCE_DECOMPRESS_X1) && !defined(HUF_FORCE_DECOMPRESS_X2) typedef struct { U32 tableTime; U32 decode256Time; } algo_time_t; static const algo_time_t algoTime[16 /* Quantization */][2 /* single, double */] = { /* single, double, quad */ {{0,0}, {1,1}}, /* Q==0 : impossible */ {{0,0}, {1,1}}, /* Q==1 : impossible */ {{ 150,216}, { 381,119}}, /* Q == 2 : 12-18% */ {{ 170,205}, { 514,112}}, /* Q == 3 : 18-25% */ {{ 177,199}, { 539,110}}, /* Q == 4 : 25-32% */ {{ 197,194}, { 644,107}}, /* Q == 5 : 32-38% */ {{ 221,192}, { 735,107}}, /* Q == 6 : 38-44% */ {{ 256,189}, { 881,106}}, /* Q == 7 : 44-50% */ {{ 359,188}, {1167,109}}, /* Q == 8 : 50-56% */ {{ 582,187}, {1570,114}}, /* Q == 9 : 56-62% */ {{ 688,187}, {1712,122}}, /* Q ==10 : 62-69% */ {{ 825,186}, {1965,136}}, /* Q ==11 : 69-75% */ {{ 976,185}, {2131,150}}, /* Q ==12 : 75-81% */ {{1180,186}, {2070,175}}, /* Q ==13 : 81-87% */ {{1377,185}, {1731,202}}, /* Q ==14 : 87-93% */ {{1412,185}, {1695,202}}, /* Q ==15 : 93-99% */ }; #endif /* HUF_selectDecoder() : * Tells which decoder is likely to decode faster, * based on a set of pre-computed metrics. * @return : 0==HUF_decompress4X1, 1==HUF_decompress4X2 . * Assumption : 0 < dstSize <= 128 KB */ U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize) { assert(dstSize > 0); assert(dstSize <= 128*1024); #if defined(HUF_FORCE_DECOMPRESS_X1) (void)dstSize; (void)cSrcSize; return 0; #elif defined(HUF_FORCE_DECOMPRESS_X2) (void)dstSize; (void)cSrcSize; return 1; #else /* decoder timing evaluation */ { U32 const Q = (cSrcSize >= dstSize) ? 15 : (U32)(cSrcSize * 16 / dstSize); /* Q < 16 */ U32 const D256 = (U32)(dstSize >> 8); U32 const DTime0 = algoTime[Q][0].tableTime + (algoTime[Q][0].decode256Time * D256); U32 DTime1 = algoTime[Q][1].tableTime + (algoTime[Q][1].decode256Time * D256); DTime1 += DTime1 >> 5; /* small advantage to algorithm using less memory, to reduce cache eviction */ return DTime1 < DTime0; } #endif } size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags) { /* validation checks */ if (dstSize == 0) return ERROR(dstSize_tooSmall); if (cSrcSize > dstSize) return ERROR(corruption_detected); /* invalid */ if (cSrcSize == dstSize) { ZSTD_memcpy(dst, cSrc, dstSize); return dstSize; } /* not compressed */ if (cSrcSize == 1) { ZSTD_memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; } /* RLE */ { U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); #if defined(HUF_FORCE_DECOMPRESS_X1) (void)algoNb; assert(algoNb == 0); return HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, flags); #elif defined(HUF_FORCE_DECOMPRESS_X2) (void)algoNb; assert(algoNb == 1); return HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, flags); #else return algoNb ? HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, flags): HUF_decompress1X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, flags); #endif } } size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int flags) { DTableDesc const dtd = HUF_getDTableDesc(DTable); #if defined(HUF_FORCE_DECOMPRESS_X1) (void)dtd; assert(dtd.tableType == 0); return HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, flags); #elif defined(HUF_FORCE_DECOMPRESS_X2) (void)dtd; assert(dtd.tableType == 1); return HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, flags); #else return dtd.tableType ? HUF_decompress1X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, flags) : HUF_decompress1X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, flags); #endif } #ifndef HUF_FORCE_DECOMPRESS_X2 size_t HUF_decompress1X1_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags) { const BYTE* ip = (const BYTE*) cSrc; size_t const hSize = HUF_readDTableX1_wksp(dctx, cSrc, cSrcSize, workSpace, wkspSize, flags); if (HUF_isError(hSize)) return hSize; if (hSize >= cSrcSize) return ERROR(srcSize_wrong); ip += hSize; cSrcSize -= hSize; return HUF_decompress1X1_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx, flags); } #endif size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable, int flags) { DTableDesc const dtd = HUF_getDTableDesc(DTable); #if defined(HUF_FORCE_DECOMPRESS_X1) (void)dtd; assert(dtd.tableType == 0); return HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, flags); #elif defined(HUF_FORCE_DECOMPRESS_X2) (void)dtd; assert(dtd.tableType == 1); return HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, flags); #else return dtd.tableType ? HUF_decompress4X2_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, flags) : HUF_decompress4X1_usingDTable_internal(dst, maxDstSize, cSrc, cSrcSize, DTable, flags); #endif } size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize, int flags) { /* validation checks */ if (dstSize == 0) return ERROR(dstSize_tooSmall); if (cSrcSize == 0) return ERROR(corruption_detected); { U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize); #if defined(HUF_FORCE_DECOMPRESS_X1) (void)algoNb; assert(algoNb == 0); return HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, flags); #elif defined(HUF_FORCE_DECOMPRESS_X2) (void)algoNb; assert(algoNb == 1); return HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, flags); #else return algoNb ? HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, flags) : HUF_decompress4X1_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize, flags); #endif } } |
| 119 120 118 119 119 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 | // SPDX-License-Identifier: GPL-2.0+ OR BSD-3-Clause /* * Copyright (c) Meta Platforms, Inc. and affiliates. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the * LICENSE file in the root directory of this source tree) and the GPLv2 (found * in the COPYING file in the root directory of this source tree). * You may select, at your option, one of the above-listed licenses. */ #include "zstd_ldm.h" #include "../common/debug.h" #include <linux/xxhash.h> #include "zstd_fast.h" /* ZSTD_fillHashTable() */ #include "zstd_double_fast.h" /* ZSTD_fillDoubleHashTable() */ #include "zstd_ldm_geartab.h" #define LDM_BUCKET_SIZE_LOG 4 #define LDM_MIN_MATCH_LENGTH 64 #define LDM_HASH_RLOG 7 typedef struct { U64 rolling; U64 stopMask; } ldmRollingHashState_t; /* ZSTD_ldm_gear_init(): * * Initializes the rolling hash state such that it will honor the * settings in params. */ static void ZSTD_ldm_gear_init(ldmRollingHashState_t* state, ldmParams_t const* params) { unsigned maxBitsInMask = MIN(params->minMatchLength, 64); unsigned hashRateLog = params->hashRateLog; state->rolling = ~(U32)0; /* The choice of the splitting criterion is subject to two conditions: * 1. it has to trigger on average every 2^(hashRateLog) bytes; * 2. ideally, it has to depend on a window of minMatchLength bytes. * * In the gear hash algorithm, bit n depends on the last n bytes; * so in order to obtain a good quality splitting criterion it is * preferable to use bits with high weight. * * To match condition 1 we use a mask with hashRateLog bits set * and, because of the previous remark, we make sure these bits * have the highest possible weight while still respecting * condition 2. */ if (hashRateLog > 0 && hashRateLog <= maxBitsInMask) { state->stopMask = (((U64)1 << hashRateLog) - 1) << (maxBitsInMask - hashRateLog); } else { /* In this degenerate case we simply honor the hash rate. */ state->stopMask = ((U64)1 << hashRateLog) - 1; } } /* ZSTD_ldm_gear_reset() * Feeds [data, data + minMatchLength) into the hash without registering any * splits. This effectively resets the hash state. This is used when skipping * over data, either at the beginning of a block, or skipping sections. */ static void ZSTD_ldm_gear_reset(ldmRollingHashState_t* state, BYTE const* data, size_t minMatchLength) { U64 hash = state->rolling; size_t n = 0; #define GEAR_ITER_ONCE() do { \ hash = (hash << 1) + ZSTD_ldm_gearTab[data[n] & 0xff]; \ n += 1; \ } while (0) while (n + 3 < minMatchLength) { GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); } while (n < minMatchLength) { GEAR_ITER_ONCE(); } #undef GEAR_ITER_ONCE } /* ZSTD_ldm_gear_feed(): * * Registers in the splits array all the split points found in the first * size bytes following the data pointer. This function terminates when * either all the data has been processed or LDM_BATCH_SIZE splits are * present in the splits array. * * Precondition: The splits array must not be full. * Returns: The number of bytes processed. */ static size_t ZSTD_ldm_gear_feed(ldmRollingHashState_t* state, BYTE const* data, size_t size, size_t* splits, unsigned* numSplits) { size_t n; U64 hash, mask; hash = state->rolling; mask = state->stopMask; n = 0; #define GEAR_ITER_ONCE() do { \ hash = (hash << 1) + ZSTD_ldm_gearTab[data[n] & 0xff]; \ n += 1; \ if (UNLIKELY((hash & mask) == 0)) { \ splits[*numSplits] = n; \ *numSplits += 1; \ if (*numSplits == LDM_BATCH_SIZE) \ goto done; \ } \ } while (0) while (n + 3 < size) { GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); GEAR_ITER_ONCE(); } while (n < size) { GEAR_ITER_ONCE(); } #undef GEAR_ITER_ONCE done: state->rolling = hash; return n; } void ZSTD_ldm_adjustParameters(ldmParams_t* params, const ZSTD_compressionParameters* cParams) { params->windowLog = cParams->windowLog; ZSTD_STATIC_ASSERT(LDM_BUCKET_SIZE_LOG <= ZSTD_LDM_BUCKETSIZELOG_MAX); DEBUGLOG(4, "ZSTD_ldm_adjustParameters"); if (params->hashRateLog == 0) { if (params->hashLog > 0) { /* if params->hashLog is set, derive hashRateLog from it */ assert(params->hashLog <= ZSTD_HASHLOG_MAX); if (params->windowLog > params->hashLog) { params->hashRateLog = params->windowLog - params->hashLog; } } else { assert(1 <= (int)cParams->strategy && (int)cParams->strategy <= 9); /* mapping from [fast, rate7] to [btultra2, rate4] */ params->hashRateLog = 7 - (cParams->strategy/3); } } if (params->hashLog == 0) { params->hashLog = BOUNDED(ZSTD_HASHLOG_MIN, params->windowLog - params->hashRateLog, ZSTD_HASHLOG_MAX); } if (params->minMatchLength == 0) { params->minMatchLength = LDM_MIN_MATCH_LENGTH; if (cParams->strategy >= ZSTD_btultra) params->minMatchLength /= 2; } if (params->bucketSizeLog==0) { assert(1 <= (int)cParams->strategy && (int)cParams->strategy <= 9); params->bucketSizeLog = BOUNDED(LDM_BUCKET_SIZE_LOG, (U32)cParams->strategy, ZSTD_LDM_BUCKETSIZELOG_MAX); } params->bucketSizeLog = MIN(params->bucketSizeLog, params->hashLog); } size_t ZSTD_ldm_getTableSize(ldmParams_t params) { size_t const ldmHSize = ((size_t)1) << params.hashLog; size_t const ldmBucketSizeLog = MIN(params.bucketSizeLog, params.hashLog); size_t const ldmBucketSize = ((size_t)1) << (params.hashLog - ldmBucketSizeLog); size_t const totalSize = ZSTD_cwksp_alloc_size(ldmBucketSize) + ZSTD_cwksp_alloc_size(ldmHSize * sizeof(ldmEntry_t)); return params.enableLdm == ZSTD_ps_enable ? totalSize : 0; } size_t ZSTD_ldm_getMaxNbSeq(ldmParams_t params, size_t maxChunkSize) { return params.enableLdm == ZSTD_ps_enable ? (maxChunkSize / params.minMatchLength) : 0; } /* ZSTD_ldm_getBucket() : * Returns a pointer to the start of the bucket associated with hash. */ static ldmEntry_t* ZSTD_ldm_getBucket( const ldmState_t* ldmState, size_t hash, U32 const bucketSizeLog) { return ldmState->hashTable + (hash << bucketSizeLog); } /* ZSTD_ldm_insertEntry() : * Insert the entry with corresponding hash into the hash table */ static void ZSTD_ldm_insertEntry(ldmState_t* ldmState, size_t const hash, const ldmEntry_t entry, U32 const bucketSizeLog) { BYTE* const pOffset = ldmState->bucketOffsets + hash; unsigned const offset = *pOffset; *(ZSTD_ldm_getBucket(ldmState, hash, bucketSizeLog) + offset) = entry; *pOffset = (BYTE)((offset + 1) & ((1u << bucketSizeLog) - 1)); } /* ZSTD_ldm_countBackwardsMatch() : * Returns the number of bytes that match backwards before pIn and pMatch. * * We count only bytes where pMatch >= pBase and pIn >= pAnchor. */ static size_t ZSTD_ldm_countBackwardsMatch( const BYTE* pIn, const BYTE* pAnchor, const BYTE* pMatch, const BYTE* pMatchBase) { size_t matchLength = 0; while (pIn > pAnchor && pMatch > pMatchBase && pIn[-1] == pMatch[-1]) { pIn--; pMatch--; matchLength++; } return matchLength; } /* ZSTD_ldm_countBackwardsMatch_2segments() : * Returns the number of bytes that match backwards from pMatch, * even with the backwards match spanning 2 different segments. * * On reaching `pMatchBase`, start counting from mEnd */ static size_t ZSTD_ldm_countBackwardsMatch_2segments( const BYTE* pIn, const BYTE* pAnchor, const BYTE* pMatch, const BYTE* pMatchBase, const BYTE* pExtDictStart, const BYTE* pExtDictEnd) { size_t matchLength = ZSTD_ldm_countBackwardsMatch(pIn, pAnchor, pMatch, pMatchBase); if (pMatch - matchLength != pMatchBase || pMatchBase == pExtDictStart) { /* If backwards match is entirely in the extDict or prefix, immediately return */ return matchLength; } DEBUGLOG(7, "ZSTD_ldm_countBackwardsMatch_2segments: found 2-parts backwards match (length in prefix==%zu)", matchLength); matchLength += ZSTD_ldm_countBackwardsMatch(pIn - matchLength, pAnchor, pExtDictEnd, pExtDictStart); DEBUGLOG(7, "final backwards match length = %zu", matchLength); return matchLength; } /* ZSTD_ldm_fillFastTables() : * * Fills the relevant tables for the ZSTD_fast and ZSTD_dfast strategies. * This is similar to ZSTD_loadDictionaryContent. * * The tables for the other strategies are filled within their * block compressors. */ static size_t ZSTD_ldm_fillFastTables(ZSTD_MatchState_t* ms, void const* end) { const BYTE* const iend = (const BYTE*)end; switch(ms->cParams.strategy) { case ZSTD_fast: ZSTD_fillHashTable(ms, iend, ZSTD_dtlm_fast, ZSTD_tfp_forCCtx); break; case ZSTD_dfast: #ifndef ZSTD_EXCLUDE_DFAST_BLOCK_COMPRESSOR ZSTD_fillDoubleHashTable(ms, iend, ZSTD_dtlm_fast, ZSTD_tfp_forCCtx); #else assert(0); /* shouldn't be called: cparams should've been adjusted. */ #endif break; case ZSTD_greedy: case ZSTD_lazy: case ZSTD_lazy2: case ZSTD_btlazy2: case ZSTD_btopt: case ZSTD_btultra: case ZSTD_btultra2: break; default: assert(0); /* not possible : not a valid strategy id */ } return 0; } void ZSTD_ldm_fillHashTable( ldmState_t* ldmState, const BYTE* ip, const BYTE* iend, ldmParams_t const* params) { U32 const minMatchLength = params->minMatchLength; U32 const bucketSizeLog = params->bucketSizeLog; U32 const hBits = params->hashLog - bucketSizeLog; BYTE const* const base = ldmState->window.base; BYTE const* const istart = ip; ldmRollingHashState_t hashState; size_t* const splits = ldmState->splitIndices; unsigned numSplits; DEBUGLOG(5, "ZSTD_ldm_fillHashTable"); ZSTD_ldm_gear_init(&hashState, params); while (ip < iend) { size_t hashed; unsigned n; numSplits = 0; hashed = ZSTD_ldm_gear_feed(&hashState, ip, (size_t)(iend - ip), splits, &numSplits); for (n = 0; n < numSplits; n++) { if (ip + splits[n] >= istart + minMatchLength) { BYTE const* const split = ip + splits[n] - minMatchLength; U64 const xxhash = xxh64(split, minMatchLength, 0); U32 const hash = (U32)(xxhash & (((U32)1 << hBits) - 1)); ldmEntry_t entry; entry.offset = (U32)(split - base); entry.checksum = (U32)(xxhash >> 32); ZSTD_ldm_insertEntry(ldmState, hash, entry, params->bucketSizeLog); } } ip += hashed; } } /* ZSTD_ldm_limitTableUpdate() : * * Sets cctx->nextToUpdate to a position corresponding closer to anchor * if it is far way * (after a long match, only update tables a limited amount). */ static void ZSTD_ldm_limitTableUpdate(ZSTD_MatchState_t* ms, const BYTE* anchor) { U32 const curr = (U32)(anchor - ms->window.base); if (curr > ms->nextToUpdate + 1024) { ms->nextToUpdate = curr - MIN(512, curr - ms->nextToUpdate - 1024); } } static ZSTD_ALLOW_POINTER_OVERFLOW_ATTR size_t ZSTD_ldm_generateSequences_internal( ldmState_t* ldmState, RawSeqStore_t* rawSeqStore, ldmParams_t const* params, void const* src, size_t srcSize) { /* LDM parameters */ int const extDict = ZSTD_window_hasExtDict(ldmState->window); U32 const minMatchLength = params->minMatchLength; U32 const entsPerBucket = 1U << params->bucketSizeLog; U32 const hBits = params->hashLog - params->bucketSizeLog; /* Prefix and extDict parameters */ U32 const dictLimit = ldmState->window.dictLimit; U32 const lowestIndex = extDict ? ldmState->window.lowLimit : dictLimit; BYTE const* const base = ldmState->window.base; BYTE const* const dictBase = extDict ? ldmState->window.dictBase : NULL; BYTE const* const dictStart = extDict ? dictBase + lowestIndex : NULL; BYTE const* const dictEnd = extDict ? dictBase + dictLimit : NULL; BYTE const* const lowPrefixPtr = base + dictLimit; /* Input bounds */ BYTE const* const istart = (BYTE const*)src; BYTE const* const iend = istart + srcSize; BYTE const* const ilimit = iend - HASH_READ_SIZE; /* Input positions */ BYTE const* anchor = istart; BYTE const* ip = istart; /* Rolling hash state */ ldmRollingHashState_t hashState; /* Arrays for staged-processing */ size_t* const splits = ldmState->splitIndices; ldmMatchCandidate_t* const candidates = ldmState->matchCandidates; unsigned numSplits; if (srcSize < minMatchLength) return iend - anchor; /* Initialize the rolling hash state with the first minMatchLength bytes */ ZSTD_ldm_gear_init(&hashState, params); ZSTD_ldm_gear_reset(&hashState, ip, minMatchLength); ip += minMatchLength; while (ip < ilimit) { size_t hashed; unsigned n; numSplits = 0; hashed = ZSTD_ldm_gear_feed(&hashState, ip, ilimit - ip, splits, &numSplits); for (n = 0; n < numSplits; n++) { BYTE const* const split = ip + splits[n] - minMatchLength; U64 const xxhash = xxh64(split, minMatchLength, 0); U32 const hash = (U32)(xxhash & (((U32)1 << hBits) - 1)); candidates[n].split = split; candidates[n].hash = hash; candidates[n].checksum = (U32)(xxhash >> 32); candidates[n].bucket = ZSTD_ldm_getBucket(ldmState, hash, params->bucketSizeLog); PREFETCH_L1(candidates[n].bucket); } for (n = 0; n < numSplits; n++) { size_t forwardMatchLength = 0, backwardMatchLength = 0, bestMatchLength = 0, mLength; U32 offset; BYTE const* const split = candidates[n].split; U32 const checksum = candidates[n].checksum; U32 const hash = candidates[n].hash; ldmEntry_t* const bucket = candidates[n].bucket; ldmEntry_t const* cur; ldmEntry_t const* bestEntry = NULL; ldmEntry_t newEntry; newEntry.offset = (U32)(split - base); newEntry.checksum = checksum; /* If a split point would generate a sequence overlapping with * the previous one, we merely register it in the hash table and * move on */ if (split < anchor) { ZSTD_ldm_insertEntry(ldmState, hash, newEntry, params->bucketSizeLog); continue; } for (cur = bucket; cur < bucket + entsPerBucket; cur++) { size_t curForwardMatchLength, curBackwardMatchLength, curTotalMatchLength; if (cur->checksum != checksum || cur->offset <= lowestIndex) { continue; } if (extDict) { BYTE const* const curMatchBase = cur->offset < dictLimit ? dictBase : base; BYTE const* const pMatch = curMatchBase + cur->offset; BYTE const* const matchEnd = cur->offset < dictLimit ? dictEnd : iend; BYTE const* const lowMatchPtr = cur->offset < dictLimit ? dictStart : lowPrefixPtr; curForwardMatchLength = ZSTD_count_2segments(split, pMatch, iend, matchEnd, lowPrefixPtr); if (curForwardMatchLength < minMatchLength) { continue; } curBackwardMatchLength = ZSTD_ldm_countBackwardsMatch_2segments( split, anchor, pMatch, lowMatchPtr, dictStart, dictEnd); } else { /* !extDict */ BYTE const* const pMatch = base + cur->offset; curForwardMatchLength = ZSTD_count(split, pMatch, iend); if (curForwardMatchLength < minMatchLength) { continue; } curBackwardMatchLength = ZSTD_ldm_countBackwardsMatch(split, anchor, pMatch, lowPrefixPtr); } curTotalMatchLength = curForwardMatchLength + curBackwardMatchLength; if (curTotalMatchLength > bestMatchLength) { bestMatchLength = curTotalMatchLength; forwardMatchLength = curForwardMatchLength; backwardMatchLength = curBackwardMatchLength; bestEntry = cur; } } /* No match found -- insert an entry into the hash table * and process the next candidate match */ if (bestEntry == NULL) { ZSTD_ldm_insertEntry(ldmState, hash, newEntry, params->bucketSizeLog); continue; } /* Match found */ offset = (U32)(split - base) - bestEntry->offset; mLength = forwardMatchLength + backwardMatchLength; { rawSeq* const seq = rawSeqStore->seq + rawSeqStore->size; /* Out of sequence storage */ if (rawSeqStore->size == rawSeqStore->capacity) return ERROR(dstSize_tooSmall); seq->litLength = (U32)(split - backwardMatchLength - anchor); seq->matchLength = (U32)mLength; seq->offset = offset; rawSeqStore->size++; } /* Insert the current entry into the hash table --- it must be * done after the previous block to avoid clobbering bestEntry */ ZSTD_ldm_insertEntry(ldmState, hash, newEntry, params->bucketSizeLog); anchor = split + forwardMatchLength; /* If we find a match that ends after the data that we've hashed * then we have a repeating, overlapping, pattern. E.g. all zeros. * If one repetition of the pattern matches our `stopMask` then all * repetitions will. We don't need to insert them all into out table, * only the first one. So skip over overlapping matches. * This is a major speed boost (20x) for compressing a single byte * repeated, when that byte ends up in the table. */ if (anchor > ip + hashed) { ZSTD_ldm_gear_reset(&hashState, anchor - minMatchLength, minMatchLength); /* Continue the outer loop at anchor (ip + hashed == anchor). */ ip = anchor - hashed; break; } } ip += hashed; } return iend - anchor; } /*! ZSTD_ldm_reduceTable() : * reduce table indexes by `reducerValue` */ static void ZSTD_ldm_reduceTable(ldmEntry_t* const table, U32 const size, U32 const reducerValue) { U32 u; for (u = 0; u < size; u++) { if (table[u].offset < reducerValue) table[u].offset = 0; else table[u].offset -= reducerValue; } } size_t ZSTD_ldm_generateSequences( ldmState_t* ldmState, RawSeqStore_t* sequences, ldmParams_t const* params, void const* src, size_t srcSize) { U32 const maxDist = 1U << params->windowLog; BYTE const* const istart = (BYTE const*)src; BYTE const* const iend = istart + srcSize; size_t const kMaxChunkSize = 1 << 20; size_t const nbChunks = (srcSize / kMaxChunkSize) + ((srcSize % kMaxChunkSize) != 0); size_t chunk; size_t leftoverSize = 0; assert(ZSTD_CHUNKSIZE_MAX >= kMaxChunkSize); /* Check that ZSTD_window_update() has been called for this chunk prior * to passing it to this function. */ assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize); /* The input could be very large (in zstdmt), so it must be broken up into * chunks to enforce the maximum distance and handle overflow correction. */ assert(sequences->pos <= sequences->size); assert(sequences->size <= sequences->capacity); for (chunk = 0; chunk < nbChunks && sequences->size < sequences->capacity; ++chunk) { BYTE const* const chunkStart = istart + chunk * kMaxChunkSize; size_t const remaining = (size_t)(iend - chunkStart); BYTE const *const chunkEnd = (remaining < kMaxChunkSize) ? iend : chunkStart + kMaxChunkSize; size_t const chunkSize = chunkEnd - chunkStart; size_t newLeftoverSize; size_t const prevSize = sequences->size; assert(chunkStart < iend); /* 1. Perform overflow correction if necessary. */ if (ZSTD_window_needOverflowCorrection(ldmState->window, 0, maxDist, ldmState->loadedDictEnd, chunkStart, chunkEnd)) { U32 const ldmHSize = 1U << params->hashLog; U32 const correction = ZSTD_window_correctOverflow( &ldmState->window, /* cycleLog */ 0, maxDist, chunkStart); ZSTD_ldm_reduceTable(ldmState->hashTable, ldmHSize, correction); /* invalidate dictionaries on overflow correction */ ldmState->loadedDictEnd = 0; } /* 2. We enforce the maximum offset allowed. * * kMaxChunkSize should be small enough that we don't lose too much of * the window through early invalidation. * TODO: * Test the chunk size. * * Try invalidation after the sequence generation and test the * offset against maxDist directly. * * NOTE: Because of dictionaries + sequence splitting we MUST make sure * that any offset used is valid at the END of the sequence, since it may * be split into two sequences. This condition holds when using * ZSTD_window_enforceMaxDist(), but if we move to checking offsets * against maxDist directly, we'll have to carefully handle that case. */ ZSTD_window_enforceMaxDist(&ldmState->window, chunkEnd, maxDist, &ldmState->loadedDictEnd, NULL); /* 3. Generate the sequences for the chunk, and get newLeftoverSize. */ newLeftoverSize = ZSTD_ldm_generateSequences_internal( ldmState, sequences, params, chunkStart, chunkSize); if (ZSTD_isError(newLeftoverSize)) return newLeftoverSize; /* 4. We add the leftover literals from previous iterations to the first * newly generated sequence, or add the `newLeftoverSize` if none are * generated. */ /* Prepend the leftover literals from the last call */ if (prevSize < sequences->size) { sequences->seq[prevSize].litLength += (U32)leftoverSize; leftoverSize = newLeftoverSize; } else { assert(newLeftoverSize == chunkSize); leftoverSize += chunkSize; } } return 0; } void ZSTD_ldm_skipSequences(RawSeqStore_t* rawSeqStore, size_t srcSize, U32 const minMatch) { while (srcSize > 0 && rawSeqStore->pos < rawSeqStore->size) { rawSeq* seq = rawSeqStore->seq + rawSeqStore->pos; if (srcSize <= seq->litLength) { /* Skip past srcSize literals */ seq->litLength -= (U32)srcSize; return; } srcSize -= seq->litLength; seq->litLength = 0; if (srcSize < seq->matchLength) { /* Skip past the first srcSize of the match */ seq->matchLength -= (U32)srcSize; if (seq->matchLength < minMatch) { /* The match is too short, omit it */ if (rawSeqStore->pos + 1 < rawSeqStore->size) { seq[1].litLength += seq[0].matchLength; } rawSeqStore->pos++; } return; } srcSize -= seq->matchLength; seq->matchLength = 0; rawSeqStore->pos++; } } /* * If the sequence length is longer than remaining then the sequence is split * between this block and the next. * * Returns the current sequence to handle, or if the rest of the block should * be literals, it returns a sequence with offset == 0. */ static rawSeq maybeSplitSequence(RawSeqStore_t* rawSeqStore, U32 const remaining, U32 const minMatch) { rawSeq sequence = rawSeqStore->seq[rawSeqStore->pos]; assert(sequence.offset > 0); /* Likely: No partial sequence */ if (remaining >= sequence.litLength + sequence.matchLength) { rawSeqStore->pos++; return sequence; } /* Cut the sequence short (offset == 0 ==> rest is literals). */ if (remaining <= sequence.litLength) { sequence.offset = 0; } else if (remaining < sequence.litLength + sequence.matchLength) { sequence.matchLength = remaining - sequence.litLength; if (sequence.matchLength < minMatch) { sequence.offset = 0; } } /* Skip past `remaining` bytes for the future sequences. */ ZSTD_ldm_skipSequences(rawSeqStore, remaining, minMatch); return sequence; } void ZSTD_ldm_skipRawSeqStoreBytes(RawSeqStore_t* rawSeqStore, size_t nbBytes) { U32 currPos = (U32)(rawSeqStore->posInSequence + nbBytes); while (currPos && rawSeqStore->pos < rawSeqStore->size) { rawSeq currSeq = rawSeqStore->seq[rawSeqStore->pos]; if (currPos >= currSeq.litLength + currSeq.matchLength) { currPos -= currSeq.litLength + currSeq.matchLength; rawSeqStore->pos++; } else { rawSeqStore->posInSequence = currPos; break; } } if (currPos == 0 || rawSeqStore->pos == rawSeqStore->size) { rawSeqStore->posInSequence = 0; } } size_t ZSTD_ldm_blockCompress(RawSeqStore_t* rawSeqStore, ZSTD_MatchState_t* ms, SeqStore_t* seqStore, U32 rep[ZSTD_REP_NUM], ZSTD_ParamSwitch_e useRowMatchFinder, void const* src, size_t srcSize) { const ZSTD_compressionParameters* const cParams = &ms->cParams; unsigned const minMatch = cParams->minMatch; ZSTD_BlockCompressor_f const blockCompressor = ZSTD_selectBlockCompressor(cParams->strategy, useRowMatchFinder, ZSTD_matchState_dictMode(ms)); /* Input bounds */ BYTE const* const istart = (BYTE const*)src; BYTE const* const iend = istart + srcSize; /* Input positions */ BYTE const* ip = istart; DEBUGLOG(5, "ZSTD_ldm_blockCompress: srcSize=%zu", srcSize); /* If using opt parser, use LDMs only as candidates rather than always accepting them */ if (cParams->strategy >= ZSTD_btopt) { size_t lastLLSize; ms->ldmSeqStore = rawSeqStore; lastLLSize = blockCompressor(ms, seqStore, rep, src, srcSize); ZSTD_ldm_skipRawSeqStoreBytes(rawSeqStore, srcSize); return lastLLSize; } assert(rawSeqStore->pos <= rawSeqStore->size); assert(rawSeqStore->size <= rawSeqStore->capacity); /* Loop through each sequence and apply the block compressor to the literals */ while (rawSeqStore->pos < rawSeqStore->size && ip < iend) { /* maybeSplitSequence updates rawSeqStore->pos */ rawSeq const sequence = maybeSplitSequence(rawSeqStore, (U32)(iend - ip), minMatch); /* End signal */ if (sequence.offset == 0) break; assert(ip + sequence.litLength + sequence.matchLength <= iend); /* Fill tables for block compressor */ ZSTD_ldm_limitTableUpdate(ms, ip); ZSTD_ldm_fillFastTables(ms, ip); /* Run the block compressor */ DEBUGLOG(5, "pos %u : calling block compressor on segment of size %u", (unsigned)(ip-istart), sequence.litLength); { int i; size_t const newLitLength = blockCompressor(ms, seqStore, rep, ip, sequence.litLength); ip += sequence.litLength; /* Update the repcodes */ for (i = ZSTD_REP_NUM - 1; i > 0; i--) rep[i] = rep[i-1]; rep[0] = sequence.offset; /* Store the sequence */ ZSTD_storeSeq(seqStore, newLitLength, ip - newLitLength, iend, OFFSET_TO_OFFBASE(sequence.offset), sequence.matchLength); ip += sequence.matchLength; } } /* Fill the tables for the block compressor */ ZSTD_ldm_limitTableUpdate(ms, ip); ZSTD_ldm_fillFastTables(ms, ip); /* Compress the last literals */ return blockCompressor(ms, seqStore, rep, ip, iend - ip); } |
| 7 36 36 25 6 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_BTREE_JOURNAL_ITER_H #define _BCACHEFS_BTREE_JOURNAL_ITER_H #include "bkey.h" struct journal_iter { struct list_head list; enum btree_id btree_id; unsigned level; size_t idx; struct journal_keys *keys; }; /* * Iterate over keys in the btree, with keys from the journal overlaid on top: */ struct btree_and_journal_iter { struct btree_trans *trans; struct btree *b; struct btree_node_iter node_iter; struct bkey unpacked; struct journal_iter journal; struct bpos pos; bool at_end; bool prefetch; bool fail_if_too_many_whiteouts; }; static inline int __journal_key_btree_cmp(enum btree_id l_btree_id, unsigned l_level, const struct journal_key *r) { return -cmp_int(l_level, r->level) ?: cmp_int(l_btree_id, r->btree_id); } static inline int __journal_key_cmp(enum btree_id l_btree_id, unsigned l_level, struct bpos l_pos, const struct journal_key *r) { return __journal_key_btree_cmp(l_btree_id, l_level, r) ?: bpos_cmp(l_pos, r->k->k.p); } static inline int journal_key_cmp(const struct journal_key *l, const struct journal_key *r) { return __journal_key_cmp(l->btree_id, l->level, l->k->k.p, r); } struct bkey_i *bch2_journal_keys_peek_max(struct bch_fs *, enum btree_id, unsigned, struct bpos, struct bpos, size_t *); struct bkey_i *bch2_journal_keys_peek_prev_min(struct bch_fs *, enum btree_id, unsigned, struct bpos, struct bpos, size_t *); struct bkey_i *bch2_journal_keys_peek_slot(struct bch_fs *, enum btree_id, unsigned, struct bpos); int bch2_btree_and_journal_iter_prefetch(struct btree_trans *, struct btree_path *, struct btree_and_journal_iter *); int bch2_journal_key_insert_take(struct bch_fs *, enum btree_id, unsigned, struct bkey_i *); int bch2_journal_key_insert(struct bch_fs *, enum btree_id, unsigned, struct bkey_i *); int bch2_journal_key_delete(struct bch_fs *, enum btree_id, unsigned, struct bpos); bool bch2_key_deleted_in_journal(struct btree_trans *, enum btree_id, unsigned, struct bpos); void bch2_journal_key_overwritten(struct bch_fs *, enum btree_id, unsigned, struct bpos); void bch2_btree_and_journal_iter_advance(struct btree_and_journal_iter *); struct bkey_s_c bch2_btree_and_journal_iter_peek(struct btree_and_journal_iter *); void bch2_btree_and_journal_iter_exit(struct btree_and_journal_iter *); void __bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *, struct btree_and_journal_iter *, struct btree *, struct btree_node_iter, struct bpos); void bch2_btree_and_journal_iter_init_node_iter(struct btree_trans *, struct btree_and_journal_iter *, struct btree *); void bch2_journal_keys_put(struct bch_fs *); static inline void bch2_journal_keys_put_initial(struct bch_fs *c) { if (c->journal_keys.initial_ref_held) bch2_journal_keys_put(c); c->journal_keys.initial_ref_held = false; } int bch2_journal_keys_sort(struct bch_fs *); void bch2_shoot_down_journal_keys(struct bch_fs *, enum btree_id, unsigned, unsigned, struct bpos, struct bpos); void bch2_journal_keys_dump(struct bch_fs *); void bch2_fs_journal_keys_init(struct bch_fs *); #endif /* _BCACHEFS_BTREE_JOURNAL_ITER_H */ |
| 216 3 1 32 3 90 3 77 24 28 1 77 77 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Copyright (C) International Business Machines Corp., 2000-2002 * Portions Copyright (C) Christoph Hellwig, 2001-2002 */ #ifndef _H_JFS_UNICODE #define _H_JFS_UNICODE #include <linux/slab.h> #include <asm/byteorder.h> #include "../nls/nls_ucs2_data.h" #include "jfs_types.h" extern int get_UCSname(struct component_name *, struct dentry *); extern int jfs_strfromUCS_le(char *, const __le16 *, int, struct nls_table *); #define free_UCSname(COMP) kfree((COMP)->name) /* * UniStrcpy: Copy a string */ static inline wchar_t *UniStrcpy(wchar_t * ucs1, const wchar_t * ucs2) { wchar_t *anchor = ucs1; /* save the start of result string */ while ((*ucs1++ = *ucs2++)); return anchor; } /* * UniStrncpy: Copy length limited string with pad */ static inline __le16 *UniStrncpy_le(__le16 * ucs1, const __le16 * ucs2, size_t n) { __le16 *anchor = ucs1; while (n-- && *ucs2) /* Copy the strings */ *ucs1++ = *ucs2++; n++; while (n--) /* Pad with nulls */ *ucs1++ = 0; return anchor; } /* * UniStrncmp_le: Compare length limited string - native to little-endian */ static inline int UniStrncmp_le(const wchar_t * ucs1, const __le16 * ucs2, size_t n) { if (!n) return 0; /* Null strings are equal */ while ((*ucs1 == __le16_to_cpu(*ucs2)) && *ucs1 && --n) { ucs1++; ucs2++; } return (int) *ucs1 - (int) __le16_to_cpu(*ucs2); } /* * UniStrncpy_to_le: Copy length limited string with pad to little-endian */ static inline __le16 *UniStrncpy_to_le(__le16 * ucs1, const wchar_t * ucs2, size_t n) { __le16 *anchor = ucs1; while (n-- && *ucs2) /* Copy the strings */ *ucs1++ = cpu_to_le16(*ucs2++); n++; while (n--) /* Pad with nulls */ *ucs1++ = 0; return anchor; } /* * UniStrncpy_from_le: Copy length limited string with pad from little-endian */ static inline wchar_t *UniStrncpy_from_le(wchar_t * ucs1, const __le16 * ucs2, size_t n) { wchar_t *anchor = ucs1; while (n-- && *ucs2) /* Copy the strings */ *ucs1++ = __le16_to_cpu(*ucs2++); n++; while (n--) /* Pad with nulls */ *ucs1++ = 0; return anchor; } /* * UniToupper: Convert a unicode character to upper case */ static inline wchar_t UniToupper(wchar_t uc) { const struct UniCaseRange *rp; if (uc < sizeof(NlsUniUpperTable)) { /* Latin characters */ return uc + NlsUniUpperTable[uc]; /* Use base tables */ } else { rp = NlsUniUpperRange; /* Use range tables */ while (rp->start) { if (uc < rp->start) /* Before start of range */ return uc; /* Uppercase = input */ if (uc <= rp->end) /* In range */ return uc + rp->table[uc - rp->start]; rp++; /* Try next range */ } } return uc; /* Past last range */ } /* * UniStrupr: Upper case a unicode string */ static inline wchar_t *UniStrupr(wchar_t * upin) { wchar_t *up; up = upin; while (*up) { /* For all characters */ *up = UniToupper(*up); up++; } return upin; /* Return input pointer */ } #endif /* !_H_JFS_UNICODE */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * "TEE" target extension for Xtables * Copyright © Sebastian Claßen, 2007 * Jan Engelhardt, 2007-2010 * * based on ipt_ROUTE.c from Cédric de Launois * <delaunois@info.ucl.be> */ #include <linux/module.h> #include <linux/skbuff.h> #include <linux/route.h> #include <linux/netfilter/x_tables.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/route.h> #include <net/netfilter/ipv4/nf_dup_ipv4.h> #include <net/netfilter/ipv6/nf_dup_ipv6.h> #include <linux/netfilter/xt_TEE.h> struct xt_tee_priv { struct list_head list; struct xt_tee_tginfo *tginfo; int oif; }; static unsigned int tee_net_id __read_mostly; static const union nf_inet_addr tee_zero_address; struct tee_net { struct list_head priv_list; /* lock protects the priv_list */ struct mutex lock; }; static unsigned int tee_tg4(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; int oif = info->priv ? info->priv->oif : 0; nf_dup_ipv4(xt_net(par), skb, xt_hooknum(par), &info->gw.in, oif); return XT_CONTINUE; } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) static unsigned int tee_tg6(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_tee_tginfo *info = par->targinfo; int oif = info->priv ? info->priv->oif : 0; nf_dup_ipv6(xt_net(par), skb, xt_hooknum(par), &info->gw.in6, oif); return XT_CONTINUE; } #endif static int tee_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net *net = dev_net(dev); struct tee_net *tn = net_generic(net, tee_net_id); struct xt_tee_priv *priv; mutex_lock(&tn->lock); list_for_each_entry(priv, &tn->priv_list, list) { switch (event) { case NETDEV_REGISTER: if (!strcmp(dev->name, priv->tginfo->oif)) priv->oif = dev->ifindex; break; case NETDEV_UNREGISTER: if (dev->ifindex == priv->oif) priv->oif = -1; break; case NETDEV_CHANGENAME: if (!strcmp(dev->name, priv->tginfo->oif)) priv->oif = dev->ifindex; else if (dev->ifindex == priv->oif) priv->oif = -1; break; } } mutex_unlock(&tn->lock); return NOTIFY_DONE; } static int tee_tg_check(const struct xt_tgchk_param *par) { struct tee_net *tn = net_generic(par->net, tee_net_id); struct xt_tee_tginfo *info = par->targinfo; struct xt_tee_priv *priv; /* 0.0.0.0 and :: not allowed */ if (memcmp(&info->gw, &tee_zero_address, sizeof(tee_zero_address)) == 0) return -EINVAL; if (info->oif[0]) { struct net_device *dev; if (info->oif[sizeof(info->oif)-1] != '\0') return -EINVAL; priv = kzalloc(sizeof(*priv), GFP_KERNEL); if (priv == NULL) return -ENOMEM; priv->tginfo = info; priv->oif = -1; info->priv = priv; dev = dev_get_by_name(par->net, info->oif); if (dev) { priv->oif = dev->ifindex; dev_put(dev); } mutex_lock(&tn->lock); list_add(&priv->list, &tn->priv_list); mutex_unlock(&tn->lock); } else info->priv = NULL; static_key_slow_inc(&xt_tee_enabled); return 0; } static void tee_tg_destroy(const struct xt_tgdtor_param *par) { struct tee_net *tn = net_generic(par->net, tee_net_id); struct xt_tee_tginfo *info = par->targinfo; if (info->priv) { mutex_lock(&tn->lock); list_del(&info->priv->list); mutex_unlock(&tn->lock); kfree(info->priv); } static_key_slow_dec(&xt_tee_enabled); } static struct xt_target tee_tg_reg[] __read_mostly = { { .name = "TEE", .revision = 1, .family = NFPROTO_IPV4, .target = tee_tg4, .targetsize = sizeof(struct xt_tee_tginfo), .usersize = offsetof(struct xt_tee_tginfo, priv), .checkentry = tee_tg_check, .destroy = tee_tg_destroy, .me = THIS_MODULE, }, #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) { .name = "TEE", .revision = 1, .family = NFPROTO_IPV6, .target = tee_tg6, .targetsize = sizeof(struct xt_tee_tginfo), .usersize = offsetof(struct xt_tee_tginfo, priv), .checkentry = tee_tg_check, .destroy = tee_tg_destroy, .me = THIS_MODULE, }, #endif }; static int __net_init tee_net_init(struct net *net) { struct tee_net *tn = net_generic(net, tee_net_id); INIT_LIST_HEAD(&tn->priv_list); mutex_init(&tn->lock); return 0; } static struct pernet_operations tee_net_ops = { .init = tee_net_init, .id = &tee_net_id, .size = sizeof(struct tee_net), }; static struct notifier_block tee_netdev_notifier = { .notifier_call = tee_netdev_event, }; static int __init tee_tg_init(void) { int ret; ret = register_pernet_subsys(&tee_net_ops); if (ret < 0) return ret; ret = xt_register_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); if (ret < 0) goto cleanup_subsys; ret = register_netdevice_notifier(&tee_netdev_notifier); if (ret < 0) goto unregister_targets; return 0; unregister_targets: xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); cleanup_subsys: unregister_pernet_subsys(&tee_net_ops); return ret; } static void __exit tee_tg_exit(void) { unregister_netdevice_notifier(&tee_netdev_notifier); xt_unregister_targets(tee_tg_reg, ARRAY_SIZE(tee_tg_reg)); unregister_pernet_subsys(&tee_net_ops); } module_init(tee_tg_init); module_exit(tee_tg_exit); MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>"); MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); MODULE_DESCRIPTION("Xtables: Reroute packet copy"); MODULE_LICENSE("GPL"); MODULE_ALIAS("ipt_TEE"); MODULE_ALIAS("ip6t_TEE"); |
| 107 107 105 2 18 18 2 2 2 2 2 2 2 39 94 133 132 1 131 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | // SPDX-License-Identifier: GPL-2.0 /* * fs/f2fs/acl.c * * Copyright (c) 2012 Samsung Electronics Co., Ltd. * http://www.samsung.com/ * * Portions of this code from linux/fs/ext2/acl.c * * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de> */ #include <linux/f2fs_fs.h> #include "f2fs.h" #include "xattr.h" #include "acl.h" static inline size_t f2fs_acl_size(int count) { if (count <= 4) { return sizeof(struct f2fs_acl_header) + count * sizeof(struct f2fs_acl_entry_short); } else { return sizeof(struct f2fs_acl_header) + 4 * sizeof(struct f2fs_acl_entry_short) + (count - 4) * sizeof(struct f2fs_acl_entry); } } static inline int f2fs_acl_count(size_t size) { ssize_t s; size -= sizeof(struct f2fs_acl_header); s = size - 4 * sizeof(struct f2fs_acl_entry_short); if (s < 0) { if (size % sizeof(struct f2fs_acl_entry_short)) return -1; return size / sizeof(struct f2fs_acl_entry_short); } else { if (s % sizeof(struct f2fs_acl_entry)) return -1; return s / sizeof(struct f2fs_acl_entry) + 4; } } static struct posix_acl *f2fs_acl_from_disk(const char *value, size_t size) { int i, count; struct posix_acl *acl; struct f2fs_acl_header *hdr = (struct f2fs_acl_header *)value; struct f2fs_acl_entry *entry = (struct f2fs_acl_entry *)(hdr + 1); const char *end = value + size; if (size < sizeof(struct f2fs_acl_header)) return ERR_PTR(-EINVAL); if (hdr->a_version != cpu_to_le32(F2FS_ACL_VERSION)) return ERR_PTR(-EINVAL); count = f2fs_acl_count(size); if (count < 0) return ERR_PTR(-EINVAL); if (count == 0) return NULL; acl = posix_acl_alloc(count, GFP_NOFS); if (!acl) return ERR_PTR(-ENOMEM); for (i = 0; i < count; i++) { if ((char *)entry > end) goto fail; acl->a_entries[i].e_tag = le16_to_cpu(entry->e_tag); acl->a_entries[i].e_perm = le16_to_cpu(entry->e_perm); switch (acl->a_entries[i].e_tag) { case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry_short)); break; case ACL_USER: acl->a_entries[i].e_uid = make_kuid(&init_user_ns, le32_to_cpu(entry->e_id)); entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry)); break; case ACL_GROUP: acl->a_entries[i].e_gid = make_kgid(&init_user_ns, le32_to_cpu(entry->e_id)); entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry)); break; default: goto fail; } } if ((char *)entry != end) goto fail; return acl; fail: posix_acl_release(acl); return ERR_PTR(-EINVAL); } static void *f2fs_acl_to_disk(struct f2fs_sb_info *sbi, const struct posix_acl *acl, size_t *size) { struct f2fs_acl_header *f2fs_acl; struct f2fs_acl_entry *entry; int i; f2fs_acl = f2fs_kmalloc(sbi, sizeof(struct f2fs_acl_header) + acl->a_count * sizeof(struct f2fs_acl_entry), GFP_NOFS); if (!f2fs_acl) return ERR_PTR(-ENOMEM); f2fs_acl->a_version = cpu_to_le32(F2FS_ACL_VERSION); entry = (struct f2fs_acl_entry *)(f2fs_acl + 1); for (i = 0; i < acl->a_count; i++) { entry->e_tag = cpu_to_le16(acl->a_entries[i].e_tag); entry->e_perm = cpu_to_le16(acl->a_entries[i].e_perm); switch (acl->a_entries[i].e_tag) { case ACL_USER: entry->e_id = cpu_to_le32( from_kuid(&init_user_ns, acl->a_entries[i].e_uid)); entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry)); break; case ACL_GROUP: entry->e_id = cpu_to_le32( from_kgid(&init_user_ns, acl->a_entries[i].e_gid)); entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry)); break; case ACL_USER_OBJ: case ACL_GROUP_OBJ: case ACL_MASK: case ACL_OTHER: entry = (struct f2fs_acl_entry *)((char *)entry + sizeof(struct f2fs_acl_entry_short)); break; default: goto fail; } } *size = f2fs_acl_size(acl->a_count); return (void *)f2fs_acl; fail: kfree(f2fs_acl); return ERR_PTR(-EINVAL); } static struct posix_acl *__f2fs_get_acl(struct inode *inode, int type, struct folio *dfolio) { int name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT; void *value = NULL; struct posix_acl *acl; int retval; if (type == ACL_TYPE_ACCESS) name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; retval = f2fs_getxattr(inode, name_index, "", NULL, 0, dfolio); if (retval > 0) { value = f2fs_kmalloc(F2FS_I_SB(inode), retval, GFP_F2FS_ZERO); if (!value) return ERR_PTR(-ENOMEM); retval = f2fs_getxattr(inode, name_index, "", value, retval, dfolio); } if (retval > 0) acl = f2fs_acl_from_disk(value, retval); else if (retval == -ENODATA) acl = NULL; else acl = ERR_PTR(retval); kfree(value); return acl; } struct posix_acl *f2fs_get_acl(struct inode *inode, int type, bool rcu) { if (rcu) return ERR_PTR(-ECHILD); return __f2fs_get_acl(inode, type, NULL); } static int f2fs_acl_update_mode(struct mnt_idmap *idmap, struct inode *inode, umode_t *mode_p, struct posix_acl **acl) { umode_t mode = inode->i_mode; int error; if (is_inode_flag_set(inode, FI_ACL_MODE)) mode = F2FS_I(inode)->i_acl_mode; error = posix_acl_equiv_mode(*acl, &mode); if (error < 0) return error; if (error == 0) *acl = NULL; if (!in_group_or_capable(idmap, inode, i_gid_into_vfsgid(idmap, inode))) mode &= ~S_ISGID; *mode_p = mode; return 0; } static int __f2fs_set_acl(struct mnt_idmap *idmap, struct inode *inode, int type, struct posix_acl *acl, struct folio *ifolio) { int name_index; void *value = NULL; size_t size = 0; int error; umode_t mode = inode->i_mode; switch (type) { case ACL_TYPE_ACCESS: name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS; if (acl && !ifolio) { error = f2fs_acl_update_mode(idmap, inode, &mode, &acl); if (error) return error; set_acl_inode(inode, mode); } break; case ACL_TYPE_DEFAULT: name_index = F2FS_XATTR_INDEX_POSIX_ACL_DEFAULT; if (!S_ISDIR(inode->i_mode)) return acl ? -EACCES : 0; break; default: return -EINVAL; } if (acl) { value = f2fs_acl_to_disk(F2FS_I_SB(inode), acl, &size); if (IS_ERR(value)) { clear_inode_flag(inode, FI_ACL_MODE); return PTR_ERR(value); } } error = f2fs_setxattr(inode, name_index, "", value, size, ifolio, 0); kfree(value); if (!error) set_cached_acl(inode, type, acl); clear_inode_flag(inode, FI_ACL_MODE); return error; } int f2fs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type) { struct inode *inode = d_inode(dentry); if (unlikely(f2fs_cp_error(F2FS_I_SB(inode)))) return -EIO; return __f2fs_set_acl(idmap, inode, type, acl, NULL); } /* * Most part of f2fs_acl_clone, f2fs_acl_create_masq, f2fs_acl_create * are copied from posix_acl.c */ static struct posix_acl *f2fs_acl_clone(const struct posix_acl *acl, gfp_t flags) { struct posix_acl *clone = NULL; if (acl) { clone = kmemdup(acl, struct_size(acl, a_entries, acl->a_count), flags); if (clone) refcount_set(&clone->a_refcount, 1); } return clone; } static int f2fs_acl_create_masq(struct posix_acl *acl, umode_t *mode_p) { struct posix_acl_entry *pa, *pe; struct posix_acl_entry *group_obj = NULL, *mask_obj = NULL; umode_t mode = *mode_p; int not_equiv = 0; /* assert(atomic_read(acl->a_refcount) == 1); */ FOREACH_ACL_ENTRY(pa, acl, pe) { switch (pa->e_tag) { case ACL_USER_OBJ: pa->e_perm &= (mode >> 6) | ~S_IRWXO; mode &= (pa->e_perm << 6) | ~S_IRWXU; break; case ACL_USER: case ACL_GROUP: not_equiv = 1; break; case ACL_GROUP_OBJ: group_obj = pa; break; case ACL_OTHER: pa->e_perm &= mode | ~S_IRWXO; mode &= pa->e_perm | ~S_IRWXO; break; case ACL_MASK: mask_obj = pa; not_equiv = 1; break; default: return -EIO; } } if (mask_obj) { mask_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (mask_obj->e_perm << 3) | ~S_IRWXG; } else { if (!group_obj) return -EIO; group_obj->e_perm &= (mode >> 3) | ~S_IRWXO; mode &= (group_obj->e_perm << 3) | ~S_IRWXG; } *mode_p = (*mode_p & ~S_IRWXUGO) | mode; return not_equiv; } static int f2fs_acl_create(struct inode *dir, umode_t *mode, struct posix_acl **default_acl, struct posix_acl **acl, struct folio *dfolio) { struct posix_acl *p; struct posix_acl *clone; int ret; *acl = NULL; *default_acl = NULL; if (S_ISLNK(*mode) || !IS_POSIXACL(dir)) return 0; p = __f2fs_get_acl(dir, ACL_TYPE_DEFAULT, dfolio); if (!p || p == ERR_PTR(-EOPNOTSUPP)) { *mode &= ~current_umask(); return 0; } if (IS_ERR(p)) return PTR_ERR(p); clone = f2fs_acl_clone(p, GFP_NOFS); if (!clone) { ret = -ENOMEM; goto release_acl; } ret = f2fs_acl_create_masq(clone, mode); if (ret < 0) goto release_clone; if (ret == 0) posix_acl_release(clone); else *acl = clone; if (!S_ISDIR(*mode)) posix_acl_release(p); else *default_acl = p; return 0; release_clone: posix_acl_release(clone); release_acl: posix_acl_release(p); return ret; } int f2fs_init_acl(struct inode *inode, struct inode *dir, struct folio *ifolio, struct folio *dfolio) { struct posix_acl *default_acl = NULL, *acl = NULL; int error; error = f2fs_acl_create(dir, &inode->i_mode, &default_acl, &acl, dfolio); if (error) return error; f2fs_mark_inode_dirty_sync(inode, true); if (default_acl) { error = __f2fs_set_acl(NULL, inode, ACL_TYPE_DEFAULT, default_acl, ifolio); posix_acl_release(default_acl); } else { inode->i_default_acl = NULL; } if (acl) { if (!error) error = __f2fs_set_acl(NULL, inode, ACL_TYPE_ACCESS, acl, ifolio); posix_acl_release(acl); } else { inode->i_acl = NULL; } return error; } |
| 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_api.c Packet scheduler API. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: * * Rani Assaf <rani@magic.metawire.com> :980802: JIFFIES and CPU clock sources are repaired. * Eduardo J. Blanco <ejbs@netlabs.com.uy> :990222: kmod support * Jamal Hadi Salim <hadi@nortelnetworks.com>: 990601: ingress support */ #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/init.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/hrtimer.h> #include <linux/slab.h> #include <linux/hashtable.h> #include <linux/bpf.h> #include <net/netdev_lock.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <trace/events/qdisc.h> /* Short review. ------------- This file consists of two interrelated parts: 1. queueing disciplines manager frontend. 2. traffic classes manager frontend. Generally, queueing discipline ("qdisc") is a black box, which is able to enqueue packets and to dequeue them (when device is ready to send something) in order and at times determined by algorithm hidden in it. qdisc's are divided to two categories: - "queues", which have no internal structure visible from outside. - "schedulers", which split all the packets to "traffic classes", using "packet classifiers" (look at cls_api.c) In turn, classes may have child qdiscs (as rule, queues) attached to them etc. etc. etc. The goal of the routines in this file is to translate information supplied by user in the form of handles to more intelligible for kernel form, to make some sanity checks and part of work, which is common to all qdiscs and to provide rtnetlink notifications. All real intelligent work is done inside qdisc modules. Every discipline has two major routines: enqueue and dequeue. ---dequeue dequeue usually returns a skb to send. It is allowed to return NULL, but it does not mean that queue is empty, it just means that discipline does not want to send anything this time. Queue is really empty if q->q.qlen == 0. For complicated disciplines with multiple queues q->q is not real packet queue, but however q->q.qlen must be valid. ---enqueue enqueue returns 0, if packet was enqueued successfully. If packet (this one or another one) was dropped, it returns not zero error code. NET_XMIT_DROP - this packet dropped Expected action: do not backoff, but wait until queue will clear. NET_XMIT_CN - probably this packet enqueued, but another one dropped. Expected action: backoff or ignore Auxiliary routines: ---peek like dequeue but without removing a packet from the queue ---reset returns qdisc to initial state: purge all buffers, clear all timers, counters (except for statistics) etc. ---init initializes newly created qdisc. ---destroy destroys resources allocated by init and during lifetime of qdisc. ---change changes qdisc parameters. */ /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(qdisc_mod_lock); /************************************************ * Queueing disciplines manipulation. * ************************************************/ /* The list of all installed queueing disciplines. */ static struct Qdisc_ops *qdisc_base; /* Register/unregister queueing discipline */ int register_qdisc(struct Qdisc_ops *qops) { struct Qdisc_ops *q, **qp; int rc = -EEXIST; write_lock(&qdisc_mod_lock); for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next) if (!strcmp(qops->id, q->id)) goto out; if (qops->enqueue == NULL) qops->enqueue = noop_qdisc_ops.enqueue; if (qops->peek == NULL) { if (qops->dequeue == NULL) qops->peek = noop_qdisc_ops.peek; else goto out_einval; } if (qops->dequeue == NULL) qops->dequeue = noop_qdisc_ops.dequeue; if (qops->cl_ops) { const struct Qdisc_class_ops *cops = qops->cl_ops; if (!(cops->find && cops->walk && cops->leaf)) goto out_einval; if (cops->tcf_block && !(cops->bind_tcf && cops->unbind_tcf)) goto out_einval; } qops->next = NULL; *qp = qops; rc = 0; out: write_unlock(&qdisc_mod_lock); return rc; out_einval: rc = -EINVAL; goto out; } EXPORT_SYMBOL(register_qdisc); void unregister_qdisc(struct Qdisc_ops *qops) { struct Qdisc_ops *q, **qp; int err = -ENOENT; write_lock(&qdisc_mod_lock); for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next) if (q == qops) break; if (q) { *qp = q->next; q->next = NULL; err = 0; } write_unlock(&qdisc_mod_lock); WARN(err, "unregister qdisc(%s) failed\n", qops->id); } EXPORT_SYMBOL(unregister_qdisc); /* Get default qdisc if not otherwise specified */ void qdisc_get_default(char *name, size_t len) { read_lock(&qdisc_mod_lock); strscpy(name, default_qdisc_ops->id, len); read_unlock(&qdisc_mod_lock); } static struct Qdisc_ops *qdisc_lookup_default(const char *name) { struct Qdisc_ops *q = NULL; for (q = qdisc_base; q; q = q->next) { if (!strcmp(name, q->id)) { if (!bpf_try_module_get(q, q->owner)) q = NULL; break; } } return q; } /* Set new default qdisc to use */ int qdisc_set_default(const char *name) { const struct Qdisc_ops *ops; if (!capable(CAP_NET_ADMIN)) return -EPERM; write_lock(&qdisc_mod_lock); ops = qdisc_lookup_default(name); if (!ops) { /* Not found, drop lock and try to load module */ write_unlock(&qdisc_mod_lock); request_module(NET_SCH_ALIAS_PREFIX "%s", name); write_lock(&qdisc_mod_lock); ops = qdisc_lookup_default(name); } if (ops) { /* Set new default */ bpf_module_put(default_qdisc_ops, default_qdisc_ops->owner); default_qdisc_ops = ops; } write_unlock(&qdisc_mod_lock); return ops ? 0 : -ENOENT; } #ifdef CONFIG_NET_SCH_DEFAULT /* Set default value from kernel config */ static int __init sch_default_qdisc(void) { return qdisc_set_default(CONFIG_DEFAULT_NET_SCH); } late_initcall(sch_default_qdisc); #endif /* We know handle. Find qdisc among all qdisc's attached to device * (root qdisc, all its children, children of children etc.) * Note: caller either uses rtnl or rcu_read_lock() */ static struct Qdisc *qdisc_match_from_root(struct Qdisc *root, u32 handle) { struct Qdisc *q; if (!qdisc_dev(root)) return (root->handle == handle ? root : NULL); if (!(root->flags & TCQ_F_BUILTIN) && root->handle == handle) return root; hash_for_each_possible_rcu(qdisc_dev(root)->qdisc_hash, q, hash, handle, lockdep_rtnl_is_held()) { if (q->handle == handle) return q; } return NULL; } void qdisc_hash_add(struct Qdisc *q, bool invisible) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { ASSERT_RTNL(); hash_add_rcu(qdisc_dev(q)->qdisc_hash, &q->hash, q->handle); if (invisible) q->flags |= TCQ_F_INVISIBLE; } } EXPORT_SYMBOL(qdisc_hash_add); void qdisc_hash_del(struct Qdisc *q) { if ((q->parent != TC_H_ROOT) && !(q->flags & TCQ_F_INGRESS)) { ASSERT_RTNL(); hash_del_rcu(&q->hash); } } EXPORT_SYMBOL(qdisc_hash_del); struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle) { struct Qdisc *q; if (!handle) return NULL; q = qdisc_match_from_root(rtnl_dereference(dev->qdisc), handle); if (q) goto out; if (dev_ingress_queue(dev)) q = qdisc_match_from_root( rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping), handle); out: return q; } struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) { struct netdev_queue *nq; struct Qdisc *q; if (!handle) return NULL; q = qdisc_match_from_root(rcu_dereference(dev->qdisc), handle); if (q) goto out; nq = dev_ingress_queue_rcu(dev); if (nq) q = qdisc_match_from_root(rcu_dereference(nq->qdisc_sleeping), handle); out: return q; } static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid, struct netlink_ext_ack *extack) { unsigned long cl; const struct Qdisc_class_ops *cops = p->ops->cl_ops; if (cops == NULL) { NL_SET_ERR_MSG(extack, "Parent qdisc is not classful"); return ERR_PTR(-EOPNOTSUPP); } cl = cops->find(p, classid); if (cl == 0) { NL_SET_ERR_MSG(extack, "Specified class not found"); return ERR_PTR(-ENOENT); } return cops->leaf(p, cl); } /* Find queueing discipline by name */ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind) { struct Qdisc_ops *q = NULL; if (kind) { read_lock(&qdisc_mod_lock); for (q = qdisc_base; q; q = q->next) { if (nla_strcmp(kind, q->id) == 0) { if (!bpf_try_module_get(q, q->owner)) q = NULL; break; } } read_unlock(&qdisc_mod_lock); } return q; } /* The linklayer setting were not transferred from iproute2, in older * versions, and the rate tables lookup systems have been dropped in * the kernel. To keep backward compatible with older iproute2 tc * utils, we detect the linklayer setting by detecting if the rate * table were modified. * * For linklayer ATM table entries, the rate table will be aligned to * 48 bytes, thus some table entries will contain the same value. The * mpu (min packet unit) is also encoded into the old rate table, thus * starting from the mpu, we find low and high table entries for * mapping this cell. If these entries contain the same value, when * the rate tables have been modified for linklayer ATM. * * This is done by rounding mpu to the nearest 48 bytes cell/entry, * and then roundup to the next cell, calc the table entry one below, * and compare. */ static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) { int low = roundup(r->mpu, 48); int high = roundup(low+1, 48); int cell_low = low >> r->cell_log; int cell_high = (high >> r->cell_log) - 1; /* rtab is too inaccurate at rates > 100Mbit/s */ if ((r->rate > (100000000/8)) || (rtab[0] == 0)) { pr_debug("TC linklayer: Giving up ATM detection\n"); return TC_LINKLAYER_ETHERNET; } if ((cell_high > cell_low) && (cell_high < 256) && (rtab[cell_low] == rtab[cell_high])) { pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n", cell_low, cell_high, rtab[cell_high]); return TC_LINKLAYER_ATM; } return TC_LINKLAYER_ETHERNET; } static struct qdisc_rate_table *qdisc_rtab_list; struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab, struct netlink_ext_ack *extack) { struct qdisc_rate_table *rtab; if (tab == NULL || r->rate == 0 || r->cell_log == 0 || r->cell_log >= 32 || nla_len(tab) != TC_RTAB_SIZE) { NL_SET_ERR_MSG(extack, "Invalid rate table parameters for searching"); return NULL; } for (rtab = qdisc_rtab_list; rtab; rtab = rtab->next) { if (!memcmp(&rtab->rate, r, sizeof(struct tc_ratespec)) && !memcmp(&rtab->data, nla_data(tab), 1024)) { rtab->refcnt++; return rtab; } } rtab = kmalloc(sizeof(*rtab), GFP_KERNEL); if (rtab) { rtab->rate = *r; rtab->refcnt = 1; memcpy(rtab->data, nla_data(tab), 1024); if (r->linklayer == TC_LINKLAYER_UNAWARE) r->linklayer = __detect_linklayer(r, rtab->data); rtab->next = qdisc_rtab_list; qdisc_rtab_list = rtab; } else { NL_SET_ERR_MSG(extack, "Failed to allocate new qdisc rate table"); } return rtab; } EXPORT_SYMBOL(qdisc_get_rtab); void qdisc_put_rtab(struct qdisc_rate_table *tab) { struct qdisc_rate_table *rtab, **rtabp; if (!tab || --tab->refcnt) return; for (rtabp = &qdisc_rtab_list; (rtab = *rtabp) != NULL; rtabp = &rtab->next) { if (rtab == tab) { *rtabp = rtab->next; kfree(rtab); return; } } } EXPORT_SYMBOL(qdisc_put_rtab); static LIST_HEAD(qdisc_stab_list); static const struct nla_policy stab_policy[TCA_STAB_MAX + 1] = { [TCA_STAB_BASE] = { .len = sizeof(struct tc_sizespec) }, [TCA_STAB_DATA] = { .type = NLA_BINARY }, }; static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_STAB_MAX + 1]; struct qdisc_size_table *stab; struct tc_sizespec *s; unsigned int tsize = 0; u16 *tab = NULL; int err; err = nla_parse_nested_deprecated(tb, TCA_STAB_MAX, opt, stab_policy, extack); if (err < 0) return ERR_PTR(err); if (!tb[TCA_STAB_BASE]) { NL_SET_ERR_MSG(extack, "Size table base attribute is missing"); return ERR_PTR(-EINVAL); } s = nla_data(tb[TCA_STAB_BASE]); if (s->tsize > 0) { if (!tb[TCA_STAB_DATA]) { NL_SET_ERR_MSG(extack, "Size table data attribute is missing"); return ERR_PTR(-EINVAL); } tab = nla_data(tb[TCA_STAB_DATA]); tsize = nla_len(tb[TCA_STAB_DATA]) / sizeof(u16); } if (tsize != s->tsize || (!tab && tsize > 0)) { NL_SET_ERR_MSG(extack, "Invalid size of size table"); return ERR_PTR(-EINVAL); } list_for_each_entry(stab, &qdisc_stab_list, list) { if (memcmp(&stab->szopts, s, sizeof(*s))) continue; if (tsize > 0 && memcmp(stab->data, tab, flex_array_size(stab, data, tsize))) continue; stab->refcnt++; return stab; } if (s->size_log > STAB_SIZE_LOG_MAX || s->cell_log > STAB_SIZE_LOG_MAX) { NL_SET_ERR_MSG(extack, "Invalid logarithmic size of size table"); return ERR_PTR(-EINVAL); } stab = kmalloc(struct_size(stab, data, tsize), GFP_KERNEL); if (!stab) return ERR_PTR(-ENOMEM); stab->refcnt = 1; stab->szopts = *s; if (tsize > 0) memcpy(stab->data, tab, flex_array_size(stab, data, tsize)); list_add_tail(&stab->list, &qdisc_stab_list); return stab; } void qdisc_put_stab(struct qdisc_size_table *tab) { if (!tab) return; if (--tab->refcnt == 0) { list_del(&tab->list); kfree_rcu(tab, rcu); } } EXPORT_SYMBOL(qdisc_put_stab); static int qdisc_dump_stab(struct sk_buff *skb, struct qdisc_size_table *stab) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, TCA_STAB); if (nest == NULL) goto nla_put_failure; if (nla_put(skb, TCA_STAB_BASE, sizeof(stab->szopts), &stab->szopts)) goto nla_put_failure; nla_nest_end(skb, nest); return skb->len; nla_put_failure: return -1; } void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab) { int pkt_len, slot; pkt_len = skb->len + stab->szopts.overhead; if (unlikely(!stab->szopts.tsize)) goto out; slot = pkt_len + stab->szopts.cell_align; if (unlikely(slot < 0)) slot = 0; slot >>= stab->szopts.cell_log; if (likely(slot < stab->szopts.tsize)) pkt_len = stab->data[slot]; else pkt_len = stab->data[stab->szopts.tsize - 1] * (slot / stab->szopts.tsize) + stab->data[slot % stab->szopts.tsize]; pkt_len <<= stab->szopts.size_log; out: if (unlikely(pkt_len < 1)) pkt_len = 1; qdisc_skb_cb(skb)->pkt_len = pkt_len; } static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) { struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog, timer); rcu_read_lock(); __netif_schedule(qdisc_root(wd->qdisc)); rcu_read_unlock(); return HRTIMER_NORESTART; } void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc, clockid_t clockid) { hrtimer_setup(&wd->timer, qdisc_watchdog, clockid, HRTIMER_MODE_ABS_PINNED); wd->qdisc = qdisc; } EXPORT_SYMBOL(qdisc_watchdog_init_clockid); void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc) { qdisc_watchdog_init_clockid(wd, qdisc, CLOCK_MONOTONIC); } EXPORT_SYMBOL(qdisc_watchdog_init); void qdisc_watchdog_schedule_range_ns(struct qdisc_watchdog *wd, u64 expires, u64 delta_ns) { bool deactivated; rcu_read_lock(); deactivated = test_bit(__QDISC_STATE_DEACTIVATED, &qdisc_root_sleeping(wd->qdisc)->state); rcu_read_unlock(); if (deactivated) return; if (hrtimer_is_queued(&wd->timer)) { u64 softexpires; softexpires = ktime_to_ns(hrtimer_get_softexpires(&wd->timer)); /* If timer is already set in [expires, expires + delta_ns], * do not reprogram it. */ if (softexpires - expires <= delta_ns) return; } hrtimer_start_range_ns(&wd->timer, ns_to_ktime(expires), delta_ns, HRTIMER_MODE_ABS_PINNED); } EXPORT_SYMBOL(qdisc_watchdog_schedule_range_ns); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { hrtimer_cancel(&wd->timer); } EXPORT_SYMBOL(qdisc_watchdog_cancel); static struct hlist_head *qdisc_class_hash_alloc(unsigned int n) { struct hlist_head *h; unsigned int i; h = kvmalloc_array(n, sizeof(struct hlist_head), GFP_KERNEL); if (h != NULL) { for (i = 0; i < n; i++) INIT_HLIST_HEAD(&h[i]); } return h; } void qdisc_class_hash_grow(struct Qdisc *sch, struct Qdisc_class_hash *clhash) { struct Qdisc_class_common *cl; struct hlist_node *next; struct hlist_head *nhash, *ohash; unsigned int nsize, nmask, osize; unsigned int i, h; /* Rehash when load factor exceeds 0.75 */ if (clhash->hashelems * 4 <= clhash->hashsize * 3) return; nsize = clhash->hashsize * 2; nmask = nsize - 1; nhash = qdisc_class_hash_alloc(nsize); if (nhash == NULL) return; ohash = clhash->hash; osize = clhash->hashsize; sch_tree_lock(sch); for (i = 0; i < osize; i++) { hlist_for_each_entry_safe(cl, next, &ohash[i], hnode) { h = qdisc_class_hash(cl->classid, nmask); hlist_add_head(&cl->hnode, &nhash[h]); } } clhash->hash = nhash; clhash->hashsize = nsize; clhash->hashmask = nmask; sch_tree_unlock(sch); kvfree(ohash); } EXPORT_SYMBOL(qdisc_class_hash_grow); int qdisc_class_hash_init(struct Qdisc_class_hash *clhash) { unsigned int size = 4; clhash->hash = qdisc_class_hash_alloc(size); if (!clhash->hash) return -ENOMEM; clhash->hashsize = size; clhash->hashmask = size - 1; clhash->hashelems = 0; return 0; } EXPORT_SYMBOL(qdisc_class_hash_init); void qdisc_class_hash_destroy(struct Qdisc_class_hash *clhash) { kvfree(clhash->hash); } EXPORT_SYMBOL(qdisc_class_hash_destroy); void qdisc_class_hash_insert(struct Qdisc_class_hash *clhash, struct Qdisc_class_common *cl) { unsigned int h; INIT_HLIST_NODE(&cl->hnode); h = qdisc_class_hash(cl->classid, clhash->hashmask); hlist_add_head(&cl->hnode, &clhash->hash[h]); clhash->hashelems++; } EXPORT_SYMBOL(qdisc_class_hash_insert); void qdisc_class_hash_remove(struct Qdisc_class_hash *clhash, struct Qdisc_class_common *cl) { hlist_del(&cl->hnode); clhash->hashelems--; } EXPORT_SYMBOL(qdisc_class_hash_remove); /* Allocate an unique handle from space managed by kernel * Possible range is [8000-FFFF]:0000 (0x8000 values) */ static u32 qdisc_alloc_handle(struct net_device *dev) { int i = 0x8000; static u32 autohandle = TC_H_MAKE(0x80000000U, 0); do { autohandle += TC_H_MAKE(0x10000U, 0); if (autohandle == TC_H_MAKE(TC_H_ROOT, 0)) autohandle = TC_H_MAKE(0x80000000U, 0); if (!qdisc_lookup(dev, autohandle)) return autohandle; cond_resched(); } while (--i > 0); return 0; } void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) { const struct Qdisc_class_ops *cops; unsigned long cl; u32 parentid; bool notify; int drops; drops = max_t(int, n, 0); rcu_read_lock(); while ((parentid = sch->parent)) { if (parentid == TC_H_ROOT) break; if (sch->flags & TCQ_F_NOPARENT) break; /* Notify parent qdisc only if child qdisc becomes empty. */ notify = !sch->q.qlen; /* TODO: perform the search on a per txq basis */ sch = qdisc_lookup_rcu(qdisc_dev(sch), TC_H_MAJ(parentid)); if (sch == NULL) { WARN_ON_ONCE(parentid != TC_H_ROOT); break; } cops = sch->ops->cl_ops; if (notify && cops->qlen_notify) { /* Note that qlen_notify must be idempotent as it may get called * multiple times. */ cl = cops->find(sch, parentid); cops->qlen_notify(sch, cl); } sch->q.qlen -= n; sch->qstats.backlog -= len; __qdisc_qstats_drop(sch, drops); } rcu_read_unlock(); } EXPORT_SYMBOL(qdisc_tree_reduce_backlog); int qdisc_offload_dump_helper(struct Qdisc *sch, enum tc_setup_type type, void *type_data) { struct net_device *dev = qdisc_dev(sch); int err; sch->flags &= ~TCQ_F_OFFLOADED; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return 0; err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); if (err == -EOPNOTSUPP) return 0; if (!err) sch->flags |= TCQ_F_OFFLOADED; return err; } EXPORT_SYMBOL(qdisc_offload_dump_helper); void qdisc_offload_graft_helper(struct net_device *dev, struct Qdisc *sch, struct Qdisc *new, struct Qdisc *old, enum tc_setup_type type, void *type_data, struct netlink_ext_ack *extack) { bool any_qdisc_is_offloaded; int err; if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc) return; err = dev->netdev_ops->ndo_setup_tc(dev, type, type_data); /* Don't report error if the graft is part of destroy operation. */ if (!err || !new || new == &noop_qdisc) return; /* Don't report error if the parent, the old child and the new * one are not offloaded. */ any_qdisc_is_offloaded = new->flags & TCQ_F_OFFLOADED; any_qdisc_is_offloaded |= sch && sch->flags & TCQ_F_OFFLOADED; any_qdisc_is_offloaded |= old && old->flags & TCQ_F_OFFLOADED; if (any_qdisc_is_offloaded) NL_SET_ERR_MSG(extack, "Offloading graft operation failed."); } EXPORT_SYMBOL(qdisc_offload_graft_helper); void qdisc_offload_query_caps(struct net_device *dev, enum tc_setup_type type, void *caps, size_t caps_len) { const struct net_device_ops *ops = dev->netdev_ops; struct tc_query_caps_base base = { .type = type, .caps = caps, }; memset(caps, 0, caps_len); if (ops->ndo_setup_tc) ops->ndo_setup_tc(dev, TC_QUERY_CAPS, &base); } EXPORT_SYMBOL(qdisc_offload_query_caps); static void qdisc_offload_graft_root(struct net_device *dev, struct Qdisc *new, struct Qdisc *old, struct netlink_ext_ack *extack) { struct tc_root_qopt_offload graft_offload = { .command = TC_ROOT_GRAFT, .handle = new ? new->handle : 0, .ingress = (new && new->flags & TCQ_F_INGRESS) || (old && old->flags & TCQ_F_INGRESS), }; qdisc_offload_graft_helper(dev, NULL, new, old, TC_SETUP_ROOT_QDISC, &graft_offload, extack); } static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, u32 portid, u32 seq, u16 flags, int event, struct netlink_ext_ack *extack) { struct gnet_stats_basic_sync __percpu *cpu_bstats = NULL; struct gnet_stats_queue __percpu *cpu_qstats = NULL; struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct gnet_dump d; struct qdisc_size_table *stab; u32 block_index; __u32 qlen; cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; tcm = nlmsg_data(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; tcm->tcm_ifindex = qdisc_dev(q)->ifindex; tcm->tcm_parent = clid; tcm->tcm_handle = q->handle; tcm->tcm_info = refcount_read(&q->refcnt); if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; if (q->ops->ingress_block_get) { block_index = q->ops->ingress_block_get(q); if (block_index && nla_put_u32(skb, TCA_INGRESS_BLOCK, block_index)) goto nla_put_failure; } if (q->ops->egress_block_get) { block_index = q->ops->egress_block_get(q); if (block_index && nla_put_u32(skb, TCA_EGRESS_BLOCK, block_index)) goto nla_put_failure; } if (q->ops->dump && q->ops->dump(q, skb) < 0) goto nla_put_failure; if (nla_put_u8(skb, TCA_HW_OFFLOAD, !!(q->flags & TCQ_F_OFFLOADED))) goto nla_put_failure; qlen = qdisc_qlen_sum(q); stab = rtnl_dereference(q->stab); if (stab && qdisc_dump_stab(skb, stab) < 0) goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, NULL, &d, TCA_PAD) < 0) goto nla_put_failure; if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0) goto nla_put_failure; if (qdisc_is_percpu_stats(q)) { cpu_bstats = q->cpu_bstats; cpu_qstats = q->cpu_qstats; } if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats, true) < 0 || gnet_stats_copy_rate_est(&d, &q->rate_est) < 0 || gnet_stats_copy_queue(&d, cpu_qstats, &q->qstats, qlen) < 0) goto nla_put_failure; if (gnet_stats_finish_copy(&d) < 0) goto nla_put_failure; if (extack && extack->_msg && nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) goto out_nlmsg_trim; nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; out_nlmsg_trim: nla_put_failure: nlmsg_trim(skb, b); return -1; } static bool tc_qdisc_dump_ignore(struct Qdisc *q, bool dump_invisible) { if (q->flags & TCQ_F_BUILTIN) return true; if ((q->flags & TCQ_F_INVISIBLE) && !dump_invisible) return true; return false; } static int qdisc_get_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, u32 clid, struct Qdisc *q, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (!tc_qdisc_dump_ignore(q, false)) { if (tc_fill_qdisc(skb, q, clid, portid, n->nlmsg_seq, 0, RTM_NEWQDISC, extack) < 0) goto err_out; } if (skb->len) return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); err_out: kfree_skb(skb); return -EINVAL; } static int qdisc_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, u32 clid, struct Qdisc *old, struct Qdisc *new, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) return 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (old && !tc_qdisc_dump_ignore(old, false)) { if (tc_fill_qdisc(skb, old, clid, portid, n->nlmsg_seq, 0, RTM_DELQDISC, extack) < 0) goto err_out; } if (new && !tc_qdisc_dump_ignore(new, false)) { if (tc_fill_qdisc(skb, new, clid, portid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC, extack) < 0) goto err_out; } if (skb->len) return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); err_out: kfree_skb(skb); return -EINVAL; } static void notify_and_destroy(struct net *net, struct sk_buff *skb, struct nlmsghdr *n, u32 clid, struct Qdisc *old, struct Qdisc *new, struct netlink_ext_ack *extack) { if (new || old) qdisc_notify(net, skb, n, clid, old, new, extack); if (old) qdisc_put(old); } static void qdisc_clear_nolock(struct Qdisc *sch) { sch->flags &= ~TCQ_F_NOLOCK; if (!(sch->flags & TCQ_F_CPUSTATS)) return; free_percpu(sch->cpu_bstats); free_percpu(sch->cpu_qstats); sch->cpu_bstats = NULL; sch->cpu_qstats = NULL; sch->flags &= ~TCQ_F_CPUSTATS; } /* Graft qdisc "new" to class "classid" of qdisc "parent" or * to device "dev". * * When appropriate send a netlink notification using 'skb' * and "n". * * On success, destroy old qdisc. */ static int qdisc_graft(struct net_device *dev, struct Qdisc *parent, struct sk_buff *skb, struct nlmsghdr *n, u32 classid, struct Qdisc *new, struct Qdisc *old, struct netlink_ext_ack *extack) { struct Qdisc *q = old; struct net *net = dev_net(dev); if (parent == NULL) { unsigned int i, num_q, ingress; struct netdev_queue *dev_queue; ingress = 0; num_q = dev->num_tx_queues; if ((q && q->flags & TCQ_F_INGRESS) || (new && new->flags & TCQ_F_INGRESS)) { ingress = 1; dev_queue = dev_ingress_queue(dev); if (!dev_queue) { NL_SET_ERR_MSG(extack, "Device does not have an ingress queue"); return -ENOENT; } q = rtnl_dereference(dev_queue->qdisc_sleeping); /* This is the counterpart of that qdisc_refcount_inc_nz() call in * __tcf_qdisc_find() for filter requests. */ if (!qdisc_refcount_dec_if_one(q)) { NL_SET_ERR_MSG(extack, "Current ingress or clsact Qdisc has ongoing filter requests"); return -EBUSY; } } if (dev->flags & IFF_UP) dev_deactivate(dev); qdisc_offload_graft_root(dev, new, old, extack); if (new && new->ops->attach && !ingress) goto skip; if (!ingress) { for (i = 0; i < num_q; i++) { dev_queue = netdev_get_tx_queue(dev, i); old = dev_graft_qdisc(dev_queue, new); if (new && i > 0) qdisc_refcount_inc(new); qdisc_put(old); } } else { old = dev_graft_qdisc(dev_queue, NULL); /* {ingress,clsact}_destroy() @old before grafting @new to avoid * unprotected concurrent accesses to net_device::miniq_{in,e}gress * pointer(s) in mini_qdisc_pair_swap(). */ qdisc_notify(net, skb, n, classid, old, new, extack); qdisc_destroy(old); dev_graft_qdisc(dev_queue, new); } skip: if (!ingress) { old = rtnl_dereference(dev->qdisc); if (new && !new->ops->attach) qdisc_refcount_inc(new); rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); notify_and_destroy(net, skb, n, classid, old, new, extack); if (new && new->ops->attach) new->ops->attach(new); } if (dev->flags & IFF_UP) dev_activate(dev); } else { const struct Qdisc_class_ops *cops = parent->ops->cl_ops; unsigned long cl; int err; /* Only support running class lockless if parent is lockless */ if (new && (new->flags & TCQ_F_NOLOCK) && !(parent->flags & TCQ_F_NOLOCK)) qdisc_clear_nolock(new); if (!cops || !cops->graft) return -EOPNOTSUPP; cl = cops->find(parent, classid); if (!cl) { NL_SET_ERR_MSG(extack, "Specified class not found"); return -ENOENT; } if (new && new->ops == &noqueue_qdisc_ops) { NL_SET_ERR_MSG(extack, "Cannot assign noqueue to a class"); return -EINVAL; } if (new && !(parent->flags & TCQ_F_MQROOT) && rcu_access_pointer(new->stab)) { NL_SET_ERR_MSG(extack, "STAB not supported on a non root"); return -EINVAL; } err = cops->graft(parent, cl, new, &old, extack); if (err) return err; notify_and_destroy(net, skb, n, classid, old, new, extack); } return 0; } static int qdisc_block_indexes_set(struct Qdisc *sch, struct nlattr **tca, struct netlink_ext_ack *extack) { u32 block_index; if (tca[TCA_INGRESS_BLOCK]) { block_index = nla_get_u32(tca[TCA_INGRESS_BLOCK]); if (!block_index) { NL_SET_ERR_MSG(extack, "Ingress block index cannot be 0"); return -EINVAL; } if (!sch->ops->ingress_block_set) { NL_SET_ERR_MSG(extack, "Ingress block sharing is not supported"); return -EOPNOTSUPP; } sch->ops->ingress_block_set(sch, block_index); } if (tca[TCA_EGRESS_BLOCK]) { block_index = nla_get_u32(tca[TCA_EGRESS_BLOCK]); if (!block_index) { NL_SET_ERR_MSG(extack, "Egress block index cannot be 0"); return -EINVAL; } if (!sch->ops->egress_block_set) { NL_SET_ERR_MSG(extack, "Egress block sharing is not supported"); return -EOPNOTSUPP; } sch->ops->egress_block_set(sch, block_index); } return 0; } /* Allocate and initialize new qdisc. Parameters are passed via opt. */ static struct Qdisc *qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, u32 parent, u32 handle, struct nlattr **tca, int *errp, struct netlink_ext_ack *extack) { int err; struct nlattr *kind = tca[TCA_KIND]; struct Qdisc *sch; struct Qdisc_ops *ops; struct qdisc_size_table *stab; ops = qdisc_lookup_ops(kind); if (!ops) { err = -ENOENT; NL_SET_ERR_MSG(extack, "Specified qdisc kind is unknown"); goto err_out; } sch = qdisc_alloc(dev_queue, ops, extack); if (IS_ERR(sch)) { err = PTR_ERR(sch); goto err_out2; } sch->parent = parent; if (handle == TC_H_INGRESS) { if (!(sch->flags & TCQ_F_INGRESS)) { NL_SET_ERR_MSG(extack, "Specified parent ID is reserved for ingress and clsact Qdiscs"); err = -EINVAL; goto err_out3; } handle = TC_H_MAKE(TC_H_INGRESS, 0); } else { if (handle == 0) { handle = qdisc_alloc_handle(dev); if (handle == 0) { NL_SET_ERR_MSG(extack, "Maximum number of qdisc handles was exceeded"); err = -ENOSPC; goto err_out3; } } if (!netif_is_multiqueue(dev)) sch->flags |= TCQ_F_ONETXQUEUE; } sch->handle = handle; /* This exist to keep backward compatible with a userspace * loophole, what allowed userspace to get IFF_NO_QUEUE * facility on older kernels by setting tx_queue_len=0 (prior * to qdisc init), and then forgot to reinit tx_queue_len * before again attaching a qdisc. */ if ((dev->priv_flags & IFF_NO_QUEUE) && (dev->tx_queue_len == 0)) { WRITE_ONCE(dev->tx_queue_len, DEFAULT_TX_QUEUE_LEN); netdev_info(dev, "Caught tx_queue_len zero misconfig\n"); } err = qdisc_block_indexes_set(sch, tca, extack); if (err) goto err_out3; if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) { err = PTR_ERR(stab); goto err_out3; } rcu_assign_pointer(sch->stab, stab); } if (ops->init) { err = ops->init(sch, tca[TCA_OPTIONS], extack); if (err != 0) goto err_out4; } if (tca[TCA_RATE]) { err = -EOPNOTSUPP; if (sch->flags & TCQ_F_MQROOT) { NL_SET_ERR_MSG(extack, "Cannot attach rate estimator to a multi-queue root qdisc"); goto err_out4; } err = gen_new_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, NULL, true, tca[TCA_RATE]); if (err) { NL_SET_ERR_MSG(extack, "Failed to generate new estimator"); goto err_out4; } } qdisc_hash_add(sch, false); trace_qdisc_create(ops, dev, parent); return sch; err_out4: /* Even if ops->init() failed, we call ops->destroy() * like qdisc_create_dflt(). */ if (ops->destroy) ops->destroy(sch); qdisc_put_stab(rtnl_dereference(sch->stab)); err_out3: lockdep_unregister_key(&sch->root_lock_key); netdev_put(dev, &sch->dev_tracker); qdisc_free(sch); err_out2: bpf_module_put(ops, ops->owner); err_out: *errp = err; return NULL; } static int qdisc_change(struct Qdisc *sch, struct nlattr **tca, struct netlink_ext_ack *extack) { struct qdisc_size_table *ostab, *stab = NULL; int err = 0; if (tca[TCA_OPTIONS]) { if (!sch->ops->change) { NL_SET_ERR_MSG(extack, "Change operation not supported by specified qdisc"); return -EINVAL; } if (tca[TCA_INGRESS_BLOCK] || tca[TCA_EGRESS_BLOCK]) { NL_SET_ERR_MSG(extack, "Change of blocks is not supported"); return -EOPNOTSUPP; } err = sch->ops->change(sch, tca[TCA_OPTIONS], extack); if (err) return err; } if (tca[TCA_STAB]) { stab = qdisc_get_stab(tca[TCA_STAB], extack); if (IS_ERR(stab)) return PTR_ERR(stab); } ostab = rtnl_dereference(sch->stab); rcu_assign_pointer(sch->stab, stab); qdisc_put_stab(ostab); if (tca[TCA_RATE]) { /* NB: ignores errors from replace_estimator because change can't be undone. */ if (sch->flags & TCQ_F_MQROOT) goto out; gen_replace_estimator(&sch->bstats, sch->cpu_bstats, &sch->rate_est, NULL, true, tca[TCA_RATE]); } out: return 0; } struct check_loop_arg { struct qdisc_walker w; struct Qdisc *p; int depth; }; static int check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w); static int check_loop(struct Qdisc *q, struct Qdisc *p, int depth) { struct check_loop_arg arg; if (q->ops->cl_ops == NULL) return 0; arg.w.stop = arg.w.skip = arg.w.count = 0; arg.w.fn = check_loop_fn; arg.depth = depth; arg.p = p; q->ops->cl_ops->walk(q, &arg.w); return arg.w.stop ? -ELOOP : 0; } static int check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) { struct Qdisc *leaf; const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct check_loop_arg *arg = (struct check_loop_arg *)w; leaf = cops->leaf(q, cl); if (leaf) { if (leaf == arg->p || arg->depth > 7) return -ELOOP; return check_loop(leaf, arg->p, arg->depth + 1); } return 0; } const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = { [TCA_KIND] = { .type = NLA_STRING }, [TCA_RATE] = { .type = NLA_BINARY, .len = sizeof(struct tc_estimator) }, [TCA_STAB] = { .type = NLA_NESTED }, [TCA_DUMP_INVISIBLE] = { .type = NLA_FLAG }, [TCA_CHAIN] = { .type = NLA_U32 }, [TCA_INGRESS_BLOCK] = { .type = NLA_U32 }, [TCA_EGRESS_BLOCK] = { .type = NLA_U32 }, }; /* * Delete/get qdisc. */ static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack, struct net_device *dev, struct nlattr *tca[TCA_MAX + 1], struct tcmsg *tcm) { struct net *net = sock_net(skb->sk); struct Qdisc *q = NULL; struct Qdisc *p = NULL; u32 clid; int err; clid = tcm->tcm_parent; if (clid) { if (clid != TC_H_ROOT) { if (TC_H_MAJ(clid) != TC_H_MAJ(TC_H_INGRESS)) { p = qdisc_lookup(dev, TC_H_MAJ(clid)); if (!p) { NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid"); return -ENOENT; } q = qdisc_leaf(p, clid, extack); } else if (dev_ingress_queue(dev)) { q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { q = rtnl_dereference(dev->qdisc); } if (!q) { NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); return -ENOENT; } if (IS_ERR(q)) return PTR_ERR(q); if (tcm->tcm_handle && q->handle != tcm->tcm_handle) { NL_SET_ERR_MSG(extack, "Invalid handle"); return -EINVAL; } } else { q = qdisc_lookup(dev, tcm->tcm_handle); if (!q) { NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified handle"); return -ENOENT; } } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; } if (n->nlmsg_type == RTM_DELQDISC) { if (!clid) { NL_SET_ERR_MSG(extack, "Classid cannot be zero"); return -EINVAL; } if (q->handle == 0) { NL_SET_ERR_MSG(extack, "Cannot delete qdisc with handle of zero"); return -ENOENT; } err = qdisc_graft(dev, p, skb, n, clid, NULL, q, extack); if (err != 0) return err; } else { qdisc_get_notify(net, skb, n, clid, q, NULL); } return 0; } static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct tcmsg *tcm = nlmsg_data(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; int err; err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) return err; dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; netdev_lock_ops(dev); err = __tc_get_qdisc(skb, n, extack, dev, tca, tcm); netdev_unlock_ops(dev); return err; } static bool req_create_or_replace(struct nlmsghdr *n) { return (n->nlmsg_flags & NLM_F_CREATE && n->nlmsg_flags & NLM_F_REPLACE); } static bool req_create_exclusive(struct nlmsghdr *n) { return (n->nlmsg_flags & NLM_F_CREATE && n->nlmsg_flags & NLM_F_EXCL); } static bool req_change(struct nlmsghdr *n) { return (!(n->nlmsg_flags & NLM_F_CREATE) && !(n->nlmsg_flags & NLM_F_REPLACE) && !(n->nlmsg_flags & NLM_F_EXCL)); } static int __tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack, struct net_device *dev, struct nlattr *tca[TCA_MAX + 1], struct tcmsg *tcm) { struct Qdisc *q = NULL; struct Qdisc *p = NULL; u32 clid; int err; clid = tcm->tcm_parent; if (clid) { if (clid != TC_H_ROOT) { if (clid != TC_H_INGRESS) { p = qdisc_lookup(dev, TC_H_MAJ(clid)); if (!p) { NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; } q = qdisc_leaf(p, clid, extack); if (IS_ERR(q)) return PTR_ERR(q); } else if (dev_ingress_queue_create(dev)) { q = rtnl_dereference(dev_ingress_queue(dev)->qdisc_sleeping); } } else { q = rtnl_dereference(dev->qdisc); } /* It may be default qdisc, ignore it */ if (q && q->handle == 0) q = NULL; if (!q || !tcm->tcm_handle || q->handle != tcm->tcm_handle) { if (tcm->tcm_handle) { if (q && !(n->nlmsg_flags & NLM_F_REPLACE)) { NL_SET_ERR_MSG(extack, "NLM_F_REPLACE needed to override"); return -EEXIST; } if (TC_H_MIN(tcm->tcm_handle)) { NL_SET_ERR_MSG(extack, "Invalid minor handle"); return -EINVAL; } q = qdisc_lookup(dev, tcm->tcm_handle); if (!q) goto create_n_graft; if (q->parent != tcm->tcm_parent) { NL_SET_ERR_MSG(extack, "Cannot move an existing qdisc to a different parent"); return -EINVAL; } if (n->nlmsg_flags & NLM_F_EXCL) { NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot override"); return -EEXIST; } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; } if (q->flags & TCQ_F_INGRESS) { NL_SET_ERR_MSG(extack, "Cannot regraft ingress or clsact Qdiscs"); return -EINVAL; } if (q == p || (p && check_loop(q, p, 0))) { NL_SET_ERR_MSG(extack, "Qdisc parent/child loop detected"); return -ELOOP; } if (clid == TC_H_INGRESS) { NL_SET_ERR_MSG(extack, "Ingress cannot graft directly"); return -EINVAL; } qdisc_refcount_inc(q); goto graft; } else { if (!q) goto create_n_graft; /* This magic test requires explanation. * * We know, that some child q is already * attached to this parent and have choice: * 1) change it or 2) create/graft new one. * If the requested qdisc kind is different * than the existing one, then we choose graft. * If they are the same then this is "change" * operation - just let it fallthrough.. * * 1. We are allowed to create/graft only * if the request is explicitly stating * "please create if it doesn't exist". * * 2. If the request is to exclusive create * then the qdisc tcm_handle is not expected * to exist, so that we choose create/graft too. * * 3. The last case is when no flags are set. * This will happen when for example tc * utility issues a "change" command. * Alas, it is sort of hole in API, we * cannot decide what to do unambiguously. * For now we select create/graft. */ if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { if (req_create_or_replace(n) || req_create_exclusive(n)) goto create_n_graft; else if (req_change(n)) goto create_n_graft2; } } } } else { if (!tcm->tcm_handle) { NL_SET_ERR_MSG(extack, "Handle cannot be zero"); return -EINVAL; } q = qdisc_lookup(dev, tcm->tcm_handle); } /* Change qdisc parameters */ if (!q) { NL_SET_ERR_MSG(extack, "Specified qdisc not found"); return -ENOENT; } if (n->nlmsg_flags & NLM_F_EXCL) { NL_SET_ERR_MSG(extack, "Exclusivity flag on, cannot modify"); return -EEXIST; } if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) { NL_SET_ERR_MSG(extack, "Invalid qdisc name: must match existing qdisc"); return -EINVAL; } err = qdisc_change(q, tca, extack); if (err == 0) qdisc_notify(sock_net(skb->sk), skb, n, clid, NULL, q, extack); return err; create_n_graft: if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Qdisc not found. To create specify NLM_F_CREATE flag"); return -ENOENT; } create_n_graft2: if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) { q = qdisc_create(dev, dev_ingress_queue(dev), tcm->tcm_parent, tcm->tcm_parent, tca, &err, extack); } else { NL_SET_ERR_MSG(extack, "Cannot find ingress queue for specified device"); err = -ENOENT; } } else { struct netdev_queue *dev_queue; if (p && p->ops->cl_ops && p->ops->cl_ops->select_queue) dev_queue = p->ops->cl_ops->select_queue(p, tcm); else if (p) dev_queue = p->dev_queue; else dev_queue = netdev_get_tx_queue(dev, 0); q = qdisc_create(dev, dev_queue, tcm->tcm_parent, tcm->tcm_handle, tca, &err, extack); } if (!q) return err; graft: err = qdisc_graft(dev, p, skb, n, clid, q, NULL, extack); if (err) { if (q) qdisc_put(q); return err; } return 0; } static void request_qdisc_module(struct nlattr *kind) { struct Qdisc_ops *ops; char name[IFNAMSIZ]; if (!kind) return; ops = qdisc_lookup_ops(kind); if (ops) { bpf_module_put(ops, ops->owner); return; } if (nla_strscpy(name, kind, IFNAMSIZ) >= 0) { rtnl_unlock(); request_module(NET_SCH_ALIAS_PREFIX "%s", name); rtnl_lock(); } } /* * Create/change qdisc. */ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; struct tcmsg *tcm; int err; err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) return err; request_qdisc_module(tca[TCA_KIND]); tcm = nlmsg_data(n); dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; netdev_lock_ops(dev); err = __tc_modify_qdisc(skb, n, extack, dev, tca, tcm); netdev_unlock_ops(dev); return err; } static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, struct netlink_callback *cb, int *q_idx_p, int s_q_idx, bool recur, bool dump_invisible) { int ret = 0, q_idx = *q_idx_p; struct Qdisc *q; int b; if (!root) return 0; q = root; if (q_idx < s_q_idx) { q_idx++; } else { if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC, NULL) <= 0) goto done; q_idx++; } /* If dumping singletons, there is no qdisc_dev(root) and the singleton * itself has already been dumped. * * If we've already dumped the top-level (ingress) qdisc above and the global * qdisc hashtable, we don't want to hit it again */ if (!qdisc_dev(root) || !recur) goto out; hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) { if (q_idx < s_q_idx) { q_idx++; continue; } if (!tc_qdisc_dump_ignore(q, dump_invisible) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC, NULL) <= 0) goto done; q_idx++; } out: *q_idx_p = q_idx; return ret; done: ret = -1; goto out; } static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); int idx, q_idx; int s_idx, s_q_idx; struct net_device *dev; const struct nlmsghdr *nlh = cb->nlh; struct nlattr *tca[TCA_MAX + 1]; int err; s_idx = cb->args[0]; s_q_idx = q_idx = cb->args[1]; idx = 0; ASSERT_RTNL(); err = nlmsg_parse_deprecated(nlh, sizeof(struct tcmsg), tca, TCA_MAX, rtm_tca_policy, cb->extack); if (err < 0) return err; for_each_netdev(net, dev) { struct netdev_queue *dev_queue; if (idx < s_idx) goto cont; if (idx > s_idx) s_q_idx = 0; q_idx = 0; netdev_lock_ops(dev); if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc), skb, cb, &q_idx, s_q_idx, true, tca[TCA_DUMP_INVISIBLE]) < 0) { netdev_unlock_ops(dev); goto done; } dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_qdisc_root(rtnl_dereference(dev_queue->qdisc_sleeping), skb, cb, &q_idx, s_q_idx, false, tca[TCA_DUMP_INVISIBLE]) < 0) { netdev_unlock_ops(dev); goto done; } netdev_unlock_ops(dev); cont: idx++; } done: cb->args[0] = idx; cb->args[1] = q_idx; return skb->len; } /************************************************ * Traffic classes manipulation. * ************************************************/ static int tc_fill_tclass(struct sk_buff *skb, struct Qdisc *q, unsigned long cl, u32 portid, u32 seq, u16 flags, int event, struct netlink_ext_ack *extack) { struct tcmsg *tcm; struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct gnet_dump d; const struct Qdisc_class_ops *cl_ops = q->ops->cl_ops; cond_resched(); nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) goto out_nlmsg_trim; tcm = nlmsg_data(nlh); tcm->tcm_family = AF_UNSPEC; tcm->tcm__pad1 = 0; tcm->tcm__pad2 = 0; tcm->tcm_ifindex = qdisc_dev(q)->ifindex; tcm->tcm_parent = q->handle; tcm->tcm_handle = q->handle; tcm->tcm_info = 0; if (nla_put_string(skb, TCA_KIND, q->ops->id)) goto nla_put_failure; if (cl_ops->dump && cl_ops->dump(q, cl, skb, tcm) < 0) goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, NULL, &d, TCA_PAD) < 0) goto nla_put_failure; if (cl_ops->dump_stats && cl_ops->dump_stats(q, cl, &d) < 0) goto nla_put_failure; if (gnet_stats_finish_copy(&d) < 0) goto nla_put_failure; if (extack && extack->_msg && nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) goto out_nlmsg_trim; nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; out_nlmsg_trim: nla_put_failure: nlmsg_trim(skb, b); return -1; } static int tclass_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct Qdisc *q, unsigned long cl, int event, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; if (!rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) return 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, event, extack) < 0) { kfree_skb(skb); return -EINVAL; } return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); } static int tclass_get_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct Qdisc *q, unsigned long cl, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, RTM_NEWTCLASS, extack) < 0) { kfree_skb(skb); return -EINVAL; } return rtnetlink_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); } static int tclass_del_notify(struct net *net, const struct Qdisc_class_ops *cops, struct sk_buff *oskb, struct nlmsghdr *n, struct Qdisc *q, unsigned long cl, struct netlink_ext_ack *extack) { u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; struct sk_buff *skb; int err = 0; if (!cops->delete) return -EOPNOTSUPP; if (rtnl_notify_needed(net, n->nlmsg_flags, RTNLGRP_TC)) { skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return -ENOBUFS; if (tc_fill_tclass(skb, q, cl, portid, n->nlmsg_seq, 0, RTM_DELTCLASS, extack) < 0) { kfree_skb(skb); return -EINVAL; } } else { skb = NULL; } err = cops->delete(q, cl, extack); if (err) { kfree_skb(skb); return err; } err = rtnetlink_maybe_send(skb, net, portid, RTNLGRP_TC, n->nlmsg_flags & NLM_F_ECHO); return err; } #ifdef CONFIG_NET_CLS struct tcf_bind_args { struct tcf_walker w; unsigned long base; unsigned long cl; u32 classid; }; static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) { struct tcf_bind_args *a = (void *)arg; if (n && tp->ops->bind_class) { struct Qdisc *q = tcf_block_q(tp->chain->block); sch_tree_lock(q); tp->ops->bind_class(n, a->classid, a->cl, q, a->base); sch_tree_unlock(q); } return 0; } struct tc_bind_class_args { struct qdisc_walker w; unsigned long new_cl; u32 portid; u32 clid; }; static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) { struct tc_bind_class_args *a = (struct tc_bind_class_args *)w; const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct tcf_block *block; struct tcf_chain *chain; block = cops->tcf_block(q, cl, NULL); if (!block) return 0; for (chain = tcf_get_next_chain(block, NULL); chain; chain = tcf_get_next_chain(block, chain)) { struct tcf_proto *tp; for (tp = tcf_get_next_proto(chain, NULL); tp; tp = tcf_get_next_proto(chain, tp)) { struct tcf_bind_args arg = {}; arg.w.fn = tcf_node_bind; arg.classid = a->clid; arg.base = cl; arg.cl = a->new_cl; tp->ops->walk(tp, &arg.w, true); } } return 0; } static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, unsigned long new_cl) { const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct tc_bind_class_args args = {}; if (!cops->tcf_block) return; args.portid = portid; args.clid = clid; args.new_cl = new_cl; args.w.fn = tc_bind_class_walker; q->ops->cl_ops->walk(q, &args.w); } #else static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, unsigned long new_cl) { } #endif static int __tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack, struct net_device *dev, struct nlattr *tca[TCA_MAX + 1], struct tcmsg *tcm) { struct net *net = sock_net(skb->sk); const struct Qdisc_class_ops *cops; struct Qdisc *q = NULL; unsigned long cl = 0; unsigned long new_cl; u32 portid; u32 clid; u32 qid; int err; /* parent == TC_H_UNSPEC - unspecified parent. parent == TC_H_ROOT - class is root, which has no parent. parent == X:0 - parent is root class. parent == X:Y - parent is a node in hierarchy. parent == 0:Y - parent is X:Y, where X:0 is qdisc. handle == 0:0 - generate handle from kernel pool. handle == 0:Y - class is X:Y, where X:0 is qdisc. handle == X:Y - clear. handle == X:0 - root class. */ /* Step 1. Determine qdisc handle X:0 */ portid = tcm->tcm_parent; clid = tcm->tcm_handle; qid = TC_H_MAJ(clid); if (portid != TC_H_ROOT) { u32 qid1 = TC_H_MAJ(portid); if (qid && qid1) { /* If both majors are known, they must be identical. */ if (qid != qid1) return -EINVAL; } else if (qid1) { qid = qid1; } else if (qid == 0) qid = rtnl_dereference(dev->qdisc)->handle; /* Now qid is genuine qdisc handle consistent * both with parent and child. * * TC_H_MAJ(portid) still may be unspecified, complete it now. */ if (portid) portid = TC_H_MAKE(qid, portid); } else { if (qid == 0) qid = rtnl_dereference(dev->qdisc)->handle; } /* OK. Locate qdisc */ q = qdisc_lookup(dev, qid); if (!q) return -ENOENT; /* An check that it supports classes */ cops = q->ops->cl_ops; if (cops == NULL) return -EINVAL; /* Now try to get class */ if (clid == 0) { if (portid == TC_H_ROOT) clid = qid; } else clid = TC_H_MAKE(qid, clid); if (clid) cl = cops->find(q, clid); if (cl == 0) { err = -ENOENT; if (n->nlmsg_type != RTM_NEWTCLASS || !(n->nlmsg_flags & NLM_F_CREATE)) goto out; } else { switch (n->nlmsg_type) { case RTM_NEWTCLASS: err = -EEXIST; if (n->nlmsg_flags & NLM_F_EXCL) goto out; break; case RTM_DELTCLASS: err = tclass_del_notify(net, cops, skb, n, q, cl, extack); /* Unbind the class with flilters with 0 */ tc_bind_tclass(q, portid, clid, 0); goto out; case RTM_GETTCLASS: err = tclass_get_notify(net, skb, n, q, cl, extack); goto out; default: err = -EINVAL; goto out; } } if (tca[TCA_INGRESS_BLOCK] || tca[TCA_EGRESS_BLOCK]) { NL_SET_ERR_MSG(extack, "Shared blocks are not supported for classes"); return -EOPNOTSUPP; } /* Prevent creation of traffic classes with classid TC_H_ROOT */ if (clid == TC_H_ROOT) { NL_SET_ERR_MSG(extack, "Cannot create traffic class with classid TC_H_ROOT"); return -EINVAL; } new_cl = cl; err = -EOPNOTSUPP; if (cops->change) err = cops->change(q, clid, portid, tca, &new_cl, extack); if (err == 0) { tclass_notify(net, skb, n, q, new_cl, RTM_NEWTCLASS, extack); /* We just create a new class, need to do reverse binding. */ if (cl != new_cl) tc_bind_tclass(q, portid, clid, new_cl); } out: return err; } static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct tcmsg *tcm = nlmsg_data(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; int err; err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) return err; dev = __dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return -ENODEV; netdev_lock_ops(dev); err = __tc_ctl_tclass(skb, n, extack, dev, tca, tcm); netdev_unlock_ops(dev); return err; } struct qdisc_dump_args { struct qdisc_walker w; struct sk_buff *skb; struct netlink_callback *cb; }; static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walker *arg) { struct qdisc_dump_args *a = (struct qdisc_dump_args *)arg; return tc_fill_tclass(a->skb, q, cl, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTCLASS, NULL); } static int tc_dump_tclass_qdisc(struct Qdisc *q, struct sk_buff *skb, struct tcmsg *tcm, struct netlink_callback *cb, int *t_p, int s_t) { struct qdisc_dump_args arg; if (tc_qdisc_dump_ignore(q, false) || *t_p < s_t || !q->ops->cl_ops || (tcm->tcm_parent && TC_H_MAJ(tcm->tcm_parent) != q->handle)) { (*t_p)++; return 0; } if (*t_p > s_t) memset(&cb->args[1], 0, sizeof(cb->args)-sizeof(cb->args[0])); arg.w.fn = qdisc_class_dump; arg.skb = skb; arg.cb = cb; arg.w.stop = 0; arg.w.skip = cb->args[1]; arg.w.count = 0; q->ops->cl_ops->walk(q, &arg.w); cb->args[1] = arg.w.count; if (arg.w.stop) return -1; (*t_p)++; return 0; } static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, struct tcmsg *tcm, struct netlink_callback *cb, int *t_p, int s_t, bool recur) { struct Qdisc *q; int b; if (!root) return 0; if (tc_dump_tclass_qdisc(root, skb, tcm, cb, t_p, s_t) < 0) return -1; if (!qdisc_dev(root) || !recur) return 0; if (tcm->tcm_parent) { q = qdisc_match_from_root(root, TC_H_MAJ(tcm->tcm_parent)); if (q && q != root && tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) return -1; return 0; } hash_for_each(qdisc_dev(root)->qdisc_hash, b, q, hash) { if (tc_dump_tclass_qdisc(q, skb, tcm, cb, t_p, s_t) < 0) return -1; } return 0; } static int __tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb, struct tcmsg *tcm, struct net_device *dev) { struct netdev_queue *dev_queue; int t, s_t; s_t = cb->args[0]; t = 0; if (tc_dump_tclass_root(rtnl_dereference(dev->qdisc), skb, tcm, cb, &t, s_t, true) < 0) goto done; dev_queue = dev_ingress_queue(dev); if (dev_queue && tc_dump_tclass_root(rtnl_dereference(dev_queue->qdisc_sleeping), skb, tcm, cb, &t, s_t, false) < 0) goto done; done: cb->args[0] = t; return skb->len; } static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) { struct tcmsg *tcm = nlmsg_data(cb->nlh); struct net *net = sock_net(skb->sk); struct net_device *dev; int err; if (nlmsg_len(cb->nlh) < sizeof(*tcm)) return 0; dev = dev_get_by_index(net, tcm->tcm_ifindex); if (!dev) return 0; netdev_lock_ops(dev); err = __tc_dump_tclass(skb, cb, tcm, dev); netdev_unlock_ops(dev); dev_put(dev); return err; } #ifdef CONFIG_PROC_FS static int psched_show(struct seq_file *seq, void *v) { seq_printf(seq, "%08x %08x %08x %08x\n", (u32)NSEC_PER_USEC, (u32)PSCHED_TICKS2NS(1), 1000000, (u32)NSEC_PER_SEC / hrtimer_resolution); return 0; } static int __net_init psched_net_init(struct net *net) { struct proc_dir_entry *e; e = proc_create_single("psched", 0, net->proc_net, psched_show); if (e == NULL) return -ENOMEM; return 0; } static void __net_exit psched_net_exit(struct net *net) { remove_proc_entry("psched", net->proc_net); } #else static int __net_init psched_net_init(struct net *net) { return 0; } static void __net_exit psched_net_exit(struct net *net) { } #endif static struct pernet_operations psched_net_ops = { .init = psched_net_init, .exit = psched_net_exit, }; #if IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) DEFINE_STATIC_KEY_FALSE(tc_skip_wrapper); #endif static const struct rtnl_msg_handler psched_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_NEWQDISC, .doit = tc_modify_qdisc}, {.msgtype = RTM_DELQDISC, .doit = tc_get_qdisc}, {.msgtype = RTM_GETQDISC, .doit = tc_get_qdisc, .dumpit = tc_dump_qdisc}, {.msgtype = RTM_NEWTCLASS, .doit = tc_ctl_tclass}, {.msgtype = RTM_DELTCLASS, .doit = tc_ctl_tclass}, {.msgtype = RTM_GETTCLASS, .doit = tc_ctl_tclass, .dumpit = tc_dump_tclass}, }; static int __init pktsched_init(void) { int err; err = register_pernet_subsys(&psched_net_ops); if (err) { pr_err("pktsched_init: " "cannot initialize per netns operations\n"); return err; } register_qdisc(&pfifo_fast_ops); register_qdisc(&pfifo_qdisc_ops); register_qdisc(&bfifo_qdisc_ops); register_qdisc(&pfifo_head_drop_qdisc_ops); register_qdisc(&mq_qdisc_ops); register_qdisc(&noqueue_qdisc_ops); rtnl_register_many(psched_rtnl_msg_handlers); tc_wrapper_init(); return 0; } subsys_initcall(pktsched_init); |
| 2 1 1 2 135 132 4 4 1 117 115 2 75 72 4 2 5 4 1 2 1 1 1 1 1 61 56 4 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "eytzinger.h" #include "journal.h" #include "journal_seq_blacklist.h" #include "super-io.h" /* * journal_seq_blacklist machinery: * * To guarantee order of btree updates after a crash, we need to detect when a * btree node entry (bset) is newer than the newest journal entry that was * successfully written, and ignore it - effectively ignoring any btree updates * that didn't make it into the journal. * * If we didn't do this, we might have two btree nodes, a and b, both with * updates that weren't written to the journal yet: if b was updated after a, * but b was flushed and not a - oops; on recovery we'll find that the updates * to b happened, but not the updates to a that happened before it. * * Ignoring bsets that are newer than the newest journal entry is always safe, * because everything they contain will also have been journalled - and must * still be present in the journal on disk until a journal entry has been * written _after_ that bset was written. * * To accomplish this, bsets record the newest journal sequence number they * contain updates for; then, on startup, the btree code queries the journal * code to ask "Is this sequence number newer than the newest journal entry? If * so, ignore it." * * When this happens, we must blacklist that journal sequence number: the * journal must not write any entries with that sequence number, and it must * record that it was blacklisted so that a) on recovery we don't think we have * missing journal entries and b) so that the btree code continues to ignore * that bset, until that btree node is rewritten. */ static unsigned sb_blacklist_u64s(unsigned nr) { struct bch_sb_field_journal_seq_blacklist *bl; return (sizeof(*bl) + sizeof(bl->start[0]) * nr) / sizeof(u64); } int bch2_journal_seq_blacklist_add(struct bch_fs *c, u64 start, u64 end) { struct bch_sb_field_journal_seq_blacklist *bl; unsigned i = 0, nr; int ret = 0; mutex_lock(&c->sb_lock); bl = bch2_sb_field_get(c->disk_sb.sb, journal_seq_blacklist); nr = blacklist_nr_entries(bl); while (i < nr) { struct journal_seq_blacklist_entry *e = bl->start + i; if (end < le64_to_cpu(e->start)) break; if (start > le64_to_cpu(e->end)) { i++; continue; } /* * Entry is contiguous or overlapping with new entry: merge it * with new entry, and delete: */ start = min(start, le64_to_cpu(e->start)); end = max(end, le64_to_cpu(e->end)); array_remove_item(bl->start, nr, i); } bl = bch2_sb_field_resize(&c->disk_sb, journal_seq_blacklist, sb_blacklist_u64s(nr + 1)); if (!bl) { ret = bch_err_throw(c, ENOSPC_sb_journal_seq_blacklist); goto out; } array_insert_item(bl->start, nr, i, ((struct journal_seq_blacklist_entry) { .start = cpu_to_le64(start), .end = cpu_to_le64(end), })); c->disk_sb.sb->features[0] |= cpu_to_le64(1ULL << BCH_FEATURE_journal_seq_blacklist_v3); ret = bch2_write_super(c); out: mutex_unlock(&c->sb_lock); return ret ?: bch2_blacklist_table_initialize(c); } static int journal_seq_blacklist_table_cmp(const void *_l, const void *_r) { const struct journal_seq_blacklist_table_entry *l = _l; const struct journal_seq_blacklist_table_entry *r = _r; return cmp_int(l->start, r->start); } bool bch2_journal_seq_is_blacklisted(struct bch_fs *c, u64 seq, bool dirty) { struct journal_seq_blacklist_table *t = c->journal_seq_blacklist_table; struct journal_seq_blacklist_table_entry search = { .start = seq }; int idx; if (!t) return false; idx = eytzinger0_find_le(t->entries, t->nr, sizeof(t->entries[0]), journal_seq_blacklist_table_cmp, &search); if (idx < 0) return false; BUG_ON(t->entries[idx].start > seq); if (seq >= t->entries[idx].end) return false; if (dirty) t->entries[idx].dirty = true; return true; } u64 bch2_journal_last_blacklisted_seq(struct bch_fs *c) { struct journal_seq_blacklist_table *t = c->journal_seq_blacklist_table; if (!t || !t->nr) return 0; return t->entries[eytzinger0_last(t->nr)].end - 1; } int bch2_blacklist_table_initialize(struct bch_fs *c) { struct bch_sb_field_journal_seq_blacklist *bl = bch2_sb_field_get(c->disk_sb.sb, journal_seq_blacklist); struct journal_seq_blacklist_table *t; unsigned i, nr = blacklist_nr_entries(bl); if (!bl) return 0; t = kzalloc(struct_size(t, entries, nr), GFP_KERNEL); if (!t) return bch_err_throw(c, ENOMEM_blacklist_table_init); t->nr = nr; for (i = 0; i < nr; i++) { t->entries[i].start = le64_to_cpu(bl->start[i].start); t->entries[i].end = le64_to_cpu(bl->start[i].end); } eytzinger0_sort(t->entries, t->nr, sizeof(t->entries[0]), journal_seq_blacklist_table_cmp, NULL); kfree(c->journal_seq_blacklist_table); c->journal_seq_blacklist_table = t; return 0; } static int bch2_sb_journal_seq_blacklist_validate(struct bch_sb *sb, struct bch_sb_field *f, enum bch_validate_flags flags, struct printbuf *err) { struct bch_sb_field_journal_seq_blacklist *bl = field_to_type(f, journal_seq_blacklist); unsigned i, nr = blacklist_nr_entries(bl); for (i = 0; i < nr; i++) { struct journal_seq_blacklist_entry *e = bl->start + i; if (le64_to_cpu(e->start) >= le64_to_cpu(e->end)) { prt_printf(err, "entry %u start >= end (%llu >= %llu)", i, le64_to_cpu(e->start), le64_to_cpu(e->end)); return -BCH_ERR_invalid_sb_journal_seq_blacklist; } if (i + 1 < nr && le64_to_cpu(e[0].end) > le64_to_cpu(e[1].start)) { prt_printf(err, "entry %u out of order with next entry (%llu > %llu)", i + 1, le64_to_cpu(e[0].end), le64_to_cpu(e[1].start)); return -BCH_ERR_invalid_sb_journal_seq_blacklist; } } return 0; } static void bch2_sb_journal_seq_blacklist_to_text(struct printbuf *out, struct bch_sb *sb, struct bch_sb_field *f) { struct bch_sb_field_journal_seq_blacklist *bl = field_to_type(f, journal_seq_blacklist); struct journal_seq_blacklist_entry *i; unsigned nr = blacklist_nr_entries(bl); for (i = bl->start; i < bl->start + nr; i++) { if (i != bl->start) prt_printf(out, " "); prt_printf(out, "%llu-%llu", le64_to_cpu(i->start), le64_to_cpu(i->end)); } prt_newline(out); } const struct bch_sb_field_ops bch_sb_field_ops_journal_seq_blacklist = { .validate = bch2_sb_journal_seq_blacklist_validate, .to_text = bch2_sb_journal_seq_blacklist_to_text }; bool bch2_blacklist_entries_gc(struct bch_fs *c) { struct journal_seq_blacklist_entry *src, *dst; struct bch_sb_field_journal_seq_blacklist *bl = bch2_sb_field_get(c->disk_sb.sb, journal_seq_blacklist); if (!bl) return false; unsigned nr = blacklist_nr_entries(bl); dst = bl->start; struct journal_seq_blacklist_table *t = c->journal_seq_blacklist_table; BUG_ON(nr != t->nr); src = bl->start; eytzinger0_for_each(i, nr) { BUG_ON(t->entries[i].start != le64_to_cpu(src->start)); BUG_ON(t->entries[i].end != le64_to_cpu(src->end)); if (t->entries[i].dirty || t->entries[i].end >= c->journal.oldest_seq_found_ondisk) *dst++ = *src; src++; } unsigned new_nr = dst - bl->start; if (new_nr == nr) return false; bch_verbose(c, "nr blacklist entries was %u, now %u", nr, new_nr); bl = bch2_sb_field_resize(&c->disk_sb, journal_seq_blacklist, new_nr ? sb_blacklist_u64s(new_nr) : 0); BUG_ON(new_nr && !bl); return true; } |
| 1 4 651 2 5 5 5 111 110 111 5 5 104 2 4 1 4 649 7 5 2 2 5 4 1 5 2 656 1 7 2 3 3 5 2 5 712 1 2 2 176 5155 173 3175 5159 5158 2 2 1 1 2 111 111 4 1 5 1 4 5 5 4 1 5 651 1 651 647 4 644 2 647 642 2 5 4 4 5 5 4 4 3 1 645 1 643 712 706 5 713 1416 676 107 107 106 107 107 107 106 1 107 1 1583 1 649 8 1483 1 1 107 107 1 3176 3172 1866 1771 694 50 622 745 714 2 1 1 5168 16 6 5159 5160 5171 3 1 1 1 2 2 1 1 2 2 2 2 1 1 1 2 1 1 1 8 1 2 4 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 1993 by Theodore Ts'o. */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/stat.h> #include <linux/errno.h> #include <linux/major.h> #include <linux/wait.h> #include <linux/blkpg.h> #include <linux/init.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/suspend.h> #include <linux/freezer.h> #include <linux/mutex.h> #include <linux/writeback.h> #include <linux/completion.h> #include <linux/highmem.h> #include <linux/splice.h> #include <linux/sysfs.h> #include <linux/miscdevice.h> #include <linux/falloc.h> #include <linux/uio.h> #include <linux/ioprio.h> #include <linux/blk-cgroup.h> #include <linux/sched/mm.h> #include <linux/statfs.h> #include <linux/uaccess.h> #include <linux/blk-mq.h> #include <linux/spinlock.h> #include <uapi/linux/loop.h> /* Possible states of device */ enum { Lo_unbound, Lo_bound, Lo_rundown, Lo_deleting, }; struct loop_device { int lo_number; loff_t lo_offset; loff_t lo_sizelimit; int lo_flags; char lo_file_name[LO_NAME_SIZE]; struct file *lo_backing_file; unsigned int lo_min_dio_size; struct block_device *lo_device; gfp_t old_gfp_mask; spinlock_t lo_lock; int lo_state; spinlock_t lo_work_lock; struct workqueue_struct *workqueue; struct work_struct rootcg_work; struct list_head rootcg_cmd_list; struct list_head idle_worker_list; struct rb_root worker_tree; struct timer_list timer; bool sysfs_inited; struct request_queue *lo_queue; struct blk_mq_tag_set tag_set; struct gendisk *lo_disk; struct mutex lo_mutex; bool idr_visible; }; struct loop_cmd { struct list_head list_entry; bool use_aio; /* use AIO interface to handle I/O */ atomic_t ref; /* only for aio */ long ret; struct kiocb iocb; struct bio_vec *bvec; struct cgroup_subsys_state *blkcg_css; struct cgroup_subsys_state *memcg_css; }; #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ) #define LOOP_DEFAULT_HW_Q_DEPTH 128 static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_ctl_mutex); static DEFINE_MUTEX(loop_validate_mutex); /** * loop_global_lock_killable() - take locks for safe loop_validate_file() test * * @lo: struct loop_device * @global: true if @lo is about to bind another "struct loop_device", false otherwise * * Returns 0 on success, -EINTR otherwise. * * Since loop_validate_file() traverses on other "struct loop_device" if * is_loop_device() is true, we need a global lock for serializing concurrent * loop_configure()/loop_change_fd()/__loop_clr_fd() calls. */ static int loop_global_lock_killable(struct loop_device *lo, bool global) { int err; if (global) { err = mutex_lock_killable(&loop_validate_mutex); if (err) return err; } err = mutex_lock_killable(&lo->lo_mutex); if (err && global) mutex_unlock(&loop_validate_mutex); return err; } /** * loop_global_unlock() - release locks taken by loop_global_lock_killable() * * @lo: struct loop_device * @global: true if @lo was about to bind another "struct loop_device", false otherwise */ static void loop_global_unlock(struct loop_device *lo, bool global) { mutex_unlock(&lo->lo_mutex); if (global) mutex_unlock(&loop_validate_mutex); } static int max_part; static int part_shift; static loff_t lo_calculate_size(struct loop_device *lo, struct file *file) { struct kstat stat; loff_t loopsize; int ret; /* * Get the accurate file size. This provides better results than * cached inode data, particularly for network filesystems where * metadata may be stale. */ ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0); if (ret) return 0; loopsize = stat.size; if (lo->lo_offset > 0) loopsize -= lo->lo_offset; /* offset is beyond i_size, weird but possible */ if (loopsize < 0) return 0; if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize) loopsize = lo->lo_sizelimit; /* * Unfortunately, if we want to do I/O on the device, * the number of 512-byte sectors has to fit into a sector_t. */ return loopsize >> 9; } /* * We support direct I/O only if lo_offset is aligned with the logical I/O size * of backing device, and the logical block size of loop is bigger than that of * the backing device. */ static bool lo_can_use_dio(struct loop_device *lo) { if (!(lo->lo_backing_file->f_mode & FMODE_CAN_ODIRECT)) return false; if (queue_logical_block_size(lo->lo_queue) < lo->lo_min_dio_size) return false; if (lo->lo_offset & (lo->lo_min_dio_size - 1)) return false; return true; } /* * Direct I/O can be enabled either by using an O_DIRECT file descriptor, or by * passing in the LO_FLAGS_DIRECT_IO flag from userspace. It will be silently * disabled when the device block size is too small or the offset is unaligned. * * loop_get_status will always report the effective LO_FLAGS_DIRECT_IO flag and * not the originally passed in one. */ static inline void loop_update_dio(struct loop_device *lo) { lockdep_assert_held(&lo->lo_mutex); WARN_ON_ONCE(lo->lo_state == Lo_bound && lo->lo_queue->mq_freeze_depth == 0); if ((lo->lo_flags & LO_FLAGS_DIRECT_IO) && !lo_can_use_dio(lo)) lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; } /** * loop_set_size() - sets device size and notifies userspace * @lo: struct loop_device to set the size for * @size: new size of the loop device * * Callers must validate that the size passed into this function fits into * a sector_t, eg using loop_validate_size() */ static void loop_set_size(struct loop_device *lo, loff_t size) { if (!set_capacity_and_notify(lo->lo_disk, size)) kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); } static void loop_clear_limits(struct loop_device *lo, int mode) { struct queue_limits lim = queue_limits_start_update(lo->lo_queue); if (mode & FALLOC_FL_ZERO_RANGE) lim.max_write_zeroes_sectors = 0; if (mode & FALLOC_FL_PUNCH_HOLE) { lim.max_hw_discard_sectors = 0; lim.discard_granularity = 0; } /* * XXX: this updates the queue limits without freezing the queue, which * is against the locking protocol and dangerous. But we can't just * freeze the queue as we're inside the ->queue_rq method here. So this * should move out into a workqueue unless we get the file operations to * advertise if they support specific fallocate operations. */ queue_limits_commit_update(lo->lo_queue, &lim); } static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, int mode) { /* * We use fallocate to manipulate the space mappings used by the image * a.k.a. discard/zerorange. */ struct file *file = lo->lo_backing_file; int ret; mode |= FALLOC_FL_KEEP_SIZE; if (!bdev_max_discard_sectors(lo->lo_device)) return -EOPNOTSUPP; ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq)); if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP)) return -EIO; /* * We initially configure the limits in a hope that fallocate is * supported and clear them here if that turns out not to be true. */ if (unlikely(ret == -EOPNOTSUPP)) loop_clear_limits(lo, mode); return ret; } static int lo_req_flush(struct loop_device *lo, struct request *rq) { int ret = vfs_fsync(lo->lo_backing_file, 0); if (unlikely(ret && ret != -EINVAL)) ret = -EIO; return ret; } static void lo_complete_rq(struct request *rq) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); blk_status_t ret = BLK_STS_OK; if (cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || req_op(rq) != REQ_OP_READ) { if (cmd->ret < 0) ret = errno_to_blk_status(cmd->ret); goto end_io; } /* * Short READ - if we got some data, advance our request and * retry it. If we got no data, end the rest with EIO. */ if (cmd->ret) { blk_update_request(rq, BLK_STS_OK, cmd->ret); cmd->ret = 0; blk_mq_requeue_request(rq, true); } else { struct bio *bio = rq->bio; while (bio) { zero_fill_bio(bio); bio = bio->bi_next; } ret = BLK_STS_IOERR; end_io: blk_mq_end_request(rq, ret); } } static void lo_rw_aio_do_completion(struct loop_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); if (!atomic_dec_and_test(&cmd->ref)) return; kfree(cmd->bvec); cmd->bvec = NULL; if (req_op(rq) == REQ_OP_WRITE) kiocb_end_write(&cmd->iocb); if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq); } static void lo_rw_aio_complete(struct kiocb *iocb, long ret) { struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb); cmd->ret = ret; lo_rw_aio_do_completion(cmd); } static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, loff_t pos, int rw) { struct iov_iter iter; struct req_iterator rq_iter; struct bio_vec *bvec; struct request *rq = blk_mq_rq_from_pdu(cmd); struct bio *bio = rq->bio; struct file *file = lo->lo_backing_file; struct bio_vec tmp; unsigned int offset; int nr_bvec = 0; int ret; rq_for_each_bvec(tmp, rq, rq_iter) nr_bvec++; if (rq->bio != rq->biotail) { bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec), GFP_NOIO); if (!bvec) return -EIO; cmd->bvec = bvec; /* * The bios of the request may be started from the middle of * the 'bvec' because of bio splitting, so we can't directly * copy bio->bi_iov_vec to new bvec. The rq_for_each_bvec * API will take care of all details for us. */ rq_for_each_bvec(tmp, rq, rq_iter) { *bvec = tmp; bvec++; } bvec = cmd->bvec; offset = 0; } else { /* * Same here, this bio may be started from the middle of the * 'bvec' because of bio splitting, so offset from the bvec * must be passed to iov iterator */ offset = bio->bi_iter.bi_bvec_done; bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } atomic_set(&cmd->ref, 2); iov_iter_bvec(&iter, rw, bvec, nr_bvec, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; cmd->iocb.ki_filp = file; cmd->iocb.ki_ioprio = req_get_ioprio(rq); if (cmd->use_aio) { cmd->iocb.ki_complete = lo_rw_aio_complete; cmd->iocb.ki_flags = IOCB_DIRECT; } else { cmd->iocb.ki_complete = NULL; cmd->iocb.ki_flags = 0; } if (rw == ITER_SOURCE) { kiocb_start_write(&cmd->iocb); ret = file->f_op->write_iter(&cmd->iocb, &iter); } else ret = file->f_op->read_iter(&cmd->iocb, &iter); lo_rw_aio_do_completion(cmd); if (ret != -EIOCBQUEUED) lo_rw_aio_complete(&cmd->iocb, ret); return -EIOCBQUEUED; } static int do_req_filebacked(struct loop_device *lo, struct request *rq) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset; switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); case REQ_OP_WRITE_ZEROES: /* * If the caller doesn't want deallocation, call zeroout to * write zeroes the range. Otherwise, punch them out. */ return lo_fallocate(lo, rq, pos, (rq->cmd_flags & REQ_NOUNMAP) ? FALLOC_FL_ZERO_RANGE : FALLOC_FL_PUNCH_HOLE); case REQ_OP_DISCARD: return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: return lo_rw_aio(lo, cmd, pos, ITER_SOURCE); case REQ_OP_READ: return lo_rw_aio(lo, cmd, pos, ITER_DEST); default: WARN_ON_ONCE(1); return -EIO; } } static void loop_reread_partitions(struct loop_device *lo) { int rc; mutex_lock(&lo->lo_disk->open_mutex); rc = bdev_disk_changed(lo->lo_disk, false); mutex_unlock(&lo->lo_disk->open_mutex); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); } static unsigned int loop_query_min_dio_size(struct loop_device *lo) { struct file *file = lo->lo_backing_file; struct block_device *sb_bdev = file->f_mapping->host->i_sb->s_bdev; struct kstat st; /* * Use the minimal dio alignment of the file system if provided. */ if (!vfs_getattr(&file->f_path, &st, STATX_DIOALIGN, 0) && (st.result_mask & STATX_DIOALIGN)) return st.dio_offset_align; /* * In a perfect world this wouldn't be needed, but as of Linux 6.13 only * a handful of file systems support the STATX_DIOALIGN flag. */ if (sb_bdev) return bdev_logical_block_size(sb_bdev); return SECTOR_SIZE; } static inline int is_loop_device(struct file *file) { struct inode *i = file->f_mapping->host; return i && S_ISBLK(i->i_mode) && imajor(i) == LOOP_MAJOR; } static int loop_validate_file(struct file *file, struct block_device *bdev) { struct inode *inode = file->f_mapping->host; struct file *f = file; /* Avoid recursion */ while (is_loop_device(f)) { struct loop_device *l; lockdep_assert_held(&loop_validate_mutex); if (f->f_mapping->host->i_rdev == bdev->bd_dev) return -EBADF; l = I_BDEV(f->f_mapping->host)->bd_disk->private_data; if (l->lo_state != Lo_bound) return -EINVAL; /* Order wrt setting lo->lo_backing_file in loop_configure(). */ rmb(); f = l->lo_backing_file; } if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) return -EINVAL; return 0; } static void loop_assign_backing_file(struct loop_device *lo, struct file *file) { lo->lo_backing_file = file; lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping); mapping_set_gfp_mask(file->f_mapping, lo->old_gfp_mask & ~(__GFP_IO | __GFP_FS)); if (lo->lo_backing_file->f_flags & O_DIRECT) lo->lo_flags |= LO_FLAGS_DIRECT_IO; lo->lo_min_dio_size = loop_query_min_dio_size(lo); } static int loop_check_backing_file(struct file *file) { if (!file->f_op->read_iter) return -EINVAL; if ((file->f_mode & FMODE_WRITE) && !file->f_op->write_iter) return -EINVAL; return 0; } /* * loop_change_fd switched the backing store of a loopback device to * a new file. This is useful for operating system installers to free up * the original file and in High Availability environments to switch to * an alternative location for the content in case of server meltdown. * This can only work if the loop device is used read-only, and if the * new backing store is the same size and type as the old backing store. */ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, unsigned int arg) { struct file *file = fget(arg); struct file *old_file; unsigned int memflags; int error; bool partscan; bool is_loop; if (!file) return -EBADF; error = loop_check_backing_file(file); if (error) return error; /* suppress uevents while reconfiguring the device */ dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); is_loop = is_loop_device(file); error = loop_global_lock_killable(lo, is_loop); if (error) goto out_putf; error = -ENXIO; if (lo->lo_state != Lo_bound) goto out_err; /* the loop device has to be read-only */ error = -EINVAL; if (!(lo->lo_flags & LO_FLAGS_READ_ONLY)) goto out_err; error = loop_validate_file(file, bdev); if (error) goto out_err; old_file = lo->lo_backing_file; error = -EINVAL; /* size of the new backing store needs to be the same */ if (lo_calculate_size(lo, file) != lo_calculate_size(lo, old_file)) goto out_err; /* * We might switch to direct I/O mode for the loop device, write back * all dirty data the page cache now that so that the individual I/O * operations don't have to do that. */ vfs_fsync(file, 0); /* and ... switch */ disk_force_media_change(lo->lo_disk); memflags = blk_mq_freeze_queue(lo->lo_queue); mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask); loop_assign_backing_file(lo, file); loop_update_dio(lo); blk_mq_unfreeze_queue(lo->lo_queue, memflags); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; loop_global_unlock(lo, is_loop); /* * Flush loop_validate_file() before fput(), for l->lo_backing_file * might be pointing at old_file which might be the last reference. */ if (!is_loop) { mutex_lock(&loop_validate_mutex); mutex_unlock(&loop_validate_mutex); } /* * We must drop file reference outside of lo_mutex as dropping * the file ref can take open_mutex which creates circular locking * dependency. */ fput(old_file); dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); if (partscan) loop_reread_partitions(lo); error = 0; done: kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); return error; out_err: loop_global_unlock(lo, is_loop); out_putf: fput(file); dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); goto done; } /* loop sysfs attributes */ static ssize_t loop_attr_show(struct device *dev, char *page, ssize_t (*callback)(struct loop_device *, char *)) { struct gendisk *disk = dev_to_disk(dev); struct loop_device *lo = disk->private_data; return callback(lo, page); } #define LOOP_ATTR_RO(_name) \ static ssize_t loop_attr_##_name##_show(struct loop_device *, char *); \ static ssize_t loop_attr_do_show_##_name(struct device *d, \ struct device_attribute *attr, char *b) \ { \ return loop_attr_show(d, b, loop_attr_##_name##_show); \ } \ static struct device_attribute loop_attr_##_name = \ __ATTR(_name, 0444, loop_attr_do_show_##_name, NULL); static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf) { ssize_t ret; char *p = NULL; spin_lock_irq(&lo->lo_lock); if (lo->lo_backing_file) p = file_path(lo->lo_backing_file, buf, PAGE_SIZE - 1); spin_unlock_irq(&lo->lo_lock); if (IS_ERR_OR_NULL(p)) ret = PTR_ERR(p); else { ret = strlen(p); memmove(buf, p, ret); buf[ret++] = '\n'; buf[ret] = 0; } return ret; } static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_offset); } static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf) { return sysfs_emit(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit); } static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf) { int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR); return sysfs_emit(buf, "%s\n", autoclear ? "1" : "0"); } static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf) { int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN); return sysfs_emit(buf, "%s\n", partscan ? "1" : "0"); } static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf) { int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO); return sysfs_emit(buf, "%s\n", dio ? "1" : "0"); } LOOP_ATTR_RO(backing_file); LOOP_ATTR_RO(offset); LOOP_ATTR_RO(sizelimit); LOOP_ATTR_RO(autoclear); LOOP_ATTR_RO(partscan); LOOP_ATTR_RO(dio); static struct attribute *loop_attrs[] = { &loop_attr_backing_file.attr, &loop_attr_offset.attr, &loop_attr_sizelimit.attr, &loop_attr_autoclear.attr, &loop_attr_partscan.attr, &loop_attr_dio.attr, NULL, }; static struct attribute_group loop_attribute_group = { .name = "loop", .attrs= loop_attrs, }; static void loop_sysfs_init(struct loop_device *lo) { lo->sysfs_inited = !sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj, &loop_attribute_group); } static void loop_sysfs_exit(struct loop_device *lo) { if (lo->sysfs_inited) sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj, &loop_attribute_group); } static void loop_get_discard_config(struct loop_device *lo, u32 *granularity, u32 *max_discard_sectors) { struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct kstatfs sbuf; /* * If the backing device is a block device, mirror its zeroing * capability. Set the discard sectors to the block device's zeroing * capabilities because loop discards result in blkdev_issue_zeroout(), * not blkdev_issue_discard(). This maintains consistent behavior with * file-backed loop devices: discarded regions read back as zero. */ if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); *max_discard_sectors = bdev_write_zeroes_sectors(bdev); *granularity = bdev_discard_granularity(bdev); /* * We use punch hole to reclaim the free space used by the * image a.k.a. discard. */ } else if (file->f_op->fallocate && !vfs_statfs(&file->f_path, &sbuf)) { *max_discard_sectors = UINT_MAX >> 9; *granularity = sbuf.f_bsize; } } struct loop_worker { struct rb_node rb_node; struct work_struct work; struct list_head cmd_list; struct list_head idle_list; struct loop_device *lo; struct cgroup_subsys_state *blkcg_css; unsigned long last_ran_at; }; static void loop_workfn(struct work_struct *work); #ifdef CONFIG_BLK_CGROUP static inline int queue_on_root_worker(struct cgroup_subsys_state *css) { return !css || css == blkcg_root_css; } #else static inline int queue_on_root_worker(struct cgroup_subsys_state *css) { return !css; } #endif static void loop_queue_work(struct loop_device *lo, struct loop_cmd *cmd) { struct rb_node **node, *parent = NULL; struct loop_worker *cur_worker, *worker = NULL; struct work_struct *work; struct list_head *cmd_list; spin_lock_irq(&lo->lo_work_lock); if (queue_on_root_worker(cmd->blkcg_css)) goto queue_work; node = &lo->worker_tree.rb_node; while (*node) { parent = *node; cur_worker = container_of(*node, struct loop_worker, rb_node); if (cur_worker->blkcg_css == cmd->blkcg_css) { worker = cur_worker; break; } else if ((long)cur_worker->blkcg_css < (long)cmd->blkcg_css) { node = &(*node)->rb_left; } else { node = &(*node)->rb_right; } } if (worker) goto queue_work; worker = kzalloc(sizeof(struct loop_worker), GFP_NOWAIT | __GFP_NOWARN); /* * In the event we cannot allocate a worker, just queue on the * rootcg worker and issue the I/O as the rootcg */ if (!worker) { cmd->blkcg_css = NULL; if (cmd->memcg_css) css_put(cmd->memcg_css); cmd->memcg_css = NULL; goto queue_work; } worker->blkcg_css = cmd->blkcg_css; css_get(worker->blkcg_css); INIT_WORK(&worker->work, loop_workfn); INIT_LIST_HEAD(&worker->cmd_list); INIT_LIST_HEAD(&worker->idle_list); worker->lo = lo; rb_link_node(&worker->rb_node, parent, node); rb_insert_color(&worker->rb_node, &lo->worker_tree); queue_work: if (worker) { /* * We need to remove from the idle list here while * holding the lock so that the idle timer doesn't * free the worker */ if (!list_empty(&worker->idle_list)) list_del_init(&worker->idle_list); work = &worker->work; cmd_list = &worker->cmd_list; } else { work = &lo->rootcg_work; cmd_list = &lo->rootcg_cmd_list; } list_add_tail(&cmd->list_entry, cmd_list); queue_work(lo->workqueue, work); spin_unlock_irq(&lo->lo_work_lock); } static void loop_set_timer(struct loop_device *lo) { timer_reduce(&lo->timer, jiffies + LOOP_IDLE_WORKER_TIMEOUT); } static void loop_free_idle_workers(struct loop_device *lo, bool delete_all) { struct loop_worker *pos, *worker; spin_lock_irq(&lo->lo_work_lock); list_for_each_entry_safe(worker, pos, &lo->idle_worker_list, idle_list) { if (!delete_all && time_is_after_jiffies(worker->last_ran_at + LOOP_IDLE_WORKER_TIMEOUT)) break; list_del(&worker->idle_list); rb_erase(&worker->rb_node, &lo->worker_tree); css_put(worker->blkcg_css); kfree(worker); } if (!list_empty(&lo->idle_worker_list)) loop_set_timer(lo); spin_unlock_irq(&lo->lo_work_lock); } static void loop_free_idle_workers_timer(struct timer_list *timer) { struct loop_device *lo = container_of(timer, struct loop_device, timer); return loop_free_idle_workers(lo, false); } /** * loop_set_status_from_info - configure device from loop_info * @lo: struct loop_device to configure * @info: struct loop_info64 to configure the device with * * Configures the loop device parameters according to the passed * in loop_info64 configuration. */ static int loop_set_status_from_info(struct loop_device *lo, const struct loop_info64 *info) { if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) return -EINVAL; switch (info->lo_encrypt_type) { case LO_CRYPT_NONE: break; case LO_CRYPT_XOR: pr_warn("support for the xor transformation has been removed.\n"); return -EINVAL; case LO_CRYPT_CRYPTOAPI: pr_warn("support for cryptoloop has been removed. Use dm-crypt instead.\n"); return -EINVAL; default: return -EINVAL; } /* Avoid assigning overflow values */ if (info->lo_offset > LLONG_MAX || info->lo_sizelimit > LLONG_MAX) return -EOVERFLOW; lo->lo_offset = info->lo_offset; lo->lo_sizelimit = info->lo_sizelimit; memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); lo->lo_file_name[LO_NAME_SIZE-1] = 0; return 0; } static unsigned int loop_default_blocksize(struct loop_device *lo) { /* In case of direct I/O, match underlying minimum I/O size */ if (lo->lo_flags & LO_FLAGS_DIRECT_IO) return lo->lo_min_dio_size; return SECTOR_SIZE; } static void loop_update_limits(struct loop_device *lo, struct queue_limits *lim, unsigned int bsize) { struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct block_device *backing_bdev = NULL; u32 granularity = 0, max_discard_sectors = 0; if (S_ISBLK(inode->i_mode)) backing_bdev = I_BDEV(inode); else if (inode->i_sb->s_bdev) backing_bdev = inode->i_sb->s_bdev; if (!bsize) bsize = loop_default_blocksize(lo); loop_get_discard_config(lo, &granularity, &max_discard_sectors); lim->logical_block_size = bsize; lim->physical_block_size = bsize; lim->io_min = bsize; lim->features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_ROTATIONAL); if (file->f_op->fsync && !(lo->lo_flags & LO_FLAGS_READ_ONLY)) lim->features |= BLK_FEAT_WRITE_CACHE; if (backing_bdev && !bdev_nonrot(backing_bdev)) lim->features |= BLK_FEAT_ROTATIONAL; lim->max_hw_discard_sectors = max_discard_sectors; lim->max_write_zeroes_sectors = max_discard_sectors; if (max_discard_sectors) lim->discard_granularity = granularity; else lim->discard_granularity = 0; } static int loop_configure(struct loop_device *lo, blk_mode_t mode, struct block_device *bdev, const struct loop_config *config) { struct file *file = fget(config->fd); struct queue_limits lim; int error; loff_t size; bool partscan; bool is_loop; if (!file) return -EBADF; error = loop_check_backing_file(file); if (error) return error; is_loop = is_loop_device(file); /* This is safe, since we have a reference from open(). */ __module_get(THIS_MODULE); /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. */ if (!(mode & BLK_OPEN_EXCL)) { error = bd_prepare_to_claim(bdev, loop_configure, NULL); if (error) goto out_putf; } error = loop_global_lock_killable(lo, is_loop); if (error) goto out_bdev; error = -EBUSY; if (lo->lo_state != Lo_unbound) goto out_unlock; error = loop_validate_file(file, bdev); if (error) goto out_unlock; if ((config->info.lo_flags & ~LOOP_CONFIGURE_SETTABLE_FLAGS) != 0) { error = -EINVAL; goto out_unlock; } error = loop_set_status_from_info(lo, &config->info); if (error) goto out_unlock; lo->lo_flags = config->info.lo_flags; if (!(file->f_mode & FMODE_WRITE) || !(mode & BLK_OPEN_WRITE) || !file->f_op->write_iter) lo->lo_flags |= LO_FLAGS_READ_ONLY; if (!lo->workqueue) { lo->workqueue = alloc_workqueue("loop%d", WQ_UNBOUND | WQ_FREEZABLE, 0, lo->lo_number); if (!lo->workqueue) { error = -ENOMEM; goto out_unlock; } } /* suppress uevents while reconfiguring the device */ dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 1); disk_force_media_change(lo->lo_disk); set_disk_ro(lo->lo_disk, (lo->lo_flags & LO_FLAGS_READ_ONLY) != 0); lo->lo_device = bdev; loop_assign_backing_file(lo, file); lim = queue_limits_start_update(lo->lo_queue); loop_update_limits(lo, &lim, config->block_size); /* No need to freeze the queue as the device isn't bound yet. */ error = queue_limits_commit_update(lo->lo_queue, &lim); if (error) goto out_unlock; /* * We might switch to direct I/O mode for the loop device, write back * all dirty data the page cache now that so that the individual I/O * operations don't have to do that. */ vfs_fsync(file, 0); loop_update_dio(lo); loop_sysfs_init(lo); size = lo_calculate_size(lo, file); loop_set_size(lo, size); /* Order wrt reading lo_state in loop_validate_file(). */ wmb(); lo->lo_state = Lo_bound; if (part_shift) lo->lo_flags |= LO_FLAGS_PARTSCAN; partscan = lo->lo_flags & LO_FLAGS_PARTSCAN; if (partscan) clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); dev_set_uevent_suppress(disk_to_dev(lo->lo_disk), 0); kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); loop_global_unlock(lo, is_loop); if (partscan) loop_reread_partitions(lo); if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, loop_configure); return 0; out_unlock: loop_global_unlock(lo, is_loop); out_bdev: if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, loop_configure); out_putf: fput(file); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); return error; } static void __loop_clr_fd(struct loop_device *lo) { struct queue_limits lim; struct file *filp; gfp_t gfp = lo->old_gfp_mask; spin_lock_irq(&lo->lo_lock); filp = lo->lo_backing_file; lo->lo_backing_file = NULL; spin_unlock_irq(&lo->lo_lock); lo->lo_device = NULL; lo->lo_offset = 0; lo->lo_sizelimit = 0; memset(lo->lo_file_name, 0, LO_NAME_SIZE); /* * Reset the block size to the default. * * No queue freezing needed because this is called from the final * ->release call only, so there can't be any outstanding I/O. */ lim = queue_limits_start_update(lo->lo_queue); lim.logical_block_size = SECTOR_SIZE; lim.physical_block_size = SECTOR_SIZE; lim.io_min = SECTOR_SIZE; queue_limits_commit_update(lo->lo_queue, &lim); invalidate_disk(lo->lo_disk); loop_sysfs_exit(lo); /* let user-space know about this change */ kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); mapping_set_gfp_mask(filp->f_mapping, gfp); /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); disk_force_media_change(lo->lo_disk); if (lo->lo_flags & LO_FLAGS_PARTSCAN) { int err; /* * open_mutex has been held already in release path, so don't * acquire it if this function is called in such case. * * If the reread partition isn't from release path, lo_refcnt * must be at least one and it can only become zero when the * current holder is released. */ err = bdev_disk_changed(lo->lo_disk, false); if (err) pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", __func__, lo->lo_number, err); /* Device is gone, no point in returning error */ } /* * lo->lo_state is set to Lo_unbound here after above partscan has * finished. There cannot be anybody else entering __loop_clr_fd() as * Lo_rundown state protects us from all the other places trying to * change the 'lo' device. */ lo->lo_flags = 0; if (!part_shift) set_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); mutex_lock(&lo->lo_mutex); lo->lo_state = Lo_unbound; mutex_unlock(&lo->lo_mutex); /* * Need not hold lo_mutex to fput backing file. Calling fput holding * lo_mutex triggers a circular lock dependency possibility warning as * fput can take open_mutex which is usually taken before lo_mutex. */ fput(filp); } static int loop_clr_fd(struct loop_device *lo) { int err; /* * Since lo_ioctl() is called without locks held, it is possible that * loop_configure()/loop_change_fd() and loop_clr_fd() run in parallel. * * Therefore, use global lock when setting Lo_rundown state in order to * make sure that loop_validate_file() will fail if the "struct file" * which loop_configure()/loop_change_fd() found via fget() was this * loop device. */ err = loop_global_lock_killable(lo, true); if (err) return err; if (lo->lo_state != Lo_bound) { loop_global_unlock(lo, true); return -ENXIO; } /* * Mark the device for removing the backing device on last close. * If we are the only opener, also switch the state to roundown here to * prevent new openers from coming in. */ lo->lo_flags |= LO_FLAGS_AUTOCLEAR; if (disk_openers(lo->lo_disk) == 1) lo->lo_state = Lo_rundown; loop_global_unlock(lo, true); return 0; } static int loop_set_status(struct loop_device *lo, const struct loop_info64 *info) { int err; bool partscan = false; bool size_changed = false; unsigned int memflags; err = mutex_lock_killable(&lo->lo_mutex); if (err) return err; if (lo->lo_state != Lo_bound) { err = -ENXIO; goto out_unlock; } if (lo->lo_offset != info->lo_offset || lo->lo_sizelimit != info->lo_sizelimit) { size_changed = true; sync_blockdev(lo->lo_device); invalidate_bdev(lo->lo_device); } /* I/O needs to be drained before changing lo_offset or lo_sizelimit */ memflags = blk_mq_freeze_queue(lo->lo_queue); err = loop_set_status_from_info(lo, info); if (err) goto out_unfreeze; partscan = !(lo->lo_flags & LO_FLAGS_PARTSCAN) && (info->lo_flags & LO_FLAGS_PARTSCAN); lo->lo_flags &= ~LOOP_SET_STATUS_CLEARABLE_FLAGS; lo->lo_flags |= (info->lo_flags & LOOP_SET_STATUS_SETTABLE_FLAGS); /* update the direct I/O flag if lo_offset changed */ loop_update_dio(lo); out_unfreeze: blk_mq_unfreeze_queue(lo->lo_queue, memflags); if (partscan) clear_bit(GD_SUPPRESS_PART_SCAN, &lo->lo_disk->state); if (!err && size_changed) { loff_t new_size = lo_calculate_size(lo, lo->lo_backing_file); loop_set_size(lo, new_size); } out_unlock: mutex_unlock(&lo->lo_mutex); if (partscan) loop_reread_partitions(lo); return err; } static int loop_get_status(struct loop_device *lo, struct loop_info64 *info) { struct path path; struct kstat stat; int ret; ret = mutex_lock_killable(&lo->lo_mutex); if (ret) return ret; if (lo->lo_state != Lo_bound) { mutex_unlock(&lo->lo_mutex); return -ENXIO; } memset(info, 0, sizeof(*info)); info->lo_number = lo->lo_number; info->lo_offset = lo->lo_offset; info->lo_sizelimit = lo->lo_sizelimit; info->lo_flags = lo->lo_flags; memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE); /* Drop lo_mutex while we call into the filesystem. */ path = lo->lo_backing_file->f_path; path_get(&path); mutex_unlock(&lo->lo_mutex); ret = vfs_getattr(&path, &stat, STATX_INO, AT_STATX_SYNC_AS_STAT); if (!ret) { info->lo_device = huge_encode_dev(stat.dev); info->lo_inode = stat.ino; info->lo_rdevice = huge_encode_dev(stat.rdev); } path_put(&path); return ret; } static void loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info64) { memset(info64, 0, sizeof(*info64)); info64->lo_number = info->lo_number; info64->lo_device = info->lo_device; info64->lo_inode = info->lo_inode; info64->lo_rdevice = info->lo_rdevice; info64->lo_offset = info->lo_offset; info64->lo_sizelimit = 0; info64->lo_flags = info->lo_flags; memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE); } static int loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info) { memset(info, 0, sizeof(*info)); info->lo_number = info64->lo_number; info->lo_device = info64->lo_device; info->lo_inode = info64->lo_inode; info->lo_rdevice = info64->lo_rdevice; info->lo_offset = info64->lo_offset; info->lo_flags = info64->lo_flags; memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE); /* error in case values were truncated */ if (info->lo_device != info64->lo_device || info->lo_rdevice != info64->lo_rdevice || info->lo_inode != info64->lo_inode || info->lo_offset != info64->lo_offset) return -EOVERFLOW; return 0; } static int loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg) { struct loop_info info; struct loop_info64 info64; if (copy_from_user(&info, arg, sizeof (struct loop_info))) return -EFAULT; loop_info64_from_old(&info, &info64); return loop_set_status(lo, &info64); } static int loop_set_status64(struct loop_device *lo, const struct loop_info64 __user *arg) { struct loop_info64 info64; if (copy_from_user(&info64, arg, sizeof (struct loop_info64))) return -EFAULT; return loop_set_status(lo, &info64); } static int loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) { struct loop_info info; struct loop_info64 info64; int err; if (!arg) return -EINVAL; err = loop_get_status(lo, &info64); if (!err) err = loop_info64_to_old(&info64, &info); if (!err && copy_to_user(arg, &info, sizeof(info))) err = -EFAULT; return err; } static int loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) { struct loop_info64 info64; int err; if (!arg) return -EINVAL; err = loop_get_status(lo, &info64); if (!err && copy_to_user(arg, &info64, sizeof(info64))) err = -EFAULT; return err; } static int loop_set_capacity(struct loop_device *lo) { loff_t size; if (unlikely(lo->lo_state != Lo_bound)) return -ENXIO; size = lo_calculate_size(lo, lo->lo_backing_file); loop_set_size(lo, size); return 0; } static int loop_set_dio(struct loop_device *lo, unsigned long arg) { bool use_dio = !!arg; unsigned int memflags; if (lo->lo_state != Lo_bound) return -ENXIO; if (use_dio == !!(lo->lo_flags & LO_FLAGS_DIRECT_IO)) return 0; if (use_dio) { if (!lo_can_use_dio(lo)) return -EINVAL; /* flush dirty pages before starting to use direct I/O */ vfs_fsync(lo->lo_backing_file, 0); } memflags = blk_mq_freeze_queue(lo->lo_queue); if (use_dio) lo->lo_flags |= LO_FLAGS_DIRECT_IO; else lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; blk_mq_unfreeze_queue(lo->lo_queue, memflags); return 0; } static int loop_set_block_size(struct loop_device *lo, blk_mode_t mode, struct block_device *bdev, unsigned long arg) { struct queue_limits lim; unsigned int memflags; int err = 0; /* * If we don't hold exclusive handle for the device, upgrade to it * here to avoid changing device under exclusive owner. */ if (!(mode & BLK_OPEN_EXCL)) { err = bd_prepare_to_claim(bdev, loop_set_block_size, NULL); if (err) return err; } err = mutex_lock_killable(&lo->lo_mutex); if (err) goto abort_claim; if (lo->lo_state != Lo_bound) { err = -ENXIO; goto unlock; } if (lo->lo_queue->limits.logical_block_size == arg) goto unlock; sync_blockdev(lo->lo_device); invalidate_bdev(lo->lo_device); lim = queue_limits_start_update(lo->lo_queue); loop_update_limits(lo, &lim, arg); memflags = blk_mq_freeze_queue(lo->lo_queue); err = queue_limits_commit_update(lo->lo_queue, &lim); loop_update_dio(lo); blk_mq_unfreeze_queue(lo->lo_queue, memflags); unlock: mutex_unlock(&lo->lo_mutex); abort_claim: if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(bdev, loop_set_block_size); return err; } static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd, unsigned long arg) { int err; err = mutex_lock_killable(&lo->lo_mutex); if (err) return err; switch (cmd) { case LOOP_SET_CAPACITY: err = loop_set_capacity(lo); break; case LOOP_SET_DIRECT_IO: err = loop_set_dio(lo, arg); break; default: err = -EINVAL; } mutex_unlock(&lo->lo_mutex); return err; } static int lo_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; void __user *argp = (void __user *) arg; int err; switch (cmd) { case LOOP_SET_FD: { /* * Legacy case - pass in a zeroed out struct loop_config with * only the file descriptor set , which corresponds with the * default parameters we'd have used otherwise. */ struct loop_config config; memset(&config, 0, sizeof(config)); config.fd = arg; return loop_configure(lo, mode, bdev, &config); } case LOOP_CONFIGURE: { struct loop_config config; if (copy_from_user(&config, argp, sizeof(config))) return -EFAULT; return loop_configure(lo, mode, bdev, &config); } case LOOP_CHANGE_FD: return loop_change_fd(lo, bdev, arg); case LOOP_CLR_FD: return loop_clr_fd(lo); case LOOP_SET_STATUS: err = -EPERM; if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN)) err = loop_set_status_old(lo, argp); break; case LOOP_GET_STATUS: return loop_get_status_old(lo, argp); case LOOP_SET_STATUS64: err = -EPERM; if ((mode & BLK_OPEN_WRITE) || capable(CAP_SYS_ADMIN)) err = loop_set_status64(lo, argp); break; case LOOP_GET_STATUS64: return loop_get_status64(lo, argp); case LOOP_SET_BLOCK_SIZE: if (!(mode & BLK_OPEN_WRITE) && !capable(CAP_SYS_ADMIN)) return -EPERM; return loop_set_block_size(lo, mode, bdev, arg); case LOOP_SET_CAPACITY: case LOOP_SET_DIRECT_IO: if (!(mode & BLK_OPEN_WRITE) && !capable(CAP_SYS_ADMIN)) return -EPERM; fallthrough; default: err = lo_simple_ioctl(lo, cmd, arg); break; } return err; } #ifdef CONFIG_COMPAT struct compat_loop_info { compat_int_t lo_number; /* ioctl r/o */ compat_dev_t lo_device; /* ioctl r/o */ compat_ulong_t lo_inode; /* ioctl r/o */ compat_dev_t lo_rdevice; /* ioctl r/o */ compat_int_t lo_offset; compat_int_t lo_encrypt_type; /* obsolete, ignored */ compat_int_t lo_encrypt_key_size; /* ioctl w/o */ compat_int_t lo_flags; /* ioctl r/o */ char lo_name[LO_NAME_SIZE]; unsigned char lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */ compat_ulong_t lo_init[2]; char reserved[4]; }; /* * Transfer 32-bit compatibility structure in userspace to 64-bit loop info * - noinlined to reduce stack space usage in main part of driver */ static noinline int loop_info64_from_compat(const struct compat_loop_info __user *arg, struct loop_info64 *info64) { struct compat_loop_info info; if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; memset(info64, 0, sizeof(*info64)); info64->lo_number = info.lo_number; info64->lo_device = info.lo_device; info64->lo_inode = info.lo_inode; info64->lo_rdevice = info.lo_rdevice; info64->lo_offset = info.lo_offset; info64->lo_sizelimit = 0; info64->lo_flags = info.lo_flags; memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE); return 0; } /* * Transfer 64-bit loop info to 32-bit compatibility structure in userspace * - noinlined to reduce stack space usage in main part of driver */ static noinline int loop_info64_to_compat(const struct loop_info64 *info64, struct compat_loop_info __user *arg) { struct compat_loop_info info; memset(&info, 0, sizeof(info)); info.lo_number = info64->lo_number; info.lo_device = info64->lo_device; info.lo_inode = info64->lo_inode; info.lo_rdevice = info64->lo_rdevice; info.lo_offset = info64->lo_offset; info.lo_flags = info64->lo_flags; memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE); /* error in case values were truncated */ if (info.lo_device != info64->lo_device || info.lo_rdevice != info64->lo_rdevice || info.lo_inode != info64->lo_inode || info.lo_offset != info64->lo_offset) return -EOVERFLOW; if (copy_to_user(arg, &info, sizeof(info))) return -EFAULT; return 0; } static int loop_set_status_compat(struct loop_device *lo, const struct compat_loop_info __user *arg) { struct loop_info64 info64; int ret; ret = loop_info64_from_compat(arg, &info64); if (ret < 0) return ret; return loop_set_status(lo, &info64); } static int loop_get_status_compat(struct loop_device *lo, struct compat_loop_info __user *arg) { struct loop_info64 info64; int err; if (!arg) return -EINVAL; err = loop_get_status(lo, &info64); if (!err) err = loop_info64_to_compat(&info64, arg); return err; } static int lo_compat_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct loop_device *lo = bdev->bd_disk->private_data; int err; switch(cmd) { case LOOP_SET_STATUS: err = loop_set_status_compat(lo, (const struct compat_loop_info __user *)arg); break; case LOOP_GET_STATUS: err = loop_get_status_compat(lo, (struct compat_loop_info __user *)arg); break; case LOOP_SET_CAPACITY: case LOOP_CLR_FD: case LOOP_GET_STATUS64: case LOOP_SET_STATUS64: case LOOP_CONFIGURE: arg = (unsigned long) compat_ptr(arg); fallthrough; case LOOP_SET_FD: case LOOP_CHANGE_FD: case LOOP_SET_BLOCK_SIZE: case LOOP_SET_DIRECT_IO: err = lo_ioctl(bdev, mode, cmd, arg); break; default: err = -ENOIOCTLCMD; break; } return err; } #endif static int lo_open(struct gendisk *disk, blk_mode_t mode) { struct loop_device *lo = disk->private_data; int err; err = mutex_lock_killable(&lo->lo_mutex); if (err) return err; if (lo->lo_state == Lo_deleting || lo->lo_state == Lo_rundown) err = -ENXIO; mutex_unlock(&lo->lo_mutex); return err; } static void lo_release(struct gendisk *disk) { struct loop_device *lo = disk->private_data; bool need_clear = false; if (disk_openers(disk) > 0) return; /* * Clear the backing device information if this is the last close of * a device that's been marked for auto clear, or on which LOOP_CLR_FD * has been called. */ mutex_lock(&lo->lo_mutex); if (lo->lo_state == Lo_bound && (lo->lo_flags & LO_FLAGS_AUTOCLEAR)) lo->lo_state = Lo_rundown; need_clear = (lo->lo_state == Lo_rundown); mutex_unlock(&lo->lo_mutex); if (need_clear) __loop_clr_fd(lo); } static void lo_free_disk(struct gendisk *disk) { struct loop_device *lo = disk->private_data; if (lo->workqueue) destroy_workqueue(lo->workqueue); loop_free_idle_workers(lo, true); timer_shutdown_sync(&lo->timer); mutex_destroy(&lo->lo_mutex); kfree(lo); } static const struct block_device_operations lo_fops = { .owner = THIS_MODULE, .open = lo_open, .release = lo_release, .ioctl = lo_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = lo_compat_ioctl, #endif .free_disk = lo_free_disk, }; /* * And now the modules code and kernel interface. */ /* * If max_loop is specified, create that many devices upfront. * This also becomes a hard limit. If max_loop is not specified, * the default isn't a hard limit (as before commit 85c50197716c * changed the default value from 0 for max_loop=0 reasons), just * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module * init time. Loop devices can be requested on-demand with the * /dev/loop-control interface, or be instantiated by accessing * a 'dead' device node. */ static int max_loop = CONFIG_BLK_DEV_LOOP_MIN_COUNT; #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD static bool max_loop_specified; static int max_loop_param_set_int(const char *val, const struct kernel_param *kp) { int ret; ret = param_set_int(val, kp); if (ret < 0) return ret; max_loop_specified = true; return 0; } static const struct kernel_param_ops max_loop_param_ops = { .set = max_loop_param_set_int, .get = param_get_int, }; module_param_cb(max_loop, &max_loop_param_ops, &max_loop, 0444); MODULE_PARM_DESC(max_loop, "Maximum number of loop devices"); #else module_param(max_loop, int, 0444); MODULE_PARM_DESC(max_loop, "Initial number of loop devices"); #endif module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device"); static int hw_queue_depth = LOOP_DEFAULT_HW_Q_DEPTH; static int loop_set_hw_queue_depth(const char *s, const struct kernel_param *p) { int qd, ret; ret = kstrtoint(s, 0, &qd); if (ret < 0) return ret; if (qd < 1) return -EINVAL; hw_queue_depth = qd; return 0; } static const struct kernel_param_ops loop_hw_qdepth_param_ops = { .set = loop_set_hw_queue_depth, .get = param_get_int, }; device_param_cb(hw_queue_depth, &loop_hw_qdepth_param_ops, &hw_queue_depth, 0444); MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: " __stringify(LOOP_DEFAULT_HW_Q_DEPTH)); MODULE_DESCRIPTION("Loopback device support"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR); static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { struct request *rq = bd->rq; struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); struct loop_device *lo = rq->q->queuedata; blk_mq_start_request(rq); if (lo->lo_state != Lo_bound) return BLK_STS_IOERR; switch (req_op(rq)) { case REQ_OP_FLUSH: case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: cmd->use_aio = false; break; default: cmd->use_aio = lo->lo_flags & LO_FLAGS_DIRECT_IO; break; } /* always use the first bio's css */ cmd->blkcg_css = NULL; cmd->memcg_css = NULL; #ifdef CONFIG_BLK_CGROUP if (rq->bio) { cmd->blkcg_css = bio_blkcg_css(rq->bio); #ifdef CONFIG_MEMCG if (cmd->blkcg_css) { cmd->memcg_css = cgroup_get_e_css(cmd->blkcg_css->cgroup, &memory_cgrp_subsys); } #endif } #endif loop_queue_work(lo, cmd); return BLK_STS_OK; } static void loop_handle_cmd(struct loop_cmd *cmd) { struct cgroup_subsys_state *cmd_blkcg_css = cmd->blkcg_css; struct cgroup_subsys_state *cmd_memcg_css = cmd->memcg_css; struct request *rq = blk_mq_rq_from_pdu(cmd); const bool write = op_is_write(req_op(rq)); struct loop_device *lo = rq->q->queuedata; int ret = 0; struct mem_cgroup *old_memcg = NULL; if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) { ret = -EIO; goto failed; } if (cmd_blkcg_css) kthread_associate_blkcg(cmd_blkcg_css); if (cmd_memcg_css) old_memcg = set_active_memcg( mem_cgroup_from_css(cmd_memcg_css)); /* * do_req_filebacked() may call blk_mq_complete_request() synchronously * or asynchronously if using aio. Hence, do not touch 'cmd' after * do_req_filebacked() has returned unless we are sure that 'cmd' has * not yet been completed. */ ret = do_req_filebacked(lo, rq); if (cmd_blkcg_css) kthread_associate_blkcg(NULL); if (cmd_memcg_css) { set_active_memcg(old_memcg); css_put(cmd_memcg_css); } failed: /* complete non-aio request */ if (ret != -EIOCBQUEUED) { if (ret == -EOPNOTSUPP) cmd->ret = ret; else cmd->ret = ret ? -EIO : 0; if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq); } } static void loop_process_work(struct loop_worker *worker, struct list_head *cmd_list, struct loop_device *lo) { int orig_flags = current->flags; struct loop_cmd *cmd; current->flags |= PF_LOCAL_THROTTLE | PF_MEMALLOC_NOIO; spin_lock_irq(&lo->lo_work_lock); while (!list_empty(cmd_list)) { cmd = container_of( cmd_list->next, struct loop_cmd, list_entry); list_del(cmd_list->next); spin_unlock_irq(&lo->lo_work_lock); loop_handle_cmd(cmd); cond_resched(); spin_lock_irq(&lo->lo_work_lock); } /* * We only add to the idle list if there are no pending cmds * *and* the worker will not run again which ensures that it * is safe to free any worker on the idle list */ if (worker && !work_pending(&worker->work)) { worker->last_ran_at = jiffies; list_add_tail(&worker->idle_list, &lo->idle_worker_list); loop_set_timer(lo); } spin_unlock_irq(&lo->lo_work_lock); current->flags = orig_flags; } static void loop_workfn(struct work_struct *work) { struct loop_worker *worker = container_of(work, struct loop_worker, work); loop_process_work(worker, &worker->cmd_list, worker->lo); } static void loop_rootcg_workfn(struct work_struct *work) { struct loop_device *lo = container_of(work, struct loop_device, rootcg_work); loop_process_work(NULL, &lo->rootcg_cmd_list, lo); } static const struct blk_mq_ops loop_mq_ops = { .queue_rq = loop_queue_rq, .complete = lo_complete_rq, }; static int loop_add(int i) { struct queue_limits lim = { /* * Random number picked from the historic block max_sectors cap. */ .max_hw_sectors = 2560u, }; struct loop_device *lo; struct gendisk *disk; int err; err = -ENOMEM; lo = kzalloc(sizeof(*lo), GFP_KERNEL); if (!lo) goto out; lo->worker_tree = RB_ROOT; INIT_LIST_HEAD(&lo->idle_worker_list); timer_setup(&lo->timer, loop_free_idle_workers_timer, TIMER_DEFERRABLE); lo->lo_state = Lo_unbound; err = mutex_lock_killable(&loop_ctl_mutex); if (err) goto out_free_dev; /* allocate id, if @id >= 0, we're requesting that specific id */ if (i >= 0) { err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL); if (err == -ENOSPC) err = -EEXIST; } else { err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL); } mutex_unlock(&loop_ctl_mutex); if (err < 0) goto out_free_dev; i = err; lo->tag_set.ops = &loop_mq_ops; lo->tag_set.nr_hw_queues = 1; lo->tag_set.queue_depth = hw_queue_depth; lo->tag_set.numa_node = NUMA_NO_NODE; lo->tag_set.cmd_size = sizeof(struct loop_cmd); lo->tag_set.flags = BLK_MQ_F_STACKING | BLK_MQ_F_NO_SCHED_BY_DEFAULT; lo->tag_set.driver_data = lo; err = blk_mq_alloc_tag_set(&lo->tag_set); if (err) goto out_free_idr; disk = lo->lo_disk = blk_mq_alloc_disk(&lo->tag_set, &lim, lo); if (IS_ERR(disk)) { err = PTR_ERR(disk); goto out_cleanup_tags; } lo->lo_queue = lo->lo_disk->queue; /* * Disable partition scanning by default. The in-kernel partition * scanning can be requested individually per-device during its * setup. Userspace can always add and remove partitions from all * devices. The needed partition minors are allocated from the * extended minor space, the main loop device numbers will continue * to match the loop minors, regardless of the number of partitions * used. * * If max_part is given, partition scanning is globally enabled for * all loop devices. The minors for the main loop devices will be * multiples of max_part. * * Note: Global-for-all-devices, set-only-at-init, read-only module * parameteters like 'max_loop' and 'max_part' make things needlessly * complicated, are too static, inflexible and may surprise * userspace tools. Parameters like this in general should be avoided. */ if (!part_shift) set_bit(GD_SUPPRESS_PART_SCAN, &disk->state); mutex_init(&lo->lo_mutex); lo->lo_number = i; spin_lock_init(&lo->lo_lock); spin_lock_init(&lo->lo_work_lock); INIT_WORK(&lo->rootcg_work, loop_rootcg_workfn); INIT_LIST_HEAD(&lo->rootcg_cmd_list); disk->major = LOOP_MAJOR; disk->first_minor = i << part_shift; disk->minors = 1 << part_shift; disk->fops = &lo_fops; disk->private_data = lo; disk->queue = lo->lo_queue; disk->events = DISK_EVENT_MEDIA_CHANGE; disk->event_flags = DISK_EVENT_FLAG_UEVENT; sprintf(disk->disk_name, "loop%d", i); /* Make this loop device reachable from pathname. */ err = add_disk(disk); if (err) goto out_cleanup_disk; /* Show this loop device. */ mutex_lock(&loop_ctl_mutex); lo->idr_visible = true; mutex_unlock(&loop_ctl_mutex); return i; out_cleanup_disk: put_disk(disk); out_cleanup_tags: blk_mq_free_tag_set(&lo->tag_set); out_free_idr: mutex_lock(&loop_ctl_mutex); idr_remove(&loop_index_idr, i); mutex_unlock(&loop_ctl_mutex); out_free_dev: kfree(lo); out: return err; } static void loop_remove(struct loop_device *lo) { /* Make this loop device unreachable from pathname. */ del_gendisk(lo->lo_disk); blk_mq_free_tag_set(&lo->tag_set); mutex_lock(&loop_ctl_mutex); idr_remove(&loop_index_idr, lo->lo_number); mutex_unlock(&loop_ctl_mutex); put_disk(lo->lo_disk); } #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD static void loop_probe(dev_t dev) { int idx = MINOR(dev) >> part_shift; if (max_loop_specified && max_loop && idx >= max_loop) return; loop_add(idx); } #else #define loop_probe NULL #endif /* !CONFIG_BLOCK_LEGACY_AUTOLOAD */ static int loop_control_remove(int idx) { struct loop_device *lo; int ret; if (idx < 0) { pr_warn_once("deleting an unspecified loop device is not supported.\n"); return -EINVAL; } /* Hide this loop device for serialization. */ ret = mutex_lock_killable(&loop_ctl_mutex); if (ret) return ret; lo = idr_find(&loop_index_idr, idx); if (!lo || !lo->idr_visible) ret = -ENODEV; else lo->idr_visible = false; mutex_unlock(&loop_ctl_mutex); if (ret) return ret; /* Check whether this loop device can be removed. */ ret = mutex_lock_killable(&lo->lo_mutex); if (ret) goto mark_visible; if (lo->lo_state != Lo_unbound || disk_openers(lo->lo_disk) > 0) { mutex_unlock(&lo->lo_mutex); ret = -EBUSY; goto mark_visible; } /* Mark this loop device as no more bound, but not quite unbound yet */ lo->lo_state = Lo_deleting; mutex_unlock(&lo->lo_mutex); loop_remove(lo); return 0; mark_visible: /* Show this loop device again. */ mutex_lock(&loop_ctl_mutex); lo->idr_visible = true; mutex_unlock(&loop_ctl_mutex); return ret; } static int loop_control_get_free(int idx) { struct loop_device *lo; int id, ret; ret = mutex_lock_killable(&loop_ctl_mutex); if (ret) return ret; idr_for_each_entry(&loop_index_idr, lo, id) { /* Hitting a race results in creating a new loop device which is harmless. */ if (lo->idr_visible && data_race(lo->lo_state) == Lo_unbound) goto found; } mutex_unlock(&loop_ctl_mutex); return loop_add(-1); found: mutex_unlock(&loop_ctl_mutex); return id; } static long loop_control_ioctl(struct file *file, unsigned int cmd, unsigned long parm) { switch (cmd) { case LOOP_CTL_ADD: return loop_add(parm); case LOOP_CTL_REMOVE: return loop_control_remove(parm); case LOOP_CTL_GET_FREE: return loop_control_get_free(parm); default: return -ENOSYS; } } static const struct file_operations loop_ctl_fops = { .open = nonseekable_open, .unlocked_ioctl = loop_control_ioctl, .compat_ioctl = loop_control_ioctl, .owner = THIS_MODULE, .llseek = noop_llseek, }; static struct miscdevice loop_misc = { .minor = LOOP_CTRL_MINOR, .name = "loop-control", .fops = &loop_ctl_fops, }; MODULE_ALIAS_MISCDEV(LOOP_CTRL_MINOR); MODULE_ALIAS("devname:loop-control"); static int __init loop_init(void) { int i; int err; part_shift = 0; if (max_part > 0) { part_shift = fls(max_part); /* * Adjust max_part according to part_shift as it is exported * to user space so that user can decide correct minor number * if [s]he want to create more devices. * * Note that -1 is required because partition 0 is reserved * for the whole disk. */ max_part = (1UL << part_shift) - 1; } if ((1UL << part_shift) > DISK_MAX_PARTS) { err = -EINVAL; goto err_out; } if (max_loop > 1UL << (MINORBITS - part_shift)) { err = -EINVAL; goto err_out; } err = misc_register(&loop_misc); if (err < 0) goto err_out; if (__register_blkdev(LOOP_MAJOR, "loop", loop_probe)) { err = -EIO; goto misc_out; } /* pre-create number of devices given by config or max_loop */ for (i = 0; i < max_loop; i++) loop_add(i); printk(KERN_INFO "loop: module loaded\n"); return 0; misc_out: misc_deregister(&loop_misc); err_out: return err; } static void __exit loop_exit(void) { struct loop_device *lo; int id; unregister_blkdev(LOOP_MAJOR, "loop"); misc_deregister(&loop_misc); /* * There is no need to use loop_ctl_mutex here, for nobody else can * access loop_index_idr when this module is unloading (unless forced * module unloading is requested). If this is not a clean unloading, * we have no means to avoid kernel crash. */ idr_for_each_entry(&loop_index_idr, lo, id) loop_remove(lo); idr_destroy(&loop_index_idr); } module_init(loop_init); module_exit(loop_exit); #ifndef MODULE static int __init max_loop_setup(char *str) { max_loop = simple_strtol(str, NULL, 0); #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD max_loop_specified = true; #endif return 1; } __setup("max_loop=", max_loop_setup); #endif |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 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 | // SPDX-License-Identifier: GPL-2.0-only /* * mac80211 configuration hooks for cfg80211 * * Copyright 2006-2010 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH * Copyright (C) 2018-2025 Intel Corporation */ #include <linux/ieee80211.h> #include <linux/nl80211.h> #include <linux/rtnetlink.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <linux/rcupdate.h> #include <linux/fips.h> #include <linux/if_ether.h> #include <net/cfg80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" #include "mesh.h" #include "wme.h" static struct ieee80211_link_data * ieee80211_link_or_deflink(struct ieee80211_sub_if_data *sdata, int link_id, bool require_valid) { struct ieee80211_link_data *link; if (link_id < 0) { /* * For keys, if sdata is not an MLD, we might not use * the return value at all (if it's not a pairwise key), * so in that case (require_valid==false) don't error. */ if (require_valid && ieee80211_vif_is_mld(&sdata->vif)) return ERR_PTR(-EINVAL); return &sdata->deflink; } link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return ERR_PTR(-ENOLINK); return link; } static void ieee80211_set_mu_mimo_follow(struct ieee80211_sub_if_data *sdata, struct vif_params *params) { bool mu_mimo_groups = false; bool mu_mimo_follow = false; if (params->vht_mumimo_groups) { u64 membership; BUILD_BUG_ON(sizeof(membership) != WLAN_MEMBERSHIP_LEN); memcpy(sdata->vif.bss_conf.mu_group.membership, params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN); memcpy(sdata->vif.bss_conf.mu_group.position, params->vht_mumimo_groups + WLAN_MEMBERSHIP_LEN, WLAN_USER_POSITION_LEN); ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_MU_GROUPS); /* don't care about endianness - just check for 0 */ memcpy(&membership, params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN); mu_mimo_groups = membership != 0; } if (params->vht_mumimo_follow_addr) { mu_mimo_follow = is_valid_ether_addr(params->vht_mumimo_follow_addr); ether_addr_copy(sdata->u.mntr.mu_follow_addr, params->vht_mumimo_follow_addr); } sdata->vif.bss_conf.mu_mimo_owner = mu_mimo_groups || mu_mimo_follow; } static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, struct vif_params *params) { struct ieee80211_local *local = sdata->local; struct ieee80211_sub_if_data *monitor_sdata; /* check flags first */ if (params->flags && ieee80211_sdata_running(sdata)) { u32 mask = MONITOR_FLAG_ACTIVE; /* * Prohibit MONITOR_FLAG_ACTIVE to be changed * while the interface is up. * Else we would need to add a lot of cruft * to update everything: * monitor and all fif_* counters * reconfigure hardware */ if ((params->flags & mask) != (sdata->u.mntr.flags & mask)) return -EBUSY; } /* also validate MU-MIMO change */ if (ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) monitor_sdata = sdata; else monitor_sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!monitor_sdata && (params->vht_mumimo_groups || params->vht_mumimo_follow_addr)) return -EOPNOTSUPP; /* apply all changes now - no failures allowed */ if (monitor_sdata && (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) || ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR))) ieee80211_set_mu_mimo_follow(monitor_sdata, params); if (params->flags) { if (ieee80211_sdata_running(sdata)) { ieee80211_adjust_monitor_flags(sdata, -1); sdata->u.mntr.flags = params->flags; ieee80211_adjust_monitor_flags(sdata, 1); ieee80211_configure_filter(local); } else { /* * Because the interface is down, ieee80211_do_stop * and ieee80211_do_open take care of "everything" * mentioned in the comment above. */ sdata->u.mntr.flags = params->flags; } } return 0; } static int ieee80211_set_ap_mbssid_options(struct ieee80211_sub_if_data *sdata, struct cfg80211_mbssid_config *params, struct ieee80211_bss_conf *link_conf) { struct ieee80211_sub_if_data *tx_sdata; struct ieee80211_bss_conf *old; link_conf->bssid_index = 0; link_conf->nontransmitted = false; link_conf->ema_ap = false; link_conf->bssid_indicator = 0; if (sdata->vif.type != NL80211_IFTYPE_AP || !params->tx_wdev) return -EINVAL; old = sdata_dereference(link_conf->tx_bss_conf, sdata); if (old) return -EALREADY; tx_sdata = IEEE80211_WDEV_TO_SUB_IF(params->tx_wdev); if (!tx_sdata) return -EINVAL; if (tx_sdata == sdata) { rcu_assign_pointer(link_conf->tx_bss_conf, link_conf); } else { struct ieee80211_bss_conf *tx_bss_conf; tx_bss_conf = sdata_dereference(tx_sdata->vif.link_conf[params->tx_link_id], sdata); if (rcu_access_pointer(tx_bss_conf->tx_bss_conf) != tx_bss_conf) return -EINVAL; rcu_assign_pointer(link_conf->tx_bss_conf, tx_bss_conf); link_conf->nontransmitted = true; link_conf->bssid_index = params->index; link_conf->bssid_indicator = tx_bss_conf->bssid_indicator; } if (params->ema) link_conf->ema_ap = true; return 0; } static struct wireless_dev *ieee80211_add_iface(struct wiphy *wiphy, const char *name, unsigned char name_assign_type, enum nl80211_iftype type, struct vif_params *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct wireless_dev *wdev; struct ieee80211_sub_if_data *sdata; int err; err = ieee80211_if_add(local, name, name_assign_type, &wdev, type, params); if (err) return ERR_PTR(err); sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (type == NL80211_IFTYPE_MONITOR) { err = ieee80211_set_mon_options(sdata, params); if (err) { ieee80211_if_remove(sdata); return NULL; } } /* Let the driver know that an interface is going to be added. * Indicate so only for interface types that will be added to the * driver. */ switch (type) { case NL80211_IFTYPE_AP_VLAN: break; case NL80211_IFTYPE_MONITOR: if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) || !(params->flags & MONITOR_FLAG_ACTIVE)) break; fallthrough; default: drv_prep_add_interface(local, ieee80211_vif_type_p2p(&sdata->vif)); break; } return wdev; } static int ieee80211_del_iface(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_if_remove(IEEE80211_WDEV_TO_SUB_IF(wdev)); return 0; } static int ieee80211_change_iface(struct wiphy *wiphy, struct net_device *dev, enum nl80211_iftype type, struct vif_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret; lockdep_assert_wiphy(local->hw.wiphy); ret = ieee80211_if_change_type(sdata, type); if (ret) return ret; if (type == NL80211_IFTYPE_AP_VLAN && params->use_4addr == 0) { RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); ieee80211_check_fast_rx_iface(sdata); } else if (type == NL80211_IFTYPE_STATION && params->use_4addr >= 0) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; if (params->use_4addr == ifmgd->use_4addr) return 0; /* FIXME: no support for 4-addr MLO yet */ if (ieee80211_vif_is_mld(&sdata->vif)) return -EOPNOTSUPP; sdata->u.mgd.use_4addr = params->use_4addr; if (!ifmgd->associated) return 0; sta = sta_info_get(sdata, sdata->deflink.u.mgd.bssid); if (sta) drv_sta_set_4addr(local, sdata, &sta->sta, params->use_4addr); if (params->use_4addr) ieee80211_send_4addr_nullfunc(local, sdata); } if (sdata->vif.type == NL80211_IFTYPE_MONITOR) { ret = ieee80211_set_mon_options(sdata, params); if (ret) return ret; } return 0; } static int ieee80211_start_p2p_device(struct wiphy *wiphy, struct wireless_dev *wdev) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; lockdep_assert_wiphy(sdata->local->hw.wiphy); ret = ieee80211_check_combinations(sdata, NULL, 0, 0, -1); if (ret < 0) return ret; return ieee80211_do_open(wdev, true); } static void ieee80211_stop_p2p_device(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_sdata_stop(IEEE80211_WDEV_TO_SUB_IF(wdev)); } static int ieee80211_start_nan(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; lockdep_assert_wiphy(sdata->local->hw.wiphy); ret = ieee80211_check_combinations(sdata, NULL, 0, 0, -1); if (ret < 0) return ret; ret = ieee80211_do_open(wdev, true); if (ret) return ret; ret = drv_start_nan(sdata->local, sdata, conf); if (ret) ieee80211_sdata_stop(sdata); sdata->u.nan.conf = *conf; return ret; } static void ieee80211_stop_nan(struct wiphy *wiphy, struct wireless_dev *wdev) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); drv_stop_nan(sdata->local, sdata); ieee80211_sdata_stop(sdata); } static int ieee80211_nan_change_conf(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_conf *conf, u32 changes) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct cfg80211_nan_conf new_conf; int ret = 0; if (sdata->vif.type != NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; new_conf = sdata->u.nan.conf; if (changes & CFG80211_NAN_CONF_CHANGED_PREF) new_conf.master_pref = conf->master_pref; if (changes & CFG80211_NAN_CONF_CHANGED_BANDS) new_conf.bands = conf->bands; ret = drv_nan_change_conf(sdata->local, sdata, &new_conf, changes); if (!ret) sdata->u.nan.conf = new_conf; return ret; } static int ieee80211_add_nan_func(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_nan_func *nan_func) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); int ret; if (sdata->vif.type != NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; spin_lock_bh(&sdata->u.nan.func_lock); ret = idr_alloc(&sdata->u.nan.function_inst_ids, nan_func, 1, sdata->local->hw.max_nan_de_entries + 1, GFP_ATOMIC); spin_unlock_bh(&sdata->u.nan.func_lock); if (ret < 0) return ret; nan_func->instance_id = ret; WARN_ON(nan_func->instance_id == 0); ret = drv_add_nan_func(sdata->local, sdata, nan_func); if (ret) { spin_lock_bh(&sdata->u.nan.func_lock); idr_remove(&sdata->u.nan.function_inst_ids, nan_func->instance_id); spin_unlock_bh(&sdata->u.nan.func_lock); } return ret; } static struct cfg80211_nan_func * ieee80211_find_nan_func_by_cookie(struct ieee80211_sub_if_data *sdata, u64 cookie) { struct cfg80211_nan_func *func; int id; lockdep_assert_held(&sdata->u.nan.func_lock); idr_for_each_entry(&sdata->u.nan.function_inst_ids, func, id) { if (func->cookie == cookie) return func; } return NULL; } static void ieee80211_del_nan_func(struct wiphy *wiphy, struct wireless_dev *wdev, u64 cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct cfg80211_nan_func *func; u8 instance_id = 0; if (sdata->vif.type != NL80211_IFTYPE_NAN || !ieee80211_sdata_running(sdata)) return; spin_lock_bh(&sdata->u.nan.func_lock); func = ieee80211_find_nan_func_by_cookie(sdata, cookie); if (func) instance_id = func->instance_id; spin_unlock_bh(&sdata->u.nan.func_lock); if (instance_id) drv_del_nan_func(sdata->local, sdata, instance_id); } static int ieee80211_set_noack_map(struct wiphy *wiphy, struct net_device *dev, u16 noack_map) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); sdata->noack_map = noack_map; ieee80211_check_fast_xmit_iface(sdata); return 0; } static int ieee80211_set_tx(struct ieee80211_sub_if_data *sdata, const u8 *mac_addr, u8 key_idx) { struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; struct sta_info *sta; int ret = -EINVAL; if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_EXT_KEY_ID)) return -EINVAL; sta = sta_info_get_bss(sdata, mac_addr); if (!sta) return -EINVAL; if (sta->ptk_idx == key_idx) return 0; key = wiphy_dereference(local->hw.wiphy, sta->ptk[key_idx]); if (key && key->conf.flags & IEEE80211_KEY_FLAG_NO_AUTO_TX) ret = ieee80211_set_tx_key(key); return ret; } static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr, struct key_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, false); struct ieee80211_local *local = sdata->local; struct sta_info *sta = NULL; struct ieee80211_key *key; int err; lockdep_assert_wiphy(local->hw.wiphy); if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; if (IS_ERR(link)) return PTR_ERR(link); if (WARN_ON(pairwise && link_id >= 0)) return -EINVAL; if (pairwise && params->mode == NL80211_KEY_SET_TX) return ieee80211_set_tx(sdata, mac_addr, key_idx); /* reject WEP and TKIP keys if WEP failed to initialize */ switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_WEP104: if (link_id >= 0) return -EINVAL; if (WARN_ON_ONCE(fips_enabled)) return -EINVAL; break; default: break; } key = ieee80211_key_alloc(params->cipher, key_idx, params->key_len, params->key, params->seq_len, params->seq); if (IS_ERR(key)) return PTR_ERR(key); if (pairwise) { key->conf.flags |= IEEE80211_KEY_FLAG_PAIRWISE; key->conf.link_id = -1; } else { key->conf.link_id = link->link_id; } if (params->mode == NL80211_KEY_NO_TX) key->conf.flags |= IEEE80211_KEY_FLAG_NO_AUTO_TX; if (mac_addr) { sta = sta_info_get_bss(sdata, mac_addr); /* * The ASSOC test makes sure the driver is ready to * receive the key. When wpa_supplicant has roamed * using FT, it attempts to set the key before * association has completed, this rejects that attempt * so it will set the key again after association. * * TODO: accept the key if we have a station entry and * add it to the device after the station. */ if (!sta || !test_sta_flag(sta, WLAN_STA_ASSOC)) { ieee80211_key_free_unused(key); return -ENOENT; } } switch (sdata->vif.type) { case NL80211_IFTYPE_STATION: if (sdata->u.mgd.mfp != IEEE80211_MFP_DISABLED) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: /* Keys without a station are used for TX only */ if (sta && test_sta_flag(sta, WLAN_STA_MFP)) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; case NL80211_IFTYPE_ADHOC: /* no MFP (yet) */ break; case NL80211_IFTYPE_MESH_POINT: #ifdef CONFIG_MAC80211_MESH if (sdata->u.mesh.security != IEEE80211_MESH_SEC_NONE) key->conf.flags |= IEEE80211_KEY_FLAG_RX_MGMT; break; #endif case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_MONITOR: case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_NAN: case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_OCB: /* shouldn't happen */ WARN_ON_ONCE(1); break; } err = ieee80211_key_link(key, link, sta); /* KRACK protection, shouldn't happen but just silently accept key */ if (err == -EALREADY) err = 0; return err; } static struct ieee80211_key * ieee80211_lookup_key(struct ieee80211_sub_if_data *sdata, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr) { struct ieee80211_local *local __maybe_unused = sdata->local; struct ieee80211_link_data *link = &sdata->deflink; struct ieee80211_key *key; if (link_id >= 0) { link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return NULL; } if (mac_addr) { struct sta_info *sta; struct link_sta_info *link_sta; sta = sta_info_get_bss(sdata, mac_addr); if (!sta) return NULL; if (link_id >= 0) { link_sta = rcu_dereference_check(sta->link[link_id], lockdep_is_held(&local->hw.wiphy->mtx)); if (!link_sta) return NULL; } else { link_sta = &sta->deflink; } if (pairwise && key_idx < NUM_DEFAULT_KEYS) return wiphy_dereference(local->hw.wiphy, sta->ptk[key_idx]); if (!pairwise && key_idx < NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + NUM_DEFAULT_BEACON_KEYS) return wiphy_dereference(local->hw.wiphy, link_sta->gtk[key_idx]); return NULL; } if (pairwise && key_idx < NUM_DEFAULT_KEYS) return wiphy_dereference(local->hw.wiphy, sdata->keys[key_idx]); key = wiphy_dereference(local->hw.wiphy, link->gtk[key_idx]); if (key) return key; /* or maybe it was a WEP key */ if (key_idx < NUM_DEFAULT_KEYS) return wiphy_dereference(local->hw.wiphy, sdata->keys[key_idx]); return NULL; } static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_key *key; lockdep_assert_wiphy(local->hw.wiphy); key = ieee80211_lookup_key(sdata, link_id, key_idx, pairwise, mac_addr); if (!key) return -ENOENT; ieee80211_key_free(key, sdata->vif.type == NL80211_IFTYPE_STATION); return 0; } static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool pairwise, const u8 *mac_addr, void *cookie, void (*callback)(void *cookie, struct key_params *params)) { struct ieee80211_sub_if_data *sdata; u8 seq[6] = {0}; struct key_params params; struct ieee80211_key *key; u64 pn64; u32 iv32; u16 iv16; int err = -ENOENT; struct ieee80211_key_seq kseq = {}; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); key = ieee80211_lookup_key(sdata, link_id, key_idx, pairwise, mac_addr); if (!key) goto out; memset(¶ms, 0, sizeof(params)); params.cipher = key->conf.cipher; switch (key->conf.cipher) { case WLAN_CIPHER_SUITE_TKIP: pn64 = atomic64_read(&key->conf.tx_pn); iv32 = TKIP_PN_TO_IV32(pn64); iv16 = TKIP_PN_TO_IV16(pn64); if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { drv_get_key_seq(sdata->local, key, &kseq); iv32 = kseq.tkip.iv32; iv16 = kseq.tkip.iv16; } seq[0] = iv16 & 0xff; seq[1] = (iv16 >> 8) & 0xff; seq[2] = iv32 & 0xff; seq[3] = (iv32 >> 8) & 0xff; seq[4] = (iv32 >> 16) & 0xff; seq[5] = (iv32 >> 24) & 0xff; params.seq = seq; params.seq_len = 6; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), aes_cmac)); fallthrough; case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), aes_gmac)); fallthrough; case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: BUILD_BUG_ON(offsetof(typeof(kseq), ccmp) != offsetof(typeof(kseq), gcmp)); if (key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE && !(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { drv_get_key_seq(sdata->local, key, &kseq); memcpy(seq, kseq.ccmp.pn, 6); } else { pn64 = atomic64_read(&key->conf.tx_pn); seq[0] = pn64; seq[1] = pn64 >> 8; seq[2] = pn64 >> 16; seq[3] = pn64 >> 24; seq[4] = pn64 >> 32; seq[5] = pn64 >> 40; } params.seq = seq; params.seq_len = 6; break; default: if (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)) break; if (WARN_ON(key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV)) break; drv_get_key_seq(sdata->local, key, &kseq); params.seq = kseq.hw.seq; params.seq_len = kseq.hw.seq_len; break; } callback(cookie, ¶ms); err = 0; out: rcu_read_unlock(); return err; } static int ieee80211_config_default_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx, bool uni, bool multi) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, false); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_key(link, key_idx, uni, multi); return 0; } static int ieee80211_config_default_mgmt_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, true); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_mgmt_key(link, key_idx); return 0; } static int ieee80211_config_default_beacon_key(struct wiphy *wiphy, struct net_device *dev, int link_id, u8 key_idx) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, link_id, true); if (IS_ERR(link)) return PTR_ERR(link); ieee80211_set_default_beacon_key(link, key_idx); return 0; } void sta_set_rate_info_tx(struct sta_info *sta, const struct ieee80211_tx_rate *rate, struct rate_info *rinfo) { rinfo->flags = 0; if (rate->flags & IEEE80211_TX_RC_MCS) { rinfo->flags |= RATE_INFO_FLAGS_MCS; rinfo->mcs = rate->idx; } else if (rate->flags & IEEE80211_TX_RC_VHT_MCS) { rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS; rinfo->mcs = ieee80211_rate_get_vht_mcs(rate); rinfo->nss = ieee80211_rate_get_vht_nss(rate); } else { struct ieee80211_supported_band *sband; sband = ieee80211_get_sband(sta->sdata); WARN_ON_ONCE(sband && !sband->bitrates); if (sband && sband->bitrates) rinfo->legacy = sband->bitrates[rate->idx].bitrate; } if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH) rinfo->bw = RATE_INFO_BW_40; else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH) rinfo->bw = RATE_INFO_BW_80; else if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH) rinfo->bw = RATE_INFO_BW_160; else rinfo->bw = RATE_INFO_BW_20; if (rate->flags & IEEE80211_TX_RC_SHORT_GI) rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; } static int ieee80211_dump_station(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *mac, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret = -ENOENT; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get_by_idx(sdata, idx); if (sta) { ret = 0; memcpy(mac, sta->sta.addr, ETH_ALEN); sta_set_sinfo(sta, sinfo, true); /* Add accumulated removed link data to sinfo data for * consistency for MLO */ if (sinfo->valid_links) sta_set_accumulated_removed_links_sinfo(sta, sinfo); } return ret; } static int ieee80211_dump_survey(struct wiphy *wiphy, struct net_device *dev, int idx, struct survey_info *survey) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); return drv_get_survey(local, idx, survey); } static int ieee80211_get_station(struct wiphy *wiphy, struct net_device *dev, const u8 *mac, struct station_info *sinfo) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct sta_info *sta; int ret = -ENOENT; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get_bss(sdata, mac); if (sta) { ret = 0; sta_set_sinfo(sta, sinfo, true); /* Add accumulated removed link data to sinfo data for * consistency for MLO */ if (sinfo->valid_links) sta_set_accumulated_removed_links_sinfo(sta, sinfo); } return ret; } static int ieee80211_set_monitor_channel(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; struct ieee80211_chan_req chanreq = { .oper = *chandef }; int ret; lockdep_assert_wiphy(local->hw.wiphy); sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (!ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) { if (cfg80211_chandef_identical(&local->monitor_chanreq.oper, &chanreq.oper)) return 0; sdata = wiphy_dereference(wiphy, local->monitor_sdata); if (!sdata) goto done; } if (rcu_access_pointer(sdata->deflink.conf->chanctx_conf) && cfg80211_chandef_identical(&sdata->vif.bss_conf.chanreq.oper, &chanreq.oper)) return 0; ieee80211_link_release_channel(&sdata->deflink); ret = ieee80211_link_use_channel(&sdata->deflink, &chanreq, IEEE80211_CHANCTX_SHARED); if (ret) return ret; done: local->monitor_chanreq = chanreq; return 0; } static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata, const u8 *resp, size_t resp_len, const struct ieee80211_csa_settings *csa, const struct ieee80211_color_change_settings *cca, struct ieee80211_link_data *link) { struct probe_resp *new, *old; if (!resp || !resp_len) return 1; old = sdata_dereference(link->u.ap.probe_resp, sdata); new = kzalloc(sizeof(struct probe_resp) + resp_len, GFP_KERNEL); if (!new) return -ENOMEM; new->len = resp_len; memcpy(new->data, resp, resp_len); if (csa) memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_presp, csa->n_counter_offsets_presp * sizeof(new->cntdwn_counter_offsets[0])); else if (cca) new->cntdwn_counter_offsets[0] = cca->counter_offset_presp; rcu_assign_pointer(link->u.ap.probe_resp, new); if (old) kfree_rcu(old, rcu_head); return 0; } static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata, struct cfg80211_fils_discovery *params, struct ieee80211_link_data *link, struct ieee80211_bss_conf *link_conf, u64 *changed) { struct fils_discovery_data *new, *old = NULL; struct ieee80211_fils_discovery *fd; if (!params->update) return 0; fd = &link_conf->fils_discovery; fd->min_interval = params->min_interval; fd->max_interval = params->max_interval; old = sdata_dereference(link->u.ap.fils_discovery, sdata); if (old) kfree_rcu(old, rcu_head); if (params->tmpl && params->tmpl_len) { new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL); if (!new) return -ENOMEM; new->len = params->tmpl_len; memcpy(new->data, params->tmpl, params->tmpl_len); rcu_assign_pointer(link->u.ap.fils_discovery, new); } else { RCU_INIT_POINTER(link->u.ap.fils_discovery, NULL); } *changed |= BSS_CHANGED_FILS_DISCOVERY; return 0; } static int ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata, struct cfg80211_unsol_bcast_probe_resp *params, struct ieee80211_link_data *link, struct ieee80211_bss_conf *link_conf, u64 *changed) { struct unsol_bcast_probe_resp_data *new, *old = NULL; if (!params->update) return 0; link_conf->unsol_bcast_probe_resp_interval = params->interval; old = sdata_dereference(link->u.ap.unsol_bcast_probe_resp, sdata); if (old) kfree_rcu(old, rcu_head); if (params->tmpl && params->tmpl_len) { new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL); if (!new) return -ENOMEM; new->len = params->tmpl_len; memcpy(new->data, params->tmpl, params->tmpl_len); rcu_assign_pointer(link->u.ap.unsol_bcast_probe_resp, new); } else { RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL); } *changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP; return 0; } static int ieee80211_set_s1g_short_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, struct cfg80211_s1g_short_beacon *params) { struct s1g_short_beacon_data *new; struct s1g_short_beacon_data *old = sdata_dereference(link->u.ap.s1g_short_beacon, sdata); size_t new_len = sizeof(*new) + params->short_head_len + params->short_tail_len; if (!params->update) return 0; if (!params->short_head) return -EINVAL; new = kzalloc(new_len, GFP_KERNEL); if (!new) return -ENOMEM; /* Memory layout: | struct | head | tail | */ new->short_head = (u8 *)new + sizeof(*new); new->short_head_len = params->short_head_len; memcpy(new->short_head, params->short_head, params->short_head_len); if (params->short_tail) { new->short_tail = new->short_head + params->short_head_len; new->short_tail_len = params->short_tail_len; memcpy(new->short_tail, params->short_tail, params->short_tail_len); } rcu_assign_pointer(link->u.ap.s1g_short_beacon, new); if (old) kfree_rcu(old, rcu_head); return 0; } static int ieee80211_set_ftm_responder_params( struct ieee80211_sub_if_data *sdata, const u8 *lci, size_t lci_len, const u8 *civicloc, size_t civicloc_len, struct ieee80211_bss_conf *link_conf) { struct ieee80211_ftm_responder_params *new, *old; u8 *pos; int len; if (!lci_len && !civicloc_len) return 0; old = link_conf->ftmr_params; len = lci_len + civicloc_len; new = kzalloc(sizeof(*new) + len, GFP_KERNEL); if (!new) return -ENOMEM; pos = (u8 *)(new + 1); if (lci_len) { new->lci_len = lci_len; new->lci = pos; memcpy(pos, lci, lci_len); pos += lci_len; } if (civicloc_len) { new->civicloc_len = civicloc_len; new->civicloc = pos; memcpy(pos, civicloc, civicloc_len); pos += civicloc_len; } link_conf->ftmr_params = new; kfree(old); return 0; } static int ieee80211_copy_mbssid_beacon(u8 *pos, struct cfg80211_mbssid_elems *dst, struct cfg80211_mbssid_elems *src) { int i, offset = 0; dst->cnt = src->cnt; for (i = 0; i < src->cnt; i++) { memcpy(pos + offset, src->elem[i].data, src->elem[i].len); dst->elem[i].len = src->elem[i].len; dst->elem[i].data = pos + offset; offset += dst->elem[i].len; } return offset; } static int ieee80211_copy_rnr_beacon(u8 *pos, struct cfg80211_rnr_elems *dst, struct cfg80211_rnr_elems *src) { int i, offset = 0; dst->cnt = src->cnt; for (i = 0; i < src->cnt; i++) { memcpy(pos + offset, src->elem[i].data, src->elem[i].len); dst->elem[i].len = src->elem[i].len; dst->elem[i].data = pos + offset; offset += dst->elem[i].len; } return offset; } static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, struct cfg80211_beacon_data *params, const struct ieee80211_csa_settings *csa, const struct ieee80211_color_change_settings *cca, u64 *changed) { struct cfg80211_mbssid_elems *mbssid = NULL; struct cfg80211_rnr_elems *rnr = NULL; struct beacon_data *new, *old; int new_head_len, new_tail_len; int size, err; u64 _changed = BSS_CHANGED_BEACON; struct ieee80211_bss_conf *link_conf = link->conf; old = sdata_dereference(link->u.ap.beacon, sdata); /* Need to have a beacon head if we don't have one yet */ if (!params->head && !old) return -EINVAL; /* new or old head? */ if (params->head) new_head_len = params->head_len; else new_head_len = old->head_len; /* new or old tail? */ if (params->tail || !old) /* params->tail_len will be zero for !params->tail */ new_tail_len = params->tail_len; else new_tail_len = old->tail_len; size = sizeof(*new) + new_head_len + new_tail_len; /* new or old multiple BSSID elements? */ if (params->mbssid_ies) { mbssid = params->mbssid_ies; size += struct_size(new->mbssid_ies, elem, mbssid->cnt); if (params->rnr_ies) { rnr = params->rnr_ies; size += struct_size(new->rnr_ies, elem, rnr->cnt); } size += ieee80211_get_mbssid_beacon_len(mbssid, rnr, mbssid->cnt); } else if (old && old->mbssid_ies) { mbssid = old->mbssid_ies; size += struct_size(new->mbssid_ies, elem, mbssid->cnt); if (old && old->rnr_ies) { rnr = old->rnr_ies; size += struct_size(new->rnr_ies, elem, rnr->cnt); } size += ieee80211_get_mbssid_beacon_len(mbssid, rnr, mbssid->cnt); } new = kzalloc(size, GFP_KERNEL); if (!new) return -ENOMEM; /* start filling the new info now */ /* * pointers go into the block we allocated, * memory is | beacon_data | head | tail | mbssid_ies | rnr_ies */ new->head = ((u8 *) new) + sizeof(*new); new->tail = new->head + new_head_len; new->head_len = new_head_len; new->tail_len = new_tail_len; /* copy in optional mbssid_ies */ if (mbssid) { u8 *pos = new->tail + new->tail_len; new->mbssid_ies = (void *)pos; pos += struct_size(new->mbssid_ies, elem, mbssid->cnt); pos += ieee80211_copy_mbssid_beacon(pos, new->mbssid_ies, mbssid); if (rnr) { new->rnr_ies = (void *)pos; pos += struct_size(new->rnr_ies, elem, rnr->cnt); ieee80211_copy_rnr_beacon(pos, new->rnr_ies, rnr); } /* update bssid_indicator */ if (new->mbssid_ies->cnt && new->mbssid_ies->elem[0].len > 2) link_conf->bssid_indicator = *(new->mbssid_ies->elem[0].data + 2); else link_conf->bssid_indicator = 0; } if (csa) { new->cntdwn_current_counter = csa->count; memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_beacon, csa->n_counter_offsets_beacon * sizeof(new->cntdwn_counter_offsets[0])); } else if (cca) { new->cntdwn_current_counter = cca->count; new->cntdwn_counter_offsets[0] = cca->counter_offset_beacon; } /* copy in head */ if (params->head) memcpy(new->head, params->head, new_head_len); else memcpy(new->head, old->head, new_head_len); /* copy in optional tail */ if (params->tail) memcpy(new->tail, params->tail, new_tail_len); else if (old) memcpy(new->tail, old->tail, new_tail_len); err = ieee80211_set_probe_resp(sdata, params->probe_resp, params->probe_resp_len, csa, cca, link); if (err < 0) { kfree(new); return err; } if (err == 0) _changed |= BSS_CHANGED_AP_PROBE_RESP; if (params->ftm_responder != -1) { link_conf->ftm_responder = params->ftm_responder; err = ieee80211_set_ftm_responder_params(sdata, params->lci, params->lci_len, params->civicloc, params->civicloc_len, link_conf); if (err < 0) { kfree(new); return err; } _changed |= BSS_CHANGED_FTM_RESPONDER; } rcu_assign_pointer(link->u.ap.beacon, new); sdata->u.ap.active = true; if (old) kfree_rcu(old, rcu_head); *changed |= _changed; return 0; } static u8 ieee80211_num_beaconing_links(struct ieee80211_sub_if_data *sdata) { struct ieee80211_link_data *link; u8 link_id, num = 0; if (sdata->vif.type != NL80211_IFTYPE_AP && sdata->vif.type != NL80211_IFTYPE_P2P_GO) return num; /* non-MLO mode of operation also uses link_id 0 in sdata so it is * safe to directly proceed with the below loop */ for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { link = sdata_dereference(sdata->link[link_id], sdata); if (!link) continue; if (sdata_dereference(link->u.ap.beacon, sdata)) num++; } return num; } static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct beacon_data *old; struct ieee80211_sub_if_data *vlan; u64 changed = BSS_CHANGED_BEACON_INT | BSS_CHANGED_BEACON_ENABLED | BSS_CHANGED_BEACON | BSS_CHANGED_P2P_PS | BSS_CHANGED_TXPOWER | BSS_CHANGED_TWT; int i, err; int prev_beacon_int; unsigned int link_id = params->beacon.link_id; struct ieee80211_link_data *link; struct ieee80211_bss_conf *link_conf; struct ieee80211_chan_req chanreq = { .oper = params->chandef }; u64 tsf; lockdep_assert_wiphy(local->hw.wiphy); link = sdata_dereference(sdata->link[link_id], sdata); if (!link) return -ENOLINK; link_conf = link->conf; old = sdata_dereference(link->u.ap.beacon, sdata); if (old) return -EALREADY; link->smps_mode = IEEE80211_SMPS_OFF; link->needed_rx_chains = sdata->local->rx_chains; prev_beacon_int = link_conf->beacon_int; link_conf->beacon_int = params->beacon_interval; if (params->ht_cap) link_conf->ht_ldpc = params->ht_cap->cap_info & cpu_to_le16(IEEE80211_HT_CAP_LDPC_CODING); if (params->vht_cap) { link_conf->vht_ldpc = params->vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_RXLDPC); link_conf->vht_su_beamformer = params->vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE); link_conf->vht_su_beamformee = params->vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE); link_conf->vht_mu_beamformer = params->vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE); link_conf->vht_mu_beamformee = params->vht_cap->vht_cap_info & cpu_to_le32(IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE); } if (params->he_cap && params->he_oper) { link_conf->he_support = true; link_conf->htc_trig_based_pkt_ext = le32_get_bits(params->he_oper->he_oper_params, IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK); link_conf->frame_time_rts_th = le32_get_bits(params->he_oper->he_oper_params, IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK); changed |= BSS_CHANGED_HE_OBSS_PD; if (params->beacon.he_bss_color.enabled) changed |= BSS_CHANGED_HE_BSS_COLOR; } if (params->he_cap) { link_conf->he_ldpc = params->he_cap->phy_cap_info[1] & IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD; link_conf->he_su_beamformer = params->he_cap->phy_cap_info[3] & IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER; link_conf->he_su_beamformee = params->he_cap->phy_cap_info[4] & IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE; link_conf->he_mu_beamformer = params->he_cap->phy_cap_info[4] & IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER; link_conf->he_full_ul_mumimo = params->he_cap->phy_cap_info[2] & IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO; } if (params->eht_cap) { if (!link_conf->he_support) return -EOPNOTSUPP; link_conf->eht_support = true; link_conf->eht_su_beamformer = params->eht_cap->fixed.phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER; link_conf->eht_su_beamformee = params->eht_cap->fixed.phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE; link_conf->eht_mu_beamformer = params->eht_cap->fixed.phy_cap_info[7] & (IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ | IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ); link_conf->eht_80mhz_full_bw_ul_mumimo = params->eht_cap->fixed.phy_cap_info[7] & (IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ | IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ); link_conf->eht_disable_mcs15 = u8_get_bits(params->eht_oper->params, IEEE80211_EHT_OPER_MCS15_DISABLE); } else { link_conf->eht_su_beamformer = false; link_conf->eht_su_beamformee = false; link_conf->eht_mu_beamformer = false; } if (sdata->vif.type == NL80211_IFTYPE_AP && params->mbssid_config.tx_wdev) { err = ieee80211_set_ap_mbssid_options(sdata, ¶ms->mbssid_config, link_conf); if (err) return err; } err = ieee80211_link_use_channel(link, &chanreq, IEEE80211_CHANCTX_SHARED); if (!err) ieee80211_link_copy_chanctx_to_vlans(link, false); if (err) { link_conf->beacon_int = prev_beacon_int; return err; } /* * Apply control port protocol, this allows us to * not encrypt dynamic WEP control frames. */ sdata->control_port_protocol = params->crypto.control_port_ethertype; sdata->control_port_no_encrypt = params->crypto.control_port_no_encrypt; sdata->control_port_over_nl80211 = params->crypto.control_port_over_nl80211; sdata->control_port_no_preauth = params->crypto.control_port_no_preauth; list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { vlan->control_port_protocol = params->crypto.control_port_ethertype; vlan->control_port_no_encrypt = params->crypto.control_port_no_encrypt; vlan->control_port_over_nl80211 = params->crypto.control_port_over_nl80211; vlan->control_port_no_preauth = params->crypto.control_port_no_preauth; } link_conf->dtim_period = params->dtim_period; link_conf->enable_beacon = true; link_conf->allow_p2p_go_ps = sdata->vif.p2p; link_conf->twt_responder = params->twt_responder; link_conf->he_obss_pd = params->he_obss_pd; link_conf->he_bss_color = params->beacon.he_bss_color; link_conf->s1g_long_beacon_period = params->s1g_long_beacon_period; sdata->vif.cfg.s1g = params->chandef.chan->band == NL80211_BAND_S1GHZ; sdata->vif.cfg.ssid_len = params->ssid_len; if (params->ssid_len) memcpy(sdata->vif.cfg.ssid, params->ssid, params->ssid_len); link_conf->hidden_ssid = (params->hidden_ssid != NL80211_HIDDEN_SSID_NOT_IN_USE); memset(&link_conf->p2p_noa_attr, 0, sizeof(link_conf->p2p_noa_attr)); link_conf->p2p_noa_attr.oppps_ctwindow = params->p2p_ctwindow & IEEE80211_P2P_OPPPS_CTWINDOW_MASK; if (params->p2p_opp_ps) link_conf->p2p_noa_attr.oppps_ctwindow |= IEEE80211_P2P_OPPPS_ENABLE_BIT; sdata->beacon_rate_set = false; if (wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_BEACON_RATE_LEGACY)) { for (i = 0; i < NUM_NL80211_BANDS; i++) { sdata->beacon_rateidx_mask[i] = params->beacon_rate.control[i].legacy; if (sdata->beacon_rateidx_mask[i]) sdata->beacon_rate_set = true; } } if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) link_conf->beacon_tx_rate = params->beacon_rate; err = ieee80211_assign_beacon(sdata, link, ¶ms->beacon, NULL, NULL, &changed); if (err < 0) goto error; err = ieee80211_set_fils_discovery(sdata, ¶ms->fils_discovery, link, link_conf, &changed); if (err < 0) goto error; err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, link, link_conf, &changed); if (err < 0) goto error; if (sdata->vif.cfg.s1g) { err = ieee80211_set_s1g_short_beacon(sdata, link, ¶ms->s1g_short_beacon); if (err < 0) goto error; } err = drv_start_ap(sdata->local, sdata, link_conf); if (err) { old = sdata_dereference(link->u.ap.beacon, sdata); if (old) kfree_rcu(old, rcu_head); RCU_INIT_POINTER(link->u.ap.beacon, NULL); if (ieee80211_num_beaconing_links(sdata) == 0) sdata->u.ap.active = false; goto error; } tsf = drv_get_tsf(local, sdata); ieee80211_recalc_dtim(sdata, tsf); if (link->u.ap.s1g_short_beacon) ieee80211_recalc_sb_count(sdata, tsf); ieee80211_vif_cfg_change_notify(sdata, BSS_CHANGED_SSID); ieee80211_link_info_change_notify(sdata, link, changed); if (ieee80211_num_beaconing_links(sdata) <= 1) netif_carrier_on(dev); list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_on(vlan->dev); return 0; error: ieee80211_link_release_channel(link); return err; } static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ap_update *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link; struct cfg80211_beacon_data *beacon = ¶ms->beacon; struct beacon_data *old; int err; struct ieee80211_bss_conf *link_conf; u64 changed = 0; lockdep_assert_wiphy(wiphy); link = sdata_dereference(sdata->link[beacon->link_id], sdata); if (!link) return -ENOLINK; link_conf = link->conf; /* don't allow changing the beacon while a countdown is in place - offset * of channel switch counter may change */ if (link_conf->csa_active || link_conf->color_change_active) return -EBUSY; old = sdata_dereference(link->u.ap.beacon, sdata); if (!old) return -ENOENT; err = ieee80211_assign_beacon(sdata, link, beacon, NULL, NULL, &changed); if (err < 0) return err; err = ieee80211_set_fils_discovery(sdata, ¶ms->fils_discovery, link, link_conf, &changed); if (err < 0) return err; err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, link, link_conf, &changed); if (err < 0) return err; if (link->u.ap.s1g_short_beacon) { err = ieee80211_set_s1g_short_beacon(sdata, link, ¶ms->s1g_short_beacon); if (err < 0) return err; } if (beacon->he_bss_color_valid && beacon->he_bss_color.enabled != link_conf->he_bss_color.enabled) { link_conf->he_bss_color.enabled = beacon->he_bss_color.enabled; changed |= BSS_CHANGED_HE_BSS_COLOR; } ieee80211_link_info_change_notify(sdata, link, changed); return 0; } static void ieee80211_free_next_beacon(struct ieee80211_link_data *link) { if (!link->u.ap.next_beacon) return; kfree(link->u.ap.next_beacon->mbssid_ies); kfree(link->u.ap.next_beacon->rnr_ies); kfree(link->u.ap.next_beacon); link->u.ap.next_beacon = NULL; } static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_sub_if_data *vlan; struct ieee80211_local *local = sdata->local; struct beacon_data *old_beacon; struct probe_resp *old_probe_resp; struct fils_discovery_data *old_fils_discovery; struct unsol_bcast_probe_resp_data *old_unsol_bcast_probe_resp; struct s1g_short_beacon_data *old_s1g_short_beacon; struct cfg80211_chan_def chandef; struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); struct ieee80211_bss_conf *link_conf = link->conf; LIST_HEAD(keys); lockdep_assert_wiphy(local->hw.wiphy); old_beacon = sdata_dereference(link->u.ap.beacon, sdata); if (!old_beacon) return -ENOENT; old_probe_resp = sdata_dereference(link->u.ap.probe_resp, sdata); old_fils_discovery = sdata_dereference(link->u.ap.fils_discovery, sdata); old_unsol_bcast_probe_resp = sdata_dereference(link->u.ap.unsol_bcast_probe_resp, sdata); old_s1g_short_beacon = sdata_dereference(link->u.ap.s1g_short_beacon, sdata); /* abort any running channel switch or color change */ link_conf->csa_active = false; link_conf->color_change_active = false; ieee80211_vif_unblock_queues_csa(sdata); ieee80211_free_next_beacon(link); /* turn off carrier for this interface and dependent VLANs */ list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) netif_carrier_off(vlan->dev); if (ieee80211_num_beaconing_links(sdata) <= 1) { netif_carrier_off(dev); sdata->u.ap.active = false; } /* remove beacon and probe response */ RCU_INIT_POINTER(link->u.ap.beacon, NULL); RCU_INIT_POINTER(link->u.ap.probe_resp, NULL); RCU_INIT_POINTER(link->u.ap.fils_discovery, NULL); RCU_INIT_POINTER(link->u.ap.unsol_bcast_probe_resp, NULL); RCU_INIT_POINTER(link->u.ap.s1g_short_beacon, NULL); kfree_rcu(old_beacon, rcu_head); if (old_probe_resp) kfree_rcu(old_probe_resp, rcu_head); if (old_fils_discovery) kfree_rcu(old_fils_discovery, rcu_head); if (old_unsol_bcast_probe_resp) kfree_rcu(old_unsol_bcast_probe_resp, rcu_head); if (old_s1g_short_beacon) kfree_rcu(old_s1g_short_beacon, rcu_head); kfree(link_conf->ftmr_params); link_conf->ftmr_params = NULL; link_conf->bssid_index = 0; link_conf->nontransmitted = false; link_conf->ema_ap = false; link_conf->bssid_indicator = 0; __sta_info_flush(sdata, true, link_id, NULL); ieee80211_remove_link_keys(link, &keys); if (!list_empty(&keys)) { synchronize_net(); ieee80211_free_key_list(local, &keys); } ieee80211_stop_mbssid(sdata); RCU_INIT_POINTER(link_conf->tx_bss_conf, NULL); link_conf->enable_beacon = false; sdata->beacon_rate_set = false; sdata->vif.cfg.ssid_len = 0; sdata->vif.cfg.s1g = false; clear_bit(SDATA_STATE_OFFCHANNEL_BEACON_STOPPED, &sdata->state); ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_BEACON_ENABLED); if (sdata->wdev.links[link_id].cac_started) { chandef = link_conf->chanreq.oper; wiphy_delayed_work_cancel(wiphy, &link->dfs_cac_timer_work); cfg80211_cac_event(sdata->dev, &chandef, NL80211_RADAR_CAC_ABORTED, GFP_KERNEL, link_id); } drv_stop_ap(sdata->local, sdata, link_conf); /* free all potentially still buffered bcast frames */ local->total_ps_buffered -= skb_queue_len(&sdata->u.ap.ps.bc_buf); ieee80211_purge_tx_queue(&local->hw, &sdata->u.ap.ps.bc_buf); ieee80211_link_copy_chanctx_to_vlans(link, true); ieee80211_link_release_channel(link); return 0; } static int sta_apply_auth_flags(struct ieee80211_local *local, struct sta_info *sta, u32 mask, u32 set) { int ret; if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED) && set & BIT(NL80211_STA_FLAG_AUTHENTICATED) && !test_sta_flag(sta, WLAN_STA_AUTH)) { ret = sta_info_move_state(sta, IEEE80211_STA_AUTH); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_ASSOCIATED) && set & BIT(NL80211_STA_FLAG_ASSOCIATED) && !test_sta_flag(sta, WLAN_STA_ASSOC)) { /* * When peer becomes associated, init rate control as * well. Some drivers require rate control initialized * before drv_sta_state() is called. */ if (!test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) rate_control_rate_init_all_links(sta); ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) ret = sta_info_move_state(sta, IEEE80211_STA_AUTHORIZED); else if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); else ret = 0; if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_ASSOCIATED) && !(set & BIT(NL80211_STA_FLAG_ASSOCIATED)) && test_sta_flag(sta, WLAN_STA_ASSOC)) { ret = sta_info_move_state(sta, IEEE80211_STA_AUTH); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED) && !(set & BIT(NL80211_STA_FLAG_AUTHENTICATED)) && test_sta_flag(sta, WLAN_STA_AUTH)) { ret = sta_info_move_state(sta, IEEE80211_STA_NONE); if (ret) return ret; } return 0; } static void sta_apply_mesh_params(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) { #ifdef CONFIG_MAC80211_MESH struct ieee80211_sub_if_data *sdata = sta->sdata; u64 changed = 0; if (params->sta_modify_mask & STATION_PARAM_APPLY_PLINK_STATE) { switch (params->plink_state) { case NL80211_PLINK_ESTAB: if (sta->mesh->plink_state != NL80211_PLINK_ESTAB) changed = mesh_plink_inc_estab_count(sdata); sta->mesh->plink_state = params->plink_state; sta->mesh->aid = params->peer_aid; ieee80211_mps_sta_status_update(sta); changed |= ieee80211_mps_set_sta_local_pm(sta, sdata->u.mesh.mshcfg.power_mode); ewma_mesh_tx_rate_avg_init(&sta->mesh->tx_rate_avg); /* init at low value */ ewma_mesh_tx_rate_avg_add(&sta->mesh->tx_rate_avg, 10); break; case NL80211_PLINK_LISTEN: case NL80211_PLINK_BLOCKED: case NL80211_PLINK_OPN_SNT: case NL80211_PLINK_OPN_RCVD: case NL80211_PLINK_CNF_RCVD: case NL80211_PLINK_HOLDING: if (sta->mesh->plink_state == NL80211_PLINK_ESTAB) changed = mesh_plink_dec_estab_count(sdata); sta->mesh->plink_state = params->plink_state; ieee80211_mps_sta_status_update(sta); changed |= ieee80211_mps_set_sta_local_pm(sta, NL80211_MESH_POWER_UNKNOWN); break; default: /* nothing */ break; } } switch (params->plink_action) { case NL80211_PLINK_ACTION_NO_ACTION: /* nothing */ break; case NL80211_PLINK_ACTION_OPEN: changed |= mesh_plink_open(sta); break; case NL80211_PLINK_ACTION_BLOCK: changed |= mesh_plink_block(sta); break; } if (params->local_pm) changed |= ieee80211_mps_set_sta_local_pm(sta, params->local_pm); ieee80211_mbss_info_change_notify(sdata, changed); #endif } enum sta_link_apply_mode { STA_LINK_MODE_NEW, STA_LINK_MODE_STA_MODIFY, STA_LINK_MODE_LINK_MODIFY, }; static int sta_link_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, enum sta_link_apply_mode mode, struct link_station_parameters *params) { struct ieee80211_supported_band *sband; struct ieee80211_sub_if_data *sdata = sta->sdata; u32 link_id = params->link_id < 0 ? 0 : params->link_id; struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); struct link_sta_info *link_sta = rcu_dereference_protected(sta->link[link_id], lockdep_is_held(&local->hw.wiphy->mtx)); bool changes = params->link_mac || params->txpwr_set || params->supported_rates_len || params->ht_capa || params->vht_capa || params->he_capa || params->eht_capa || params->s1g_capa || params->opmode_notif_used; switch (mode) { case STA_LINK_MODE_NEW: if (!params->link_mac) return -EINVAL; break; case STA_LINK_MODE_LINK_MODIFY: break; case STA_LINK_MODE_STA_MODIFY: if (params->link_id >= 0) break; if (!changes) return 0; break; } if (!link || !link_sta) return -EINVAL; sband = ieee80211_get_link_sband(link); if (!sband) return -EINVAL; if (params->link_mac) { if (mode == STA_LINK_MODE_NEW) { memcpy(link_sta->addr, params->link_mac, ETH_ALEN); memcpy(link_sta->pub->addr, params->link_mac, ETH_ALEN); } else if (!ether_addr_equal(link_sta->addr, params->link_mac)) { return -EINVAL; } } if (params->txpwr_set) { int ret; link_sta->pub->txpwr.type = params->txpwr.type; if (params->txpwr.type == NL80211_TX_POWER_LIMITED) link_sta->pub->txpwr.power = params->txpwr.power; ret = drv_sta_set_txpwr(local, sdata, sta); if (ret) return ret; } if (params->supported_rates && params->supported_rates_len && !ieee80211_parse_bitrates(link->conf->chanreq.oper.width, sband, params->supported_rates, params->supported_rates_len, &link_sta->pub->supp_rates[sband->band])) return -EINVAL; if (params->ht_capa) ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband, params->ht_capa, link_sta); /* VHT can override some HT caps such as the A-MSDU max length */ if (params->vht_capa) ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband, params->vht_capa, NULL, link_sta); if (params->he_capa) ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband, (void *)params->he_capa, params->he_capa_len, (void *)params->he_6ghz_capa, link_sta); if (params->he_capa && params->eht_capa) ieee80211_eht_cap_ie_to_sta_eht_cap(sdata, sband, (u8 *)params->he_capa, params->he_capa_len, params->eht_capa, params->eht_capa_len, link_sta); if (params->s1g_capa) ieee80211_s1g_cap_to_sta_s1g_cap(sdata, params->s1g_capa, link_sta); ieee80211_sta_init_nss(link_sta); if (params->opmode_notif_used) { enum nl80211_chan_width width = link->conf->chanreq.oper.width; switch (width) { case NL80211_CHAN_WIDTH_20: case NL80211_CHAN_WIDTH_40: case NL80211_CHAN_WIDTH_80: case NL80211_CHAN_WIDTH_160: case NL80211_CHAN_WIDTH_80P80: case NL80211_CHAN_WIDTH_320: /* not VHT, allowed for HE/EHT */ break; default: return -EINVAL; } /* returned value is only needed for rc update, but the * rc isn't initialized here yet, so ignore it */ __ieee80211_vht_handle_opmode(sdata, link_sta, params->opmode_notif, sband->band); } return 0; } static int sta_apply_parameters(struct ieee80211_local *local, struct sta_info *sta, struct station_parameters *params) { struct ieee80211_sub_if_data *sdata = sta->sdata; u32 mask, set; int ret = 0; mask = params->sta_flags_mask; set = params->sta_flags_set; if (ieee80211_vif_is_mesh(&sdata->vif)) { /* * In mesh mode, ASSOCIATED isn't part of the nl80211 * API but must follow AUTHENTICATED for driver state. */ if (mask & BIT(NL80211_STA_FLAG_AUTHENTICATED)) mask |= BIT(NL80211_STA_FLAG_ASSOCIATED); if (set & BIT(NL80211_STA_FLAG_AUTHENTICATED)) set |= BIT(NL80211_STA_FLAG_ASSOCIATED); } else if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { /* * TDLS -- everything follows authorized, but * only becoming authorized is possible, not * going back */ if (set & BIT(NL80211_STA_FLAG_AUTHORIZED)) { set |= BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_ASSOCIATED); mask |= BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_ASSOCIATED); } } if (mask & BIT(NL80211_STA_FLAG_WME) && local->hw.queues >= IEEE80211_NUM_ACS) sta->sta.wme = set & BIT(NL80211_STA_FLAG_WME); /* auth flags will be set later for TDLS, * and for unassociated stations that move to associated */ if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER) && !((mask & BIT(NL80211_STA_FLAG_ASSOCIATED)) && (set & BIT(NL80211_STA_FLAG_ASSOCIATED)))) { ret = sta_apply_auth_flags(local, sta, mask, set); if (ret) return ret; } if (mask & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) { if (set & BIT(NL80211_STA_FLAG_SHORT_PREAMBLE)) set_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE); else clear_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE); } if (mask & BIT(NL80211_STA_FLAG_MFP)) { sta->sta.mfp = !!(set & BIT(NL80211_STA_FLAG_MFP)); if (set & BIT(NL80211_STA_FLAG_MFP)) set_sta_flag(sta, WLAN_STA_MFP); else clear_sta_flag(sta, WLAN_STA_MFP); } if (mask & BIT(NL80211_STA_FLAG_TDLS_PEER)) { if (set & BIT(NL80211_STA_FLAG_TDLS_PEER)) set_sta_flag(sta, WLAN_STA_TDLS_PEER); else clear_sta_flag(sta, WLAN_STA_TDLS_PEER); } if (mask & BIT(NL80211_STA_FLAG_SPP_AMSDU)) sta->sta.spp_amsdu = set & BIT(NL80211_STA_FLAG_SPP_AMSDU); /* mark TDLS channel switch support, if the AP allows it */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && !sdata->deflink.u.mgd.tdls_chan_switch_prohibited && params->ext_capab_len >= 4 && params->ext_capab[3] & WLAN_EXT_CAPA4_TDLS_CHAN_SWITCH) set_sta_flag(sta, WLAN_STA_TDLS_CHAN_SWITCH); if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) && !sdata->u.mgd.tdls_wider_bw_prohibited && ieee80211_hw_check(&local->hw, TDLS_WIDER_BW) && params->ext_capab_len >= 8 && params->ext_capab[7] & WLAN_EXT_CAPA8_TDLS_WIDE_BW_ENABLED) set_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW); if (params->sta_modify_mask & STATION_PARAM_APPLY_UAPSD) { sta->sta.uapsd_queues = params->uapsd_queues; sta->sta.max_sp = params->max_sp; } ieee80211_sta_set_max_amsdu_subframes(sta, params->ext_capab, params->ext_capab_len); /* * cfg80211 validates this (1-2007) and allows setting the AID * only when creating a new station entry */ if (params->aid) sta->sta.aid = params->aid; /* * Some of the following updates would be racy if called on an * existing station, via ieee80211_change_station(). However, * all such changes are rejected by cfg80211 except for updates * changing the supported rates on an existing but not yet used * TDLS peer. */ if (params->listen_interval >= 0) sta->listen_interval = params->listen_interval; if (params->eml_cap_present) sta->sta.eml_cap = params->eml_cap; ret = sta_link_apply_parameters(local, sta, STA_LINK_MODE_STA_MODIFY, ¶ms->link_sta_params); if (ret) return ret; if (params->support_p2p_ps >= 0) sta->sta.support_p2p_ps = params->support_p2p_ps; if (ieee80211_vif_is_mesh(&sdata->vif)) sta_apply_mesh_params(local, sta, params); if (params->airtime_weight) sta->airtime_weight = params->airtime_weight; /* set the STA state after all sta info from usermode has been set */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) || set & BIT(NL80211_STA_FLAG_ASSOCIATED)) { ret = sta_apply_auth_flags(local, sta, mask, set); if (ret) return ret; } /* Mark the STA as MLO if MLD MAC address is available */ if (params->link_sta_params.mld_mac) sta->sta.mlo = true; return 0; } static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, const u8 *mac, struct station_parameters *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; struct ieee80211_sub_if_data *sdata; int err; lockdep_assert_wiphy(local->hw.wiphy); if (params->vlan) { sdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); if (sdata->vif.type != NL80211_IFTYPE_AP_VLAN && sdata->vif.type != NL80211_IFTYPE_AP) return -EINVAL; } else sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (ether_addr_equal(mac, sdata->vif.addr)) return -EINVAL; if (!is_valid_ether_addr(mac)) return -EINVAL; if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER) && sdata->vif.type == NL80211_IFTYPE_STATION && !sdata->u.mgd.associated) return -EINVAL; /* * If we have a link ID, it can be a non-MLO station on an AP MLD, * but we need to have a link_mac in that case as well, so use the * STA's MAC address in that case. */ if (params->link_sta_params.link_id >= 0) sta = sta_info_alloc_with_link(sdata, mac, params->link_sta_params.link_id, params->link_sta_params.link_mac ?: mac, GFP_KERNEL); else sta = sta_info_alloc(sdata, mac, GFP_KERNEL); if (!sta) return -ENOMEM; if (params->sta_flags_set & BIT(NL80211_STA_FLAG_TDLS_PEER)) sta->sta.tdls = true; /* Though the mutex is not needed here (since the station is not * visible yet), sta_apply_parameters (and inner functions) require * the mutex due to other paths. */ err = sta_apply_parameters(local, sta, params); if (err) { sta_info_free(local, sta); return err; } /* * for TDLS and for unassociated station, rate control should be * initialized only when rates are known and station is marked * authorized/associated */ if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER) && test_sta_flag(sta, WLAN_STA_ASSOC)) rate_control_rate_init_all_links(sta); return sta_info_insert(sta); } static int ieee80211_del_station(struct wiphy *wiphy, struct net_device *dev, struct station_del_parameters *params) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (params->mac) return sta_info_destroy_addr_bss(sdata, params->mac); sta_info_flush(sdata, params->link_id); return 0; } static int ieee80211_change_station(struct wiphy *wiphy, struct net_device *dev, const u8 *mac, struct station_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; struct ieee80211_sub_if_data *vlansdata; enum cfg80211_station_type statype; int err; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get_bss(sdata, mac); if (!sta) return -ENOENT; switch (sdata->vif.type) { case NL80211_IFTYPE_MESH_POINT: if (sdata->u.mesh.user_mpm) statype = CFG80211_STA_MESH_PEER_USER; else statype = CFG80211_STA_MESH_PEER_KERNEL; break; case NL80211_IFTYPE_ADHOC: statype = CFG80211_STA_IBSS; break; case NL80211_IFTYPE_STATION: if (!test_sta_flag(sta, WLAN_STA_TDLS_PEER)) { statype = CFG80211_STA_AP_STA; break; } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) statype = CFG80211_STA_TDLS_PEER_ACTIVE; else statype = CFG80211_STA_TDLS_PEER_SETUP; break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: if (test_sta_flag(sta, WLAN_STA_ASSOC)) statype = CFG80211_STA_AP_CLIENT; else statype = CFG80211_STA_AP_CLIENT_UNASSOC; break; default: return -EOPNOTSUPP; } err = cfg80211_check_station_change(wiphy, params, statype); if (err) return err; if (params->vlan && params->vlan != sta->sdata->dev) { vlansdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); if (params->vlan->ieee80211_ptr->use_4addr) { if (vlansdata->u.vlan.sta) return -EBUSY; rcu_assign_pointer(vlansdata->u.vlan.sta, sta); __ieee80211_check_fast_rx_iface(vlansdata); drv_sta_set_4addr(local, sta->sdata, &sta->sta, true); } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && sta->sdata->u.vlan.sta) RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); sta->sdata = vlansdata; ieee80211_check_fast_rx(sta); ieee80211_check_fast_xmit(sta); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { ieee80211_vif_inc_num_mcast(sta->sdata); cfg80211_send_layer2_update(sta->sdata->dev, sta->sta.addr); } } err = sta_apply_parameters(local, sta, params); if (err) return err; if (sdata->vif.type == NL80211_IFTYPE_STATION && params->sta_flags_mask & BIT(NL80211_STA_FLAG_AUTHORIZED)) { ieee80211_recalc_ps(local); ieee80211_recalc_ps_vif(sdata); } return 0; } #ifdef CONFIG_MAC80211_MESH static int ieee80211_add_mpath(struct wiphy *wiphy, struct net_device *dev, const u8 *dst, const u8 *next_hop) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; struct sta_info *sta; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); sta = sta_info_get(sdata, next_hop); if (!sta) { rcu_read_unlock(); return -ENOENT; } mpath = mesh_path_add(sdata, dst); if (IS_ERR(mpath)) { rcu_read_unlock(); return PTR_ERR(mpath); } mesh_path_fix_nexthop(mpath, sta); rcu_read_unlock(); return 0; } static int ieee80211_del_mpath(struct wiphy *wiphy, struct net_device *dev, const u8 *dst) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (dst) return mesh_path_del(sdata, dst); mesh_path_flush_by_iface(sdata); return 0; } static int ieee80211_change_mpath(struct wiphy *wiphy, struct net_device *dev, const u8 *dst, const u8 *next_hop) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; struct sta_info *sta; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); sta = sta_info_get(sdata, next_hop); if (!sta) { rcu_read_unlock(); return -ENOENT; } mpath = mesh_path_lookup(sdata, dst); if (!mpath) { rcu_read_unlock(); return -ENOENT; } mesh_path_fix_nexthop(mpath, sta); rcu_read_unlock(); return 0; } static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, struct mpath_info *pinfo) { struct sta_info *next_hop_sta = rcu_dereference(mpath->next_hop); if (next_hop_sta) memcpy(next_hop, next_hop_sta->sta.addr, ETH_ALEN); else eth_zero_addr(next_hop); memset(pinfo, 0, sizeof(*pinfo)); pinfo->generation = mpath->sdata->u.mesh.mesh_paths_generation; pinfo->filled = MPATH_INFO_FRAME_QLEN | MPATH_INFO_SN | MPATH_INFO_METRIC | MPATH_INFO_EXPTIME | MPATH_INFO_DISCOVERY_TIMEOUT | MPATH_INFO_DISCOVERY_RETRIES | MPATH_INFO_FLAGS | MPATH_INFO_HOP_COUNT | MPATH_INFO_PATH_CHANGE; pinfo->frame_qlen = mpath->frame_queue.qlen; pinfo->sn = mpath->sn; pinfo->metric = mpath->metric; if (time_before(jiffies, mpath->exp_time)) pinfo->exptime = jiffies_to_msecs(mpath->exp_time - jiffies); pinfo->discovery_timeout = jiffies_to_msecs(mpath->discovery_timeout); pinfo->discovery_retries = mpath->discovery_retries; if (mpath->flags & MESH_PATH_ACTIVE) pinfo->flags |= NL80211_MPATH_FLAG_ACTIVE; if (mpath->flags & MESH_PATH_RESOLVING) pinfo->flags |= NL80211_MPATH_FLAG_RESOLVING; if (mpath->flags & MESH_PATH_SN_VALID) pinfo->flags |= NL80211_MPATH_FLAG_SN_VALID; if (mpath->flags & MESH_PATH_FIXED) pinfo->flags |= NL80211_MPATH_FLAG_FIXED; if (mpath->flags & MESH_PATH_RESOLVED) pinfo->flags |= NL80211_MPATH_FLAG_RESOLVED; pinfo->hop_count = mpath->hop_count; pinfo->path_change_count = mpath->path_change_count; } static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mesh_path_lookup(sdata, dst); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpath_set_pinfo(mpath, next_hop, pinfo); rcu_read_unlock(); return 0; } static int ieee80211_dump_mpath(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *next_hop, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mesh_path_lookup_by_idx(sdata, idx); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpath_set_pinfo(mpath, next_hop, pinfo); rcu_read_unlock(); return 0; } static void mpp_set_pinfo(struct mesh_path *mpath, u8 *mpp, struct mpath_info *pinfo) { memset(pinfo, 0, sizeof(*pinfo)); memcpy(mpp, mpath->mpp, ETH_ALEN); pinfo->generation = mpath->sdata->u.mesh.mpp_paths_generation; } static int ieee80211_get_mpp(struct wiphy *wiphy, struct net_device *dev, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mpp_path_lookup(sdata, dst); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpp_set_pinfo(mpath, mpp, pinfo); rcu_read_unlock(); return 0; } static int ieee80211_dump_mpp(struct wiphy *wiphy, struct net_device *dev, int idx, u8 *dst, u8 *mpp, struct mpath_info *pinfo) { struct ieee80211_sub_if_data *sdata; struct mesh_path *mpath; sdata = IEEE80211_DEV_TO_SUB_IF(dev); rcu_read_lock(); mpath = mpp_path_lookup_by_idx(sdata, idx); if (!mpath) { rcu_read_unlock(); return -ENOENT; } memcpy(dst, mpath->dst, ETH_ALEN); mpp_set_pinfo(mpath, mpp, pinfo); rcu_read_unlock(); return 0; } static int ieee80211_get_mesh_config(struct wiphy *wiphy, struct net_device *dev, struct mesh_config *conf) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_DEV_TO_SUB_IF(dev); memcpy(conf, &(sdata->u.mesh.mshcfg), sizeof(struct mesh_config)); return 0; } static inline bool _chg_mesh_attr(enum nl80211_meshconf_params parm, u32 mask) { return (mask >> (parm-1)) & 0x1; } static int copy_mesh_setup(struct ieee80211_if_mesh *ifmsh, const struct mesh_setup *setup) { u8 *new_ie; struct ieee80211_sub_if_data *sdata = container_of(ifmsh, struct ieee80211_sub_if_data, u.mesh); int i; /* allocate information elements */ new_ie = NULL; if (setup->ie_len) { new_ie = kmemdup(setup->ie, setup->ie_len, GFP_KERNEL); if (!new_ie) return -ENOMEM; } ifmsh->ie_len = setup->ie_len; ifmsh->ie = new_ie; /* now copy the rest of the setup parameters */ ifmsh->mesh_id_len = setup->mesh_id_len; memcpy(ifmsh->mesh_id, setup->mesh_id, ifmsh->mesh_id_len); ifmsh->mesh_sp_id = setup->sync_method; ifmsh->mesh_pp_id = setup->path_sel_proto; ifmsh->mesh_pm_id = setup->path_metric; ifmsh->user_mpm = setup->user_mpm; ifmsh->mesh_auth_id = setup->auth_id; ifmsh->security = IEEE80211_MESH_SEC_NONE; ifmsh->userspace_handles_dfs = setup->userspace_handles_dfs; if (setup->is_authenticated) ifmsh->security |= IEEE80211_MESH_SEC_AUTHED; if (setup->is_secure) ifmsh->security |= IEEE80211_MESH_SEC_SECURED; /* mcast rate setting in Mesh Node */ memcpy(sdata->vif.bss_conf.mcast_rate, setup->mcast_rate, sizeof(setup->mcast_rate)); sdata->vif.bss_conf.basic_rates = setup->basic_rates; sdata->vif.bss_conf.beacon_int = setup->beacon_interval; sdata->vif.bss_conf.dtim_period = setup->dtim_period; sdata->beacon_rate_set = false; if (wiphy_ext_feature_isset(sdata->local->hw.wiphy, NL80211_EXT_FEATURE_BEACON_RATE_LEGACY)) { for (i = 0; i < NUM_NL80211_BANDS; i++) { sdata->beacon_rateidx_mask[i] = setup->beacon_rate.control[i].legacy; if (sdata->beacon_rateidx_mask[i]) sdata->beacon_rate_set = true; } } return 0; } static int ieee80211_update_mesh_config(struct wiphy *wiphy, struct net_device *dev, u32 mask, const struct mesh_config *nconf) { struct mesh_config *conf; struct ieee80211_sub_if_data *sdata; struct ieee80211_if_mesh *ifmsh; sdata = IEEE80211_DEV_TO_SUB_IF(dev); ifmsh = &sdata->u.mesh; /* Set the config options which we are interested in setting */ conf = &(sdata->u.mesh.mshcfg); if (_chg_mesh_attr(NL80211_MESHCONF_RETRY_TIMEOUT, mask)) conf->dot11MeshRetryTimeout = nconf->dot11MeshRetryTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_CONFIRM_TIMEOUT, mask)) conf->dot11MeshConfirmTimeout = nconf->dot11MeshConfirmTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_HOLDING_TIMEOUT, mask)) conf->dot11MeshHoldingTimeout = nconf->dot11MeshHoldingTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_MAX_PEER_LINKS, mask)) conf->dot11MeshMaxPeerLinks = nconf->dot11MeshMaxPeerLinks; if (_chg_mesh_attr(NL80211_MESHCONF_MAX_RETRIES, mask)) conf->dot11MeshMaxRetries = nconf->dot11MeshMaxRetries; if (_chg_mesh_attr(NL80211_MESHCONF_TTL, mask)) conf->dot11MeshTTL = nconf->dot11MeshTTL; if (_chg_mesh_attr(NL80211_MESHCONF_ELEMENT_TTL, mask)) conf->element_ttl = nconf->element_ttl; if (_chg_mesh_attr(NL80211_MESHCONF_AUTO_OPEN_PLINKS, mask)) { if (ifmsh->user_mpm) return -EBUSY; conf->auto_open_plinks = nconf->auto_open_plinks; } if (_chg_mesh_attr(NL80211_MESHCONF_SYNC_OFFSET_MAX_NEIGHBOR, mask)) conf->dot11MeshNbrOffsetMaxNeighbor = nconf->dot11MeshNbrOffsetMaxNeighbor; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_MAX_PREQ_RETRIES, mask)) conf->dot11MeshHWMPmaxPREQretries = nconf->dot11MeshHWMPmaxPREQretries; if (_chg_mesh_attr(NL80211_MESHCONF_PATH_REFRESH_TIME, mask)) conf->path_refresh_time = nconf->path_refresh_time; if (_chg_mesh_attr(NL80211_MESHCONF_MIN_DISCOVERY_TIMEOUT, mask)) conf->min_discovery_timeout = nconf->min_discovery_timeout; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ACTIVE_PATH_TIMEOUT, mask)) conf->dot11MeshHWMPactivePathTimeout = nconf->dot11MeshHWMPactivePathTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PREQ_MIN_INTERVAL, mask)) conf->dot11MeshHWMPpreqMinInterval = nconf->dot11MeshHWMPpreqMinInterval; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PERR_MIN_INTERVAL, mask)) conf->dot11MeshHWMPperrMinInterval = nconf->dot11MeshHWMPperrMinInterval; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_NET_DIAM_TRVS_TIME, mask)) conf->dot11MeshHWMPnetDiameterTraversalTime = nconf->dot11MeshHWMPnetDiameterTraversalTime; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ROOTMODE, mask)) { conf->dot11MeshHWMPRootMode = nconf->dot11MeshHWMPRootMode; ieee80211_mesh_root_setup(ifmsh); } if (_chg_mesh_attr(NL80211_MESHCONF_GATE_ANNOUNCEMENTS, mask)) { /* our current gate announcement implementation rides on root * announcements, so require this ifmsh to also be a root node * */ if (nconf->dot11MeshGateAnnouncementProtocol && !(conf->dot11MeshHWMPRootMode > IEEE80211_ROOTMODE_ROOT)) { conf->dot11MeshHWMPRootMode = IEEE80211_PROACTIVE_RANN; ieee80211_mesh_root_setup(ifmsh); } conf->dot11MeshGateAnnouncementProtocol = nconf->dot11MeshGateAnnouncementProtocol; } if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_RANN_INTERVAL, mask)) conf->dot11MeshHWMPRannInterval = nconf->dot11MeshHWMPRannInterval; if (_chg_mesh_attr(NL80211_MESHCONF_FORWARDING, mask)) conf->dot11MeshForwarding = nconf->dot11MeshForwarding; if (_chg_mesh_attr(NL80211_MESHCONF_RSSI_THRESHOLD, mask)) { /* our RSSI threshold implementation is supported only for * devices that report signal in dBm. */ if (!ieee80211_hw_check(&sdata->local->hw, SIGNAL_DBM)) return -EOPNOTSUPP; conf->rssi_threshold = nconf->rssi_threshold; } if (_chg_mesh_attr(NL80211_MESHCONF_HT_OPMODE, mask)) { conf->ht_opmode = nconf->ht_opmode; sdata->vif.bss_conf.ht_operation_mode = nconf->ht_opmode; ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_HT); } if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_PATH_TO_ROOT_TIMEOUT, mask)) conf->dot11MeshHWMPactivePathToRootTimeout = nconf->dot11MeshHWMPactivePathToRootTimeout; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_ROOT_INTERVAL, mask)) conf->dot11MeshHWMProotInterval = nconf->dot11MeshHWMProotInterval; if (_chg_mesh_attr(NL80211_MESHCONF_HWMP_CONFIRMATION_INTERVAL, mask)) conf->dot11MeshHWMPconfirmationInterval = nconf->dot11MeshHWMPconfirmationInterval; if (_chg_mesh_attr(NL80211_MESHCONF_POWER_MODE, mask)) { conf->power_mode = nconf->power_mode; ieee80211_mps_local_status_update(sdata); } if (_chg_mesh_attr(NL80211_MESHCONF_AWAKE_WINDOW, mask)) conf->dot11MeshAwakeWindowDuration = nconf->dot11MeshAwakeWindowDuration; if (_chg_mesh_attr(NL80211_MESHCONF_PLINK_TIMEOUT, mask)) conf->plink_timeout = nconf->plink_timeout; if (_chg_mesh_attr(NL80211_MESHCONF_CONNECTED_TO_GATE, mask)) conf->dot11MeshConnectedToMeshGate = nconf->dot11MeshConnectedToMeshGate; if (_chg_mesh_attr(NL80211_MESHCONF_NOLEARN, mask)) conf->dot11MeshNolearn = nconf->dot11MeshNolearn; if (_chg_mesh_attr(NL80211_MESHCONF_CONNECTED_TO_AS, mask)) conf->dot11MeshConnectedToAuthServer = nconf->dot11MeshConnectedToAuthServer; ieee80211_mbss_info_change_notify(sdata, BSS_CHANGED_BEACON); return 0; } static int ieee80211_join_mesh(struct wiphy *wiphy, struct net_device *dev, const struct mesh_config *conf, const struct mesh_setup *setup) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_chan_req chanreq = { .oper = setup->chandef }; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; int err; lockdep_assert_wiphy(sdata->local->hw.wiphy); memcpy(&ifmsh->mshcfg, conf, sizeof(struct mesh_config)); err = copy_mesh_setup(ifmsh, setup); if (err) return err; sdata->control_port_over_nl80211 = setup->control_port_over_nl80211; /* can mesh use other SMPS modes? */ sdata->deflink.smps_mode = IEEE80211_SMPS_OFF; sdata->deflink.needed_rx_chains = sdata->local->rx_chains; err = ieee80211_link_use_channel(&sdata->deflink, &chanreq, IEEE80211_CHANCTX_SHARED); if (err) return err; return ieee80211_start_mesh(sdata); } static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); lockdep_assert_wiphy(sdata->local->hw.wiphy); ieee80211_stop_mesh(sdata); ieee80211_link_release_channel(&sdata->deflink); kfree(sdata->u.mesh.ie); return 0; } #endif static int ieee80211_change_bss(struct wiphy *wiphy, struct net_device *dev, struct bss_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link; struct ieee80211_supported_band *sband; u64 changed = 0; link = ieee80211_link_or_deflink(sdata, params->link_id, true); if (IS_ERR(link)) return PTR_ERR(link); if (!sdata_dereference(link->u.ap.beacon, sdata)) return -ENOENT; sband = ieee80211_get_link_sband(link); if (!sband) return -EINVAL; if (params->basic_rates) { if (!ieee80211_parse_bitrates(link->conf->chanreq.oper.width, wiphy->bands[sband->band], params->basic_rates, params->basic_rates_len, &link->conf->basic_rates)) return -EINVAL; changed |= BSS_CHANGED_BASIC_RATES; ieee80211_check_rate_mask(link); } if (params->use_cts_prot >= 0) { link->conf->use_cts_prot = params->use_cts_prot; changed |= BSS_CHANGED_ERP_CTS_PROT; } if (params->use_short_preamble >= 0) { link->conf->use_short_preamble = params->use_short_preamble; changed |= BSS_CHANGED_ERP_PREAMBLE; } if (!link->conf->use_short_slot && (sband->band == NL80211_BAND_5GHZ || sband->band == NL80211_BAND_6GHZ)) { link->conf->use_short_slot = true; changed |= BSS_CHANGED_ERP_SLOT; } if (params->use_short_slot_time >= 0) { link->conf->use_short_slot = params->use_short_slot_time; changed |= BSS_CHANGED_ERP_SLOT; } if (params->ap_isolate >= 0) { if (params->ap_isolate) sdata->flags |= IEEE80211_SDATA_DONT_BRIDGE_PACKETS; else sdata->flags &= ~IEEE80211_SDATA_DONT_BRIDGE_PACKETS; ieee80211_check_fast_rx_iface(sdata); } if (params->ht_opmode >= 0) { link->conf->ht_operation_mode = (u16)params->ht_opmode; changed |= BSS_CHANGED_HT; } if (params->p2p_ctwindow >= 0) { link->conf->p2p_noa_attr.oppps_ctwindow &= ~IEEE80211_P2P_OPPPS_CTWINDOW_MASK; link->conf->p2p_noa_attr.oppps_ctwindow |= params->p2p_ctwindow & IEEE80211_P2P_OPPPS_CTWINDOW_MASK; changed |= BSS_CHANGED_P2P_PS; } if (params->p2p_opp_ps > 0) { link->conf->p2p_noa_attr.oppps_ctwindow |= IEEE80211_P2P_OPPPS_ENABLE_BIT; changed |= BSS_CHANGED_P2P_PS; } else if (params->p2p_opp_ps == 0) { link->conf->p2p_noa_attr.oppps_ctwindow &= ~IEEE80211_P2P_OPPPS_ENABLE_BIT; changed |= BSS_CHANGED_P2P_PS; } ieee80211_link_info_change_notify(sdata, link, changed); return 0; } static int ieee80211_set_txq_params(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_txq_params *params) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link = ieee80211_link_or_deflink(sdata, params->link_id, true); struct ieee80211_tx_queue_params p; if (!local->ops->conf_tx) return -EOPNOTSUPP; if (local->hw.queues < IEEE80211_NUM_ACS) return -EOPNOTSUPP; if (IS_ERR(link)) return PTR_ERR(link); memset(&p, 0, sizeof(p)); p.aifs = params->aifs; p.cw_max = params->cwmax; p.cw_min = params->cwmin; p.txop = params->txop; /* * Setting tx queue params disables u-apsd because it's only * called in master mode. */ p.uapsd = false; ieee80211_regulatory_limit_wmm_params(sdata, &p, params->ac); link->tx_conf[params->ac] = p; if (drv_conf_tx(local, link, params->ac, &p)) { wiphy_debug(local->hw.wiphy, "failed to set TX queue parameters for AC %d\n", params->ac); return -EINVAL; } ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_QOS); return 0; } #ifdef CONFIG_PM static int ieee80211_suspend(struct wiphy *wiphy, struct cfg80211_wowlan *wowlan) { return __ieee80211_suspend(wiphy_priv(wiphy), wowlan); } static int ieee80211_resume(struct wiphy *wiphy) { return __ieee80211_resume(wiphy_priv(wiphy)); } #else #define ieee80211_suspend NULL #define ieee80211_resume NULL #endif static int ieee80211_scan(struct wiphy *wiphy, struct cfg80211_scan_request *req) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_WDEV_TO_SUB_IF(req->wdev); switch (ieee80211_vif_type_p2p(&sdata->vif)) { case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_ADHOC: case NL80211_IFTYPE_MESH_POINT: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_P2P_DEVICE: break; case NL80211_IFTYPE_P2P_GO: if (sdata->local->ops->hw_scan) break; /* * FIXME: implement NoA while scanning in software, * for now fall through to allow scanning only when * beaconing hasn't been configured yet */ fallthrough; case NL80211_IFTYPE_AP: /* * If the scan has been forced (and the driver supports * forcing), don't care about being beaconing already. * This will create problems to the attached stations (e.g. all * the frames sent while scanning on other channel will be * lost) */ if (ieee80211_num_beaconing_links(sdata) && (!(wiphy->features & NL80211_FEATURE_AP_SCAN) || !(req->flags & NL80211_SCAN_FLAG_AP))) return -EOPNOTSUPP; break; case NL80211_IFTYPE_NAN: default: return -EOPNOTSUPP; } return ieee80211_request_scan(sdata, req); } static void ieee80211_abort_scan(struct wiphy *wiphy, struct wireless_dev *wdev) { ieee80211_scan_cancel(wiphy_priv(wiphy)); } static int ieee80211_sched_scan_start(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_sched_scan_request *req) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (!sdata->local->ops->sched_scan_start) return -EOPNOTSUPP; return ieee80211_request_sched_scan_start(sdata, req); } static int ieee80211_sched_scan_stop(struct wiphy *wiphy, struct net_device *dev, u64 reqid) { struct ieee80211_local *local = wiphy_priv(wiphy); if (!local->ops->sched_scan_stop) return -EOPNOTSUPP; return ieee80211_request_sched_scan_stop(local); } static int ieee80211_auth(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_auth_request *req) { return ieee80211_mgd_auth(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_assoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_assoc_request *req) { return ieee80211_mgd_assoc(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_deauth(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_deauth_request *req) { return ieee80211_mgd_deauth(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_disassoc(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_disassoc_request *req) { return ieee80211_mgd_disassoc(IEEE80211_DEV_TO_SUB_IF(dev), req); } static int ieee80211_join_ibss(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ibss_params *params) { return ieee80211_ibss_join(IEEE80211_DEV_TO_SUB_IF(dev), params); } static int ieee80211_leave_ibss(struct wiphy *wiphy, struct net_device *dev) { return ieee80211_ibss_leave(IEEE80211_DEV_TO_SUB_IF(dev)); } static int ieee80211_join_ocb(struct wiphy *wiphy, struct net_device *dev, struct ocb_setup *setup) { return ieee80211_ocb_join(IEEE80211_DEV_TO_SUB_IF(dev), setup); } static int ieee80211_leave_ocb(struct wiphy *wiphy, struct net_device *dev) { return ieee80211_ocb_leave(IEEE80211_DEV_TO_SUB_IF(dev)); } static int ieee80211_set_mcast_rate(struct wiphy *wiphy, struct net_device *dev, int rate[NUM_NL80211_BANDS]) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); memcpy(sdata->vif.bss_conf.mcast_rate, rate, sizeof(int) * NUM_NL80211_BANDS); if (ieee80211_sdata_running(sdata)) ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_MCAST_RATE); return 0; } static int ieee80211_set_wiphy_params(struct wiphy *wiphy, int radio_idx, u32 changed) { struct ieee80211_local *local = wiphy_priv(wiphy); int err; if (changed & WIPHY_PARAM_FRAG_THRESHOLD) { ieee80211_check_fast_xmit_all(local); err = drv_set_frag_threshold(local, radio_idx, wiphy->frag_threshold); if (err) { ieee80211_check_fast_xmit_all(local); return err; } } if ((changed & WIPHY_PARAM_COVERAGE_CLASS) || (changed & WIPHY_PARAM_DYN_ACK)) { s16 coverage_class; coverage_class = changed & WIPHY_PARAM_COVERAGE_CLASS ? wiphy->coverage_class : -1; err = drv_set_coverage_class(local, radio_idx, coverage_class); if (err) return err; } if (changed & WIPHY_PARAM_RTS_THRESHOLD) { u32 rts_threshold; if ((radio_idx == -1) || (radio_idx >= wiphy->n_radio)) rts_threshold = wiphy->rts_threshold; else rts_threshold = wiphy->radio_cfg[radio_idx].rts_threshold; err = drv_set_rts_threshold(local, radio_idx, rts_threshold); if (err) return err; } if (changed & WIPHY_PARAM_RETRY_SHORT) { if (wiphy->retry_short > IEEE80211_MAX_TX_RETRY) return -EINVAL; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; } if (changed & WIPHY_PARAM_RETRY_LONG) { if (wiphy->retry_long > IEEE80211_MAX_TX_RETRY) return -EINVAL; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; } if (changed & (WIPHY_PARAM_RETRY_SHORT | WIPHY_PARAM_RETRY_LONG)) ieee80211_hw_config(local, radio_idx, IEEE80211_CONF_CHANGE_RETRY_LIMITS); if (changed & (WIPHY_PARAM_TXQ_LIMIT | WIPHY_PARAM_TXQ_MEMORY_LIMIT | WIPHY_PARAM_TXQ_QUANTUM)) ieee80211_txq_set_params(local, radio_idx); return 0; } static int ieee80211_set_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, int radio_idx, enum nl80211_tx_power_setting type, int mbm) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; enum nl80211_tx_power_setting txp_type = type; bool update_txp_type = false; bool has_monitor = false; int user_power_level; int old_power = local->user_power_level; lockdep_assert_wiphy(local->hw.wiphy); switch (type) { case NL80211_TX_POWER_AUTOMATIC: user_power_level = IEEE80211_UNSET_POWER_LEVEL; txp_type = NL80211_TX_POWER_LIMITED; break; case NL80211_TX_POWER_LIMITED: case NL80211_TX_POWER_FIXED: if (mbm < 0 || (mbm % 100)) return -EOPNOTSUPP; user_power_level = MBM_TO_DBM(mbm); break; default: return -EINVAL; } if (wdev) { sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->vif.type == NL80211_IFTYPE_MONITOR && !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) { if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) return -EOPNOTSUPP; sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (!sdata) return -EOPNOTSUPP; } for (int link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { struct ieee80211_link_data *link = wiphy_dereference(wiphy, sdata->link[link_id]); if (!link) continue; link->user_power_level = user_power_level; if (txp_type != link->conf->txpower_type) { update_txp_type = true; link->conf->txpower_type = txp_type; } ieee80211_recalc_txpower(link, update_txp_type); } return 0; } local->user_power_level = user_power_level; list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type == NL80211_IFTYPE_MONITOR && !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) { has_monitor = true; continue; } for (int link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { struct ieee80211_link_data *link = wiphy_dereference(wiphy, sdata->link[link_id]); if (!link) continue; link->user_power_level = local->user_power_level; if (txp_type != link->conf->txpower_type) update_txp_type = true; link->conf->txpower_type = txp_type; } } list_for_each_entry(sdata, &local->interfaces, list) { if (sdata->vif.type == NL80211_IFTYPE_MONITOR && !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) continue; for (int link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { struct ieee80211_link_data *link = wiphy_dereference(wiphy, sdata->link[link_id]); if (!link) continue; ieee80211_recalc_txpower(link, update_txp_type); } } if (has_monitor) { sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) { sdata->deflink.user_power_level = local->user_power_level; if (txp_type != sdata->vif.bss_conf.txpower_type) update_txp_type = true; sdata->vif.bss_conf.txpower_type = txp_type; ieee80211_recalc_txpower(&sdata->deflink, update_txp_type); } } if (local->emulate_chanctx && (old_power != local->user_power_level)) ieee80211_hw_conf_chan(local); return 0; } static int ieee80211_get_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev, int radio_idx, unsigned int link_id, int *dbm) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct ieee80211_link_data *link_data; if (local->ops->get_txpower && (sdata->flags & IEEE80211_SDATA_IN_DRIVER)) return drv_get_txpower(local, sdata, link_id, dbm); if (local->emulate_chanctx) { *dbm = local->hw.conf.power_level; } else { link_data = wiphy_dereference(wiphy, sdata->link[link_id]); if (link_data) *dbm = link_data->conf->txpower; else return -ENOLINK; } /* INT_MIN indicates no power level was set yet */ if (*dbm == INT_MIN) return -EINVAL; return 0; } static void ieee80211_rfkill_poll(struct wiphy *wiphy) { struct ieee80211_local *local = wiphy_priv(wiphy); drv_rfkill_poll(local); } #ifdef CONFIG_NL80211_TESTMODE static int ieee80211_testmode_cmd(struct wiphy *wiphy, struct wireless_dev *wdev, void *data, int len) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_vif *vif = NULL; if (!local->ops->testmode_cmd) return -EOPNOTSUPP; if (wdev) { struct ieee80211_sub_if_data *sdata; sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (sdata->flags & IEEE80211_SDATA_IN_DRIVER) vif = &sdata->vif; } return local->ops->testmode_cmd(&local->hw, vif, data, len); } static int ieee80211_testmode_dump(struct wiphy *wiphy, struct sk_buff *skb, struct netlink_callback *cb, void *data, int len) { struct ieee80211_local *local = wiphy_priv(wiphy); if (!local->ops->testmode_dump) return -EOPNOTSUPP; return local->ops->testmode_dump(&local->hw, skb, cb, data, len); } #endif int __ieee80211_request_smps_mgd(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, enum ieee80211_smps_mode smps_mode) { const u8 *ap; enum ieee80211_smps_mode old_req; int err; struct sta_info *sta; bool tdls_peer_found = false; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION)) return -EINVAL; if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) return 0; old_req = link->u.mgd.req_smps; link->u.mgd.req_smps = smps_mode; /* The driver indicated that EML is enabled for the interface, which * implies that SMPS flows towards the AP should be stopped. */ if (sdata->vif.driver_flags & IEEE80211_VIF_EML_ACTIVE) return 0; if (old_req == smps_mode && smps_mode != IEEE80211_SMPS_AUTOMATIC) return 0; /* * If not associated, or current association is not an HT * association, there's no need to do anything, just store * the new value until we associate. */ if (!sdata->u.mgd.associated || link->conf->chanreq.oper.width == NL80211_CHAN_WIDTH_20_NOHT) return 0; ap = sdata->vif.cfg.ap_addr; rcu_read_lock(); list_for_each_entry_rcu(sta, &sdata->local->sta_list, list) { if (!sta->sta.tdls || sta->sdata != sdata || !sta->uploaded || !test_sta_flag(sta, WLAN_STA_AUTHORIZED)) continue; tdls_peer_found = true; break; } rcu_read_unlock(); if (smps_mode == IEEE80211_SMPS_AUTOMATIC) { if (tdls_peer_found || !sdata->u.mgd.powersave) smps_mode = IEEE80211_SMPS_OFF; else smps_mode = IEEE80211_SMPS_DYNAMIC; } /* send SM PS frame to AP */ err = ieee80211_send_smps_action(sdata, smps_mode, ap, ap, ieee80211_vif_is_mld(&sdata->vif) ? link->link_id : -1); if (err) link->u.mgd.req_smps = old_req; else if (smps_mode != IEEE80211_SMPS_OFF && tdls_peer_found) ieee80211_teardown_tdls_peers(link); return err; } static int ieee80211_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev, bool enabled, int timeout) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); unsigned int link_id; if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!ieee80211_hw_check(&local->hw, SUPPORTS_PS)) return -EOPNOTSUPP; if (enabled == sdata->u.mgd.powersave && timeout == local->dynamic_ps_forced_timeout) return 0; sdata->u.mgd.powersave = enabled; local->dynamic_ps_forced_timeout = timeout; /* no change, but if automatic follow powersave */ for (link_id = 0; link_id < ARRAY_SIZE(sdata->link); link_id++) { struct ieee80211_link_data *link; link = sdata_dereference(sdata->link[link_id], sdata); if (!link) continue; __ieee80211_request_smps_mgd(sdata, link, link->u.mgd.req_smps); } if (ieee80211_hw_check(&local->hw, SUPPORTS_DYNAMIC_PS)) ieee80211_hw_config(local, -1, IEEE80211_CONF_CHANGE_PS); ieee80211_recalc_ps(local); ieee80211_recalc_ps_vif(sdata); ieee80211_check_fast_rx_iface(sdata); return 0; } static void ieee80211_set_cqm_rssi_link(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, s32 rssi_thold, u32 rssi_hyst, s32 rssi_low, s32 rssi_high) { struct ieee80211_bss_conf *conf; if (!link || !link->conf) return; conf = link->conf; if (rssi_thold && rssi_hyst && rssi_thold == conf->cqm_rssi_thold && rssi_hyst == conf->cqm_rssi_hyst) return; conf->cqm_rssi_thold = rssi_thold; conf->cqm_rssi_hyst = rssi_hyst; conf->cqm_rssi_low = rssi_low; conf->cqm_rssi_high = rssi_high; link->u.mgd.last_cqm_event_signal = 0; if (!ieee80211_vif_link_active(&sdata->vif, link->link_id)) return; if (sdata->u.mgd.associated && (sdata->vif.driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_CQM); } static int ieee80211_set_cqm_rssi_config(struct wiphy *wiphy, struct net_device *dev, s32 rssi_thold, u32 rssi_hyst) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_vif *vif = &sdata->vif; int link_id; if (vif->driver_flags & IEEE80211_VIF_BEACON_FILTER && !(vif->driver_flags & IEEE80211_VIF_SUPPORTS_CQM_RSSI)) return -EOPNOTSUPP; /* For MLD, handle CQM change on all the active links */ for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); ieee80211_set_cqm_rssi_link(sdata, link, rssi_thold, rssi_hyst, 0, 0); } return 0; } static int ieee80211_set_cqm_rssi_range_config(struct wiphy *wiphy, struct net_device *dev, s32 rssi_low, s32 rssi_high) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_vif *vif = &sdata->vif; int link_id; if (vif->driver_flags & IEEE80211_VIF_BEACON_FILTER) return -EOPNOTSUPP; /* For MLD, handle CQM change on all the active links */ for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) { struct ieee80211_link_data *link = sdata_dereference(sdata->link[link_id], sdata); ieee80211_set_cqm_rssi_link(sdata, link, 0, 0, rssi_low, rssi_high); } return 0; } static int ieee80211_set_bitrate_mask(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id, const u8 *addr, const struct cfg80211_bitrate_mask *mask) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); int i, ret; if (!ieee80211_sdata_running(sdata)) return -ENETDOWN; /* * If active validate the setting and reject it if it doesn't leave * at least one basic rate usable, since we really have to be able * to send something, and if we're an AP we have to be able to do * so at a basic rate so that all clients can receive it. */ if (rcu_access_pointer(sdata->vif.bss_conf.chanctx_conf) && sdata->vif.bss_conf.chanreq.oper.chan) { u32 basic_rates = sdata->vif.bss_conf.basic_rates; enum nl80211_band band; band = sdata->vif.bss_conf.chanreq.oper.chan->band; if (!(mask->control[band].legacy & basic_rates)) return -EINVAL; } if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) { ret = drv_set_bitrate_mask(local, sdata, mask); if (ret) return ret; } for (i = 0; i < NUM_NL80211_BANDS; i++) { struct ieee80211_supported_band *sband = wiphy->bands[i]; int j; sdata->rc_rateidx_mask[i] = mask->control[i].legacy; memcpy(sdata->rc_rateidx_mcs_mask[i], mask->control[i].ht_mcs, sizeof(mask->control[i].ht_mcs)); memcpy(sdata->rc_rateidx_vht_mcs_mask[i], mask->control[i].vht_mcs, sizeof(mask->control[i].vht_mcs)); sdata->rc_has_mcs_mask[i] = false; sdata->rc_has_vht_mcs_mask[i] = false; if (!sband) continue; for (j = 0; j < IEEE80211_HT_MCS_MASK_LEN; j++) { if (sdata->rc_rateidx_mcs_mask[i][j] != 0xff) { sdata->rc_has_mcs_mask[i] = true; break; } } for (j = 0; j < NL80211_VHT_NSS_MAX; j++) { if (sdata->rc_rateidx_vht_mcs_mask[i][j] != 0xffff) { sdata->rc_has_vht_mcs_mask[i] = true; break; } } } return 0; } static bool ieee80211_is_scan_ongoing(struct wiphy *wiphy, struct ieee80211_local *local, struct cfg80211_chan_def *chandef) { struct cfg80211_scan_request *scan_req; int chan_radio_idx, req_radio_idx; struct ieee80211_roc_work *roc; if (list_empty(&local->roc_list) && !local->scanning) return false; if (wiphy->n_radio < 2) return true; req_radio_idx = cfg80211_get_radio_idx_by_chan(wiphy, chandef->chan); if (req_radio_idx < 0) return true; if (local->scanning) { scan_req = wiphy_dereference(wiphy, local->scan_req); /* * Scan is going on but info is not there. Should not happen * but if it does, let's not take risk and assume we can't use * the hw hence return true */ if (WARN_ON_ONCE(!scan_req)) return true; return ieee80211_is_radio_idx_in_scan_req(wiphy, scan_req, req_radio_idx); } list_for_each_entry(roc, &local->roc_list, list) { chan_radio_idx = cfg80211_get_radio_idx_by_chan(wiphy, roc->chan); /* * The roc work is added but chan_radio_idx is invalid. * Should not happen but if it does, let's not take * risk and return true. */ if (chan_radio_idx < 0) return true; if (chan_radio_idx == req_radio_idx) return true; } return false; } static int ieee80211_start_radar_detection(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_chan_def *chandef, u32 cac_time_ms, int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_chan_req chanreq = { .oper = *chandef }; struct ieee80211_local *local = sdata->local; struct ieee80211_link_data *link_data; int err; lockdep_assert_wiphy(local->hw.wiphy); if (ieee80211_is_scan_ongoing(wiphy, local, chandef)) return -EBUSY; link_data = sdata_dereference(sdata->link[link_id], sdata); if (!link_data) return -ENOLINK; /* whatever, but channel contexts should not complain about that one */ link_data->smps_mode = IEEE80211_SMPS_OFF; link_data->needed_rx_chains = local->rx_chains; err = ieee80211_link_use_channel(link_data, &chanreq, IEEE80211_CHANCTX_SHARED); if (err) return err; wiphy_delayed_work_queue(wiphy, &link_data->dfs_cac_timer_work, msecs_to_jiffies(cac_time_ms)); return 0; } static void ieee80211_end_cac(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_link_data *link_data; lockdep_assert_wiphy(local->hw.wiphy); list_for_each_entry(sdata, &local->interfaces, list) { link_data = sdata_dereference(sdata->link[link_id], sdata); if (!link_data) continue; wiphy_delayed_work_cancel(wiphy, &link_data->dfs_cac_timer_work); if (sdata->wdev.links[link_id].cac_started) { ieee80211_link_release_channel(link_data); sdata->wdev.links[link_id].cac_started = false; } } } static struct cfg80211_beacon_data * cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) { struct cfg80211_beacon_data *new_beacon; u8 *pos; int len; len = beacon->head_len + beacon->tail_len + beacon->beacon_ies_len + beacon->proberesp_ies_len + beacon->assocresp_ies_len + beacon->probe_resp_len + beacon->lci_len + beacon->civicloc_len; if (beacon->mbssid_ies) len += ieee80211_get_mbssid_beacon_len(beacon->mbssid_ies, beacon->rnr_ies, beacon->mbssid_ies->cnt); new_beacon = kzalloc(sizeof(*new_beacon) + len, GFP_KERNEL); if (!new_beacon) return NULL; if (beacon->mbssid_ies && beacon->mbssid_ies->cnt) { new_beacon->mbssid_ies = kzalloc(struct_size(new_beacon->mbssid_ies, elem, beacon->mbssid_ies->cnt), GFP_KERNEL); if (!new_beacon->mbssid_ies) { kfree(new_beacon); return NULL; } if (beacon->rnr_ies && beacon->rnr_ies->cnt) { new_beacon->rnr_ies = kzalloc(struct_size(new_beacon->rnr_ies, elem, beacon->rnr_ies->cnt), GFP_KERNEL); if (!new_beacon->rnr_ies) { kfree(new_beacon->mbssid_ies); kfree(new_beacon); return NULL; } } } pos = (u8 *)(new_beacon + 1); if (beacon->head_len) { new_beacon->head_len = beacon->head_len; new_beacon->head = pos; memcpy(pos, beacon->head, beacon->head_len); pos += beacon->head_len; } if (beacon->tail_len) { new_beacon->tail_len = beacon->tail_len; new_beacon->tail = pos; memcpy(pos, beacon->tail, beacon->tail_len); pos += beacon->tail_len; } if (beacon->beacon_ies_len) { new_beacon->beacon_ies_len = beacon->beacon_ies_len; new_beacon->beacon_ies = pos; memcpy(pos, beacon->beacon_ies, beacon->beacon_ies_len); pos += beacon->beacon_ies_len; } if (beacon->proberesp_ies_len) { new_beacon->proberesp_ies_len = beacon->proberesp_ies_len; new_beacon->proberesp_ies = pos; memcpy(pos, beacon->proberesp_ies, beacon->proberesp_ies_len); pos += beacon->proberesp_ies_len; } if (beacon->assocresp_ies_len) { new_beacon->assocresp_ies_len = beacon->assocresp_ies_len; new_beacon->assocresp_ies = pos; memcpy(pos, beacon->assocresp_ies, beacon->assocresp_ies_len); pos += beacon->assocresp_ies_len; } if (beacon->probe_resp_len) { new_beacon->probe_resp_len = beacon->probe_resp_len; new_beacon->probe_resp = pos; memcpy(pos, beacon->probe_resp, beacon->probe_resp_len); pos += beacon->probe_resp_len; } if (beacon->mbssid_ies && beacon->mbssid_ies->cnt) { pos += ieee80211_copy_mbssid_beacon(pos, new_beacon->mbssid_ies, beacon->mbssid_ies); if (beacon->rnr_ies && beacon->rnr_ies->cnt) pos += ieee80211_copy_rnr_beacon(pos, new_beacon->rnr_ies, beacon->rnr_ies); } /* might copy -1, meaning no changes requested */ new_beacon->ftm_responder = beacon->ftm_responder; if (beacon->lci) { new_beacon->lci_len = beacon->lci_len; new_beacon->lci = pos; memcpy(pos, beacon->lci, beacon->lci_len); pos += beacon->lci_len; } if (beacon->civicloc) { new_beacon->civicloc_len = beacon->civicloc_len; new_beacon->civicloc = pos; memcpy(pos, beacon->civicloc, beacon->civicloc_len); pos += beacon->civicloc_len; } return new_beacon; } void ieee80211_csa_finish(struct ieee80211_vif *vif, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_local *local = sdata->local; struct ieee80211_bss_conf *tx_bss_conf; struct ieee80211_link_data *link_data; if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) return; rcu_read_lock(); link_data = rcu_dereference(sdata->link[link_id]); if (WARN_ON(!link_data)) { rcu_read_unlock(); return; } tx_bss_conf = rcu_dereference(link_data->conf->tx_bss_conf); if (tx_bss_conf == link_data->conf) { /* Trigger ieee80211_csa_finish() on the non-transmitting * interfaces when channel switch is received on * transmitting interface */ struct ieee80211_link_data *iter; for_each_sdata_link_rcu(local, iter) { if (iter->sdata == sdata || rcu_access_pointer(iter->conf->tx_bss_conf) != tx_bss_conf) continue; wiphy_work_queue(iter->sdata->local->hw.wiphy, &iter->csa.finalize_work); } } wiphy_work_queue(local->hw.wiphy, &link_data->csa.finalize_work); rcu_read_unlock(); } EXPORT_SYMBOL(ieee80211_csa_finish); void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = sdata->local; sdata_info(sdata, "channel switch failed, disconnecting\n"); wiphy_work_queue(local->hw.wiphy, &ifmgd->csa_connection_drop_work); } EXPORT_SYMBOL(ieee80211_channel_switch_disconnect); static int ieee80211_set_after_csa_beacon(struct ieee80211_link_data *link_data, u64 *changed) { struct ieee80211_sub_if_data *sdata = link_data->sdata; int err; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: if (!link_data->u.ap.next_beacon) return -EINVAL; err = ieee80211_assign_beacon(sdata, link_data, link_data->u.ap.next_beacon, NULL, NULL, changed); ieee80211_free_next_beacon(link_data); if (err < 0) return err; break; case NL80211_IFTYPE_ADHOC: err = ieee80211_ibss_finish_csa(sdata, changed); if (err < 0) return err; break; #ifdef CONFIG_MAC80211_MESH case NL80211_IFTYPE_MESH_POINT: err = ieee80211_mesh_finish_csa(sdata, changed); if (err < 0) return err; break; #endif default: WARN_ON(1); return -EINVAL; } return 0; } static int __ieee80211_csa_finalize(struct ieee80211_link_data *link_data) { struct ieee80211_sub_if_data *sdata = link_data->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_bss_conf *link_conf = link_data->conf; u64 changed = 0; int err; lockdep_assert_wiphy(local->hw.wiphy); /* * using reservation isn't immediate as it may be deferred until later * with multi-vif. once reservation is complete it will re-schedule the * work with no reserved_chanctx so verify chandef to check if it * completed successfully */ if (link_data->reserved_chanctx) { /* * with multi-vif csa driver may call ieee80211_csa_finish() * many times while waiting for other interfaces to use their * reservations */ if (link_data->reserved_ready) return 0; return ieee80211_link_use_reserved_context(link_data); } if (!cfg80211_chandef_identical(&link_conf->chanreq.oper, &link_data->csa.chanreq.oper)) return -EINVAL; link_conf->csa_active = false; err = ieee80211_set_after_csa_beacon(link_data, &changed); if (err) return err; ieee80211_link_info_change_notify(sdata, link_data, changed); ieee80211_vif_unblock_queues_csa(sdata); err = drv_post_channel_switch(link_data); if (err) return err; cfg80211_ch_switch_notify(sdata->dev, &link_data->csa.chanreq.oper, link_data->link_id); return 0; } static void ieee80211_csa_finalize(struct ieee80211_link_data *link_data) { struct ieee80211_sub_if_data *sdata = link_data->sdata; if (__ieee80211_csa_finalize(link_data)) { sdata_info(sdata, "failed to finalize CSA on link %d, disconnecting\n", link_data->link_id); cfg80211_stop_iface(sdata->local->hw.wiphy, &sdata->wdev, GFP_KERNEL); } } void ieee80211_csa_finalize_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_link_data *link = container_of(work, struct ieee80211_link_data, csa.finalize_work); struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(local->hw.wiphy); /* AP might have been stopped while waiting for the lock. */ if (!link->conf->csa_active) return; if (!ieee80211_sdata_running(sdata)) return; ieee80211_csa_finalize(link); } static int ieee80211_set_csa_beacon(struct ieee80211_link_data *link_data, struct cfg80211_csa_settings *params, u64 *changed) { struct ieee80211_sub_if_data *sdata = link_data->sdata; struct ieee80211_csa_settings csa = {}; int err; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: link_data->u.ap.next_beacon = cfg80211_beacon_dup(¶ms->beacon_after); if (!link_data->u.ap.next_beacon) return -ENOMEM; /* * With a count of 0, we don't have to wait for any * TBTT before switching, so complete the CSA * immediately. In theory, with a count == 1 we * should delay the switch until just before the next * TBTT, but that would complicate things so we switch * immediately too. If we would delay the switch * until the next TBTT, we would have to set the probe * response here. * * TODO: A channel switch with count <= 1 without * sending a CSA action frame is kind of useless, * because the clients won't know we're changing * channels. The action frame must be implemented * either here or in the userspace. */ if (params->count <= 1) break; if ((params->n_counter_offsets_beacon > IEEE80211_MAX_CNTDWN_COUNTERS_NUM) || (params->n_counter_offsets_presp > IEEE80211_MAX_CNTDWN_COUNTERS_NUM)) { ieee80211_free_next_beacon(link_data); return -EINVAL; } csa.counter_offsets_beacon = params->counter_offsets_beacon; csa.counter_offsets_presp = params->counter_offsets_presp; csa.n_counter_offsets_beacon = params->n_counter_offsets_beacon; csa.n_counter_offsets_presp = params->n_counter_offsets_presp; csa.count = params->count; err = ieee80211_assign_beacon(sdata, link_data, ¶ms->beacon_csa, &csa, NULL, changed); if (err < 0) { ieee80211_free_next_beacon(link_data); return err; } break; case NL80211_IFTYPE_ADHOC: if (!sdata->vif.cfg.ibss_joined) return -EINVAL; if (params->chandef.width != sdata->u.ibss.chandef.width) return -EINVAL; switch (params->chandef.width) { case NL80211_CHAN_WIDTH_40: if (cfg80211_get_chandef_type(¶ms->chandef) != cfg80211_get_chandef_type(&sdata->u.ibss.chandef)) return -EINVAL; break; case NL80211_CHAN_WIDTH_5: case NL80211_CHAN_WIDTH_10: case NL80211_CHAN_WIDTH_20_NOHT: case NL80211_CHAN_WIDTH_20: break; default: return -EINVAL; } /* changes into another band are not supported */ if (sdata->u.ibss.chandef.chan->band != params->chandef.chan->band) return -EINVAL; /* see comments in the NL80211_IFTYPE_AP block */ if (params->count > 1) { err = ieee80211_ibss_csa_beacon(sdata, params, changed); if (err < 0) return err; } ieee80211_send_action_csa(sdata, params); break; #ifdef CONFIG_MAC80211_MESH case NL80211_IFTYPE_MESH_POINT: { struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; /* changes into another band are not supported */ if (sdata->vif.bss_conf.chanreq.oper.chan->band != params->chandef.chan->band) return -EINVAL; if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_NONE) { ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_INIT; if (!ifmsh->pre_value) ifmsh->pre_value = 1; else ifmsh->pre_value++; } /* see comments in the NL80211_IFTYPE_AP block */ if (params->count > 1) { err = ieee80211_mesh_csa_beacon(sdata, params, changed); if (err < 0) { ifmsh->csa_role = IEEE80211_MESH_CSA_ROLE_NONE; return err; } } if (ifmsh->csa_role == IEEE80211_MESH_CSA_ROLE_INIT) ieee80211_send_action_csa(sdata, params); break; } #endif default: return -EOPNOTSUPP; } return 0; } static void ieee80211_color_change_abort(struct ieee80211_link_data *link) { link->conf->color_change_active = false; ieee80211_free_next_beacon(link); cfg80211_color_change_aborted_notify(link->sdata->dev, link->link_id); } static int __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_chan_req chanreq = { .oper = params->chandef }; struct ieee80211_local *local = sdata->local; struct ieee80211_channel_switch ch_switch = { .link_id = params->link_id, }; struct ieee80211_chanctx_conf *conf; struct ieee80211_chanctx *chanctx; struct ieee80211_bss_conf *link_conf; struct ieee80211_link_data *link_data; u64 changed = 0; u8 link_id = params->link_id; int err; lockdep_assert_wiphy(local->hw.wiphy); if (ieee80211_is_scan_ongoing(wiphy, local, ¶ms->chandef)) return -EBUSY; if (sdata->wdev.links[link_id].cac_started) return -EBUSY; if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) return -EINVAL; link_data = wiphy_dereference(wiphy, sdata->link[link_id]); if (!link_data) return -ENOLINK; link_conf = link_data->conf; if (chanreq.oper.punctured && !link_conf->eht_support) return -EINVAL; /* don't allow another channel switch if one is already active. */ if (link_conf->csa_active) return -EBUSY; conf = wiphy_dereference(wiphy, link_conf->chanctx_conf); if (!conf) { err = -EBUSY; goto out; } if (params->chandef.chan->freq_offset) { /* this may work, but is untested */ err = -EOPNOTSUPP; goto out; } err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, link_data, link_conf, &changed); if (err) goto out; chanctx = container_of(conf, struct ieee80211_chanctx, conf); ch_switch.timestamp = 0; ch_switch.device_timestamp = 0; ch_switch.block_tx = params->block_tx; ch_switch.chandef = chanreq.oper; ch_switch.count = params->count; err = drv_pre_channel_switch(sdata, &ch_switch); if (err) goto out; err = ieee80211_link_reserve_chanctx(link_data, &chanreq, chanctx->mode, params->radar_required); if (err) goto out; /* if reservation is invalid then this will fail */ err = ieee80211_check_combinations(sdata, NULL, chanctx->mode, 0, -1); if (err) { ieee80211_link_unreserve_chanctx(link_data); goto out; } /* if there is a color change in progress, abort it */ if (link_conf->color_change_active) ieee80211_color_change_abort(link_data); err = ieee80211_set_csa_beacon(link_data, params, &changed); if (err) { ieee80211_link_unreserve_chanctx(link_data); goto out; } link_data->csa.chanreq = chanreq; link_conf->csa_active = true; if (params->block_tx) ieee80211_vif_block_queues_csa(sdata); cfg80211_ch_switch_started_notify(sdata->dev, &link_data->csa.chanreq.oper, link_id, params->count, params->block_tx); if (changed) { ieee80211_link_info_change_notify(sdata, link_data, changed); drv_channel_switch_beacon(sdata, &link_data->csa.chanreq.oper); } else { /* if the beacon didn't change, we can finalize immediately */ ieee80211_csa_finalize(link_data); } out: return err; } int ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_csa_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(local->hw.wiphy); return __ieee80211_channel_switch(wiphy, dev, params); } u64 ieee80211_mgmt_tx_cookie(struct ieee80211_local *local) { lockdep_assert_wiphy(local->hw.wiphy); local->roc_cookie_counter++; /* wow, you wrapped 64 bits ... more likely a bug */ if (WARN_ON(local->roc_cookie_counter == 0)) local->roc_cookie_counter++; return local->roc_cookie_counter; } int ieee80211_attach_ack_skb(struct ieee80211_local *local, struct sk_buff *skb, u64 *cookie, gfp_t gfp) { unsigned long spin_flags; struct sk_buff *ack_skb; int id; ack_skb = skb_copy(skb, gfp); if (!ack_skb) return -ENOMEM; spin_lock_irqsave(&local->ack_status_lock, spin_flags); id = idr_alloc(&local->ack_status_frames, ack_skb, 1, 0x2000, GFP_ATOMIC); spin_unlock_irqrestore(&local->ack_status_lock, spin_flags); if (id < 0) { kfree_skb(ack_skb); return -ENOMEM; } IEEE80211_SKB_CB(skb)->status_data_idr = 1; IEEE80211_SKB_CB(skb)->status_data = id; *cookie = ieee80211_mgmt_tx_cookie(local); IEEE80211_SKB_CB(ack_skb)->ack.cookie = *cookie; return 0; } static void ieee80211_update_mgmt_frame_registrations(struct wiphy *wiphy, struct wireless_dev *wdev, struct mgmt_frame_regs *upd) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); u32 preq_mask = BIT(IEEE80211_STYPE_PROBE_REQ >> 4); u32 action_mask = BIT(IEEE80211_STYPE_ACTION >> 4); bool global_change, intf_change; global_change = (local->probe_req_reg != !!(upd->global_stypes & preq_mask)) || (local->rx_mcast_action_reg != !!(upd->global_mcast_stypes & action_mask)); local->probe_req_reg = upd->global_stypes & preq_mask; local->rx_mcast_action_reg = upd->global_mcast_stypes & action_mask; intf_change = (sdata->vif.probe_req_reg != !!(upd->interface_stypes & preq_mask)) || (sdata->vif.rx_mcast_action_reg != !!(upd->interface_mcast_stypes & action_mask)); sdata->vif.probe_req_reg = upd->interface_stypes & preq_mask; sdata->vif.rx_mcast_action_reg = upd->interface_mcast_stypes & action_mask; if (!local->open_count) return; if (intf_change && ieee80211_sdata_running(sdata)) drv_config_iface_filter(local, sdata, sdata->vif.probe_req_reg ? FIF_PROBE_REQ : 0, FIF_PROBE_REQ); if (global_change) ieee80211_configure_filter(local); } static int ieee80211_set_antenna(struct wiphy *wiphy, int radio_idx, u32 tx_ant, u32 rx_ant) { struct ieee80211_local *local = wiphy_priv(wiphy); int ret; if (local->started) return -EOPNOTSUPP; ret = drv_set_antenna(local, tx_ant, rx_ant); if (ret) return ret; local->rx_chains = hweight8(rx_ant); return 0; } static int ieee80211_get_antenna(struct wiphy *wiphy, int radio_idx, u32 *tx_ant, u32 *rx_ant) { struct ieee80211_local *local = wiphy_priv(wiphy); return drv_get_antenna(local, radio_idx, tx_ant, rx_ant); } static int ieee80211_set_rekey_data(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_gtk_rekey_data *data) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (!local->ops->set_rekey_data) return -EOPNOTSUPP; drv_set_rekey_data(local, sdata, data); return 0; } static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, u64 *cookie) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_qos_hdr *nullfunc; struct sk_buff *skb; int size = sizeof(*nullfunc); __le16 fc; bool qos; struct ieee80211_tx_info *info; struct sta_info *sta; struct ieee80211_chanctx_conf *chanctx_conf; enum nl80211_band band; int ret; /* the lock is needed to assign the cookie later */ lockdep_assert_wiphy(local->hw.wiphy); rcu_read_lock(); sta = sta_info_get_bss(sdata, peer); if (!sta) { ret = -ENOLINK; goto unlock; } qos = sta->sta.wme; chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf); if (WARN_ON(!chanctx_conf)) { ret = -EINVAL; goto unlock; } band = chanctx_conf->def.chan->band; if (qos) { fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_NULLFUNC | IEEE80211_FCTL_FROMDS); } else { size -= 2; fc = cpu_to_le16(IEEE80211_FTYPE_DATA | IEEE80211_STYPE_NULLFUNC | IEEE80211_FCTL_FROMDS); } skb = dev_alloc_skb(local->hw.extra_tx_headroom + size); if (!skb) { ret = -ENOMEM; goto unlock; } skb->dev = dev; skb_reserve(skb, local->hw.extra_tx_headroom); nullfunc = skb_put(skb, size); nullfunc->frame_control = fc; nullfunc->duration_id = 0; memcpy(nullfunc->addr1, sta->sta.addr, ETH_ALEN); memcpy(nullfunc->addr2, sdata->vif.addr, ETH_ALEN); memcpy(nullfunc->addr3, sdata->vif.addr, ETH_ALEN); nullfunc->seq_ctrl = 0; info = IEEE80211_SKB_CB(skb); info->flags |= IEEE80211_TX_CTL_REQ_TX_STATUS | IEEE80211_TX_INTFL_NL80211_FRAME_TX; info->band = band; skb_set_queue_mapping(skb, IEEE80211_AC_VO); skb->priority = 7; if (qos) nullfunc->qos_ctrl = cpu_to_le16(7); ret = ieee80211_attach_ack_skb(local, skb, cookie, GFP_ATOMIC); if (ret) { kfree_skb(skb); goto unlock; } local_bh_disable(); ieee80211_xmit(sdata, sta, skb); local_bh_enable(); ret = 0; unlock: rcu_read_unlock(); return ret; } static int ieee80211_cfg_get_channel(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id, struct cfg80211_chan_def *chandef) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_chanctx_conf *chanctx_conf; struct ieee80211_link_data *link; int ret = -ENODATA; rcu_read_lock(); link = rcu_dereference(sdata->link[link_id]); if (!link) { ret = -ENOLINK; goto out; } chanctx_conf = rcu_dereference(link->conf->chanctx_conf); if (chanctx_conf) { *chandef = link->conf->chanreq.oper; ret = 0; } else if (local->open_count > 0 && local->open_count == local->virt_monitors && sdata->vif.type == NL80211_IFTYPE_MONITOR) { *chandef = local->monitor_chanreq.oper; ret = 0; } out: rcu_read_unlock(); return ret; } #ifdef CONFIG_PM static void ieee80211_set_wakeup(struct wiphy *wiphy, bool enabled) { drv_set_wakeup(wiphy_priv(wiphy), enabled); } #endif static int ieee80211_set_qos_map(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_qos_map *qos_map) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct mac80211_qos_map *new_qos_map, *old_qos_map; if (qos_map) { new_qos_map = kzalloc(sizeof(*new_qos_map), GFP_KERNEL); if (!new_qos_map) return -ENOMEM; memcpy(&new_qos_map->qos_map, qos_map, sizeof(*qos_map)); } else { /* A NULL qos_map was passed to disable QoS mapping */ new_qos_map = NULL; } old_qos_map = sdata_dereference(sdata->qos_map, sdata); rcu_assign_pointer(sdata->qos_map, new_qos_map); if (old_qos_map) kfree_rcu(old_qos_map, rcu_head); return 0; } static int ieee80211_set_ap_chanwidth(struct wiphy *wiphy, struct net_device *dev, unsigned int link_id, struct cfg80211_chan_def *chandef) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_link_data *link; struct ieee80211_chan_req chanreq = { .oper = *chandef }; int ret; u64 changed = 0; link = sdata_dereference(sdata->link[link_id], sdata); ret = ieee80211_link_change_chanreq(link, &chanreq, &changed); if (ret == 0) ieee80211_link_info_change_notify(sdata, link, changed); return ret; } static int ieee80211_add_tx_ts(struct wiphy *wiphy, struct net_device *dev, u8 tsid, const u8 *peer, u8 up, u16 admitted_time) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; int ac = ieee802_1d_to_ac[up]; if (sdata->vif.type != NL80211_IFTYPE_STATION) return -EOPNOTSUPP; if (!(sdata->wmm_acm & BIT(up))) return -EINVAL; if (ifmgd->tx_tspec[ac].admitted_time) return -EBUSY; if (admitted_time) { ifmgd->tx_tspec[ac].admitted_time = 32 * admitted_time; ifmgd->tx_tspec[ac].tsid = tsid; ifmgd->tx_tspec[ac].up = up; } return 0; } static int ieee80211_del_tx_ts(struct wiphy *wiphy, struct net_device *dev, u8 tsid, const u8 *peer) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; struct ieee80211_local *local = wiphy_priv(wiphy); int ac; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { struct ieee80211_sta_tx_tspec *tx_tspec = &ifmgd->tx_tspec[ac]; /* skip unused entries */ if (!tx_tspec->admitted_time) continue; if (tx_tspec->tsid != tsid) continue; /* due to this new packets will be reassigned to non-ACM ACs */ tx_tspec->up = -1; /* Make sure that all packets have been sent to avoid to * restore the QoS params on packets that are still on the * queues. */ synchronize_net(); ieee80211_flush_queues(local, sdata, false); /* restore the normal QoS parameters * (unconditionally to avoid races) */ tx_tspec->action = TX_TSPEC_ACTION_STOP_DOWNGRADE; tx_tspec->downgraded = false; ieee80211_sta_handle_tspec_ac_params(sdata); /* finally clear all the data */ memset(tx_tspec, 0, sizeof(*tx_tspec)); return 0; } return -ENOENT; } void ieee80211_nan_func_terminated(struct ieee80211_vif *vif, u8 inst_id, enum nl80211_nan_func_term_reason reason, gfp_t gfp) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct cfg80211_nan_func *func; u64 cookie; if (WARN_ON(vif->type != NL80211_IFTYPE_NAN)) return; spin_lock_bh(&sdata->u.nan.func_lock); func = idr_find(&sdata->u.nan.function_inst_ids, inst_id); if (WARN_ON(!func)) { spin_unlock_bh(&sdata->u.nan.func_lock); return; } cookie = func->cookie; idr_remove(&sdata->u.nan.function_inst_ids, inst_id); spin_unlock_bh(&sdata->u.nan.func_lock); cfg80211_free_nan_func(func); cfg80211_nan_func_terminated(ieee80211_vif_to_wdev(vif), inst_id, reason, cookie, gfp); } EXPORT_SYMBOL(ieee80211_nan_func_terminated); void ieee80211_nan_func_match(struct ieee80211_vif *vif, struct cfg80211_nan_match_params *match, gfp_t gfp) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct cfg80211_nan_func *func; if (WARN_ON(vif->type != NL80211_IFTYPE_NAN)) return; spin_lock_bh(&sdata->u.nan.func_lock); func = idr_find(&sdata->u.nan.function_inst_ids, match->inst_id); if (WARN_ON(!func)) { spin_unlock_bh(&sdata->u.nan.func_lock); return; } match->cookie = func->cookie; spin_unlock_bh(&sdata->u.nan.func_lock); cfg80211_nan_match(ieee80211_vif_to_wdev(vif), match, gfp); } EXPORT_SYMBOL(ieee80211_nan_func_match); static int ieee80211_set_multicast_to_unicast(struct wiphy *wiphy, struct net_device *dev, const bool enabled) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); sdata->u.ap.multicast_to_unicast = enabled; return 0; } void ieee80211_fill_txq_stats(struct cfg80211_txq_stats *txqstats, struct txq_info *txqi) { if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_BACKLOG_BYTES))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_BACKLOG_BYTES); txqstats->backlog_bytes = txqi->tin.backlog_bytes; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_BACKLOG_PACKETS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_BACKLOG_PACKETS); txqstats->backlog_packets = txqi->tin.backlog_packets; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_FLOWS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_FLOWS); txqstats->flows = txqi->tin.flows; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_DROPS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_DROPS); txqstats->drops = txqi->cstats.drop_count; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_ECN_MARKS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_ECN_MARKS); txqstats->ecn_marks = txqi->cstats.ecn_mark; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_OVERLIMIT))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_OVERLIMIT); txqstats->overlimit = txqi->tin.overlimit; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_COLLISIONS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_COLLISIONS); txqstats->collisions = txqi->tin.collisions; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_TX_BYTES))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_TX_BYTES); txqstats->tx_bytes = txqi->tin.tx_bytes; } if (!(txqstats->filled & BIT(NL80211_TXQ_STATS_TX_PACKETS))) { txqstats->filled |= BIT(NL80211_TXQ_STATS_TX_PACKETS); txqstats->tx_packets = txqi->tin.tx_packets; } } static int ieee80211_get_txq_stats(struct wiphy *wiphy, struct wireless_dev *wdev, struct cfg80211_txq_stats *txqstats) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata; int ret = 0; spin_lock_bh(&local->fq.lock); rcu_read_lock(); if (wdev) { sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); if (!sdata->vif.txq) { ret = 1; goto out; } ieee80211_fill_txq_stats(txqstats, to_txq_info(sdata->vif.txq)); } else { /* phy stats */ txqstats->filled |= BIT(NL80211_TXQ_STATS_BACKLOG_PACKETS) | BIT(NL80211_TXQ_STATS_BACKLOG_BYTES) | BIT(NL80211_TXQ_STATS_OVERLIMIT) | BIT(NL80211_TXQ_STATS_OVERMEMORY) | BIT(NL80211_TXQ_STATS_COLLISIONS) | BIT(NL80211_TXQ_STATS_MAX_FLOWS); txqstats->backlog_packets = local->fq.backlog; txqstats->backlog_bytes = local->fq.memory_usage; txqstats->overlimit = local->fq.overlimit; txqstats->overmemory = local->fq.overmemory; txqstats->collisions = local->fq.collisions; txqstats->max_flows = local->fq.flows_cnt; } out: rcu_read_unlock(); spin_unlock_bh(&local->fq.lock); return ret; } static int ieee80211_get_ftm_responder_stats(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ftm_responder_stats *ftm_stats) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); return drv_get_ftm_responder_stats(local, sdata, ftm_stats); } static int ieee80211_start_pmsr(struct wiphy *wiphy, struct wireless_dev *dev, struct cfg80211_pmsr_request *request) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(dev); return drv_start_pmsr(local, sdata, request); } static void ieee80211_abort_pmsr(struct wiphy *wiphy, struct wireless_dev *dev, struct cfg80211_pmsr_request *request) { struct ieee80211_local *local = wiphy_priv(wiphy); struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(dev); return drv_abort_pmsr(local, sdata, request); } static int ieee80211_set_tid_config(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_tid_config *tid_conf) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (!sdata->local->ops->set_tid_config) return -EOPNOTSUPP; if (!tid_conf->peer) return drv_set_tid_config(sdata->local, sdata, NULL, tid_conf); sta = sta_info_get_bss(sdata, tid_conf->peer); if (!sta) return -ENOENT; return drv_set_tid_config(sdata->local, sdata, &sta->sta, tid_conf); } static int ieee80211_reset_tid_config(struct wiphy *wiphy, struct net_device *dev, const u8 *peer, u8 tids) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); if (!sdata->local->ops->reset_tid_config) return -EOPNOTSUPP; if (!peer) return drv_reset_tid_config(sdata->local, sdata, NULL, tids); sta = sta_info_get_bss(sdata, peer); if (!sta) return -ENOENT; return drv_reset_tid_config(sdata->local, sdata, &sta->sta, tids); } static int ieee80211_set_sar_specs(struct wiphy *wiphy, struct cfg80211_sar_specs *sar) { struct ieee80211_local *local = wiphy_priv(wiphy); if (!local->ops->set_sar_specs) return -EOPNOTSUPP; return local->ops->set_sar_specs(&local->hw, sar); } static int ieee80211_set_after_color_change_beacon(struct ieee80211_link_data *link, u64 *changed) { struct ieee80211_sub_if_data *sdata = link->sdata; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: { int ret; if (!link->u.ap.next_beacon) return -EINVAL; ret = ieee80211_assign_beacon(sdata, link, link->u.ap.next_beacon, NULL, NULL, changed); ieee80211_free_next_beacon(link); if (ret < 0) return ret; break; } default: WARN_ON_ONCE(1); return -EINVAL; } return 0; } static int ieee80211_set_color_change_beacon(struct ieee80211_link_data *link, struct cfg80211_color_change_settings *params, u64 *changed) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_color_change_settings color_change = {}; int err; switch (sdata->vif.type) { case NL80211_IFTYPE_AP: link->u.ap.next_beacon = cfg80211_beacon_dup(¶ms->beacon_next); if (!link->u.ap.next_beacon) return -ENOMEM; if (params->count <= 1) break; color_change.counter_offset_beacon = params->counter_offset_beacon; color_change.counter_offset_presp = params->counter_offset_presp; color_change.count = params->count; err = ieee80211_assign_beacon(sdata, link, ¶ms->beacon_color_change, NULL, &color_change, changed); if (err < 0) { ieee80211_free_next_beacon(link); return err; } break; default: return -EOPNOTSUPP; } return 0; } static void ieee80211_color_change_bss_config_notify(struct ieee80211_link_data *link, u8 color, int enable, u64 changed) { struct ieee80211_sub_if_data *sdata = link->sdata; lockdep_assert_wiphy(sdata->local->hw.wiphy); link->conf->he_bss_color.color = color; link->conf->he_bss_color.enabled = enable; changed |= BSS_CHANGED_HE_BSS_COLOR; ieee80211_link_info_change_notify(sdata, link, changed); if (!link->conf->nontransmitted && rcu_access_pointer(link->conf->tx_bss_conf)) { struct ieee80211_link_data *tmp; for_each_sdata_link(sdata->local, tmp) { if (tmp->sdata == sdata || rcu_access_pointer(tmp->conf->tx_bss_conf) != link->conf) continue; tmp->conf->he_bss_color.color = color; tmp->conf->he_bss_color.enabled = enable; ieee80211_link_info_change_notify(tmp->sdata, tmp, BSS_CHANGED_HE_BSS_COLOR); } } } static int ieee80211_color_change_finalize(struct ieee80211_link_data *link) { struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_local *local = sdata->local; u64 changed = 0; int err; lockdep_assert_wiphy(local->hw.wiphy); link->conf->color_change_active = false; err = ieee80211_set_after_color_change_beacon(link, &changed); if (err) { cfg80211_color_change_aborted_notify(sdata->dev, link->link_id); return err; } ieee80211_color_change_bss_config_notify(link, link->conf->color_change_color, 1, changed); cfg80211_color_change_notify(sdata->dev, link->link_id); return 0; } void ieee80211_color_change_finalize_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_link_data *link = container_of(work, struct ieee80211_link_data, color_change_finalize_work); struct ieee80211_sub_if_data *sdata = link->sdata; struct ieee80211_bss_conf *link_conf = link->conf; struct ieee80211_local *local = sdata->local; lockdep_assert_wiphy(local->hw.wiphy); /* AP might have been stopped while waiting for the lock. */ if (!link_conf->color_change_active) return; if (!ieee80211_sdata_running(sdata)) return; ieee80211_color_change_finalize(link); } void ieee80211_color_collision_detection_work(struct wiphy *wiphy, struct wiphy_work *work) { struct ieee80211_link_data *link = container_of(work, struct ieee80211_link_data, color_collision_detect_work.work); struct ieee80211_sub_if_data *sdata = link->sdata; cfg80211_obss_color_collision_notify(sdata->dev, link->color_bitmap, link->link_id); } void ieee80211_color_change_finish(struct ieee80211_vif *vif, u8 link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_link_data *link; if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) return; rcu_read_lock(); link = rcu_dereference(sdata->link[link_id]); if (WARN_ON(!link)) { rcu_read_unlock(); return; } wiphy_work_queue(sdata->local->hw.wiphy, &link->color_change_finalize_work); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_color_change_finish); void ieee80211_obss_color_collision_notify(struct ieee80211_vif *vif, u64 color_bitmap, u8 link_id) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); struct ieee80211_link_data *link; if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) return; rcu_read_lock(); link = rcu_dereference(sdata->link[link_id]); if (WARN_ON(!link)) { rcu_read_unlock(); return; } if (link->conf->color_change_active || link->conf->csa_active) { rcu_read_unlock(); return; } if (wiphy_delayed_work_pending(sdata->local->hw.wiphy, &link->color_collision_detect_work)) { rcu_read_unlock(); return; } link->color_bitmap = color_bitmap; /* queue the color collision detection event every 500 ms in order to * avoid sending too much netlink messages to userspace. */ wiphy_delayed_work_queue(sdata->local->hw.wiphy, &link->color_collision_detect_work, msecs_to_jiffies(500)); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ieee80211_obss_color_collision_notify); static int ieee80211_color_change(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_color_change_settings *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; struct ieee80211_bss_conf *link_conf; struct ieee80211_link_data *link; u8 link_id = params->link_id; u64 changed = 0; int err; lockdep_assert_wiphy(local->hw.wiphy); if (WARN_ON(link_id >= IEEE80211_MLD_MAX_NUM_LINKS)) return -EINVAL; link = wiphy_dereference(wiphy, sdata->link[link_id]); if (!link) return -ENOLINK; link_conf = link->conf; if (link_conf->nontransmitted) return -EINVAL; /* don't allow another color change if one is already active or if csa * is active */ if (link_conf->color_change_active || link_conf->csa_active) { err = -EBUSY; goto out; } err = ieee80211_set_unsol_bcast_probe_resp(sdata, ¶ms->unsol_bcast_probe_resp, link, link_conf, &changed); if (err) goto out; err = ieee80211_set_color_change_beacon(link, params, &changed); if (err) goto out; link_conf->color_change_active = true; link_conf->color_change_color = params->color; cfg80211_color_change_started_notify(sdata->dev, params->count, link_id); if (changed) ieee80211_color_change_bss_config_notify(link, 0, 0, changed); else /* if the beacon didn't change, we can finalize immediately */ ieee80211_color_change_finalize(link); out: return err; } static int ieee80211_set_radar_background(struct wiphy *wiphy, struct cfg80211_chan_def *chandef) { struct ieee80211_local *local = wiphy_priv(wiphy); if (!local->ops->set_radar_background) return -EOPNOTSUPP; return local->ops->set_radar_background(&local->hw, chandef); } static int ieee80211_add_intf_link(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); lockdep_assert_wiphy(sdata->local->hw.wiphy); if (wdev->use_4addr) return -EOPNOTSUPP; return ieee80211_vif_set_links(sdata, wdev->valid_links, 0); } static void ieee80211_del_intf_link(struct wiphy *wiphy, struct wireless_dev *wdev, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev); u16 new_links = wdev->valid_links & ~BIT(link_id); lockdep_assert_wiphy(sdata->local->hw.wiphy); /* During the link teardown process, certain functions require the * link_id to remain in the valid_links bitmap. Therefore, instead * of removing the link_id from the bitmap, pass a masked value to * simulate as if link_id does not exist anymore. */ ieee80211_vif_set_links(sdata, new_links, 0); } static int ieee80211_add_link_station(struct wiphy *wiphy, struct net_device *dev, struct link_station_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; int ret; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get_bss(sdata, params->mld_mac); if (!sta) return -ENOENT; if (!sta->sta.valid_links) return -EINVAL; if (sta->sta.valid_links & BIT(params->link_id)) return -EALREADY; ret = ieee80211_sta_allocate_link(sta, params->link_id); if (ret) return ret; ret = sta_link_apply_parameters(local, sta, STA_LINK_MODE_NEW, params); if (ret) { ieee80211_sta_free_link(sta, params->link_id); return ret; } if (test_sta_flag(sta, WLAN_STA_ASSOC)) { struct link_sta_info *link_sta; link_sta = sdata_dereference(sta->link[params->link_id], sdata); rate_control_rate_init(link_sta); } /* ieee80211_sta_activate_link frees the link upon failure */ return ieee80211_sta_activate_link(sta, params->link_id); } static int ieee80211_mod_link_station(struct wiphy *wiphy, struct net_device *dev, struct link_station_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = wiphy_priv(wiphy); struct sta_info *sta; lockdep_assert_wiphy(local->hw.wiphy); sta = sta_info_get_bss(sdata, params->mld_mac); if (!sta) return -ENOENT; if (!(sta->sta.valid_links & BIT(params->link_id))) return -EINVAL; return sta_link_apply_parameters(local, sta, STA_LINK_MODE_LINK_MODIFY, params); } static int ieee80211_del_link_station(struct wiphy *wiphy, struct net_device *dev, struct link_station_del_parameters *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); sta = sta_info_get_bss(sdata, params->mld_mac); if (!sta) return -ENOENT; if (!(sta->sta.valid_links & BIT(params->link_id))) return -EINVAL; /* must not create a STA without links */ if (sta->sta.valid_links == BIT(params->link_id)) return -EINVAL; ieee80211_sta_remove_link(sta, params->link_id); return 0; } static int ieee80211_set_hw_timestamp(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_set_hw_timestamp *hwts) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; if (!local->ops->set_hw_timestamp) return -EOPNOTSUPP; if (!check_sdata_in_driver(sdata)) return -EIO; return local->ops->set_hw_timestamp(&local->hw, &sdata->vif, hwts); } static int ieee80211_set_ttlm(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ttlm_params *params) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); lockdep_assert_wiphy(sdata->local->hw.wiphy); return ieee80211_req_neg_ttlm(sdata, params); } static int ieee80211_assoc_ml_reconf(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_ml_reconf_req *req) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); lockdep_assert_wiphy(sdata->local->hw.wiphy); return ieee80211_mgd_assoc_ml_reconf(sdata, req); } static int ieee80211_set_epcs(struct wiphy *wiphy, struct net_device *dev, bool enable) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); return ieee80211_mgd_set_epcs(sdata, enable); } const struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, .change_virtual_intf = ieee80211_change_iface, .start_p2p_device = ieee80211_start_p2p_device, .stop_p2p_device = ieee80211_stop_p2p_device, .add_key = ieee80211_add_key, .del_key = ieee80211_del_key, .get_key = ieee80211_get_key, .set_default_key = ieee80211_config_default_key, .set_default_mgmt_key = ieee80211_config_default_mgmt_key, .set_default_beacon_key = ieee80211_config_default_beacon_key, .start_ap = ieee80211_start_ap, .change_beacon = ieee80211_change_beacon, .stop_ap = ieee80211_stop_ap, .add_station = ieee80211_add_station, .del_station = ieee80211_del_station, .change_station = ieee80211_change_station, .get_station = ieee80211_get_station, .dump_station = ieee80211_dump_station, .dump_survey = ieee80211_dump_survey, #ifdef CONFIG_MAC80211_MESH .add_mpath = ieee80211_add_mpath, .del_mpath = ieee80211_del_mpath, .change_mpath = ieee80211_change_mpath, .get_mpath = ieee80211_get_mpath, .dump_mpath = ieee80211_dump_mpath, .get_mpp = ieee80211_get_mpp, .dump_mpp = ieee80211_dump_mpp, .update_mesh_config = ieee80211_update_mesh_config, .get_mesh_config = ieee80211_get_mesh_config, .join_mesh = ieee80211_join_mesh, .leave_mesh = ieee80211_leave_mesh, #endif .join_ocb = ieee80211_join_ocb, .leave_ocb = ieee80211_leave_ocb, .change_bss = ieee80211_change_bss, .inform_bss = ieee80211_inform_bss, .set_txq_params = ieee80211_set_txq_params, .set_monitor_channel = ieee80211_set_monitor_channel, .suspend = ieee80211_suspend, .resume = ieee80211_resume, .scan = ieee80211_scan, .abort_scan = ieee80211_abort_scan, .sched_scan_start = ieee80211_sched_scan_start, .sched_scan_stop = ieee80211_sched_scan_stop, .auth = ieee80211_auth, .assoc = ieee80211_assoc, .deauth = ieee80211_deauth, .disassoc = ieee80211_disassoc, .join_ibss = ieee80211_join_ibss, .leave_ibss = ieee80211_leave_ibss, .set_mcast_rate = ieee80211_set_mcast_rate, .set_wiphy_params = ieee80211_set_wiphy_params, .set_tx_power = ieee80211_set_tx_power, .get_tx_power = ieee80211_get_tx_power, .rfkill_poll = ieee80211_rfkill_poll, CFG80211_TESTMODE_CMD(ieee80211_testmode_cmd) CFG80211_TESTMODE_DUMP(ieee80211_testmode_dump) .set_power_mgmt = ieee80211_set_power_mgmt, .set_bitrate_mask = ieee80211_set_bitrate_mask, .remain_on_channel = ieee80211_remain_on_channel, .cancel_remain_on_channel = ieee80211_cancel_remain_on_channel, .mgmt_tx = ieee80211_mgmt_tx, .mgmt_tx_cancel_wait = ieee80211_mgmt_tx_cancel_wait, .set_cqm_rssi_config = ieee80211_set_cqm_rssi_config, .set_cqm_rssi_range_config = ieee80211_set_cqm_rssi_range_config, .update_mgmt_frame_registrations = ieee80211_update_mgmt_frame_registrations, .set_antenna = ieee80211_set_antenna, .get_antenna = ieee80211_get_antenna, .set_rekey_data = ieee80211_set_rekey_data, .tdls_oper = ieee80211_tdls_oper, .tdls_mgmt = ieee80211_tdls_mgmt, .tdls_channel_switch = ieee80211_tdls_channel_switch, .tdls_cancel_channel_switch = ieee80211_tdls_cancel_channel_switch, .probe_client = ieee80211_probe_client, .set_noack_map = ieee80211_set_noack_map, #ifdef CONFIG_PM .set_wakeup = ieee80211_set_wakeup, #endif .get_channel = ieee80211_cfg_get_channel, .start_radar_detection = ieee80211_start_radar_detection, .end_cac = ieee80211_end_cac, .channel_switch = ieee80211_channel_switch, .set_qos_map = ieee80211_set_qos_map, .set_ap_chanwidth = ieee80211_set_ap_chanwidth, .add_tx_ts = ieee80211_add_tx_ts, .del_tx_ts = ieee80211_del_tx_ts, .start_nan = ieee80211_start_nan, .stop_nan = ieee80211_stop_nan, .nan_change_conf = ieee80211_nan_change_conf, .add_nan_func = ieee80211_add_nan_func, .del_nan_func = ieee80211_del_nan_func, .set_multicast_to_unicast = ieee80211_set_multicast_to_unicast, .tx_control_port = ieee80211_tx_control_port, .get_txq_stats = ieee80211_get_txq_stats, .get_ftm_responder_stats = ieee80211_get_ftm_responder_stats, .start_pmsr = ieee80211_start_pmsr, .abort_pmsr = ieee80211_abort_pmsr, .probe_mesh_link = ieee80211_probe_mesh_link, .set_tid_config = ieee80211_set_tid_config, .reset_tid_config = ieee80211_reset_tid_config, .set_sar_specs = ieee80211_set_sar_specs, .color_change = ieee80211_color_change, .set_radar_background = ieee80211_set_radar_background, .add_intf_link = ieee80211_add_intf_link, .del_intf_link = ieee80211_del_intf_link, .add_link_station = ieee80211_add_link_station, .mod_link_station = ieee80211_mod_link_station, .del_link_station = ieee80211_del_link_station, .set_hw_timestamp = ieee80211_set_hw_timestamp, .set_ttlm = ieee80211_set_ttlm, .get_radio_mask = ieee80211_get_radio_mask, .assoc_ml_reconf = ieee80211_assoc_ml_reconf, .set_epcs = ieee80211_set_epcs, }; |
| 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 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 | // SPDX-License-Identifier: GPL-2.0 /* * Wireless utility functions * * Copyright 2007-2009 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright 2017 Intel Deutschland GmbH * Copyright (C) 2018-2023, 2025 Intel Corporation */ #include <linux/export.h> #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/slab.h> #include <linux/ieee80211.h> #include <net/cfg80211.h> #include <net/ip.h> #include <net/dsfield.h> #include <linux/if_vlan.h> #include <linux/mpls.h> #include <linux/gcd.h> #include <linux/bitfield.h> #include <linux/nospec.h> #include "core.h" #include "rdev-ops.h" const struct ieee80211_rate * ieee80211_get_response_rate(struct ieee80211_supported_band *sband, u32 basic_rates, int bitrate) { struct ieee80211_rate *result = &sband->bitrates[0]; int i; for (i = 0; i < sband->n_bitrates; i++) { if (!(basic_rates & BIT(i))) continue; if (sband->bitrates[i].bitrate > bitrate) continue; result = &sband->bitrates[i]; } return result; } EXPORT_SYMBOL(ieee80211_get_response_rate); u32 ieee80211_mandatory_rates(struct ieee80211_supported_band *sband) { struct ieee80211_rate *bitrates; u32 mandatory_rates = 0; enum ieee80211_rate_flags mandatory_flag; int i; if (WARN_ON(!sband)) return 1; if (sband->band == NL80211_BAND_2GHZ) mandatory_flag = IEEE80211_RATE_MANDATORY_B; else mandatory_flag = IEEE80211_RATE_MANDATORY_A; bitrates = sband->bitrates; for (i = 0; i < sband->n_bitrates; i++) if (bitrates[i].flags & mandatory_flag) mandatory_rates |= BIT(i); return mandatory_rates; } EXPORT_SYMBOL(ieee80211_mandatory_rates); u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band) { /* see 802.11 17.3.8.3.2 and Annex J * there are overlapping channel numbers in 5GHz and 2GHz bands */ if (chan <= 0) return 0; /* not supported */ switch (band) { case NL80211_BAND_2GHZ: case NL80211_BAND_LC: if (chan == 14) return MHZ_TO_KHZ(2484); else if (chan < 14) return MHZ_TO_KHZ(2407 + chan * 5); break; case NL80211_BAND_5GHZ: if (chan >= 182 && chan <= 196) return MHZ_TO_KHZ(4000 + chan * 5); else return MHZ_TO_KHZ(5000 + chan * 5); break; case NL80211_BAND_6GHZ: /* see 802.11ax D6.1 27.3.23.2 */ if (chan == 2) return MHZ_TO_KHZ(5935); if (chan <= 233) return MHZ_TO_KHZ(5950 + chan * 5); break; case NL80211_BAND_60GHZ: if (chan < 7) return MHZ_TO_KHZ(56160 + chan * 2160); break; case NL80211_BAND_S1GHZ: return 902000 + chan * 500; default: ; } return 0; /* not supported */ } EXPORT_SYMBOL(ieee80211_channel_to_freq_khz); enum nl80211_chan_width ieee80211_s1g_channel_width(const struct ieee80211_channel *chan) { if (WARN_ON(!chan || chan->band != NL80211_BAND_S1GHZ)) return NL80211_CHAN_WIDTH_20_NOHT; /*S1G defines a single allowed channel width per channel. * Extract that width here. */ if (chan->flags & IEEE80211_CHAN_1MHZ) return NL80211_CHAN_WIDTH_1; else if (chan->flags & IEEE80211_CHAN_2MHZ) return NL80211_CHAN_WIDTH_2; else if (chan->flags & IEEE80211_CHAN_4MHZ) return NL80211_CHAN_WIDTH_4; else if (chan->flags & IEEE80211_CHAN_8MHZ) return NL80211_CHAN_WIDTH_8; else if (chan->flags & IEEE80211_CHAN_16MHZ) return NL80211_CHAN_WIDTH_16; pr_err("unknown channel width for channel at %dKHz?\n", ieee80211_channel_to_khz(chan)); return NL80211_CHAN_WIDTH_1; } EXPORT_SYMBOL(ieee80211_s1g_channel_width); int ieee80211_freq_khz_to_channel(u32 freq) { /* TODO: just handle MHz for now */ freq = KHZ_TO_MHZ(freq); /* see 802.11 17.3.8.3.2 and Annex J */ if (freq == 2484) return 14; else if (freq < 2484) return (freq - 2407) / 5; else if (freq >= 4910 && freq <= 4980) return (freq - 4000) / 5; else if (freq < 5925) return (freq - 5000) / 5; else if (freq == 5935) return 2; else if (freq <= 45000) /* DMG band lower limit */ /* see 802.11ax D6.1 27.3.22.2 */ return (freq - 5950) / 5; else if (freq >= 58320 && freq <= 70200) return (freq - 56160) / 2160; else return 0; } EXPORT_SYMBOL(ieee80211_freq_khz_to_channel); struct ieee80211_channel *ieee80211_get_channel_khz(struct wiphy *wiphy, u32 freq) { enum nl80211_band band; struct ieee80211_supported_band *sband; int i; for (band = 0; band < NUM_NL80211_BANDS; band++) { sband = wiphy->bands[band]; if (!sband) continue; for (i = 0; i < sband->n_channels; i++) { struct ieee80211_channel *chan = &sband->channels[i]; if (ieee80211_channel_to_khz(chan) == freq) return chan; } } return NULL; } EXPORT_SYMBOL(ieee80211_get_channel_khz); static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) { int i, want; switch (sband->band) { case NL80211_BAND_5GHZ: case NL80211_BAND_6GHZ: want = 3; for (i = 0; i < sband->n_bitrates; i++) { if (sband->bitrates[i].bitrate == 60 || sband->bitrates[i].bitrate == 120 || sband->bitrates[i].bitrate == 240) { sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_A; want--; } } WARN_ON(want); break; case NL80211_BAND_2GHZ: case NL80211_BAND_LC: want = 7; for (i = 0; i < sband->n_bitrates; i++) { switch (sband->bitrates[i].bitrate) { case 10: case 20: case 55: case 110: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_B | IEEE80211_RATE_MANDATORY_G; want--; break; case 60: case 120: case 240: sband->bitrates[i].flags |= IEEE80211_RATE_MANDATORY_G; want--; fallthrough; default: sband->bitrates[i].flags |= IEEE80211_RATE_ERP_G; break; } } WARN_ON(want != 0 && want != 3); break; case NL80211_BAND_60GHZ: /* check for mandatory HT MCS 1..4 */ WARN_ON(!sband->ht_cap.ht_supported); WARN_ON((sband->ht_cap.mcs.rx_mask[0] & 0x1e) != 0x1e); break; case NL80211_BAND_S1GHZ: /* Figure 9-589bd: 3 means unsupported, so != 3 means at least * mandatory is ok. */ WARN_ON((sband->s1g_cap.nss_mcs[0] & 0x3) == 0x3); break; case NUM_NL80211_BANDS: default: WARN_ON(1); break; } } void ieee80211_set_bitrate_flags(struct wiphy *wiphy) { enum nl80211_band band; for (band = 0; band < NUM_NL80211_BANDS; band++) if (wiphy->bands[band]) set_mandatory_flags_band(wiphy->bands[band]); } bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher) { int i; for (i = 0; i < wiphy->n_cipher_suites; i++) if (cipher == wiphy->cipher_suites[i]) return true; return false; } static bool cfg80211_igtk_cipher_supported(struct cfg80211_registered_device *rdev) { struct wiphy *wiphy = &rdev->wiphy; int i; for (i = 0; i < wiphy->n_cipher_suites; i++) { switch (wiphy->cipher_suites[i]) { case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: return true; } } return false; } bool cfg80211_valid_key_idx(struct cfg80211_registered_device *rdev, int key_idx, bool pairwise) { int max_key_idx; if (pairwise) max_key_idx = 3; else if (wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION) || wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT)) max_key_idx = 7; else if (cfg80211_igtk_cipher_supported(rdev)) max_key_idx = 5; else max_key_idx = 3; if (key_idx < 0 || key_idx > max_key_idx) return false; return true; } int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev, struct key_params *params, int key_idx, bool pairwise, const u8 *mac_addr) { if (!cfg80211_valid_key_idx(rdev, key_idx, pairwise)) return -EINVAL; if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN)) return -EINVAL; if (pairwise && !mac_addr) return -EINVAL; switch (params->cipher) { case WLAN_CIPHER_SUITE_TKIP: /* Extended Key ID can only be used with CCMP/GCMP ciphers */ if ((pairwise && key_idx) || params->mode != NL80211_KEY_RX_TX) return -EINVAL; break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: /* IEEE802.11-2016 allows only 0 and - when supporting * Extended Key ID - 1 as index for pairwise keys. * @NL80211_KEY_NO_TX is only allowed for pairwise keys when * the driver supports Extended Key ID. * @NL80211_KEY_SET_TX can't be set when installing and * validating a key. */ if ((params->mode == NL80211_KEY_NO_TX && !pairwise) || params->mode == NL80211_KEY_SET_TX) return -EINVAL; if (wiphy_ext_feature_isset(&rdev->wiphy, NL80211_EXT_FEATURE_EXT_KEY_ID)) { if (pairwise && (key_idx < 0 || key_idx > 1)) return -EINVAL; } else if (pairwise && key_idx) { return -EINVAL; } break; case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: /* Disallow BIP (group-only) cipher as pairwise cipher */ if (pairwise) return -EINVAL; if (key_idx < 4) return -EINVAL; break; case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: if (key_idx > 3) return -EINVAL; break; default: break; } switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: if (params->key_len != WLAN_KEY_LEN_WEP40) return -EINVAL; break; case WLAN_CIPHER_SUITE_TKIP: if (params->key_len != WLAN_KEY_LEN_TKIP) return -EINVAL; break; case WLAN_CIPHER_SUITE_CCMP: if (params->key_len != WLAN_KEY_LEN_CCMP) return -EINVAL; break; case WLAN_CIPHER_SUITE_CCMP_256: if (params->key_len != WLAN_KEY_LEN_CCMP_256) return -EINVAL; break; case WLAN_CIPHER_SUITE_GCMP: if (params->key_len != WLAN_KEY_LEN_GCMP) return -EINVAL; break; case WLAN_CIPHER_SUITE_GCMP_256: if (params->key_len != WLAN_KEY_LEN_GCMP_256) return -EINVAL; break; case WLAN_CIPHER_SUITE_WEP104: if (params->key_len != WLAN_KEY_LEN_WEP104) return -EINVAL; break; case WLAN_CIPHER_SUITE_AES_CMAC: if (params->key_len != WLAN_KEY_LEN_AES_CMAC) return -EINVAL; break; case WLAN_CIPHER_SUITE_BIP_CMAC_256: if (params->key_len != WLAN_KEY_LEN_BIP_CMAC_256) return -EINVAL; break; case WLAN_CIPHER_SUITE_BIP_GMAC_128: if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_128) return -EINVAL; break; case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (params->key_len != WLAN_KEY_LEN_BIP_GMAC_256) return -EINVAL; break; default: /* * We don't know anything about this algorithm, * allow using it -- but the driver must check * all parameters! We still check below whether * or not the driver supports this algorithm, * of course. */ break; } if (params->seq) { switch (params->cipher) { case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_WEP104: /* These ciphers do not use key sequence */ return -EINVAL; case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_GCMP: case WLAN_CIPHER_SUITE_GCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: case WLAN_CIPHER_SUITE_BIP_CMAC_256: case WLAN_CIPHER_SUITE_BIP_GMAC_128: case WLAN_CIPHER_SUITE_BIP_GMAC_256: if (params->seq_len != 6) return -EINVAL; break; } } if (!cfg80211_supported_cipher_suite(&rdev->wiphy, params->cipher)) return -EINVAL; return 0; } unsigned int __attribute_const__ ieee80211_hdrlen(__le16 fc) { unsigned int hdrlen = 24; if (ieee80211_is_ext(fc)) { hdrlen = 4; goto out; } if (ieee80211_is_data(fc)) { if (ieee80211_has_a4(fc)) hdrlen = 30; if (ieee80211_is_data_qos(fc)) { hdrlen += IEEE80211_QOS_CTL_LEN; if (ieee80211_has_order(fc)) hdrlen += IEEE80211_HT_CTL_LEN; } goto out; } if (ieee80211_is_mgmt(fc)) { if (ieee80211_has_order(fc)) hdrlen += IEEE80211_HT_CTL_LEN; goto out; } if (ieee80211_is_ctl(fc)) { /* * ACK and CTS are 10 bytes, all others 16. To see how * to get this condition consider * subtype mask: 0b0000000011110000 (0x00F0) * ACK subtype: 0b0000000011010000 (0x00D0) * CTS subtype: 0b0000000011000000 (0x00C0) * bits that matter: ^^^ (0x00E0) * value of those: 0b0000000011000000 (0x00C0) */ if ((fc & cpu_to_le16(0x00E0)) == cpu_to_le16(0x00C0)) hdrlen = 10; else hdrlen = 16; } out: return hdrlen; } EXPORT_SYMBOL(ieee80211_hdrlen); unsigned int ieee80211_get_hdrlen_from_skb(const struct sk_buff *skb) { const struct ieee80211_hdr *hdr = (const struct ieee80211_hdr *)skb->data; unsigned int hdrlen; if (unlikely(skb->len < 10)) return 0; hdrlen = ieee80211_hdrlen(hdr->frame_control); if (unlikely(hdrlen > skb->len)) return 0; return hdrlen; } EXPORT_SYMBOL(ieee80211_get_hdrlen_from_skb); static unsigned int __ieee80211_get_mesh_hdrlen(u8 flags) { int ae = flags & MESH_FLAGS_AE; /* 802.11-2012, 8.2.4.7.3 */ switch (ae) { default: case 0: return 6; case MESH_FLAGS_AE_A4: return 12; case MESH_FLAGS_AE_A5_A6: return 18; } } unsigned int ieee80211_get_mesh_hdrlen(struct ieee80211s_hdr *meshhdr) { return __ieee80211_get_mesh_hdrlen(meshhdr->flags); } EXPORT_SYMBOL(ieee80211_get_mesh_hdrlen); bool ieee80211_get_8023_tunnel_proto(const void *hdr, __be16 *proto) { const __be16 *hdr_proto = hdr + ETH_ALEN; if (!(ether_addr_equal(hdr, rfc1042_header) && *hdr_proto != htons(ETH_P_AARP) && *hdr_proto != htons(ETH_P_IPX)) && !ether_addr_equal(hdr, bridge_tunnel_header)) return false; *proto = *hdr_proto; return true; } EXPORT_SYMBOL(ieee80211_get_8023_tunnel_proto); int ieee80211_strip_8023_mesh_hdr(struct sk_buff *skb) { const void *mesh_addr; struct { struct ethhdr eth; u8 flags; } payload; int hdrlen; int ret; ret = skb_copy_bits(skb, 0, &payload, sizeof(payload)); if (ret) return ret; hdrlen = sizeof(payload.eth) + __ieee80211_get_mesh_hdrlen(payload.flags); if (likely(pskb_may_pull(skb, hdrlen + 8) && ieee80211_get_8023_tunnel_proto(skb->data + hdrlen, &payload.eth.h_proto))) hdrlen += ETH_ALEN + 2; else if (!pskb_may_pull(skb, hdrlen)) return -EINVAL; else payload.eth.h_proto = htons(skb->len - hdrlen); mesh_addr = skb->data + sizeof(payload.eth) + ETH_ALEN; switch (payload.flags & MESH_FLAGS_AE) { case MESH_FLAGS_AE_A4: memcpy(&payload.eth.h_source, mesh_addr, ETH_ALEN); break; case MESH_FLAGS_AE_A5_A6: memcpy(&payload.eth, mesh_addr, 2 * ETH_ALEN); break; default: break; } pskb_pull(skb, hdrlen - sizeof(payload.eth)); memcpy(skb->data, &payload.eth, sizeof(payload.eth)); return 0; } EXPORT_SYMBOL(ieee80211_strip_8023_mesh_hdr); 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) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct { u8 hdr[ETH_ALEN] __aligned(2); __be16 proto; } payload; struct ethhdr tmp; u16 hdrlen; if (unlikely(!ieee80211_is_data_present(hdr->frame_control))) return -1; hdrlen = ieee80211_hdrlen(hdr->frame_control) + data_offset; if (skb->len < hdrlen) return -1; /* convert IEEE 802.11 header + possible LLC headers into Ethernet * header * IEEE 802.11 address fields: * ToDS FromDS Addr1 Addr2 Addr3 Addr4 * 0 0 DA SA BSSID n/a * 0 1 DA BSSID SA n/a * 1 0 BSSID SA DA n/a * 1 1 RA TA DA SA */ memcpy(tmp.h_dest, ieee80211_get_DA(hdr), ETH_ALEN); memcpy(tmp.h_source, ieee80211_get_SA(hdr), ETH_ALEN); switch (hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS)) { case cpu_to_le16(IEEE80211_FCTL_TODS): if (unlikely(iftype != NL80211_IFTYPE_AP && iftype != NL80211_IFTYPE_AP_VLAN && iftype != NL80211_IFTYPE_P2P_GO)) return -1; break; case cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS): if (unlikely(iftype != NL80211_IFTYPE_MESH_POINT && iftype != NL80211_IFTYPE_AP_VLAN && iftype != NL80211_IFTYPE_STATION)) return -1; break; case cpu_to_le16(IEEE80211_FCTL_FROMDS): if ((iftype != NL80211_IFTYPE_STATION && iftype != NL80211_IFTYPE_P2P_CLIENT && iftype != NL80211_IFTYPE_MESH_POINT) || (is_multicast_ether_addr(tmp.h_dest) && ether_addr_equal(tmp.h_source, addr))) return -1; break; case cpu_to_le16(0): if (iftype != NL80211_IFTYPE_ADHOC && iftype != NL80211_IFTYPE_STATION && iftype != NL80211_IFTYPE_OCB) return -1; break; } if (likely(!is_amsdu && iftype != NL80211_IFTYPE_MESH_POINT && skb_copy_bits(skb, hdrlen, &payload, sizeof(payload)) == 0 && ieee80211_get_8023_tunnel_proto(&payload, &tmp.h_proto))) { /* remove RFC1042 or Bridge-Tunnel encapsulation */ hdrlen += ETH_ALEN + 2; skb_postpull_rcsum(skb, &payload, ETH_ALEN + 2); } else { tmp.h_proto = htons(skb->len - hdrlen); } pskb_pull(skb, hdrlen); if (!ehdr) ehdr = skb_push(skb, sizeof(struct ethhdr)); memcpy(ehdr, &tmp, sizeof(tmp)); return 0; } EXPORT_SYMBOL(ieee80211_data_to_8023_exthdr); static void __frame_add_frag(struct sk_buff *skb, struct page *page, void *ptr, int len, int size) { struct skb_shared_info *sh = skb_shinfo(skb); int page_offset; get_page(page); page_offset = ptr - page_address(page); skb_add_rx_frag(skb, sh->nr_frags, page, page_offset, len, size); } static void __ieee80211_amsdu_copy_frag(struct sk_buff *skb, struct sk_buff *frame, int offset, int len) { struct skb_shared_info *sh = skb_shinfo(skb); const skb_frag_t *frag = &sh->frags[0]; struct page *frag_page; void *frag_ptr; int frag_len, frag_size; int head_size = skb->len - skb->data_len; int cur_len; frag_page = virt_to_head_page(skb->head); frag_ptr = skb->data; frag_size = head_size; while (offset >= frag_size) { offset -= frag_size; frag_page = skb_frag_page(frag); frag_ptr = skb_frag_address(frag); frag_size = skb_frag_size(frag); frag++; } frag_ptr += offset; frag_len = frag_size - offset; cur_len = min(len, frag_len); __frame_add_frag(frame, frag_page, frag_ptr, cur_len, frag_size); len -= cur_len; while (len > 0) { frag_len = skb_frag_size(frag); cur_len = min(len, frag_len); __frame_add_frag(frame, skb_frag_page(frag), skb_frag_address(frag), cur_len, frag_len); len -= cur_len; frag++; } } static struct sk_buff * __ieee80211_amsdu_copy(struct sk_buff *skb, unsigned int hlen, int offset, int len, bool reuse_frag, int min_len) { struct sk_buff *frame; int cur_len = len; if (skb->len - offset < len) return NULL; /* * When reusing fragments, copy some data to the head to simplify * ethernet header handling and speed up protocol header processing * in the stack later. */ if (reuse_frag) cur_len = min_t(int, len, min_len); /* * Allocate and reserve two bytes more for payload * alignment since sizeof(struct ethhdr) is 14. */ frame = dev_alloc_skb(hlen + sizeof(struct ethhdr) + 2 + cur_len); if (!frame) return NULL; frame->priority = skb->priority; skb_reserve(frame, hlen + sizeof(struct ethhdr) + 2); skb_copy_bits(skb, offset, skb_put(frame, cur_len), cur_len); len -= cur_len; if (!len) return frame; offset += cur_len; __ieee80211_amsdu_copy_frag(skb, frame, offset, len); return frame; } static u16 ieee80211_amsdu_subframe_length(void *field, u8 mesh_flags, u8 hdr_type) { __le16 *field_le = field; __be16 *field_be = field; u16 len; if (hdr_type >= 2) len = le16_to_cpu(*field_le); else len = be16_to_cpu(*field_be); if (hdr_type) len += __ieee80211_get_mesh_hdrlen(mesh_flags); return len; } bool ieee80211_is_valid_amsdu(struct sk_buff *skb, u8 mesh_hdr) { int offset = 0, subframe_len, padding; for (offset = 0; offset < skb->len; offset += subframe_len + padding) { int remaining = skb->len - offset; struct { __be16 len; u8 mesh_flags; } hdr; u16 len; if (sizeof(hdr) > remaining) return false; if (skb_copy_bits(skb, offset + 2 * ETH_ALEN, &hdr, sizeof(hdr)) < 0) return false; len = ieee80211_amsdu_subframe_length(&hdr.len, hdr.mesh_flags, mesh_hdr); subframe_len = sizeof(struct ethhdr) + len; padding = (4 - subframe_len) & 0x3; if (subframe_len > remaining) return false; } return true; } EXPORT_SYMBOL(ieee80211_is_valid_amsdu); /* * Detects if an MSDU frame was maliciously converted into an A-MSDU * frame by an adversary. This is done by parsing the received frame * as if it were a regular MSDU, even though the A-MSDU flag is set. * * For non-mesh interfaces, detection involves checking whether the * payload, when interpreted as an MSDU, begins with a valid RFC1042 * header. This is done by comparing the A-MSDU subheader's destination * address to the start of the RFC1042 header. * * For mesh interfaces, the MSDU includes a 6-byte Mesh Control field * and an optional variable-length Mesh Address Extension field before * the RFC1042 header. The position of the RFC1042 header must therefore * be calculated based on the mesh header length. * * Since this function intentionally parses an A-MSDU frame as an MSDU, * it only assumes that the A-MSDU subframe header is present, and * beyond this it performs its own bounds checks under the assumption * that the frame is instead parsed as a non-aggregated MSDU. */ static bool is_amsdu_aggregation_attack(struct ethhdr *eth, struct sk_buff *skb, enum nl80211_iftype iftype) { int offset; /* Non-mesh case can be directly compared */ if (iftype != NL80211_IFTYPE_MESH_POINT) return ether_addr_equal(eth->h_dest, rfc1042_header); offset = __ieee80211_get_mesh_hdrlen(eth->h_dest[0]); if (offset == 6) { /* Mesh case with empty address extension field */ return ether_addr_equal(eth->h_source, rfc1042_header); } else if (offset + ETH_ALEN <= skb->len) { /* Mesh case with non-empty address extension field */ u8 temp[ETH_ALEN]; skb_copy_bits(skb, offset, temp, ETH_ALEN); return ether_addr_equal(temp, rfc1042_header); } return false; } 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) { unsigned int hlen = ALIGN(extra_headroom, 4); struct sk_buff *frame = NULL; int offset = 0; struct { struct ethhdr eth; uint8_t flags; } hdr; bool reuse_frag = skb->head_frag && !skb_has_frag_list(skb); bool reuse_skb = false; bool last = false; int copy_len = sizeof(hdr.eth); if (iftype == NL80211_IFTYPE_MESH_POINT) copy_len = sizeof(hdr); while (!last) { int remaining = skb->len - offset; unsigned int subframe_len; int len, mesh_len = 0; u8 padding; if (copy_len > remaining) goto purge; skb_copy_bits(skb, offset, &hdr, copy_len); if (iftype == NL80211_IFTYPE_MESH_POINT) mesh_len = __ieee80211_get_mesh_hdrlen(hdr.flags); len = ieee80211_amsdu_subframe_length(&hdr.eth.h_proto, hdr.flags, mesh_control); subframe_len = sizeof(struct ethhdr) + len; padding = (4 - subframe_len) & 0x3; /* the last MSDU has no padding */ if (subframe_len > remaining) goto purge; /* mitigate A-MSDU aggregation injection attacks, to be * checked when processing first subframe (offset == 0). */ if (offset == 0 && is_amsdu_aggregation_attack(&hdr.eth, skb, iftype)) goto purge; offset += sizeof(struct ethhdr); last = remaining <= subframe_len + padding; /* FIXME: should we really accept multicast DA? */ if ((check_da && !is_multicast_ether_addr(hdr.eth.h_dest) && !ether_addr_equal(check_da, hdr.eth.h_dest)) || (check_sa && !ether_addr_equal(check_sa, hdr.eth.h_source))) { offset += len + padding; continue; } /* reuse skb for the last subframe */ if (!skb_is_nonlinear(skb) && !reuse_frag && last) { skb_pull(skb, offset); frame = skb; reuse_skb = true; } else { frame = __ieee80211_amsdu_copy(skb, hlen, offset, len, reuse_frag, 32 + mesh_len); if (!frame) goto purge; offset += len + padding; } skb_reset_network_header(frame); frame->dev = skb->dev; frame->priority = skb->priority; if (likely(iftype != NL80211_IFTYPE_MESH_POINT && ieee80211_get_8023_tunnel_proto(frame->data, &hdr.eth.h_proto))) skb_pull(frame, ETH_ALEN + 2); memcpy(skb_push(frame, sizeof(hdr.eth)), &hdr.eth, sizeof(hdr.eth)); __skb_queue_tail(list, frame); } if (!reuse_skb) dev_kfree_skb(skb); return; purge: __skb_queue_purge(list); dev_kfree_skb(skb); } EXPORT_SYMBOL(ieee80211_amsdu_to_8023s); /* Given a data frame determine the 802.1p/1d tag to use. */ unsigned int cfg80211_classify8021d(struct sk_buff *skb, struct cfg80211_qos_map *qos_map) { unsigned int dscp; unsigned char vlan_priority; unsigned int ret; /* skb->priority values from 256->263 are magic values to * directly indicate a specific 802.1d priority. This is used * to allow 802.1d priority to be passed directly in from VLAN * tags, etc. */ if (skb->priority >= 256 && skb->priority <= 263) { ret = skb->priority - 256; goto out; } if (skb_vlan_tag_present(skb)) { vlan_priority = (skb_vlan_tag_get(skb) & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; if (vlan_priority > 0) { ret = vlan_priority; goto out; } } switch (skb->protocol) { case htons(ETH_P_IP): dscp = ipv4_get_dsfield(ip_hdr(skb)) & 0xfc; break; case htons(ETH_P_IPV6): dscp = ipv6_get_dsfield(ipv6_hdr(skb)) & 0xfc; break; case htons(ETH_P_MPLS_UC): case htons(ETH_P_MPLS_MC): { struct mpls_label mpls_tmp, *mpls; mpls = skb_header_pointer(skb, sizeof(struct ethhdr), sizeof(*mpls), &mpls_tmp); if (!mpls) return 0; ret = (ntohl(mpls->entry) & MPLS_LS_TC_MASK) >> MPLS_LS_TC_SHIFT; goto out; } case htons(ETH_P_80221): /* 802.21 is always network control traffic */ return 7; default: return 0; } if (qos_map) { unsigned int i, tmp_dscp = dscp >> 2; for (i = 0; i < qos_map->num_des; i++) { if (tmp_dscp == qos_map->dscp_exception[i].dscp) { ret = qos_map->dscp_exception[i].up; goto out; } } for (i = 0; i < 8; i++) { if (tmp_dscp >= qos_map->up[i].low && tmp_dscp <= qos_map->up[i].high) { ret = i; goto out; } } } /* The default mapping as defined Section 2.3 in RFC8325: The three * Most Significant Bits (MSBs) of the DSCP are used as the * corresponding L2 markings. */ ret = dscp >> 5; /* Handle specific DSCP values for which the default mapping (as * described above) doesn't adhere to the intended usage of the DSCP * value. See section 4 in RFC8325. Specifically, for the following * Diffserv Service Classes no update is needed: * - Standard: DF * - Low Priority Data: CS1 * - Multimedia Conferencing: AF41, AF42, AF43 * - Network Control Traffic: CS7 * - Real-Time Interactive: CS4 * - Signaling: CS5 */ switch (dscp >> 2) { case 10: case 12: case 14: /* High throughput data: AF11, AF12, AF13 */ ret = 0; break; case 16: /* Operations, Administration, and Maintenance and Provisioning: * CS2 */ ret = 0; break; case 18: case 20: case 22: /* Low latency data: AF21, AF22, AF23 */ ret = 3; break; case 24: /* Broadcasting video: CS3 */ ret = 4; break; case 26: case 28: case 30: /* Multimedia Streaming: AF31, AF32, AF33 */ ret = 4; break; case 44: /* Voice Admit: VA */ ret = 6; break; case 46: /* Telephony traffic: EF */ ret = 6; break; case 48: /* Network Control Traffic: CS6 */ ret = 7; break; } out: return array_index_nospec(ret, IEEE80211_NUM_TIDS); } EXPORT_SYMBOL(cfg80211_classify8021d); const struct element *ieee80211_bss_get_elem(struct cfg80211_bss *bss, u8 id) { const struct cfg80211_bss_ies *ies; ies = rcu_dereference(bss->ies); if (!ies) return NULL; return cfg80211_find_elem(id, ies->data, ies->len); } EXPORT_SYMBOL(ieee80211_bss_get_elem); void cfg80211_upload_connect_keys(struct wireless_dev *wdev) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); struct net_device *dev = wdev->netdev; int i; if (!wdev->connect_keys) return; for (i = 0; i < 4; i++) { if (!wdev->connect_keys->params[i].cipher) continue; if (rdev_add_key(rdev, dev, -1, i, false, NULL, &wdev->connect_keys->params[i])) { netdev_err(dev, "failed to set key %d\n", i); continue; } if (wdev->connect_keys->def == i && rdev_set_default_key(rdev, dev, -1, i, true, true)) { netdev_err(dev, "failed to set defkey %d\n", i); continue; } } kfree_sensitive(wdev->connect_keys); wdev->connect_keys = NULL; } void cfg80211_process_wdev_events(struct wireless_dev *wdev) { struct cfg80211_event *ev; unsigned long flags; spin_lock_irqsave(&wdev->event_lock, flags); while (!list_empty(&wdev->event_list)) { ev = list_first_entry(&wdev->event_list, struct cfg80211_event, list); list_del(&ev->list); spin_unlock_irqrestore(&wdev->event_lock, flags); switch (ev->type) { case EVENT_CONNECT_RESULT: __cfg80211_connect_result( wdev->netdev, &ev->cr, ev->cr.status == WLAN_STATUS_SUCCESS); break; case EVENT_ROAMED: __cfg80211_roamed(wdev, &ev->rm); break; case EVENT_DISCONNECTED: __cfg80211_disconnected(wdev->netdev, ev->dc.ie, ev->dc.ie_len, ev->dc.reason, !ev->dc.locally_generated); break; case EVENT_IBSS_JOINED: __cfg80211_ibss_joined(wdev->netdev, ev->ij.bssid, ev->ij.channel); break; case EVENT_STOPPED: cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); break; case EVENT_PORT_AUTHORIZED: __cfg80211_port_authorized(wdev, ev->pa.peer_addr, ev->pa.td_bitmap, ev->pa.td_bitmap_len); break; } kfree(ev); spin_lock_irqsave(&wdev->event_lock, flags); } spin_unlock_irqrestore(&wdev->event_lock, flags); } void cfg80211_process_rdev_events(struct cfg80211_registered_device *rdev) { struct wireless_dev *wdev; lockdep_assert_held(&rdev->wiphy.mtx); list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) cfg80211_process_wdev_events(wdev); } int cfg80211_change_iface(struct cfg80211_registered_device *rdev, struct net_device *dev, enum nl80211_iftype ntype, struct vif_params *params) { int err; enum nl80211_iftype otype = dev->ieee80211_ptr->iftype; lockdep_assert_held(&rdev->wiphy.mtx); /* don't support changing VLANs, you just re-create them */ if (otype == NL80211_IFTYPE_AP_VLAN) return -EOPNOTSUPP; /* cannot change into P2P device or NAN */ if (ntype == NL80211_IFTYPE_P2P_DEVICE || ntype == NL80211_IFTYPE_NAN) return -EOPNOTSUPP; if (!rdev->ops->change_virtual_intf || !(rdev->wiphy.interface_modes & (1 << ntype))) return -EOPNOTSUPP; if (ntype != otype) { /* if it's part of a bridge, reject changing type to station/ibss */ if (netif_is_bridge_port(dev) && (ntype == NL80211_IFTYPE_ADHOC || ntype == NL80211_IFTYPE_STATION || ntype == NL80211_IFTYPE_P2P_CLIENT)) return -EBUSY; dev->ieee80211_ptr->use_4addr = false; rdev_set_qos_map(rdev, dev, NULL); switch (otype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, dev, -1, true); break; case NL80211_IFTYPE_ADHOC: cfg80211_leave_ibss(rdev, dev, false); break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: cfg80211_disconnect(rdev, dev, WLAN_REASON_DEAUTH_LEAVING, true); break; case NL80211_IFTYPE_MESH_POINT: /* mesh should be handled? */ break; case NL80211_IFTYPE_OCB: cfg80211_leave_ocb(rdev, dev); break; default: break; } cfg80211_process_rdev_events(rdev); cfg80211_mlme_purge_registrations(dev->ieee80211_ptr); memset(&dev->ieee80211_ptr->u, 0, sizeof(dev->ieee80211_ptr->u)); memset(&dev->ieee80211_ptr->links, 0, sizeof(dev->ieee80211_ptr->links)); } err = rdev_change_virtual_intf(rdev, dev, ntype, params); WARN_ON(!err && dev->ieee80211_ptr->iftype != ntype); if (!err && params && params->use_4addr != -1) dev->ieee80211_ptr->use_4addr = params->use_4addr; if (!err) { dev->priv_flags &= ~IFF_DONT_BRIDGE; switch (ntype) { case NL80211_IFTYPE_STATION: if (dev->ieee80211_ptr->use_4addr) break; fallthrough; case NL80211_IFTYPE_OCB: case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_ADHOC: dev->priv_flags |= IFF_DONT_BRIDGE; break; case NL80211_IFTYPE_P2P_GO: case NL80211_IFTYPE_AP: case NL80211_IFTYPE_AP_VLAN: case NL80211_IFTYPE_MESH_POINT: /* bridging OK */ break; case NL80211_IFTYPE_MONITOR: /* monitor can't bridge anyway */ break; case NL80211_IFTYPE_UNSPECIFIED: case NUM_NL80211_IFTYPES: /* not happening */ break; case NL80211_IFTYPE_P2P_DEVICE: case NL80211_IFTYPE_WDS: case NL80211_IFTYPE_NAN: WARN_ON(1); break; } } if (!err && ntype != otype && netif_running(dev)) { cfg80211_update_iface_num(rdev, ntype, 1); cfg80211_update_iface_num(rdev, otype, -1); } return err; } static u32 cfg80211_calculate_bitrate_ht(struct rate_info *rate) { int modulation, streams, bitrate; /* the formula below does only work for MCS values smaller than 32 */ if (WARN_ON_ONCE(rate->mcs >= 32)) return 0; modulation = rate->mcs & 7; streams = (rate->mcs >> 3) + 1; bitrate = (rate->bw == RATE_INFO_BW_40) ? 13500000 : 6500000; if (modulation < 4) bitrate *= (modulation + 1); else if (modulation == 4) bitrate *= (modulation + 2); else bitrate *= (modulation + 3); bitrate *= streams; if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) bitrate = (bitrate / 9) * 10; /* do NOT round down here */ return (bitrate + 50000) / 100000; } static u32 cfg80211_calculate_bitrate_dmg(struct rate_info *rate) { static const u32 __mcs2bitrate[] = { /* control PHY */ [0] = 275, /* SC PHY */ [1] = 3850, [2] = 7700, [3] = 9625, [4] = 11550, [5] = 12512, /* 1251.25 mbps */ [6] = 15400, [7] = 19250, [8] = 23100, [9] = 25025, [10] = 30800, [11] = 38500, [12] = 46200, /* OFDM PHY */ [13] = 6930, [14] = 8662, /* 866.25 mbps */ [15] = 13860, [16] = 17325, [17] = 20790, [18] = 27720, [19] = 34650, [20] = 41580, [21] = 45045, [22] = 51975, [23] = 62370, [24] = 67568, /* 6756.75 mbps */ /* LP-SC PHY */ [25] = 6260, [26] = 8340, [27] = 11120, [28] = 12510, [29] = 16680, [30] = 22240, [31] = 25030, }; if (WARN_ON_ONCE(rate->mcs >= ARRAY_SIZE(__mcs2bitrate))) return 0; return __mcs2bitrate[rate->mcs]; } static u32 cfg80211_calculate_bitrate_extended_sc_dmg(struct rate_info *rate) { static const u32 __mcs2bitrate[] = { [6 - 6] = 26950, /* MCS 9.1 : 2695.0 mbps */ [7 - 6] = 50050, /* MCS 12.1 */ [8 - 6] = 53900, [9 - 6] = 57750, [10 - 6] = 63900, [11 - 6] = 75075, [12 - 6] = 80850, }; /* Extended SC MCS not defined for base MCS below 6 or above 12 */ if (WARN_ON_ONCE(rate->mcs < 6 || rate->mcs > 12)) return 0; return __mcs2bitrate[rate->mcs - 6]; } static u32 cfg80211_calculate_bitrate_edmg(struct rate_info *rate) { static const u32 __mcs2bitrate[] = { /* control PHY */ [0] = 275, /* SC PHY */ [1] = 3850, [2] = 7700, [3] = 9625, [4] = 11550, [5] = 12512, /* 1251.25 mbps */ [6] = 13475, [7] = 15400, [8] = 19250, [9] = 23100, [10] = 25025, [11] = 26950, [12] = 30800, [13] = 38500, [14] = 46200, [15] = 50050, [16] = 53900, [17] = 57750, [18] = 69300, [19] = 75075, [20] = 80850, }; if (WARN_ON_ONCE(rate->mcs >= ARRAY_SIZE(__mcs2bitrate))) return 0; return __mcs2bitrate[rate->mcs] * rate->n_bonded_ch; } static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate) { static const u32 base[4][12] = { { 6500000, 13000000, 19500000, 26000000, 39000000, 52000000, 58500000, 65000000, 78000000, /* not in the spec, but some devices use this: */ 86700000, 97500000, 108300000, }, { 13500000, 27000000, 40500000, 54000000, 81000000, 108000000, 121500000, 135000000, 162000000, 180000000, 202500000, 225000000, }, { 29300000, 58500000, 87800000, 117000000, 175500000, 234000000, 263300000, 292500000, 351000000, 390000000, 438800000, 487500000, }, { 58500000, 117000000, 175500000, 234000000, 351000000, 468000000, 526500000, 585000000, 702000000, 780000000, 877500000, 975000000, }, }; u32 bitrate; int idx; if (rate->mcs > 11) goto warn; switch (rate->bw) { case RATE_INFO_BW_160: idx = 3; break; case RATE_INFO_BW_80: idx = 2; break; case RATE_INFO_BW_40: idx = 1; break; case RATE_INFO_BW_5: case RATE_INFO_BW_10: default: goto warn; case RATE_INFO_BW_20: idx = 0; } bitrate = base[idx][rate->mcs]; bitrate *= rate->nss; if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) bitrate = (bitrate / 9) * 10; /* do NOT round down here */ return (bitrate + 50000) / 100000; warn: WARN_ONCE(1, "invalid rate bw=%d, mcs=%d, nss=%d\n", rate->bw, rate->mcs, rate->nss); return 0; } static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate) { #define SCALE 6144 u32 mcs_divisors[14] = { 102399, /* 16.666666... */ 51201, /* 8.333333... */ 34134, /* 5.555555... */ 25599, /* 4.166666... */ 17067, /* 2.777777... */ 12801, /* 2.083333... */ 11377, /* 1.851725... */ 10239, /* 1.666666... */ 8532, /* 1.388888... */ 7680, /* 1.250000... */ 6828, /* 1.111111... */ 6144, /* 1.000000... */ 5690, /* 0.926106... */ 5120, /* 0.833333... */ }; u32 rates_160M[3] = { 960777777, 907400000, 816666666 }; u32 rates_996[3] = { 480388888, 453700000, 408333333 }; u32 rates_484[3] = { 229411111, 216666666, 195000000 }; u32 rates_242[3] = { 114711111, 108333333, 97500000 }; u32 rates_106[3] = { 40000000, 37777777, 34000000 }; u32 rates_52[3] = { 18820000, 17777777, 16000000 }; u32 rates_26[3] = { 9411111, 8888888, 8000000 }; u64 tmp; u32 result; if (WARN_ON_ONCE(rate->mcs > 13)) return 0; if (WARN_ON_ONCE(rate->he_gi > NL80211_RATE_INFO_HE_GI_3_2)) return 0; if (WARN_ON_ONCE(rate->he_ru_alloc > NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) return 0; if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; if (rate->bw == RATE_INFO_BW_160 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_2x996)) result = rates_160M[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996)) result = rates_996[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_40 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484)) result = rates_484[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_20 || (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_242)) result = rates_242[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_106) result = rates_106[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_52) result = rates_52[rate->he_gi]; else if (rate->bw == RATE_INFO_BW_HE_RU && rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26) result = rates_26[rate->he_gi]; else { WARN(1, "invalid HE MCS: bw:%d, ru:%d\n", rate->bw, rate->he_ru_alloc); return 0; } /* now scale to the appropriate MCS */ tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); result = tmp; /* and take NSS, DCM into account */ result = (result * rate->nss) / 8; if (rate->he_dcm) result /= 2; return result / 10000; } static u32 cfg80211_calculate_bitrate_eht(struct rate_info *rate) { #define SCALE 6144 static const u32 mcs_divisors[16] = { 102399, /* 16.666666... */ 51201, /* 8.333333... */ 34134, /* 5.555555... */ 25599, /* 4.166666... */ 17067, /* 2.777777... */ 12801, /* 2.083333... */ 11377, /* 1.851725... */ 10239, /* 1.666666... */ 8532, /* 1.388888... */ 7680, /* 1.250000... */ 6828, /* 1.111111... */ 6144, /* 1.000000... */ 5690, /* 0.926106... */ 5120, /* 0.833333... */ 409600, /* 66.666666... */ 204800, /* 33.333333... */ }; static const u32 rates_996[3] = { 480388888, 453700000, 408333333 }; static const u32 rates_484[3] = { 229411111, 216666666, 195000000 }; static const u32 rates_242[3] = { 114711111, 108333333, 97500000 }; static const u32 rates_106[3] = { 40000000, 37777777, 34000000 }; static const u32 rates_52[3] = { 18820000, 17777777, 16000000 }; static const u32 rates_26[3] = { 9411111, 8888888, 8000000 }; u64 tmp; u32 result; if (WARN_ON_ONCE(rate->mcs > 15)) return 0; if (WARN_ON_ONCE(rate->eht_gi > NL80211_RATE_INFO_EHT_GI_3_2)) return 0; if (WARN_ON_ONCE(rate->eht_ru_alloc > NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) return 0; if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8)) return 0; /* Bandwidth checks for MCS 14 */ if (rate->mcs == 14) { if ((rate->bw != RATE_INFO_BW_EHT_RU && rate->bw != RATE_INFO_BW_80 && rate->bw != RATE_INFO_BW_160 && rate->bw != RATE_INFO_BW_320) || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_996 && rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_2x996 && rate->eht_ru_alloc != NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) { WARN(1, "invalid EHT BW for MCS 14: bw:%d, ru:%d\n", rate->bw, rate->eht_ru_alloc); return 0; } } if (rate->bw == RATE_INFO_BW_320 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_4x996)) result = 4 * rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_3x996P484) result = 3 * rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_3x996) result = 3 * rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_2x996P484) result = 2 * rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_160 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_2x996)) result = 2 * rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996P484P242) result = rates_996[rate->eht_gi] + rates_484[rate->eht_gi] + rates_242[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996P484) result = rates_996[rate->eht_gi] + rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_80 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_996)) result = rates_996[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_484P242) result = rates_484[rate->eht_gi] + rates_242[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_40 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_484)) result = rates_484[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_20 || (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_242)) result = rates_242[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_106P26) result = rates_106[rate->eht_gi] + rates_26[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_106) result = rates_106[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_52P26) result = rates_52[rate->eht_gi] + rates_26[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_52) result = rates_52[rate->eht_gi]; else if (rate->bw == RATE_INFO_BW_EHT_RU && rate->eht_ru_alloc == NL80211_RATE_INFO_EHT_RU_ALLOC_26) result = rates_26[rate->eht_gi]; else { WARN(1, "invalid EHT MCS: bw:%d, ru:%d\n", rate->bw, rate->eht_ru_alloc); return 0; } /* now scale to the appropriate MCS */ tmp = result; tmp *= SCALE; do_div(tmp, mcs_divisors[rate->mcs]); /* and take NSS */ tmp *= rate->nss; do_div(tmp, 8); result = tmp; return result / 10000; } static u32 cfg80211_calculate_bitrate_s1g(struct rate_info *rate) { /* For 1, 2, 4, 8 and 16 MHz channels */ static const u32 base[5][11] = { { 300000, 600000, 900000, 1200000, 1800000, 2400000, 2700000, 3000000, 3600000, 4000000, /* MCS 10 supported in 1 MHz only */ 150000, }, { 650000, 1300000, 1950000, 2600000, 3900000, 5200000, 5850000, 6500000, 7800000, /* MCS 9 not valid */ }, { 1350000, 2700000, 4050000, 5400000, 8100000, 10800000, 12150000, 13500000, 16200000, 18000000, }, { 2925000, 5850000, 8775000, 11700000, 17550000, 23400000, 26325000, 29250000, 35100000, 39000000, }, { 8580000, 11700000, 17550000, 23400000, 35100000, 46800000, 52650000, 58500000, 70200000, 78000000, }, }; u32 bitrate; /* default is 1 MHz index */ int idx = 0; if (rate->mcs >= 11) goto warn; switch (rate->bw) { case RATE_INFO_BW_16: idx = 4; break; case RATE_INFO_BW_8: idx = 3; break; case RATE_INFO_BW_4: idx = 2; break; case RATE_INFO_BW_2: idx = 1; break; case RATE_INFO_BW_1: idx = 0; break; case RATE_INFO_BW_5: case RATE_INFO_BW_10: case RATE_INFO_BW_20: case RATE_INFO_BW_40: case RATE_INFO_BW_80: case RATE_INFO_BW_160: default: goto warn; } bitrate = base[idx][rate->mcs]; bitrate *= rate->nss; if (rate->flags & RATE_INFO_FLAGS_SHORT_GI) bitrate = (bitrate / 9) * 10; /* do NOT round down here */ return (bitrate + 50000) / 100000; warn: WARN_ONCE(1, "invalid rate bw=%d, mcs=%d, nss=%d\n", rate->bw, rate->mcs, rate->nss); return 0; } u32 cfg80211_calculate_bitrate(struct rate_info *rate) { if (rate->flags & RATE_INFO_FLAGS_MCS) return cfg80211_calculate_bitrate_ht(rate); if (rate->flags & RATE_INFO_FLAGS_DMG) return cfg80211_calculate_bitrate_dmg(rate); if (rate->flags & RATE_INFO_FLAGS_EXTENDED_SC_DMG) return cfg80211_calculate_bitrate_extended_sc_dmg(rate); if (rate->flags & RATE_INFO_FLAGS_EDMG) return cfg80211_calculate_bitrate_edmg(rate); if (rate->flags & RATE_INFO_FLAGS_VHT_MCS) return cfg80211_calculate_bitrate_vht(rate); if (rate->flags & RATE_INFO_FLAGS_HE_MCS) return cfg80211_calculate_bitrate_he(rate); if (rate->flags & RATE_INFO_FLAGS_EHT_MCS) return cfg80211_calculate_bitrate_eht(rate); if (rate->flags & RATE_INFO_FLAGS_S1G_MCS) return cfg80211_calculate_bitrate_s1g(rate); return rate->legacy; } EXPORT_SYMBOL(cfg80211_calculate_bitrate); int cfg80211_get_p2p_attr(const u8 *ies, unsigned int len, enum ieee80211_p2p_attr_id attr, u8 *buf, unsigned int bufsize) { u8 *out = buf; u16 attr_remaining = 0; bool desired_attr = false; u16 desired_len = 0; while (len > 0) { unsigned int iedatalen; unsigned int copy; const u8 *iedata; if (len < 2) return -EILSEQ; iedatalen = ies[1]; if (iedatalen + 2 > len) return -EILSEQ; if (ies[0] != WLAN_EID_VENDOR_SPECIFIC) goto cont; if (iedatalen < 4) goto cont; iedata = ies + 2; /* check WFA OUI, P2P subtype */ if (iedata[0] != 0x50 || iedata[1] != 0x6f || iedata[2] != 0x9a || iedata[3] != 0x09) goto cont; iedatalen -= 4; iedata += 4; /* check attribute continuation into this IE */ copy = min_t(unsigned int, attr_remaining, iedatalen); if (copy && desired_attr) { desired_len += copy; if (out) { memcpy(out, iedata, min(bufsize, copy)); out += min(bufsize, copy); bufsize -= min(bufsize, copy); } if (copy == attr_remaining) return desired_len; } attr_remaining -= copy; if (attr_remaining) goto cont; iedatalen -= copy; iedata += copy; while (iedatalen > 0) { u16 attr_len; /* P2P attribute ID & size must fit */ if (iedatalen < 3) return -EILSEQ; desired_attr = iedata[0] == attr; attr_len = get_unaligned_le16(iedata + 1); iedatalen -= 3; iedata += 3; copy = min_t(unsigned int, attr_len, iedatalen); if (desired_attr) { desired_len += copy; if (out) { memcpy(out, iedata, min(bufsize, copy)); out += min(bufsize, copy); bufsize -= min(bufsize, copy); } if (copy == attr_len) return desired_len; } iedata += copy; iedatalen -= copy; attr_remaining = attr_len - copy; } cont: len -= ies[1] + 2; ies += ies[1] + 2; } if (attr_remaining && desired_attr) return -EILSEQ; return -ENOENT; } EXPORT_SYMBOL(cfg80211_get_p2p_attr); static bool ieee80211_id_in_list(const u8 *ids, int n_ids, u8 id, bool id_ext) { int i; /* Make sure array values are legal */ if (WARN_ON(ids[n_ids - 1] == WLAN_EID_EXTENSION)) return false; i = 0; while (i < n_ids) { if (ids[i] == WLAN_EID_EXTENSION) { if (id_ext && (ids[i + 1] == id)) return true; i += 2; continue; } if (ids[i] == id && !id_ext) return true; i++; } return false; } static size_t skip_ie(const u8 *ies, size_t ielen, size_t pos) { /* we assume a validly formed IEs buffer */ u8 len = ies[pos + 1]; pos += 2 + len; /* the IE itself must have 255 bytes for fragments to follow */ if (len < 255) return pos; while (pos < ielen && ies[pos] == WLAN_EID_FRAGMENT) { len = ies[pos + 1]; pos += 2 + len; } return pos; } 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) { size_t pos = offset; while (pos < ielen) { u8 ext = 0; if (ies[pos] == WLAN_EID_EXTENSION) ext = 2; if ((pos + ext) >= ielen) break; if (!ieee80211_id_in_list(ids, n_ids, ies[pos + ext], ies[pos] == WLAN_EID_EXTENSION)) break; if (ies[pos] == WLAN_EID_RIC_DATA && n_after_ric) { pos = skip_ie(ies, ielen, pos); while (pos < ielen) { if (ies[pos] == WLAN_EID_EXTENSION) ext = 2; else ext = 0; if ((pos + ext) >= ielen) break; if (!ieee80211_id_in_list(after_ric, n_after_ric, ies[pos + ext], ext == 2)) pos = skip_ie(ies, ielen, pos); else break; } } else { pos = skip_ie(ies, ielen, pos); } } return pos; } EXPORT_SYMBOL(ieee80211_ie_split_ric); void ieee80211_fragment_element(struct sk_buff *skb, u8 *len_pos, u8 frag_id) { unsigned int elem_len; if (!len_pos) return; elem_len = skb->data + skb->len - len_pos - 1; while (elem_len > 255) { /* this one is 255 */ *len_pos = 255; /* remaining data gets smaller */ elem_len -= 255; /* make space for the fragment ID/len in SKB */ skb_put(skb, 2); /* shift back the remaining data to place fragment ID/len */ memmove(len_pos + 255 + 3, len_pos + 255 + 1, elem_len); /* place the fragment ID */ len_pos += 255 + 1; *len_pos = frag_id; /* and point to fragment length to update later */ len_pos++; } *len_pos = elem_len; } EXPORT_SYMBOL(ieee80211_fragment_element); bool ieee80211_operating_class_to_band(u8 operating_class, enum nl80211_band *band) { switch (operating_class) { case 112: case 115 ... 127: case 128 ... 130: *band = NL80211_BAND_5GHZ; return true; case 131 ... 135: case 137: *band = NL80211_BAND_6GHZ; return true; case 81: case 82: case 83: case 84: *band = NL80211_BAND_2GHZ; return true; case 180: *band = NL80211_BAND_60GHZ; return true; } return false; } EXPORT_SYMBOL(ieee80211_operating_class_to_band); bool ieee80211_operating_class_to_chandef(u8 operating_class, struct ieee80211_channel *chan, struct cfg80211_chan_def *chandef) { u32 control_freq, offset = 0; enum nl80211_band band; if (!ieee80211_operating_class_to_band(operating_class, &band) || !chan || band != chan->band) return false; control_freq = chan->center_freq; chandef->chan = chan; if (control_freq >= 5955) offset = control_freq - 5955; else if (control_freq >= 5745) offset = control_freq - 5745; else if (control_freq >= 5180) offset = control_freq - 5180; offset /= 20; switch (operating_class) { case 81: /* 2 GHz band; 20 MHz; channels 1..13 */ case 82: /* 2 GHz band; 20 MHz; channel 14 */ case 115: /* 5 GHz band; 20 MHz; channels 36,40,44,48 */ case 118: /* 5 GHz band; 20 MHz; channels 52,56,60,64 */ case 121: /* 5 GHz band; 20 MHz; channels 100..144 */ case 124: /* 5 GHz band; 20 MHz; channels 149,153,157,161 */ case 125: /* 5 GHz band; 20 MHz; channels 149..177 */ case 131: /* 6 GHz band; 20 MHz; channels 1..233*/ case 136: /* 6 GHz band; 20 MHz; channel 2 */ chandef->center_freq1 = control_freq; chandef->width = NL80211_CHAN_WIDTH_20; return true; case 83: /* 2 GHz band; 40 MHz; channels 1..9 */ case 116: /* 5 GHz band; 40 MHz; channels 36,44 */ case 119: /* 5 GHz band; 40 MHz; channels 52,60 */ case 122: /* 5 GHz band; 40 MHz; channels 100,108,116,124,132,140 */ case 126: /* 5 GHz band; 40 MHz; channels 149,157,165,173 */ chandef->center_freq1 = control_freq + 10; chandef->width = NL80211_CHAN_WIDTH_40; return true; case 84: /* 2 GHz band; 40 MHz; channels 5..13 */ case 117: /* 5 GHz band; 40 MHz; channels 40,48 */ case 120: /* 5 GHz band; 40 MHz; channels 56,64 */ case 123: /* 5 GHz band; 40 MHz; channels 104,112,120,128,136,144 */ case 127: /* 5 GHz band; 40 MHz; channels 153,161,169,177 */ chandef->center_freq1 = control_freq - 10; chandef->width = NL80211_CHAN_WIDTH_40; return true; case 132: /* 6 GHz band; 40 MHz; channels 1,5,..,229*/ chandef->center_freq1 = control_freq + 10 - (offset & 1) * 20; chandef->width = NL80211_CHAN_WIDTH_40; return true; case 128: /* 5 GHz band; 80 MHz; channels 36..64,100..144,149..177 */ case 133: /* 6 GHz band; 80 MHz; channels 1,5,..,229 */ chandef->center_freq1 = control_freq + 30 - (offset & 3) * 20; chandef->width = NL80211_CHAN_WIDTH_80; return true; case 129: /* 5 GHz band; 160 MHz; channels 36..64,100..144,149..177 */ case 134: /* 6 GHz band; 160 MHz; channels 1,5,..,229 */ chandef->center_freq1 = control_freq + 70 - (offset & 7) * 20; chandef->width = NL80211_CHAN_WIDTH_160; return true; case 130: /* 5 GHz band; 80+80 MHz; channels 36..64,100..144,149..177 */ case 135: /* 6 GHz band; 80+80 MHz; channels 1,5,..,229 */ /* The center_freq2 of 80+80 MHz is unknown */ case 137: /* 6 GHz band; 320 MHz; channels 1,5,..,229 */ /* 320-1 or 320-2 channelization is unknown */ default: return false; } } EXPORT_SYMBOL(ieee80211_operating_class_to_chandef); bool ieee80211_chandef_to_operating_class(struct cfg80211_chan_def *chandef, u8 *op_class) { u8 vht_opclass; u32 freq = chandef->center_freq1; if (freq >= 2412 && freq <= 2472) { if (chandef->width > NL80211_CHAN_WIDTH_40) return false; /* 2.407 GHz, channels 1..13 */ if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 83; /* HT40+ */ else *op_class = 84; /* HT40- */ } else { *op_class = 81; } return true; } if (freq == 2484) { /* channel 14 is only for IEEE 802.11b */ if (chandef->width != NL80211_CHAN_WIDTH_20_NOHT) return false; *op_class = 82; /* channel 14 */ return true; } switch (chandef->width) { case NL80211_CHAN_WIDTH_80: vht_opclass = 128; break; case NL80211_CHAN_WIDTH_160: vht_opclass = 129; break; case NL80211_CHAN_WIDTH_80P80: vht_opclass = 130; break; case NL80211_CHAN_WIDTH_10: case NL80211_CHAN_WIDTH_5: return false; /* unsupported for now */ default: vht_opclass = 0; break; } /* 5 GHz, channels 36..48 */ if (freq >= 5180 && freq <= 5240) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 116; else *op_class = 117; } else { *op_class = 115; } return true; } /* 5 GHz, channels 52..64 */ if (freq >= 5260 && freq <= 5320) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 119; else *op_class = 120; } else { *op_class = 118; } return true; } /* 5 GHz, channels 100..144 */ if (freq >= 5500 && freq <= 5720) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 122; else *op_class = 123; } else { *op_class = 121; } return true; } /* 5 GHz, channels 149..169 */ if (freq >= 5745 && freq <= 5845) { if (vht_opclass) { *op_class = vht_opclass; } else if (chandef->width == NL80211_CHAN_WIDTH_40) { if (freq > chandef->chan->center_freq) *op_class = 126; else *op_class = 127; } else if (freq <= 5805) { *op_class = 124; } else { *op_class = 125; } return true; } /* 56.16 GHz, channel 1..4 */ if (freq >= 56160 + 2160 * 1 && freq <= 56160 + 2160 * 6) { if (chandef->width >= NL80211_CHAN_WIDTH_40) return false; *op_class = 180; return true; } /* not supported yet */ return false; } EXPORT_SYMBOL(ieee80211_chandef_to_operating_class); static int cfg80211_wdev_bi(struct wireless_dev *wdev) { switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: WARN_ON(wdev->valid_links); return wdev->links[0].ap.beacon_interval; case NL80211_IFTYPE_MESH_POINT: return wdev->u.mesh.beacon_interval; case NL80211_IFTYPE_ADHOC: return wdev->u.ibss.beacon_interval; default: break; } return 0; } static void cfg80211_calculate_bi_data(struct wiphy *wiphy, u32 new_beacon_int, u32 *beacon_int_gcd, bool *beacon_int_different, int radio_idx) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; *beacon_int_gcd = 0; *beacon_int_different = false; rdev = wiphy_to_rdev(wiphy); list_for_each_entry(wdev, &wiphy->wdev_list, list) { int wdev_bi; /* this feature isn't supported with MLO */ if (wdev->valid_links) continue; /* skip wdevs not active on the given wiphy radio */ if (radio_idx >= 0 && !(rdev_get_radio_mask(rdev, wdev->netdev) & BIT(radio_idx))) continue; wdev_bi = cfg80211_wdev_bi(wdev); if (!wdev_bi) continue; if (!*beacon_int_gcd) { *beacon_int_gcd = wdev_bi; continue; } if (wdev_bi == *beacon_int_gcd) continue; *beacon_int_different = true; *beacon_int_gcd = gcd(*beacon_int_gcd, wdev_bi); } if (new_beacon_int && *beacon_int_gcd != new_beacon_int) { if (*beacon_int_gcd) *beacon_int_different = true; *beacon_int_gcd = gcd(*beacon_int_gcd, new_beacon_int); } } int cfg80211_validate_beacon_int(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype, u32 beacon_int) { /* * This is just a basic pre-condition check; if interface combinations * are possible the driver must already be checking those with a call * to cfg80211_check_combinations(), in which case we'll validate more * through the cfg80211_calculate_bi_data() call and code in * cfg80211_iter_combinations(). */ if (beacon_int < 10 || beacon_int > 10000) return -EINVAL; return 0; } int cfg80211_iter_combinations(struct wiphy *wiphy, struct iface_combination_params *params, void (*iter)(const struct ieee80211_iface_combination *c, void *data), void *data) { const struct wiphy_radio *radio = NULL; const struct ieee80211_iface_combination *c, *cs; const struct ieee80211_regdomain *regdom; enum nl80211_dfs_regions region = 0; int i, j, n, iftype; int num_interfaces = 0; u32 used_iftypes = 0; u32 beacon_int_gcd; bool beacon_int_different; if (params->radio_idx >= 0) radio = &wiphy->radio[params->radio_idx]; /* * This is a bit strange, since the iteration used to rely only on * the data given by the driver, but here it now relies on context, * in form of the currently operating interfaces. * This is OK for all current users, and saves us from having to * push the GCD calculations into all the drivers. * In the future, this should probably rely more on data that's in * cfg80211 already - the only thing not would appear to be any new * interfaces (while being brought up) and channel/radar data. */ cfg80211_calculate_bi_data(wiphy, params->new_beacon_int, &beacon_int_gcd, &beacon_int_different, params->radio_idx); if (params->radar_detect) { rcu_read_lock(); regdom = rcu_dereference(cfg80211_regdomain); if (regdom) region = regdom->dfs_region; rcu_read_unlock(); } for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { num_interfaces += params->iftype_num[iftype]; if (params->iftype_num[iftype] > 0 && !cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) used_iftypes |= BIT(iftype); } if (radio) { cs = radio->iface_combinations; n = radio->n_iface_combinations; } else { cs = wiphy->iface_combinations; n = wiphy->n_iface_combinations; } for (i = 0; i < n; i++) { struct ieee80211_iface_limit *limits; u32 all_iftypes = 0; c = &cs[i]; if (num_interfaces > c->max_interfaces) continue; if (params->num_different_channels > c->num_different_channels) continue; limits = kmemdup_array(c->limits, c->n_limits, sizeof(*limits), GFP_KERNEL); if (!limits) return -ENOMEM; for (iftype = 0; iftype < NUM_NL80211_IFTYPES; iftype++) { if (cfg80211_iftype_allowed(wiphy, iftype, 0, 1)) continue; for (j = 0; j < c->n_limits; j++) { all_iftypes |= limits[j].types; if (!(limits[j].types & BIT(iftype))) continue; if (limits[j].max < params->iftype_num[iftype]) goto cont; limits[j].max -= params->iftype_num[iftype]; } } if (params->radar_detect != (c->radar_detect_widths & params->radar_detect)) goto cont; if (params->radar_detect && c->radar_detect_regions && !(c->radar_detect_regions & BIT(region))) goto cont; /* Finally check that all iftypes that we're currently * using are actually part of this combination. If they * aren't then we can't use this combination and have * to continue to the next. */ if ((all_iftypes & used_iftypes) != used_iftypes) goto cont; if (beacon_int_gcd) { if (c->beacon_int_min_gcd && beacon_int_gcd < c->beacon_int_min_gcd) goto cont; if (!c->beacon_int_min_gcd && beacon_int_different) goto cont; } /* This combination covered all interface types and * supported the requested numbers, so we're good. */ (*iter)(c, data); cont: kfree(limits); } return 0; } EXPORT_SYMBOL(cfg80211_iter_combinations); static void cfg80211_iter_sum_ifcombs(const struct ieee80211_iface_combination *c, void *data) { int *num = data; (*num)++; } int cfg80211_check_combinations(struct wiphy *wiphy, struct iface_combination_params *params) { int err, num = 0; err = cfg80211_iter_combinations(wiphy, params, cfg80211_iter_sum_ifcombs, &num); if (err) return err; if (num == 0) return -EBUSY; return 0; } EXPORT_SYMBOL(cfg80211_check_combinations); int cfg80211_get_radio_idx_by_chan(struct wiphy *wiphy, const struct ieee80211_channel *chan) { const struct wiphy_radio *radio; int i, j; u32 freq; if (!chan) return -EINVAL; freq = ieee80211_channel_to_khz(chan); for (i = 0; i < wiphy->n_radio; i++) { radio = &wiphy->radio[i]; for (j = 0; j < radio->n_freq_range; j++) { if (freq >= radio->freq_range[j].start_freq && freq < radio->freq_range[j].end_freq) return i; } } return -ENOENT; } EXPORT_SYMBOL(cfg80211_get_radio_idx_by_chan); int ieee80211_get_ratemask(struct ieee80211_supported_band *sband, const u8 *rates, unsigned int n_rates, u32 *mask) { int i, j; if (!sband) return -EINVAL; if (n_rates == 0 || n_rates > NL80211_MAX_SUPP_RATES) return -EINVAL; *mask = 0; for (i = 0; i < n_rates; i++) { int rate = (rates[i] & 0x7f) * 5; bool found = false; for (j = 0; j < sband->n_bitrates; j++) { if (sband->bitrates[j].bitrate == rate) { found = true; *mask |= BIT(j); break; } } if (!found) return -EINVAL; } /* * mask must have at least one bit set here since we * didn't accept a 0-length rates array nor allowed * entries in the array that didn't exist */ return 0; } unsigned int ieee80211_get_num_supported_channels(struct wiphy *wiphy) { enum nl80211_band band; unsigned int n_channels = 0; for (band = 0; band < NUM_NL80211_BANDS; band++) if (wiphy->bands[band]) n_channels += wiphy->bands[band]->n_channels; return n_channels; } EXPORT_SYMBOL(ieee80211_get_num_supported_channels); int cfg80211_get_station(struct net_device *dev, const u8 *mac_addr, struct station_info *sinfo) { struct cfg80211_registered_device *rdev; struct wireless_dev *wdev; wdev = dev->ieee80211_ptr; if (!wdev) return -EOPNOTSUPP; rdev = wiphy_to_rdev(wdev->wiphy); if (!rdev->ops->get_station) return -EOPNOTSUPP; memset(sinfo, 0, sizeof(*sinfo)); guard(wiphy)(&rdev->wiphy); return rdev_get_station(rdev, dev, mac_addr, sinfo); } EXPORT_SYMBOL(cfg80211_get_station); void cfg80211_free_nan_func(struct cfg80211_nan_func *f) { int i; if (!f) return; kfree(f->serv_spec_info); kfree(f->srf_bf); kfree(f->srf_macs); for (i = 0; i < f->num_rx_filters; i++) kfree(f->rx_filters[i].filter); for (i = 0; i < f->num_tx_filters; i++) kfree(f->tx_filters[i].filter); kfree(f->rx_filters); kfree(f->tx_filters); kfree(f); } EXPORT_SYMBOL(cfg80211_free_nan_func); bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range, u32 center_freq_khz, u32 bw_khz) { u32 start_freq_khz, end_freq_khz; start_freq_khz = center_freq_khz - (bw_khz / 2); end_freq_khz = center_freq_khz + (bw_khz / 2); if (start_freq_khz >= freq_range->start_freq_khz && end_freq_khz <= freq_range->end_freq_khz) return true; return false; } int cfg80211_link_sinfo_alloc_tid_stats(struct link_station_info *link_sinfo, gfp_t gfp) { link_sinfo->pertid = kcalloc(IEEE80211_NUM_TIDS + 1, sizeof(*link_sinfo->pertid), gfp); if (!link_sinfo->pertid) return -ENOMEM; return 0; } EXPORT_SYMBOL(cfg80211_link_sinfo_alloc_tid_stats); int cfg80211_sinfo_alloc_tid_stats(struct station_info *sinfo, gfp_t gfp) { sinfo->pertid = kcalloc(IEEE80211_NUM_TIDS + 1, sizeof(*(sinfo->pertid)), gfp); if (!sinfo->pertid) return -ENOMEM; return 0; } EXPORT_SYMBOL(cfg80211_sinfo_alloc_tid_stats); /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ /* Ethernet-II snap header (RFC1042 for most EtherTypes) */ const unsigned char rfc1042_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 }; EXPORT_SYMBOL(rfc1042_header); /* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */ const unsigned char bridge_tunnel_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 }; EXPORT_SYMBOL(bridge_tunnel_header); /* Layer 2 Update frame (802.2 Type 1 LLC XID Update response) */ struct iapp_layer2_update { u8 da[ETH_ALEN]; /* broadcast */ u8 sa[ETH_ALEN]; /* STA addr */ __be16 len; /* 6 */ u8 dsap; /* 0 */ u8 ssap; /* 0 */ u8 control; u8 xid_info[3]; } __packed; void cfg80211_send_layer2_update(struct net_device *dev, const u8 *addr) { struct iapp_layer2_update *msg; struct sk_buff *skb; /* Send Level 2 Update Frame to update forwarding tables in layer 2 * bridge devices */ skb = dev_alloc_skb(sizeof(*msg)); if (!skb) return; msg = skb_put(skb, sizeof(*msg)); /* 802.2 Type 1 Logical Link Control (LLC) Exchange Identifier (XID) * Update response frame; IEEE Std 802.2-1998, 5.4.1.2.1 */ eth_broadcast_addr(msg->da); ether_addr_copy(msg->sa, addr); msg->len = htons(6); msg->dsap = 0; msg->ssap = 0x01; /* NULL LSAP, CR Bit: Response */ msg->control = 0xaf; /* XID response lsb.1111F101. * F=0 (no poll command; unsolicited frame) */ msg->xid_info[0] = 0x81; /* XID format identifier */ msg->xid_info[1] = 1; /* LLC types/classes: Type 1 LLC */ msg->xid_info[2] = 0; /* XID sender's receive window size (RW) */ skb->dev = dev; skb->protocol = eth_type_trans(skb, dev); memset(skb->cb, 0, sizeof(skb->cb)); netif_rx(skb); } EXPORT_SYMBOL(cfg80211_send_layer2_update); int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, enum ieee80211_vht_chanwidth bw, int mcs, bool ext_nss_bw_capable, unsigned int max_vht_nss) { u16 map = le16_to_cpu(cap->supp_mcs.rx_mcs_map); int ext_nss_bw; int supp_width; int i, mcs_encoding; if (map == 0xffff) return 0; if (WARN_ON(mcs > 9 || max_vht_nss > 8)) return 0; if (mcs <= 7) mcs_encoding = 0; else if (mcs == 8) mcs_encoding = 1; else mcs_encoding = 2; if (!max_vht_nss) { /* find max_vht_nss for the given MCS */ for (i = 7; i >= 0; i--) { int supp = (map >> (2 * i)) & 3; if (supp == 3) continue; if (supp >= mcs_encoding) { max_vht_nss = i + 1; break; } } } if (!(cap->supp_mcs.tx_mcs_map & cpu_to_le16(IEEE80211_VHT_EXT_NSS_BW_CAPABLE))) return max_vht_nss; ext_nss_bw = le32_get_bits(cap->vht_cap_info, IEEE80211_VHT_CAP_EXT_NSS_BW_MASK); supp_width = le32_get_bits(cap->vht_cap_info, IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK); /* if not capable, treat ext_nss_bw as 0 */ if (!ext_nss_bw_capable) ext_nss_bw = 0; /* This is invalid */ if (supp_width == 3) return 0; /* This is an invalid combination so pretend nothing is supported */ if (supp_width == 2 && (ext_nss_bw == 1 || ext_nss_bw == 2)) return 0; /* * Cover all the special cases according to IEEE 802.11-2016 * Table 9-250. All other cases are either factor of 1 or not * valid/supported. */ switch (bw) { case IEEE80211_VHT_CHANWIDTH_USE_HT: case IEEE80211_VHT_CHANWIDTH_80MHZ: if ((supp_width == 1 || supp_width == 2) && ext_nss_bw == 3) return 2 * max_vht_nss; break; case IEEE80211_VHT_CHANWIDTH_160MHZ: if (supp_width == 0 && (ext_nss_bw == 1 || ext_nss_bw == 2)) return max_vht_nss / 2; if (supp_width == 0 && ext_nss_bw == 3) return (3 * max_vht_nss) / 4; if (supp_width == 1 && ext_nss_bw == 3) return 2 * max_vht_nss; break; case IEEE80211_VHT_CHANWIDTH_80P80MHZ: if (supp_width == 0 && ext_nss_bw == 1) return 0; /* not possible */ if (supp_width == 0 && ext_nss_bw == 2) return max_vht_nss / 2; if (supp_width == 0 && ext_nss_bw == 3) return (3 * max_vht_nss) / 4; if (supp_width == 1 && ext_nss_bw == 0) return 0; /* not possible */ if (supp_width == 1 && ext_nss_bw == 1) return max_vht_nss / 2; if (supp_width == 1 && ext_nss_bw == 2) return (3 * max_vht_nss) / 4; break; } /* not covered or invalid combination received */ return max_vht_nss; } EXPORT_SYMBOL(ieee80211_get_vht_max_nss); bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, bool is_4addr, u8 check_swif) { bool is_vlan = iftype == NL80211_IFTYPE_AP_VLAN; switch (check_swif) { case 0: if (is_vlan && is_4addr) return wiphy->flags & WIPHY_FLAG_4ADDR_AP; return wiphy->interface_modes & BIT(iftype); case 1: if (!(wiphy->software_iftypes & BIT(iftype)) && is_vlan) return wiphy->flags & WIPHY_FLAG_4ADDR_AP; return wiphy->software_iftypes & BIT(iftype); default: break; } return false; } EXPORT_SYMBOL(cfg80211_iftype_allowed); void cfg80211_remove_link(struct wireless_dev *wdev, unsigned int link_id) { struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); lockdep_assert_wiphy(wdev->wiphy); switch (wdev->iftype) { case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: cfg80211_stop_ap(rdev, wdev->netdev, link_id, true); break; default: /* per-link not relevant */ break; } rdev_del_intf_link(rdev, wdev, link_id); wdev->valid_links &= ~BIT(link_id); eth_zero_addr(wdev->links[link_id].addr); } void cfg80211_remove_links(struct wireless_dev *wdev) { unsigned int link_id; /* * links are controlled by upper layers (userspace/cfg) * only for AP mode, so only remove them here for AP */ if (wdev->iftype != NL80211_IFTYPE_AP) return; if (wdev->valid_links) { for_each_valid_link(wdev, link_id) cfg80211_remove_link(wdev, link_id); } } int cfg80211_remove_virtual_intf(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev) { cfg80211_remove_links(wdev); return rdev_del_virtual_intf(rdev, wdev); } const struct wiphy_iftype_ext_capab * cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type) { int i; for (i = 0; i < wiphy->num_iftype_ext_capab; i++) { if (wiphy->iftype_ext_capab[i].iftype == type) return &wiphy->iftype_ext_capab[i]; } return NULL; } EXPORT_SYMBOL(cfg80211_get_iftype_ext_capa); static bool ieee80211_radio_freq_range_valid(const struct wiphy_radio *radio, u32 freq, u32 width) { const struct wiphy_radio_freq_range *r; int i; for (i = 0; i < radio->n_freq_range; i++) { r = &radio->freq_range[i]; if (freq - width / 2 >= r->start_freq && freq + width / 2 <= r->end_freq) return true; } return false; } bool cfg80211_radio_chandef_valid(const struct wiphy_radio *radio, const struct cfg80211_chan_def *chandef) { u32 freq, width; freq = ieee80211_chandef_to_khz(chandef); width = cfg80211_chandef_get_width(chandef); if (!ieee80211_radio_freq_range_valid(radio, freq, width)) return false; freq = MHZ_TO_KHZ(chandef->center_freq2); if (freq && !ieee80211_radio_freq_range_valid(radio, freq, width)) return false; return true; } EXPORT_SYMBOL(cfg80211_radio_chandef_valid); bool cfg80211_wdev_channel_allowed(struct wireless_dev *wdev, struct ieee80211_channel *chan) { struct wiphy *wiphy = wdev->wiphy; const struct wiphy_radio *radio; struct cfg80211_chan_def chandef; u32 radio_mask; int i; radio_mask = wdev->radio_mask; if (!wiphy->n_radio || radio_mask == BIT(wiphy->n_radio) - 1) return true; cfg80211_chandef_create(&chandef, chan, NL80211_CHAN_HT20); for (i = 0; i < wiphy->n_radio; i++) { if (!(radio_mask & BIT(i))) continue; radio = &wiphy->radio[i]; if (!cfg80211_radio_chandef_valid(radio, &chandef)) continue; return true; } return false; } EXPORT_SYMBOL(cfg80211_wdev_channel_allowed); |
| 99 99 67 67 67 67 67 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 | // SPDX-License-Identifier: GPL-2.0-only /* * lowlevel.c * * PURPOSE * Low Level Device Routines for the UDF filesystem * * COPYRIGHT * (C) 1999-2001 Ben Fennema * * HISTORY * * 03/26/99 blf Created. */ #include "udfdecl.h" #include <linux/blkdev.h> #include <linux/cdrom.h> #include <linux/uaccess.h> #include "udf_sb.h" unsigned int udf_get_last_session(struct super_block *sb) { struct cdrom_device_info *cdi = disk_to_cdi(sb->s_bdev->bd_disk); struct cdrom_multisession ms_info; if (!cdi) { udf_debug("CDROMMULTISESSION not supported.\n"); return 0; } ms_info.addr_format = CDROM_LBA; if (cdrom_multisession(cdi, &ms_info) == 0) { udf_debug("XA disk: %s, vol_desc_start=%d\n", ms_info.xa_flag ? "yes" : "no", ms_info.addr.lba); if (ms_info.xa_flag) /* necessary for a valid ms_info.addr */ return ms_info.addr.lba; } return 0; } udf_pblk_t udf_get_last_block(struct super_block *sb) { struct cdrom_device_info *cdi = disk_to_cdi(sb->s_bdev->bd_disk); unsigned long lblock = 0; /* * The cdrom layer call failed or returned obviously bogus value? * Try using the device size... */ if (!cdi || cdrom_get_last_written(cdi, &lblock) || lblock == 0) { if (sb_bdev_nr_blocks(sb) > ~(udf_pblk_t)0) return 0; lblock = sb_bdev_nr_blocks(sb); } if (lblock) return lblock - 1; return 0; } |
| 2 1 2 1 1 1 1 1 3 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include "seq_oss_device.h" #include "seq_oss_synth.h" #include "seq_oss_midi.h" #include "seq_oss_event.h" #include "seq_oss_timer.h" #include <sound/seq_oss_legacy.h> #include "seq_oss_readq.h" #include "seq_oss_writeq.h" #include <linux/nospec.h> /* * prototypes */ static int extended_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev); static int chn_voice_event(struct seq_oss_devinfo *dp, union evrec *event_rec, struct snd_seq_event *ev); static int chn_common_event(struct seq_oss_devinfo *dp, union evrec *event_rec, struct snd_seq_event *ev); static int timing_event(struct seq_oss_devinfo *dp, union evrec *event_rec, struct snd_seq_event *ev); static int local_event(struct seq_oss_devinfo *dp, union evrec *event_rec, struct snd_seq_event *ev); static int old_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev); static int note_on_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, struct snd_seq_event *ev); static int note_off_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, struct snd_seq_event *ev); static int set_note_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int note, int vel, struct snd_seq_event *ev); static int set_control_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int param, int val, struct snd_seq_event *ev); static int set_echo_event(struct seq_oss_devinfo *dp, union evrec *rec, struct snd_seq_event *ev); /* * convert an OSS event to ALSA event * return 0 : enqueued * non-zero : invalid - ignored */ int snd_seq_oss_process_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { switch (q->s.code) { case SEQ_EXTENDED: return extended_event(dp, q, ev); case EV_CHN_VOICE: return chn_voice_event(dp, q, ev); case EV_CHN_COMMON: return chn_common_event(dp, q, ev); case EV_TIMING: return timing_event(dp, q, ev); case EV_SEQ_LOCAL: return local_event(dp, q, ev); case EV_SYSEX: return snd_seq_oss_synth_sysex(dp, q->x.dev, q->x.buf, ev); case SEQ_MIDIPUTC: if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return -EINVAL; /* put a midi byte */ if (! is_write_mode(dp->file_mode)) break; if (snd_seq_oss_midi_open(dp, q->s.dev, SNDRV_SEQ_OSS_FILE_WRITE)) break; if (snd_seq_oss_midi_filemode(dp, q->s.dev) & SNDRV_SEQ_OSS_FILE_WRITE) return snd_seq_oss_midi_putc(dp, q->s.dev, q->s.parm1, ev); break; case SEQ_ECHO: if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return -EINVAL; return set_echo_event(dp, q, ev); case SEQ_PRIVATE: if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return -EINVAL; return snd_seq_oss_synth_raw_event(dp, q->c[1], q->c, ev); default: if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return -EINVAL; return old_event(dp, q, ev); } return -EINVAL; } /* old type events: mode1 only */ static int old_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { switch (q->s.code) { case SEQ_NOTEOFF: return note_off_event(dp, 0, q->n.chn, q->n.note, q->n.vel, ev); case SEQ_NOTEON: return note_on_event(dp, 0, q->n.chn, q->n.note, q->n.vel, ev); case SEQ_WAIT: /* skip */ break; case SEQ_PGMCHANGE: return set_control_event(dp, 0, SNDRV_SEQ_EVENT_PGMCHANGE, q->n.chn, 0, q->n.note, ev); case SEQ_SYNCTIMER: return snd_seq_oss_timer_reset(dp->timer); } return -EINVAL; } /* 8bytes extended event: mode1 only */ static int extended_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { int val; switch (q->e.cmd) { case SEQ_NOTEOFF: return note_off_event(dp, q->e.dev, q->e.chn, q->e.p1, q->e.p2, ev); case SEQ_NOTEON: return note_on_event(dp, q->e.dev, q->e.chn, q->e.p1, q->e.p2, ev); case SEQ_PGMCHANGE: return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_PGMCHANGE, q->e.chn, 0, q->e.p1, ev); case SEQ_AFTERTOUCH: return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_CHANPRESS, q->e.chn, 0, q->e.p1, ev); case SEQ_BALANCE: /* convert -128:127 to 0:127 */ val = (char)q->e.p1; val = (val + 128) / 2; return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_CONTROLLER, q->e.chn, CTL_PAN, val, ev); case SEQ_CONTROLLER: val = ((short)q->e.p3 << 8) | (short)q->e.p2; switch (q->e.p1) { case CTRL_PITCH_BENDER: /* SEQ1 V2 control */ /* -0x2000:0x1fff */ return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_PITCHBEND, q->e.chn, 0, val, ev); case CTRL_PITCH_BENDER_RANGE: /* conversion: 100/semitone -> 128/semitone */ return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_REGPARAM, q->e.chn, 0, val*128/100, ev); default: return set_control_event(dp, q->e.dev, SNDRV_SEQ_EVENT_CONTROL14, q->e.chn, q->e.p1, val, ev); } case SEQ_VOLMODE: return snd_seq_oss_synth_raw_event(dp, q->e.dev, q->c, ev); } return -EINVAL; } /* channel voice events: mode1 and 2 */ static int chn_voice_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { if (q->v.chn >= 32) return -EINVAL; switch (q->v.cmd) { case MIDI_NOTEON: return note_on_event(dp, q->v.dev, q->v.chn, q->v.note, q->v.parm, ev); case MIDI_NOTEOFF: return note_off_event(dp, q->v.dev, q->v.chn, q->v.note, q->v.parm, ev); case MIDI_KEY_PRESSURE: return set_note_event(dp, q->v.dev, SNDRV_SEQ_EVENT_KEYPRESS, q->v.chn, q->v.note, q->v.parm, ev); } return -EINVAL; } /* channel common events: mode1 and 2 */ static int chn_common_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { if (q->l.chn >= 32) return -EINVAL; switch (q->l.cmd) { case MIDI_PGM_CHANGE: return set_control_event(dp, q->l.dev, SNDRV_SEQ_EVENT_PGMCHANGE, q->l.chn, 0, q->l.p1, ev); case MIDI_CTL_CHANGE: return set_control_event(dp, q->l.dev, SNDRV_SEQ_EVENT_CONTROLLER, q->l.chn, q->l.p1, q->l.val, ev); case MIDI_PITCH_BEND: /* conversion: 0:0x3fff -> -0x2000:0x1fff */ return set_control_event(dp, q->l.dev, SNDRV_SEQ_EVENT_PITCHBEND, q->l.chn, 0, q->l.val - 8192, ev); case MIDI_CHN_PRESSURE: return set_control_event(dp, q->l.dev, SNDRV_SEQ_EVENT_CHANPRESS, q->l.chn, 0, q->l.val, ev); } return -EINVAL; } /* timer events: mode1 and mode2 */ static int timing_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { switch (q->t.cmd) { case TMR_ECHO: if (dp->seq_mode == SNDRV_SEQ_OSS_MODE_MUSIC) return set_echo_event(dp, q, ev); else { union evrec tmp; memset(&tmp, 0, sizeof(tmp)); /* XXX: only for little-endian! */ tmp.echo = (q->t.time << 8) | SEQ_ECHO; return set_echo_event(dp, &tmp, ev); } case TMR_STOP: if (dp->seq_mode) return snd_seq_oss_timer_stop(dp->timer); return 0; case TMR_CONTINUE: if (dp->seq_mode) return snd_seq_oss_timer_continue(dp->timer); return 0; case TMR_TEMPO: if (dp->seq_mode) return snd_seq_oss_timer_tempo(dp->timer, q->t.time); return 0; } return -EINVAL; } /* local events: mode1 and 2 */ static int local_event(struct seq_oss_devinfo *dp, union evrec *q, struct snd_seq_event *ev) { return -EINVAL; } /* * process note-on event for OSS synth * three different modes are available: * - SNDRV_SEQ_OSS_PROCESS_EVENTS (for one-voice per channel mode) * Accept note 255 as volume change. * - SNDRV_SEQ_OSS_PASS_EVENTS * Pass all events to lowlevel driver anyway * - SNDRV_SEQ_OSS_PROCESS_KEYPRESS (mostly for Emu8000) * Use key-pressure if note >= 128 */ static int note_on_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, struct snd_seq_event *ev) { struct seq_oss_synthinfo *info; info = snd_seq_oss_synth_info(dp, dev); if (!info) return -ENXIO; switch (info->arg.event_passing) { case SNDRV_SEQ_OSS_PROCESS_EVENTS: if (! info->ch || ch < 0 || ch >= info->nr_voices) { /* pass directly */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev); } ch = array_index_nospec(ch, info->nr_voices); if (note == 255 && info->ch[ch].note >= 0) { /* volume control */ int type; if (info->ch[ch].vel) /* sample already started -- volume change */ type = SNDRV_SEQ_EVENT_KEYPRESS; else /* sample not started -- start now */ type = SNDRV_SEQ_EVENT_NOTEON; info->ch[ch].vel = vel; return set_note_event(dp, dev, type, ch, info->ch[ch].note, vel, ev); } else if (note >= 128) return -EINVAL; /* invalid */ if (note != info->ch[ch].note && info->ch[ch].note >= 0) /* note changed - note off at beginning */ set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEOFF, ch, info->ch[ch].note, 0, ev); /* set current status */ info->ch[ch].note = note; info->ch[ch].vel = vel; if (vel) /* non-zero velocity - start the note now */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev); return -EINVAL; case SNDRV_SEQ_OSS_PASS_EVENTS: /* pass the event anyway */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev); case SNDRV_SEQ_OSS_PROCESS_KEYPRESS: if (note >= 128) /* key pressure: shifted by 128 */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_KEYPRESS, ch, note - 128, vel, ev); else /* normal note-on event */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev); } return -EINVAL; } /* * process note-off event for OSS synth */ static int note_off_event(struct seq_oss_devinfo *dp, int dev, int ch, int note, int vel, struct snd_seq_event *ev) { struct seq_oss_synthinfo *info; info = snd_seq_oss_synth_info(dp, dev); if (!info) return -ENXIO; switch (info->arg.event_passing) { case SNDRV_SEQ_OSS_PROCESS_EVENTS: if (! info->ch || ch < 0 || ch >= info->nr_voices) { /* pass directly */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEON, ch, note, vel, ev); } ch = array_index_nospec(ch, info->nr_voices); if (info->ch[ch].note >= 0) { note = info->ch[ch].note; info->ch[ch].vel = 0; info->ch[ch].note = -1; return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEOFF, ch, note, vel, ev); } return -EINVAL; /* invalid */ case SNDRV_SEQ_OSS_PASS_EVENTS: case SNDRV_SEQ_OSS_PROCESS_KEYPRESS: /* pass the event anyway */ return set_note_event(dp, dev, SNDRV_SEQ_EVENT_NOTEOFF, ch, note, vel, ev); } return -EINVAL; } /* * create a note event */ static int set_note_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int note, int vel, struct snd_seq_event *ev) { if (!snd_seq_oss_synth_info(dp, dev)) return -ENXIO; ev->type = type; snd_seq_oss_synth_addr(dp, dev, ev); ev->data.note.channel = ch; ev->data.note.note = note; ev->data.note.velocity = vel; return 0; } /* * create a control event */ static int set_control_event(struct seq_oss_devinfo *dp, int dev, int type, int ch, int param, int val, struct snd_seq_event *ev) { if (!snd_seq_oss_synth_info(dp, dev)) return -ENXIO; ev->type = type; snd_seq_oss_synth_addr(dp, dev, ev); ev->data.control.channel = ch; ev->data.control.param = param; ev->data.control.value = val; return 0; } /* * create an echo event */ static int set_echo_event(struct seq_oss_devinfo *dp, union evrec *rec, struct snd_seq_event *ev) { ev->type = SNDRV_SEQ_EVENT_ECHO; /* echo back to itself */ snd_seq_oss_fill_addr(dp, ev, dp->addr.client, dp->addr.port); memcpy(&ev->data, rec, LONG_EVENT_SIZE); return 0; } /* * event input callback from ALSA sequencer: * the echo event is processed here. */ int snd_seq_oss_event_input(struct snd_seq_event *ev, int direct, void *private_data, int atomic, int hop) { struct seq_oss_devinfo *dp = (struct seq_oss_devinfo *)private_data; union evrec *rec; if (ev->type != SNDRV_SEQ_EVENT_ECHO) return snd_seq_oss_midi_input(ev, direct, private_data); if (ev->source.client != dp->cseq) return 0; /* ignored */ rec = (union evrec*)&ev->data; if (rec->s.code == SEQ_SYNCTIMER) { /* sync echo back */ snd_seq_oss_writeq_wakeup(dp->writeq, rec->t.time); } else { /* echo back event */ if (dp->readq == NULL) return 0; snd_seq_oss_readq_put_event(dp->readq, rec); } return 0; } |
| 46 19 1 1 1 136 73 1 81 132 9 7 2 6 3 5 4 2 7 5 4 4 5 3 6 1 6 2 6 3 7 4 4 3 5 3 181 181 83 83 29 16 20 16 17 11 13 37 32 21 14 7 1 9 8 57 67 1 1 1 2 1 1 1 1 70 69 1 70 70 1 1 56 12 55 13 68 68 68 68 68 1 67 2 76 68 4 1 3 18 76 11 65 75 1 76 27 30 1 57 57 1 77 10 85 77 10 4 85 85 21 21 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2012-2013 Samsung Electronics Co., Ltd. */ #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/module.h> #include <linux/init.h> #include <linux/time.h> #include <linux/mount.h> #include <linux/cred.h> #include <linux/statfs.h> #include <linux/seq_file.h> #include <linux/blkdev.h> #include <linux/fs_struct.h> #include <linux/iversion.h> #include <linux/nls.h> #include <linux/buffer_head.h> #include <linux/magic.h> #include "exfat_raw.h" #include "exfat_fs.h" static char exfat_default_iocharset[] = CONFIG_EXFAT_DEFAULT_IOCHARSET; static struct kmem_cache *exfat_inode_cachep; static void exfat_free_iocharset(struct exfat_sb_info *sbi) { if (sbi->options.iocharset != exfat_default_iocharset) kfree(sbi->options.iocharset); } static void exfat_put_super(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); mutex_lock(&sbi->s_lock); exfat_clear_volume_dirty(sb); exfat_free_bitmap(sbi); brelse(sbi->boot_bh); mutex_unlock(&sbi->s_lock); } static int exfat_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); unsigned long long id = huge_encode_dev(sb->s_bdev->bd_dev); buf->f_type = sb->s_magic; buf->f_bsize = sbi->cluster_size; buf->f_blocks = sbi->num_clusters - 2; /* clu 0 & 1 */ buf->f_bfree = buf->f_blocks - sbi->used_clusters; buf->f_bavail = buf->f_bfree; buf->f_fsid = u64_to_fsid(id); /* Unicode utf16 255 characters */ buf->f_namelen = EXFAT_MAX_FILE_LEN * NLS_MAX_CHARSET_SIZE; return 0; } static int exfat_set_vol_flags(struct super_block *sb, unsigned short new_flags) { struct exfat_sb_info *sbi = EXFAT_SB(sb); struct boot_sector *p_boot = (struct boot_sector *)sbi->boot_bh->b_data; /* retain persistent-flags */ new_flags |= sbi->vol_flags_persistent; /* flags are not changed */ if (sbi->vol_flags == new_flags) return 0; sbi->vol_flags = new_flags; /* skip updating volume dirty flag, * if this volume has been mounted with read-only */ if (sb_rdonly(sb)) return 0; p_boot->vol_flags = cpu_to_le16(new_flags); set_buffer_uptodate(sbi->boot_bh); mark_buffer_dirty(sbi->boot_bh); __sync_dirty_buffer(sbi->boot_bh, REQ_SYNC | REQ_FUA | REQ_PREFLUSH); return 0; } int exfat_set_volume_dirty(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); return exfat_set_vol_flags(sb, sbi->vol_flags | VOLUME_DIRTY); } int exfat_clear_volume_dirty(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); return exfat_set_vol_flags(sb, sbi->vol_flags & ~VOLUME_DIRTY); } static int exfat_show_options(struct seq_file *m, struct dentry *root) { struct super_block *sb = root->d_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_mount_options *opts = &sbi->options; /* Show partition info */ if (!uid_eq(opts->fs_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, opts->fs_uid)); if (!gid_eq(opts->fs_gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, opts->fs_gid)); seq_printf(m, ",fmask=%04o,dmask=%04o", opts->fs_fmask, opts->fs_dmask); if (opts->allow_utime) seq_printf(m, ",allow_utime=%04o", opts->allow_utime); if (opts->utf8) seq_puts(m, ",iocharset=utf8"); else if (sbi->nls_io) seq_printf(m, ",iocharset=%s", sbi->nls_io->charset); if (opts->errors == EXFAT_ERRORS_CONT) seq_puts(m, ",errors=continue"); else if (opts->errors == EXFAT_ERRORS_PANIC) seq_puts(m, ",errors=panic"); else seq_puts(m, ",errors=remount-ro"); if (opts->discard) seq_puts(m, ",discard"); if (opts->keep_last_dots) seq_puts(m, ",keep_last_dots"); if (opts->sys_tz) seq_puts(m, ",sys_tz"); else if (opts->time_offset) seq_printf(m, ",time_offset=%d", opts->time_offset); if (opts->zero_size_dir) seq_puts(m, ",zero_size_dir"); return 0; } int exfat_force_shutdown(struct super_block *sb, u32 flags) { int ret; struct exfat_sb_info *sbi = sb->s_fs_info; struct exfat_mount_options *opts = &sbi->options; if (exfat_forced_shutdown(sb)) return 0; switch (flags) { case EXFAT_GOING_DOWN_DEFAULT: case EXFAT_GOING_DOWN_FULLSYNC: ret = bdev_freeze(sb->s_bdev); if (ret) return ret; bdev_thaw(sb->s_bdev); set_bit(EXFAT_FLAGS_SHUTDOWN, &sbi->s_exfat_flags); break; case EXFAT_GOING_DOWN_NOSYNC: set_bit(EXFAT_FLAGS_SHUTDOWN, &sbi->s_exfat_flags); break; default: return -EINVAL; } if (opts->discard) opts->discard = 0; return 0; } static void exfat_shutdown(struct super_block *sb) { exfat_force_shutdown(sb, EXFAT_GOING_DOWN_NOSYNC); } static struct inode *exfat_alloc_inode(struct super_block *sb) { struct exfat_inode_info *ei; ei = alloc_inode_sb(sb, exfat_inode_cachep, GFP_NOFS); if (!ei) return NULL; init_rwsem(&ei->truncate_lock); return &ei->vfs_inode; } static void exfat_free_inode(struct inode *inode) { kmem_cache_free(exfat_inode_cachep, EXFAT_I(inode)); } static const struct super_operations exfat_sops = { .alloc_inode = exfat_alloc_inode, .free_inode = exfat_free_inode, .write_inode = exfat_write_inode, .evict_inode = exfat_evict_inode, .put_super = exfat_put_super, .statfs = exfat_statfs, .show_options = exfat_show_options, .shutdown = exfat_shutdown, }; enum { Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, Opt_allow_utime, Opt_charset, Opt_errors, Opt_discard, Opt_keep_last_dots, Opt_sys_tz, Opt_time_offset, Opt_zero_size_dir, /* Deprecated options */ Opt_utf8, Opt_debug, Opt_namecase, Opt_codepage, }; static const struct constant_table exfat_param_enums[] = { { "continue", EXFAT_ERRORS_CONT }, { "panic", EXFAT_ERRORS_PANIC }, { "remount-ro", EXFAT_ERRORS_RO }, {} }; static const struct fs_parameter_spec exfat_parameters[] = { fsparam_uid("uid", Opt_uid), fsparam_gid("gid", Opt_gid), fsparam_u32oct("umask", Opt_umask), fsparam_u32oct("dmask", Opt_dmask), fsparam_u32oct("fmask", Opt_fmask), fsparam_u32oct("allow_utime", Opt_allow_utime), fsparam_string("iocharset", Opt_charset), fsparam_enum("errors", Opt_errors, exfat_param_enums), fsparam_flag("discard", Opt_discard), fsparam_flag("keep_last_dots", Opt_keep_last_dots), fsparam_flag("sys_tz", Opt_sys_tz), fsparam_s32("time_offset", Opt_time_offset), fsparam_flag("zero_size_dir", Opt_zero_size_dir), __fsparam(NULL, "utf8", Opt_utf8, fs_param_deprecated, NULL), __fsparam(NULL, "debug", Opt_debug, fs_param_deprecated, NULL), __fsparam(fs_param_is_u32, "namecase", Opt_namecase, fs_param_deprecated, NULL), __fsparam(fs_param_is_u32, "codepage", Opt_codepage, fs_param_deprecated, NULL), {} }; static int exfat_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct exfat_sb_info *sbi = fc->s_fs_info; struct exfat_mount_options *opts = &sbi->options; struct fs_parse_result result; int opt; opt = fs_parse(fc, exfat_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_uid: opts->fs_uid = result.uid; break; case Opt_gid: opts->fs_gid = result.gid; break; case Opt_umask: opts->fs_fmask = result.uint_32; opts->fs_dmask = result.uint_32; break; case Opt_dmask: opts->fs_dmask = result.uint_32; break; case Opt_fmask: opts->fs_fmask = result.uint_32; break; case Opt_allow_utime: opts->allow_utime = result.uint_32 & 0022; break; case Opt_charset: exfat_free_iocharset(sbi); opts->iocharset = param->string; param->string = NULL; break; case Opt_errors: opts->errors = result.uint_32; break; case Opt_discard: opts->discard = 1; break; case Opt_keep_last_dots: opts->keep_last_dots = 1; break; case Opt_sys_tz: opts->sys_tz = 1; break; case Opt_time_offset: /* * Make the limit 24 just in case someone invents something * unusual. */ if (result.int_32 < -24 * 60 || result.int_32 > 24 * 60) return -EINVAL; opts->time_offset = result.int_32; break; case Opt_zero_size_dir: opts->zero_size_dir = true; break; case Opt_utf8: case Opt_debug: case Opt_namecase: case Opt_codepage: break; default: return -EINVAL; } return 0; } static void exfat_hash_init(struct super_block *sb) { struct exfat_sb_info *sbi = EXFAT_SB(sb); int i; spin_lock_init(&sbi->inode_hash_lock); for (i = 0; i < EXFAT_HASH_SIZE; i++) INIT_HLIST_HEAD(&sbi->inode_hashtable[i]); } static int exfat_read_root(struct inode *inode, struct exfat_chain *root_clu) { struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); int num_subdirs; exfat_chain_set(&ei->dir, sbi->root_dir, 0, ALLOC_FAT_CHAIN); ei->entry = -1; ei->start_clu = sbi->root_dir; ei->flags = ALLOC_FAT_CHAIN; ei->type = TYPE_DIR; ei->version = 0; ei->hint_bmap.off = EXFAT_EOF_CLUSTER; ei->hint_stat.eidx = 0; ei->hint_stat.clu = sbi->root_dir; ei->hint_femp.eidx = EXFAT_HINT_NONE; i_size_write(inode, EXFAT_CLU_TO_B(root_clu->size, sbi)); num_subdirs = exfat_count_dir_entries(sb, root_clu); if (num_subdirs < 0) return -EIO; set_nlink(inode, num_subdirs + EXFAT_MIN_SUBDIR); inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode_inc_iversion(inode); inode->i_generation = 0; inode->i_mode = exfat_make_mode(sbi, EXFAT_ATTR_SUBDIR, 0777); inode->i_op = &exfat_dir_inode_operations; inode->i_fop = &exfat_dir_operations; inode->i_blocks = round_up(i_size_read(inode), sbi->cluster_size) >> 9; ei->i_pos = ((loff_t)sbi->root_dir << 32) | 0xffffffff; exfat_save_attr(inode, EXFAT_ATTR_SUBDIR); ei->i_crtime = simple_inode_init_ts(inode); exfat_truncate_inode_atime(inode); return 0; } static int exfat_calibrate_blocksize(struct super_block *sb, int logical_sect) { struct exfat_sb_info *sbi = EXFAT_SB(sb); if (!is_power_of_2(logical_sect)) { exfat_err(sb, "bogus logical sector size %u", logical_sect); return -EIO; } if (logical_sect < sb->s_blocksize) { exfat_err(sb, "logical sector size too small for device (logical sector size = %u)", logical_sect); return -EIO; } if (logical_sect > sb->s_blocksize) { brelse(sbi->boot_bh); sbi->boot_bh = NULL; if (!sb_set_blocksize(sb, logical_sect)) { exfat_err(sb, "unable to set blocksize %u", logical_sect); return -EIO; } sbi->boot_bh = sb_bread(sb, 0); if (!sbi->boot_bh) { exfat_err(sb, "unable to read boot sector (logical sector size = %lu)", sb->s_blocksize); return -EIO; } } return 0; } static int exfat_read_boot_sector(struct super_block *sb) { struct boot_sector *p_boot; struct exfat_sb_info *sbi = EXFAT_SB(sb); /* set block size to read super block */ sb_min_blocksize(sb, 512); /* read boot sector */ sbi->boot_bh = sb_bread(sb, 0); if (!sbi->boot_bh) { exfat_err(sb, "unable to read boot sector"); return -EIO; } p_boot = (struct boot_sector *)sbi->boot_bh->b_data; /* check the validity of BOOT */ if (le16_to_cpu((p_boot->signature)) != BOOT_SIGNATURE) { exfat_err(sb, "invalid boot record signature"); return -EINVAL; } if (memcmp(p_boot->fs_name, STR_EXFAT, BOOTSEC_FS_NAME_LEN)) { exfat_err(sb, "invalid fs_name"); /* fs_name may unprintable */ return -EINVAL; } /* * must_be_zero field must be filled with zero to prevent mounting * from FAT volume. */ if (memchr_inv(p_boot->must_be_zero, 0, sizeof(p_boot->must_be_zero))) return -EINVAL; if (p_boot->num_fats != 1 && p_boot->num_fats != 2) { exfat_err(sb, "bogus number of FAT structure"); return -EINVAL; } /* * sect_size_bits could be at least 9 and at most 12. */ if (p_boot->sect_size_bits < EXFAT_MIN_SECT_SIZE_BITS || p_boot->sect_size_bits > EXFAT_MAX_SECT_SIZE_BITS) { exfat_err(sb, "bogus sector size bits : %u", p_boot->sect_size_bits); return -EINVAL; } /* * sect_per_clus_bits could be at least 0 and at most 25 - sect_size_bits. */ if (p_boot->sect_per_clus_bits > EXFAT_MAX_SECT_PER_CLUS_BITS(p_boot)) { exfat_err(sb, "bogus sectors bits per cluster : %u", p_boot->sect_per_clus_bits); return -EINVAL; } sbi->sect_per_clus = 1 << p_boot->sect_per_clus_bits; sbi->sect_per_clus_bits = p_boot->sect_per_clus_bits; sbi->cluster_size_bits = p_boot->sect_per_clus_bits + p_boot->sect_size_bits; sbi->cluster_size = 1 << sbi->cluster_size_bits; sbi->num_FAT_sectors = le32_to_cpu(p_boot->fat_length); sbi->FAT1_start_sector = le32_to_cpu(p_boot->fat_offset); sbi->FAT2_start_sector = le32_to_cpu(p_boot->fat_offset); if (p_boot->num_fats == 2) sbi->FAT2_start_sector += sbi->num_FAT_sectors; sbi->data_start_sector = le32_to_cpu(p_boot->clu_offset); sbi->num_sectors = le64_to_cpu(p_boot->vol_length); /* because the cluster index starts with 2 */ sbi->num_clusters = le32_to_cpu(p_boot->clu_count) + EXFAT_RESERVED_CLUSTERS; sbi->root_dir = le32_to_cpu(p_boot->root_cluster); sbi->dentries_per_clu = 1 << (sbi->cluster_size_bits - DENTRY_SIZE_BITS); sbi->vol_flags = le16_to_cpu(p_boot->vol_flags); sbi->vol_flags_persistent = sbi->vol_flags & (VOLUME_DIRTY | MEDIA_FAILURE); sbi->clu_srch_ptr = EXFAT_FIRST_CLUSTER; /* check consistencies */ if ((u64)sbi->num_FAT_sectors << p_boot->sect_size_bits < (u64)sbi->num_clusters * 4) { exfat_err(sb, "bogus fat length"); return -EINVAL; } if (sbi->data_start_sector < (u64)sbi->FAT1_start_sector + (u64)sbi->num_FAT_sectors * p_boot->num_fats) { exfat_err(sb, "bogus data start sector"); return -EINVAL; } if (sbi->vol_flags & VOLUME_DIRTY) exfat_warn(sb, "Volume was not properly unmounted. Some data may be corrupt. Please run fsck."); if (sbi->vol_flags & MEDIA_FAILURE) exfat_warn(sb, "Medium has reported failures. Some data may be lost."); /* exFAT file size is limited by a disk volume size */ sb->s_maxbytes = (u64)(sbi->num_clusters - EXFAT_RESERVED_CLUSTERS) << sbi->cluster_size_bits; /* check logical sector size */ if (exfat_calibrate_blocksize(sb, 1 << p_boot->sect_size_bits)) return -EIO; return 0; } static int exfat_verify_boot_region(struct super_block *sb) { struct buffer_head *bh = NULL; u32 chksum = 0; __le32 *p_sig, *p_chksum; int sn, i; /* read boot sector sub-regions */ for (sn = 0; sn < 11; sn++) { bh = sb_bread(sb, sn); if (!bh) return -EIO; if (sn != 0 && sn <= 8) { /* extended boot sector sub-regions */ p_sig = (__le32 *)&bh->b_data[sb->s_blocksize - 4]; if (le32_to_cpu(*p_sig) != EXBOOT_SIGNATURE) exfat_warn(sb, "Invalid exboot-signature(sector = %d): 0x%08x", sn, le32_to_cpu(*p_sig)); } chksum = exfat_calc_chksum32(bh->b_data, sb->s_blocksize, chksum, sn ? CS_DEFAULT : CS_BOOT_SECTOR); brelse(bh); } /* boot checksum sub-regions */ bh = sb_bread(sb, sn); if (!bh) return -EIO; for (i = 0; i < sb->s_blocksize; i += sizeof(u32)) { p_chksum = (__le32 *)&bh->b_data[i]; if (le32_to_cpu(*p_chksum) != chksum) { exfat_err(sb, "Invalid boot checksum (boot checksum : 0x%08x, checksum : 0x%08x)", le32_to_cpu(*p_chksum), chksum); brelse(bh); return -EINVAL; } } brelse(bh); return 0; } /* mount the file system volume */ static int __exfat_fill_super(struct super_block *sb, struct exfat_chain *root_clu) { int ret; struct exfat_sb_info *sbi = EXFAT_SB(sb); ret = exfat_read_boot_sector(sb); if (ret) { exfat_err(sb, "failed to read boot sector"); goto free_bh; } ret = exfat_verify_boot_region(sb); if (ret) { exfat_err(sb, "invalid boot region"); goto free_bh; } /* * Call exfat_count_num_cluster() before searching for up-case and * bitmap directory entries to avoid infinite loop if they are missing * and the cluster chain includes a loop. */ exfat_chain_set(root_clu, sbi->root_dir, 0, ALLOC_FAT_CHAIN); ret = exfat_count_num_clusters(sb, root_clu, &root_clu->size); if (ret) { exfat_err(sb, "failed to count the number of clusters in root"); goto free_bh; } ret = exfat_create_upcase_table(sb); if (ret) { exfat_err(sb, "failed to load upcase table"); goto free_bh; } ret = exfat_load_bitmap(sb); if (ret) { exfat_err(sb, "failed to load alloc-bitmap"); goto free_bh; } ret = exfat_count_used_clusters(sb, &sbi->used_clusters); if (ret) { exfat_err(sb, "failed to scan clusters"); goto free_alloc_bitmap; } return 0; free_alloc_bitmap: exfat_free_bitmap(sbi); free_bh: brelse(sbi->boot_bh); return ret; } static int exfat_fill_super(struct super_block *sb, struct fs_context *fc) { struct exfat_sb_info *sbi = sb->s_fs_info; struct exfat_mount_options *opts = &sbi->options; struct inode *root_inode; struct exfat_chain root_clu; int err; if (opts->allow_utime == (unsigned short)-1) opts->allow_utime = ~opts->fs_dmask & 0022; if (opts->discard && !bdev_max_discard_sectors(sb->s_bdev)) { exfat_warn(sb, "mounting with \"discard\" option, but the device does not support discard"); opts->discard = 0; } sb->s_flags |= SB_NODIRATIME; sb->s_magic = EXFAT_SUPER_MAGIC; sb->s_op = &exfat_sops; sb->s_time_gran = 10 * NSEC_PER_MSEC; sb->s_time_min = EXFAT_MIN_TIMESTAMP_SECS; sb->s_time_max = EXFAT_MAX_TIMESTAMP_SECS; err = __exfat_fill_super(sb, &root_clu); if (err) { exfat_err(sb, "failed to recognize exfat type"); goto check_nls_io; } /* set up enough so that it can read an inode */ exfat_hash_init(sb); if (!strcmp(sbi->options.iocharset, "utf8")) opts->utf8 = 1; else { sbi->nls_io = load_nls(sbi->options.iocharset); if (!sbi->nls_io) { exfat_err(sb, "IO charset %s not found", sbi->options.iocharset); err = -EINVAL; goto free_table; } } if (sbi->options.utf8) set_default_d_op(sb, &exfat_utf8_dentry_ops); else set_default_d_op(sb, &exfat_dentry_ops); root_inode = new_inode(sb); if (!root_inode) { exfat_err(sb, "failed to allocate root inode"); err = -ENOMEM; goto free_table; } root_inode->i_ino = EXFAT_ROOT_INO; inode_set_iversion(root_inode, 1); err = exfat_read_root(root_inode, &root_clu); if (err) { exfat_err(sb, "failed to initialize root inode"); goto put_inode; } exfat_hash_inode(root_inode, EXFAT_I(root_inode)->i_pos); insert_inode_hash(root_inode); sb->s_root = d_make_root(root_inode); if (!sb->s_root) { exfat_err(sb, "failed to get the root dentry"); err = -ENOMEM; goto free_table; } return 0; put_inode: iput(root_inode); sb->s_root = NULL; free_table: exfat_free_bitmap(sbi); brelse(sbi->boot_bh); check_nls_io: return err; } static int exfat_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, exfat_fill_super); } static void exfat_free_sbi(struct exfat_sb_info *sbi) { exfat_free_iocharset(sbi); kfree(sbi); } static void exfat_free(struct fs_context *fc) { struct exfat_sb_info *sbi = fc->s_fs_info; if (sbi) exfat_free_sbi(sbi); } static int exfat_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; fc->sb_flags |= SB_NODIRATIME; sync_filesystem(sb); mutex_lock(&EXFAT_SB(sb)->s_lock); exfat_clear_volume_dirty(sb); mutex_unlock(&EXFAT_SB(sb)->s_lock); return 0; } static const struct fs_context_operations exfat_context_ops = { .parse_param = exfat_parse_param, .get_tree = exfat_get_tree, .free = exfat_free, .reconfigure = exfat_reconfigure, }; static int exfat_init_fs_context(struct fs_context *fc) { struct exfat_sb_info *sbi; sbi = kzalloc(sizeof(struct exfat_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; mutex_init(&sbi->s_lock); mutex_init(&sbi->bitmap_lock); ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); sbi->options.fs_uid = current_uid(); sbi->options.fs_gid = current_gid(); sbi->options.fs_fmask = current->fs->umask; sbi->options.fs_dmask = current->fs->umask; sbi->options.allow_utime = -1; sbi->options.iocharset = exfat_default_iocharset; sbi->options.errors = EXFAT_ERRORS_RO; fc->s_fs_info = sbi; fc->ops = &exfat_context_ops; return 0; } static void delayed_free(struct rcu_head *p) { struct exfat_sb_info *sbi = container_of(p, struct exfat_sb_info, rcu); unload_nls(sbi->nls_io); exfat_free_upcase_table(sbi); exfat_free_sbi(sbi); } static void exfat_kill_sb(struct super_block *sb) { struct exfat_sb_info *sbi = sb->s_fs_info; kill_block_super(sb); if (sbi) call_rcu(&sbi->rcu, delayed_free); } static struct file_system_type exfat_fs_type = { .owner = THIS_MODULE, .name = "exfat", .init_fs_context = exfat_init_fs_context, .parameters = exfat_parameters, .kill_sb = exfat_kill_sb, .fs_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, }; static void exfat_inode_init_once(void *foo) { struct exfat_inode_info *ei = (struct exfat_inode_info *)foo; spin_lock_init(&ei->cache_lru_lock); ei->nr_caches = 0; ei->cache_valid_id = EXFAT_CACHE_VALID + 1; INIT_LIST_HEAD(&ei->cache_lru); INIT_HLIST_NODE(&ei->i_hash_fat); inode_init_once(&ei->vfs_inode); } static int __init init_exfat_fs(void) { int err; err = exfat_cache_init(); if (err) return err; exfat_inode_cachep = kmem_cache_create("exfat_inode_cache", sizeof(struct exfat_inode_info), 0, SLAB_RECLAIM_ACCOUNT, exfat_inode_init_once); if (!exfat_inode_cachep) { err = -ENOMEM; goto shutdown_cache; } err = register_filesystem(&exfat_fs_type); if (err) goto destroy_cache; return 0; destroy_cache: kmem_cache_destroy(exfat_inode_cachep); shutdown_cache: exfat_cache_shutdown(); return err; } static void __exit exit_exfat_fs(void) { /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(exfat_inode_cachep); unregister_filesystem(&exfat_fs_type); exfat_cache_shutdown(); } module_init(init_exfat_fs); module_exit(exit_exfat_fs); MODULE_ALIAS_FS("exfat"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("exFAT filesystem support"); MODULE_AUTHOR("Samsung Electronics Co., Ltd."); |
| 60 59 60 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 | // SPDX-License-Identifier: GPL-2.0 /* * fs/partitions/ultrix.c * * Code extracted from drivers/block/genhd.c * * Re-organised Jul 1999 Russell King */ #include "check.h" int ultrix_partition(struct parsed_partitions *state) { int i; Sector sect; unsigned char *data; struct ultrix_disklabel { s32 pt_magic; /* magic no. indicating part. info exits */ s32 pt_valid; /* set by driver if pt is current */ struct pt_info { s32 pi_nblocks; /* no. of sectors */ u32 pi_blkoff; /* block offset for start */ } pt_part[8]; } *label; #define PT_MAGIC 0x032957 /* Partition magic number */ #define PT_VALID 1 /* Indicates if struct is valid */ data = read_part_sector(state, (16384 - sizeof(*label))/512, §); if (!data) return -1; label = (struct ultrix_disklabel *)(data + 512 - sizeof(*label)); if (label->pt_magic == PT_MAGIC && label->pt_valid == PT_VALID) { for (i=0; i<8; i++) if (label->pt_part[i].pi_nblocks) put_partition(state, i+1, label->pt_part[i].pi_blkoff, label->pt_part[i].pi_nblocks); put_dev_sector(sect); strlcat(state->pp_buf, "\n", PAGE_SIZE); return 1; } else { put_dev_sector(sect); return 0; } } |
| 138 1 479 115 1 1 318 1 234 4 2 113 426 336 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2018 Red Hat, Inc. * All rights reserved. */ #ifndef __LIBXFS_AG_H #define __LIBXFS_AG_H 1 #include "xfs_group.h" struct xfs_mount; struct xfs_trans; struct xfs_perag; /* * Per-ag infrastructure */ /* per-AG block reservation data structures*/ struct xfs_ag_resv { /* number of blocks originally reserved here */ xfs_extlen_t ar_orig_reserved; /* number of blocks reserved here */ xfs_extlen_t ar_reserved; /* number of blocks originally asked for */ xfs_extlen_t ar_asked; }; /* * Per-ag incore structure, copies of information in agf and agi, to improve the * performance of allocation group selection. */ struct xfs_perag { struct xfs_group pag_group; unsigned long pag_opstate; uint8_t pagf_bno_level; /* # of levels in bno btree */ uint8_t pagf_cnt_level; /* # of levels in cnt btree */ uint8_t pagf_rmap_level;/* # of levels in rmap btree */ uint32_t pagf_flcount; /* count of blocks in freelist */ xfs_extlen_t pagf_freeblks; /* total free blocks */ xfs_extlen_t pagf_longest; /* longest free space */ uint32_t pagf_btreeblks; /* # of blocks held in AGF btrees */ xfs_agino_t pagi_freecount; /* number of free inodes */ xfs_agino_t pagi_count; /* number of allocated inodes */ /* * Inode allocation search lookup optimisation. * If the pagino matches, the search for new inodes * doesn't need to search the near ones again straight away */ xfs_agino_t pagl_pagino; xfs_agino_t pagl_leftrec; xfs_agino_t pagl_rightrec; uint8_t pagf_refcount_level; /* recount btree height */ /* Blocks reserved for all kinds of metadata. */ struct xfs_ag_resv pag_meta_resv; /* Blocks reserved for the reverse mapping btree. */ struct xfs_ag_resv pag_rmapbt_resv; /* Precalculated geometry info */ xfs_agino_t agino_min; xfs_agino_t agino_max; #ifdef __KERNEL__ /* -- kernel only structures below this line -- */ #ifdef CONFIG_XFS_ONLINE_REPAIR /* * Alternate btree heights so that online repair won't trip the write * verifiers while rebuilding the AG btrees. */ uint8_t pagf_repair_bno_level; uint8_t pagf_repair_cnt_level; uint8_t pagf_repair_refcount_level; uint8_t pagf_repair_rmap_level; #endif atomic_t pagf_fstrms; /* # of filestreams active in this AG */ spinlock_t pag_ici_lock; /* incore inode cache lock */ struct radix_tree_root pag_ici_root; /* incore inode cache root */ int pag_ici_reclaimable; /* reclaimable inodes */ unsigned long pag_ici_reclaim_cursor; /* reclaim restart point */ struct xfs_buf_cache pag_bcache; /* background prealloc block trimming */ struct delayed_work pag_blockgc_work; #endif /* __KERNEL__ */ }; static inline struct xfs_perag *to_perag(struct xfs_group *xg) { return container_of(xg, struct xfs_perag, pag_group); } static inline struct xfs_group *pag_group(struct xfs_perag *pag) { return &pag->pag_group; } static inline struct xfs_mount *pag_mount(const struct xfs_perag *pag) { return pag->pag_group.xg_mount; } static inline xfs_agnumber_t pag_agno(const struct xfs_perag *pag) { return pag->pag_group.xg_gno; } /* * Per-AG operational state. These are atomic flag bits. */ #define XFS_AGSTATE_AGF_INIT 0 #define XFS_AGSTATE_AGI_INIT 1 #define XFS_AGSTATE_PREFERS_METADATA 2 #define XFS_AGSTATE_ALLOWS_INODES 3 #define XFS_AGSTATE_AGFL_NEEDS_RESET 4 #define __XFS_AG_OPSTATE(name, NAME) \ static inline bool xfs_perag_ ## name (struct xfs_perag *pag) \ { \ return test_bit(XFS_AGSTATE_ ## NAME, &pag->pag_opstate); \ } __XFS_AG_OPSTATE(initialised_agf, AGF_INIT) __XFS_AG_OPSTATE(initialised_agi, AGI_INIT) __XFS_AG_OPSTATE(prefers_metadata, PREFERS_METADATA) __XFS_AG_OPSTATE(allows_inodes, ALLOWS_INODES) __XFS_AG_OPSTATE(agfl_needs_reset, AGFL_NEEDS_RESET) int xfs_initialize_perag(struct xfs_mount *mp, xfs_agnumber_t orig_agcount, xfs_agnumber_t new_agcount, xfs_rfsblock_t dcount, xfs_agnumber_t *maxagi); void xfs_free_perag_range(struct xfs_mount *mp, xfs_agnumber_t first_agno, xfs_agnumber_t end_agno); int xfs_initialize_perag_data(struct xfs_mount *mp, xfs_agnumber_t agno); int xfs_update_last_ag_size(struct xfs_mount *mp, xfs_agnumber_t prev_agcount); /* Passive AG references */ static inline struct xfs_perag * xfs_perag_get( struct xfs_mount *mp, xfs_agnumber_t agno) { return to_perag(xfs_group_get(mp, agno, XG_TYPE_AG)); } static inline struct xfs_perag * xfs_perag_hold( struct xfs_perag *pag) { return to_perag(xfs_group_hold(pag_group(pag))); } static inline void xfs_perag_put( struct xfs_perag *pag) { xfs_group_put(pag_group(pag)); } /* Active AG references */ static inline struct xfs_perag * xfs_perag_grab( struct xfs_mount *mp, xfs_agnumber_t agno) { return to_perag(xfs_group_grab(mp, agno, XG_TYPE_AG)); } static inline void xfs_perag_rele( struct xfs_perag *pag) { xfs_group_rele(pag_group(pag)); } static inline struct xfs_perag * xfs_perag_next_range( struct xfs_mount *mp, struct xfs_perag *pag, xfs_agnumber_t start_agno, xfs_agnumber_t end_agno) { return to_perag(xfs_group_next_range(mp, pag ? pag_group(pag) : NULL, start_agno, end_agno, XG_TYPE_AG)); } static inline struct xfs_perag * xfs_perag_next_from( struct xfs_mount *mp, struct xfs_perag *pag, xfs_agnumber_t start_agno) { return xfs_perag_next_range(mp, pag, start_agno, mp->m_sb.sb_agcount - 1); } static inline struct xfs_perag * xfs_perag_next( struct xfs_mount *mp, struct xfs_perag *pag) { return xfs_perag_next_from(mp, pag, 0); } /* * Per-ag geometry infomation and validation */ xfs_agblock_t xfs_ag_block_count(struct xfs_mount *mp, xfs_agnumber_t agno); void xfs_agino_range(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agino_t *first, xfs_agino_t *last); static inline bool xfs_verify_agbno(struct xfs_perag *pag, xfs_agblock_t agbno) { return xfs_verify_gbno(pag_group(pag), agbno); } static inline bool xfs_verify_agbext( struct xfs_perag *pag, xfs_agblock_t agbno, xfs_agblock_t len) { return xfs_verify_gbext(pag_group(pag), agbno, len); } /* * Verify that an AG inode number pointer neither points outside the AG * nor points at static metadata. */ static inline bool xfs_verify_agino(struct xfs_perag *pag, xfs_agino_t agino) { if (agino < pag->agino_min) return false; if (agino > pag->agino_max) return false; return true; } /* * Verify that an AG inode number pointer neither points outside the AG * nor points at static metadata, or is NULLAGINO. */ static inline bool xfs_verify_agino_or_null(struct xfs_perag *pag, xfs_agino_t agino) { if (agino == NULLAGINO) return true; return xfs_verify_agino(pag, agino); } static inline bool xfs_ag_contains_log(struct xfs_mount *mp, xfs_agnumber_t agno) { return mp->m_sb.sb_logstart > 0 && agno == XFS_FSB_TO_AGNO(mp, mp->m_sb.sb_logstart); } static inline struct xfs_perag * xfs_perag_next_wrap( struct xfs_perag *pag, xfs_agnumber_t *agno, xfs_agnumber_t stop_agno, xfs_agnumber_t restart_agno, xfs_agnumber_t wrap_agno) { struct xfs_mount *mp = pag_mount(pag); *agno = pag_agno(pag) + 1; xfs_perag_rele(pag); while (*agno != stop_agno) { if (*agno >= wrap_agno) { if (restart_agno >= stop_agno) break; *agno = restart_agno; } pag = xfs_perag_grab(mp, *agno); if (pag) return pag; (*agno)++; } return NULL; } /* * Iterate all AGs from start_agno through wrap_agno, then restart_agno through * (start_agno - 1). */ #define for_each_perag_wrap_range(mp, start_agno, restart_agno, wrap_agno, agno, pag) \ for ((agno) = (start_agno), (pag) = xfs_perag_grab((mp), (agno)); \ (pag) != NULL; \ (pag) = xfs_perag_next_wrap((pag), &(agno), (start_agno), \ (restart_agno), (wrap_agno))) /* * Iterate all AGs from start_agno through wrap_agno, then 0 through * (start_agno - 1). */ #define for_each_perag_wrap_at(mp, start_agno, wrap_agno, agno, pag) \ for_each_perag_wrap_range((mp), (start_agno), 0, (wrap_agno), (agno), (pag)) /* * Iterate all AGs from start_agno through to the end of the filesystem, then 0 * through (start_agno - 1). */ #define for_each_perag_wrap(mp, start_agno, agno, pag) \ for_each_perag_wrap_at((mp), (start_agno), (mp)->m_sb.sb_agcount, \ (agno), (pag)) struct aghdr_init_data { /* per ag data */ xfs_agblock_t agno; /* ag to init */ xfs_extlen_t agsize; /* new AG size */ struct list_head buffer_list; /* buffer writeback list */ xfs_rfsblock_t nfree; /* cumulative new free space */ /* per header data */ xfs_daddr_t daddr; /* header location */ size_t numblks; /* size of header */ const struct xfs_btree_ops *bc_ops; /* btree ops */ }; int xfs_ag_init_headers(struct xfs_mount *mp, struct aghdr_init_data *id); int xfs_ag_shrink_space(struct xfs_perag *pag, struct xfs_trans **tpp, xfs_extlen_t delta); int xfs_ag_extend_space(struct xfs_perag *pag, struct xfs_trans *tp, xfs_extlen_t len); int xfs_ag_get_geometry(struct xfs_perag *pag, struct xfs_ag_geometry *ageo); static inline xfs_fsblock_t xfs_agbno_to_fsb( struct xfs_perag *pag, xfs_agblock_t agbno) { return XFS_AGB_TO_FSB(pag_mount(pag), pag_agno(pag), agbno); } static inline xfs_daddr_t xfs_agbno_to_daddr( struct xfs_perag *pag, xfs_agblock_t agbno) { return XFS_AGB_TO_DADDR(pag_mount(pag), pag_agno(pag), agbno); } static inline xfs_ino_t xfs_agino_to_ino( struct xfs_perag *pag, xfs_agino_t agino) { return XFS_AGINO_TO_INO(pag_mount(pag), pag_agno(pag), agino); } #endif /* __LIBXFS_AG_H */ |
| 178 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MBCACHE_H #define _LINUX_MBCACHE_H #include <linux/hash.h> #include <linux/list_bl.h> #include <linux/list.h> #include <linux/atomic.h> #include <linux/fs.h> struct mb_cache; /* Cache entry flags */ enum { MBE_REFERENCED_B = 0, MBE_REUSABLE_B }; struct mb_cache_entry { /* List of entries in cache - protected by cache->c_list_lock */ struct list_head e_list; /* * Hash table list - protected by hash chain bitlock. The entry is * guaranteed to be hashed while e_refcnt > 0. */ struct hlist_bl_node e_hash_list; /* * Entry refcount. Once it reaches zero, entry is unhashed and freed. * While refcount > 0, the entry is guaranteed to stay in the hash and * e.g. mb_cache_entry_try_delete() will fail. */ atomic_t e_refcnt; /* Key in hash - stable during lifetime of the entry */ u32 e_key; unsigned long e_flags; /* User provided value - stable during lifetime of the entry */ u64 e_value; }; struct mb_cache *mb_cache_create(int bucket_bits); void mb_cache_destroy(struct mb_cache *cache); int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key, u64 value, bool reusable); void __mb_cache_entry_free(struct mb_cache *cache, struct mb_cache_entry *entry); void mb_cache_entry_wait_unused(struct mb_cache_entry *entry); static inline void mb_cache_entry_put(struct mb_cache *cache, struct mb_cache_entry *entry) { unsigned int cnt = atomic_dec_return(&entry->e_refcnt); if (cnt > 0) { if (cnt <= 2) wake_up_var(&entry->e_refcnt); return; } __mb_cache_entry_free(cache, entry); } struct mb_cache_entry *mb_cache_entry_delete_or_get(struct mb_cache *cache, u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key, u64 value); struct mb_cache_entry *mb_cache_entry_find_first(struct mb_cache *cache, u32 key); struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache, struct mb_cache_entry *entry); void mb_cache_entry_touch(struct mb_cache *cache, struct mb_cache_entry *entry); #endif /* _LINUX_MBCACHE_H */ |
| 117 10 93 48 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 | #ifndef _BCACHEFS_RECOVERY_PASSES_H #define _BCACHEFS_RECOVERY_PASSES_H extern const char * const bch2_recovery_passes[]; extern const struct bch_sb_field_ops bch_sb_field_ops_recovery_passes; u64 bch2_recovery_passes_to_stable(u64 v); u64 bch2_recovery_passes_from_stable(u64 v); u64 bch2_fsck_recovery_passes(void); void bch2_recovery_pass_set_no_ratelimit(struct bch_fs *, enum bch_recovery_pass); enum bch_run_recovery_pass_flags { RUN_RECOVERY_PASS_nopersistent = BIT(0), RUN_RECOVERY_PASS_ratelimit = BIT(1), }; static inline bool go_rw_in_recovery(struct bch_fs *c) { return (c->journal_keys.nr || !c->opts.read_only || !c->sb.clean || c->opts.recovery_passes || (c->opts.fsck && !(c->sb.features & BIT_ULL(BCH_FEATURE_no_alloc_info)))); } int bch2_run_print_explicit_recovery_pass(struct bch_fs *, enum bch_recovery_pass); int __bch2_run_explicit_recovery_pass(struct bch_fs *, struct printbuf *, enum bch_recovery_pass, enum bch_run_recovery_pass_flags); int bch2_run_explicit_recovery_pass(struct bch_fs *, struct printbuf *, enum bch_recovery_pass, enum bch_run_recovery_pass_flags); int bch2_require_recovery_pass(struct bch_fs *, struct printbuf *, enum bch_recovery_pass); int bch2_run_online_recovery_passes(struct bch_fs *, u64); int bch2_run_recovery_passes(struct bch_fs *, enum bch_recovery_pass); void bch2_recovery_pass_status_to_text(struct printbuf *, struct bch_fs *); void bch2_fs_recovery_passes_init(struct bch_fs *); #endif /* _BCACHEFS_RECOVERY_PASSES_H */ |
| 52 51 267 219 51 4 3 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 | // SPDX-License-Identifier: GPL-2.0 /* * Supplementary group IDs */ #include <linux/cred.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/sort.h> #include <linux/syscalls.h> #include <linux/user_namespace.h> #include <linux/vmalloc.h> #include <linux/uaccess.h> struct group_info *groups_alloc(int gidsetsize) { struct group_info *gi; gi = kvmalloc(struct_size(gi, gid, gidsetsize), GFP_KERNEL_ACCOUNT); if (!gi) return NULL; refcount_set(&gi->usage, 1); gi->ngroups = gidsetsize; return gi; } EXPORT_SYMBOL(groups_alloc); void groups_free(struct group_info *group_info) { kvfree(group_info); } EXPORT_SYMBOL(groups_free); /* export the group_info to a user-space array */ static int groups_to_user(gid_t __user *grouplist, const struct group_info *group_info) { struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; for (i = 0; i < count; i++) { gid_t gid; gid = from_kgid_munged(user_ns, group_info->gid[i]); if (put_user(gid, grouplist+i)) return -EFAULT; } return 0; } /* fill a group_info from a user-space array - it must be allocated already */ static int groups_from_user(struct group_info *group_info, gid_t __user *grouplist) { struct user_namespace *user_ns = current_user_ns(); int i; unsigned int count = group_info->ngroups; for (i = 0; i < count; i++) { gid_t gid; kgid_t kgid; if (get_user(gid, grouplist+i)) return -EFAULT; kgid = make_kgid(user_ns, gid); if (!gid_valid(kgid)) return -EINVAL; group_info->gid[i] = kgid; } return 0; } static int gid_cmp(const void *_a, const void *_b) { kgid_t a = *(kgid_t *)_a; kgid_t b = *(kgid_t *)_b; return gid_gt(a, b) - gid_lt(a, b); } void groups_sort(struct group_info *group_info) { sort(group_info->gid, group_info->ngroups, sizeof(*group_info->gid), gid_cmp, NULL); } EXPORT_SYMBOL(groups_sort); /* a simple bsearch */ int groups_search(const struct group_info *group_info, kgid_t grp) { unsigned int left, right; if (!group_info) return 0; left = 0; right = group_info->ngroups; while (left < right) { unsigned int mid = (left+right)/2; if (gid_gt(grp, group_info->gid[mid])) left = mid + 1; else if (gid_lt(grp, group_info->gid[mid])) right = mid; else return 1; } return 0; } /** * set_groups - Change a group subscription in a set of credentials * @new: The newly prepared set of credentials to alter * @group_info: The group list to install */ void set_groups(struct cred *new, struct group_info *group_info) { put_group_info(new->group_info); get_group_info(group_info); new->group_info = group_info; } EXPORT_SYMBOL(set_groups); /** * set_current_groups - Change current's group subscription * @group_info: The group list to impose * * Validate a group subscription and, if valid, impose it upon current's task * security record. */ int set_current_groups(struct group_info *group_info) { struct cred *new; const struct cred *old; int retval; new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); set_groups(new, group_info); retval = security_task_fix_setgroups(new, old); if (retval < 0) goto error; return commit_creds(new); error: abort_creds(new); return retval; } EXPORT_SYMBOL(set_current_groups); SYSCALL_DEFINE2(getgroups, int, gidsetsize, gid_t __user *, grouplist) { const struct cred *cred = current_cred(); int i; if (gidsetsize < 0) return -EINVAL; /* no need to grab task_lock here; it cannot change */ i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } if (groups_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: return i; } bool may_setgroups(void) { struct user_namespace *user_ns = current_user_ns(); return ns_capable_setid(user_ns, CAP_SETGID) && userns_may_setgroups(user_ns); } /* * SMP: Our groups are copy-on-write. We can set them safely * without another task interfering. */ SYSCALL_DEFINE2(setgroups, int, gidsetsize, gid_t __user *, grouplist) { struct group_info *group_info; int retval; if (!may_setgroups()) return -EPERM; if ((unsigned)gidsetsize > NGROUPS_MAX) return -EINVAL; group_info = groups_alloc(gidsetsize); if (!group_info) return -ENOMEM; retval = groups_from_user(group_info, grouplist); if (retval) { put_group_info(group_info); return retval; } groups_sort(group_info); retval = set_current_groups(group_info); put_group_info(group_info); return retval; } /* * Check whether we're fsgid/egid or in the supplemental group.. */ int in_group_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; if (!gid_eq(grp, cred->fsgid)) retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_group_p); int in_egroup_p(kgid_t grp) { const struct cred *cred = current_cred(); int retval = 1; if (!gid_eq(grp, cred->egid)) retval = groups_search(cred->group_info, grp); return retval; } EXPORT_SYMBOL(in_egroup_p); |
| 31 31 30 31 31 31 11 31 31 31 31 31 30 31 31 17 24 19 31 11 30 16 31 31 31 31 31 31 30 31 31 31 11 20 31 30 31 30 31 31 30 31 31 31 11 31 31 31 30 31 31 31 31 20 20 20 37 37 37 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 | // 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 list_head dispatch; 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 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; u32 async_depth; 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; if (!node) return NULL; rq = rb_entry_rq(node); 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); } /* * 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; enum dd_prio prio; u8 ioprio_class; lockdep_assert_held(&dd->lock); if (!list_empty(&per_prio->dispatch)) { rq = list_first_entry(&per_prio->dispatch, struct request, queuelist); if (started_after(dd, rq, latest_start)) return NULL; list_del_init(&rq->queuelist); data_dir = rq_data_dir(rq); goto done; } /* * 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); done: ioprio_class = dd_rq_ioclass(rq); 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; } /* * 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); 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; } /* * Called by __blk_mq_alloc_request(). The shallow_depth value set by this * function is used by __blk_mq_get_tag(). */ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) { struct deadline_data *dd = data->q->elevator->elevator_data; /* Do not throttle synchronous reads. */ if (op_is_sync(opf) && !op_is_write(opf)) return; /* * Throttle asynchronous requests and writes such that these requests * do not block the allocation of synchronous requests. */ data->shallow_depth = dd->async_depth; } /* Called by blk_mq_update_nr_requests(). */ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct deadline_data *dd = q->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; dd->async_depth = q->nr_requests; sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, 1); } /* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */ static int dd_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { dd_depth_updated(hctx); return 0; } 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; for (prio = 0; prio <= DD_PRIO_MAX; prio++) { struct dd_per_prio *per_prio = &dd->per_prio[prio]; INIT_LIST_HEAD(&per_prio->dispatch); 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; 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, &per_prio->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->dispatch) || !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; 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_async_depth_show, dd->async_depth); 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_async_depth_store, &dd->async_depth, 1, INT_MAX); 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(async_depth), 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_async_depth_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->async_depth); 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; } #define DEADLINE_DISPATCH_ATTR(prio) \ static void *deadline_dispatch##prio##_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->dispatch, *pos); \ } \ \ static void *deadline_dispatch##prio##_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->dispatch, pos); \ } \ \ static void deadline_dispatch##prio##_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##prio##_seq_ops = { \ .start = deadline_dispatch##prio##_start, \ .next = deadline_dispatch##prio##_next, \ .stop = deadline_dispatch##prio##_stop, \ .show = blk_mq_debugfs_rq_show, \ } DEADLINE_DISPATCH_ATTR(0); DEADLINE_DISPATCH_ATTR(1); DEADLINE_DISPATCH_ATTR(2); #undef DEADLINE_DISPATCH_ATTR #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}, {"async_depth", 0400, dd_async_depth_show}, {"dispatch0", 0400, .seq_ops = &deadline_dispatch0_seq_ops}, {"dispatch1", 0400, .seq_ops = &deadline_dispatch1_seq_ops}, {"dispatch2", 0400, .seq_ops = &deadline_dispatch2_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, .init_hctx = dd_init_hctx, }, #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"); |
| 352 6 1 16 115 1 846 849 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * bvec iterator * * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com> */ #ifndef __LINUX_BVEC_H #define __LINUX_BVEC_H #include <linux/highmem.h> #include <linux/bug.h> #include <linux/errno.h> #include <linux/limits.h> #include <linux/minmax.h> #include <linux/types.h> struct page; /** * struct bio_vec - a contiguous range of physical memory addresses * @bv_page: First page associated with the address range. * @bv_len: Number of bytes in the address range. * @bv_offset: Start of the address range relative to the start of @bv_page. * * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len: * * nth_page(@bv_page, n) == @bv_page + n * * This holds because page_is_mergeable() checks the above property. */ struct bio_vec { struct page *bv_page; unsigned int bv_len; unsigned int bv_offset; }; /** * bvec_set_page - initialize a bvec based off a struct page * @bv: bvec to initialize * @page: page the bvec should point to * @len: length of the bvec * @offset: offset into the page */ static inline void bvec_set_page(struct bio_vec *bv, struct page *page, unsigned int len, unsigned int offset) { bv->bv_page = page; bv->bv_len = len; bv->bv_offset = offset; } /** * bvec_set_folio - initialize a bvec based off a struct folio * @bv: bvec to initialize * @folio: folio the bvec should point to * @len: length of the bvec * @offset: offset into the folio */ static inline void bvec_set_folio(struct bio_vec *bv, struct folio *folio, size_t len, size_t offset) { unsigned long nr = offset / PAGE_SIZE; WARN_ON_ONCE(len > UINT_MAX); bvec_set_page(bv, folio_page(folio, nr), len, offset % PAGE_SIZE); } /** * bvec_set_virt - initialize a bvec based on a virtual address * @bv: bvec to initialize * @vaddr: virtual address to set the bvec to * @len: length of the bvec */ static inline void bvec_set_virt(struct bio_vec *bv, void *vaddr, unsigned int len) { bvec_set_page(bv, virt_to_page(vaddr), len, offset_in_page(vaddr)); } struct bvec_iter { sector_t bi_sector; /* device address in 512 byte sectors */ unsigned int bi_size; /* residual I/O count */ unsigned int bi_idx; /* current index into bvl_vec */ unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ } __packed __aligned(4); struct bvec_iter_all { struct bio_vec bv; int idx; unsigned done; }; /* * various member access, note that bio_data should of course not be used * on highmem page vectors */ #define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) /* multi-page (mp_bvec) helpers */ #define mp_bvec_iter_page(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_page) #define mp_bvec_iter_len(bvec, iter) \ min((iter).bi_size, \ __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done) #define mp_bvec_iter_offset(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done) #define mp_bvec_iter_page_idx(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) / PAGE_SIZE) #define mp_bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = mp_bvec_iter_page((bvec), (iter)), \ .bv_len = mp_bvec_iter_len((bvec), (iter)), \ .bv_offset = mp_bvec_iter_offset((bvec), (iter)), \ }) /* For building single-page bvec in flight */ #define bvec_iter_offset(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) % PAGE_SIZE) #define bvec_iter_len(bvec, iter) \ min_t(unsigned, mp_bvec_iter_len((bvec), (iter)), \ PAGE_SIZE - bvec_iter_offset((bvec), (iter))) #define bvec_iter_page(bvec, iter) \ (mp_bvec_iter_page((bvec), (iter)) + \ mp_bvec_iter_page_idx((bvec), (iter))) #define bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = bvec_iter_page((bvec), (iter)), \ .bv_len = bvec_iter_len((bvec), (iter)), \ .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) static inline bool bvec_iter_advance(const struct bio_vec *bv, struct bvec_iter *iter, unsigned bytes) { unsigned int idx = iter->bi_idx; if (WARN_ONCE(bytes > iter->bi_size, "Attempted to advance past end of bvec iter\n")) { iter->bi_size = 0; return false; } iter->bi_size -= bytes; bytes += iter->bi_bvec_done; while (bytes && bytes >= bv[idx].bv_len) { bytes -= bv[idx].bv_len; idx++; } iter->bi_idx = idx; iter->bi_bvec_done = bytes; return true; } /* * A simpler version of bvec_iter_advance(), @bytes should not span * across multiple bvec entries, i.e. bytes <= bv[i->bi_idx].bv_len */ static inline void bvec_iter_advance_single(const struct bio_vec *bv, struct bvec_iter *iter, unsigned int bytes) { unsigned int done = iter->bi_bvec_done + bytes; if (done == bv[iter->bi_idx].bv_len) { done = 0; iter->bi_idx++; } iter->bi_bvec_done = done; iter->bi_size -= bytes; } #define for_each_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ bvec_iter_advance_single((bio_vec), &(iter), (bvl).bv_len)) #define for_each_mp_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = mp_bvec_iter_bvec((bio_vec), (iter))), 1); \ bvec_iter_advance_single((bio_vec), &(iter), (bvl).bv_len)) /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ { \ .bi_sector = 0, \ .bi_size = UINT_MAX, \ .bi_idx = 0, \ .bi_bvec_done = 0, \ } static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) { iter_all->done = 0; iter_all->idx = 0; return &iter_all->bv; } static inline void bvec_advance(const struct bio_vec *bvec, struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; if (iter_all->done) { bv->bv_page++; bv->bv_offset = 0; } else { bv->bv_page = bvec->bv_page + (bvec->bv_offset >> PAGE_SHIFT); bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); iter_all->done += bv->bv_len; if (iter_all->done == bvec->bv_len) { iter_all->idx++; iter_all->done = 0; } } /** * bvec_kmap_local - map a bvec into the kernel virtual address space * @bvec: bvec to map * * Must be called on single-page bvecs only. Call kunmap_local on the returned * address to unmap. */ static inline void *bvec_kmap_local(struct bio_vec *bvec) { return kmap_local_page(bvec->bv_page) + bvec->bv_offset; } /** * memcpy_from_bvec - copy data from a bvec * @bvec: bvec to copy from * * Must be called on single-page bvecs only. */ static inline void memcpy_from_bvec(char *to, struct bio_vec *bvec) { memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, bvec->bv_len); } /** * memcpy_to_bvec - copy data to a bvec * @bvec: bvec to copy to * * Must be called on single-page bvecs only. */ static inline void memcpy_to_bvec(struct bio_vec *bvec, const char *from) { memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, bvec->bv_len); } /** * memzero_bvec - zero all data in a bvec * @bvec: bvec to zero * * Must be called on single-page bvecs only. */ static inline void memzero_bvec(struct bio_vec *bvec) { memzero_page(bvec->bv_page, bvec->bv_offset, bvec->bv_len); } /** * bvec_virt - return the virtual address for a bvec * @bvec: bvec to return the virtual address for * * Note: the caller must ensure that @bvec->bv_page is not a highmem page. */ static inline void *bvec_virt(struct bio_vec *bvec) { WARN_ON_ONCE(PageHighMem(bvec->bv_page)); return page_address(bvec->bv_page) + bvec->bv_offset; } /** * bvec_phys - return the physical address for a bvec * @bvec: bvec to return the physical address for */ static inline phys_addr_t bvec_phys(const struct bio_vec *bvec) { return page_to_phys(bvec->bv_page) + bvec->bv_offset; } #endif /* __LINUX_BVEC_H */ |
| 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 | // SPDX-License-Identifier: GPL-2.0-only /* * drivers/net/veth.c * * Copyright (C) 2007 OpenVZ http://openvz.org, SWsoft Inc * * Author: Pavel Emelianov <xemul@openvz.org> * Ethtool interface from: Eric W. Biederman <ebiederm@xmission.com> * */ #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/ethtool.h> #include <linux/etherdevice.h> #include <linux/u64_stats_sync.h> #include <net/rtnetlink.h> #include <net/dst.h> #include <net/netdev_lock.h> #include <net/xfrm.h> #include <net/xdp.h> #include <linux/veth.h> #include <linux/module.h> #include <linux/bpf.h> #include <linux/filter.h> #include <linux/ptr_ring.h> #include <linux/bpf_trace.h> #include <linux/net_tstamp.h> #include <linux/skbuff_ref.h> #include <net/page_pool/helpers.h> #define DRV_NAME "veth" #define DRV_VERSION "1.0" #define VETH_XDP_FLAG BIT(0) #define VETH_RING_SIZE 256 #define VETH_XDP_HEADROOM (XDP_PACKET_HEADROOM + NET_IP_ALIGN) #define VETH_XDP_TX_BULK_SIZE 16 #define VETH_XDP_BATCH 16 struct veth_stats { u64 rx_drops; /* xdp */ u64 xdp_packets; u64 xdp_bytes; u64 xdp_redirect; u64 xdp_drops; u64 xdp_tx; u64 xdp_tx_err; u64 peer_tq_xdp_xmit; u64 peer_tq_xdp_xmit_err; }; struct veth_rq_stats { struct veth_stats vs; struct u64_stats_sync syncp; }; struct veth_rq { struct napi_struct xdp_napi; struct napi_struct __rcu *napi; /* points to xdp_napi when the latter is initialized */ struct net_device *dev; struct bpf_prog __rcu *xdp_prog; struct xdp_mem_info xdp_mem; struct veth_rq_stats stats; bool rx_notify_masked; struct ptr_ring xdp_ring; struct xdp_rxq_info xdp_rxq; struct page_pool *page_pool; }; struct veth_priv { struct net_device __rcu *peer; atomic64_t dropped; struct bpf_prog *_xdp_prog; struct veth_rq *rq; unsigned int requested_headroom; }; struct veth_xdp_tx_bq { struct xdp_frame *q[VETH_XDP_TX_BULK_SIZE]; unsigned int count; }; /* * ethtool interface */ struct veth_q_stat_desc { char desc[ETH_GSTRING_LEN]; size_t offset; }; #define VETH_RQ_STAT(m) offsetof(struct veth_stats, m) static const struct veth_q_stat_desc veth_rq_stats_desc[] = { { "xdp_packets", VETH_RQ_STAT(xdp_packets) }, { "xdp_bytes", VETH_RQ_STAT(xdp_bytes) }, { "drops", VETH_RQ_STAT(rx_drops) }, { "xdp_redirect", VETH_RQ_STAT(xdp_redirect) }, { "xdp_drops", VETH_RQ_STAT(xdp_drops) }, { "xdp_tx", VETH_RQ_STAT(xdp_tx) }, { "xdp_tx_errors", VETH_RQ_STAT(xdp_tx_err) }, }; #define VETH_RQ_STATS_LEN ARRAY_SIZE(veth_rq_stats_desc) static const struct veth_q_stat_desc veth_tq_stats_desc[] = { { "xdp_xmit", VETH_RQ_STAT(peer_tq_xdp_xmit) }, { "xdp_xmit_errors", VETH_RQ_STAT(peer_tq_xdp_xmit_err) }, }; #define VETH_TQ_STATS_LEN ARRAY_SIZE(veth_tq_stats_desc) static struct { const char string[ETH_GSTRING_LEN]; } ethtool_stats_keys[] = { { "peer_ifindex" }, }; struct veth_xdp_buff { struct xdp_buff xdp; struct sk_buff *skb; }; static int veth_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *cmd) { cmd->base.speed = SPEED_10000; cmd->base.duplex = DUPLEX_FULL; cmd->base.port = PORT_TP; cmd->base.autoneg = AUTONEG_DISABLE; return 0; } static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->version, DRV_VERSION, sizeof(info->version)); } static void veth_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { u8 *p = buf; int i, j; switch(stringset) { case ETH_SS_STATS: memcpy(p, ðtool_stats_keys, sizeof(ethtool_stats_keys)); p += sizeof(ethtool_stats_keys); for (i = 0; i < dev->real_num_rx_queues; i++) for (j = 0; j < VETH_RQ_STATS_LEN; j++) ethtool_sprintf(&p, "rx_queue_%u_%.18s", i, veth_rq_stats_desc[j].desc); for (i = 0; i < dev->real_num_tx_queues; i++) for (j = 0; j < VETH_TQ_STATS_LEN; j++) ethtool_sprintf(&p, "tx_queue_%u_%.18s", i, veth_tq_stats_desc[j].desc); page_pool_ethtool_stats_get_strings(p); break; } } static int veth_get_sset_count(struct net_device *dev, int sset) { switch (sset) { case ETH_SS_STATS: return ARRAY_SIZE(ethtool_stats_keys) + VETH_RQ_STATS_LEN * dev->real_num_rx_queues + VETH_TQ_STATS_LEN * dev->real_num_tx_queues + page_pool_ethtool_stats_get_count(); default: return -EOPNOTSUPP; } } static void veth_get_page_pool_stats(struct net_device *dev, u64 *data) { #ifdef CONFIG_PAGE_POOL_STATS struct veth_priv *priv = netdev_priv(dev); struct page_pool_stats pp_stats = {}; int i; for (i = 0; i < dev->real_num_rx_queues; i++) { if (!priv->rq[i].page_pool) continue; page_pool_get_stats(priv->rq[i].page_pool, &pp_stats); } page_pool_ethtool_stats_get(data, &pp_stats); #endif /* CONFIG_PAGE_POOL_STATS */ } static void veth_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); int i, j, idx, pp_idx; data[0] = peer ? peer->ifindex : 0; idx = 1; for (i = 0; i < dev->real_num_rx_queues; i++) { const struct veth_rq_stats *rq_stats = &priv->rq[i].stats; const void *stats_base = (void *)&rq_stats->vs; unsigned int start; size_t offset; do { start = u64_stats_fetch_begin(&rq_stats->syncp); for (j = 0; j < VETH_RQ_STATS_LEN; j++) { offset = veth_rq_stats_desc[j].offset; data[idx + j] = *(u64 *)(stats_base + offset); } } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); idx += VETH_RQ_STATS_LEN; } pp_idx = idx; if (!peer) goto page_pool_stats; rcv_priv = netdev_priv(peer); for (i = 0; i < peer->real_num_rx_queues; i++) { const struct veth_rq_stats *rq_stats = &rcv_priv->rq[i].stats; const void *base = (void *)&rq_stats->vs; unsigned int start, tx_idx = idx; size_t offset; tx_idx += (i % dev->real_num_tx_queues) * VETH_TQ_STATS_LEN; do { start = u64_stats_fetch_begin(&rq_stats->syncp); for (j = 0; j < VETH_TQ_STATS_LEN; j++) { offset = veth_tq_stats_desc[j].offset; data[tx_idx + j] += *(u64 *)(base + offset); } } while (u64_stats_fetch_retry(&rq_stats->syncp, start)); } pp_idx = idx + dev->real_num_tx_queues * VETH_TQ_STATS_LEN; page_pool_stats: veth_get_page_pool_stats(dev, &data[pp_idx]); } static void veth_get_channels(struct net_device *dev, struct ethtool_channels *channels) { channels->tx_count = dev->real_num_tx_queues; channels->rx_count = dev->real_num_rx_queues; channels->max_tx = dev->num_tx_queues; channels->max_rx = dev->num_rx_queues; } static int veth_set_channels(struct net_device *dev, struct ethtool_channels *ch); static const struct ethtool_ops veth_ethtool_ops = { .get_drvinfo = veth_get_drvinfo, .get_link = ethtool_op_get_link, .get_strings = veth_get_strings, .get_sset_count = veth_get_sset_count, .get_ethtool_stats = veth_get_ethtool_stats, .get_link_ksettings = veth_get_link_ksettings, .get_ts_info = ethtool_op_get_ts_info, .get_channels = veth_get_channels, .set_channels = veth_set_channels, }; /* general routines */ static bool veth_is_xdp_frame(void *ptr) { return (unsigned long)ptr & VETH_XDP_FLAG; } static struct xdp_frame *veth_ptr_to_xdp(void *ptr) { return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG); } static void *veth_xdp_to_ptr(struct xdp_frame *xdp) { return (void *)((unsigned long)xdp | VETH_XDP_FLAG); } static void veth_ptr_free(void *ptr) { if (veth_is_xdp_frame(ptr)) xdp_return_frame(veth_ptr_to_xdp(ptr)); else kfree_skb(ptr); } static void __veth_xdp_flush(struct veth_rq *rq) { /* Write ptr_ring before reading rx_notify_masked */ smp_mb(); if (!READ_ONCE(rq->rx_notify_masked) && napi_schedule_prep(&rq->xdp_napi)) { WRITE_ONCE(rq->rx_notify_masked, true); __napi_schedule(&rq->xdp_napi); } } static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb) { if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb))) return NETDEV_TX_BUSY; /* signal qdisc layer */ return NET_RX_SUCCESS; /* same as NETDEV_TX_OK */ } static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb, struct veth_rq *rq, bool xdp) { return __dev_forward_skb(dev, skb) ?: xdp ? veth_xdp_rx(rq, skb) : __netif_rx(skb); } /* return true if the specified skb has chances of GRO aggregation * Don't strive for accuracy, but try to avoid GRO overhead in the most * common scenarios. * When XDP is enabled, all traffic is considered eligible, as the xmit * device has TSO off. * When TSO is enabled on the xmit device, we are likely interested only * in UDP aggregation, explicitly check for that if the skb is suspected * - the sock_wfree destructor is used by UDP, ICMP and XDP sockets - * to belong to locally generated UDP traffic. */ static bool veth_skb_is_eligible_for_gro(const struct net_device *dev, const struct net_device *rcv, const struct sk_buff *skb) { return !(dev->features & NETIF_F_ALL_TSO) || (skb->destructor == sock_wfree && rcv->features & (NETIF_F_GRO_FRAGLIST | NETIF_F_GRO_UDP_FWD)); } static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); struct veth_rq *rq = NULL; struct netdev_queue *txq; struct net_device *rcv; int length = skb->len; bool use_napi = false; int ret, rxq; rcu_read_lock(); rcv = rcu_dereference(priv->peer); if (unlikely(!rcv) || !pskb_may_pull(skb, ETH_HLEN)) { kfree_skb(skb); goto drop; } rcv_priv = netdev_priv(rcv); rxq = skb_get_queue_mapping(skb); if (rxq < rcv->real_num_rx_queues) { rq = &rcv_priv->rq[rxq]; /* The napi pointer is available when an XDP program is * attached or when GRO is enabled * Don't bother with napi/GRO if the skb can't be aggregated */ use_napi = rcu_access_pointer(rq->napi) && veth_skb_is_eligible_for_gro(dev, rcv, skb); } skb_tx_timestamp(skb); ret = veth_forward_skb(rcv, skb, rq, use_napi); switch (ret) { case NET_RX_SUCCESS: /* same as NETDEV_TX_OK */ if (!use_napi) dev_sw_netstats_tx_add(dev, 1, length); else __veth_xdp_flush(rq); break; case NETDEV_TX_BUSY: /* If a qdisc is attached to our virtual device, returning * NETDEV_TX_BUSY is allowed. */ txq = netdev_get_tx_queue(dev, rxq); if (qdisc_txq_has_no_queue(txq)) { dev_kfree_skb_any(skb); goto drop; } /* Restore Eth hdr pulled by dev_forward_skb/eth_type_trans */ __skb_push(skb, ETH_HLEN); /* Depend on prior success packets started NAPI consumer via * __veth_xdp_flush(). Cancel TXQ stop if consumer stopped, * paired with empty check in veth_poll(). */ netif_tx_stop_queue(txq); smp_mb__after_atomic(); if (unlikely(__ptr_ring_empty(&rq->xdp_ring))) netif_tx_wake_queue(txq); break; case NET_RX_DROP: /* same as NET_XMIT_DROP */ drop: atomic64_inc(&priv->dropped); ret = NET_XMIT_DROP; break; default: net_crit_ratelimited("%s(%s): Invalid return code(%d)", __func__, dev->name, ret); } rcu_read_unlock(); return ret; } static void veth_stats_rx(struct veth_stats *result, struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int i; result->peer_tq_xdp_xmit_err = 0; result->xdp_packets = 0; result->xdp_tx_err = 0; result->xdp_bytes = 0; result->rx_drops = 0; for (i = 0; i < dev->num_rx_queues; i++) { u64 packets, bytes, drops, xdp_tx_err, peer_tq_xdp_xmit_err; struct veth_rq_stats *stats = &priv->rq[i].stats; unsigned int start; do { start = u64_stats_fetch_begin(&stats->syncp); peer_tq_xdp_xmit_err = stats->vs.peer_tq_xdp_xmit_err; xdp_tx_err = stats->vs.xdp_tx_err; packets = stats->vs.xdp_packets; bytes = stats->vs.xdp_bytes; drops = stats->vs.rx_drops; } while (u64_stats_fetch_retry(&stats->syncp, start)); result->peer_tq_xdp_xmit_err += peer_tq_xdp_xmit_err; result->xdp_tx_err += xdp_tx_err; result->xdp_packets += packets; result->xdp_bytes += bytes; result->rx_drops += drops; } } static void veth_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *tot) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; struct veth_stats rx; tot->tx_dropped = atomic64_read(&priv->dropped); dev_fetch_sw_netstats(tot, dev->tstats); veth_stats_rx(&rx, dev); tot->tx_dropped += rx.xdp_tx_err; tot->rx_dropped = rx.rx_drops + rx.peer_tq_xdp_xmit_err; tot->rx_bytes += rx.xdp_bytes; tot->rx_packets += rx.xdp_packets; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (peer) { struct rtnl_link_stats64 tot_peer = {}; dev_fetch_sw_netstats(&tot_peer, peer->tstats); tot->rx_bytes += tot_peer.tx_bytes; tot->rx_packets += tot_peer.tx_packets; veth_stats_rx(&rx, peer); tot->tx_dropped += rx.peer_tq_xdp_xmit_err; tot->rx_dropped += rx.xdp_tx_err; tot->tx_bytes += rx.xdp_bytes; tot->tx_packets += rx.xdp_packets; } rcu_read_unlock(); } /* fake multicast ability */ static void veth_set_multicast_list(struct net_device *dev) { } static int veth_select_rxq(struct net_device *dev) { return smp_processor_id() % dev->real_num_rx_queues; } static struct net_device *veth_peer_dev(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); /* Callers must be under RCU read side. */ return rcu_dereference(priv->peer); } static int veth_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags, bool ndo_xmit) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); int i, ret = -ENXIO, nxmit = 0; struct net_device *rcv; unsigned int max_len; struct veth_rq *rq; if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; rcu_read_lock(); rcv = rcu_dereference(priv->peer); if (unlikely(!rcv)) goto out; rcv_priv = netdev_priv(rcv); rq = &rcv_priv->rq[veth_select_rxq(rcv)]; /* The napi pointer is set if NAPI is enabled, which ensures that * xdp_ring is initialized on receive side and the peer device is up. */ if (!rcu_access_pointer(rq->napi)) goto out; max_len = rcv->mtu + rcv->hard_header_len + VLAN_HLEN; spin_lock(&rq->xdp_ring.producer_lock); for (i = 0; i < n; i++) { struct xdp_frame *frame = frames[i]; void *ptr = veth_xdp_to_ptr(frame); if (unlikely(xdp_get_frame_len(frame) > max_len || __ptr_ring_produce(&rq->xdp_ring, ptr))) break; nxmit++; } spin_unlock(&rq->xdp_ring.producer_lock); if (flags & XDP_XMIT_FLUSH) __veth_xdp_flush(rq); ret = nxmit; if (ndo_xmit) { u64_stats_update_begin(&rq->stats.syncp); rq->stats.vs.peer_tq_xdp_xmit += nxmit; rq->stats.vs.peer_tq_xdp_xmit_err += n - nxmit; u64_stats_update_end(&rq->stats.syncp); } out: rcu_read_unlock(); return ret; } static int veth_ndo_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags) { int err; err = veth_xdp_xmit(dev, n, frames, flags, true); if (err < 0) { struct veth_priv *priv = netdev_priv(dev); atomic64_add(n, &priv->dropped); } return err; } static void veth_xdp_flush_bq(struct veth_rq *rq, struct veth_xdp_tx_bq *bq) { int sent, i, err = 0, drops; sent = veth_xdp_xmit(rq->dev, bq->count, bq->q, 0, false); if (sent < 0) { err = sent; sent = 0; } for (i = sent; unlikely(i < bq->count); i++) xdp_return_frame(bq->q[i]); drops = bq->count - sent; trace_xdp_bulk_tx(rq->dev, sent, drops, err); u64_stats_update_begin(&rq->stats.syncp); rq->stats.vs.xdp_tx += sent; rq->stats.vs.xdp_tx_err += drops; u64_stats_update_end(&rq->stats.syncp); bq->count = 0; } static void veth_xdp_flush(struct veth_rq *rq, struct veth_xdp_tx_bq *bq) { struct veth_priv *rcv_priv, *priv = netdev_priv(rq->dev); struct net_device *rcv; struct veth_rq *rcv_rq; rcu_read_lock(); veth_xdp_flush_bq(rq, bq); rcv = rcu_dereference(priv->peer); if (unlikely(!rcv)) goto out; rcv_priv = netdev_priv(rcv); rcv_rq = &rcv_priv->rq[veth_select_rxq(rcv)]; /* xdp_ring is initialized on receive side? */ if (unlikely(!rcu_access_pointer(rcv_rq->xdp_prog))) goto out; __veth_xdp_flush(rcv_rq); out: rcu_read_unlock(); } static int veth_xdp_tx(struct veth_rq *rq, struct xdp_buff *xdp, struct veth_xdp_tx_bq *bq) { struct xdp_frame *frame = xdp_convert_buff_to_frame(xdp); if (unlikely(!frame)) return -EOVERFLOW; if (unlikely(bq->count == VETH_XDP_TX_BULK_SIZE)) veth_xdp_flush_bq(rq, bq); bq->q[bq->count++] = frame; return 0; } static struct xdp_frame *veth_xdp_rcv_one(struct veth_rq *rq, struct xdp_frame *frame, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { struct xdp_frame orig_frame; struct bpf_prog *xdp_prog; rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (likely(xdp_prog)) { struct veth_xdp_buff vxbuf; struct xdp_buff *xdp = &vxbuf.xdp; u32 act; xdp_convert_frame_to_buff(frame, xdp); xdp->rxq = &rq->xdp_rxq; vxbuf.skb = NULL; act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: if (xdp_update_frame_from_buff(xdp, frame)) goto err_xdp; break; case XDP_TX: orig_frame = *frame; xdp->rxq->mem.type = frame->mem_type; if (unlikely(veth_xdp_tx(rq, xdp, bq) < 0)) { trace_xdp_exception(rq->dev, xdp_prog, act); frame = &orig_frame; stats->rx_drops++; goto err_xdp; } stats->xdp_tx++; rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: orig_frame = *frame; xdp->rxq->mem.type = frame->mem_type; if (xdp_do_redirect(rq->dev, xdp, xdp_prog)) { frame = &orig_frame; stats->rx_drops++; goto err_xdp; } stats->xdp_redirect++; rcu_read_unlock(); goto xdp_xmit; default: bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); fallthrough; case XDP_DROP: stats->xdp_drops++; goto err_xdp; } } rcu_read_unlock(); return frame; err_xdp: rcu_read_unlock(); xdp_return_frame(frame); xdp_xmit: return NULL; } /* frames array contains VETH_XDP_BATCH at most */ static void veth_xdp_rcv_bulk_skb(struct veth_rq *rq, void **frames, int n_xdpf, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { void *skbs[VETH_XDP_BATCH]; int i; if (unlikely(!napi_skb_cache_get_bulk(skbs, n_xdpf))) { for (i = 0; i < n_xdpf; i++) xdp_return_frame(frames[i]); stats->rx_drops += n_xdpf; return; } for (i = 0; i < n_xdpf; i++) { struct sk_buff *skb = skbs[i]; skb = __xdp_build_skb_from_frame(frames[i], skb, rq->dev); if (!skb) { xdp_return_frame(frames[i]); stats->rx_drops++; continue; } napi_gro_receive(&rq->xdp_napi, skb); } } static void veth_xdp_get(struct xdp_buff *xdp) { struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); int i; get_page(virt_to_page(xdp->data)); if (likely(!xdp_buff_has_frags(xdp))) return; for (i = 0; i < sinfo->nr_frags; i++) __skb_frag_ref(&sinfo->frags[i]); } static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, struct xdp_buff *xdp, struct sk_buff **pskb) { struct sk_buff *skb = *pskb; u32 frame_sz; if (skb_shared(skb) || skb_head_is_locked(skb) || skb_shinfo(skb)->nr_frags || skb_headroom(skb) < XDP_PACKET_HEADROOM) { if (skb_pp_cow_data(rq->page_pool, pskb, XDP_PACKET_HEADROOM)) goto drop; skb = *pskb; } /* SKB "head" area always have tailroom for skb_shared_info */ frame_sz = skb_end_pointer(skb) - skb->head; frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); xdp_init_buff(xdp, frame_sz, &rq->xdp_rxq); xdp_prepare_buff(xdp, skb->head, skb_headroom(skb), skb_headlen(skb), true); if (skb_is_nonlinear(skb)) { skb_shinfo(skb)->xdp_frags_size = skb->data_len; xdp_buff_set_frags_flag(xdp); } else { xdp_buff_clear_frags_flag(xdp); } *pskb = skb; return 0; drop: consume_skb(skb); *pskb = NULL; return -ENOMEM; } static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { void *orig_data, *orig_data_end; struct bpf_prog *xdp_prog; struct veth_xdp_buff vxbuf; struct xdp_buff *xdp = &vxbuf.xdp; u32 act, metalen; int off; skb_prepare_for_gro(skb); rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (unlikely(!xdp_prog)) { rcu_read_unlock(); goto out; } __skb_push(skb, skb->data - skb_mac_header(skb)); if (veth_convert_skb_to_xdp_buff(rq, xdp, &skb)) goto drop; vxbuf.skb = skb; orig_data = xdp->data; orig_data_end = xdp->data_end; act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: break; case XDP_TX: veth_xdp_get(xdp); consume_skb(skb); xdp->rxq->mem = rq->xdp_mem; if (unlikely(veth_xdp_tx(rq, xdp, bq) < 0)) { trace_xdp_exception(rq->dev, xdp_prog, act); stats->rx_drops++; goto err_xdp; } stats->xdp_tx++; rcu_read_unlock(); goto xdp_xmit; case XDP_REDIRECT: veth_xdp_get(xdp); consume_skb(skb); xdp->rxq->mem = rq->xdp_mem; if (xdp_do_redirect(rq->dev, xdp, xdp_prog)) { stats->rx_drops++; goto err_xdp; } stats->xdp_redirect++; rcu_read_unlock(); goto xdp_xmit; default: bpf_warn_invalid_xdp_action(rq->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception(rq->dev, xdp_prog, act); fallthrough; case XDP_DROP: stats->xdp_drops++; goto xdp_drop; } rcu_read_unlock(); /* check if bpf_xdp_adjust_head was used */ off = orig_data - xdp->data; if (off > 0) __skb_push(skb, off); else if (off < 0) __skb_pull(skb, -off); skb_reset_mac_header(skb); /* check if bpf_xdp_adjust_tail was used */ off = xdp->data_end - orig_data_end; if (off != 0) __skb_put(skb, off); /* positive on grow, negative on shrink */ /* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers * (e.g. bpf_xdp_adjust_tail), we need to update data_len here. */ if (xdp_buff_has_frags(xdp)) skb->data_len = skb_shinfo(skb)->xdp_frags_size; else skb->data_len = 0; skb->protocol = eth_type_trans(skb, rq->dev); metalen = xdp->data - xdp->data_meta; if (metalen) skb_metadata_set(skb, metalen); out: return skb; drop: stats->rx_drops++; xdp_drop: rcu_read_unlock(); kfree_skb(skb); return NULL; err_xdp: rcu_read_unlock(); xdp_return_buff(xdp); xdp_xmit: return NULL; } static int veth_xdp_rcv(struct veth_rq *rq, int budget, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { struct veth_priv *priv = netdev_priv(rq->dev); int queue_idx = rq->xdp_rxq.queue_index; struct netdev_queue *peer_txq; struct net_device *peer_dev; int i, done = 0, n_xdpf = 0; void *xdpf[VETH_XDP_BATCH]; /* NAPI functions as RCU section */ peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; for (i = 0; i < budget; i++) { void *ptr = __ptr_ring_consume(&rq->xdp_ring); if (!ptr) break; if (veth_is_xdp_frame(ptr)) { /* ndo_xdp_xmit */ struct xdp_frame *frame = veth_ptr_to_xdp(ptr); stats->xdp_bytes += xdp_get_frame_len(frame); frame = veth_xdp_rcv_one(rq, frame, bq, stats); if (frame) { /* XDP_PASS */ xdpf[n_xdpf++] = frame; if (n_xdpf == VETH_XDP_BATCH) { veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, bq, stats); n_xdpf = 0; } } } else { /* ndo_start_xmit */ struct sk_buff *skb = ptr; stats->xdp_bytes += skb->len; skb = veth_xdp_rcv_skb(rq, skb, bq, stats); if (skb) { if (skb_shared(skb) || skb_unclone(skb, GFP_ATOMIC)) netif_receive_skb(skb); else napi_gro_receive(&rq->xdp_napi, skb); } } done++; } if (n_xdpf) veth_xdp_rcv_bulk_skb(rq, xdpf, n_xdpf, bq, stats); u64_stats_update_begin(&rq->stats.syncp); rq->stats.vs.xdp_redirect += stats->xdp_redirect; rq->stats.vs.xdp_bytes += stats->xdp_bytes; rq->stats.vs.xdp_drops += stats->xdp_drops; rq->stats.vs.rx_drops += stats->rx_drops; rq->stats.vs.xdp_packets += done; u64_stats_update_end(&rq->stats.syncp); if (peer_txq && unlikely(netif_tx_queue_stopped(peer_txq))) netif_tx_wake_queue(peer_txq); return done; } static int veth_poll(struct napi_struct *napi, int budget) { struct veth_rq *rq = container_of(napi, struct veth_rq, xdp_napi); struct veth_stats stats = {}; struct veth_xdp_tx_bq bq; int done; bq.count = 0; xdp_set_return_frame_no_direct(); done = veth_xdp_rcv(rq, budget, &bq, &stats); if (stats.xdp_redirect > 0) xdp_do_flush(); if (done < budget && napi_complete_done(napi, done)) { /* Write rx_notify_masked before reading ptr_ring */ smp_store_mb(rq->rx_notify_masked, false); if (unlikely(!__ptr_ring_empty(&rq->xdp_ring))) { if (napi_schedule_prep(&rq->xdp_napi)) { WRITE_ONCE(rq->rx_notify_masked, true); __napi_schedule(&rq->xdp_napi); } } } if (stats.xdp_tx > 0) veth_xdp_flush(rq, &bq); xdp_clear_return_frame_no_direct(); return done; } static int veth_create_page_pool(struct veth_rq *rq) { struct page_pool_params pp_params = { .order = 0, .pool_size = VETH_RING_SIZE, .nid = NUMA_NO_NODE, .dev = &rq->dev->dev, }; rq->page_pool = page_pool_create(&pp_params); if (IS_ERR(rq->page_pool)) { int err = PTR_ERR(rq->page_pool); rq->page_pool = NULL; return err; } return 0; } static int __veth_napi_enable_range(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int err, i; for (i = start; i < end; i++) { err = veth_create_page_pool(&priv->rq[i]); if (err) goto err_page_pool; } for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; err = ptr_ring_init(&rq->xdp_ring, VETH_RING_SIZE, GFP_KERNEL); if (err) goto err_xdp_ring; } for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; napi_enable(&rq->xdp_napi); rcu_assign_pointer(priv->rq[i].napi, &priv->rq[i].xdp_napi); } return 0; err_xdp_ring: for (i--; i >= start; i--) ptr_ring_cleanup(&priv->rq[i].xdp_ring, veth_ptr_free); i = end; err_page_pool: for (i--; i >= start; i--) { page_pool_destroy(priv->rq[i].page_pool); priv->rq[i].page_pool = NULL; } return err; } static int __veth_napi_enable(struct net_device *dev) { return __veth_napi_enable_range(dev, 0, dev->real_num_rx_queues); } static void veth_napi_del_range(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; rcu_assign_pointer(priv->rq[i].napi, NULL); napi_disable(&rq->xdp_napi); __netif_napi_del(&rq->xdp_napi); } synchronize_net(); for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; rq->rx_notify_masked = false; ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free); } for (i = start; i < end; i++) { page_pool_destroy(priv->rq[i].page_pool); priv->rq[i].page_pool = NULL; } } static void veth_napi_del(struct net_device *dev) { veth_napi_del_range(dev, 0, dev->real_num_rx_queues); } static bool veth_gro_requested(const struct net_device *dev) { return !!(dev->wanted_features & NETIF_F_GRO); } static int veth_enable_xdp_range(struct net_device *dev, int start, int end, bool napi_already_on) { struct veth_priv *priv = netdev_priv(dev); int err, i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; if (!napi_already_on) netif_napi_add(dev, &rq->xdp_napi, veth_poll); err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i, rq->xdp_napi.napi_id); if (err < 0) goto err_rxq_reg; err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL); if (err < 0) goto err_reg_mem; /* Save original mem info as it can be overwritten */ rq->xdp_mem = rq->xdp_rxq.mem; } return 0; err_reg_mem: xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq); err_rxq_reg: for (i--; i >= start; i--) { struct veth_rq *rq = &priv->rq[i]; xdp_rxq_info_unreg(&rq->xdp_rxq); if (!napi_already_on) netif_napi_del(&rq->xdp_napi); } return err; } static void veth_disable_xdp_range(struct net_device *dev, int start, int end, bool delete_napi) { struct veth_priv *priv = netdev_priv(dev); int i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; rq->xdp_rxq.mem = rq->xdp_mem; xdp_rxq_info_unreg(&rq->xdp_rxq); if (delete_napi) netif_napi_del(&rq->xdp_napi); } } static int veth_enable_xdp(struct net_device *dev) { bool napi_already_on = veth_gro_requested(dev) && (dev->flags & IFF_UP); struct veth_priv *priv = netdev_priv(dev); int err, i; if (!xdp_rxq_info_is_reg(&priv->rq[0].xdp_rxq)) { err = veth_enable_xdp_range(dev, 0, dev->real_num_rx_queues, napi_already_on); if (err) return err; if (!napi_already_on) { err = __veth_napi_enable(dev); if (err) { veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, true); return err; } } } for (i = 0; i < dev->real_num_rx_queues; i++) { rcu_assign_pointer(priv->rq[i].xdp_prog, priv->_xdp_prog); rcu_assign_pointer(priv->rq[i].napi, &priv->rq[i].xdp_napi); } return 0; } static void veth_disable_xdp(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int i; for (i = 0; i < dev->real_num_rx_queues; i++) rcu_assign_pointer(priv->rq[i].xdp_prog, NULL); if (!netif_running(dev) || !veth_gro_requested(dev)) veth_napi_del(dev); veth_disable_xdp_range(dev, 0, dev->real_num_rx_queues, false); } static int veth_napi_enable_range(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int err, i; for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; netif_napi_add(dev, &rq->xdp_napi, veth_poll); } err = __veth_napi_enable_range(dev, start, end); if (err) { for (i = start; i < end; i++) { struct veth_rq *rq = &priv->rq[i]; netif_napi_del(&rq->xdp_napi); } return err; } return err; } static int veth_napi_enable(struct net_device *dev) { return veth_napi_enable_range(dev, 0, dev->real_num_rx_queues); } static void veth_disable_range_safe(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); if (start >= end) return; if (priv->_xdp_prog) { veth_napi_del_range(dev, start, end); veth_disable_xdp_range(dev, start, end, false); } else if (veth_gro_requested(dev)) { veth_napi_del_range(dev, start, end); } } static int veth_enable_range_safe(struct net_device *dev, int start, int end) { struct veth_priv *priv = netdev_priv(dev); int err; if (start >= end) return 0; if (priv->_xdp_prog) { /* these channels are freshly initialized, napi is not on there even * when GRO is requeste */ err = veth_enable_xdp_range(dev, start, end, false); if (err) return err; err = __veth_napi_enable_range(dev, start, end); if (err) { /* on error always delete the newly added napis */ veth_disable_xdp_range(dev, start, end, true); return err; } } else if (veth_gro_requested(dev)) { return veth_napi_enable_range(dev, start, end); } return 0; } static void veth_set_xdp_features(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; peer = rtnl_dereference(priv->peer); if (peer && peer->real_num_tx_queues <= dev->real_num_rx_queues) { struct veth_priv *priv_peer = netdev_priv(peer); xdp_features_t val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_RX_SG; if (priv_peer->_xdp_prog || veth_gro_requested(peer)) val |= NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_NDO_XMIT_SG; xdp_set_features_flag(dev, val); } else { xdp_clear_features_flag(dev); } } static int veth_set_channels(struct net_device *dev, struct ethtool_channels *ch) { struct veth_priv *priv = netdev_priv(dev); unsigned int old_rx_count, new_rx_count; struct veth_priv *peer_priv; struct net_device *peer; int err; /* sanity check. Upper bounds are already enforced by the caller */ if (!ch->rx_count || !ch->tx_count) return -EINVAL; /* avoid braking XDP, if that is enabled */ peer = rtnl_dereference(priv->peer); peer_priv = peer ? netdev_priv(peer) : NULL; if (priv->_xdp_prog && peer && ch->rx_count < peer->real_num_tx_queues) return -EINVAL; if (peer && peer_priv && peer_priv->_xdp_prog && ch->tx_count > peer->real_num_rx_queues) return -EINVAL; old_rx_count = dev->real_num_rx_queues; new_rx_count = ch->rx_count; if (netif_running(dev)) { /* turn device off */ netif_carrier_off(dev); if (peer) netif_carrier_off(peer); /* try to allocate new resurces, as needed*/ err = veth_enable_range_safe(dev, old_rx_count, new_rx_count); if (err) goto out; } err = netif_set_real_num_rx_queues(dev, ch->rx_count); if (err) goto revert; err = netif_set_real_num_tx_queues(dev, ch->tx_count); if (err) { int err2 = netif_set_real_num_rx_queues(dev, old_rx_count); /* this error condition could happen only if rx and tx change * in opposite directions (e.g. tx nr raises, rx nr decreases) * and we can't do anything to fully restore the original * status */ if (err2) pr_warn("Can't restore rx queues config %d -> %d %d", new_rx_count, old_rx_count, err2); else goto revert; } out: if (netif_running(dev)) { /* note that we need to swap the arguments WRT the enable part * to identify the range we have to disable */ veth_disable_range_safe(dev, new_rx_count, old_rx_count); netif_carrier_on(dev); if (peer) netif_carrier_on(peer); } /* update XDP supported features */ veth_set_xdp_features(dev); if (peer) veth_set_xdp_features(peer); return err; revert: new_rx_count = old_rx_count; old_rx_count = ch->rx_count; goto out; } static int veth_open(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); int err; if (!peer) return -ENOTCONN; if (priv->_xdp_prog) { err = veth_enable_xdp(dev); if (err) return err; } else if (veth_gro_requested(dev)) { err = veth_napi_enable(dev); if (err) return err; } if (peer->flags & IFF_UP) { netif_carrier_on(dev); netif_carrier_on(peer); } veth_set_xdp_features(dev); return 0; } static int veth_close(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); netif_carrier_off(dev); if (peer) netif_carrier_off(peer); if (priv->_xdp_prog) veth_disable_xdp(dev); else if (veth_gro_requested(dev)) veth_napi_del(dev); return 0; } static int is_valid_veth_mtu(int mtu) { return mtu >= ETH_MIN_MTU && mtu <= ETH_MAX_MTU; } static int veth_alloc_queues(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); int i; priv->rq = kvcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!priv->rq) return -ENOMEM; for (i = 0; i < dev->num_rx_queues; i++) { priv->rq[i].dev = dev; u64_stats_init(&priv->rq[i].stats.syncp); } return 0; } static void veth_free_queues(struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); kvfree(priv->rq); } static int veth_dev_init(struct net_device *dev) { netdev_lockdep_set_classes(dev); return veth_alloc_queues(dev); } static void veth_dev_free(struct net_device *dev) { veth_free_queues(dev); } #ifdef CONFIG_NET_POLL_CONTROLLER static void veth_poll_controller(struct net_device *dev) { /* veth only receives frames when its peer sends one * Since it has nothing to do with disabling irqs, we are guaranteed * never to have pending data when we poll for it so * there is nothing to do here. * * We need this though so netpoll recognizes us as an interface that * supports polling, which enables bridge devices in virt setups to * still use netconsole */ } #endif /* CONFIG_NET_POLL_CONTROLLER */ static int veth_get_iflink(const struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; int iflink; rcu_read_lock(); peer = rcu_dereference(priv->peer); iflink = peer ? READ_ONCE(peer->ifindex) : 0; rcu_read_unlock(); return iflink; } static netdev_features_t veth_fix_features(struct net_device *dev, netdev_features_t features) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; peer = rtnl_dereference(priv->peer); if (peer) { struct veth_priv *peer_priv = netdev_priv(peer); if (peer_priv->_xdp_prog) features &= ~NETIF_F_GSO_SOFTWARE; } return features; } static int veth_set_features(struct net_device *dev, netdev_features_t features) { netdev_features_t changed = features ^ dev->features; struct veth_priv *priv = netdev_priv(dev); struct net_device *peer; int err; if (!(changed & NETIF_F_GRO) || !(dev->flags & IFF_UP) || priv->_xdp_prog) return 0; peer = rtnl_dereference(priv->peer); if (features & NETIF_F_GRO) { err = veth_napi_enable(dev); if (err) return err; if (peer) xdp_features_set_redirect_target(peer, true); } else { if (peer) xdp_features_clear_redirect_target(peer); veth_napi_del(dev); } return 0; } static void veth_set_rx_headroom(struct net_device *dev, int new_hr) { struct veth_priv *peer_priv, *priv = netdev_priv(dev); struct net_device *peer; if (new_hr < 0) new_hr = 0; rcu_read_lock(); peer = rcu_dereference(priv->peer); if (unlikely(!peer)) goto out; peer_priv = netdev_priv(peer); priv->requested_headroom = new_hr; new_hr = max(priv->requested_headroom, peer_priv->requested_headroom); dev->needed_headroom = new_hr; peer->needed_headroom = new_hr; out: rcu_read_unlock(); } static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog, struct netlink_ext_ack *extack) { struct veth_priv *priv = netdev_priv(dev); struct bpf_prog *old_prog; struct net_device *peer; unsigned int max_mtu; int err; old_prog = priv->_xdp_prog; priv->_xdp_prog = prog; peer = rtnl_dereference(priv->peer); if (prog) { if (!peer) { NL_SET_ERR_MSG_MOD(extack, "Cannot set XDP when peer is detached"); err = -ENOTCONN; goto err; } max_mtu = SKB_WITH_OVERHEAD(PAGE_SIZE - VETH_XDP_HEADROOM) - peer->hard_header_len; /* Allow increasing the max_mtu if the program supports * XDP fragments. */ if (prog->aux->xdp_has_frags) max_mtu += PAGE_SIZE * MAX_SKB_FRAGS; if (peer->mtu > max_mtu) { NL_SET_ERR_MSG_MOD(extack, "Peer MTU is too large to set XDP"); err = -ERANGE; goto err; } if (dev->real_num_rx_queues < peer->real_num_tx_queues) { NL_SET_ERR_MSG_MOD(extack, "XDP expects number of rx queues not less than peer tx queues"); err = -ENOSPC; goto err; } if (dev->flags & IFF_UP) { err = veth_enable_xdp(dev); if (err) { NL_SET_ERR_MSG_MOD(extack, "Setup for XDP failed"); goto err; } } if (!old_prog) { peer->hw_features &= ~NETIF_F_GSO_SOFTWARE; peer->max_mtu = max_mtu; } xdp_features_set_redirect_target(peer, true); } if (old_prog) { if (!prog) { if (peer && !veth_gro_requested(dev)) xdp_features_clear_redirect_target(peer); if (dev->flags & IFF_UP) veth_disable_xdp(dev); if (peer) { peer->hw_features |= NETIF_F_GSO_SOFTWARE; peer->max_mtu = ETH_MAX_MTU; } } bpf_prog_put(old_prog); } if ((!!old_prog ^ !!prog) && peer) netdev_update_features(peer); return 0; err: priv->_xdp_prog = old_prog; return err; } static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp) { switch (xdp->command) { case XDP_SETUP_PROG: return veth_xdp_set(dev, xdp->prog, xdp->extack); default: return -EINVAL; } } static int veth_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) { struct veth_xdp_buff *_ctx = (void *)ctx; if (!_ctx->skb) return -ENODATA; *timestamp = skb_hwtstamps(_ctx->skb)->hwtstamp; return 0; } static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type) { struct veth_xdp_buff *_ctx = (void *)ctx; struct sk_buff *skb = _ctx->skb; if (!skb) return -ENODATA; *hash = skb_get_hash(skb); *rss_type = skb->l4_hash ? XDP_RSS_TYPE_L4_ANY : XDP_RSS_TYPE_NONE; return 0; } static int veth_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci) { const struct veth_xdp_buff *_ctx = (void *)ctx; const struct sk_buff *skb = _ctx->skb; int err; if (!skb) return -ENODATA; err = __vlan_hwaccel_get_tag(skb, vlan_tci); if (err) return err; *vlan_proto = skb->vlan_proto; return err; } static const struct net_device_ops veth_netdev_ops = { .ndo_init = veth_dev_init, .ndo_open = veth_open, .ndo_stop = veth_close, .ndo_start_xmit = veth_xmit, .ndo_get_stats64 = veth_get_stats64, .ndo_set_rx_mode = veth_set_multicast_list, .ndo_set_mac_address = eth_mac_addr, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = veth_poll_controller, #endif .ndo_get_iflink = veth_get_iflink, .ndo_fix_features = veth_fix_features, .ndo_set_features = veth_set_features, .ndo_features_check = passthru_features_check, .ndo_set_rx_headroom = veth_set_rx_headroom, .ndo_bpf = veth_xdp, .ndo_xdp_xmit = veth_ndo_xdp_xmit, .ndo_get_peer_dev = veth_peer_dev, }; static const struct xdp_metadata_ops veth_xdp_metadata_ops = { .xmo_rx_timestamp = veth_xdp_rx_timestamp, .xmo_rx_hash = veth_xdp_rx_hash, .xmo_rx_vlan_tag = veth_xdp_rx_vlan_tag, }; #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \ NETIF_F_RXCSUM | NETIF_F_SCTP_CRC | NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ENCAP_ALL | \ NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_STAG_RX ) static void veth_setup(struct net_device *dev) { ether_setup(dev); dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; dev->priv_flags |= IFF_NO_QUEUE; dev->priv_flags |= IFF_PHONY_HEADROOM; dev->priv_flags |= IFF_DISABLE_NETPOLL; dev->lltx = true; dev->netdev_ops = &veth_netdev_ops; dev->xdp_metadata_ops = &veth_xdp_metadata_ops; dev->ethtool_ops = &veth_ethtool_ops; dev->features |= VETH_FEATURES; dev->vlan_features = dev->features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX); dev->needs_free_netdev = true; dev->priv_destructor = veth_dev_free; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; dev->max_mtu = ETH_MAX_MTU; dev->hw_features = VETH_FEATURES; dev->hw_enc_features = VETH_FEATURES; dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE; netif_set_tso_max_size(dev, GSO_MAX_SIZE); } /* * netlink interface */ static int veth_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; } if (tb[IFLA_MTU]) { if (!is_valid_veth_mtu(nla_get_u32(tb[IFLA_MTU]))) return -EINVAL; } return 0; } static struct rtnl_link_ops veth_link_ops; static void veth_disable_gro(struct net_device *dev) { dev->features &= ~NETIF_F_GRO; dev->wanted_features &= ~NETIF_F_GRO; netdev_update_features(dev); } static int veth_init_queues(struct net_device *dev, struct nlattr *tb[]) { int err; if (!tb[IFLA_NUM_TX_QUEUES] && dev->num_tx_queues > 1) { err = netif_set_real_num_tx_queues(dev, 1); if (err) return err; } if (!tb[IFLA_NUM_RX_QUEUES] && dev->num_rx_queues > 1) { err = netif_set_real_num_rx_queues(dev, 1); if (err) return err; } return 0; } static int veth_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct net *peer_net = rtnl_newlink_peer_net(params); struct nlattr **data = params->data; struct nlattr **tb = params->tb; int err; struct net_device *peer; struct veth_priv *priv; char ifname[IFNAMSIZ]; struct nlattr *peer_tb[IFLA_MAX + 1], **tbp; unsigned char name_assign_type; struct ifinfomsg *ifmp; /* * create and register peer first */ if (data && data[VETH_INFO_PEER]) { struct nlattr *nla_peer = data[VETH_INFO_PEER]; ifmp = nla_data(nla_peer); rtnl_nla_parse_ifinfomsg(peer_tb, nla_peer, extack); tbp = peer_tb; } else { ifmp = NULL; tbp = tb; } if (ifmp && tbp[IFLA_IFNAME]) { nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ); name_assign_type = NET_NAME_USER; } else { snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d"); name_assign_type = NET_NAME_ENUM; } peer = rtnl_create_link(peer_net, ifname, name_assign_type, &veth_link_ops, tbp, extack); if (IS_ERR(peer)) return PTR_ERR(peer); if (!ifmp || !tbp[IFLA_ADDRESS]) eth_hw_addr_random(peer); if (ifmp && (dev->ifindex != 0)) peer->ifindex = ifmp->ifi_index; netif_inherit_tso_max(peer, dev); err = register_netdevice(peer); if (err < 0) goto err_register_peer; /* keep GRO disabled by default to be consistent with the established * veth behavior */ veth_disable_gro(peer); netif_carrier_off(peer); err = rtnl_configure_link(peer, ifmp, 0, NULL); if (err < 0) goto err_configure_peer; /* * register dev last * * note, that since we've registered new device the dev's name * should be re-allocated */ if (tb[IFLA_ADDRESS] == NULL) eth_hw_addr_random(dev); if (tb[IFLA_IFNAME]) nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); else snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d"); err = register_netdevice(dev); if (err < 0) goto err_register_dev; netif_carrier_off(dev); /* * tie the deviced together */ priv = netdev_priv(dev); rcu_assign_pointer(priv->peer, peer); err = veth_init_queues(dev, tb); if (err) goto err_queues; priv = netdev_priv(peer); rcu_assign_pointer(priv->peer, dev); err = veth_init_queues(peer, tb); if (err) goto err_queues; veth_disable_gro(dev); /* update XDP supported features */ veth_set_xdp_features(dev); veth_set_xdp_features(peer); return 0; err_queues: unregister_netdevice(dev); err_register_dev: /* nothing to do */ err_configure_peer: unregister_netdevice(peer); return err; err_register_peer: free_netdev(peer); return err; } static void veth_dellink(struct net_device *dev, struct list_head *head) { struct veth_priv *priv; struct net_device *peer; priv = netdev_priv(dev); peer = rtnl_dereference(priv->peer); /* Note : dellink() is called from default_device_exit_batch(), * before a rcu_synchronize() point. The devices are guaranteed * not being freed before one RCU grace period. */ RCU_INIT_POINTER(priv->peer, NULL); unregister_netdevice_queue(dev, head); if (peer) { priv = netdev_priv(peer); RCU_INIT_POINTER(priv->peer, NULL); unregister_netdevice_queue(peer, head); } } static const struct nla_policy veth_policy[VETH_INFO_MAX + 1] = { [VETH_INFO_PEER] = { .len = sizeof(struct ifinfomsg) }, }; static struct net *veth_get_link_net(const struct net_device *dev) { struct veth_priv *priv = netdev_priv(dev); struct net_device *peer = rtnl_dereference(priv->peer); return peer ? dev_net(peer) : dev_net(dev); } static unsigned int veth_get_num_queues(void) { /* enforce the same queue limit as rtnl_create_link */ int queues = num_possible_cpus(); if (queues > 4096) queues = 4096; return queues; } static struct rtnl_link_ops veth_link_ops = { .kind = DRV_NAME, .priv_size = sizeof(struct veth_priv), .setup = veth_setup, .validate = veth_validate, .newlink = veth_newlink, .dellink = veth_dellink, .policy = veth_policy, .peer_type = VETH_INFO_PEER, .maxtype = VETH_INFO_MAX, .get_link_net = veth_get_link_net, .get_num_tx_queues = veth_get_num_queues, .get_num_rx_queues = veth_get_num_queues, }; /* * init/fini */ static __init int veth_init(void) { return rtnl_link_register(&veth_link_ops); } static __exit void veth_exit(void) { rtnl_link_unregister(&veth_link_ops); } module_init(veth_init); module_exit(veth_exit); MODULE_DESCRIPTION("Virtual Ethernet Tunnel"); MODULE_LICENSE("GPL v2"); MODULE_ALIAS_RTNL_LINK(DRV_NAME); |
| 265 3 166 2 54 426 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef BTRFS_MISC_H #define BTRFS_MISC_H #include <linux/types.h> #include <linux/bitmap.h> #include <linux/sched.h> #include <linux/wait.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/math64.h> #include <linux/rbtree.h> /* * Enumerate bits using enum autoincrement. Define the @name as the n-th bit. */ #define ENUM_BIT(name) \ __ ## name ## _BIT, \ name = (1U << __ ## name ## _BIT), \ __ ## name ## _SEQ = __ ## name ## _BIT static inline void cond_wake_up(struct wait_queue_head *wq) { /* * This implies a full smp_mb barrier, see comments for * waitqueue_active why. */ if (wq_has_sleeper(wq)) wake_up(wq); } static inline void cond_wake_up_nomb(struct wait_queue_head *wq) { /* * Special case for conditional wakeup where the barrier required for * waitqueue_active is implied by some of the preceding code. Eg. one * of such atomic operations (atomic_dec_and_return, ...), or a * unlock/lock sequence, etc. */ if (waitqueue_active(wq)) wake_up(wq); } static inline u64 mult_perc(u64 num, u32 percent) { return div_u64(num * percent, 100); } /* Copy of is_power_of_two that is 64bit safe */ static inline bool is_power_of_two_u64(u64 n) { return n != 0 && (n & (n - 1)) == 0; } static inline bool has_single_bit_set(u64 n) { return is_power_of_two_u64(n); } /* * Simple bytenr based rb_tree relate structures * * Any structure wants to use bytenr as single search index should have their * structure start with these members. */ struct rb_simple_node { struct rb_node rb_node; u64 bytenr; }; static inline struct rb_node *rb_simple_search(const struct rb_root *root, u64 bytenr) { struct rb_node *node = root->rb_node; struct rb_simple_node *entry; while (node) { entry = rb_entry(node, struct rb_simple_node, rb_node); if (bytenr < entry->bytenr) node = node->rb_left; else if (bytenr > entry->bytenr) node = node->rb_right; else return node; } return NULL; } /* * Search @root from an entry that starts or comes after @bytenr. * * @root: the root to search. * @bytenr: bytenr to search from. * * Return the rb_node that start at or after @bytenr. If there is no entry at * or after @bytner return NULL. */ static inline struct rb_node *rb_simple_search_first(const struct rb_root *root, u64 bytenr) { struct rb_node *node = root->rb_node, *ret = NULL; struct rb_simple_node *entry, *ret_entry = NULL; while (node) { entry = rb_entry(node, struct rb_simple_node, rb_node); if (bytenr < entry->bytenr) { if (!ret || entry->bytenr < ret_entry->bytenr) { ret = node; ret_entry = entry; } node = node->rb_left; } else if (bytenr > entry->bytenr) { node = node->rb_right; } else { return node; } } return ret; } static int rb_simple_node_bytenr_cmp(struct rb_node *new, const struct rb_node *existing) { struct rb_simple_node *new_entry = rb_entry(new, struct rb_simple_node, rb_node); struct rb_simple_node *existing_entry = rb_entry(existing, struct rb_simple_node, rb_node); if (new_entry->bytenr < existing_entry->bytenr) return -1; else if (new_entry->bytenr > existing_entry->bytenr) return 1; return 0; } static inline struct rb_node *rb_simple_insert(struct rb_root *root, struct rb_simple_node *simple_node) { return rb_find_add(&simple_node->rb_node, root, rb_simple_node_bytenr_cmp); } static inline bool bitmap_test_range_all_set(const unsigned long *addr, unsigned long start, unsigned long nbits) { unsigned long found_zero; found_zero = find_next_zero_bit(addr, start + nbits, start); return (found_zero == start + nbits); } static inline bool bitmap_test_range_all_zero(const unsigned long *addr, unsigned long start, unsigned long nbits) { unsigned long found_set; found_set = find_next_bit(addr, start + nbits, start); return (found_set == start + nbits); } static inline u64 folio_end(struct folio *folio) { return folio_pos(folio) + folio_size(folio); } #endif |
| 1724 1726 1725 1722 1723 364 1 1728 364 363 362 1 364 1713 1723 1713 3 364 1 1713 1712 1713 1713 1715 1715 1712 29 29 29 1717 1717 1719 1719 29 1715 1719 902 903 904 902 192 193 1 1 2 2 2 2 1 1 2 1715 1717 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* audit.c -- Auditing support * Gateway between the kernel (e.g., selinux) and the user-space audit daemon. * System-call specific features have moved to auditsc.c * * Copyright 2003-2007 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> * * Goals: 1) Integrate fully with Security Modules. * 2) Minimal run-time overhead: * a) Minimal when syscall auditing is disabled (audit_enable=0). * b) Small when syscall auditing is enabled and no audit record * is generated (defer as much work as possible to record * generation time): * i) context is allocated, * ii) names from getname are stored without a copy, and * iii) inode information stored from path_lookup. * 3) Ability to disable syscall auditing at boot time (audit=0). * 4) Usable by other parts of the kernel (if audit_log* is called, * then a syscall record will be generated automatically for the * current syscall). * 5) Netlink interface to user-space. * 6) Support low-overhead kernel-based filtering to minimize the * information that must be passed to user-space. * * Audit userspace, documentation, tests, and bug/issue trackers: * https://github.com/linux-audit */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/file.h> #include <linux/init.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/kthread.h> #include <linux/kernel.h> #include <linux/syscalls.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/pid.h> #include <linux/audit.h> #include <net/sock.h> #include <net/netlink.h> #include <linux/skbuff.h> #include <linux/security.h> #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <net/netns/generic.h> #include "audit.h" /* No auditing will take place until audit_initialized == AUDIT_INITIALIZED. * (Initialization happens after skb_init is called.) */ #define AUDIT_DISABLED -1 #define AUDIT_UNINITIALIZED 0 #define AUDIT_INITIALIZED 1 static int audit_initialized = AUDIT_UNINITIALIZED; u32 audit_enabled = AUDIT_OFF; bool audit_ever_enabled = !!AUDIT_OFF; EXPORT_SYMBOL_GPL(audit_enabled); /* Default state when kernel boots without any parameters. */ static u32 audit_default = AUDIT_OFF; /* If auditing cannot proceed, audit_failure selects what happens. */ static u32 audit_failure = AUDIT_FAIL_PRINTK; /* private audit network namespace index */ static unsigned int audit_net_id; /** * struct audit_net - audit private network namespace data * @sk: communication socket */ struct audit_net { struct sock *sk; }; /** * struct auditd_connection - kernel/auditd connection state * @pid: auditd PID * @portid: netlink portid * @net: the associated network namespace * @rcu: RCU head * * Description: * This struct is RCU protected; you must either hold the RCU lock for reading * or the associated spinlock for writing. */ struct auditd_connection { struct pid *pid; u32 portid; struct net *net; struct rcu_head rcu; }; static struct auditd_connection __rcu *auditd_conn; static DEFINE_SPINLOCK(auditd_conn_lock); /* If audit_rate_limit is non-zero, limit the rate of sending audit records * to that number per second. This prevents DoS attacks, but results in * audit records being dropped. */ static u32 audit_rate_limit; /* Number of outstanding audit_buffers allowed. * When set to zero, this means unlimited. */ static u32 audit_backlog_limit = 64; #define AUDIT_BACKLOG_WAIT_TIME (60 * HZ) static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME; /* The identity of the user shutting down the audit system. */ static kuid_t audit_sig_uid = INVALID_UID; static pid_t audit_sig_pid = -1; static struct lsm_prop audit_sig_lsm; /* Records can be lost in several ways: 0) [suppressed in audit_alloc] 1) out of memory in audit_log_start [kmalloc of struct audit_buffer] 2) out of memory in audit_log_move [alloc_skb] 3) suppressed due to audit_rate_limit 4) suppressed due to audit_backlog_limit */ static atomic_t audit_lost = ATOMIC_INIT(0); /* Monotonically increasing sum of time the kernel has spent * waiting while the backlog limit is exceeded. */ static atomic_t audit_backlog_wait_time_actual = ATOMIC_INIT(0); /* Hash for inode-based rules */ struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS]; static struct kmem_cache *audit_buffer_cache; /* queue msgs to send via kauditd_task */ static struct sk_buff_head audit_queue; /* queue msgs due to temporary unicast send problems */ static struct sk_buff_head audit_retry_queue; /* queue msgs waiting for new auditd connection */ static struct sk_buff_head audit_hold_queue; /* queue servicing thread */ static struct task_struct *kauditd_task; static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait); /* waitqueue for callers who are blocked on the audit backlog */ static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait); static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION, .mask = -1, .features = 0, .lock = 0,}; static char *audit_feature_names[2] = { "only_unset_loginuid", "loginuid_immutable", }; /** * struct audit_ctl_mutex - serialize requests from userspace * @lock: the mutex used for locking * @owner: the task which owns the lock * * Description: * This is the lock struct used to ensure we only process userspace requests * in an orderly fashion. We can't simply use a mutex/lock here because we * need to track lock ownership so we don't end up blocking the lock owner in * audit_log_start() or similar. */ static struct audit_ctl_mutex { struct mutex lock; void *owner; } audit_cmd_mutex; /* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting * audit records. Since printk uses a 1024 byte buffer, this buffer * should be at least that large. */ #define AUDIT_BUFSIZ 1024 /* The audit_buffer is used when formatting an audit record. The caller * locks briefly to get the record off the freelist or to allocate the * buffer, and locks briefly to send the buffer to the netlink layer or * to place it on a transmit queue. Multiple audit_buffers can be in * use simultaneously. */ struct audit_buffer { struct sk_buff *skb; /* formatted skb ready to send */ struct audit_context *ctx; /* NULL or associated context */ gfp_t gfp_mask; }; struct audit_reply { __u32 portid; struct net *net; struct sk_buff *skb; }; /** * auditd_test_task - Check to see if a given task is an audit daemon * @task: the task to check * * Description: * Return 1 if the task is a registered audit daemon, 0 otherwise. */ int auditd_test_task(struct task_struct *task) { int rc; struct auditd_connection *ac; rcu_read_lock(); ac = rcu_dereference(auditd_conn); rc = (ac && ac->pid == task_tgid(task) ? 1 : 0); rcu_read_unlock(); return rc; } /** * audit_ctl_lock - Take the audit control lock */ void audit_ctl_lock(void) { mutex_lock(&audit_cmd_mutex.lock); audit_cmd_mutex.owner = current; } /** * audit_ctl_unlock - Drop the audit control lock */ void audit_ctl_unlock(void) { audit_cmd_mutex.owner = NULL; mutex_unlock(&audit_cmd_mutex.lock); } /** * audit_ctl_owner_current - Test to see if the current task owns the lock * * Description: * Return true if the current task owns the audit control lock, false if it * doesn't own the lock. */ static bool audit_ctl_owner_current(void) { return (current == audit_cmd_mutex.owner); } /** * auditd_pid_vnr - Return the auditd PID relative to the namespace * * Description: * Returns the PID in relation to the namespace, 0 on failure. */ static pid_t auditd_pid_vnr(void) { pid_t pid; const struct auditd_connection *ac; rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac || !ac->pid) pid = 0; else pid = pid_vnr(ac->pid); rcu_read_unlock(); return pid; } /** * audit_get_sk - Return the audit socket for the given network namespace * @net: the destination network namespace * * Description: * Returns the sock pointer if valid, NULL otherwise. The caller must ensure * that a reference is held for the network namespace while the sock is in use. */ static struct sock *audit_get_sk(const struct net *net) { struct audit_net *aunet; if (!net) return NULL; aunet = net_generic(net, audit_net_id); return aunet->sk; } void audit_panic(const char *message) { switch (audit_failure) { case AUDIT_FAIL_SILENT: break; case AUDIT_FAIL_PRINTK: if (printk_ratelimit()) pr_err("%s\n", message); break; case AUDIT_FAIL_PANIC: panic("audit: %s\n", message); break; } } static inline int audit_rate_check(void) { static unsigned long last_check = 0; static int messages = 0; static DEFINE_SPINLOCK(lock); unsigned long flags; unsigned long now; int retval = 0; if (!audit_rate_limit) return 1; spin_lock_irqsave(&lock, flags); if (++messages < audit_rate_limit) { retval = 1; } else { now = jiffies; if (time_after(now, last_check + HZ)) { last_check = now; messages = 0; retval = 1; } } spin_unlock_irqrestore(&lock, flags); return retval; } /** * audit_log_lost - conditionally log lost audit message event * @message: the message stating reason for lost audit message * * Emit at least 1 message per second, even if audit_rate_check is * throttling. * Always increment the lost messages counter. */ void audit_log_lost(const char *message) { static unsigned long last_msg = 0; static DEFINE_SPINLOCK(lock); unsigned long flags; unsigned long now; int print; atomic_inc(&audit_lost); print = (audit_failure == AUDIT_FAIL_PANIC || !audit_rate_limit); if (!print) { spin_lock_irqsave(&lock, flags); now = jiffies; if (time_after(now, last_msg + HZ)) { print = 1; last_msg = now; } spin_unlock_irqrestore(&lock, flags); } if (print) { if (printk_ratelimit()) pr_warn("audit_lost=%u audit_rate_limit=%u audit_backlog_limit=%u\n", atomic_read(&audit_lost), audit_rate_limit, audit_backlog_limit); audit_panic(message); } } static int audit_log_config_change(char *function_name, u32 new, u32 old, int allow_changes) { struct audit_buffer *ab; int rc = 0; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (unlikely(!ab)) return rc; audit_log_format(ab, "op=set %s=%u old=%u ", function_name, new, old); audit_log_session_info(ab); rc = audit_log_task_context(ab); if (rc) allow_changes = 0; /* Something weird, deny request */ audit_log_format(ab, " res=%d", allow_changes); audit_log_end(ab); return rc; } static int audit_do_config_change(char *function_name, u32 *to_change, u32 new) { int allow_changes, rc = 0; u32 old = *to_change; /* check if we are locked */ if (audit_enabled == AUDIT_LOCKED) allow_changes = 0; else allow_changes = 1; if (audit_enabled != AUDIT_OFF) { rc = audit_log_config_change(function_name, new, old, allow_changes); if (rc) allow_changes = 0; } /* If we are allowed, make the change */ if (allow_changes == 1) *to_change = new; /* Not allowed, update reason */ else if (rc == 0) rc = -EPERM; return rc; } static int audit_set_rate_limit(u32 limit) { return audit_do_config_change("audit_rate_limit", &audit_rate_limit, limit); } static int audit_set_backlog_limit(u32 limit) { return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit, limit); } static int audit_set_backlog_wait_time(u32 timeout) { return audit_do_config_change("audit_backlog_wait_time", &audit_backlog_wait_time, timeout); } static int audit_set_enabled(u32 state) { int rc; if (state > AUDIT_LOCKED) return -EINVAL; rc = audit_do_config_change("audit_enabled", &audit_enabled, state); if (!rc) audit_ever_enabled |= !!state; return rc; } static int audit_set_failure(u32 state) { if (state != AUDIT_FAIL_SILENT && state != AUDIT_FAIL_PRINTK && state != AUDIT_FAIL_PANIC) return -EINVAL; return audit_do_config_change("audit_failure", &audit_failure, state); } /** * auditd_conn_free - RCU helper to release an auditd connection struct * @rcu: RCU head * * Description: * Drop any references inside the auditd connection tracking struct and free * the memory. */ static void auditd_conn_free(struct rcu_head *rcu) { struct auditd_connection *ac; ac = container_of(rcu, struct auditd_connection, rcu); put_pid(ac->pid); put_net(ac->net); kfree(ac); } /** * auditd_set - Set/Reset the auditd connection state * @pid: auditd PID * @portid: auditd netlink portid * @net: auditd network namespace pointer * @skb: the netlink command from the audit daemon * @ack: netlink ack flag, cleared if ack'd here * * Description: * This function will obtain and drop network namespace references as * necessary. Returns zero on success, negative values on failure. */ static int auditd_set(struct pid *pid, u32 portid, struct net *net, struct sk_buff *skb, bool *ack) { unsigned long flags; struct auditd_connection *ac_old, *ac_new; struct nlmsghdr *nlh; if (!pid || !net) return -EINVAL; ac_new = kzalloc(sizeof(*ac_new), GFP_KERNEL); if (!ac_new) return -ENOMEM; ac_new->pid = get_pid(pid); ac_new->portid = portid; ac_new->net = get_net(net); /* send the ack now to avoid a race with the queue backlog */ if (*ack) { nlh = nlmsg_hdr(skb); netlink_ack(skb, nlh, 0, NULL); *ack = false; } spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); rcu_assign_pointer(auditd_conn, ac_new); spin_unlock_irqrestore(&auditd_conn_lock, flags); if (ac_old) call_rcu(&ac_old->rcu, auditd_conn_free); return 0; } /** * kauditd_printk_skb - Print the audit record to the ring buffer * @skb: audit record * * Whatever the reason, this packet may not make it to the auditd connection * so write it via printk so the information isn't completely lost. */ static void kauditd_printk_skb(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); char *data = nlmsg_data(nlh); if (nlh->nlmsg_type != AUDIT_EOE && printk_ratelimit()) pr_notice("type=%d %s\n", nlh->nlmsg_type, data); } /** * kauditd_rehold_skb - Handle a audit record send failure in the hold queue * @skb: audit record * @error: error code (unused) * * Description: * This should only be used by the kauditd_thread when it fails to flush the * hold queue. */ static void kauditd_rehold_skb(struct sk_buff *skb, __always_unused int error) { /* put the record back in the queue */ skb_queue_tail(&audit_hold_queue, skb); } /** * kauditd_hold_skb - Queue an audit record, waiting for auditd * @skb: audit record * @error: error code * * Description: * Queue the audit record, waiting for an instance of auditd. When this * function is called we haven't given up yet on sending the record, but things * are not looking good. The first thing we want to do is try to write the * record via printk and then see if we want to try and hold on to the record * and queue it, if we have room. If we want to hold on to the record, but we * don't have room, record a record lost message. */ static void kauditd_hold_skb(struct sk_buff *skb, int error) { /* at this point it is uncertain if we will ever send this to auditd so * try to send the message via printk before we go any further */ kauditd_printk_skb(skb); /* can we just silently drop the message? */ if (!audit_default) goto drop; /* the hold queue is only for when the daemon goes away completely, * not -EAGAIN failures; if we are in a -EAGAIN state requeue the * record on the retry queue unless it's full, in which case drop it */ if (error == -EAGAIN) { if (!audit_backlog_limit || skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { skb_queue_tail(&audit_retry_queue, skb); return; } audit_log_lost("kauditd retry queue overflow"); goto drop; } /* if we have room in the hold queue, queue the message */ if (!audit_backlog_limit || skb_queue_len(&audit_hold_queue) < audit_backlog_limit) { skb_queue_tail(&audit_hold_queue, skb); return; } /* we have no other options - drop the message */ audit_log_lost("kauditd hold queue overflow"); drop: kfree_skb(skb); } /** * kauditd_retry_skb - Queue an audit record, attempt to send again to auditd * @skb: audit record * @error: error code (unused) * * Description: * Not as serious as kauditd_hold_skb() as we still have a connected auditd, * but for some reason we are having problems sending it audit records so * queue the given record and attempt to resend. */ static void kauditd_retry_skb(struct sk_buff *skb, __always_unused int error) { if (!audit_backlog_limit || skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { skb_queue_tail(&audit_retry_queue, skb); return; } /* we have to drop the record, send it via printk as a last effort */ kauditd_printk_skb(skb); audit_log_lost("kauditd retry queue overflow"); kfree_skb(skb); } /** * auditd_reset - Disconnect the auditd connection * @ac: auditd connection state * * Description: * Break the auditd/kauditd connection and move all the queued records into the * hold queue in case auditd reconnects. It is important to note that the @ac * pointer should never be dereferenced inside this function as it may be NULL * or invalid, you can only compare the memory address! If @ac is NULL then * the connection will always be reset. */ static void auditd_reset(const struct auditd_connection *ac) { unsigned long flags; struct sk_buff *skb; struct auditd_connection *ac_old; /* if it isn't already broken, break the connection */ spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); if (ac && ac != ac_old) { /* someone already registered a new auditd connection */ spin_unlock_irqrestore(&auditd_conn_lock, flags); return; } rcu_assign_pointer(auditd_conn, NULL); spin_unlock_irqrestore(&auditd_conn_lock, flags); if (ac_old) call_rcu(&ac_old->rcu, auditd_conn_free); /* flush the retry queue to the hold queue, but don't touch the main * queue since we need to process that normally for multicast */ while ((skb = skb_dequeue(&audit_retry_queue))) kauditd_hold_skb(skb, -ECONNREFUSED); } /** * auditd_send_unicast_skb - Send a record via unicast to auditd * @skb: audit record * * Description: * Send a skb to the audit daemon, returns positive/zero values on success and * negative values on failure; in all cases the skb will be consumed by this * function. If the send results in -ECONNREFUSED the connection with auditd * will be reset. This function may sleep so callers should not hold any locks * where this would cause a problem. */ static int auditd_send_unicast_skb(struct sk_buff *skb) { int rc; u32 portid; struct net *net; struct sock *sk; struct auditd_connection *ac; /* NOTE: we can't call netlink_unicast while in the RCU section so * take a reference to the network namespace and grab local * copies of the namespace, the sock, and the portid; the * namespace and sock aren't going to go away while we hold a * reference and if the portid does become invalid after the RCU * section netlink_unicast() should safely return an error */ rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac) { rcu_read_unlock(); kfree_skb(skb); rc = -ECONNREFUSED; goto err; } net = get_net(ac->net); sk = audit_get_sk(net); portid = ac->portid; rcu_read_unlock(); rc = netlink_unicast(sk, skb, portid, 0); put_net(net); if (rc < 0) goto err; return rc; err: if (ac && rc == -ECONNREFUSED) auditd_reset(ac); return rc; } /** * kauditd_send_queue - Helper for kauditd_thread to flush skb queues * @sk: the sending sock * @portid: the netlink destination * @queue: the skb queue to process * @retry_limit: limit on number of netlink unicast failures * @skb_hook: per-skb hook for additional processing * @err_hook: hook called if the skb fails the netlink unicast send * * Description: * Run through the given queue and attempt to send the audit records to auditd, * returns zero on success, negative values on failure. It is up to the caller * to ensure that the @sk is valid for the duration of this function. * */ static int kauditd_send_queue(struct sock *sk, u32 portid, struct sk_buff_head *queue, unsigned int retry_limit, void (*skb_hook)(struct sk_buff *skb), void (*err_hook)(struct sk_buff *skb, int error)) { int rc = 0; struct sk_buff *skb = NULL; struct sk_buff *skb_tail; unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ skb_tail = skb_peek_tail(queue); while ((skb != skb_tail) && (skb = skb_dequeue(queue))) { /* call the skb_hook for each skb we touch */ if (skb_hook) (*skb_hook)(skb); /* can we send to anyone via unicast? */ if (!sk) { if (err_hook) (*err_hook)(skb, -ECONNREFUSED); continue; } retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { sk = NULL; if (err_hook) (*err_hook)(skb, rc); if (rc == -EAGAIN) rc = 0; /* continue to drain the queue */ continue; } else goto retry; } else { /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } } return (rc >= 0 ? 0 : rc); } /* * kauditd_send_multicast_skb - Send a record to any multicast listeners * @skb: audit record * * Description: * Write a multicast message to anyone listening in the initial network * namespace. This function doesn't consume an skb as might be expected since * it has to copy it anyways. */ static void kauditd_send_multicast_skb(struct sk_buff *skb) { struct sk_buff *copy; struct sock *sock = audit_get_sk(&init_net); struct nlmsghdr *nlh; /* NOTE: we are not taking an additional reference for init_net since * we don't have to worry about it going away */ if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG)) return; /* * The seemingly wasteful skb_copy() rather than bumping the refcount * using skb_get() is necessary because non-standard mods are made to * the skb by the original kaudit unicast socket send routine. The * existing auditd daemon assumes this breakage. Fixing this would * require co-ordinating a change in the established protocol between * the kaudit kernel subsystem and the auditd userspace code. There is * no reason for new multicast clients to continue with this * non-compliance. */ copy = skb_copy(skb, GFP_KERNEL); if (!copy) return; nlh = nlmsg_hdr(copy); nlh->nlmsg_len = skb->len; nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, GFP_KERNEL); } /** * kauditd_thread - Worker thread to send audit records to userspace * @dummy: unused */ static int kauditd_thread(void *dummy) { int rc; u32 portid = 0; struct net *net = NULL; struct sock *sk = NULL; struct auditd_connection *ac; #define UNICAST_RETRIES 5 set_freezable(); while (!kthread_should_stop()) { /* NOTE: see the lock comments in auditd_send_unicast_skb() */ rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac) { rcu_read_unlock(); goto main_queue; } net = get_net(ac->net); sk = audit_get_sk(net); portid = ac->portid; rcu_read_unlock(); /* attempt to flush the hold queue */ rc = kauditd_send_queue(sk, portid, &audit_hold_queue, UNICAST_RETRIES, NULL, kauditd_rehold_skb); if (rc < 0) { sk = NULL; auditd_reset(ac); goto main_queue; } /* attempt to flush the retry queue */ rc = kauditd_send_queue(sk, portid, &audit_retry_queue, UNICAST_RETRIES, NULL, kauditd_hold_skb); if (rc < 0) { sk = NULL; auditd_reset(ac); goto main_queue; } main_queue: /* process the main queue - do the multicast send and attempt * unicast, dump failed record sends to the retry queue; if * sk == NULL due to previous failures we will just do the * multicast send and move the record to the hold queue */ rc = kauditd_send_queue(sk, portid, &audit_queue, 1, kauditd_send_multicast_skb, (sk ? kauditd_retry_skb : kauditd_hold_skb)); if (ac && rc < 0) auditd_reset(ac); sk = NULL; /* drop our netns reference, no auditd sends past this line */ if (net) { put_net(net); net = NULL; } /* we have processed all the queues so wake everyone */ wake_up(&audit_backlog_wait); /* NOTE: we want to wake up if there is anything on the queue, * regardless of if an auditd is connected, as we need to * do the multicast send and rotate records from the * main queue to the retry/hold queues */ wait_event_freezable(kauditd_wait, (skb_queue_len(&audit_queue) ? 1 : 0)); } return 0; } int audit_send_list_thread(void *_dest) { struct audit_netlink_list *dest = _dest; struct sk_buff *skb; struct sock *sk = audit_get_sk(dest->net); /* wait for parent to finish and send an ACK */ audit_ctl_lock(); audit_ctl_unlock(); while ((skb = __skb_dequeue(&dest->q)) != NULL) netlink_unicast(sk, skb, dest->portid, 0); put_net(dest->net); kfree(dest); return 0; } struct sk_buff *audit_make_reply(int seq, int type, int done, int multi, const void *payload, int size) { struct sk_buff *skb; struct nlmsghdr *nlh; void *data; int flags = multi ? NLM_F_MULTI : 0; int t = done ? NLMSG_DONE : type; skb = nlmsg_new(size, GFP_KERNEL); if (!skb) return NULL; nlh = nlmsg_put(skb, 0, seq, t, size, flags); if (!nlh) goto out_kfree_skb; data = nlmsg_data(nlh); memcpy(data, payload, size); return skb; out_kfree_skb: kfree_skb(skb); return NULL; } static void audit_free_reply(struct audit_reply *reply) { if (!reply) return; kfree_skb(reply->skb); if (reply->net) put_net(reply->net); kfree(reply); } static int audit_send_reply_thread(void *arg) { struct audit_reply *reply = (struct audit_reply *)arg; audit_ctl_lock(); audit_ctl_unlock(); /* Ignore failure. It'll only happen if the sender goes away, because our timeout is set to infinite. */ netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0); reply->skb = NULL; audit_free_reply(reply); return 0; } /** * audit_send_reply - send an audit reply message via netlink * @request_skb: skb of request we are replying to (used to target the reply) * @seq: sequence number * @type: audit message type * @done: done (last) flag * @multi: multi-part message flag * @payload: payload data * @size: payload size * * Allocates a skb, builds the netlink message, and sends it to the port id. */ static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done, int multi, const void *payload, int size) { struct task_struct *tsk; struct audit_reply *reply; reply = kzalloc(sizeof(*reply), GFP_KERNEL); if (!reply) return; reply->skb = audit_make_reply(seq, type, done, multi, payload, size); if (!reply->skb) goto err; reply->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); reply->portid = NETLINK_CB(request_skb).portid; tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply"); if (IS_ERR(tsk)) goto err; return; err: audit_free_reply(reply); } /* * Check for appropriate CAP_AUDIT_ capabilities on incoming audit * control messages. */ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) { int err = 0; /* Only support initial user namespace for now. */ /* * We return ECONNREFUSED because it tricks userspace into thinking * that audit was not configured into the kernel. Lots of users * configure their PAM stack (because that's what the distro does) * to reject login if unable to send messages to audit. If we return * ECONNREFUSED the PAM stack thinks the kernel does not have audit * configured in and will let login proceed. If we return EPERM * userspace will reject all logins. This should be removed when we * support non init namespaces!! */ if (current_user_ns() != &init_user_ns) return -ECONNREFUSED; switch (msg_type) { case AUDIT_LIST: case AUDIT_ADD: case AUDIT_DEL: return -EOPNOTSUPP; case AUDIT_GET: case AUDIT_SET: case AUDIT_GET_FEATURE: case AUDIT_SET_FEATURE: case AUDIT_LIST_RULES: case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: case AUDIT_SIGNAL_INFO: case AUDIT_TTY_GET: case AUDIT_TTY_SET: case AUDIT_TRIM: case AUDIT_MAKE_EQUIV: /* Only support auditd and auditctl in initial pid namespace * for now. */ if (task_active_pid_ns(current) != &init_pid_ns) return -EPERM; if (!netlink_capable(skb, CAP_AUDIT_CONTROL)) err = -EPERM; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: if (!netlink_capable(skb, CAP_AUDIT_WRITE)) err = -EPERM; break; default: /* bad msg */ err = -EINVAL; } return err; } static void audit_log_common_recv_msg(struct audit_context *context, struct audit_buffer **ab, u16 msg_type) { uid_t uid = from_kuid(&init_user_ns, current_uid()); pid_t pid = task_tgid_nr(current); if (!audit_enabled && msg_type != AUDIT_USER_AVC) { *ab = NULL; return; } *ab = audit_log_start(context, GFP_KERNEL, msg_type); if (unlikely(!*ab)) return; audit_log_format(*ab, "pid=%d uid=%u ", pid, uid); audit_log_session_info(*ab); audit_log_task_context(*ab); } static inline void audit_log_user_recv_msg(struct audit_buffer **ab, u16 msg_type) { audit_log_common_recv_msg(NULL, ab, msg_type); } static int is_audit_feature_set(int i) { return af.features & AUDIT_FEATURE_TO_MASK(i); } static int audit_get_feature(struct sk_buff *skb) { u32 seq; seq = nlmsg_hdr(skb)->nlmsg_seq; audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af)); return 0; } static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature, u32 old_lock, u32 new_lock, int res) { struct audit_buffer *ab; if (audit_enabled == AUDIT_OFF) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_FEATURE_CHANGE); if (!ab) return; audit_log_task_info(ab); audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", audit_feature_names[which], !!old_feature, !!new_feature, !!old_lock, !!new_lock, res); audit_log_end(ab); } static int audit_set_feature(struct audit_features *uaf) { int i; BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); /* if there is ever a version 2 we should handle that here */ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { u32 feature = AUDIT_FEATURE_TO_MASK(i); u32 old_feature, new_feature, old_lock, new_lock; /* if we are not changing this feature, move along */ if (!(feature & uaf->mask)) continue; old_feature = af.features & feature; new_feature = uaf->features & feature; new_lock = (uaf->lock | af.lock) & feature; old_lock = af.lock & feature; /* are we changing a locked feature? */ if (old_lock && (new_feature != old_feature)) { audit_log_feature_change(i, old_feature, new_feature, old_lock, new_lock, 0); return -EPERM; } } /* nothing invalid, do the changes */ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { u32 feature = AUDIT_FEATURE_TO_MASK(i); u32 old_feature, new_feature, old_lock, new_lock; /* if we are not changing this feature, move along */ if (!(feature & uaf->mask)) continue; old_feature = af.features & feature; new_feature = uaf->features & feature; old_lock = af.lock & feature; new_lock = (uaf->lock | af.lock) & feature; if (new_feature != old_feature) audit_log_feature_change(i, old_feature, new_feature, old_lock, new_lock, 1); if (new_feature) af.features |= feature; else af.features &= ~feature; af.lock |= new_lock; } return 0; } static int audit_replace(struct pid *pid) { pid_t pvnr; struct sk_buff *skb; pvnr = pid_vnr(pid); skb = audit_make_reply(0, AUDIT_REPLACE, 0, 0, &pvnr, sizeof(pvnr)); if (!skb) return -ENOMEM; return auditd_send_unicast_skb(skb); } static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, bool *ack) { u32 seq; void *data; int data_len; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; struct audit_sig_info *sig_data; struct lsm_context lsmctx = { NULL, 0, 0 }; err = audit_netlink_ok(skb, msg_type); if (err) return err; seq = nlh->nlmsg_seq; data = nlmsg_data(nlh); data_len = nlmsg_len(nlh); switch (msg_type) { case AUDIT_GET: { struct audit_status s; memset(&s, 0, sizeof(s)); s.enabled = audit_enabled; s.failure = audit_failure; /* NOTE: use pid_vnr() so the PID is relative to the current * namespace */ s.pid = auditd_pid_vnr(); s.rate_limit = audit_rate_limit; s.backlog_limit = audit_backlog_limit; s.lost = atomic_read(&audit_lost); s.backlog = skb_queue_len(&audit_queue); s.feature_bitmap = AUDIT_FEATURE_BITMAP_ALL; s.backlog_wait_time = audit_backlog_wait_time; s.backlog_wait_time_actual = atomic_read(&audit_backlog_wait_time_actual); audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_SET: { struct audit_status s; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); if (s.mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(s.enabled); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_FAILURE) { err = audit_set_failure(s.failure); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_PID) { /* NOTE: we are using the vnr PID functions below * because the s.pid value is relative to the * namespace of the caller; at present this * doesn't matter much since you can really only * run auditd from the initial pid namespace, but * something to keep in mind if this changes */ pid_t new_pid = s.pid; pid_t auditd_pid; struct pid *req_pid = task_tgid(current); /* Sanity check - PID values must match. Setting * pid to 0 is how auditd ends auditing. */ if (new_pid && (new_pid != pid_vnr(req_pid))) return -EINVAL; /* test the auditd connection */ audit_replace(req_pid); auditd_pid = auditd_pid_vnr(); if (auditd_pid) { /* replacing a healthy auditd is not allowed */ if (new_pid) { audit_log_config_change("audit_pid", new_pid, auditd_pid, 0); return -EEXIST; } /* only current auditd can unregister itself */ if (pid_vnr(req_pid) != auditd_pid) { audit_log_config_change("audit_pid", new_pid, auditd_pid, 0); return -EACCES; } } if (new_pid) { /* register a new auditd connection */ err = auditd_set(req_pid, NETLINK_CB(skb).portid, sock_net(NETLINK_CB(skb).sk), skb, ack); if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, auditd_pid, err ? 0 : 1); if (err) return err; /* try to process any backlog */ wake_up_interruptible(&kauditd_wait); } else { if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, auditd_pid, 1); /* unregister the auditd connection */ auditd_reset(NULL); } } if (s.mask & AUDIT_STATUS_RATE_LIMIT) { err = audit_set_rate_limit(s.rate_limit); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_BACKLOG_LIMIT) { err = audit_set_backlog_limit(s.backlog_limit); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_BACKLOG_WAIT_TIME) { if (sizeof(s) > (size_t)nlh->nlmsg_len) return -EINVAL; if (s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME) return -EINVAL; err = audit_set_backlog_wait_time(s.backlog_wait_time); if (err < 0) return err; } if (s.mask == AUDIT_STATUS_LOST) { u32 lost = atomic_xchg(&audit_lost, 0); audit_log_config_change("lost", 0, lost, 1); return lost; } if (s.mask == AUDIT_STATUS_BACKLOG_WAIT_TIME_ACTUAL) { u32 actual = atomic_xchg(&audit_backlog_wait_time_actual, 0); audit_log_config_change("backlog_wait_time_actual", 0, actual, 1); return actual; } break; } case AUDIT_GET_FEATURE: err = audit_get_feature(skb); if (err) return err; break; case AUDIT_SET_FEATURE: if (data_len < sizeof(struct audit_features)) return -EINVAL; err = audit_set_feature(data); if (err) return err; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: if (!audit_enabled && msg_type != AUDIT_USER_AVC) return 0; /* exit early if there isn't at least one character to print */ if (data_len < 2) return -EINVAL; err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ char *str = data; err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push(); if (err) break; } audit_log_user_recv_msg(&ab, msg_type); if (msg_type != AUDIT_USER_TTY) { /* ensure NULL termination */ str[data_len - 1] = '\0'; audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, str); } else { audit_log_format(ab, " data="); if (str[data_len - 1] == '\0') data_len--; audit_log_n_untrustedstring(ab, str, data_len); } audit_log_end(ab); } break; case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: if (data_len < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=%s audit_enabled=%d res=0", msg_type == AUDIT_ADD_RULE ? "add_rule" : "remove_rule", audit_enabled); audit_log_end(ab); return -EPERM; } err = audit_rule_change(msg_type, seq, data, data_len); break; case AUDIT_LIST_RULES: err = audit_list_rules_send(skb, seq); break; case AUDIT_TRIM: audit_trim_trees(); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=trim res=1"); audit_log_end(ab); break; case AUDIT_MAKE_EQUIV: { void *bufp = data; u32 sizes[2]; size_t msglen = data_len; char *old, *new; err = -EINVAL; if (msglen < 2 * sizeof(u32)) break; memcpy(sizes, bufp, 2 * sizeof(u32)); bufp += 2 * sizeof(u32); msglen -= 2 * sizeof(u32); old = audit_unpack_string(&bufp, &msglen, sizes[0]); if (IS_ERR(old)) { err = PTR_ERR(old); break; } new = audit_unpack_string(&bufp, &msglen, sizes[1]); if (IS_ERR(new)) { err = PTR_ERR(new); kfree(old); break; } /* OK, here comes... */ err = audit_tag_tree(old, new); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=make_equiv old="); audit_log_untrustedstring(ab, old); audit_log_format(ab, " new="); audit_log_untrustedstring(ab, new); audit_log_format(ab, " res=%d", !err); audit_log_end(ab); kfree(old); kfree(new); break; } case AUDIT_SIGNAL_INFO: if (lsmprop_is_set(&audit_sig_lsm)) { err = security_lsmprop_to_secctx(&audit_sig_lsm, &lsmctx); if (err < 0) return err; } sig_data = kmalloc(struct_size(sig_data, ctx, lsmctx.len), GFP_KERNEL); if (!sig_data) { if (lsmprop_is_set(&audit_sig_lsm)) security_release_secctx(&lsmctx); return -ENOMEM; } sig_data->uid = from_kuid(&init_user_ns, audit_sig_uid); sig_data->pid = audit_sig_pid; if (lsmprop_is_set(&audit_sig_lsm)) { memcpy(sig_data->ctx, lsmctx.context, lsmctx.len); security_release_secctx(&lsmctx); } audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, sig_data, struct_size(sig_data, ctx, lsmctx.len)); kfree(sig_data); break; case AUDIT_TTY_GET: { struct audit_tty_status s; unsigned int t; t = READ_ONCE(current->signal->audit_tty); s.enabled = t & AUDIT_TTY_ENABLE; s.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD); audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_TTY_SET: { struct audit_tty_status s, old; struct audit_buffer *ab; unsigned int t; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); /* check if new data is valid */ if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) err = -EINVAL; if (err) t = READ_ONCE(current->signal->audit_tty); else { t = s.enabled | (-s.log_passwd & AUDIT_TTY_LOG_PASSWD); t = xchg(¤t->signal->audit_tty, t); } old.enabled = t & AUDIT_TTY_ENABLE; old.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=tty_set old-enabled=%d new-enabled=%d" " old-log_passwd=%d new-log_passwd=%d res=%d", old.enabled, s.enabled, old.log_passwd, s.log_passwd, !err); audit_log_end(ab); break; } default: err = -EINVAL; break; } return err < 0 ? err : 0; } /** * audit_receive - receive messages from a netlink control socket * @skb: the message buffer * * Parse the provided skb and deal with any messages that may be present, * malformed skbs are discarded. */ static void audit_receive(struct sk_buff *skb) { struct nlmsghdr *nlh; bool ack; /* * len MUST be signed for nlmsg_next to be able to dec it below 0 * if the nlmsg_len was not aligned */ int len; int err; nlh = nlmsg_hdr(skb); len = skb->len; audit_ctl_lock(); while (nlmsg_ok(nlh, len)) { ack = nlh->nlmsg_flags & NLM_F_ACK; err = audit_receive_msg(skb, nlh, &ack); /* send an ack if the user asked for one and audit_receive_msg * didn't already do it, or if there was an error. */ if (ack || err) netlink_ack(skb, nlh, err, NULL); nlh = nlmsg_next(nlh, &len); } audit_ctl_unlock(); /* can't block with the ctrl lock, so penalize the sender now */ if (audit_backlog_limit && (skb_queue_len(&audit_queue) > audit_backlog_limit)) { DECLARE_WAITQUEUE(wait, current); /* wake kauditd to try and flush the queue */ wake_up_interruptible(&kauditd_wait); add_wait_queue_exclusive(&audit_backlog_wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); schedule_timeout(audit_backlog_wait_time); remove_wait_queue(&audit_backlog_wait, &wait); } } /* Log information about who is connecting to the audit multicast socket */ static void audit_log_multicast(int group, const char *op, int err) { const struct cred *cred; struct tty_struct *tty; char comm[sizeof(current->comm)]; struct audit_buffer *ab; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_EVENT_LISTENER); if (!ab) return; cred = current_cred(); tty = audit_get_tty(); audit_log_format(ab, "pid=%u uid=%u auid=%u tty=%s ses=%u", task_tgid_nr(current), from_kuid(&init_user_ns, cred->uid), from_kuid(&init_user_ns, audit_get_loginuid(current)), tty ? tty_name(tty) : "(none)", audit_get_sessionid(current)); audit_put_tty(tty); audit_log_task_context(ab); /* subj= */ audit_log_format(ab, " comm="); audit_log_untrustedstring(ab, get_task_comm(comm, current)); audit_log_d_path_exe(ab, current->mm); /* exe= */ audit_log_format(ab, " nl-mcgrp=%d op=%s res=%d", group, op, !err); audit_log_end(ab); } /* Run custom bind function on netlink socket group connect or bind requests. */ static int audit_multicast_bind(struct net *net, int group) { int err = 0; if (!capable(CAP_AUDIT_READ)) err = -EPERM; audit_log_multicast(group, "connect", err); return err; } static void audit_multicast_unbind(struct net *net, int group) { audit_log_multicast(group, "disconnect", 0); } static int __net_init audit_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = audit_receive, .bind = audit_multicast_bind, .unbind = audit_multicast_unbind, .flags = NL_CFG_F_NONROOT_RECV, .groups = AUDIT_NLGRP_MAX, }; struct audit_net *aunet = net_generic(net, audit_net_id); aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg); if (aunet->sk == NULL) { audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } /* limit the timeout in case auditd is blocked/stopped */ aunet->sk->sk_sndtimeo = HZ / 10; return 0; } static void __net_exit audit_net_exit(struct net *net) { struct audit_net *aunet = net_generic(net, audit_net_id); /* NOTE: you would think that we would want to check the auditd * connection and potentially reset it here if it lives in this * namespace, but since the auditd connection tracking struct holds a * reference to this namespace (see auditd_set()) we are only ever * going to get here after that connection has been released */ netlink_kernel_release(aunet->sk); } static struct pernet_operations audit_net_ops __net_initdata = { .init = audit_net_init, .exit = audit_net_exit, .id = &audit_net_id, .size = sizeof(struct audit_net), }; /* Initialize audit support at boot time. */ static int __init audit_init(void) { int i; if (audit_initialized == AUDIT_DISABLED) return 0; audit_buffer_cache = KMEM_CACHE(audit_buffer, SLAB_PANIC); skb_queue_head_init(&audit_queue); skb_queue_head_init(&audit_retry_queue); skb_queue_head_init(&audit_hold_queue); for (i = 0; i < AUDIT_INODE_BUCKETS; i++) INIT_LIST_HEAD(&audit_inode_hash[i]); mutex_init(&audit_cmd_mutex.lock); audit_cmd_mutex.owner = NULL; pr_info("initializing netlink subsys (%s)\n", str_enabled_disabled(audit_default)); register_pernet_subsys(&audit_net_ops); audit_initialized = AUDIT_INITIALIZED; kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd"); if (IS_ERR(kauditd_task)) { int err = PTR_ERR(kauditd_task); panic("audit: failed to start the kauditd thread (%d)\n", err); } audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "state=initialized audit_enabled=%u res=1", audit_enabled); return 0; } postcore_initcall(audit_init); /* * Process kernel command-line parameter at boot time. * audit={0|off} or audit={1|on}. */ static int __init audit_enable(char *str) { if (!strcasecmp(str, "off") || !strcmp(str, "0")) audit_default = AUDIT_OFF; else if (!strcasecmp(str, "on") || !strcmp(str, "1")) audit_default = AUDIT_ON; else { pr_err("audit: invalid 'audit' parameter value (%s)\n", str); audit_default = AUDIT_ON; } if (audit_default == AUDIT_OFF) audit_initialized = AUDIT_DISABLED; if (audit_set_enabled(audit_default)) pr_err("audit: error setting audit state (%d)\n", audit_default); pr_info("%s\n", audit_default ? "enabled (after initialization)" : "disabled (until reboot)"); return 1; } __setup("audit=", audit_enable); /* Process kernel command-line parameter at boot time. * audit_backlog_limit=<n> */ static int __init audit_backlog_limit_set(char *str) { u32 audit_backlog_limit_arg; pr_info("audit_backlog_limit: "); if (kstrtouint(str, 0, &audit_backlog_limit_arg)) { pr_cont("using default of %u, unable to parse %s\n", audit_backlog_limit, str); return 1; } audit_backlog_limit = audit_backlog_limit_arg; pr_cont("%d\n", audit_backlog_limit); return 1; } __setup("audit_backlog_limit=", audit_backlog_limit_set); static void audit_buffer_free(struct audit_buffer *ab) { if (!ab) return; kfree_skb(ab->skb); kmem_cache_free(audit_buffer_cache, ab); } static struct audit_buffer *audit_buffer_alloc(struct audit_context *ctx, gfp_t gfp_mask, int type) { struct audit_buffer *ab; ab = kmem_cache_alloc(audit_buffer_cache, gfp_mask); if (!ab) return NULL; ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask); if (!ab->skb) goto err; if (!nlmsg_put(ab->skb, 0, 0, type, 0, 0)) goto err; ab->ctx = ctx; ab->gfp_mask = gfp_mask; return ab; err: audit_buffer_free(ab); return NULL; } /** * audit_serial - compute a serial number for the audit record * * Compute a serial number for the audit record. Audit records are * written to user-space as soon as they are generated, so a complete * audit record may be written in several pieces. The timestamp of the * record and this serial number are used by the user-space tools to * determine which pieces belong to the same audit record. The * (timestamp,serial) tuple is unique for each syscall and is live from * syscall entry to syscall exit. * * NOTE: Another possibility is to store the formatted records off the * audit context (for those records that have a context), and emit them * all at syscall exit. However, this could delay the reporting of * significant errors until syscall exit (or never, if the system * halts). */ unsigned int audit_serial(void) { static atomic_t serial = ATOMIC_INIT(0); return atomic_inc_return(&serial); } static inline void audit_get_stamp(struct audit_context *ctx, struct timespec64 *t, unsigned int *serial) { if (!ctx || !auditsc_get_stamp(ctx, t, serial)) { ktime_get_coarse_real_ts64(t); *serial = audit_serial(); } } /** * audit_log_start - obtain an audit buffer * @ctx: audit_context (may be NULL) * @gfp_mask: type of allocation * @type: audit message type * * Returns audit_buffer pointer on success or NULL on error. * * Obtain an audit buffer. This routine does locking to obtain the * audit buffer, but then no locking is required for calls to * audit_log_*format. If the task (ctx) is a task that is currently in a * syscall, then the syscall is marked as auditable and an audit record * will be written at syscall exit. If there is no associated task, then * task context (ctx) should be NULL. */ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { struct audit_buffer *ab; struct timespec64 t; unsigned int serial; if (audit_initialized != AUDIT_INITIALIZED) return NULL; if (unlikely(!audit_filter(type, AUDIT_FILTER_EXCLUDE))) return NULL; /* NOTE: don't ever fail/sleep on these two conditions: * 1. auditd generated record - since we need auditd to drain the * queue; also, when we are checking for auditd, compare PIDs using * task_tgid_vnr() since auditd_pid is set in audit_receive_msg() * using a PID anchored in the caller's namespace * 2. generator holding the audit_cmd_mutex - we don't want to block * while holding the mutex, although we do penalize the sender * later in audit_receive() when it is safe to block */ if (!(auditd_test_task(current) || audit_ctl_owner_current())) { long stime = audit_backlog_wait_time; while (audit_backlog_limit && (skb_queue_len(&audit_queue) > audit_backlog_limit)) { /* wake kauditd to try and flush the queue */ wake_up_interruptible(&kauditd_wait); /* sleep if we are allowed and we haven't exhausted our * backlog wait limit */ if (gfpflags_allow_blocking(gfp_mask) && (stime > 0)) { long rtime = stime; DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&audit_backlog_wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); stime = schedule_timeout(rtime); atomic_add(rtime - stime, &audit_backlog_wait_time_actual); remove_wait_queue(&audit_backlog_wait, &wait); } else { if (audit_rate_check() && printk_ratelimit()) pr_warn("audit_backlog=%d > audit_backlog_limit=%d\n", skb_queue_len(&audit_queue), audit_backlog_limit); audit_log_lost("backlog limit exceeded"); return NULL; } } } ab = audit_buffer_alloc(ctx, gfp_mask, type); if (!ab) { audit_log_lost("out of memory in audit_log_start"); return NULL; } audit_get_stamp(ab->ctx, &t, &serial); /* cancel dummy context to enable supporting records */ if (ctx) ctx->dummy = 0; audit_log_format(ab, "audit(%llu.%03lu:%u): ", (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial); return ab; } /** * audit_expand - expand skb in the audit buffer * @ab: audit_buffer * @extra: space to add at tail of the skb * * Returns 0 (no space) on failed expansion, or available space if * successful. */ static inline int audit_expand(struct audit_buffer *ab, int extra) { struct sk_buff *skb = ab->skb; int oldtail = skb_tailroom(skb); int ret = pskb_expand_head(skb, 0, extra, ab->gfp_mask); int newtail = skb_tailroom(skb); if (ret < 0) { audit_log_lost("out of memory in audit_expand"); return 0; } skb->truesize += newtail - oldtail; return newtail; } /* * Format an audit message into the audit buffer. If there isn't enough * room in the audit buffer, more room will be allocated and vsnprint * will be called a second time. Currently, we assume that a printk * can't format message larger than 1024 bytes, so we don't either. */ static __printf(2, 0) void audit_log_vformat(struct audit_buffer *ab, const char *fmt, va_list args) { int len, avail; struct sk_buff *skb; va_list args2; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); if (avail == 0) { avail = audit_expand(ab, AUDIT_BUFSIZ); if (!avail) goto out; } va_copy(args2, args); len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args); if (len >= avail) { /* The printk buffer is 1024 bytes long, so if we get * here and AUDIT_BUFSIZ is at least 1024, then we can * log everything that printk could have logged. */ avail = audit_expand(ab, max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail)); if (!avail) goto out_va_end; len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2); } if (len > 0) skb_put(skb, len); out_va_end: va_end(args2); out: return; } /** * audit_log_format - format a message into the audit buffer. * @ab: audit_buffer * @fmt: format string * @...: optional parameters matching @fmt string * * All the work is done in audit_log_vformat. */ void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { va_list args; if (!ab) return; va_start(args, fmt); audit_log_vformat(ab, fmt, args); va_end(args); } /** * audit_log_n_hex - convert a buffer to hex and append it to the audit skb * @ab: the audit_buffer * @buf: buffer to convert to hex * @len: length of @buf to be converted * * No return value; failure to expand is silently ignored. * * This function will take the passed buf and convert it into a string of * ascii hex digits. The new string is placed onto the skb. */ void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { int i, avail, new_len; unsigned char *ptr; struct sk_buff *skb; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); new_len = len<<1; if (new_len >= avail) { /* Round the buffer request up to the next multiple */ new_len = AUDIT_BUFSIZ*(((new_len-avail)/AUDIT_BUFSIZ) + 1); avail = audit_expand(ab, new_len); if (!avail) return; } ptr = skb_tail_pointer(skb); for (i = 0; i < len; i++) ptr = hex_byte_pack_upper(ptr, buf[i]); *ptr = 0; skb_put(skb, len << 1); /* new string is twice the old string */ } /* * Format a string of no more than slen characters into the audit buffer, * enclosed in quote marks. */ void audit_log_n_string(struct audit_buffer *ab, const char *string, size_t slen) { int avail, new_len; unsigned char *ptr; struct sk_buff *skb; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); new_len = slen + 3; /* enclosing quotes + null terminator */ if (new_len > avail) { avail = audit_expand(ab, new_len); if (!avail) return; } ptr = skb_tail_pointer(skb); *ptr++ = '"'; memcpy(ptr, string, slen); ptr += slen; *ptr++ = '"'; *ptr = 0; skb_put(skb, slen + 2); /* don't include null terminator */ } /** * audit_string_contains_control - does a string need to be logged in hex * @string: string to be checked * @len: max length of the string to check */ bool audit_string_contains_control(const char *string, size_t len) { const unsigned char *p; for (p = string; p < (const unsigned char *)string + len; p++) { if (*p == '"' || *p < 0x21 || *p > 0x7e) return true; } return false; } /** * audit_log_n_untrustedstring - log a string that may contain random characters * @ab: audit_buffer * @string: string to be logged * @len: length of string (not including trailing null) * * This code will escape a string that is passed to it if the string * contains a control character, unprintable character, double quote mark, * or a space. Unescaped strings will start and end with a double quote mark. * Strings that are escaped are printed in hex (2 digits per char). * * The caller specifies the number of characters in the string to log, which may * or may not be the entire string. */ void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t len) { if (audit_string_contains_control(string, len)) audit_log_n_hex(ab, string, len); else audit_log_n_string(ab, string, len); } /** * audit_log_untrustedstring - log a string that may contain random characters * @ab: audit_buffer * @string: string to be logged * * Same as audit_log_n_untrustedstring(), except that strlen is used to * determine string length. */ void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { audit_log_n_untrustedstring(ab, string, strlen(string)); } /* This is a helper-function to print the escaped d_path */ void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { char *p, *pathname; if (prefix) audit_log_format(ab, "%s", prefix); /* We will allow 11 spaces for ' (deleted)' to be appended */ pathname = kmalloc(PATH_MAX+11, ab->gfp_mask); if (!pathname) { audit_log_format(ab, "\"<no_memory>\""); return; } p = d_path(path, pathname, PATH_MAX+11); if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */ /* FIXME: can we save some information here? */ audit_log_format(ab, "\"<too_long>\""); } else audit_log_untrustedstring(ab, p); kfree(pathname); } void audit_log_session_info(struct audit_buffer *ab) { unsigned int sessionid = audit_get_sessionid(current); uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current)); audit_log_format(ab, "auid=%u ses=%u", auid, sessionid); } void audit_log_key(struct audit_buffer *ab, char *key) { audit_log_format(ab, " key="); if (key) audit_log_untrustedstring(ab, key); else audit_log_format(ab, "(null)"); } int audit_log_task_context(struct audit_buffer *ab) { struct lsm_prop prop; struct lsm_context ctx; int error; security_current_getlsmprop_subj(&prop); if (!lsmprop_is_set(&prop)) return 0; error = security_lsmprop_to_secctx(&prop, &ctx); if (error < 0) { if (error != -EINVAL) goto error_path; return 0; } audit_log_format(ab, " subj=%s", ctx.context); security_release_secctx(&ctx); return 0; error_path: audit_panic("error in audit_log_task_context"); return error; } EXPORT_SYMBOL(audit_log_task_context); void audit_log_d_path_exe(struct audit_buffer *ab, struct mm_struct *mm) { struct file *exe_file; if (!mm) goto out_null; exe_file = get_mm_exe_file(mm); if (!exe_file) goto out_null; audit_log_d_path(ab, " exe=", &exe_file->f_path); fput(exe_file); return; out_null: audit_log_format(ab, " exe=(null)"); } struct tty_struct *audit_get_tty(void) { struct tty_struct *tty = NULL; unsigned long flags; spin_lock_irqsave(¤t->sighand->siglock, flags); if (current->signal) tty = tty_kref_get(current->signal->tty); spin_unlock_irqrestore(¤t->sighand->siglock, flags); return tty; } void audit_put_tty(struct tty_struct *tty) { tty_kref_put(tty); } void audit_log_task_info(struct audit_buffer *ab) { const struct cred *cred; char comm[sizeof(current->comm)]; struct tty_struct *tty; if (!ab) return; cred = current_cred(); tty = audit_get_tty(); audit_log_format(ab, " ppid=%d pid=%d auid=%u uid=%u gid=%u" " euid=%u suid=%u fsuid=%u" " egid=%u sgid=%u fsgid=%u tty=%s ses=%u", task_ppid_nr(current), task_tgid_nr(current), from_kuid(&init_user_ns, audit_get_loginuid(current)), from_kuid(&init_user_ns, cred->uid), from_kgid(&init_user_ns, cred->gid), from_kuid(&init_user_ns, cred->euid), from_kuid(&init_user_ns, cred->suid), from_kuid(&init_user_ns, cred->fsuid), from_kgid(&init_user_ns, cred->egid), from_kgid(&init_user_ns, cred->sgid), from_kgid(&init_user_ns, cred->fsgid), tty ? tty_name(tty) : "(none)", audit_get_sessionid(current)); audit_put_tty(tty); audit_log_format(ab, " comm="); audit_log_untrustedstring(ab, get_task_comm(comm, current)); audit_log_d_path_exe(ab, current->mm); audit_log_task_context(ab); } EXPORT_SYMBOL(audit_log_task_info); /** * audit_log_path_denied - report a path restriction denial * @type: audit message type (AUDIT_ANOM_LINK, AUDIT_ANOM_CREAT, etc) * @operation: specific operation name */ void audit_log_path_denied(int type, const char *operation) { struct audit_buffer *ab; if (!audit_enabled) return; /* Generate log with subject, operation, outcome. */ ab = audit_log_start(audit_context(), GFP_KERNEL, type); if (!ab) return; audit_log_format(ab, "op=%s", operation); audit_log_task_info(ab); audit_log_format(ab, " res=0"); audit_log_end(ab); } /* global counter which is incremented every time something logs in */ static atomic_t session_id = ATOMIC_INIT(0); static int audit_set_loginuid_perm(kuid_t loginuid) { /* if we are unset, we don't need privs */ if (!audit_loginuid_set(current)) return 0; /* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/ if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE)) return -EPERM; /* it is set, you need permission */ if (!capable(CAP_AUDIT_CONTROL)) return -EPERM; /* reject if this is not an unset and we don't allow that */ if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid)) return -EPERM; return 0; } static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, unsigned int oldsessionid, unsigned int sessionid, int rc) { struct audit_buffer *ab; uid_t uid, oldloginuid, loginuid; struct tty_struct *tty; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_LOGIN); if (!ab) return; uid = from_kuid(&init_user_ns, task_uid(current)); oldloginuid = from_kuid(&init_user_ns, koldloginuid); loginuid = from_kuid(&init_user_ns, kloginuid); tty = audit_get_tty(); audit_log_format(ab, "pid=%d uid=%u", task_tgid_nr(current), uid); audit_log_task_context(ab); audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d", oldloginuid, loginuid, tty ? tty_name(tty) : "(none)", oldsessionid, sessionid, !rc); audit_put_tty(tty); audit_log_end(ab); } /** * audit_set_loginuid - set current task's loginuid * @loginuid: loginuid value * * Returns 0. * * Called (set) from fs/proc/base.c::proc_loginuid_write(). */ int audit_set_loginuid(kuid_t loginuid) { unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET; kuid_t oldloginuid; int rc; oldloginuid = audit_get_loginuid(current); oldsessionid = audit_get_sessionid(current); rc = audit_set_loginuid_perm(loginuid); if (rc) goto out; /* are we setting or clearing? */ if (uid_valid(loginuid)) { sessionid = (unsigned int)atomic_inc_return(&session_id); if (unlikely(sessionid == AUDIT_SID_UNSET)) sessionid = (unsigned int)atomic_inc_return(&session_id); } current->sessionid = sessionid; current->loginuid = loginuid; out: audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc); return rc; } /** * audit_signal_info - record signal info for shutting down audit subsystem * @sig: signal value * @t: task being signaled * * If the audit subsystem is being terminated, record the task (pid) * and uid that is doing that. */ int audit_signal_info(int sig, struct task_struct *t) { kuid_t uid = current_uid(), auid; if (auditd_test_task(t) && (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2)) { audit_sig_pid = task_tgid_nr(current); auid = audit_get_loginuid(current); if (uid_valid(auid)) audit_sig_uid = auid; else audit_sig_uid = uid; security_current_getlsmprop_subj(&audit_sig_lsm); } return audit_signal_info_syscall(t); } /** * audit_log_end - end one audit record * @ab: the audit_buffer * * We can not do a netlink send inside an irq context because it blocks (last * arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed on a * queue and a kthread is scheduled to remove them from the queue outside the * irq context. May be called in any context. */ void audit_log_end(struct audit_buffer *ab) { struct sk_buff *skb; struct nlmsghdr *nlh; if (!ab) return; if (audit_rate_check()) { skb = ab->skb; ab->skb = NULL; /* setup the netlink header, see the comments in * kauditd_send_multicast_skb() for length quirks */ nlh = nlmsg_hdr(skb); nlh->nlmsg_len = skb->len - NLMSG_HDRLEN; /* queue the netlink packet and poke the kauditd thread */ skb_queue_tail(&audit_queue, skb); wake_up_interruptible(&kauditd_wait); } else audit_log_lost("rate limit exceeded"); audit_buffer_free(ab); } /** * audit_log - Log an audit record * @ctx: audit context * @gfp_mask: type of allocation * @type: audit message type * @fmt: format string to use * @...: variable parameters matching the format string * * This is a convenience function that calls audit_log_start, * audit_log_vformat, and audit_log_end. It may be called * in any context. */ void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { struct audit_buffer *ab; va_list args; ab = audit_log_start(ctx, gfp_mask, type); if (ab) { va_start(args, fmt); audit_log_vformat(ab, fmt, args); va_end(args); audit_log_end(ab); } } EXPORT_SYMBOL(audit_log_start); EXPORT_SYMBOL(audit_log_end); EXPORT_SYMBOL(audit_log_format); EXPORT_SYMBOL(audit_log); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Internal header to deal with irq_desc->status which will be renamed * to irq_desc->settings. */ enum { _IRQ_DEFAULT_INIT_FLAGS = IRQ_DEFAULT_INIT_FLAGS, _IRQ_PER_CPU = IRQ_PER_CPU, _IRQ_LEVEL = IRQ_LEVEL, _IRQ_NOPROBE = IRQ_NOPROBE, _IRQ_NOREQUEST = IRQ_NOREQUEST, _IRQ_NOTHREAD = IRQ_NOTHREAD, _IRQ_NOAUTOEN = IRQ_NOAUTOEN, _IRQ_NO_BALANCING = IRQ_NO_BALANCING, _IRQ_NESTED_THREAD = IRQ_NESTED_THREAD, _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, _IRQ_IS_POLLED = IRQ_IS_POLLED, _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, _IRQ_HIDDEN = IRQ_HIDDEN, _IRQ_NO_DEBUG = IRQ_NO_DEBUG, _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, }; #define IRQ_PER_CPU GOT_YOU_MORON #define IRQ_NO_BALANCING GOT_YOU_MORON #define IRQ_LEVEL GOT_YOU_MORON #define IRQ_NOPROBE GOT_YOU_MORON #define IRQ_NOREQUEST GOT_YOU_MORON #define IRQ_NOTHREAD GOT_YOU_MORON #define IRQ_NOAUTOEN GOT_YOU_MORON #define IRQ_NESTED_THREAD GOT_YOU_MORON #define IRQ_PER_CPU_DEVID GOT_YOU_MORON #define IRQ_IS_POLLED GOT_YOU_MORON #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON #define IRQ_HIDDEN GOT_YOU_MORON #define IRQ_NO_DEBUG GOT_YOU_MORON #undef IRQF_MODIFY_MASK #define IRQF_MODIFY_MASK GOT_YOU_MORON static inline void irq_settings_clr_and_set(struct irq_desc *desc, u32 clr, u32 set) { desc->status_use_accessors &= ~(clr & _IRQF_MODIFY_MASK); desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); } static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_PER_CPU; } static inline bool irq_settings_is_per_cpu_devid(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_PER_CPU_DEVID; } static inline void irq_settings_set_per_cpu(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_PER_CPU; } static inline void irq_settings_set_no_balancing(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NO_BALANCING; } static inline bool irq_settings_has_no_balance_set(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_NO_BALANCING; } static inline u32 irq_settings_get_trigger_mask(struct irq_desc *desc) { return desc->status_use_accessors & IRQ_TYPE_SENSE_MASK; } static inline void irq_settings_set_trigger_mask(struct irq_desc *desc, u32 mask) { desc->status_use_accessors &= ~IRQ_TYPE_SENSE_MASK; desc->status_use_accessors |= mask & IRQ_TYPE_SENSE_MASK; } static inline bool irq_settings_is_level(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_LEVEL; } static inline void irq_settings_clr_level(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_LEVEL; } static inline void irq_settings_set_level(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_LEVEL; } static inline bool irq_settings_can_request(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOREQUEST); } static inline void irq_settings_clr_norequest(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_NOREQUEST; } static inline void irq_settings_set_norequest(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NOREQUEST; } static inline bool irq_settings_can_thread(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOTHREAD); } static inline void irq_settings_clr_nothread(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_NOTHREAD; } static inline void irq_settings_set_nothread(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NOTHREAD; } static inline bool irq_settings_can_probe(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOPROBE); } static inline void irq_settings_clr_noprobe(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_NOPROBE; } static inline void irq_settings_set_noprobe(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NOPROBE; } static inline bool irq_settings_can_autoenable(struct irq_desc *desc) { return !(desc->status_use_accessors & _IRQ_NOAUTOEN); } static inline bool irq_settings_is_nested_thread(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_NESTED_THREAD; } static inline bool irq_settings_is_polled(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_IS_POLLED; } static inline bool irq_settings_disable_unlazy(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_DISABLE_UNLAZY; } static inline void irq_settings_clr_disable_unlazy(struct irq_desc *desc) { desc->status_use_accessors &= ~_IRQ_DISABLE_UNLAZY; } static inline bool irq_settings_is_hidden(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_HIDDEN; } static inline void irq_settings_set_no_debug(struct irq_desc *desc) { desc->status_use_accessors |= _IRQ_NO_DEBUG; } static inline bool irq_settings_no_debug(struct irq_desc *desc) { return desc->status_use_accessors & _IRQ_NO_DEBUG; } |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 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 10752 10753 10754 10755 10756 10757 10758 10759 10760 10761 10762 10763 10764 10765 10766 10767 10768 10769 10770 10771 10772 10773 10774 10775 10776 10777 10778 10779 10780 10781 10782 10783 10784 10785 10786 10787 10788 10789 10790 10791 10792 10793 10794 10795 10796 10797 10798 10799 10800 10801 10802 10803 10804 10805 10806 10807 10808 10809 10810 10811 10812 10813 10814 10815 10816 10817 10818 10819 10820 10821 10822 10823 10824 10825 10826 10827 10828 10829 10830 10831 10832 10833 10834 10835 10836 10837 10838 10839 10840 10841 10842 10843 10844 10845 10846 10847 10848 10849 10850 10851 10852 10853 10854 10855 10856 10857 10858 10859 10860 10861 10862 10863 10864 10865 10866 10867 10868 10869 10870 10871 10872 10873 10874 10875 10876 10877 10878 10879 10880 10881 10882 10883 10884 10885 10886 10887 10888 10889 10890 10891 10892 10893 10894 10895 10896 10897 10898 10899 10900 10901 10902 10903 10904 10905 10906 10907 10908 10909 10910 10911 10912 10913 10914 10915 10916 10917 10918 10919 10920 10921 10922 10923 10924 10925 10926 10927 10928 10929 10930 10931 10932 10933 10934 10935 10936 10937 10938 10939 10940 10941 10942 10943 10944 10945 10946 10947 10948 10949 10950 10951 10952 10953 10954 10955 10956 10957 10958 10959 10960 10961 10962 10963 10964 10965 10966 10967 10968 10969 10970 10971 10972 10973 10974 10975 10976 10977 10978 10979 10980 10981 10982 10983 10984 10985 10986 10987 10988 10989 10990 10991 10992 10993 10994 10995 10996 10997 10998 10999 11000 11001 11002 11003 11004 11005 11006 11007 11008 11009 11010 11011 11012 11013 11014 11015 11016 11017 11018 11019 11020 11021 11022 11023 11024 11025 11026 11027 11028 11029 11030 11031 11032 11033 11034 11035 11036 11037 11038 11039 11040 11041 11042 11043 11044 11045 11046 11047 11048 11049 11050 11051 11052 11053 11054 11055 11056 11057 11058 11059 11060 11061 11062 11063 11064 11065 11066 11067 11068 11069 11070 11071 11072 11073 11074 11075 11076 11077 11078 11079 11080 11081 11082 11083 11084 11085 11086 11087 11088 11089 11090 11091 11092 11093 11094 11095 11096 11097 11098 11099 11100 11101 11102 11103 11104 11105 11106 11107 11108 11109 11110 11111 11112 11113 11114 11115 11116 11117 11118 11119 11120 11121 11122 11123 11124 11125 11126 11127 11128 11129 11130 11131 11132 11133 11134 11135 11136 11137 11138 11139 11140 11141 11142 11143 11144 11145 11146 11147 11148 11149 11150 11151 11152 11153 11154 11155 11156 11157 11158 11159 11160 11161 11162 11163 11164 11165 11166 11167 11168 11169 11170 11171 11172 11173 11174 11175 11176 11177 11178 11179 11180 11181 11182 11183 11184 11185 11186 11187 11188 11189 11190 11191 11192 11193 11194 11195 11196 11197 11198 11199 11200 11201 11202 11203 11204 11205 11206 11207 11208 11209 11210 11211 11212 11213 11214 11215 11216 | // SPDX-License-Identifier: GPL-2.0 /* * ring buffer based function tracer * * Copyright (C) 2007-2012 Steven Rostedt <srostedt@redhat.com> * Copyright (C) 2008 Ingo Molnar <mingo@redhat.com> * * Originally taken from the RT patch by: * Arnaldo Carvalho de Melo <acme@redhat.com> * * Based on code from the latency_tracer, that is: * Copyright (C) 2004-2006 Ingo Molnar * Copyright (C) 2004 Nadia Yvette Chambers */ #include <linux/ring_buffer.h> #include <linux/utsname.h> #include <linux/stacktrace.h> #include <linux/writeback.h> #include <linux/kallsyms.h> #include <linux/security.h> #include <linux/seq_file.h> #include <linux/irqflags.h> #include <linux/debugfs.h> #include <linux/tracefs.h> #include <linux/pagemap.h> #include <linux/hardirq.h> #include <linux/linkage.h> #include <linux/uaccess.h> #include <linux/cleanup.h> #include <linux/vmalloc.h> #include <linux/ftrace.h> #include <linux/module.h> #include <linux/percpu.h> #include <linux/splice.h> #include <linux/kdebug.h> #include <linux/string.h> #include <linux/mount.h> #include <linux/rwsem.h> #include <linux/slab.h> #include <linux/ctype.h> #include <linux/init.h> #include <linux/panic_notifier.h> #include <linux/poll.h> #include <linux/nmi.h> #include <linux/fs.h> #include <linux/trace.h> #include <linux/sched/clock.h> #include <linux/sched/rt.h> #include <linux/fsnotify.h> #include <linux/irq_work.h> #include <linux/workqueue.h> #include <linux/sort.h> #include <linux/io.h> /* vmap_page_range() */ #include <linux/fs_context.h> #include <asm/setup.h> /* COMMAND_LINE_SIZE */ #include "trace.h" #include "trace_output.h" #ifdef CONFIG_FTRACE_STARTUP_TEST /* * We need to change this state when a selftest is running. * A selftest will lurk into the ring-buffer to count the * entries inserted during the selftest although some concurrent * insertions into the ring-buffer such as trace_printk could occurred * at the same time, giving false positive or negative results. */ static bool __read_mostly tracing_selftest_running; /* * If boot-time tracing including tracers/events via kernel cmdline * is running, we do not want to run SELFTEST. */ bool __read_mostly tracing_selftest_disabled; void __init disable_tracing_selftest(const char *reason) { if (!tracing_selftest_disabled) { tracing_selftest_disabled = true; pr_info("Ftrace startup test is disabled due to %s\n", reason); } } #else #define tracing_selftest_running 0 #define tracing_selftest_disabled 0 #endif /* Pipe tracepoints to printk */ static struct trace_iterator *tracepoint_print_iter; int tracepoint_printk; static bool tracepoint_printk_stop_on_boot __initdata; static bool traceoff_after_boot __initdata; static DEFINE_STATIC_KEY_FALSE(tracepoint_printk_key); /* For tracers that don't implement custom flags */ static struct tracer_opt dummy_tracer_opt[] = { { } }; static int dummy_set_flag(struct trace_array *tr, u32 old_flags, u32 bit, int set) { return 0; } /* * To prevent the comm cache from being overwritten when no * tracing is active, only save the comm when a trace event * occurred. */ DEFINE_PER_CPU(bool, trace_taskinfo_save); /* * Kill all tracing for good (never come back). * It is initialized to 1 but will turn to zero if the initialization * of the tracer is successful. But that is the only place that sets * this back to zero. */ static int tracing_disabled = 1; cpumask_var_t __read_mostly tracing_buffer_mask; #define MAX_TRACER_SIZE 100 /* * ftrace_dump_on_oops - variable to dump ftrace buffer on oops * * If there is an oops (or kernel panic) and the ftrace_dump_on_oops * is set, then ftrace_dump is called. This will output the contents * of the ftrace buffers to the console. This is very useful for * capturing traces that lead to crashes and outputing it to a * serial console. * * It is default off, but you can enable it with either specifying * "ftrace_dump_on_oops" in the kernel command line, or setting * /proc/sys/kernel/ftrace_dump_on_oops * Set 1 if you want to dump buffers of all CPUs * Set 2 if you want to dump the buffer of the CPU that triggered oops * Set instance name if you want to dump the specific trace instance * Multiple instance dump is also supported, and instances are seperated * by commas. */ /* Set to string format zero to disable by default */ char ftrace_dump_on_oops[MAX_TRACER_SIZE] = "0"; /* When set, tracing will stop when a WARN*() is hit */ static int __disable_trace_on_warning; int tracepoint_printk_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); static const struct ctl_table trace_sysctl_table[] = { { .procname = "ftrace_dump_on_oops", .data = &ftrace_dump_on_oops, .maxlen = MAX_TRACER_SIZE, .mode = 0644, .proc_handler = proc_dostring, }, { .procname = "traceoff_on_warning", .data = &__disable_trace_on_warning, .maxlen = sizeof(__disable_trace_on_warning), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "tracepoint_printk", .data = &tracepoint_printk, .maxlen = sizeof(tracepoint_printk), .mode = 0644, .proc_handler = tracepoint_printk_sysctl, }, }; static int __init init_trace_sysctls(void) { register_sysctl_init("kernel", trace_sysctl_table); return 0; } subsys_initcall(init_trace_sysctls); #ifdef CONFIG_TRACE_EVAL_MAP_FILE /* Map of enums to their values, for "eval_map" file */ struct trace_eval_map_head { struct module *mod; unsigned long length; }; union trace_eval_map_item; struct trace_eval_map_tail { /* * "end" is first and points to NULL as it must be different * than "mod" or "eval_string" */ union trace_eval_map_item *next; const char *end; /* points to NULL */ }; static DEFINE_MUTEX(trace_eval_mutex); /* * The trace_eval_maps are saved in an array with two extra elements, * one at the beginning, and one at the end. The beginning item contains * the count of the saved maps (head.length), and the module they * belong to if not built in (head.mod). The ending item contains a * pointer to the next array of saved eval_map items. */ union trace_eval_map_item { struct trace_eval_map map; struct trace_eval_map_head head; struct trace_eval_map_tail tail; }; static union trace_eval_map_item *trace_eval_maps; #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ int tracing_set_tracer(struct trace_array *tr, const char *buf); static void ftrace_trace_userstack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx); static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata; static char *default_bootup_tracer; static bool allocate_snapshot; static bool snapshot_at_boot; static char boot_instance_info[COMMAND_LINE_SIZE] __initdata; static int boot_instance_index; static char boot_snapshot_info[COMMAND_LINE_SIZE] __initdata; static int boot_snapshot_index; static int __init set_cmdline_ftrace(char *str) { strscpy(bootup_tracer_buf, str, MAX_TRACER_SIZE); default_bootup_tracer = bootup_tracer_buf; /* We are using ftrace early, expand it */ trace_set_ring_buffer_expanded(NULL); return 1; } __setup("ftrace=", set_cmdline_ftrace); int ftrace_dump_on_oops_enabled(void) { if (!strcmp("0", ftrace_dump_on_oops)) return 0; else return 1; } static int __init set_ftrace_dump_on_oops(char *str) { if (!*str) { strscpy(ftrace_dump_on_oops, "1", MAX_TRACER_SIZE); return 1; } if (*str == ',') { strscpy(ftrace_dump_on_oops, "1", MAX_TRACER_SIZE); strscpy(ftrace_dump_on_oops + 1, str, MAX_TRACER_SIZE - 1); return 1; } if (*str++ == '=') { strscpy(ftrace_dump_on_oops, str, MAX_TRACER_SIZE); return 1; } return 0; } __setup("ftrace_dump_on_oops", set_ftrace_dump_on_oops); static int __init stop_trace_on_warning(char *str) { if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0)) __disable_trace_on_warning = 1; return 1; } __setup("traceoff_on_warning", stop_trace_on_warning); static int __init boot_alloc_snapshot(char *str) { char *slot = boot_snapshot_info + boot_snapshot_index; int left = sizeof(boot_snapshot_info) - boot_snapshot_index; int ret; if (str[0] == '=') { str++; if (strlen(str) >= left) return -1; ret = snprintf(slot, left, "%s\t", str); boot_snapshot_index += ret; } else { allocate_snapshot = true; /* We also need the main ring buffer expanded */ trace_set_ring_buffer_expanded(NULL); } return 1; } __setup("alloc_snapshot", boot_alloc_snapshot); static int __init boot_snapshot(char *str) { snapshot_at_boot = true; boot_alloc_snapshot(str); return 1; } __setup("ftrace_boot_snapshot", boot_snapshot); static int __init boot_instance(char *str) { char *slot = boot_instance_info + boot_instance_index; int left = sizeof(boot_instance_info) - boot_instance_index; int ret; if (strlen(str) >= left) return -1; ret = snprintf(slot, left, "%s\t", str); boot_instance_index += ret; return 1; } __setup("trace_instance=", boot_instance); static char trace_boot_options_buf[MAX_TRACER_SIZE] __initdata; static int __init set_trace_boot_options(char *str) { strscpy(trace_boot_options_buf, str, MAX_TRACER_SIZE); return 1; } __setup("trace_options=", set_trace_boot_options); static char trace_boot_clock_buf[MAX_TRACER_SIZE] __initdata; static char *trace_boot_clock __initdata; static int __init set_trace_boot_clock(char *str) { strscpy(trace_boot_clock_buf, str, MAX_TRACER_SIZE); trace_boot_clock = trace_boot_clock_buf; return 1; } __setup("trace_clock=", set_trace_boot_clock); static int __init set_tracepoint_printk(char *str) { /* Ignore the "tp_printk_stop_on_boot" param */ if (*str == '_') return 0; if ((strcmp(str, "=0") != 0 && strcmp(str, "=off") != 0)) tracepoint_printk = 1; return 1; } __setup("tp_printk", set_tracepoint_printk); static int __init set_tracepoint_printk_stop(char *str) { tracepoint_printk_stop_on_boot = true; return 1; } __setup("tp_printk_stop_on_boot", set_tracepoint_printk_stop); static int __init set_traceoff_after_boot(char *str) { traceoff_after_boot = true; return 1; } __setup("traceoff_after_boot", set_traceoff_after_boot); unsigned long long ns2usecs(u64 nsec) { nsec += 500; do_div(nsec, 1000); return nsec; } static void trace_process_export(struct trace_export *export, struct ring_buffer_event *event, int flag) { struct trace_entry *entry; unsigned int size = 0; if (export->flags & flag) { entry = ring_buffer_event_data(event); size = ring_buffer_event_length(event); export->write(export, entry, size); } } static DEFINE_MUTEX(ftrace_export_lock); static struct trace_export __rcu *ftrace_exports_list __read_mostly; static DEFINE_STATIC_KEY_FALSE(trace_function_exports_enabled); static DEFINE_STATIC_KEY_FALSE(trace_event_exports_enabled); static DEFINE_STATIC_KEY_FALSE(trace_marker_exports_enabled); static inline void ftrace_exports_enable(struct trace_export *export) { if (export->flags & TRACE_EXPORT_FUNCTION) static_branch_inc(&trace_function_exports_enabled); if (export->flags & TRACE_EXPORT_EVENT) static_branch_inc(&trace_event_exports_enabled); if (export->flags & TRACE_EXPORT_MARKER) static_branch_inc(&trace_marker_exports_enabled); } static inline void ftrace_exports_disable(struct trace_export *export) { if (export->flags & TRACE_EXPORT_FUNCTION) static_branch_dec(&trace_function_exports_enabled); if (export->flags & TRACE_EXPORT_EVENT) static_branch_dec(&trace_event_exports_enabled); if (export->flags & TRACE_EXPORT_MARKER) static_branch_dec(&trace_marker_exports_enabled); } static void ftrace_exports(struct ring_buffer_event *event, int flag) { struct trace_export *export; guard(preempt_notrace)(); export = rcu_dereference_raw_check(ftrace_exports_list); while (export) { trace_process_export(export, event, flag); export = rcu_dereference_raw_check(export->next); } } static inline void add_trace_export(struct trace_export **list, struct trace_export *export) { rcu_assign_pointer(export->next, *list); /* * We are entering export into the list but another * CPU might be walking that list. We need to make sure * the export->next pointer is valid before another CPU sees * the export pointer included into the list. */ rcu_assign_pointer(*list, export); } static inline int rm_trace_export(struct trace_export **list, struct trace_export *export) { struct trace_export **p; for (p = list; *p != NULL; p = &(*p)->next) if (*p == export) break; if (*p != export) return -1; rcu_assign_pointer(*p, (*p)->next); return 0; } static inline void add_ftrace_export(struct trace_export **list, struct trace_export *export) { ftrace_exports_enable(export); add_trace_export(list, export); } static inline int rm_ftrace_export(struct trace_export **list, struct trace_export *export) { int ret; ret = rm_trace_export(list, export); ftrace_exports_disable(export); return ret; } int register_ftrace_export(struct trace_export *export) { if (WARN_ON_ONCE(!export->write)) return -1; guard(mutex)(&ftrace_export_lock); add_ftrace_export(&ftrace_exports_list, export); return 0; } EXPORT_SYMBOL_GPL(register_ftrace_export); int unregister_ftrace_export(struct trace_export *export) { guard(mutex)(&ftrace_export_lock); return rm_ftrace_export(&ftrace_exports_list, export); } EXPORT_SYMBOL_GPL(unregister_ftrace_export); /* trace_flags holds trace_options default values */ #define TRACE_DEFAULT_FLAGS \ (FUNCTION_DEFAULT_FLAGS | \ TRACE_ITER_PRINT_PARENT | TRACE_ITER_PRINTK | \ TRACE_ITER_ANNOTATE | TRACE_ITER_CONTEXT_INFO | \ TRACE_ITER_RECORD_CMD | TRACE_ITER_OVERWRITE | \ TRACE_ITER_IRQ_INFO | TRACE_ITER_MARKERS | \ TRACE_ITER_HASH_PTR | TRACE_ITER_TRACE_PRINTK | \ TRACE_ITER_COPY_MARKER) /* trace_options that are only supported by global_trace */ #define TOP_LEVEL_TRACE_FLAGS (TRACE_ITER_PRINTK | \ TRACE_ITER_PRINTK_MSGONLY | TRACE_ITER_RECORD_CMD) /* trace_flags that are default zero for instances */ #define ZEROED_TRACE_FLAGS \ (TRACE_ITER_EVENT_FORK | TRACE_ITER_FUNC_FORK | TRACE_ITER_TRACE_PRINTK | \ TRACE_ITER_COPY_MARKER) /* * The global_trace is the descriptor that holds the top-level tracing * buffers for the live tracing. */ static struct trace_array global_trace = { .trace_flags = TRACE_DEFAULT_FLAGS, }; static struct trace_array *printk_trace = &global_trace; /* List of trace_arrays interested in the top level trace_marker */ static LIST_HEAD(marker_copies); static __always_inline bool printk_binsafe(struct trace_array *tr) { /* * The binary format of traceprintk can cause a crash if used * by a buffer from another boot. Force the use of the * non binary version of trace_printk if the trace_printk * buffer is a boot mapped ring buffer. */ return !(tr->flags & TRACE_ARRAY_FL_BOOT); } static void update_printk_trace(struct trace_array *tr) { if (printk_trace == tr) return; printk_trace->trace_flags &= ~TRACE_ITER_TRACE_PRINTK; printk_trace = tr; tr->trace_flags |= TRACE_ITER_TRACE_PRINTK; } /* Returns true if the status of tr changed */ static bool update_marker_trace(struct trace_array *tr, int enabled) { lockdep_assert_held(&event_mutex); if (enabled) { if (!list_empty(&tr->marker_list)) return false; list_add_rcu(&tr->marker_list, &marker_copies); tr->trace_flags |= TRACE_ITER_COPY_MARKER; return true; } if (list_empty(&tr->marker_list)) return false; list_del_init(&tr->marker_list); tr->trace_flags &= ~TRACE_ITER_COPY_MARKER; return true; } void trace_set_ring_buffer_expanded(struct trace_array *tr) { if (!tr) tr = &global_trace; tr->ring_buffer_expanded = true; } LIST_HEAD(ftrace_trace_arrays); int trace_array_get(struct trace_array *this_tr) { struct trace_array *tr; guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (tr == this_tr) { tr->ref++; return 0; } } return -ENODEV; } static void __trace_array_put(struct trace_array *this_tr) { WARN_ON(!this_tr->ref); this_tr->ref--; } /** * trace_array_put - Decrement the reference counter for this trace array. * @this_tr : pointer to the trace array * * NOTE: Use this when we no longer need the trace array returned by * trace_array_get_by_name(). This ensures the trace array can be later * destroyed. * */ void trace_array_put(struct trace_array *this_tr) { if (!this_tr) return; guard(mutex)(&trace_types_lock); __trace_array_put(this_tr); } EXPORT_SYMBOL_GPL(trace_array_put); int tracing_check_open_get_tr(struct trace_array *tr) { int ret; ret = security_locked_down(LOCKDOWN_TRACEFS); if (ret) return ret; if (tracing_disabled) return -ENODEV; if (tr && trace_array_get(tr) < 0) return -ENODEV; return 0; } /** * trace_find_filtered_pid - check if a pid exists in a filtered_pid list * @filtered_pids: The list of pids to check * @search_pid: The PID to find in @filtered_pids * * Returns true if @search_pid is found in @filtered_pids, and false otherwise. */ bool trace_find_filtered_pid(struct trace_pid_list *filtered_pids, pid_t search_pid) { return trace_pid_list_is_set(filtered_pids, search_pid); } /** * trace_ignore_this_task - should a task be ignored for tracing * @filtered_pids: The list of pids to check * @filtered_no_pids: The list of pids not to be traced * @task: The task that should be ignored if not filtered * * Checks if @task should be traced or not from @filtered_pids. * Returns true if @task should *NOT* be traced. * Returns false if @task should be traced. */ bool trace_ignore_this_task(struct trace_pid_list *filtered_pids, struct trace_pid_list *filtered_no_pids, struct task_struct *task) { /* * If filtered_no_pids is not empty, and the task's pid is listed * in filtered_no_pids, then return true. * Otherwise, if filtered_pids is empty, that means we can * trace all tasks. If it has content, then only trace pids * within filtered_pids. */ return (filtered_pids && !trace_find_filtered_pid(filtered_pids, task->pid)) || (filtered_no_pids && trace_find_filtered_pid(filtered_no_pids, task->pid)); } /** * trace_filter_add_remove_task - Add or remove a task from a pid_list * @pid_list: The list to modify * @self: The current task for fork or NULL for exit * @task: The task to add or remove * * If adding a task, if @self is defined, the task is only added if @self * is also included in @pid_list. This happens on fork and tasks should * only be added when the parent is listed. If @self is NULL, then the * @task pid will be removed from the list, which would happen on exit * of a task. */ void trace_filter_add_remove_task(struct trace_pid_list *pid_list, struct task_struct *self, struct task_struct *task) { if (!pid_list) return; /* For forks, we only add if the forking task is listed */ if (self) { if (!trace_find_filtered_pid(pid_list, self->pid)) return; } /* "self" is set for forks, and NULL for exits */ if (self) trace_pid_list_set(pid_list, task->pid); else trace_pid_list_clear(pid_list, task->pid); } /** * trace_pid_next - Used for seq_file to get to the next pid of a pid_list * @pid_list: The pid list to show * @v: The last pid that was shown (+1 the actual pid to let zero be displayed) * @pos: The position of the file * * This is used by the seq_file "next" operation to iterate the pids * listed in a trace_pid_list structure. * * Returns the pid+1 as we want to display pid of zero, but NULL would * stop the iteration. */ void *trace_pid_next(struct trace_pid_list *pid_list, void *v, loff_t *pos) { long pid = (unsigned long)v; unsigned int next; (*pos)++; /* pid already is +1 of the actual previous bit */ if (trace_pid_list_next(pid_list, pid, &next) < 0) return NULL; pid = next; /* Return pid + 1 to allow zero to be represented */ return (void *)(pid + 1); } /** * trace_pid_start - Used for seq_file to start reading pid lists * @pid_list: The pid list to show * @pos: The position of the file * * This is used by seq_file "start" operation to start the iteration * of listing pids. * * Returns the pid+1 as we want to display pid of zero, but NULL would * stop the iteration. */ void *trace_pid_start(struct trace_pid_list *pid_list, loff_t *pos) { unsigned long pid; unsigned int first; loff_t l = 0; if (trace_pid_list_first(pid_list, &first) < 0) return NULL; pid = first; /* Return pid + 1 so that zero can be the exit value */ for (pid++; pid && l < *pos; pid = (unsigned long)trace_pid_next(pid_list, (void *)pid, &l)) ; return (void *)pid; } /** * trace_pid_show - show the current pid in seq_file processing * @m: The seq_file structure to write into * @v: A void pointer of the pid (+1) value to display * * Can be directly used by seq_file operations to display the current * pid value. */ int trace_pid_show(struct seq_file *m, void *v) { unsigned long pid = (unsigned long)v - 1; seq_printf(m, "%lu\n", pid); return 0; } /* 128 should be much more than enough */ #define PID_BUF_SIZE 127 int trace_pid_write(struct trace_pid_list *filtered_pids, struct trace_pid_list **new_pid_list, const char __user *ubuf, size_t cnt) { struct trace_pid_list *pid_list; struct trace_parser parser; unsigned long val; int nr_pids = 0; ssize_t read = 0; ssize_t ret; loff_t pos; pid_t pid; if (trace_parser_get_init(&parser, PID_BUF_SIZE + 1)) return -ENOMEM; /* * Always recreate a new array. The write is an all or nothing * operation. Always create a new array when adding new pids by * the user. If the operation fails, then the current list is * not modified. */ pid_list = trace_pid_list_alloc(); if (!pid_list) { trace_parser_put(&parser); return -ENOMEM; } if (filtered_pids) { /* copy the current bits to the new max */ ret = trace_pid_list_first(filtered_pids, &pid); while (!ret) { trace_pid_list_set(pid_list, pid); ret = trace_pid_list_next(filtered_pids, pid + 1, &pid); nr_pids++; } } ret = 0; while (cnt > 0) { pos = 0; ret = trace_get_user(&parser, ubuf, cnt, &pos); if (ret < 0) break; read += ret; ubuf += ret; cnt -= ret; if (!trace_parser_loaded(&parser)) break; ret = -EINVAL; if (kstrtoul(parser.buffer, 0, &val)) break; pid = (pid_t)val; if (trace_pid_list_set(pid_list, pid) < 0) { ret = -1; break; } nr_pids++; trace_parser_clear(&parser); ret = 0; } trace_parser_put(&parser); if (ret < 0) { trace_pid_list_free(pid_list); return ret; } if (!nr_pids) { /* Cleared the list of pids */ trace_pid_list_free(pid_list); pid_list = NULL; } *new_pid_list = pid_list; return read; } static u64 buffer_ftrace_now(struct array_buffer *buf, int cpu) { u64 ts; /* Early boot up does not have a buffer yet */ if (!buf->buffer) return trace_clock_local(); ts = ring_buffer_time_stamp(buf->buffer); ring_buffer_normalize_time_stamp(buf->buffer, cpu, &ts); return ts; } u64 ftrace_now(int cpu) { return buffer_ftrace_now(&global_trace.array_buffer, cpu); } /** * tracing_is_enabled - Show if global_trace has been enabled * * Shows if the global trace has been enabled or not. It uses the * mirror flag "buffer_disabled" to be used in fast paths such as for * the irqsoff tracer. But it may be inaccurate due to races. If you * need to know the accurate state, use tracing_is_on() which is a little * slower, but accurate. */ int tracing_is_enabled(void) { /* * For quick access (irqsoff uses this in fast path), just * return the mirror variable of the state of the ring buffer. * It's a little racy, but we don't really care. */ return !global_trace.buffer_disabled; } /* * trace_buf_size is the size in bytes that is allocated * for a buffer. Note, the number of bytes is always rounded * to page size. * * This number is purposely set to a low number of 16384. * If the dump on oops happens, it will be much appreciated * to not have to wait for all that output. Anyway this can be * boot time and run time configurable. */ #define TRACE_BUF_SIZE_DEFAULT 1441792UL /* 16384 * 88 (sizeof(entry)) */ static unsigned long trace_buf_size = TRACE_BUF_SIZE_DEFAULT; /* trace_types holds a link list of available tracers. */ static struct tracer *trace_types __read_mostly; /* * trace_types_lock is used to protect the trace_types list. */ DEFINE_MUTEX(trace_types_lock); /* * serialize the access of the ring buffer * * ring buffer serializes readers, but it is low level protection. * The validity of the events (which returns by ring_buffer_peek() ..etc) * are not protected by ring buffer. * * The content of events may become garbage if we allow other process consumes * these events concurrently: * A) the page of the consumed events may become a normal page * (not reader page) in ring buffer, and this page will be rewritten * by events producer. * B) The page of the consumed events may become a page for splice_read, * and this page will be returned to system. * * These primitives allow multi process access to different cpu ring buffer * concurrently. * * These primitives don't distinguish read-only and read-consume access. * Multi read-only access are also serialized. */ #ifdef CONFIG_SMP static DECLARE_RWSEM(all_cpu_access_lock); static DEFINE_PER_CPU(struct mutex, cpu_access_lock); static inline void trace_access_lock(int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { /* gain it for accessing the whole ring buffer. */ down_write(&all_cpu_access_lock); } else { /* gain it for accessing a cpu ring buffer. */ /* Firstly block other trace_access_lock(RING_BUFFER_ALL_CPUS). */ down_read(&all_cpu_access_lock); /* Secondly block other access to this @cpu ring buffer. */ mutex_lock(&per_cpu(cpu_access_lock, cpu)); } } static inline void trace_access_unlock(int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { up_write(&all_cpu_access_lock); } else { mutex_unlock(&per_cpu(cpu_access_lock, cpu)); up_read(&all_cpu_access_lock); } } static inline void trace_access_lock_init(void) { int cpu; for_each_possible_cpu(cpu) mutex_init(&per_cpu(cpu_access_lock, cpu)); } #else static DEFINE_MUTEX(access_lock); static inline void trace_access_lock(int cpu) { (void)cpu; mutex_lock(&access_lock); } static inline void trace_access_unlock(int cpu) { (void)cpu; mutex_unlock(&access_lock); } static inline void trace_access_lock_init(void) { } #endif #ifdef CONFIG_STACKTRACE static void __ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx, int skip, struct pt_regs *regs); static inline void ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx, int skip, struct pt_regs *regs); #else static inline void __ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx, int skip, struct pt_regs *regs) { } static inline void ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned long trace_ctx, int skip, struct pt_regs *regs) { } #endif static __always_inline void trace_event_setup(struct ring_buffer_event *event, int type, unsigned int trace_ctx) { struct trace_entry *ent = ring_buffer_event_data(event); tracing_generic_entry_update(ent, type, trace_ctx); } static __always_inline struct ring_buffer_event * __trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, unsigned int trace_ctx) { struct ring_buffer_event *event; event = ring_buffer_lock_reserve(buffer, len); if (event != NULL) trace_event_setup(event, type, trace_ctx); return event; } void tracer_tracing_on(struct trace_array *tr) { if (tr->array_buffer.buffer) ring_buffer_record_on(tr->array_buffer.buffer); /* * This flag is looked at when buffers haven't been allocated * yet, or by some tracers (like irqsoff), that just want to * know if the ring buffer has been disabled, but it can handle * races of where it gets disabled but we still do a record. * As the check is in the fast path of the tracers, it is more * important to be fast than accurate. */ tr->buffer_disabled = 0; } /** * tracing_on - enable tracing buffers * * This function enables tracing buffers that may have been * disabled with tracing_off. */ void tracing_on(void) { tracer_tracing_on(&global_trace); } EXPORT_SYMBOL_GPL(tracing_on); static __always_inline void __buffer_unlock_commit(struct trace_buffer *buffer, struct ring_buffer_event *event) { __this_cpu_write(trace_taskinfo_save, true); /* If this is the temp buffer, we need to commit fully */ if (this_cpu_read(trace_buffered_event) == event) { /* Length is in event->array[0] */ ring_buffer_write(buffer, event->array[0], &event->array[1]); /* Release the temp buffer */ this_cpu_dec(trace_buffered_event_cnt); /* ring_buffer_unlock_commit() enables preemption */ preempt_enable_notrace(); } else ring_buffer_unlock_commit(buffer); } int __trace_array_puts(struct trace_array *tr, unsigned long ip, const char *str, int size) { struct ring_buffer_event *event; struct trace_buffer *buffer; struct print_entry *entry; unsigned int trace_ctx; int alloc; if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; if (unlikely(tracing_selftest_running && tr == &global_trace)) return 0; if (unlikely(tracing_disabled)) return 0; alloc = sizeof(*entry) + size + 2; /* possible \n added */ trace_ctx = tracing_gen_ctx(); buffer = tr->array_buffer.buffer; guard(ring_buffer_nest)(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc, trace_ctx); if (!event) return 0; entry = ring_buffer_event_data(event); entry->ip = ip; memcpy(&entry->buf, str, size); /* Add a newline if necessary */ if (entry->buf[size - 1] != '\n') { entry->buf[size] = '\n'; entry->buf[size + 1] = '\0'; } else entry->buf[size] = '\0'; __buffer_unlock_commit(buffer, event); ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); return size; } EXPORT_SYMBOL_GPL(__trace_array_puts); /** * __trace_puts - write a constant string into the trace buffer. * @ip: The address of the caller * @str: The constant string to write * @size: The size of the string. */ int __trace_puts(unsigned long ip, const char *str, int size) { return __trace_array_puts(printk_trace, ip, str, size); } EXPORT_SYMBOL_GPL(__trace_puts); /** * __trace_bputs - write the pointer to a constant string into trace buffer * @ip: The address of the caller * @str: The constant string to write to the buffer to */ int __trace_bputs(unsigned long ip, const char *str) { struct trace_array *tr = READ_ONCE(printk_trace); struct ring_buffer_event *event; struct trace_buffer *buffer; struct bputs_entry *entry; unsigned int trace_ctx; int size = sizeof(struct bputs_entry); if (!printk_binsafe(tr)) return __trace_puts(ip, str, strlen(str)); if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; trace_ctx = tracing_gen_ctx(); buffer = tr->array_buffer.buffer; guard(ring_buffer_nest)(buffer); event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size, trace_ctx); if (!event) return 0; entry = ring_buffer_event_data(event); entry->ip = ip; entry->str = str; __buffer_unlock_commit(buffer, event); ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL); return 1; } EXPORT_SYMBOL_GPL(__trace_bputs); #ifdef CONFIG_TRACER_SNAPSHOT static void tracing_snapshot_instance_cond(struct trace_array *tr, void *cond_data) { struct tracer *tracer = tr->current_trace; unsigned long flags; if (in_nmi()) { trace_array_puts(tr, "*** SNAPSHOT CALLED FROM NMI CONTEXT ***\n"); trace_array_puts(tr, "*** snapshot is being ignored ***\n"); return; } if (!tr->allocated_snapshot) { trace_array_puts(tr, "*** SNAPSHOT NOT ALLOCATED ***\n"); trace_array_puts(tr, "*** stopping trace here! ***\n"); tracer_tracing_off(tr); return; } /* Note, snapshot can not be used when the tracer uses it */ if (tracer->use_max_tr) { trace_array_puts(tr, "*** LATENCY TRACER ACTIVE ***\n"); trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); return; } if (tr->mapped) { trace_array_puts(tr, "*** BUFFER MEMORY MAPPED ***\n"); trace_array_puts(tr, "*** Can not use snapshot (sorry) ***\n"); return; } local_irq_save(flags); update_max_tr(tr, current, smp_processor_id(), cond_data); local_irq_restore(flags); } void tracing_snapshot_instance(struct trace_array *tr) { tracing_snapshot_instance_cond(tr, NULL); } /** * tracing_snapshot - take a snapshot of the current buffer. * * This causes a swap between the snapshot buffer and the current live * tracing buffer. You can use this to take snapshots of the live * trace when some condition is triggered, but continue to trace. * * Note, make sure to allocate the snapshot with either * a tracing_snapshot_alloc(), or by doing it manually * with: echo 1 > /sys/kernel/tracing/snapshot * * If the snapshot buffer is not allocated, it will stop tracing. * Basically making a permanent snapshot. */ void tracing_snapshot(void) { struct trace_array *tr = &global_trace; tracing_snapshot_instance(tr); } EXPORT_SYMBOL_GPL(tracing_snapshot); /** * tracing_snapshot_cond - conditionally take a snapshot of the current buffer. * @tr: The tracing instance to snapshot * @cond_data: The data to be tested conditionally, and possibly saved * * This is the same as tracing_snapshot() except that the snapshot is * conditional - the snapshot will only happen if the * cond_snapshot.update() implementation receiving the cond_data * returns true, which means that the trace array's cond_snapshot * update() operation used the cond_data to determine whether the * snapshot should be taken, and if it was, presumably saved it along * with the snapshot. */ void tracing_snapshot_cond(struct trace_array *tr, void *cond_data) { tracing_snapshot_instance_cond(tr, cond_data); } EXPORT_SYMBOL_GPL(tracing_snapshot_cond); /** * tracing_cond_snapshot_data - get the user data associated with a snapshot * @tr: The tracing instance * * When the user enables a conditional snapshot using * tracing_snapshot_cond_enable(), the user-defined cond_data is saved * with the snapshot. This accessor is used to retrieve it. * * Should not be called from cond_snapshot.update(), since it takes * the tr->max_lock lock, which the code calling * cond_snapshot.update() has already done. * * Returns the cond_data associated with the trace array's snapshot. */ void *tracing_cond_snapshot_data(struct trace_array *tr) { void *cond_data = NULL; local_irq_disable(); arch_spin_lock(&tr->max_lock); if (tr->cond_snapshot) cond_data = tr->cond_snapshot->cond_data; arch_spin_unlock(&tr->max_lock); local_irq_enable(); return cond_data; } EXPORT_SYMBOL_GPL(tracing_cond_snapshot_data); static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, struct array_buffer *size_buf, int cpu_id); static void set_buffer_entries(struct array_buffer *buf, unsigned long val); int tracing_alloc_snapshot_instance(struct trace_array *tr) { int order; int ret; if (!tr->allocated_snapshot) { /* Make the snapshot buffer have the same order as main buffer */ order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); if (ret < 0) return ret; /* allocate spare buffer */ ret = resize_buffer_duplicate_size(&tr->max_buffer, &tr->array_buffer, RING_BUFFER_ALL_CPUS); if (ret < 0) return ret; tr->allocated_snapshot = true; } return 0; } static void free_snapshot(struct trace_array *tr) { /* * We don't free the ring buffer. instead, resize it because * The max_tr ring buffer has some state (e.g. ring->clock) and * we want preserve it. */ ring_buffer_subbuf_order_set(tr->max_buffer.buffer, 0); ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); set_buffer_entries(&tr->max_buffer, 1); tracing_reset_online_cpus(&tr->max_buffer); tr->allocated_snapshot = false; } static int tracing_arm_snapshot_locked(struct trace_array *tr) { int ret; lockdep_assert_held(&trace_types_lock); spin_lock(&tr->snapshot_trigger_lock); if (tr->snapshot == UINT_MAX || tr->mapped) { spin_unlock(&tr->snapshot_trigger_lock); return -EBUSY; } tr->snapshot++; spin_unlock(&tr->snapshot_trigger_lock); ret = tracing_alloc_snapshot_instance(tr); if (ret) { spin_lock(&tr->snapshot_trigger_lock); tr->snapshot--; spin_unlock(&tr->snapshot_trigger_lock); } return ret; } int tracing_arm_snapshot(struct trace_array *tr) { guard(mutex)(&trace_types_lock); return tracing_arm_snapshot_locked(tr); } void tracing_disarm_snapshot(struct trace_array *tr) { spin_lock(&tr->snapshot_trigger_lock); if (!WARN_ON(!tr->snapshot)) tr->snapshot--; spin_unlock(&tr->snapshot_trigger_lock); } /** * tracing_alloc_snapshot - allocate snapshot buffer. * * This only allocates the snapshot buffer if it isn't already * allocated - it doesn't also take a snapshot. * * This is meant to be used in cases where the snapshot buffer needs * to be set up for events that can't sleep but need to be able to * trigger a snapshot. */ int tracing_alloc_snapshot(void) { struct trace_array *tr = &global_trace; int ret; ret = tracing_alloc_snapshot_instance(tr); WARN_ON(ret < 0); return ret; } EXPORT_SYMBOL_GPL(tracing_alloc_snapshot); /** * tracing_snapshot_alloc - allocate and take a snapshot of the current buffer. * * This is similar to tracing_snapshot(), but it will allocate the * snapshot buffer if it isn't already allocated. Use this only * where it is safe to sleep, as the allocation may sleep. * * This causes a swap between the snapshot buffer and the current live * tracing buffer. You can use this to take snapshots of the live * trace when some condition is triggered, but continue to trace. */ void tracing_snapshot_alloc(void) { int ret; ret = tracing_alloc_snapshot(); if (ret < 0) return; tracing_snapshot(); } EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); /** * tracing_snapshot_cond_enable - enable conditional snapshot for an instance * @tr: The tracing instance * @cond_data: User data to associate with the snapshot * @update: Implementation of the cond_snapshot update function * * Check whether the conditional snapshot for the given instance has * already been enabled, or if the current tracer is already using a * snapshot; if so, return -EBUSY, else create a cond_snapshot and * save the cond_data and update function inside. * * Returns 0 if successful, error otherwise. */ int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update) { struct cond_snapshot *cond_snapshot __free(kfree) = kzalloc(sizeof(*cond_snapshot), GFP_KERNEL); int ret; if (!cond_snapshot) return -ENOMEM; cond_snapshot->cond_data = cond_data; cond_snapshot->update = update; guard(mutex)(&trace_types_lock); if (tr->current_trace->use_max_tr) return -EBUSY; /* * The cond_snapshot can only change to NULL without the * trace_types_lock. We don't care if we race with it going * to NULL, but we want to make sure that it's not set to * something other than NULL when we get here, which we can * do safely with only holding the trace_types_lock and not * having to take the max_lock. */ if (tr->cond_snapshot) return -EBUSY; ret = tracing_arm_snapshot_locked(tr); if (ret) return ret; local_irq_disable(); arch_spin_lock(&tr->max_lock); tr->cond_snapshot = no_free_ptr(cond_snapshot); arch_spin_unlock(&tr->max_lock); local_irq_enable(); return 0; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable); /** * tracing_snapshot_cond_disable - disable conditional snapshot for an instance * @tr: The tracing instance * * Check whether the conditional snapshot for the given instance is * enabled; if so, free the cond_snapshot associated with it, * otherwise return -EINVAL. * * Returns 0 if successful, error otherwise. */ int tracing_snapshot_cond_disable(struct trace_array *tr) { int ret = 0; local_irq_disable(); arch_spin_lock(&tr->max_lock); if (!tr->cond_snapshot) ret = -EINVAL; else { kfree(tr->cond_snapshot); tr->cond_snapshot = NULL; } arch_spin_unlock(&tr->max_lock); local_irq_enable(); tracing_disarm_snapshot(tr); return ret; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable); #else void tracing_snapshot(void) { WARN_ONCE(1, "Snapshot feature not enabled, but internal snapshot used"); } EXPORT_SYMBOL_GPL(tracing_snapshot); void tracing_snapshot_cond(struct trace_array *tr, void *cond_data) { WARN_ONCE(1, "Snapshot feature not enabled, but internal conditional snapshot used"); } EXPORT_SYMBOL_GPL(tracing_snapshot_cond); int tracing_alloc_snapshot(void) { WARN_ONCE(1, "Snapshot feature not enabled, but snapshot allocation used"); return -ENODEV; } EXPORT_SYMBOL_GPL(tracing_alloc_snapshot); void tracing_snapshot_alloc(void) { /* Give warning */ tracing_snapshot(); } EXPORT_SYMBOL_GPL(tracing_snapshot_alloc); void *tracing_cond_snapshot_data(struct trace_array *tr) { return NULL; } EXPORT_SYMBOL_GPL(tracing_cond_snapshot_data); int tracing_snapshot_cond_enable(struct trace_array *tr, void *cond_data, cond_update_fn_t update) { return -ENODEV; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_enable); int tracing_snapshot_cond_disable(struct trace_array *tr) { return false; } EXPORT_SYMBOL_GPL(tracing_snapshot_cond_disable); #define free_snapshot(tr) do { } while (0) #define tracing_arm_snapshot_locked(tr) ({ -EBUSY; }) #endif /* CONFIG_TRACER_SNAPSHOT */ void tracer_tracing_off(struct trace_array *tr) { if (tr->array_buffer.buffer) ring_buffer_record_off(tr->array_buffer.buffer); /* * This flag is looked at when buffers haven't been allocated * yet, or by some tracers (like irqsoff), that just want to * know if the ring buffer has been disabled, but it can handle * races of where it gets disabled but we still do a record. * As the check is in the fast path of the tracers, it is more * important to be fast than accurate. */ tr->buffer_disabled = 1; } /** * tracer_tracing_disable() - temporary disable the buffer from write * @tr: The trace array to disable its buffer for * * Expects trace_tracing_enable() to re-enable tracing. * The difference between this and tracer_tracing_off() is that this * is a counter and can nest, whereas, tracer_tracing_off() can * be called multiple times and a single trace_tracing_on() will * enable it. */ void tracer_tracing_disable(struct trace_array *tr) { if (WARN_ON_ONCE(!tr->array_buffer.buffer)) return; ring_buffer_record_disable(tr->array_buffer.buffer); } /** * tracer_tracing_enable() - counter part of tracer_tracing_disable() * @tr: The trace array that had tracer_tracincg_disable() called on it * * This is called after tracer_tracing_disable() has been called on @tr, * when it's safe to re-enable tracing. */ void tracer_tracing_enable(struct trace_array *tr) { if (WARN_ON_ONCE(!tr->array_buffer.buffer)) return; ring_buffer_record_enable(tr->array_buffer.buffer); } /** * tracing_off - turn off tracing buffers * * This function stops the tracing buffers from recording data. * It does not disable any overhead the tracers themselves may * be causing. This function simply causes all recording to * the ring buffers to fail. */ void tracing_off(void) { tracer_tracing_off(&global_trace); } EXPORT_SYMBOL_GPL(tracing_off); void disable_trace_on_warning(void) { if (__disable_trace_on_warning) { trace_array_printk_buf(global_trace.array_buffer.buffer, _THIS_IP_, "Disabling tracing due to warning\n"); tracing_off(); } } /** * tracer_tracing_is_on - show real state of ring buffer enabled * @tr : the trace array to know if ring buffer is enabled * * Shows real state of the ring buffer if it is enabled or not. */ bool tracer_tracing_is_on(struct trace_array *tr) { if (tr->array_buffer.buffer) return ring_buffer_record_is_set_on(tr->array_buffer.buffer); return !tr->buffer_disabled; } /** * tracing_is_on - show state of ring buffers enabled */ int tracing_is_on(void) { return tracer_tracing_is_on(&global_trace); } EXPORT_SYMBOL_GPL(tracing_is_on); static int __init set_buf_size(char *str) { unsigned long buf_size; if (!str) return 0; buf_size = memparse(str, &str); /* * nr_entries can not be zero and the startup * tests require some buffer space. Therefore * ensure we have at least 4096 bytes of buffer. */ trace_buf_size = max(4096UL, buf_size); return 1; } __setup("trace_buf_size=", set_buf_size); static int __init set_tracing_thresh(char *str) { unsigned long threshold; int ret; if (!str) return 0; ret = kstrtoul(str, 0, &threshold); if (ret < 0) return 0; tracing_thresh = threshold * 1000; return 1; } __setup("tracing_thresh=", set_tracing_thresh); unsigned long nsecs_to_usecs(unsigned long nsecs) { return nsecs / 1000; } /* * TRACE_FLAGS is defined as a tuple matching bit masks with strings. * It uses C(a, b) where 'a' is the eval (enum) name and 'b' is the string that * matches it. By defining "C(a, b) b", TRACE_FLAGS becomes a list * of strings in the order that the evals (enum) were defined. */ #undef C #define C(a, b) b /* These must match the bit positions in trace_iterator_flags */ static const char *trace_options[] = { TRACE_FLAGS NULL }; static struct { u64 (*func)(void); const char *name; int in_ns; /* is this clock in nanoseconds? */ } trace_clocks[] = { { trace_clock_local, "local", 1 }, { trace_clock_global, "global", 1 }, { trace_clock_counter, "counter", 0 }, { trace_clock_jiffies, "uptime", 0 }, { trace_clock, "perf", 1 }, { ktime_get_mono_fast_ns, "mono", 1 }, { ktime_get_raw_fast_ns, "mono_raw", 1 }, { ktime_get_boot_fast_ns, "boot", 1 }, { ktime_get_tai_fast_ns, "tai", 1 }, ARCH_TRACE_CLOCKS }; bool trace_clock_in_ns(struct trace_array *tr) { if (trace_clocks[tr->clock_id].in_ns) return true; return false; } /* * trace_parser_get_init - gets the buffer for trace parser */ int trace_parser_get_init(struct trace_parser *parser, int size) { memset(parser, 0, sizeof(*parser)); parser->buffer = kmalloc(size, GFP_KERNEL); if (!parser->buffer) return 1; parser->size = size; return 0; } /* * trace_parser_put - frees the buffer for trace parser */ void trace_parser_put(struct trace_parser *parser) { kfree(parser->buffer); parser->buffer = NULL; } /* * trace_get_user - reads the user input string separated by space * (matched by isspace(ch)) * * For each string found the 'struct trace_parser' is updated, * and the function returns. * * Returns number of bytes read. * * See kernel/trace/trace.h for 'struct trace_parser' details. */ int trace_get_user(struct trace_parser *parser, const char __user *ubuf, size_t cnt, loff_t *ppos) { char ch; size_t read = 0; ssize_t ret; if (!*ppos) trace_parser_clear(parser); ret = get_user(ch, ubuf++); if (ret) goto fail; read++; cnt--; /* * The parser is not finished with the last write, * continue reading the user input without skipping spaces. */ if (!parser->cont) { /* skip white space */ while (cnt && isspace(ch)) { ret = get_user(ch, ubuf++); if (ret) goto fail; read++; cnt--; } parser->idx = 0; /* only spaces were written */ if (isspace(ch) || !ch) { *ppos += read; return read; } } /* read the non-space input */ while (cnt && !isspace(ch) && ch) { if (parser->idx < parser->size - 1) parser->buffer[parser->idx++] = ch; else { ret = -EINVAL; goto fail; } ret = get_user(ch, ubuf++); if (ret) goto fail; read++; cnt--; } /* We either got finished input or we have to wait for another call. */ if (isspace(ch) || !ch) { parser->buffer[parser->idx] = 0; parser->cont = false; } else if (parser->idx < parser->size - 1) { parser->cont = true; parser->buffer[parser->idx++] = ch; /* Make sure the parsed string always terminates with '\0'. */ parser->buffer[parser->idx] = 0; } else { ret = -EINVAL; goto fail; } *ppos += read; return read; fail: trace_parser_fail(parser); return ret; } /* TODO add a seq_buf_to_buffer() */ static ssize_t trace_seq_to_buffer(struct trace_seq *s, void *buf, size_t cnt) { int len; if (trace_seq_used(s) <= s->readpos) return -EBUSY; len = trace_seq_used(s) - s->readpos; if (cnt > len) cnt = len; memcpy(buf, s->buffer + s->readpos, cnt); s->readpos += cnt; return cnt; } unsigned long __read_mostly tracing_thresh; #ifdef CONFIG_TRACER_MAX_TRACE static const struct file_operations tracing_max_lat_fops; #ifdef LATENCY_FS_NOTIFY static struct workqueue_struct *fsnotify_wq; static void latency_fsnotify_workfn(struct work_struct *work) { struct trace_array *tr = container_of(work, struct trace_array, fsnotify_work); fsnotify_inode(tr->d_max_latency->d_inode, FS_MODIFY); } static void latency_fsnotify_workfn_irq(struct irq_work *iwork) { struct trace_array *tr = container_of(iwork, struct trace_array, fsnotify_irqwork); queue_work(fsnotify_wq, &tr->fsnotify_work); } static void trace_create_maxlat_file(struct trace_array *tr, struct dentry *d_tracer) { INIT_WORK(&tr->fsnotify_work, latency_fsnotify_workfn); init_irq_work(&tr->fsnotify_irqwork, latency_fsnotify_workfn_irq); tr->d_max_latency = trace_create_file("tracing_max_latency", TRACE_MODE_WRITE, d_tracer, tr, &tracing_max_lat_fops); } __init static int latency_fsnotify_init(void) { fsnotify_wq = alloc_workqueue("tr_max_lat_wq", WQ_UNBOUND | WQ_HIGHPRI, 0); if (!fsnotify_wq) { pr_err("Unable to allocate tr_max_lat_wq\n"); return -ENOMEM; } return 0; } late_initcall_sync(latency_fsnotify_init); void latency_fsnotify(struct trace_array *tr) { if (!fsnotify_wq) return; /* * We cannot call queue_work(&tr->fsnotify_work) from here because it's * possible that we are called from __schedule() or do_idle(), which * could cause a deadlock. */ irq_work_queue(&tr->fsnotify_irqwork); } #else /* !LATENCY_FS_NOTIFY */ #define trace_create_maxlat_file(tr, d_tracer) \ trace_create_file("tracing_max_latency", TRACE_MODE_WRITE, \ d_tracer, tr, &tracing_max_lat_fops) #endif /* * Copy the new maximum trace into the separate maximum-trace * structure. (this way the maximum trace is permanently saved, * for later retrieval via /sys/kernel/tracing/tracing_max_latency) */ static void __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) { struct array_buffer *trace_buf = &tr->array_buffer; struct array_buffer *max_buf = &tr->max_buffer; struct trace_array_cpu *data = per_cpu_ptr(trace_buf->data, cpu); struct trace_array_cpu *max_data = per_cpu_ptr(max_buf->data, cpu); max_buf->cpu = cpu; max_buf->time_start = data->preempt_timestamp; max_data->saved_latency = tr->max_latency; max_data->critical_start = data->critical_start; max_data->critical_end = data->critical_end; strscpy(max_data->comm, tsk->comm); max_data->pid = tsk->pid; /* * If tsk == current, then use current_uid(), as that does not use * RCU. The irq tracer can be called out of RCU scope. */ if (tsk == current) max_data->uid = current_uid(); else max_data->uid = task_uid(tsk); max_data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; max_data->policy = tsk->policy; max_data->rt_priority = tsk->rt_priority; /* record this tasks comm */ tracing_record_cmdline(tsk); latency_fsnotify(tr); } /** * update_max_tr - snapshot all trace buffers from global_trace to max_tr * @tr: tracer * @tsk: the task with the latency * @cpu: The cpu that initiated the trace. * @cond_data: User data associated with a conditional snapshot * * Flip the buffers between the @tr and the max_tr and record information * about which task was the cause of this latency. */ void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu, void *cond_data) { if (tr->stop_count) return; WARN_ON_ONCE(!irqs_disabled()); if (!tr->allocated_snapshot) { /* Only the nop tracer should hit this when disabling */ WARN_ON_ONCE(tr->current_trace != &nop_trace); return; } arch_spin_lock(&tr->max_lock); /* Inherit the recordable setting from array_buffer */ if (ring_buffer_record_is_set_on(tr->array_buffer.buffer)) ring_buffer_record_on(tr->max_buffer.buffer); else ring_buffer_record_off(tr->max_buffer.buffer); #ifdef CONFIG_TRACER_SNAPSHOT if (tr->cond_snapshot && !tr->cond_snapshot->update(tr, cond_data)) { arch_spin_unlock(&tr->max_lock); return; } #endif swap(tr->array_buffer.buffer, tr->max_buffer.buffer); __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); /* Any waiters on the old snapshot buffer need to wake up */ ring_buffer_wake_waiters(tr->array_buffer.buffer, RING_BUFFER_ALL_CPUS); } /** * update_max_tr_single - only copy one trace over, and reset the rest * @tr: tracer * @tsk: task with the latency * @cpu: the cpu of the buffer to copy. * * Flip the trace of a single CPU buffer between the @tr and the max_tr. */ void update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) { int ret; if (tr->stop_count) return; WARN_ON_ONCE(!irqs_disabled()); if (!tr->allocated_snapshot) { /* Only the nop tracer should hit this when disabling */ WARN_ON_ONCE(tr->current_trace != &nop_trace); return; } arch_spin_lock(&tr->max_lock); ret = ring_buffer_swap_cpu(tr->max_buffer.buffer, tr->array_buffer.buffer, cpu); if (ret == -EBUSY) { /* * We failed to swap the buffer due to a commit taking * place on this CPU. We fail to record, but we reset * the max trace buffer (no one writes directly to it) * and flag that it failed. * Another reason is resize is in progress. */ trace_array_printk_buf(tr->max_buffer.buffer, _THIS_IP_, "Failed to swap buffers due to commit or resize in progress\n"); } WARN_ON_ONCE(ret && ret != -EAGAIN && ret != -EBUSY); __update_max_tr(tr, tsk, cpu); arch_spin_unlock(&tr->max_lock); } #endif /* CONFIG_TRACER_MAX_TRACE */ struct pipe_wait { struct trace_iterator *iter; int wait_index; }; static bool wait_pipe_cond(void *data) { struct pipe_wait *pwait = data; struct trace_iterator *iter = pwait->iter; if (atomic_read_acquire(&iter->wait_index) != pwait->wait_index) return true; return iter->closed; } static int wait_on_pipe(struct trace_iterator *iter, int full) { struct pipe_wait pwait; int ret; /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; pwait.wait_index = atomic_read_acquire(&iter->wait_index); pwait.iter = iter; ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full, wait_pipe_cond, &pwait); #ifdef CONFIG_TRACER_MAX_TRACE /* * Make sure this is still the snapshot buffer, as if a snapshot were * to happen, this would now be the main buffer. */ if (iter->snapshot) iter->array_buffer = &iter->tr->max_buffer; #endif return ret; } #ifdef CONFIG_FTRACE_STARTUP_TEST static bool selftests_can_run; struct trace_selftests { struct list_head list; struct tracer *type; }; static LIST_HEAD(postponed_selftests); static int save_selftest(struct tracer *type) { struct trace_selftests *selftest; selftest = kmalloc(sizeof(*selftest), GFP_KERNEL); if (!selftest) return -ENOMEM; selftest->type = type; list_add(&selftest->list, &postponed_selftests); return 0; } static int run_tracer_selftest(struct tracer *type) { struct trace_array *tr = &global_trace; struct tracer *saved_tracer = tr->current_trace; int ret; if (!type->selftest || tracing_selftest_disabled) return 0; /* * If a tracer registers early in boot up (before scheduling is * initialized and such), then do not run its selftests yet. * Instead, run it a little later in the boot process. */ if (!selftests_can_run) return save_selftest(type); if (!tracing_is_on()) { pr_warn("Selftest for tracer %s skipped due to tracing disabled\n", type->name); return 0; } /* * Run a selftest on this tracer. * Here we reset the trace buffer, and set the current * tracer to be this tracer. The tracer can then run some * internal tracing to verify that everything is in order. * If we fail, we do not register this tracer. */ tracing_reset_online_cpus(&tr->array_buffer); tr->current_trace = type; #ifdef CONFIG_TRACER_MAX_TRACE if (type->use_max_tr) { /* If we expanded the buffers, make sure the max is expanded too */ if (tr->ring_buffer_expanded) ring_buffer_resize(tr->max_buffer.buffer, trace_buf_size, RING_BUFFER_ALL_CPUS); tr->allocated_snapshot = true; } #endif /* the test is responsible for initializing and enabling */ pr_info("Testing tracer %s: ", type->name); ret = type->selftest(type, tr); /* the test is responsible for resetting too */ tr->current_trace = saved_tracer; if (ret) { printk(KERN_CONT "FAILED!\n"); /* Add the warning after printing 'FAILED' */ WARN_ON(1); return -1; } /* Only reset on passing, to avoid touching corrupted buffers */ tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE if (type->use_max_tr) { tr->allocated_snapshot = false; /* Shrink the max buffer again */ if (tr->ring_buffer_expanded) ring_buffer_resize(tr->max_buffer.buffer, 1, RING_BUFFER_ALL_CPUS); } #endif printk(KERN_CONT "PASSED\n"); return 0; } static int do_run_tracer_selftest(struct tracer *type) { int ret; /* * Tests can take a long time, especially if they are run one after the * other, as does happen during bootup when all the tracers are * registered. This could cause the soft lockup watchdog to trigger. */ cond_resched(); tracing_selftest_running = true; ret = run_tracer_selftest(type); tracing_selftest_running = false; return ret; } static __init int init_trace_selftests(void) { struct trace_selftests *p, *n; struct tracer *t, **last; int ret; selftests_can_run = true; guard(mutex)(&trace_types_lock); if (list_empty(&postponed_selftests)) return 0; pr_info("Running postponed tracer tests:\n"); tracing_selftest_running = true; list_for_each_entry_safe(p, n, &postponed_selftests, list) { /* This loop can take minutes when sanitizers are enabled, so * lets make sure we allow RCU processing. */ cond_resched(); ret = run_tracer_selftest(p->type); /* If the test fails, then warn and remove from available_tracers */ if (ret < 0) { WARN(1, "tracer: %s failed selftest, disabling\n", p->type->name); last = &trace_types; for (t = trace_types; t; t = t->next) { if (t == p->type) { *last = t->next; break; } last = &t->next; } } list_del(&p->list); kfree(p); } tracing_selftest_running = false; return 0; } core_initcall(init_trace_selftests); #else static inline int do_run_tracer_selftest(struct tracer *type) { return 0; } #endif /* CONFIG_FTRACE_STARTUP_TEST */ static void add_tracer_options(struct trace_array *tr, struct tracer *t); static void __init apply_trace_boot_options(void); /** * register_tracer - register a tracer with the ftrace system. * @type: the plugin for the tracer * * Register a new plugin tracer. */ int __init register_tracer(struct tracer *type) { struct tracer *t; int ret = 0; if (!type->name) { pr_info("Tracer must have a name\n"); return -1; } if (strlen(type->name) >= MAX_TRACER_SIZE) { pr_info("Tracer has a name longer than %d\n", MAX_TRACER_SIZE); return -1; } if (security_locked_down(LOCKDOWN_TRACEFS)) { pr_warn("Can not register tracer %s due to lockdown\n", type->name); return -EPERM; } mutex_lock(&trace_types_lock); for (t = trace_types; t; t = t->next) { if (strcmp(type->name, t->name) == 0) { /* already found */ pr_info("Tracer %s already registered\n", type->name); ret = -1; goto out; } } if (!type->set_flag) type->set_flag = &dummy_set_flag; if (!type->flags) { /*allocate a dummy tracer_flags*/ type->flags = kmalloc(sizeof(*type->flags), GFP_KERNEL); if (!type->flags) { ret = -ENOMEM; goto out; } type->flags->val = 0; type->flags->opts = dummy_tracer_opt; } else if (!type->flags->opts) type->flags->opts = dummy_tracer_opt; /* store the tracer for __set_tracer_option */ type->flags->trace = type; ret = do_run_tracer_selftest(type); if (ret < 0) goto out; type->next = trace_types; trace_types = type; add_tracer_options(&global_trace, type); out: mutex_unlock(&trace_types_lock); if (ret || !default_bootup_tracer) return ret; if (strncmp(default_bootup_tracer, type->name, MAX_TRACER_SIZE)) return 0; printk(KERN_INFO "Starting tracer '%s'\n", type->name); /* Do we want this tracer to start on bootup? */ tracing_set_tracer(&global_trace, type->name); default_bootup_tracer = NULL; apply_trace_boot_options(); /* disable other selftests, since this will break it. */ disable_tracing_selftest("running a tracer"); return 0; } static void tracing_reset_cpu(struct array_buffer *buf, int cpu) { struct trace_buffer *buffer = buf->buffer; if (!buffer) return; ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ synchronize_rcu(); ring_buffer_reset_cpu(buffer, cpu); ring_buffer_record_enable(buffer); } void tracing_reset_online_cpus(struct array_buffer *buf) { struct trace_buffer *buffer = buf->buffer; if (!buffer) return; ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ synchronize_rcu(); buf->time_start = buffer_ftrace_now(buf, buf->cpu); ring_buffer_reset_online_cpus(buffer); ring_buffer_record_enable(buffer); } static void tracing_reset_all_cpus(struct array_buffer *buf) { struct trace_buffer *buffer = buf->buffer; if (!buffer) return; ring_buffer_record_disable(buffer); /* Make sure all commits have finished */ synchronize_rcu(); buf->time_start = buffer_ftrace_now(buf, buf->cpu); ring_buffer_reset(buffer); ring_buffer_record_enable(buffer); } /* Must have trace_types_lock held */ void tracing_reset_all_online_cpus_unlocked(void) { struct trace_array *tr; lockdep_assert_held(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (!tr->clear_trace) continue; tr->clear_trace = false; tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE tracing_reset_online_cpus(&tr->max_buffer); #endif } } void tracing_reset_all_online_cpus(void) { guard(mutex)(&trace_types_lock); tracing_reset_all_online_cpus_unlocked(); } int is_tracing_stopped(void) { return global_trace.stop_count; } static void tracing_start_tr(struct trace_array *tr) { struct trace_buffer *buffer; if (tracing_disabled) return; guard(raw_spinlock_irqsave)(&tr->start_lock); if (--tr->stop_count) { if (WARN_ON_ONCE(tr->stop_count < 0)) { /* Someone screwed up their debugging */ tr->stop_count = 0; } return; } /* Prevent the buffers from switching */ arch_spin_lock(&tr->max_lock); buffer = tr->array_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); #ifdef CONFIG_TRACER_MAX_TRACE buffer = tr->max_buffer.buffer; if (buffer) ring_buffer_record_enable(buffer); #endif arch_spin_unlock(&tr->max_lock); } /** * tracing_start - quick start of the tracer * * If tracing is enabled but was stopped by tracing_stop, * this will start the tracer back up. */ void tracing_start(void) { return tracing_start_tr(&global_trace); } static void tracing_stop_tr(struct trace_array *tr) { struct trace_buffer *buffer; guard(raw_spinlock_irqsave)(&tr->start_lock); if (tr->stop_count++) return; /* Prevent the buffers from switching */ arch_spin_lock(&tr->max_lock); buffer = tr->array_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); #ifdef CONFIG_TRACER_MAX_TRACE buffer = tr->max_buffer.buffer; if (buffer) ring_buffer_record_disable(buffer); #endif arch_spin_unlock(&tr->max_lock); } /** * tracing_stop - quick stop of the tracer * * Light weight way to stop tracing. Use in conjunction with * tracing_start. */ void tracing_stop(void) { return tracing_stop_tr(&global_trace); } /* * Several functions return TRACE_TYPE_PARTIAL_LINE if the trace_seq * overflowed, and TRACE_TYPE_HANDLED otherwise. This helper function * simplifies those functions and keeps them in sync. */ enum print_line_t trace_handle_return(struct trace_seq *s) { return trace_seq_has_overflowed(s) ? TRACE_TYPE_PARTIAL_LINE : TRACE_TYPE_HANDLED; } EXPORT_SYMBOL_GPL(trace_handle_return); static unsigned short migration_disable_value(void) { #if defined(CONFIG_SMP) return current->migration_disabled; #else return 0; #endif } unsigned int tracing_gen_ctx_irq_test(unsigned int irqs_status) { unsigned int trace_flags = irqs_status; unsigned int pc; pc = preempt_count(); if (pc & NMI_MASK) trace_flags |= TRACE_FLAG_NMI; if (pc & HARDIRQ_MASK) trace_flags |= TRACE_FLAG_HARDIRQ; if (in_serving_softirq()) trace_flags |= TRACE_FLAG_SOFTIRQ; if (softirq_count() >> (SOFTIRQ_SHIFT + 1)) trace_flags |= TRACE_FLAG_BH_OFF; if (tif_need_resched()) trace_flags |= TRACE_FLAG_NEED_RESCHED; if (test_preempt_need_resched()) trace_flags |= TRACE_FLAG_PREEMPT_RESCHED; if (IS_ENABLED(CONFIG_ARCH_HAS_PREEMPT_LAZY) && tif_test_bit(TIF_NEED_RESCHED_LAZY)) trace_flags |= TRACE_FLAG_NEED_RESCHED_LAZY; return (trace_flags << 16) | (min_t(unsigned int, pc & 0xff, 0xf)) | (min_t(unsigned int, migration_disable_value(), 0xf)) << 4; } struct ring_buffer_event * trace_buffer_lock_reserve(struct trace_buffer *buffer, int type, unsigned long len, unsigned int trace_ctx) { return __trace_buffer_lock_reserve(buffer, type, len, trace_ctx); } DEFINE_PER_CPU(struct ring_buffer_event *, trace_buffered_event); DEFINE_PER_CPU(int, trace_buffered_event_cnt); static int trace_buffered_event_ref; /** * trace_buffered_event_enable - enable buffering events * * When events are being filtered, it is quicker to use a temporary * buffer to write the event data into if there's a likely chance * that it will not be committed. The discard of the ring buffer * is not as fast as committing, and is much slower than copying * a commit. * * When an event is to be filtered, allocate per cpu buffers to * write the event data into, and if the event is filtered and discarded * it is simply dropped, otherwise, the entire data is to be committed * in one shot. */ void trace_buffered_event_enable(void) { struct ring_buffer_event *event; struct page *page; int cpu; WARN_ON_ONCE(!mutex_is_locked(&event_mutex)); if (trace_buffered_event_ref++) return; for_each_tracing_cpu(cpu) { page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_NORETRY, 0); /* This is just an optimization and can handle failures */ if (!page) { pr_err("Failed to allocate event buffer\n"); break; } event = page_address(page); memset(event, 0, sizeof(*event)); per_cpu(trace_buffered_event, cpu) = event; scoped_guard(preempt,) { if (cpu == smp_processor_id() && __this_cpu_read(trace_buffered_event) != per_cpu(trace_buffered_event, cpu)) WARN_ON_ONCE(1); } } } static void enable_trace_buffered_event(void *data) { this_cpu_dec(trace_buffered_event_cnt); } static void disable_trace_buffered_event(void *data) { this_cpu_inc(trace_buffered_event_cnt); } /** * trace_buffered_event_disable - disable buffering events * * When a filter is removed, it is faster to not use the buffered * events, and to commit directly into the ring buffer. Free up * the temp buffers when there are no more users. This requires * special synchronization with current events. */ void trace_buffered_event_disable(void) { int cpu; WARN_ON_ONCE(!mutex_is_locked(&event_mutex)); if (WARN_ON_ONCE(!trace_buffered_event_ref)) return; if (--trace_buffered_event_ref) return; /* For each CPU, set the buffer as used. */ on_each_cpu_mask(tracing_buffer_mask, disable_trace_buffered_event, NULL, true); /* Wait for all current users to finish */ synchronize_rcu(); for_each_tracing_cpu(cpu) { free_page((unsigned long)per_cpu(trace_buffered_event, cpu)); per_cpu(trace_buffered_event, cpu) = NULL; } /* * Wait for all CPUs that potentially started checking if they can use * their event buffer only after the previous synchronize_rcu() call and * they still read a valid pointer from trace_buffered_event. It must be * ensured they don't see cleared trace_buffered_event_cnt else they * could wrongly decide to use the pointed-to buffer which is now freed. */ synchronize_rcu(); /* For each CPU, relinquish the buffer */ on_each_cpu_mask(tracing_buffer_mask, enable_trace_buffered_event, NULL, true); } static struct trace_buffer *temp_buffer; struct ring_buffer_event * trace_event_buffer_lock_reserve(struct trace_buffer **current_rb, struct trace_event_file *trace_file, int type, unsigned long len, unsigned int trace_ctx) { struct ring_buffer_event *entry; struct trace_array *tr = trace_file->tr; int val; *current_rb = tr->array_buffer.buffer; if (!tr->no_filter_buffering_ref && (trace_file->flags & (EVENT_FILE_FL_SOFT_DISABLED | EVENT_FILE_FL_FILTERED))) { preempt_disable_notrace(); /* * Filtering is on, so try to use the per cpu buffer first. * This buffer will simulate a ring_buffer_event, * where the type_len is zero and the array[0] will * hold the full length. * (see include/linux/ring-buffer.h for details on * how the ring_buffer_event is structured). * * Using a temp buffer during filtering and copying it * on a matched filter is quicker than writing directly * into the ring buffer and then discarding it when * it doesn't match. That is because the discard * requires several atomic operations to get right. * Copying on match and doing nothing on a failed match * is still quicker than no copy on match, but having * to discard out of the ring buffer on a failed match. */ if ((entry = __this_cpu_read(trace_buffered_event))) { int max_len = PAGE_SIZE - struct_size(entry, array, 1); val = this_cpu_inc_return(trace_buffered_event_cnt); /* * Preemption is disabled, but interrupts and NMIs * can still come in now. If that happens after * the above increment, then it will have to go * back to the old method of allocating the event * on the ring buffer, and if the filter fails, it * will have to call ring_buffer_discard_commit() * to remove it. * * Need to also check the unlikely case that the * length is bigger than the temp buffer size. * If that happens, then the reserve is pretty much * guaranteed to fail, as the ring buffer currently * only allows events less than a page. But that may * change in the future, so let the ring buffer reserve * handle the failure in that case. */ if (val == 1 && likely(len <= max_len)) { trace_event_setup(entry, type, trace_ctx); entry->array[0] = len; /* Return with preemption disabled */ return entry; } this_cpu_dec(trace_buffered_event_cnt); } /* __trace_buffer_lock_reserve() disables preemption */ preempt_enable_notrace(); } entry = __trace_buffer_lock_reserve(*current_rb, type, len, trace_ctx); /* * If tracing is off, but we have triggers enabled * we still need to look at the event data. Use the temp_buffer * to store the trace event for the trigger to use. It's recursive * safe and will not be recorded anywhere. */ if (!entry && trace_file->flags & EVENT_FILE_FL_TRIGGER_COND) { *current_rb = temp_buffer; entry = __trace_buffer_lock_reserve(*current_rb, type, len, trace_ctx); } return entry; } EXPORT_SYMBOL_GPL(trace_event_buffer_lock_reserve); static DEFINE_RAW_SPINLOCK(tracepoint_iter_lock); static DEFINE_MUTEX(tracepoint_printk_mutex); static void output_printk(struct trace_event_buffer *fbuffer) { struct trace_event_call *event_call; struct trace_event_file *file; struct trace_event *event; unsigned long flags; struct trace_iterator *iter = tracepoint_print_iter; /* We should never get here if iter is NULL */ if (WARN_ON_ONCE(!iter)) return; event_call = fbuffer->trace_file->event_call; if (!event_call || !event_call->event.funcs || !event_call->event.funcs->trace) return; file = fbuffer->trace_file; if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags) || (unlikely(file->flags & EVENT_FILE_FL_FILTERED) && !filter_match_preds(file->filter, fbuffer->entry))) return; event = &fbuffer->trace_file->event_call->event; raw_spin_lock_irqsave(&tracepoint_iter_lock, flags); trace_seq_init(&iter->seq); iter->ent = fbuffer->entry; event_call->event.funcs->trace(iter, 0, event); trace_seq_putc(&iter->seq, 0); printk("%s", iter->seq.buffer); raw_spin_unlock_irqrestore(&tracepoint_iter_lock, flags); } int tracepoint_printk_sysctl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int save_tracepoint_printk; int ret; guard(mutex)(&tracepoint_printk_mutex); save_tracepoint_printk = tracepoint_printk; ret = proc_dointvec(table, write, buffer, lenp, ppos); /* * This will force exiting early, as tracepoint_printk * is always zero when tracepoint_printk_iter is not allocated */ if (!tracepoint_print_iter) tracepoint_printk = 0; if (save_tracepoint_printk == tracepoint_printk) return ret; if (tracepoint_printk) static_key_enable(&tracepoint_printk_key.key); else static_key_disable(&tracepoint_printk_key.key); return ret; } void trace_event_buffer_commit(struct trace_event_buffer *fbuffer) { enum event_trigger_type tt = ETT_NONE; struct trace_event_file *file = fbuffer->trace_file; if (__event_trigger_test_discard(file, fbuffer->buffer, fbuffer->event, fbuffer->entry, &tt)) goto discard; if (static_key_false(&tracepoint_printk_key.key)) output_printk(fbuffer); if (static_branch_unlikely(&trace_event_exports_enabled)) ftrace_exports(fbuffer->event, TRACE_EXPORT_EVENT); trace_buffer_unlock_commit_regs(file->tr, fbuffer->buffer, fbuffer->event, fbuffer->trace_ctx, fbuffer->regs); discard: if (tt) event_triggers_post_call(file, tt); } EXPORT_SYMBOL_GPL(trace_event_buffer_commit); /* * Skip 3: * * trace_buffer_unlock_commit_regs() * trace_event_buffer_commit() * trace_event_raw_event_xxx() */ # define STACK_SKIP 3 void trace_buffer_unlock_commit_regs(struct trace_array *tr, struct trace_buffer *buffer, struct ring_buffer_event *event, unsigned int trace_ctx, struct pt_regs *regs) { __buffer_unlock_commit(buffer, event); /* * If regs is not set, then skip the necessary functions. * Note, we can still get here via blktrace, wakeup tracer * and mmiotrace, but that's ok if they lose a function or * two. They are not that meaningful. */ ftrace_trace_stack(tr, buffer, trace_ctx, regs ? 0 : STACK_SKIP, regs); ftrace_trace_userstack(tr, buffer, trace_ctx); } /* * Similar to trace_buffer_unlock_commit_regs() but do not dump stack. */ void trace_buffer_unlock_commit_nostack(struct trace_buffer *buffer, struct ring_buffer_event *event) { __buffer_unlock_commit(buffer, event); } void trace_function(struct trace_array *tr, unsigned long ip, unsigned long parent_ip, unsigned int trace_ctx, struct ftrace_regs *fregs) { struct trace_buffer *buffer = tr->array_buffer.buffer; struct ring_buffer_event *event; struct ftrace_entry *entry; int size = sizeof(*entry); size += FTRACE_REGS_MAX_ARGS * !!fregs * sizeof(long); event = __trace_buffer_lock_reserve(buffer, TRACE_FN, size, trace_ctx); if (!event) return; entry = ring_buffer_event_data(event); entry->ip = ip; entry->parent_ip = parent_ip; #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API if (fregs) { for (int i = 0; i < FTRACE_REGS_MAX_ARGS; i++) entry->args[i] = ftrace_regs_get_argument(fregs, i); } #endif if (static_branch_unlikely(&trace_function_exports_enabled)) ftrace_exports(event, TRACE_EXPORT_FUNCTION); __buffer_unlock_commit(buffer, event); } #ifdef CONFIG_STACKTRACE /* Allow 4 levels of nesting: normal, softirq, irq, NMI */ #define FTRACE_KSTACK_NESTING 4 #define FTRACE_KSTACK_ENTRIES (SZ_4K / FTRACE_KSTACK_NESTING) struct ftrace_stack { unsigned long calls[FTRACE_KSTACK_ENTRIES]; }; struct ftrace_stacks { struct ftrace_stack stacks[FTRACE_KSTACK_NESTING]; }; static DEFINE_PER_CPU(struct ftrace_stacks, ftrace_stacks); static DEFINE_PER_CPU(int, ftrace_stack_reserve); static void __ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx, int skip, struct pt_regs *regs) { struct ring_buffer_event *event; unsigned int size, nr_entries; struct ftrace_stack *fstack; struct stack_entry *entry; int stackidx; /* * Add one, for this function and the call to save_stack_trace() * If regs is set, then these functions will not be in the way. */ #ifndef CONFIG_UNWINDER_ORC if (!regs) skip++; #endif guard(preempt_notrace)(); stackidx = __this_cpu_inc_return(ftrace_stack_reserve) - 1; /* This should never happen. If it does, yell once and skip */ if (WARN_ON_ONCE(stackidx >= FTRACE_KSTACK_NESTING)) goto out; /* * The above __this_cpu_inc_return() is 'atomic' cpu local. An * interrupt will either see the value pre increment or post * increment. If the interrupt happens pre increment it will have * restored the counter when it returns. We just need a barrier to * keep gcc from moving things around. */ barrier(); fstack = this_cpu_ptr(ftrace_stacks.stacks) + stackidx; size = ARRAY_SIZE(fstack->calls); if (regs) { nr_entries = stack_trace_save_regs(regs, fstack->calls, size, skip); } else { nr_entries = stack_trace_save(fstack->calls, size, skip); } #ifdef CONFIG_DYNAMIC_FTRACE /* Mark entry of stack trace as trampoline code */ if (tr->ops && tr->ops->trampoline) { unsigned long tramp_start = tr->ops->trampoline; unsigned long tramp_end = tramp_start + tr->ops->trampoline_size; unsigned long *calls = fstack->calls; for (int i = 0; i < nr_entries; i++) { if (calls[i] >= tramp_start && calls[i] < tramp_end) calls[i] = FTRACE_TRAMPOLINE_MARKER; } } #endif event = __trace_buffer_lock_reserve(buffer, TRACE_STACK, struct_size(entry, caller, nr_entries), trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); entry->size = nr_entries; memcpy(&entry->caller, fstack->calls, flex_array_size(entry, caller, nr_entries)); __buffer_unlock_commit(buffer, event); out: /* Again, don't let gcc optimize things here */ barrier(); __this_cpu_dec(ftrace_stack_reserve); } static inline void ftrace_trace_stack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx, int skip, struct pt_regs *regs) { if (!(tr->trace_flags & TRACE_ITER_STACKTRACE)) return; __ftrace_trace_stack(tr, buffer, trace_ctx, skip, regs); } void __trace_stack(struct trace_array *tr, unsigned int trace_ctx, int skip) { struct trace_buffer *buffer = tr->array_buffer.buffer; if (rcu_is_watching()) { __ftrace_trace_stack(tr, buffer, trace_ctx, skip, NULL); return; } if (WARN_ON_ONCE(IS_ENABLED(CONFIG_GENERIC_ENTRY))) return; /* * When an NMI triggers, RCU is enabled via ct_nmi_enter(), * but if the above rcu_is_watching() failed, then the NMI * triggered someplace critical, and ct_irq_enter() should * not be called from NMI. */ if (unlikely(in_nmi())) return; ct_irq_enter_irqson(); __ftrace_trace_stack(tr, buffer, trace_ctx, skip, NULL); ct_irq_exit_irqson(); } /** * trace_dump_stack - record a stack back trace in the trace buffer * @skip: Number of functions to skip (helper handlers) */ void trace_dump_stack(int skip) { if (tracing_disabled || tracing_selftest_running) return; #ifndef CONFIG_UNWINDER_ORC /* Skip 1 to skip this function. */ skip++; #endif __ftrace_trace_stack(printk_trace, printk_trace->array_buffer.buffer, tracing_gen_ctx(), skip, NULL); } EXPORT_SYMBOL_GPL(trace_dump_stack); #ifdef CONFIG_USER_STACKTRACE_SUPPORT static DEFINE_PER_CPU(int, user_stack_count); static void ftrace_trace_userstack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx) { struct ring_buffer_event *event; struct userstack_entry *entry; if (!(tr->trace_flags & TRACE_ITER_USERSTACKTRACE)) return; /* * NMIs can not handle page faults, even with fix ups. * The save user stack can (and often does) fault. */ if (unlikely(in_nmi())) return; /* * prevent recursion, since the user stack tracing may * trigger other kernel events. */ guard(preempt)(); if (__this_cpu_read(user_stack_count)) return; __this_cpu_inc(user_stack_count); event = __trace_buffer_lock_reserve(buffer, TRACE_USER_STACK, sizeof(*entry), trace_ctx); if (!event) goto out_drop_count; entry = ring_buffer_event_data(event); entry->tgid = current->tgid; memset(&entry->caller, 0, sizeof(entry->caller)); stack_trace_save_user(entry->caller, FTRACE_STACK_ENTRIES); __buffer_unlock_commit(buffer, event); out_drop_count: __this_cpu_dec(user_stack_count); } #else /* CONFIG_USER_STACKTRACE_SUPPORT */ static void ftrace_trace_userstack(struct trace_array *tr, struct trace_buffer *buffer, unsigned int trace_ctx) { } #endif /* !CONFIG_USER_STACKTRACE_SUPPORT */ #endif /* CONFIG_STACKTRACE */ static inline void func_repeats_set_delta_ts(struct func_repeats_entry *entry, unsigned long long delta) { entry->bottom_delta_ts = delta & U32_MAX; entry->top_delta_ts = (delta >> 32); } void trace_last_func_repeats(struct trace_array *tr, struct trace_func_repeats *last_info, unsigned int trace_ctx) { struct trace_buffer *buffer = tr->array_buffer.buffer; struct func_repeats_entry *entry; struct ring_buffer_event *event; u64 delta; event = __trace_buffer_lock_reserve(buffer, TRACE_FUNC_REPEATS, sizeof(*entry), trace_ctx); if (!event) return; delta = ring_buffer_event_time_stamp(buffer, event) - last_info->ts_last_call; entry = ring_buffer_event_data(event); entry->ip = last_info->ip; entry->parent_ip = last_info->parent_ip; entry->count = last_info->count; func_repeats_set_delta_ts(entry, delta); __buffer_unlock_commit(buffer, event); } /* created for use with alloc_percpu */ struct trace_buffer_struct { int nesting; char buffer[4][TRACE_BUF_SIZE]; }; static struct trace_buffer_struct __percpu *trace_percpu_buffer; /* * This allows for lockless recording. If we're nested too deeply, then * this returns NULL. */ static char *get_trace_buf(void) { struct trace_buffer_struct *buffer = this_cpu_ptr(trace_percpu_buffer); if (!trace_percpu_buffer || buffer->nesting >= 4) return NULL; buffer->nesting++; /* Interrupts must see nesting incremented before we use the buffer */ barrier(); return &buffer->buffer[buffer->nesting - 1][0]; } static void put_trace_buf(void) { /* Don't let the decrement of nesting leak before this */ barrier(); this_cpu_dec(trace_percpu_buffer->nesting); } static int alloc_percpu_trace_buffer(void) { struct trace_buffer_struct __percpu *buffers; if (trace_percpu_buffer) return 0; buffers = alloc_percpu(struct trace_buffer_struct); if (MEM_FAIL(!buffers, "Could not allocate percpu trace_printk buffer")) return -ENOMEM; trace_percpu_buffer = buffers; return 0; } static int buffers_allocated; void trace_printk_init_buffers(void) { if (buffers_allocated) return; if (alloc_percpu_trace_buffer()) return; /* trace_printk() is for debug use only. Don't use it in production. */ pr_warn("\n"); pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("** **\n"); pr_warn("** trace_printk() being used. Allocating extra memory. **\n"); pr_warn("** **\n"); pr_warn("** This means that this is a DEBUG kernel and it is **\n"); pr_warn("** unsafe for production use. **\n"); pr_warn("** **\n"); pr_warn("** If you see this message and you are not debugging **\n"); pr_warn("** the kernel, report this immediately to your vendor! **\n"); pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); /* Expand the buffers to set size */ tracing_update_buffers(&global_trace); buffers_allocated = 1; /* * trace_printk_init_buffers() can be called by modules. * If that happens, then we need to start cmdline recording * directly here. If the global_trace.buffer is already * allocated here, then this was called by module code. */ if (global_trace.array_buffer.buffer) tracing_start_cmdline_record(); } EXPORT_SYMBOL_GPL(trace_printk_init_buffers); void trace_printk_start_comm(void) { /* Start tracing comms if trace printk is set */ if (!buffers_allocated) return; tracing_start_cmdline_record(); } static void trace_printk_start_stop_comm(int enabled) { if (!buffers_allocated) return; if (enabled) tracing_start_cmdline_record(); else tracing_stop_cmdline_record(); } /** * trace_vbprintk - write binary msg to tracing buffer * @ip: The address of the caller * @fmt: The string format to write to the buffer * @args: Arguments for @fmt */ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args) { struct ring_buffer_event *event; struct trace_buffer *buffer; struct trace_array *tr = READ_ONCE(printk_trace); struct bprint_entry *entry; unsigned int trace_ctx; char *tbuffer; int len = 0, size; if (!printk_binsafe(tr)) return trace_vprintk(ip, fmt, args); if (unlikely(tracing_selftest_running || tracing_disabled)) return 0; /* Don't pollute graph traces with trace_vprintk internals */ pause_graph_tracing(); trace_ctx = tracing_gen_ctx(); guard(preempt_notrace)(); tbuffer = get_trace_buf(); if (!tbuffer) { len = 0; goto out_nobuffer; } len = vbin_printf((u32 *)tbuffer, TRACE_BUF_SIZE/sizeof(int), fmt, args); if (len > TRACE_BUF_SIZE/sizeof(int) || len < 0) goto out_put; size = sizeof(*entry) + sizeof(u32) * len; buffer = tr->array_buffer.buffer; scoped_guard(ring_buffer_nest, buffer) { event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size, trace_ctx); if (!event) goto out_put; entry = ring_buffer_event_data(event); entry->ip = ip; entry->fmt = fmt; memcpy(entry->buf, tbuffer, sizeof(u32) * len); __buffer_unlock_commit(buffer, event); ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL); } out_put: put_trace_buf(); out_nobuffer: unpause_graph_tracing(); return len; } EXPORT_SYMBOL_GPL(trace_vbprintk); static __printf(3, 0) int __trace_array_vprintk(struct trace_buffer *buffer, unsigned long ip, const char *fmt, va_list args) { struct ring_buffer_event *event; int len = 0, size; struct print_entry *entry; unsigned int trace_ctx; char *tbuffer; if (tracing_disabled) return 0; /* Don't pollute graph traces with trace_vprintk internals */ pause_graph_tracing(); trace_ctx = tracing_gen_ctx(); guard(preempt_notrace)(); tbuffer = get_trace_buf(); if (!tbuffer) { len = 0; goto out_nobuffer; } len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args); size = sizeof(*entry) + len + 1; scoped_guard(ring_buffer_nest, buffer) { event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, trace_ctx); if (!event) goto out; entry = ring_buffer_event_data(event); entry->ip = ip; memcpy(&entry->buf, tbuffer, len + 1); __buffer_unlock_commit(buffer, event); ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL); } out: put_trace_buf(); out_nobuffer: unpause_graph_tracing(); return len; } int trace_array_vprintk(struct trace_array *tr, unsigned long ip, const char *fmt, va_list args) { if (tracing_selftest_running && tr == &global_trace) return 0; return __trace_array_vprintk(tr->array_buffer.buffer, ip, fmt, args); } /** * trace_array_printk - Print a message to a specific instance * @tr: The instance trace_array descriptor * @ip: The instruction pointer that this is called from. * @fmt: The format to print (printf format) * * If a subsystem sets up its own instance, they have the right to * printk strings into their tracing instance buffer using this * function. Note, this function will not write into the top level * buffer (use trace_printk() for that), as writing into the top level * buffer should only have events that can be individually disabled. * trace_printk() is only used for debugging a kernel, and should not * be ever incorporated in normal use. * * trace_array_printk() can be used, as it will not add noise to the * top level tracing buffer. * * Note, trace_array_init_printk() must be called on @tr before this * can be used. */ int trace_array_printk(struct trace_array *tr, unsigned long ip, const char *fmt, ...) { int ret; va_list ap; if (!tr) return -ENOENT; /* This is only allowed for created instances */ if (tr == &global_trace) return 0; if (!(tr->trace_flags & TRACE_ITER_PRINTK)) return 0; va_start(ap, fmt); ret = trace_array_vprintk(tr, ip, fmt, ap); va_end(ap); return ret; } EXPORT_SYMBOL_GPL(trace_array_printk); /** * trace_array_init_printk - Initialize buffers for trace_array_printk() * @tr: The trace array to initialize the buffers for * * As trace_array_printk() only writes into instances, they are OK to * have in the kernel (unlike trace_printk()). This needs to be called * before trace_array_printk() can be used on a trace_array. */ int trace_array_init_printk(struct trace_array *tr) { if (!tr) return -ENOENT; /* This is only allowed for created instances */ if (tr == &global_trace) return -EINVAL; return alloc_percpu_trace_buffer(); } EXPORT_SYMBOL_GPL(trace_array_init_printk); int trace_array_printk_buf(struct trace_buffer *buffer, unsigned long ip, const char *fmt, ...) { int ret; va_list ap; if (!(printk_trace->trace_flags & TRACE_ITER_PRINTK)) return 0; va_start(ap, fmt); ret = __trace_array_vprintk(buffer, ip, fmt, ap); va_end(ap); return ret; } int trace_vprintk(unsigned long ip, const char *fmt, va_list args) { return trace_array_vprintk(printk_trace, ip, fmt, args); } EXPORT_SYMBOL_GPL(trace_vprintk); static void trace_iterator_increment(struct trace_iterator *iter) { struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, iter->cpu); iter->idx++; if (buf_iter) ring_buffer_iter_advance(buf_iter); } static struct trace_entry * peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts, unsigned long *lost_events) { struct ring_buffer_event *event; struct ring_buffer_iter *buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) { event = ring_buffer_iter_peek(buf_iter, ts); if (lost_events) *lost_events = ring_buffer_iter_dropped(buf_iter) ? (unsigned long)-1 : 0; } else { event = ring_buffer_peek(iter->array_buffer->buffer, cpu, ts, lost_events); } if (event) { iter->ent_size = ring_buffer_event_length(event); return ring_buffer_event_data(event); } iter->ent_size = 0; return NULL; } static struct trace_entry * __find_next_entry(struct trace_iterator *iter, int *ent_cpu, unsigned long *missing_events, u64 *ent_ts) { struct trace_buffer *buffer = iter->array_buffer->buffer; struct trace_entry *ent, *next = NULL; unsigned long lost_events = 0, next_lost = 0; int cpu_file = iter->cpu_file; u64 next_ts = 0, ts; int next_cpu = -1; int next_size = 0; int cpu; /* * If we are in a per_cpu trace file, don't bother by iterating over * all cpu and peek directly. */ if (cpu_file > RING_BUFFER_ALL_CPUS) { if (ring_buffer_empty_cpu(buffer, cpu_file)) return NULL; ent = peek_next_entry(iter, cpu_file, ent_ts, missing_events); if (ent_cpu) *ent_cpu = cpu_file; return ent; } for_each_tracing_cpu(cpu) { if (ring_buffer_empty_cpu(buffer, cpu)) continue; ent = peek_next_entry(iter, cpu, &ts, &lost_events); /* * Pick the entry with the smallest timestamp: */ if (ent && (!next || ts < next_ts)) { next = ent; next_cpu = cpu; next_ts = ts; next_lost = lost_events; next_size = iter->ent_size; } } iter->ent_size = next_size; if (ent_cpu) *ent_cpu = next_cpu; if (ent_ts) *ent_ts = next_ts; if (missing_events) *missing_events = next_lost; return next; } #define STATIC_FMT_BUF_SIZE 128 static char static_fmt_buf[STATIC_FMT_BUF_SIZE]; char *trace_iter_expand_format(struct trace_iterator *iter) { char *tmp; /* * iter->tr is NULL when used with tp_printk, which makes * this get called where it is not safe to call krealloc(). */ if (!iter->tr || iter->fmt == static_fmt_buf) return NULL; tmp = krealloc(iter->fmt, iter->fmt_size + STATIC_FMT_BUF_SIZE, GFP_KERNEL); if (tmp) { iter->fmt_size += STATIC_FMT_BUF_SIZE; iter->fmt = tmp; } return tmp; } /* Returns true if the string is safe to dereference from an event */ static bool trace_safe_str(struct trace_iterator *iter, const char *str) { unsigned long addr = (unsigned long)str; struct trace_event *trace_event; struct trace_event_call *event; /* OK if part of the event data */ if ((addr >= (unsigned long)iter->ent) && (addr < (unsigned long)iter->ent + iter->ent_size)) return true; /* OK if part of the temp seq buffer */ if ((addr >= (unsigned long)iter->tmp_seq.buffer) && (addr < (unsigned long)iter->tmp_seq.buffer + TRACE_SEQ_BUFFER_SIZE)) return true; /* Core rodata can not be freed */ if (is_kernel_rodata(addr)) return true; if (trace_is_tracepoint_string(str)) return true; /* * Now this could be a module event, referencing core module * data, which is OK. */ if (!iter->ent) return false; trace_event = ftrace_find_event(iter->ent->type); if (!trace_event) return false; event = container_of(trace_event, struct trace_event_call, event); if ((event->flags & TRACE_EVENT_FL_DYNAMIC) || !event->module) return false; /* Would rather have rodata, but this will suffice */ if (within_module_core(addr, event->module)) return true; return false; } /** * ignore_event - Check dereferenced fields while writing to the seq buffer * @iter: The iterator that holds the seq buffer and the event being printed * * At boot up, test_event_printk() will flag any event that dereferences * a string with "%s" that does exist in the ring buffer. It may still * be valid, as the string may point to a static string in the kernel * rodata that never gets freed. But if the string pointer is pointing * to something that was allocated, there's a chance that it can be freed * by the time the user reads the trace. This would cause a bad memory * access by the kernel and possibly crash the system. * * This function will check if the event has any fields flagged as needing * to be checked at runtime and perform those checks. * * If it is found that a field is unsafe, it will write into the @iter->seq * a message stating what was found to be unsafe. * * @return: true if the event is unsafe and should be ignored, * false otherwise. */ bool ignore_event(struct trace_iterator *iter) { struct ftrace_event_field *field; struct trace_event *trace_event; struct trace_event_call *event; struct list_head *head; struct trace_seq *seq; const void *ptr; trace_event = ftrace_find_event(iter->ent->type); seq = &iter->seq; if (!trace_event) { trace_seq_printf(seq, "EVENT ID %d NOT FOUND?\n", iter->ent->type); return true; } event = container_of(trace_event, struct trace_event_call, event); if (!(event->flags & TRACE_EVENT_FL_TEST_STR)) return false; head = trace_get_fields(event); if (!head) { trace_seq_printf(seq, "FIELDS FOR EVENT '%s' NOT FOUND?\n", trace_event_name(event)); return true; } /* Offsets are from the iter->ent that points to the raw event */ ptr = iter->ent; list_for_each_entry(field, head, link) { const char *str; bool good; if (!field->needs_test) continue; str = *(const char **)(ptr + field->offset); good = trace_safe_str(iter, str); /* * If you hit this warning, it is likely that the * trace event in question used %s on a string that * was saved at the time of the event, but may not be * around when the trace is read. Use __string(), * __assign_str() and __get_str() helpers in the TRACE_EVENT() * instead. See samples/trace_events/trace-events-sample.h * for reference. */ if (WARN_ONCE(!good, "event '%s' has unsafe pointer field '%s'", trace_event_name(event), field->name)) { trace_seq_printf(seq, "EVENT %s: HAS UNSAFE POINTER FIELD '%s'\n", trace_event_name(event), field->name); return true; } } return false; } const char *trace_event_format(struct trace_iterator *iter, const char *fmt) { const char *p, *new_fmt; char *q; if (WARN_ON_ONCE(!fmt)) return fmt; if (!iter->tr || iter->tr->trace_flags & TRACE_ITER_HASH_PTR) return fmt; p = fmt; new_fmt = q = iter->fmt; while (*p) { if (unlikely(q - new_fmt + 3 > iter->fmt_size)) { if (!trace_iter_expand_format(iter)) return fmt; q += iter->fmt - new_fmt; new_fmt = iter->fmt; } *q++ = *p++; /* Replace %p with %px */ if (p[-1] == '%') { if (p[0] == '%') { *q++ = *p++; } else if (p[0] == 'p' && !isalnum(p[1])) { *q++ = *p++; *q++ = 'x'; } } } *q = '\0'; return new_fmt; } #define STATIC_TEMP_BUF_SIZE 128 static char static_temp_buf[STATIC_TEMP_BUF_SIZE] __aligned(4); /* Find the next real entry, without updating the iterator itself */ struct trace_entry *trace_find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts) { /* __find_next_entry will reset ent_size */ int ent_size = iter->ent_size; struct trace_entry *entry; /* * If called from ftrace_dump(), then the iter->temp buffer * will be the static_temp_buf and not created from kmalloc. * If the entry size is greater than the buffer, we can * not save it. Just return NULL in that case. This is only * used to add markers when two consecutive events' time * stamps have a large delta. See trace_print_lat_context() */ if (iter->temp == static_temp_buf && STATIC_TEMP_BUF_SIZE < ent_size) return NULL; /* * The __find_next_entry() may call peek_next_entry(), which may * call ring_buffer_peek() that may make the contents of iter->ent * undefined. Need to copy iter->ent now. */ if (iter->ent && iter->ent != iter->temp) { if ((!iter->temp || iter->temp_size < iter->ent_size) && !WARN_ON_ONCE(iter->temp == static_temp_buf)) { void *temp; temp = kmalloc(iter->ent_size, GFP_KERNEL); if (!temp) return NULL; kfree(iter->temp); iter->temp = temp; iter->temp_size = iter->ent_size; } memcpy(iter->temp, iter->ent, iter->ent_size); iter->ent = iter->temp; } entry = __find_next_entry(iter, ent_cpu, NULL, ent_ts); /* Put back the original ent_size */ iter->ent_size = ent_size; return entry; } /* Find the next real entry, and increment the iterator to the next entry */ void *trace_find_next_entry_inc(struct trace_iterator *iter) { iter->ent = __find_next_entry(iter, &iter->cpu, &iter->lost_events, &iter->ts); if (iter->ent) trace_iterator_increment(iter); return iter->ent ? iter : NULL; } static void trace_consume(struct trace_iterator *iter) { ring_buffer_consume(iter->array_buffer->buffer, iter->cpu, &iter->ts, &iter->lost_events); } static void *s_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_iterator *iter = m->private; int i = (int)*pos; void *ent; WARN_ON_ONCE(iter->leftover); (*pos)++; /* can't go backwards */ if (iter->idx > i) return NULL; if (iter->idx < 0) ent = trace_find_next_entry_inc(iter); else ent = iter; while (ent && iter->idx < i) ent = trace_find_next_entry_inc(iter); iter->pos = *pos; return ent; } void tracing_iter_reset(struct trace_iterator *iter, int cpu) { struct ring_buffer_iter *buf_iter; unsigned long entries = 0; u64 ts; per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = 0; buf_iter = trace_buffer_iter(iter, cpu); if (!buf_iter) return; ring_buffer_iter_reset(buf_iter); /* * We could have the case with the max latency tracers * that a reset never took place on a cpu. This is evident * by the timestamp being before the start of the buffer. */ while (ring_buffer_iter_peek(buf_iter, &ts)) { if (ts >= iter->array_buffer->time_start) break; entries++; ring_buffer_iter_advance(buf_iter); /* This could be a big loop */ cond_resched(); } per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries; } /* * The current tracer is copied to avoid a global locking * all around. */ static void *s_start(struct seq_file *m, loff_t *pos) { struct trace_iterator *iter = m->private; struct trace_array *tr = iter->tr; int cpu_file = iter->cpu_file; void *p = NULL; loff_t l = 0; int cpu; mutex_lock(&trace_types_lock); if (unlikely(tr->current_trace != iter->trace)) { /* Close iter->trace before switching to the new current tracer */ if (iter->trace->close) iter->trace->close(iter); iter->trace = tr->current_trace; /* Reopen the new current tracer */ if (iter->trace->open) iter->trace->open(iter); } mutex_unlock(&trace_types_lock); #ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->trace->use_max_tr) return ERR_PTR(-EBUSY); #endif if (*pos != iter->pos) { iter->ent = NULL; iter->cpu = 0; iter->idx = -1; if (cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) tracing_iter_reset(iter, cpu); } else tracing_iter_reset(iter, cpu_file); iter->leftover = 0; for (p = iter; p && l < *pos; p = s_next(m, p, &l)) ; } else { /* * If we overflowed the seq_file before, then we want * to just reuse the trace_seq buffer again. */ if (iter->leftover) p = iter; else { l = *pos - 1; p = s_next(m, p, &l); } } trace_event_read_lock(); trace_access_lock(cpu_file); return p; } static void s_stop(struct seq_file *m, void *p) { struct trace_iterator *iter = m->private; #ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->trace->use_max_tr) return; #endif trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); } static void get_total_entries_cpu(struct array_buffer *buf, unsigned long *total, unsigned long *entries, int cpu) { unsigned long count; count = ring_buffer_entries_cpu(buf->buffer, cpu); /* * If this buffer has skipped entries, then we hold all * entries for the trace and we need to ignore the * ones before the time stamp. */ if (per_cpu_ptr(buf->data, cpu)->skipped_entries) { count -= per_cpu_ptr(buf->data, cpu)->skipped_entries; /* total is the same as the entries */ *total = count; } else *total = count + ring_buffer_overrun_cpu(buf->buffer, cpu); *entries = count; } static void get_total_entries(struct array_buffer *buf, unsigned long *total, unsigned long *entries) { unsigned long t, e; int cpu; *total = 0; *entries = 0; for_each_tracing_cpu(cpu) { get_total_entries_cpu(buf, &t, &e, cpu); *total += t; *entries += e; } } unsigned long trace_total_entries_cpu(struct trace_array *tr, int cpu) { unsigned long total, entries; if (!tr) tr = &global_trace; get_total_entries_cpu(&tr->array_buffer, &total, &entries, cpu); return entries; } unsigned long trace_total_entries(struct trace_array *tr) { unsigned long total, entries; if (!tr) tr = &global_trace; get_total_entries(&tr->array_buffer, &total, &entries); return entries; } static void print_lat_help_header(struct seq_file *m) { seq_puts(m, "# _------=> CPU# \n" "# / _-----=> irqs-off/BH-disabled\n" "# | / _----=> need-resched \n" "# || / _---=> hardirq/softirq \n" "# ||| / _--=> preempt-depth \n" "# |||| / _-=> migrate-disable \n" "# ||||| / delay \n" "# cmd pid |||||| time | caller \n" "# \\ / |||||| \\ | / \n"); } static void print_event_info(struct array_buffer *buf, struct seq_file *m) { unsigned long total; unsigned long entries; get_total_entries(buf, &total, &entries); seq_printf(m, "# entries-in-buffer/entries-written: %lu/%lu #P:%d\n", entries, total, num_online_cpus()); seq_puts(m, "#\n"); } static void print_func_help_header(struct array_buffer *buf, struct seq_file *m, unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; print_event_info(buf, m); seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? " TGID " : ""); seq_printf(m, "# | | %s | | |\n", tgid ? " | " : ""); } static void print_func_help_header_irq(struct array_buffer *buf, struct seq_file *m, unsigned int flags) { bool tgid = flags & TRACE_ITER_RECORD_TGID; static const char space[] = " "; int prec = tgid ? 12 : 2; print_event_info(buf, m); seq_printf(m, "# %.*s _-----=> irqs-off/BH-disabled\n", prec, space); seq_printf(m, "# %.*s / _----=> need-resched\n", prec, space); seq_printf(m, "# %.*s| / _---=> hardirq/softirq\n", prec, space); seq_printf(m, "# %.*s|| / _--=> preempt-depth\n", prec, space); seq_printf(m, "# %.*s||| / _-=> migrate-disable\n", prec, space); seq_printf(m, "# %.*s|||| / delay\n", prec, space); seq_printf(m, "# TASK-PID %.*s CPU# ||||| TIMESTAMP FUNCTION\n", prec, " TGID "); seq_printf(m, "# | | %.*s | ||||| | |\n", prec, " | "); } void print_trace_header(struct seq_file *m, struct trace_iterator *iter) { unsigned long sym_flags = (global_trace.trace_flags & TRACE_ITER_SYM_MASK); struct array_buffer *buf = iter->array_buffer; struct trace_array_cpu *data = per_cpu_ptr(buf->data, buf->cpu); struct tracer *type = iter->trace; unsigned long entries; unsigned long total; const char *name = type->name; get_total_entries(buf, &total, &entries); seq_printf(m, "# %s latency trace v1.1.5 on %s\n", name, init_utsname()->release); seq_puts(m, "# -----------------------------------" "---------------------------------\n"); seq_printf(m, "# latency: %lu us, #%lu/%lu, CPU#%d |" " (M:%s VP:%d, KP:%d, SP:%d HP:%d", nsecs_to_usecs(data->saved_latency), entries, total, buf->cpu, preempt_model_str(), /* These are reserved for later use */ 0, 0, 0, 0); #ifdef CONFIG_SMP seq_printf(m, " #P:%d)\n", num_online_cpus()); #else seq_puts(m, ")\n"); #endif seq_puts(m, "# -----------------\n"); seq_printf(m, "# | task: %.16s-%d " "(uid:%d nice:%ld policy:%ld rt_prio:%ld)\n", data->comm, data->pid, from_kuid_munged(seq_user_ns(m), data->uid), data->nice, data->policy, data->rt_priority); seq_puts(m, "# -----------------\n"); if (data->critical_start) { seq_puts(m, "# => started at: "); seq_print_ip_sym(&iter->seq, data->critical_start, sym_flags); trace_print_seq(m, &iter->seq); seq_puts(m, "\n# => ended at: "); seq_print_ip_sym(&iter->seq, data->critical_end, sym_flags); trace_print_seq(m, &iter->seq); seq_puts(m, "\n#\n"); } seq_puts(m, "#\n"); } static void test_cpu_buff_start(struct trace_iterator *iter) { struct trace_seq *s = &iter->seq; struct trace_array *tr = iter->tr; if (!(tr->trace_flags & TRACE_ITER_ANNOTATE)) return; if (!(iter->iter_flags & TRACE_FILE_ANNOTATE)) return; if (cpumask_available(iter->started) && cpumask_test_cpu(iter->cpu, iter->started)) return; if (per_cpu_ptr(iter->array_buffer->data, iter->cpu)->skipped_entries) return; if (cpumask_available(iter->started)) cpumask_set_cpu(iter->cpu, iter->started); /* Don't print started cpu buffer for the first entry of the trace */ if (iter->idx > 1) trace_seq_printf(s, "##### CPU %u buffer started ####\n", iter->cpu); } static enum print_line_t print_trace_fmt(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; unsigned long sym_flags = (tr->trace_flags & TRACE_ITER_SYM_MASK); struct trace_entry *entry; struct trace_event *event; entry = iter->ent; test_cpu_buff_start(iter); event = ftrace_find_event(entry->type); if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) { if (iter->iter_flags & TRACE_FILE_LAT_FMT) trace_print_lat_context(iter); else trace_print_context(iter); } if (trace_seq_has_overflowed(s)) return TRACE_TYPE_PARTIAL_LINE; if (event) { if (tr->trace_flags & TRACE_ITER_FIELDS) return print_event_fields(iter, event); /* * For TRACE_EVENT() events, the print_fmt is not * safe to use if the array has delta offsets * Force printing via the fields. */ if ((tr->text_delta) && event->type > __TRACE_LAST_TYPE) return print_event_fields(iter, event); return event->funcs->trace(iter, sym_flags, event); } trace_seq_printf(s, "Unknown type %d\n", entry->type); return trace_handle_return(s); } static enum print_line_t print_raw_fmt(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; struct trace_entry *entry; struct trace_event *event; entry = iter->ent; if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) trace_seq_printf(s, "%d %d %llu ", entry->pid, iter->cpu, iter->ts); if (trace_seq_has_overflowed(s)) return TRACE_TYPE_PARTIAL_LINE; event = ftrace_find_event(entry->type); if (event) return event->funcs->raw(iter, 0, event); trace_seq_printf(s, "%d ?\n", entry->type); return trace_handle_return(s); } static enum print_line_t print_hex_fmt(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; unsigned char newline = '\n'; struct trace_entry *entry; struct trace_event *event; entry = iter->ent; if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) { SEQ_PUT_HEX_FIELD(s, entry->pid); SEQ_PUT_HEX_FIELD(s, iter->cpu); SEQ_PUT_HEX_FIELD(s, iter->ts); if (trace_seq_has_overflowed(s)) return TRACE_TYPE_PARTIAL_LINE; } event = ftrace_find_event(entry->type); if (event) { enum print_line_t ret = event->funcs->hex(iter, 0, event); if (ret != TRACE_TYPE_HANDLED) return ret; } SEQ_PUT_FIELD(s, newline); return trace_handle_return(s); } static enum print_line_t print_bin_fmt(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; struct trace_seq *s = &iter->seq; struct trace_entry *entry; struct trace_event *event; entry = iter->ent; if (tr->trace_flags & TRACE_ITER_CONTEXT_INFO) { SEQ_PUT_FIELD(s, entry->pid); SEQ_PUT_FIELD(s, iter->cpu); SEQ_PUT_FIELD(s, iter->ts); if (trace_seq_has_overflowed(s)) return TRACE_TYPE_PARTIAL_LINE; } event = ftrace_find_event(entry->type); return event ? event->funcs->binary(iter, 0, event) : TRACE_TYPE_HANDLED; } int trace_empty(struct trace_iterator *iter) { struct ring_buffer_iter *buf_iter; int cpu; /* If we are looking at one CPU buffer, only check that one */ if (iter->cpu_file != RING_BUFFER_ALL_CPUS) { cpu = iter->cpu_file; buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) { if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->array_buffer->buffer, cpu)) return 0; } return 1; } for_each_tracing_cpu(cpu) { buf_iter = trace_buffer_iter(iter, cpu); if (buf_iter) { if (!ring_buffer_iter_empty(buf_iter)) return 0; } else { if (!ring_buffer_empty_cpu(iter->array_buffer->buffer, cpu)) return 0; } } return 1; } /* Called with trace_event_read_lock() held. */ enum print_line_t print_trace_line(struct trace_iterator *iter) { struct trace_array *tr = iter->tr; unsigned long trace_flags = tr->trace_flags; enum print_line_t ret; if (iter->lost_events) { if (iter->lost_events == (unsigned long)-1) trace_seq_printf(&iter->seq, "CPU:%d [LOST EVENTS]\n", iter->cpu); else trace_seq_printf(&iter->seq, "CPU:%d [LOST %lu EVENTS]\n", iter->cpu, iter->lost_events); if (trace_seq_has_overflowed(&iter->seq)) return TRACE_TYPE_PARTIAL_LINE; } if (iter->trace && iter->trace->print_line) { ret = iter->trace->print_line(iter); if (ret != TRACE_TYPE_UNHANDLED) return ret; } if (iter->ent->type == TRACE_BPUTS && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) return trace_print_bputs_msg_only(iter); if (iter->ent->type == TRACE_BPRINT && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) return trace_print_bprintk_msg_only(iter); if (iter->ent->type == TRACE_PRINT && trace_flags & TRACE_ITER_PRINTK && trace_flags & TRACE_ITER_PRINTK_MSGONLY) return trace_print_printk_msg_only(iter); if (trace_flags & TRACE_ITER_BIN) return print_bin_fmt(iter); if (trace_flags & TRACE_ITER_HEX) return print_hex_fmt(iter); if (trace_flags & TRACE_ITER_RAW) return print_raw_fmt(iter); return print_trace_fmt(iter); } void trace_latency_header(struct seq_file *m) { struct trace_iterator *iter = m->private; struct trace_array *tr = iter->tr; /* print nothing if the buffers are empty */ if (trace_empty(iter)) return; if (iter->iter_flags & TRACE_FILE_LAT_FMT) print_trace_header(m, iter); if (!(tr->trace_flags & TRACE_ITER_VERBOSE)) print_lat_help_header(m); } void trace_default_header(struct seq_file *m) { struct trace_iterator *iter = m->private; struct trace_array *tr = iter->tr; unsigned long trace_flags = tr->trace_flags; if (!(trace_flags & TRACE_ITER_CONTEXT_INFO)) return; if (iter->iter_flags & TRACE_FILE_LAT_FMT) { /* print nothing if the buffers are empty */ if (trace_empty(iter)) return; print_trace_header(m, iter); if (!(trace_flags & TRACE_ITER_VERBOSE)) print_lat_help_header(m); } else { if (!(trace_flags & TRACE_ITER_VERBOSE)) { if (trace_flags & TRACE_ITER_IRQ_INFO) print_func_help_header_irq(iter->array_buffer, m, trace_flags); else print_func_help_header(iter->array_buffer, m, trace_flags); } } } static void test_ftrace_alive(struct seq_file *m) { if (!ftrace_is_dead()) return; seq_puts(m, "# WARNING: FUNCTION TRACING IS CORRUPTED\n" "# MAY BE MISSING FUNCTION EVENTS\n"); } #ifdef CONFIG_TRACER_MAX_TRACE static void show_snapshot_main_help(struct seq_file *m) { seq_puts(m, "# echo 0 > snapshot : Clears and frees snapshot buffer\n" "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n" "# Takes a snapshot of the main buffer.\n" "# echo 2 > snapshot : Clears snapshot buffer (but does not allocate or free)\n" "# (Doesn't have to be '2' works with any number that\n" "# is not a '0' or '1')\n"); } static void show_snapshot_percpu_help(struct seq_file *m) { seq_puts(m, "# echo 0 > snapshot : Invalid for per_cpu snapshot file.\n"); #ifdef CONFIG_RING_BUFFER_ALLOW_SWAP seq_puts(m, "# echo 1 > snapshot : Allocates snapshot buffer, if not already allocated.\n" "# Takes a snapshot of the main buffer for this cpu.\n"); #else seq_puts(m, "# echo 1 > snapshot : Not supported with this kernel.\n" "# Must use main snapshot file to allocate.\n"); #endif seq_puts(m, "# echo 2 > snapshot : Clears this cpu's snapshot buffer (but does not allocate)\n" "# (Doesn't have to be '2' works with any number that\n" "# is not a '0' or '1')\n"); } static void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { if (iter->tr->allocated_snapshot) seq_puts(m, "#\n# * Snapshot is allocated *\n#\n"); else seq_puts(m, "#\n# * Snapshot is freed *\n#\n"); seq_puts(m, "# Snapshot commands:\n"); if (iter->cpu_file == RING_BUFFER_ALL_CPUS) show_snapshot_main_help(m); else show_snapshot_percpu_help(m); } #else /* Should never be called */ static inline void print_snapshot_help(struct seq_file *m, struct trace_iterator *iter) { } #endif static int s_show(struct seq_file *m, void *v) { struct trace_iterator *iter = v; int ret; if (iter->ent == NULL) { if (iter->tr) { seq_printf(m, "# tracer: %s\n", iter->trace->name); seq_puts(m, "#\n"); test_ftrace_alive(m); } if (iter->snapshot && trace_empty(iter)) print_snapshot_help(m, iter); else if (iter->trace && iter->trace->print_header) iter->trace->print_header(m); else trace_default_header(m); } else if (iter->leftover) { /* * If we filled the seq_file buffer earlier, we * want to just show it now. */ ret = trace_print_seq(m, &iter->seq); /* ret should this time be zero, but you never know */ iter->leftover = ret; } else { ret = print_trace_line(iter); if (ret == TRACE_TYPE_PARTIAL_LINE) { iter->seq.full = 0; trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); } ret = trace_print_seq(m, &iter->seq); /* * If we overflow the seq_file buffer, then it will * ask us for this data again at start up. * Use that instead. * ret is 0 if seq_file write succeeded. * -1 otherwise. */ iter->leftover = ret; } return 0; } /* * Should be used after trace_array_get(), trace_types_lock * ensures that i_cdev was already initialized. */ static inline int tracing_get_cpu(struct inode *inode) { if (inode->i_cdev) /* See trace_create_cpu_file() */ return (long)inode->i_cdev - 1; return RING_BUFFER_ALL_CPUS; } static const struct seq_operations tracer_seq_ops = { .start = s_start, .next = s_next, .stop = s_stop, .show = s_show, }; /* * Note, as iter itself can be allocated and freed in different * ways, this function is only used to free its content, and not * the iterator itself. The only requirement to all the allocations * is that it must zero all fields (kzalloc), as freeing works with * ethier allocated content or NULL. */ static void free_trace_iter_content(struct trace_iterator *iter) { /* The fmt is either NULL, allocated or points to static_fmt_buf */ if (iter->fmt != static_fmt_buf) kfree(iter->fmt); kfree(iter->temp); kfree(iter->buffer_iter); mutex_destroy(&iter->mutex); free_cpumask_var(iter->started); } static struct trace_iterator * __tracing_open(struct inode *inode, struct file *file, bool snapshot) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int cpu; if (tracing_disabled) return ERR_PTR(-ENODEV); iter = __seq_open_private(file, &tracer_seq_ops, sizeof(*iter)); if (!iter) return ERR_PTR(-ENOMEM); iter->buffer_iter = kcalloc(nr_cpu_ids, sizeof(*iter->buffer_iter), GFP_KERNEL); if (!iter->buffer_iter) goto release; /* * trace_find_next_entry() may need to save off iter->ent. * It will place it into the iter->temp buffer. As most * events are less than 128, allocate a buffer of that size. * If one is greater, then trace_find_next_entry() will * allocate a new buffer to adjust for the bigger iter->ent. * It's not critical if it fails to get allocated here. */ iter->temp = kmalloc(128, GFP_KERNEL); if (iter->temp) iter->temp_size = 128; /* * trace_event_printf() may need to modify given format * string to replace %p with %px so that it shows real address * instead of hash value. However, that is only for the event * tracing, other tracer may not need. Defer the allocation * until it is needed. */ iter->fmt = NULL; iter->fmt_size = 0; mutex_lock(&trace_types_lock); iter->trace = tr->current_trace; if (!zalloc_cpumask_var(&iter->started, GFP_KERNEL)) goto fail; iter->tr = tr; #ifdef CONFIG_TRACER_MAX_TRACE /* Currently only the top directory has a snapshot */ if (tr->current_trace->print_max || snapshot) iter->array_buffer = &tr->max_buffer; else #endif iter->array_buffer = &tr->array_buffer; iter->snapshot = snapshot; iter->pos = -1; iter->cpu_file = tracing_get_cpu(inode); mutex_init(&iter->mutex); /* Notify the tracer early; before we stop tracing. */ if (iter->trace->open) iter->trace->open(iter); /* Annotate start of buffers if we had overruns */ if (ring_buffer_overruns(iter->array_buffer->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; /* * If pause-on-trace is enabled, then stop the trace while * dumping, unless this is the "snapshot" file */ if (!iter->snapshot && (tr->trace_flags & TRACE_ITER_PAUSE_ON_TRACE)) tracing_stop_tr(tr); if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { iter->buffer_iter[cpu] = ring_buffer_read_start(iter->array_buffer->buffer, cpu, GFP_KERNEL); tracing_iter_reset(iter, cpu); } } else { cpu = iter->cpu_file; iter->buffer_iter[cpu] = ring_buffer_read_start(iter->array_buffer->buffer, cpu, GFP_KERNEL); tracing_iter_reset(iter, cpu); } mutex_unlock(&trace_types_lock); return iter; fail: mutex_unlock(&trace_types_lock); free_trace_iter_content(iter); release: seq_release_private(inode, file); return ERR_PTR(-ENOMEM); } int tracing_open_generic(struct inode *inode, struct file *filp) { int ret; ret = tracing_check_open_get_tr(NULL); if (ret) return ret; filp->private_data = inode->i_private; return 0; } bool tracing_is_disabled(void) { return (tracing_disabled) ? true: false; } /* * Open and update trace_array ref count. * Must have the current trace_array passed to it. */ int tracing_open_generic_tr(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; filp->private_data = inode->i_private; return 0; } /* * The private pointer of the inode is the trace_event_file. * Update the tr ref count associated to it. */ int tracing_open_file_tr(struct inode *inode, struct file *filp) { struct trace_event_file *file = inode->i_private; int ret; ret = tracing_check_open_get_tr(file->tr); if (ret) return ret; guard(mutex)(&event_mutex); /* Fail if the file is marked for removal */ if (file->flags & EVENT_FILE_FL_FREED) { trace_array_put(file->tr); return -ENODEV; } else { event_file_get(file); } filp->private_data = inode->i_private; return 0; } int tracing_release_file_tr(struct inode *inode, struct file *filp) { struct trace_event_file *file = inode->i_private; trace_array_put(file->tr); event_file_put(file); return 0; } int tracing_single_release_file_tr(struct inode *inode, struct file *filp) { tracing_release_file_tr(inode, filp); return single_release(inode, filp); } static int tracing_mark_open(struct inode *inode, struct file *filp) { stream_open(inode, filp); return tracing_open_generic_tr(inode, filp); } static int tracing_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct seq_file *m = file->private_data; struct trace_iterator *iter; int cpu; if (!(file->f_mode & FMODE_READ)) { trace_array_put(tr); return 0; } /* Writes do not use seq_file */ iter = m->private; mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { if (iter->buffer_iter[cpu]) ring_buffer_read_finish(iter->buffer_iter[cpu]); } if (iter->trace && iter->trace->close) iter->trace->close(iter); if (!iter->snapshot && tr->stop_count) /* reenable tracing if it was previously enabled */ tracing_start_tr(tr); __trace_array_put(tr); mutex_unlock(&trace_types_lock); free_trace_iter_content(iter); seq_release_private(inode, file); return 0; } int tracing_release_generic_tr(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; trace_array_put(tr); return 0; } static int tracing_single_release_tr(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; trace_array_put(tr); return single_release(inode, file); } static int tracing_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; /* If this file was open for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) { int cpu = tracing_get_cpu(inode); struct array_buffer *trace_buf = &tr->array_buffer; #ifdef CONFIG_TRACER_MAX_TRACE if (tr->current_trace->print_max) trace_buf = &tr->max_buffer; #endif if (cpu == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(trace_buf); else tracing_reset_cpu(trace_buf, cpu); } if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, false); if (IS_ERR(iter)) ret = PTR_ERR(iter); else if (tr->trace_flags & TRACE_ITER_LATENCY_FMT) iter->iter_flags |= TRACE_FILE_LAT_FMT; } if (ret < 0) trace_array_put(tr); return ret; } /* * Some tracers are not suitable for instance buffers. * A tracer is always available for the global array (toplevel) * or if it explicitly states that it is. */ static bool trace_ok_for_array(struct tracer *t, struct trace_array *tr) { #ifdef CONFIG_TRACER_SNAPSHOT /* arrays with mapped buffer range do not have snapshots */ if (tr->range_addr_start && t->use_max_tr) return false; #endif return (tr->flags & TRACE_ARRAY_FL_GLOBAL) || t->allow_instances; } /* Find the next tracer that this trace array may use */ static struct tracer * get_tracer_for_array(struct trace_array *tr, struct tracer *t) { while (t && !trace_ok_for_array(t, tr)) t = t->next; return t; } static void * t_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_array *tr = m->private; struct tracer *t = v; (*pos)++; if (t) t = get_tracer_for_array(tr, t->next); return t; } static void *t_start(struct seq_file *m, loff_t *pos) { struct trace_array *tr = m->private; struct tracer *t; loff_t l = 0; mutex_lock(&trace_types_lock); t = get_tracer_for_array(tr, trace_types); for (; t && l < *pos; t = t_next(m, t, &l)) ; return t; } static void t_stop(struct seq_file *m, void *p) { mutex_unlock(&trace_types_lock); } static int t_show(struct seq_file *m, void *v) { struct tracer *t = v; if (!t) return 0; seq_puts(m, t->name); if (t->next) seq_putc(m, ' '); else seq_putc(m, '\n'); return 0; } static const struct seq_operations show_traces_seq_ops = { .start = t_start, .next = t_next, .stop = t_stop, .show = t_show, }; static int show_traces_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct seq_file *m; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = seq_open(file, &show_traces_seq_ops); if (ret) { trace_array_put(tr); return ret; } m = file->private_data; m->private = tr; return 0; } static int tracing_seq_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; trace_array_put(tr); return seq_release(inode, file); } static ssize_t tracing_write_stub(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) { return count; } loff_t tracing_lseek(struct file *file, loff_t offset, int whence) { int ret; if (file->f_mode & FMODE_READ) ret = seq_lseek(file, offset, whence); else file->f_pos = ret = 0; return ret; } static const struct file_operations tracing_fops = { .open = tracing_open, .read = seq_read, .read_iter = seq_read_iter, .splice_read = copy_splice_read, .write = tracing_write_stub, .llseek = tracing_lseek, .release = tracing_release, }; static const struct file_operations show_traces_fops = { .open = show_traces_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_seq_release, }; static ssize_t tracing_cpumask_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { struct trace_array *tr = file_inode(filp)->i_private; char *mask_str __free(kfree) = NULL; int len; len = snprintf(NULL, 0, "%*pb\n", cpumask_pr_args(tr->tracing_cpumask)) + 1; mask_str = kmalloc(len, GFP_KERNEL); if (!mask_str) return -ENOMEM; len = snprintf(mask_str, len, "%*pb\n", cpumask_pr_args(tr->tracing_cpumask)); if (len >= count) return -EINVAL; return simple_read_from_buffer(ubuf, count, ppos, mask_str, len); } int tracing_set_cpumask(struct trace_array *tr, cpumask_var_t tracing_cpumask_new) { int cpu; if (!tr) return -EINVAL; local_irq_disable(); arch_spin_lock(&tr->max_lock); for_each_tracing_cpu(cpu) { /* * Increase/decrease the disabled counter if we are * about to flip a bit in the cpumask: */ if (cpumask_test_cpu(cpu, tr->tracing_cpumask) && !cpumask_test_cpu(cpu, tracing_cpumask_new)) { ring_buffer_record_disable_cpu(tr->array_buffer.buffer, cpu); #ifdef CONFIG_TRACER_MAX_TRACE ring_buffer_record_disable_cpu(tr->max_buffer.buffer, cpu); #endif } if (!cpumask_test_cpu(cpu, tr->tracing_cpumask) && cpumask_test_cpu(cpu, tracing_cpumask_new)) { ring_buffer_record_enable_cpu(tr->array_buffer.buffer, cpu); #ifdef CONFIG_TRACER_MAX_TRACE ring_buffer_record_enable_cpu(tr->max_buffer.buffer, cpu); #endif } } arch_spin_unlock(&tr->max_lock); local_irq_enable(); cpumask_copy(tr->tracing_cpumask, tracing_cpumask_new); return 0; } static ssize_t tracing_cpumask_write(struct file *filp, const char __user *ubuf, size_t count, loff_t *ppos) { struct trace_array *tr = file_inode(filp)->i_private; cpumask_var_t tracing_cpumask_new; int err; if (count == 0 || count > KMALLOC_MAX_SIZE) return -EINVAL; if (!zalloc_cpumask_var(&tracing_cpumask_new, GFP_KERNEL)) return -ENOMEM; err = cpumask_parse_user(ubuf, count, tracing_cpumask_new); if (err) goto err_free; err = tracing_set_cpumask(tr, tracing_cpumask_new); if (err) goto err_free; free_cpumask_var(tracing_cpumask_new); return count; err_free: free_cpumask_var(tracing_cpumask_new); return err; } static const struct file_operations tracing_cpumask_fops = { .open = tracing_open_generic_tr, .read = tracing_cpumask_read, .write = tracing_cpumask_write, .release = tracing_release_generic_tr, .llseek = generic_file_llseek, }; static int tracing_trace_options_show(struct seq_file *m, void *v) { struct tracer_opt *trace_opts; struct trace_array *tr = m->private; u32 tracer_flags; int i; guard(mutex)(&trace_types_lock); tracer_flags = tr->current_trace->flags->val; trace_opts = tr->current_trace->flags->opts; for (i = 0; trace_options[i]; i++) { if (tr->trace_flags & (1 << i)) seq_printf(m, "%s\n", trace_options[i]); else seq_printf(m, "no%s\n", trace_options[i]); } for (i = 0; trace_opts[i].name; i++) { if (tracer_flags & trace_opts[i].bit) seq_printf(m, "%s\n", trace_opts[i].name); else seq_printf(m, "no%s\n", trace_opts[i].name); } return 0; } static int __set_tracer_option(struct trace_array *tr, struct tracer_flags *tracer_flags, struct tracer_opt *opts, int neg) { struct tracer *trace = tracer_flags->trace; int ret; ret = trace->set_flag(tr, tracer_flags->val, opts->bit, !neg); if (ret) return ret; if (neg) tracer_flags->val &= ~opts->bit; else tracer_flags->val |= opts->bit; return 0; } /* Try to assign a tracer specific option */ static int set_tracer_option(struct trace_array *tr, char *cmp, int neg) { struct tracer *trace = tr->current_trace; struct tracer_flags *tracer_flags = trace->flags; struct tracer_opt *opts = NULL; int i; for (i = 0; tracer_flags->opts[i].name; i++) { opts = &tracer_flags->opts[i]; if (strcmp(cmp, opts->name) == 0) return __set_tracer_option(tr, trace->flags, opts, neg); } return -EINVAL; } /* Some tracers require overwrite to stay enabled */ int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set) { if (tracer->enabled && (mask & TRACE_ITER_OVERWRITE) && !set) return -1; return 0; } int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled) { if ((mask == TRACE_ITER_RECORD_TGID) || (mask == TRACE_ITER_RECORD_CMD) || (mask == TRACE_ITER_TRACE_PRINTK) || (mask == TRACE_ITER_COPY_MARKER)) lockdep_assert_held(&event_mutex); /* do nothing if flag is already set */ if (!!(tr->trace_flags & mask) == !!enabled) return 0; /* Give the tracer a chance to approve the change */ if (tr->current_trace->flag_changed) if (tr->current_trace->flag_changed(tr, mask, !!enabled)) return -EINVAL; if (mask == TRACE_ITER_TRACE_PRINTK) { if (enabled) { update_printk_trace(tr); } else { /* * The global_trace cannot clear this. * It's flag only gets cleared if another instance sets it. */ if (printk_trace == &global_trace) return -EINVAL; /* * An instance must always have it set. * by default, that's the global_trace instane. */ if (printk_trace == tr) update_printk_trace(&global_trace); } } if (mask == TRACE_ITER_COPY_MARKER) update_marker_trace(tr, enabled); if (enabled) tr->trace_flags |= mask; else tr->trace_flags &= ~mask; if (mask == TRACE_ITER_RECORD_CMD) trace_event_enable_cmd_record(enabled); if (mask == TRACE_ITER_RECORD_TGID) { if (trace_alloc_tgid_map() < 0) { tr->trace_flags &= ~TRACE_ITER_RECORD_TGID; return -ENOMEM; } trace_event_enable_tgid_record(enabled); } if (mask == TRACE_ITER_EVENT_FORK) trace_event_follow_fork(tr, enabled); if (mask == TRACE_ITER_FUNC_FORK) ftrace_pid_follow_fork(tr, enabled); if (mask == TRACE_ITER_OVERWRITE) { ring_buffer_change_overwrite(tr->array_buffer.buffer, enabled); #ifdef CONFIG_TRACER_MAX_TRACE ring_buffer_change_overwrite(tr->max_buffer.buffer, enabled); #endif } if (mask == TRACE_ITER_PRINTK) { trace_printk_start_stop_comm(enabled); trace_printk_control(enabled); } return 0; } int trace_set_options(struct trace_array *tr, char *option) { char *cmp; int neg = 0; int ret; size_t orig_len = strlen(option); int len; cmp = strstrip(option); len = str_has_prefix(cmp, "no"); if (len) neg = 1; cmp += len; mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = match_string(trace_options, -1, cmp); /* If no option could be set, test the specific tracer options */ if (ret < 0) ret = set_tracer_option(tr, cmp, neg); else ret = set_tracer_flag(tr, 1 << ret, !neg); mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); /* * If the first trailing whitespace is replaced with '\0' by strstrip, * turn it back into a space. */ if (orig_len > strlen(option)) option[strlen(option)] = ' '; return ret; } static void __init apply_trace_boot_options(void) { char *buf = trace_boot_options_buf; char *option; while (true) { option = strsep(&buf, ","); if (!option) break; if (*option) trace_set_options(&global_trace, option); /* Put back the comma to allow this to be called again */ if (buf) *(buf - 1) = ','; } } static ssize_t tracing_trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct seq_file *m = filp->private_data; struct trace_array *tr = m->private; char buf[64]; int ret; if (cnt >= sizeof(buf)) return -EINVAL; if (copy_from_user(buf, ubuf, cnt)) return -EFAULT; buf[cnt] = 0; ret = trace_set_options(tr, buf); if (ret < 0) return ret; *ppos += cnt; return cnt; } static int tracing_trace_options_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = single_open(file, tracing_trace_options_show, inode->i_private); if (ret < 0) trace_array_put(tr); return ret; } static const struct file_operations tracing_iter_fops = { .open = tracing_trace_options_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_single_release_tr, .write = tracing_trace_options_write, }; static const char readme_msg[] = "tracing mini-HOWTO:\n\n" "By default tracefs removes all OTH file permission bits.\n" "When mounting tracefs an optional group id can be specified\n" "which adds the group to every directory and file in tracefs:\n\n" "\t e.g. mount -t tracefs [-o [gid=<gid>]] nodev /sys/kernel/tracing\n\n" "# echo 0 > tracing_on : quick way to disable tracing\n" "# echo 1 > tracing_on : quick way to re-enable tracing\n\n" " Important files:\n" " trace\t\t\t- The static contents of the buffer\n" "\t\t\t To clear the buffer write into this file: echo > trace\n" " trace_pipe\t\t- A consuming read to see the contents of the buffer\n" " current_tracer\t- function and latency tracers\n" " available_tracers\t- list of configured tracers for current_tracer\n" " error_log\t- error log for failed commands (that support it)\n" " buffer_size_kb\t- view and modify size of per cpu buffer\n" " buffer_total_size_kb - view total size of all cpu buffers\n\n" " trace_clock\t\t- change the clock used to order events\n" " local: Per cpu clock but may not be synced across CPUs\n" " global: Synced across CPUs but slows tracing down.\n" " counter: Not a clock, but just an increment\n" " uptime: Jiffy counter from time of boot\n" " perf: Same clock that perf events use\n" #ifdef CONFIG_X86_64 " x86-tsc: TSC cycle counter\n" #endif "\n timestamp_mode\t- view the mode used to timestamp events\n" " delta: Delta difference against a buffer-wide timestamp\n" " absolute: Absolute (standalone) timestamp\n" "\n trace_marker\t\t- Writes into this file writes into the kernel buffer\n" "\n trace_marker_raw\t\t- Writes into this file writes binary data into the kernel buffer\n" " tracing_cpumask\t- Limit which CPUs to trace\n" " instances\t\t- Make sub-buffers with: mkdir instances/foo\n" "\t\t\t Remove sub-buffer with rmdir\n" " trace_options\t\t- Set format or modify how tracing happens\n" "\t\t\t Disable an option by prefixing 'no' to the\n" "\t\t\t option name\n" " saved_cmdlines_size\t- echo command number in here to store comm-pid list\n" #ifdef CONFIG_DYNAMIC_FTRACE "\n available_filter_functions - list of functions that can be filtered on\n" " set_ftrace_filter\t- echo function name in here to only trace these\n" "\t\t\t functions\n" "\t accepts: func_full_name or glob-matching-pattern\n" "\t modules: Can select a group via module\n" "\t Format: :mod:<module-name>\n" "\t example: echo :mod:ext3 > set_ftrace_filter\n" "\t triggers: a command to perform when function is hit\n" "\t Format: <function>:<trigger>[:count]\n" "\t trigger: traceon, traceoff\n" "\t\t enable_event:<system>:<event>\n" "\t\t disable_event:<system>:<event>\n" #ifdef CONFIG_STACKTRACE "\t\t stacktrace\n" #endif #ifdef CONFIG_TRACER_SNAPSHOT "\t\t snapshot\n" #endif "\t\t dump\n" "\t\t cpudump\n" "\t example: echo do_fault:traceoff > set_ftrace_filter\n" "\t echo do_trap:traceoff:3 > set_ftrace_filter\n" "\t The first one will disable tracing every time do_fault is hit\n" "\t The second will disable tracing at most 3 times when do_trap is hit\n" "\t The first time do trap is hit and it disables tracing, the\n" "\t counter will decrement to 2. If tracing is already disabled,\n" "\t the counter will not decrement. It only decrements when the\n" "\t trigger did work\n" "\t To remove trigger without count:\n" "\t echo '!<function>:<trigger> > set_ftrace_filter\n" "\t To remove trigger with a count:\n" "\t echo '!<function>:<trigger>:0 > set_ftrace_filter\n" " set_ftrace_notrace\t- echo function name in here to never trace.\n" "\t accepts: func_full_name, *func_end, func_begin*, *func_middle*\n" "\t modules: Can select a group via module command :mod:\n" "\t Does not accept triggers\n" #endif /* CONFIG_DYNAMIC_FTRACE */ #ifdef CONFIG_FUNCTION_TRACER " set_ftrace_pid\t- Write pid(s) to only function trace those pids\n" "\t\t (function)\n" " set_ftrace_notrace_pid\t- Write pid(s) to not function trace those pids\n" "\t\t (function)\n" #endif #ifdef CONFIG_FUNCTION_GRAPH_TRACER " set_graph_function\t- Trace the nested calls of a function (function_graph)\n" " set_graph_notrace\t- Do not trace the nested calls of a function (function_graph)\n" " max_graph_depth\t- Trace a limited depth of nested calls (0 is unlimited)\n" #endif #ifdef CONFIG_TRACER_SNAPSHOT "\n snapshot\t\t- Like 'trace' but shows the content of the static\n" "\t\t\t snapshot buffer. Read the contents for more\n" "\t\t\t information\n" #endif #ifdef CONFIG_STACK_TRACER " stack_trace\t\t- Shows the max stack trace when active\n" " stack_max_size\t- Shows current max stack size that was traced\n" "\t\t\t Write into this file to reset the max size (trigger a\n" "\t\t\t new trace)\n" #ifdef CONFIG_DYNAMIC_FTRACE " stack_trace_filter\t- Like set_ftrace_filter but limits what stack_trace\n" "\t\t\t traces\n" #endif #endif /* CONFIG_STACK_TRACER */ #ifdef CONFIG_DYNAMIC_EVENTS " dynamic_events\t\t- Create/append/remove/show the generic dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #ifdef CONFIG_KPROBE_EVENTS " kprobe_events\t\t- Create/append/remove/show the kernel dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #ifdef CONFIG_UPROBE_EVENTS " uprobe_events\t\t- Create/append/remove/show the userspace dynamic events\n" "\t\t\t Write into this file to define/undefine new trace events.\n" #endif #if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) || \ defined(CONFIG_FPROBE_EVENTS) "\t accepts: event-definitions (one definition per line)\n" #if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) "\t Format: p[:[<group>/][<event>]] <place> [<args>]\n" "\t r[maxactive][:[<group>/][<event>]] <place> [<args>]\n" #endif #ifdef CONFIG_FPROBE_EVENTS "\t f[:[<group>/][<event>]] <func-name>[%return] [<args>]\n" "\t t[:[<group>/][<event>]] <tracepoint> [<args>]\n" #endif #ifdef CONFIG_HIST_TRIGGERS "\t s:[synthetic/]<event> <field> [<field>]\n" #endif "\t e[:[<group>/][<event>]] <attached-group>.<attached-event> [<args>] [if <filter>]\n" "\t -:[<group>/][<event>]\n" #ifdef CONFIG_KPROBE_EVENTS "\t place: [<module>:]<symbol>[+<offset>]|<memaddr>\n" "place (kretprobe): [<module>:]<symbol>[+<offset>]%return|<memaddr>\n" #endif #ifdef CONFIG_UPROBE_EVENTS " place (uprobe): <path>:<offset>[%return][(ref_ctr_offset)]\n" #endif "\t args: <name>=fetcharg[:type]\n" "\t fetcharg: (%<register>|$<efield>), @<address>, @<symbol>[+|-<offset>],\n" #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n" #ifdef CONFIG_PROBE_EVENTS_BTF_ARGS "\t <argname>[->field[->field|.field...]],\n" #endif #else "\t $stack<index>, $stack, $retval, $comm,\n" #endif "\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n" "\t kernel return probes support: $retval, $arg<N>, $comm\n" "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n" "\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n" "\t symstr, %pd/%pD, <type>\\[<array-size>\\]\n" #ifdef CONFIG_HIST_TRIGGERS "\t field: <stype> <name>;\n" "\t stype: u8/u16/u32/u64, s8/s16/s32/s64, pid_t,\n" "\t [unsigned] char/int/long\n" #endif "\t efield: For event probes ('e' types), the field is on of the fields\n" "\t of the <attached-group>/<attached-event>.\n" #endif " set_event\t\t- Enables events by name written into it\n" "\t\t\t Can enable module events via: :mod:<module>\n" " events/\t\t- Directory containing all trace event subsystems:\n" " enable\t\t- Write 0/1 to enable/disable tracing of all events\n" " events/<system>/\t- Directory containing all trace events for <system>:\n" " enable\t\t- Write 0/1 to enable/disable tracing of all <system>\n" "\t\t\t events\n" " filter\t\t- If set, only events passing filter are traced\n" " events/<system>/<event>/\t- Directory containing control files for\n" "\t\t\t <event>:\n" " enable\t\t- Write 0/1 to enable/disable tracing of <event>\n" " filter\t\t- If set, only events passing filter are traced\n" " trigger\t\t- If set, a command to perform when event is hit\n" "\t Format: <trigger>[:count][if <filter>]\n" "\t trigger: traceon, traceoff\n" "\t enable_event:<system>:<event>\n" "\t disable_event:<system>:<event>\n" #ifdef CONFIG_HIST_TRIGGERS "\t enable_hist:<system>:<event>\n" "\t disable_hist:<system>:<event>\n" #endif #ifdef CONFIG_STACKTRACE "\t\t stacktrace\n" #endif #ifdef CONFIG_TRACER_SNAPSHOT "\t\t snapshot\n" #endif #ifdef CONFIG_HIST_TRIGGERS "\t\t hist (see below)\n" #endif "\t example: echo traceoff > events/block/block_unplug/trigger\n" "\t echo traceoff:3 > events/block/block_unplug/trigger\n" "\t echo 'enable_event:kmem:kmalloc:3 if nr_rq > 1' > \\\n" "\t events/block/block_unplug/trigger\n" "\t The first disables tracing every time block_unplug is hit.\n" "\t The second disables tracing the first 3 times block_unplug is hit.\n" "\t The third enables the kmalloc event the first 3 times block_unplug\n" "\t is hit and has value of greater than 1 for the 'nr_rq' event field.\n" "\t Like function triggers, the counter is only decremented if it\n" "\t enabled or disabled tracing.\n" "\t To remove a trigger without a count:\n" "\t echo '!<trigger> > <system>/<event>/trigger\n" "\t To remove a trigger with a count:\n" "\t echo '!<trigger>:0 > <system>/<event>/trigger\n" "\t Filters can be ignored when removing a trigger.\n" #ifdef CONFIG_HIST_TRIGGERS " hist trigger\t- If set, event hits are aggregated into a hash table\n" "\t Format: hist:keys=<field1[,field2,...]>\n" "\t [:<var1>=<field|var_ref|numeric_literal>[,<var2>=...]]\n" "\t [:values=<field1[,field2,...]>]\n" "\t [:sort=<field1[,field2,...]>]\n" "\t [:size=#entries]\n" "\t [:pause][:continue][:clear]\n" "\t [:name=histname1]\n" "\t [:nohitcount]\n" "\t [:<handler>.<action>]\n" "\t [if <filter>]\n\n" "\t Note, special fields can be used as well:\n" "\t common_timestamp - to record current timestamp\n" "\t common_cpu - to record the CPU the event happened on\n" "\n" "\t A hist trigger variable can be:\n" "\t - a reference to a field e.g. x=current_timestamp,\n" "\t - a reference to another variable e.g. y=$x,\n" "\t - a numeric literal: e.g. ms_per_sec=1000,\n" "\t - an arithmetic expression: e.g. time_secs=current_timestamp/1000\n" "\n" "\t hist trigger arithmetic expressions support addition(+), subtraction(-),\n" "\t multiplication(*) and division(/) operators. An operand can be either a\n" "\t variable reference, field or numeric literal.\n" "\n" "\t When a matching event is hit, an entry is added to a hash\n" "\t table using the key(s) and value(s) named, and the value of a\n" "\t sum called 'hitcount' is incremented. Keys and values\n" "\t correspond to fields in the event's format description. Keys\n" "\t can be any field, or the special string 'common_stacktrace'.\n" "\t Compound keys consisting of up to two fields can be specified\n" "\t by the 'keys' keyword. Values must correspond to numeric\n" "\t fields. Sort keys consisting of up to two fields can be\n" "\t specified using the 'sort' keyword. The sort direction can\n" "\t be modified by appending '.descending' or '.ascending' to a\n" "\t sort field. The 'size' parameter can be used to specify more\n" "\t or fewer than the default 2048 entries for the hashtable size.\n" "\t If a hist trigger is given a name using the 'name' parameter,\n" "\t its histogram data will be shared with other triggers of the\n" "\t same name, and trigger hits will update this common data.\n\n" "\t Reading the 'hist' file for the event will dump the hash\n" "\t table in its entirety to stdout. If there are multiple hist\n" "\t triggers attached to an event, there will be a table for each\n" "\t trigger in the output. The table displayed for a named\n" "\t trigger will be the same as any other instance having the\n" "\t same name. The default format used to display a given field\n" "\t can be modified by appending any of the following modifiers\n" "\t to the field name, as applicable:\n\n" "\t .hex display a number as a hex value\n" "\t .sym display an address as a symbol\n" "\t .sym-offset display an address as a symbol and offset\n" "\t .execname display a common_pid as a program name\n" "\t .syscall display a syscall id as a syscall name\n" "\t .log2 display log2 value rather than raw number\n" "\t .buckets=size display values in groups of size rather than raw number\n" "\t .usecs display a common_timestamp in microseconds\n" "\t .percent display a number of percentage value\n" "\t .graph display a bar-graph of a value\n\n" "\t The 'pause' parameter can be used to pause an existing hist\n" "\t trigger or to start a hist trigger but not log any events\n" "\t until told to do so. 'continue' can be used to start or\n" "\t restart a paused hist trigger.\n\n" "\t The 'clear' parameter will clear the contents of a running\n" "\t hist trigger and leave its current paused/active state\n" "\t unchanged.\n\n" "\t The 'nohitcount' (or NOHC) parameter will suppress display of\n" "\t raw hitcount in the histogram.\n\n" "\t The enable_hist and disable_hist triggers can be used to\n" "\t have one event conditionally start and stop another event's\n" "\t already-attached hist trigger. The syntax is analogous to\n" "\t the enable_event and disable_event triggers.\n\n" "\t Hist trigger handlers and actions are executed whenever a\n" "\t a histogram entry is added or updated. They take the form:\n\n" "\t <handler>.<action>\n\n" "\t The available handlers are:\n\n" "\t onmatch(matching.event) - invoke on addition or update\n" "\t onmax(var) - invoke if var exceeds current max\n" "\t onchange(var) - invoke action if var changes\n\n" "\t The available actions are:\n\n" "\t trace(<synthetic_event>,param list) - generate synthetic event\n" "\t save(field,...) - save current event fields\n" #ifdef CONFIG_TRACER_SNAPSHOT "\t snapshot() - snapshot the trace buffer\n\n" #endif #ifdef CONFIG_SYNTH_EVENTS " events/synthetic_events\t- Create/append/remove/show synthetic events\n" "\t Write into this file to define/undefine new synthetic events.\n" "\t example: echo 'myevent u64 lat; char name[]; long[] stack' >> synthetic_events\n" #endif #endif ; static ssize_t tracing_readme_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { return simple_read_from_buffer(ubuf, cnt, ppos, readme_msg, strlen(readme_msg)); } static const struct file_operations tracing_readme_fops = { .open = tracing_open_generic, .read = tracing_readme_read, .llseek = generic_file_llseek, }; #ifdef CONFIG_TRACE_EVAL_MAP_FILE static union trace_eval_map_item * update_eval_map(union trace_eval_map_item *ptr) { if (!ptr->map.eval_string) { if (ptr->tail.next) { ptr = ptr->tail.next; /* Set ptr to the next real item (skip head) */ ptr++; } else return NULL; } return ptr; } static void *eval_map_next(struct seq_file *m, void *v, loff_t *pos) { union trace_eval_map_item *ptr = v; /* * Paranoid! If ptr points to end, we don't want to increment past it. * This really should never happen. */ (*pos)++; ptr = update_eval_map(ptr); if (WARN_ON_ONCE(!ptr)) return NULL; ptr++; ptr = update_eval_map(ptr); return ptr; } static void *eval_map_start(struct seq_file *m, loff_t *pos) { union trace_eval_map_item *v; loff_t l = 0; mutex_lock(&trace_eval_mutex); v = trace_eval_maps; if (v) v++; while (v && l < *pos) { v = eval_map_next(m, v, &l); } return v; } static void eval_map_stop(struct seq_file *m, void *v) { mutex_unlock(&trace_eval_mutex); } static int eval_map_show(struct seq_file *m, void *v) { union trace_eval_map_item *ptr = v; seq_printf(m, "%s %ld (%s)\n", ptr->map.eval_string, ptr->map.eval_value, ptr->map.system); return 0; } static const struct seq_operations tracing_eval_map_seq_ops = { .start = eval_map_start, .next = eval_map_next, .stop = eval_map_stop, .show = eval_map_show, }; static int tracing_eval_map_open(struct inode *inode, struct file *filp) { int ret; ret = tracing_check_open_get_tr(NULL); if (ret) return ret; return seq_open(filp, &tracing_eval_map_seq_ops); } static const struct file_operations tracing_eval_map_fops = { .open = tracing_eval_map_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; static inline union trace_eval_map_item * trace_eval_jmp_to_tail(union trace_eval_map_item *ptr) { /* Return tail of array given the head */ return ptr + ptr->head.length + 1; } static void trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, int len) { struct trace_eval_map **stop; struct trace_eval_map **map; union trace_eval_map_item *map_array; union trace_eval_map_item *ptr; stop = start + len; /* * The trace_eval_maps contains the map plus a head and tail item, * where the head holds the module and length of array, and the * tail holds a pointer to the next list. */ map_array = kmalloc_array(len + 2, sizeof(*map_array), GFP_KERNEL); if (!map_array) { pr_warn("Unable to allocate trace eval mapping\n"); return; } guard(mutex)(&trace_eval_mutex); if (!trace_eval_maps) trace_eval_maps = map_array; else { ptr = trace_eval_maps; for (;;) { ptr = trace_eval_jmp_to_tail(ptr); if (!ptr->tail.next) break; ptr = ptr->tail.next; } ptr->tail.next = map_array; } map_array->head.mod = mod; map_array->head.length = len; map_array++; for (map = start; (unsigned long)map < (unsigned long)stop; map++) { map_array->map = **map; map_array++; } memset(map_array, 0, sizeof(*map_array)); } static void trace_create_eval_file(struct dentry *d_tracer) { trace_create_file("eval_map", TRACE_MODE_READ, d_tracer, NULL, &tracing_eval_map_fops); } #else /* CONFIG_TRACE_EVAL_MAP_FILE */ static inline void trace_create_eval_file(struct dentry *d_tracer) { } static inline void trace_insert_eval_map_file(struct module *mod, struct trace_eval_map **start, int len) { } #endif /* !CONFIG_TRACE_EVAL_MAP_FILE */ static void trace_event_update_with_eval_map(struct module *mod, struct trace_eval_map **start, int len) { struct trace_eval_map **map; /* Always run sanitizer only if btf_type_tag attr exists. */ if (len <= 0) { if (!(IS_ENABLED(CONFIG_DEBUG_INFO_BTF) && IS_ENABLED(CONFIG_PAHOLE_HAS_BTF_TAG) && __has_attribute(btf_type_tag))) return; } map = start; trace_event_update_all(map, len); if (len <= 0) return; trace_insert_eval_map_file(mod, start, len); } static ssize_t tracing_set_trace_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; char buf[MAX_TRACER_SIZE+2]; int r; scoped_guard(mutex, &trace_types_lock) { r = sprintf(buf, "%s\n", tr->current_trace->name); } return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } int tracer_init(struct tracer *t, struct trace_array *tr) { tracing_reset_online_cpus(&tr->array_buffer); return t->init(tr); } static void set_buffer_entries(struct array_buffer *buf, unsigned long val) { int cpu; for_each_tracing_cpu(cpu) per_cpu_ptr(buf->data, cpu)->entries = val; } static void update_buffer_entries(struct array_buffer *buf, int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { set_buffer_entries(buf, ring_buffer_size(buf->buffer, 0)); } else { per_cpu_ptr(buf->data, cpu)->entries = ring_buffer_size(buf->buffer, cpu); } } #ifdef CONFIG_TRACER_MAX_TRACE /* resize @tr's buffer to the size of @size_tr's entries */ static int resize_buffer_duplicate_size(struct array_buffer *trace_buf, struct array_buffer *size_buf, int cpu_id) { int cpu, ret = 0; if (cpu_id == RING_BUFFER_ALL_CPUS) { for_each_tracing_cpu(cpu) { ret = ring_buffer_resize(trace_buf->buffer, per_cpu_ptr(size_buf->data, cpu)->entries, cpu); if (ret < 0) break; per_cpu_ptr(trace_buf->data, cpu)->entries = per_cpu_ptr(size_buf->data, cpu)->entries; } } else { ret = ring_buffer_resize(trace_buf->buffer, per_cpu_ptr(size_buf->data, cpu_id)->entries, cpu_id); if (ret == 0) per_cpu_ptr(trace_buf->data, cpu_id)->entries = per_cpu_ptr(size_buf->data, cpu_id)->entries; } return ret; } #endif /* CONFIG_TRACER_MAX_TRACE */ static int __tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu) { int ret; /* * If kernel or user changes the size of the ring buffer * we use the size that was given, and we can forget about * expanding it later. */ trace_set_ring_buffer_expanded(tr); /* May be called before buffers are initialized */ if (!tr->array_buffer.buffer) return 0; /* Do not allow tracing while resizing ring buffer */ tracing_stop_tr(tr); ret = ring_buffer_resize(tr->array_buffer.buffer, size, cpu); if (ret < 0) goto out_start; #ifdef CONFIG_TRACER_MAX_TRACE if (!tr->allocated_snapshot) goto out; ret = ring_buffer_resize(tr->max_buffer.buffer, size, cpu); if (ret < 0) { int r = resize_buffer_duplicate_size(&tr->array_buffer, &tr->array_buffer, cpu); if (r < 0) { /* * AARGH! We are left with different * size max buffer!!!! * The max buffer is our "snapshot" buffer. * When a tracer needs a snapshot (one of the * latency tracers), it swaps the max buffer * with the saved snap shot. We succeeded to * update the size of the main buffer, but failed to * update the size of the max buffer. But when we tried * to reset the main buffer to the original size, we * failed there too. This is very unlikely to * happen, but if it does, warn and kill all * tracing. */ WARN_ON(1); tracing_disabled = 1; } goto out_start; } update_buffer_entries(&tr->max_buffer, cpu); out: #endif /* CONFIG_TRACER_MAX_TRACE */ update_buffer_entries(&tr->array_buffer, cpu); out_start: tracing_start_tr(tr); return ret; } ssize_t tracing_resize_ring_buffer(struct trace_array *tr, unsigned long size, int cpu_id) { guard(mutex)(&trace_types_lock); if (cpu_id != RING_BUFFER_ALL_CPUS) { /* make sure, this cpu is enabled in the mask */ if (!cpumask_test_cpu(cpu_id, tracing_buffer_mask)) return -EINVAL; } return __tracing_resize_ring_buffer(tr, size, cpu_id); } struct trace_mod_entry { unsigned long mod_addr; char mod_name[MODULE_NAME_LEN]; }; struct trace_scratch { unsigned int clock_id; unsigned long text_addr; unsigned long nr_entries; struct trace_mod_entry entries[]; }; static DEFINE_MUTEX(scratch_mutex); static int cmp_mod_entry(const void *key, const void *pivot) { unsigned long addr = (unsigned long)key; const struct trace_mod_entry *ent = pivot; if (addr >= ent[0].mod_addr && addr < ent[1].mod_addr) return 0; else return addr - ent->mod_addr; } /** * trace_adjust_address() - Adjust prev boot address to current address. * @tr: Persistent ring buffer's trace_array. * @addr: Address in @tr which is adjusted. */ unsigned long trace_adjust_address(struct trace_array *tr, unsigned long addr) { struct trace_module_delta *module_delta; struct trace_scratch *tscratch; struct trace_mod_entry *entry; unsigned long raddr; int idx = 0, nr_entries; /* If we don't have last boot delta, return the address */ if (!(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) return addr; /* tr->module_delta must be protected by rcu. */ guard(rcu)(); tscratch = tr->scratch; /* if there is no tscrach, module_delta must be NULL. */ module_delta = READ_ONCE(tr->module_delta); if (!module_delta || !tscratch->nr_entries || tscratch->entries[0].mod_addr > addr) { raddr = addr + tr->text_delta; return __is_kernel(raddr) || is_kernel_core_data(raddr) || is_kernel_rodata(raddr) ? raddr : addr; } /* Note that entries must be sorted. */ nr_entries = tscratch->nr_entries; if (nr_entries == 1 || tscratch->entries[nr_entries - 1].mod_addr < addr) idx = nr_entries - 1; else { entry = __inline_bsearch((void *)addr, tscratch->entries, nr_entries - 1, sizeof(tscratch->entries[0]), cmp_mod_entry); if (entry) idx = entry - tscratch->entries; } return addr + module_delta->delta[idx]; } #ifdef CONFIG_MODULES static int save_mod(struct module *mod, void *data) { struct trace_array *tr = data; struct trace_scratch *tscratch; struct trace_mod_entry *entry; unsigned int size; tscratch = tr->scratch; if (!tscratch) return -1; size = tr->scratch_size; if (struct_size(tscratch, entries, tscratch->nr_entries + 1) > size) return -1; entry = &tscratch->entries[tscratch->nr_entries]; tscratch->nr_entries++; entry->mod_addr = (unsigned long)mod->mem[MOD_TEXT].base; strscpy(entry->mod_name, mod->name); return 0; } #else static int save_mod(struct module *mod, void *data) { return 0; } #endif static void update_last_data(struct trace_array *tr) { struct trace_module_delta *module_delta; struct trace_scratch *tscratch; if (!(tr->flags & TRACE_ARRAY_FL_BOOT)) return; if (!(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) return; /* Only if the buffer has previous boot data clear and update it. */ tr->flags &= ~TRACE_ARRAY_FL_LAST_BOOT; /* Reset the module list and reload them */ if (tr->scratch) { struct trace_scratch *tscratch = tr->scratch; tscratch->clock_id = tr->clock_id; memset(tscratch->entries, 0, flex_array_size(tscratch, entries, tscratch->nr_entries)); tscratch->nr_entries = 0; guard(mutex)(&scratch_mutex); module_for_each_mod(save_mod, tr); } /* * Need to clear all CPU buffers as there cannot be events * from the previous boot mixed with events with this boot * as that will cause a confusing trace. Need to clear all * CPU buffers, even for those that may currently be offline. */ tracing_reset_all_cpus(&tr->array_buffer); /* Using current data now */ tr->text_delta = 0; if (!tr->scratch) return; tscratch = tr->scratch; module_delta = READ_ONCE(tr->module_delta); WRITE_ONCE(tr->module_delta, NULL); kfree_rcu(module_delta, rcu); /* Set the persistent ring buffer meta data to this address */ tscratch->text_addr = (unsigned long)_text; } /** * tracing_update_buffers - used by tracing facility to expand ring buffers * @tr: The tracing instance * * To save on memory when the tracing is never used on a system with it * configured in. The ring buffers are set to a minimum size. But once * a user starts to use the tracing facility, then they need to grow * to their default size. * * This function is to be called when a tracer is about to be used. */ int tracing_update_buffers(struct trace_array *tr) { int ret = 0; guard(mutex)(&trace_types_lock); update_last_data(tr); if (!tr->ring_buffer_expanded) ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); return ret; } struct trace_option_dentry; static void create_trace_option_files(struct trace_array *tr, struct tracer *tracer); /* * Used to clear out the tracer before deletion of an instance. * Must have trace_types_lock held. */ static void tracing_set_nop(struct trace_array *tr) { if (tr->current_trace == &nop_trace) return; tr->current_trace->enabled--; if (tr->current_trace->reset) tr->current_trace->reset(tr); tr->current_trace = &nop_trace; } static bool tracer_options_updated; static void add_tracer_options(struct trace_array *tr, struct tracer *t) { /* Only enable if the directory has been created already. */ if (!tr->dir && !(tr->flags & TRACE_ARRAY_FL_GLOBAL)) return; /* Only create trace option files after update_tracer_options finish */ if (!tracer_options_updated) return; create_trace_option_files(tr, t); } int tracing_set_tracer(struct trace_array *tr, const char *buf) { struct tracer *t; #ifdef CONFIG_TRACER_MAX_TRACE bool had_max_tr; #endif int ret; guard(mutex)(&trace_types_lock); update_last_data(tr); if (!tr->ring_buffer_expanded) { ret = __tracing_resize_ring_buffer(tr, trace_buf_size, RING_BUFFER_ALL_CPUS); if (ret < 0) return ret; ret = 0; } for (t = trace_types; t; t = t->next) { if (strcmp(t->name, buf) == 0) break; } if (!t) return -EINVAL; if (t == tr->current_trace) return 0; #ifdef CONFIG_TRACER_SNAPSHOT if (t->use_max_tr) { local_irq_disable(); arch_spin_lock(&tr->max_lock); ret = tr->cond_snapshot ? -EBUSY : 0; arch_spin_unlock(&tr->max_lock); local_irq_enable(); if (ret) return ret; } #endif /* Some tracers won't work on kernel command line */ if (system_state < SYSTEM_RUNNING && t->noboot) { pr_warn("Tracer '%s' is not allowed on command line, ignored\n", t->name); return -EINVAL; } /* Some tracers are only allowed for the top level buffer */ if (!trace_ok_for_array(t, tr)) return -EINVAL; /* If trace pipe files are being read, we can't change the tracer */ if (tr->trace_ref) return -EBUSY; trace_branch_disable(); tr->current_trace->enabled--; if (tr->current_trace->reset) tr->current_trace->reset(tr); #ifdef CONFIG_TRACER_MAX_TRACE had_max_tr = tr->current_trace->use_max_tr; /* Current trace needs to be nop_trace before synchronize_rcu */ tr->current_trace = &nop_trace; if (had_max_tr && !t->use_max_tr) { /* * We need to make sure that the update_max_tr sees that * current_trace changed to nop_trace to keep it from * swapping the buffers after we resize it. * The update_max_tr is called from interrupts disabled * so a synchronized_sched() is sufficient. */ synchronize_rcu(); free_snapshot(tr); tracing_disarm_snapshot(tr); } if (!had_max_tr && t->use_max_tr) { ret = tracing_arm_snapshot_locked(tr); if (ret) return ret; } #else tr->current_trace = &nop_trace; #endif if (t->init) { ret = tracer_init(t, tr); if (ret) { #ifdef CONFIG_TRACER_MAX_TRACE if (t->use_max_tr) tracing_disarm_snapshot(tr); #endif return ret; } } tr->current_trace = t; tr->current_trace->enabled++; trace_branch_enable(tr); return 0; } static ssize_t tracing_set_trace_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; char buf[MAX_TRACER_SIZE+1]; char *name; size_t ret; int err; ret = cnt; if (cnt > MAX_TRACER_SIZE) cnt = MAX_TRACER_SIZE; if (copy_from_user(buf, ubuf, cnt)) return -EFAULT; buf[cnt] = 0; name = strim(buf); err = tracing_set_tracer(tr, name); if (err) return err; *ppos += ret; return ret; } static ssize_t tracing_nsecs_read(unsigned long *ptr, char __user *ubuf, size_t cnt, loff_t *ppos) { char buf[64]; int r; r = snprintf(buf, sizeof(buf), "%ld\n", *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr)); if (r > sizeof(buf)) r = sizeof(buf); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static ssize_t tracing_nsecs_write(unsigned long *ptr, const char __user *ubuf, size_t cnt, loff_t *ppos) { unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; *ptr = val * 1000; return cnt; } static ssize_t tracing_thresh_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { return tracing_nsecs_read(&tracing_thresh, ubuf, cnt, ppos); } static ssize_t tracing_thresh_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; int ret; guard(mutex)(&trace_types_lock); ret = tracing_nsecs_write(&tracing_thresh, ubuf, cnt, ppos); if (ret < 0) return ret; if (tr->current_trace->update_thresh) { ret = tr->current_trace->update_thresh(tr); if (ret < 0) return ret; } return cnt; } #ifdef CONFIG_TRACER_MAX_TRACE static ssize_t tracing_max_lat_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; return tracing_nsecs_read(&tr->max_latency, ubuf, cnt, ppos); } static ssize_t tracing_max_lat_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; return tracing_nsecs_write(&tr->max_latency, ubuf, cnt, ppos); } #endif static int open_pipe_on_cpu(struct trace_array *tr, int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { if (cpumask_empty(tr->pipe_cpumask)) { cpumask_setall(tr->pipe_cpumask); return 0; } } else if (!cpumask_test_cpu(cpu, tr->pipe_cpumask)) { cpumask_set_cpu(cpu, tr->pipe_cpumask); return 0; } return -EBUSY; } static void close_pipe_on_cpu(struct trace_array *tr, int cpu) { if (cpu == RING_BUFFER_ALL_CPUS) { WARN_ON(!cpumask_full(tr->pipe_cpumask)); cpumask_clear(tr->pipe_cpumask); } else { WARN_ON(!cpumask_test_cpu(cpu, tr->pipe_cpumask)); cpumask_clear_cpu(cpu, tr->pipe_cpumask); } } static int tracing_open_pipe(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; int cpu; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; guard(mutex)(&trace_types_lock); cpu = tracing_get_cpu(inode); ret = open_pipe_on_cpu(tr, cpu); if (ret) goto fail_pipe_on_cpu; /* create a buffer to store the information to pass to userspace */ iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { ret = -ENOMEM; goto fail_alloc_iter; } trace_seq_init(&iter->seq); iter->trace = tr->current_trace; if (!alloc_cpumask_var(&iter->started, GFP_KERNEL)) { ret = -ENOMEM; goto fail; } /* trace pipe does not show start of buffer */ cpumask_setall(iter->started); if (tr->trace_flags & TRACE_ITER_LATENCY_FMT) iter->iter_flags |= TRACE_FILE_LAT_FMT; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ if (trace_clocks[tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; iter->tr = tr; iter->array_buffer = &tr->array_buffer; iter->cpu_file = cpu; mutex_init(&iter->mutex); filp->private_data = iter; if (iter->trace->pipe_open) iter->trace->pipe_open(iter); nonseekable_open(inode, filp); tr->trace_ref++; return ret; fail: kfree(iter); fail_alloc_iter: close_pipe_on_cpu(tr, cpu); fail_pipe_on_cpu: __trace_array_put(tr); return ret; } static int tracing_release_pipe(struct inode *inode, struct file *file) { struct trace_iterator *iter = file->private_data; struct trace_array *tr = inode->i_private; scoped_guard(mutex, &trace_types_lock) { tr->trace_ref--; if (iter->trace->pipe_close) iter->trace->pipe_close(iter); close_pipe_on_cpu(tr, iter->cpu_file); } free_trace_iter_content(iter); kfree(iter); trace_array_put(tr); return 0; } static __poll_t trace_poll(struct trace_iterator *iter, struct file *filp, poll_table *poll_table) { struct trace_array *tr = iter->tr; /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return EPOLLIN | EPOLLRDNORM; if (tr->trace_flags & TRACE_ITER_BLOCK) /* * Always select as readable when in blocking mode */ return EPOLLIN | EPOLLRDNORM; else return ring_buffer_poll_wait(iter->array_buffer->buffer, iter->cpu_file, filp, poll_table, iter->tr->buffer_percent); } static __poll_t tracing_poll_pipe(struct file *filp, poll_table *poll_table) { struct trace_iterator *iter = filp->private_data; return trace_poll(iter, filp, poll_table); } /* Must be called with iter->mutex held. */ static int tracing_wait_pipe(struct file *filp) { struct trace_iterator *iter = filp->private_data; int ret; while (trace_empty(iter)) { if ((filp->f_flags & O_NONBLOCK)) { return -EAGAIN; } /* * We block until we read something and tracing is disabled. * We still block if tracing is disabled, but we have never * read anything. This allows a user to cat this file, and * then enable tracing. But after we have read something, * we give an EOF when tracing is again disabled. * * iter->pos will be 0 if we haven't read anything. */ if (!tracer_tracing_is_on(iter->tr) && iter->pos) break; mutex_unlock(&iter->mutex); ret = wait_on_pipe(iter, 0); mutex_lock(&iter->mutex); if (ret) return ret; } return 1; } static bool update_last_data_if_empty(struct trace_array *tr) { if (!(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) return false; if (!ring_buffer_empty(tr->array_buffer.buffer)) return false; /* * If the buffer contains the last boot data and all per-cpu * buffers are empty, reset it from the kernel side. */ update_last_data(tr); return true; } /* * Consumer reader. */ static ssize_t tracing_read_pipe(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_iterator *iter = filp->private_data; ssize_t sret; /* * Avoid more than one consumer on a single file descriptor * This is just a matter of traces coherency, the ring buffer itself * is protected. */ guard(mutex)(&iter->mutex); /* return any leftover data */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); if (sret != -EBUSY) return sret; trace_seq_init(&iter->seq); if (iter->trace->read) { sret = iter->trace->read(iter, filp, ubuf, cnt, ppos); if (sret) return sret; } waitagain: if (update_last_data_if_empty(iter->tr)) return 0; sret = tracing_wait_pipe(filp); if (sret <= 0) return sret; /* stop when tracing is finished */ if (trace_empty(iter)) return 0; if (cnt >= TRACE_SEQ_BUFFER_SIZE) cnt = TRACE_SEQ_BUFFER_SIZE - 1; /* reset all but tr, trace, and overruns */ trace_iterator_reset(iter); cpumask_clear(iter->started); trace_seq_init(&iter->seq); trace_event_read_lock(); trace_access_lock(iter->cpu_file); while (trace_find_next_entry_inc(iter) != NULL) { enum print_line_t ret; int save_len = iter->seq.seq.len; ret = print_trace_line(iter); if (ret == TRACE_TYPE_PARTIAL_LINE) { /* * If one print_trace_line() fills entire trace_seq in one shot, * trace_seq_to_user() will returns -EBUSY because save_len == 0, * In this case, we need to consume it, otherwise, loop will peek * this event next time, resulting in an infinite loop. */ if (save_len == 0) { iter->seq.full = 0; trace_seq_puts(&iter->seq, "[LINE TOO BIG]\n"); trace_consume(iter); break; } /* In other cases, don't print partial lines */ iter->seq.seq.len = save_len; break; } if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(iter); if (trace_seq_used(&iter->seq) >= cnt) break; /* * Setting the full flag means we reached the trace_seq buffer * size and we should leave by partial output condition above. * One of the trace_seq_* functions is not used properly. */ WARN_ONCE(iter->seq.full, "full flag set for trace type %d", iter->ent->type); } trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); /* Now copy what we have to the user */ sret = trace_seq_to_user(&iter->seq, ubuf, cnt); if (iter->seq.readpos >= trace_seq_used(&iter->seq)) trace_seq_init(&iter->seq); /* * If there was nothing to send to user, in spite of consuming trace * entries, go back to wait for more entries. */ if (sret == -EBUSY) goto waitagain; return sret; } static void tracing_spd_release_pipe(struct splice_pipe_desc *spd, unsigned int idx) { __free_page(spd->pages[idx]); } static size_t tracing_fill_pipe_page(size_t rem, struct trace_iterator *iter) { size_t count; int save_len; int ret; /* Seq buffer is page-sized, exactly what we need. */ for (;;) { save_len = iter->seq.seq.len; ret = print_trace_line(iter); if (trace_seq_has_overflowed(&iter->seq)) { iter->seq.seq.len = save_len; break; } /* * This should not be hit, because it should only * be set if the iter->seq overflowed. But check it * anyway to be safe. */ if (ret == TRACE_TYPE_PARTIAL_LINE) { iter->seq.seq.len = save_len; break; } count = trace_seq_used(&iter->seq) - save_len; if (rem < count) { rem = 0; iter->seq.seq.len = save_len; break; } if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(iter); rem -= count; if (!trace_find_next_entry_inc(iter)) { rem = 0; iter->ent = NULL; break; } } return rem; } static ssize_t tracing_splice_read_pipe(struct file *filp, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct page *pages_def[PIPE_DEF_BUFFERS]; struct partial_page partial_def[PIPE_DEF_BUFFERS]; struct trace_iterator *iter = filp->private_data; struct splice_pipe_desc spd = { .pages = pages_def, .partial = partial_def, .nr_pages = 0, /* This gets updated below. */ .nr_pages_max = PIPE_DEF_BUFFERS, .ops = &default_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, }; ssize_t ret; size_t rem; unsigned int i; if (splice_grow_spd(pipe, &spd)) return -ENOMEM; mutex_lock(&iter->mutex); if (iter->trace->splice_read) { ret = iter->trace->splice_read(iter, filp, ppos, pipe, len, flags); if (ret) goto out_err; } ret = tracing_wait_pipe(filp); if (ret <= 0) goto out_err; if (!iter->ent && !trace_find_next_entry_inc(iter)) { ret = -EFAULT; goto out_err; } trace_event_read_lock(); trace_access_lock(iter->cpu_file); /* Fill as many pages as possible. */ for (i = 0, rem = len; i < spd.nr_pages_max && rem; i++) { spd.pages[i] = alloc_page(GFP_KERNEL); if (!spd.pages[i]) break; rem = tracing_fill_pipe_page(rem, iter); /* Copy the data into the page, so we can start over. */ ret = trace_seq_to_buffer(&iter->seq, page_address(spd.pages[i]), min((size_t)trace_seq_used(&iter->seq), (size_t)PAGE_SIZE)); if (ret < 0) { __free_page(spd.pages[i]); break; } spd.partial[i].offset = 0; spd.partial[i].len = ret; trace_seq_init(&iter->seq); } trace_access_unlock(iter->cpu_file); trace_event_read_unlock(); mutex_unlock(&iter->mutex); spd.nr_pages = i; if (i) ret = splice_to_pipe(pipe, &spd); else ret = 0; out: splice_shrink_spd(&spd); return ret; out_err: mutex_unlock(&iter->mutex); goto out; } static ssize_t tracing_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct inode *inode = file_inode(filp); struct trace_array *tr = inode->i_private; int cpu = tracing_get_cpu(inode); char buf[64]; int r = 0; ssize_t ret; mutex_lock(&trace_types_lock); if (cpu == RING_BUFFER_ALL_CPUS) { int cpu, buf_size_same; unsigned long size; size = 0; buf_size_same = 1; /* check if all cpu sizes are same */ for_each_tracing_cpu(cpu) { /* fill in the size from first enabled cpu */ if (size == 0) size = per_cpu_ptr(tr->array_buffer.data, cpu)->entries; if (size != per_cpu_ptr(tr->array_buffer.data, cpu)->entries) { buf_size_same = 0; break; } } if (buf_size_same) { if (!tr->ring_buffer_expanded) r = sprintf(buf, "%lu (expanded: %lu)\n", size >> 10, trace_buf_size >> 10); else r = sprintf(buf, "%lu\n", size >> 10); } else r = sprintf(buf, "X\n"); } else r = sprintf(buf, "%lu\n", per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10); mutex_unlock(&trace_types_lock); ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); return ret; } static ssize_t tracing_entries_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct inode *inode = file_inode(filp); struct trace_array *tr = inode->i_private; unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; /* must have at least 1 entry */ if (!val) return -EINVAL; /* value is in KB */ val <<= 10; ret = tracing_resize_ring_buffer(tr, val, tracing_get_cpu(inode)); if (ret < 0) return ret; *ppos += cnt; return cnt; } static ssize_t tracing_total_entries_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; char buf[64]; int r, cpu; unsigned long size = 0, expanded_size = 0; mutex_lock(&trace_types_lock); for_each_tracing_cpu(cpu) { size += per_cpu_ptr(tr->array_buffer.data, cpu)->entries >> 10; if (!tr->ring_buffer_expanded) expanded_size += trace_buf_size >> 10; } if (tr->ring_buffer_expanded) r = sprintf(buf, "%lu\n", size); else r = sprintf(buf, "%lu (expanded: %lu)\n", size, expanded_size); mutex_unlock(&trace_types_lock); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } #define LAST_BOOT_HEADER ((void *)1) static void *l_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_array *tr = m->private; struct trace_scratch *tscratch = tr->scratch; unsigned int index = *pos; (*pos)++; if (*pos == 1) return LAST_BOOT_HEADER; /* Only show offsets of the last boot data */ if (!tscratch || !(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) return NULL; /* *pos 0 is for the header, 1 is for the first module */ index--; if (index >= tscratch->nr_entries) return NULL; return &tscratch->entries[index]; } static void *l_start(struct seq_file *m, loff_t *pos) { mutex_lock(&scratch_mutex); return l_next(m, NULL, pos); } static void l_stop(struct seq_file *m, void *p) { mutex_unlock(&scratch_mutex); } static void show_last_boot_header(struct seq_file *m, struct trace_array *tr) { struct trace_scratch *tscratch = tr->scratch; /* * Do not leak KASLR address. This only shows the KASLR address of * the last boot. When the ring buffer is started, the LAST_BOOT * flag gets cleared, and this should only report "current". * Otherwise it shows the KASLR address from the previous boot which * should not be the same as the current boot. */ if (tscratch && (tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) seq_printf(m, "%lx\t[kernel]\n", tscratch->text_addr); else seq_puts(m, "# Current\n"); } static int l_show(struct seq_file *m, void *v) { struct trace_array *tr = m->private; struct trace_mod_entry *entry = v; if (v == LAST_BOOT_HEADER) { show_last_boot_header(m, tr); return 0; } seq_printf(m, "%lx\t%s\n", entry->mod_addr, entry->mod_name); return 0; } static const struct seq_operations last_boot_seq_ops = { .start = l_start, .next = l_next, .stop = l_stop, .show = l_show, }; static int tracing_last_boot_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct seq_file *m; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = seq_open(file, &last_boot_seq_ops); if (ret) { trace_array_put(tr); return ret; } m = file->private_data; m->private = tr; return 0; } static int tracing_buffer_meta_open(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; int cpu = tracing_get_cpu(inode); int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = ring_buffer_meta_seq_init(filp, tr->array_buffer.buffer, cpu); if (ret < 0) __trace_array_put(tr); return ret; } static ssize_t tracing_free_buffer_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { /* * There is no need to read what the user has written, this function * is just to make sure that there is no error when "echo" is used */ *ppos += cnt; return cnt; } static int tracing_free_buffer_release(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; /* disable tracing ? */ if (tr->trace_flags & TRACE_ITER_STOP_ON_FREE) tracer_tracing_off(tr); /* resize the ring buffer to 0 */ tracing_resize_ring_buffer(tr, 0, RING_BUFFER_ALL_CPUS); trace_array_put(tr); return 0; } #define TRACE_MARKER_MAX_SIZE 4096 static ssize_t write_marker_to_buffer(struct trace_array *tr, const char __user *ubuf, size_t cnt, unsigned long ip) { struct ring_buffer_event *event; enum event_trigger_type tt = ETT_NONE; struct trace_buffer *buffer; struct print_entry *entry; int meta_size; ssize_t written; size_t size; int len; /* Used in tracing_mark_raw_write() as well */ #define FAULTED_STR "<faulted>" #define FAULTED_SIZE (sizeof(FAULTED_STR) - 1) /* '\0' is already accounted for */ meta_size = sizeof(*entry) + 2; /* add '\0' and possible '\n' */ again: size = cnt + meta_size; /* If less than "<faulted>", then make sure we can still add that */ if (cnt < FAULTED_SIZE) size += FAULTED_SIZE - cnt; buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, tracing_gen_ctx()); if (unlikely(!event)) { /* * If the size was greater than what was allowed, then * make it smaller and try again. */ if (size > ring_buffer_max_event_size(buffer)) { /* cnt < FAULTED size should never be bigger than max */ if (WARN_ON_ONCE(cnt < FAULTED_SIZE)) return -EBADF; cnt = ring_buffer_max_event_size(buffer) - meta_size; /* The above should only happen once */ if (WARN_ON_ONCE(cnt + meta_size == size)) return -EBADF; goto again; } /* Ring buffer disabled, return as if not open for write */ return -EBADF; } entry = ring_buffer_event_data(event); entry->ip = ip; len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt); if (len) { memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); cnt = FAULTED_SIZE; written = -EFAULT; } else written = cnt; if (tr->trace_marker_file && !list_empty(&tr->trace_marker_file->triggers)) { /* do not add \n before testing triggers, but add \0 */ entry->buf[cnt] = '\0'; tt = event_triggers_call(tr->trace_marker_file, buffer, entry, event); } if (entry->buf[cnt - 1] != '\n') { entry->buf[cnt] = '\n'; entry->buf[cnt + 1] = '\0'; } else entry->buf[cnt] = '\0'; if (static_branch_unlikely(&trace_marker_exports_enabled)) ftrace_exports(event, TRACE_EXPORT_MARKER); __buffer_unlock_commit(buffer, event); if (tt) event_triggers_post_call(tr->trace_marker_file, tt); return written; } static ssize_t tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { struct trace_array *tr = filp->private_data; ssize_t written = -ENODEV; unsigned long ip; if (tracing_disabled) return -EINVAL; if (!(tr->trace_flags & TRACE_ITER_MARKERS)) return -EINVAL; if ((ssize_t)cnt < 0) return -EINVAL; if (cnt > TRACE_MARKER_MAX_SIZE) cnt = TRACE_MARKER_MAX_SIZE; /* The selftests expect this function to be the IP address */ ip = _THIS_IP_; /* The global trace_marker can go to multiple instances */ if (tr == &global_trace) { guard(rcu)(); list_for_each_entry_rcu(tr, &marker_copies, marker_list) { written = write_marker_to_buffer(tr, ubuf, cnt, ip); if (written < 0) break; } } else { written = write_marker_to_buffer(tr, ubuf, cnt, ip); } return written; } static ssize_t write_raw_marker_to_buffer(struct trace_array *tr, const char __user *ubuf, size_t cnt) { struct ring_buffer_event *event; struct trace_buffer *buffer; struct raw_data_entry *entry; ssize_t written; int size; int len; #define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int)) size = sizeof(*entry) + cnt; if (cnt < FAULT_SIZE_ID) size += FAULT_SIZE_ID - cnt; buffer = tr->array_buffer.buffer; if (size > ring_buffer_max_event_size(buffer)) return -EINVAL; event = __trace_buffer_lock_reserve(buffer, TRACE_RAW_DATA, size, tracing_gen_ctx()); if (!event) /* Ring buffer disabled, return as if not open for write */ return -EBADF; entry = ring_buffer_event_data(event); len = __copy_from_user_inatomic(&entry->id, ubuf, cnt); if (len) { entry->id = -1; memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); written = -EFAULT; } else written = cnt; __buffer_unlock_commit(buffer, event); return written; } static ssize_t tracing_mark_raw_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { struct trace_array *tr = filp->private_data; ssize_t written = -ENODEV; #define FAULT_SIZE_ID (FAULTED_SIZE + sizeof(int)) if (tracing_disabled) return -EINVAL; if (!(tr->trace_flags & TRACE_ITER_MARKERS)) return -EINVAL; /* The marker must at least have a tag id */ if (cnt < sizeof(unsigned int)) return -EINVAL; /* The global trace_marker_raw can go to multiple instances */ if (tr == &global_trace) { guard(rcu)(); list_for_each_entry_rcu(tr, &marker_copies, marker_list) { written = write_raw_marker_to_buffer(tr, ubuf, cnt); if (written < 0) break; } } else { written = write_raw_marker_to_buffer(tr, ubuf, cnt); } return written; } static int tracing_clock_show(struct seq_file *m, void *v) { struct trace_array *tr = m->private; int i; for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) seq_printf(m, "%s%s%s%s", i ? " " : "", i == tr->clock_id ? "[" : "", trace_clocks[i].name, i == tr->clock_id ? "]" : ""); seq_putc(m, '\n'); return 0; } int tracing_set_clock(struct trace_array *tr, const char *clockstr) { int i; for (i = 0; i < ARRAY_SIZE(trace_clocks); i++) { if (strcmp(trace_clocks[i].name, clockstr) == 0) break; } if (i == ARRAY_SIZE(trace_clocks)) return -EINVAL; guard(mutex)(&trace_types_lock); tr->clock_id = i; ring_buffer_set_clock(tr->array_buffer.buffer, trace_clocks[i].func); /* * New clock may not be consistent with the previous clock. * Reset the buffer so that it doesn't have incomparable timestamps. */ tracing_reset_online_cpus(&tr->array_buffer); #ifdef CONFIG_TRACER_MAX_TRACE if (tr->max_buffer.buffer) ring_buffer_set_clock(tr->max_buffer.buffer, trace_clocks[i].func); tracing_reset_online_cpus(&tr->max_buffer); #endif if (tr->scratch && !(tr->flags & TRACE_ARRAY_FL_LAST_BOOT)) { struct trace_scratch *tscratch = tr->scratch; tscratch->clock_id = i; } return 0; } static ssize_t tracing_clock_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { struct seq_file *m = filp->private_data; struct trace_array *tr = m->private; char buf[64]; const char *clockstr; int ret; if (cnt >= sizeof(buf)) return -EINVAL; if (copy_from_user(buf, ubuf, cnt)) return -EFAULT; buf[cnt] = 0; clockstr = strstrip(buf); ret = tracing_set_clock(tr, clockstr); if (ret) return ret; *fpos += cnt; return cnt; } static int tracing_clock_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = single_open(file, tracing_clock_show, inode->i_private); if (ret < 0) trace_array_put(tr); return ret; } static int tracing_time_stamp_mode_show(struct seq_file *m, void *v) { struct trace_array *tr = m->private; guard(mutex)(&trace_types_lock); if (ring_buffer_time_stamp_abs(tr->array_buffer.buffer)) seq_puts(m, "delta [absolute]\n"); else seq_puts(m, "[delta] absolute\n"); return 0; } static int tracing_time_stamp_mode_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; ret = single_open(file, tracing_time_stamp_mode_show, inode->i_private); if (ret < 0) trace_array_put(tr); return ret; } u64 tracing_event_time_stamp(struct trace_buffer *buffer, struct ring_buffer_event *rbe) { if (rbe == this_cpu_read(trace_buffered_event)) return ring_buffer_time_stamp(buffer); return ring_buffer_event_time_stamp(buffer, rbe); } /* * Set or disable using the per CPU trace_buffer_event when possible. */ int tracing_set_filter_buffering(struct trace_array *tr, bool set) { guard(mutex)(&trace_types_lock); if (set && tr->no_filter_buffering_ref++) return 0; if (!set) { if (WARN_ON_ONCE(!tr->no_filter_buffering_ref)) return -EINVAL; --tr->no_filter_buffering_ref; } return 0; } struct ftrace_buffer_info { struct trace_iterator iter; void *spare; unsigned int spare_cpu; unsigned int spare_size; unsigned int read; }; #ifdef CONFIG_TRACER_SNAPSHOT static int tracing_snapshot_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; struct trace_iterator *iter; struct seq_file *m; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; if (file->f_mode & FMODE_READ) { iter = __tracing_open(inode, file, true); if (IS_ERR(iter)) ret = PTR_ERR(iter); } else { /* Writes still need the seq_file to hold the private data */ ret = -ENOMEM; m = kzalloc(sizeof(*m), GFP_KERNEL); if (!m) goto out; iter = kzalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { kfree(m); goto out; } ret = 0; iter->tr = tr; iter->array_buffer = &tr->max_buffer; iter->cpu_file = tracing_get_cpu(inode); m->private = iter; file->private_data = m; } out: if (ret < 0) trace_array_put(tr); return ret; } static void tracing_swap_cpu_buffer(void *tr) { update_max_tr_single((struct trace_array *)tr, current, smp_processor_id()); } static ssize_t tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct seq_file *m = filp->private_data; struct trace_iterator *iter = m->private; struct trace_array *tr = iter->tr; unsigned long val; int ret; ret = tracing_update_buffers(tr); if (ret < 0) return ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; guard(mutex)(&trace_types_lock); if (tr->current_trace->use_max_tr) return -EBUSY; local_irq_disable(); arch_spin_lock(&tr->max_lock); if (tr->cond_snapshot) ret = -EBUSY; arch_spin_unlock(&tr->max_lock); local_irq_enable(); if (ret) return ret; switch (val) { case 0: if (iter->cpu_file != RING_BUFFER_ALL_CPUS) return -EINVAL; if (tr->allocated_snapshot) free_snapshot(tr); break; case 1: /* Only allow per-cpu swap if the ring buffer supports it */ #ifndef CONFIG_RING_BUFFER_ALLOW_SWAP if (iter->cpu_file != RING_BUFFER_ALL_CPUS) return -EINVAL; #endif if (tr->allocated_snapshot) ret = resize_buffer_duplicate_size(&tr->max_buffer, &tr->array_buffer, iter->cpu_file); ret = tracing_arm_snapshot_locked(tr); if (ret) return ret; /* Now, we're going to swap */ if (iter->cpu_file == RING_BUFFER_ALL_CPUS) { local_irq_disable(); update_max_tr(tr, current, smp_processor_id(), NULL); local_irq_enable(); } else { smp_call_function_single(iter->cpu_file, tracing_swap_cpu_buffer, (void *)tr, 1); } tracing_disarm_snapshot(tr); break; default: if (tr->allocated_snapshot) { if (iter->cpu_file == RING_BUFFER_ALL_CPUS) tracing_reset_online_cpus(&tr->max_buffer); else tracing_reset_cpu(&tr->max_buffer, iter->cpu_file); } break; } if (ret >= 0) { *ppos += cnt; ret = cnt; } return ret; } static int tracing_snapshot_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; int ret; ret = tracing_release(inode, file); if (file->f_mode & FMODE_READ) return ret; /* If write only, the seq_file is just a stub */ if (m) kfree(m->private); kfree(m); return 0; } static int tracing_buffers_open(struct inode *inode, struct file *filp); static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos); static int tracing_buffers_release(struct inode *inode, struct file *file); static ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); static int snapshot_raw_open(struct inode *inode, struct file *filp) { struct ftrace_buffer_info *info; int ret; /* The following checks for tracefs lockdown */ ret = tracing_buffers_open(inode, filp); if (ret < 0) return ret; info = filp->private_data; if (info->iter.trace->use_max_tr) { tracing_buffers_release(inode, filp); return -EBUSY; } info->iter.snapshot = true; info->iter.array_buffer = &info->iter.tr->max_buffer; return ret; } #endif /* CONFIG_TRACER_SNAPSHOT */ static const struct file_operations tracing_thresh_fops = { .open = tracing_open_generic, .read = tracing_thresh_read, .write = tracing_thresh_write, .llseek = generic_file_llseek, }; #ifdef CONFIG_TRACER_MAX_TRACE static const struct file_operations tracing_max_lat_fops = { .open = tracing_open_generic_tr, .read = tracing_max_lat_read, .write = tracing_max_lat_write, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; #endif static const struct file_operations set_tracer_fops = { .open = tracing_open_generic_tr, .read = tracing_set_trace_read, .write = tracing_set_trace_write, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; static const struct file_operations tracing_pipe_fops = { .open = tracing_open_pipe, .poll = tracing_poll_pipe, .read = tracing_read_pipe, .splice_read = tracing_splice_read_pipe, .release = tracing_release_pipe, }; static const struct file_operations tracing_entries_fops = { .open = tracing_open_generic_tr, .read = tracing_entries_read, .write = tracing_entries_write, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; static const struct file_operations tracing_buffer_meta_fops = { .open = tracing_buffer_meta_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_seq_release, }; static const struct file_operations tracing_total_entries_fops = { .open = tracing_open_generic_tr, .read = tracing_total_entries_read, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; static const struct file_operations tracing_free_buffer_fops = { .open = tracing_open_generic_tr, .write = tracing_free_buffer_write, .release = tracing_free_buffer_release, }; static const struct file_operations tracing_mark_fops = { .open = tracing_mark_open, .write = tracing_mark_write, .release = tracing_release_generic_tr, }; static const struct file_operations tracing_mark_raw_fops = { .open = tracing_mark_open, .write = tracing_mark_raw_write, .release = tracing_release_generic_tr, }; static const struct file_operations trace_clock_fops = { .open = tracing_clock_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_single_release_tr, .write = tracing_clock_write, }; static const struct file_operations trace_time_stamp_mode_fops = { .open = tracing_time_stamp_mode_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_single_release_tr, }; static const struct file_operations last_boot_fops = { .open = tracing_last_boot_open, .read = seq_read, .llseek = seq_lseek, .release = tracing_seq_release, }; #ifdef CONFIG_TRACER_SNAPSHOT static const struct file_operations snapshot_fops = { .open = tracing_snapshot_open, .read = seq_read, .write = tracing_snapshot_write, .llseek = tracing_lseek, .release = tracing_snapshot_release, }; static const struct file_operations snapshot_raw_fops = { .open = snapshot_raw_open, .read = tracing_buffers_read, .release = tracing_buffers_release, .splice_read = tracing_buffers_splice_read, }; #endif /* CONFIG_TRACER_SNAPSHOT */ /* * trace_min_max_write - Write a u64 value to a trace_min_max_param struct * @filp: The active open file structure * @ubuf: The userspace provided buffer to read value into * @cnt: The maximum number of bytes to read * @ppos: The current "file" position * * This function implements the write interface for a struct trace_min_max_param. * The filp->private_data must point to a trace_min_max_param structure that * defines where to write the value, the min and the max acceptable values, * and a lock to protect the write. */ static ssize_t trace_min_max_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_min_max_param *param = filp->private_data; u64 val; int err; if (!param) return -EFAULT; err = kstrtoull_from_user(ubuf, cnt, 10, &val); if (err) return err; if (param->lock) mutex_lock(param->lock); if (param->min && val < *param->min) err = -EINVAL; if (param->max && val > *param->max) err = -EINVAL; if (!err) *param->val = val; if (param->lock) mutex_unlock(param->lock); if (err) return err; return cnt; } /* * trace_min_max_read - Read a u64 value from a trace_min_max_param struct * @filp: The active open file structure * @ubuf: The userspace provided buffer to read value into * @cnt: The maximum number of bytes to read * @ppos: The current "file" position * * This function implements the read interface for a struct trace_min_max_param. * The filp->private_data must point to a trace_min_max_param struct with valid * data. */ static ssize_t trace_min_max_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_min_max_param *param = filp->private_data; char buf[U64_STR_SIZE]; int len; u64 val; if (!param) return -EFAULT; val = *param->val; if (cnt > sizeof(buf)) cnt = sizeof(buf); len = snprintf(buf, sizeof(buf), "%llu\n", val); return simple_read_from_buffer(ubuf, cnt, ppos, buf, len); } const struct file_operations trace_min_max_fops = { .open = tracing_open_generic, .read = trace_min_max_read, .write = trace_min_max_write, }; #define TRACING_LOG_ERRS_MAX 8 #define TRACING_LOG_LOC_MAX 128 #define CMD_PREFIX " Command: " struct err_info { const char **errs; /* ptr to loc-specific array of err strings */ u8 type; /* index into errs -> specific err string */ u16 pos; /* caret position */ u64 ts; }; struct tracing_log_err { struct list_head list; struct err_info info; char loc[TRACING_LOG_LOC_MAX]; /* err location */ char *cmd; /* what caused err */ }; static DEFINE_MUTEX(tracing_err_log_lock); static struct tracing_log_err *alloc_tracing_log_err(int len) { struct tracing_log_err *err; err = kzalloc(sizeof(*err), GFP_KERNEL); if (!err) return ERR_PTR(-ENOMEM); err->cmd = kzalloc(len, GFP_KERNEL); if (!err->cmd) { kfree(err); return ERR_PTR(-ENOMEM); } return err; } static void free_tracing_log_err(struct tracing_log_err *err) { kfree(err->cmd); kfree(err); } static struct tracing_log_err *get_tracing_log_err(struct trace_array *tr, int len) { struct tracing_log_err *err; char *cmd; if (tr->n_err_log_entries < TRACING_LOG_ERRS_MAX) { err = alloc_tracing_log_err(len); if (PTR_ERR(err) != -ENOMEM) tr->n_err_log_entries++; return err; } cmd = kzalloc(len, GFP_KERNEL); if (!cmd) return ERR_PTR(-ENOMEM); err = list_first_entry(&tr->err_log, struct tracing_log_err, list); kfree(err->cmd); err->cmd = cmd; list_del(&err->list); return err; } /** * err_pos - find the position of a string within a command for error careting * @cmd: The tracing command that caused the error * @str: The string to position the caret at within @cmd * * Finds the position of the first occurrence of @str within @cmd. The * return value can be passed to tracing_log_err() for caret placement * within @cmd. * * Returns the index within @cmd of the first occurrence of @str or 0 * if @str was not found. */ unsigned int err_pos(char *cmd, const char *str) { char *found; if (WARN_ON(!strlen(cmd))) return 0; found = strstr(cmd, str); if (found) return found - cmd; return 0; } /** * tracing_log_err - write an error to the tracing error log * @tr: The associated trace array for the error (NULL for top level array) * @loc: A string describing where the error occurred * @cmd: The tracing command that caused the error * @errs: The array of loc-specific static error strings * @type: The index into errs[], which produces the specific static err string * @pos: The position the caret should be placed in the cmd * * Writes an error into tracing/error_log of the form: * * <loc>: error: <text> * Command: <cmd> * ^ * * tracing/error_log is a small log file containing the last * TRACING_LOG_ERRS_MAX errors (8). Memory for errors isn't allocated * unless there has been a tracing error, and the error log can be * cleared and have its memory freed by writing the empty string in * truncation mode to it i.e. echo > tracing/error_log. * * NOTE: the @errs array along with the @type param are used to * produce a static error string - this string is not copied and saved * when the error is logged - only a pointer to it is saved. See * existing callers for examples of how static strings are typically * defined for use with tracing_log_err(). */ void tracing_log_err(struct trace_array *tr, const char *loc, const char *cmd, const char **errs, u8 type, u16 pos) { struct tracing_log_err *err; int len = 0; if (!tr) tr = &global_trace; len += sizeof(CMD_PREFIX) + 2 * sizeof("\n") + strlen(cmd) + 1; guard(mutex)(&tracing_err_log_lock); err = get_tracing_log_err(tr, len); if (PTR_ERR(err) == -ENOMEM) return; snprintf(err->loc, TRACING_LOG_LOC_MAX, "%s: error: ", loc); snprintf(err->cmd, len, "\n" CMD_PREFIX "%s\n", cmd); err->info.errs = errs; err->info.type = type; err->info.pos = pos; err->info.ts = local_clock(); list_add_tail(&err->list, &tr->err_log); } static void clear_tracing_err_log(struct trace_array *tr) { struct tracing_log_err *err, *next; guard(mutex)(&tracing_err_log_lock); list_for_each_entry_safe(err, next, &tr->err_log, list) { list_del(&err->list); free_tracing_log_err(err); } tr->n_err_log_entries = 0; } static void *tracing_err_log_seq_start(struct seq_file *m, loff_t *pos) { struct trace_array *tr = m->private; mutex_lock(&tracing_err_log_lock); return seq_list_start(&tr->err_log, *pos); } static void *tracing_err_log_seq_next(struct seq_file *m, void *v, loff_t *pos) { struct trace_array *tr = m->private; return seq_list_next(v, &tr->err_log, pos); } static void tracing_err_log_seq_stop(struct seq_file *m, void *v) { mutex_unlock(&tracing_err_log_lock); } static void tracing_err_log_show_pos(struct seq_file *m, u16 pos) { u16 i; for (i = 0; i < sizeof(CMD_PREFIX) - 1; i++) seq_putc(m, ' '); for (i = 0; i < pos; i++) seq_putc(m, ' '); seq_puts(m, "^\n"); } static int tracing_err_log_seq_show(struct seq_file *m, void *v) { struct tracing_log_err *err = v; if (err) { const char *err_text = err->info.errs[err->info.type]; u64 sec = err->info.ts; u32 nsec; nsec = do_div(sec, NSEC_PER_SEC); seq_printf(m, "[%5llu.%06u] %s%s", sec, nsec / 1000, err->loc, err_text); seq_printf(m, "%s", err->cmd); tracing_err_log_show_pos(m, err->info.pos); } return 0; } static const struct seq_operations tracing_err_log_seq_ops = { .start = tracing_err_log_seq_start, .next = tracing_err_log_seq_next, .stop = tracing_err_log_seq_stop, .show = tracing_err_log_seq_show }; static int tracing_err_log_open(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; int ret = 0; ret = tracing_check_open_get_tr(tr); if (ret) return ret; /* If this file was opened for write, then erase contents */ if ((file->f_mode & FMODE_WRITE) && (file->f_flags & O_TRUNC)) clear_tracing_err_log(tr); if (file->f_mode & FMODE_READ) { ret = seq_open(file, &tracing_err_log_seq_ops); if (!ret) { struct seq_file *m = file->private_data; m->private = tr; } else { trace_array_put(tr); } } return ret; } static ssize_t tracing_err_log_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { return count; } static int tracing_err_log_release(struct inode *inode, struct file *file) { struct trace_array *tr = inode->i_private; trace_array_put(tr); if (file->f_mode & FMODE_READ) seq_release(inode, file); return 0; } static const struct file_operations tracing_err_log_fops = { .open = tracing_err_log_open, .write = tracing_err_log_write, .read = seq_read, .llseek = tracing_lseek, .release = tracing_err_log_release, }; static int tracing_buffers_open(struct inode *inode, struct file *filp) { struct trace_array *tr = inode->i_private; struct ftrace_buffer_info *info; int ret; ret = tracing_check_open_get_tr(tr); if (ret) return ret; info = kvzalloc(sizeof(*info), GFP_KERNEL); if (!info) { trace_array_put(tr); return -ENOMEM; } mutex_lock(&trace_types_lock); info->iter.tr = tr; info->iter.cpu_file = tracing_get_cpu(inode); info->iter.trace = tr->current_trace; info->iter.array_buffer = &tr->array_buffer; info->spare = NULL; /* Force reading ring buffer for first read */ info->read = (unsigned int)-1; filp->private_data = info; tr->trace_ref++; mutex_unlock(&trace_types_lock); ret = nonseekable_open(inode, filp); if (ret < 0) trace_array_put(tr); return ret; } static __poll_t tracing_buffers_poll(struct file *filp, poll_table *poll_table) { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; return trace_poll(iter, filp, poll_table); } static ssize_t tracing_buffers_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; void *trace_data; int page_size; ssize_t ret = 0; ssize_t size; if (!count) return 0; #ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->tr->current_trace->use_max_tr) return -EBUSY; #endif page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); /* Make sure the spare matches the current sub buffer size */ if (info->spare) { if (page_size != info->spare_size) { ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); info->spare = NULL; } } if (!info->spare) { info->spare = ring_buffer_alloc_read_page(iter->array_buffer->buffer, iter->cpu_file); if (IS_ERR(info->spare)) { ret = PTR_ERR(info->spare); info->spare = NULL; } else { info->spare_cpu = iter->cpu_file; info->spare_size = page_size; } } if (!info->spare) return ret; /* Do we have previous read data to read? */ if (info->read < page_size) goto read; again: trace_access_lock(iter->cpu_file); ret = ring_buffer_read_page(iter->array_buffer->buffer, info->spare, count, iter->cpu_file, 0); trace_access_unlock(iter->cpu_file); if (ret < 0) { if (trace_empty(iter) && !iter->closed) { if (update_last_data_if_empty(iter->tr)) return 0; if ((filp->f_flags & O_NONBLOCK)) return -EAGAIN; ret = wait_on_pipe(iter, 0); if (ret) return ret; goto again; } return 0; } info->read = 0; read: size = page_size - info->read; if (size > count) size = count; trace_data = ring_buffer_read_page_data(info->spare); ret = copy_to_user(ubuf, trace_data + info->read, size); if (ret == size) return -EFAULT; size -= ret; *ppos += size; info->read += size; return size; } static int tracing_buffers_flush(struct file *file, fl_owner_t id) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; iter->closed = true; /* Make sure the waiters see the new wait_index */ (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); return 0; } static int tracing_buffers_release(struct inode *inode, struct file *file) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; guard(mutex)(&trace_types_lock); iter->tr->trace_ref--; __trace_array_put(iter->tr); if (info->spare) ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); kvfree(info); return 0; } struct buffer_ref { struct trace_buffer *buffer; void *page; int cpu; refcount_t refcount; }; static void buffer_ref_release(struct buffer_ref *ref) { if (!refcount_dec_and_test(&ref->refcount)) return; ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); kfree(ref); } static void buffer_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; buffer_ref_release(ref); buf->private = 0; } static bool buffer_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct buffer_ref *ref = (struct buffer_ref *)buf->private; if (refcount_read(&ref->refcount) > INT_MAX/2) return false; refcount_inc(&ref->refcount); return true; } /* Pipe buffer operations for a buffer. */ static const struct pipe_buf_operations buffer_pipe_buf_ops = { .release = buffer_pipe_buf_release, .get = buffer_pipe_buf_get, }; /* * Callback from splice_to_pipe(), if we need to release some pages * at the end of the spd in case we error'ed out in filling the pipe. */ static void buffer_spd_release(struct splice_pipe_desc *spd, unsigned int i) { struct buffer_ref *ref = (struct buffer_ref *)spd->partial[i].private; buffer_ref_release(ref); spd->partial[i].private = 0; } static ssize_t tracing_buffers_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; struct partial_page partial_def[PIPE_DEF_BUFFERS]; struct page *pages_def[PIPE_DEF_BUFFERS]; struct splice_pipe_desc spd = { .pages = pages_def, .partial = partial_def, .nr_pages_max = PIPE_DEF_BUFFERS, .ops = &buffer_pipe_buf_ops, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; bool woken = false; int page_size; int entries, i; ssize_t ret = 0; #ifdef CONFIG_TRACER_MAX_TRACE if (iter->snapshot && iter->tr->current_trace->use_max_tr) return -EBUSY; #endif page_size = ring_buffer_subbuf_size_get(iter->array_buffer->buffer); if (*ppos & (page_size - 1)) return -EINVAL; if (len & (page_size - 1)) { if (len < page_size) return -EINVAL; len &= (~(page_size - 1)); } if (splice_grow_spd(pipe, &spd)) return -ENOMEM; again: trace_access_lock(iter->cpu_file); entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); for (i = 0; i < spd.nr_pages_max && len && entries; i++, len -= page_size) { struct page *page; int r; ref = kzalloc(sizeof(*ref), GFP_KERNEL); if (!ref) { ret = -ENOMEM; break; } refcount_set(&ref->refcount, 1); ref->buffer = iter->array_buffer->buffer; ref->page = ring_buffer_alloc_read_page(ref->buffer, iter->cpu_file); if (IS_ERR(ref->page)) { ret = PTR_ERR(ref->page); ref->page = NULL; kfree(ref); break; } ref->cpu = iter->cpu_file; r = ring_buffer_read_page(ref->buffer, ref->page, len, iter->cpu_file, 1); if (r < 0) { ring_buffer_free_read_page(ref->buffer, ref->cpu, ref->page); kfree(ref); break; } page = virt_to_page(ring_buffer_read_page_data(ref->page)); spd.pages[i] = page; spd.partial[i].len = page_size; spd.partial[i].offset = 0; spd.partial[i].private = (unsigned long)ref; spd.nr_pages++; *ppos += page_size; entries = ring_buffer_entries_cpu(iter->array_buffer->buffer, iter->cpu_file); } trace_access_unlock(iter->cpu_file); spd.nr_pages = i; /* did we read anything? */ if (!spd.nr_pages) { if (ret) goto out; if (woken) goto out; ret = -EAGAIN; if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out; ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; /* No need to wait after waking up when tracing is off */ if (!tracer_tracing_is_on(iter->tr)) goto out; /* Iterate one more time to collect any new data then exit */ woken = true; goto again; } ret = splice_to_pipe(pipe, &spd); out: splice_shrink_spd(&spd); return ret; } static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; int err; if (cmd == TRACE_MMAP_IOCTL_GET_READER) { if (!(file->f_flags & O_NONBLOCK)) { err = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, iter->tr->buffer_percent, NULL, NULL); if (err) return err; } return ring_buffer_map_get_reader(iter->array_buffer->buffer, iter->cpu_file); } else if (cmd) { return -ENOTTY; } /* * An ioctl call with cmd 0 to the ring buffer file will wake up all * waiters */ guard(mutex)(&trace_types_lock); /* Make sure the waiters see the new wait_index */ (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); return 0; } #ifdef CONFIG_TRACER_MAX_TRACE static int get_snapshot_map(struct trace_array *tr) { int err = 0; /* * Called with mmap_lock held. lockdep would be unhappy if we would now * take trace_types_lock. Instead use the specific * snapshot_trigger_lock. */ spin_lock(&tr->snapshot_trigger_lock); if (tr->snapshot || tr->mapped == UINT_MAX) err = -EBUSY; else tr->mapped++; spin_unlock(&tr->snapshot_trigger_lock); /* Wait for update_max_tr() to observe iter->tr->mapped */ if (tr->mapped == 1) synchronize_rcu(); return err; } static void put_snapshot_map(struct trace_array *tr) { spin_lock(&tr->snapshot_trigger_lock); if (!WARN_ON(!tr->mapped)) tr->mapped--; spin_unlock(&tr->snapshot_trigger_lock); } #else static inline int get_snapshot_map(struct trace_array *tr) { return 0; } static inline void put_snapshot_map(struct trace_array *tr) { } #endif static void tracing_buffers_mmap_close(struct vm_area_struct *vma) { struct ftrace_buffer_info *info = vma->vm_file->private_data; struct trace_iterator *iter = &info->iter; WARN_ON(ring_buffer_unmap(iter->array_buffer->buffer, iter->cpu_file)); put_snapshot_map(iter->tr); } static const struct vm_operations_struct tracing_buffers_vmops = { .close = tracing_buffers_mmap_close, }; static int tracing_buffers_mmap(struct file *filp, struct vm_area_struct *vma) { struct ftrace_buffer_info *info = filp->private_data; struct trace_iterator *iter = &info->iter; int ret = 0; /* A memmap'ed buffer is not supported for user space mmap */ if (iter->tr->flags & TRACE_ARRAY_FL_MEMMAP) return -ENODEV; ret = get_snapshot_map(iter->tr); if (ret) return ret; ret = ring_buffer_map(iter->array_buffer->buffer, iter->cpu_file, vma); if (ret) put_snapshot_map(iter->tr); vma->vm_ops = &tracing_buffers_vmops; return ret; } static const struct file_operations tracing_buffers_fops = { .open = tracing_buffers_open, .read = tracing_buffers_read, .poll = tracing_buffers_poll, .release = tracing_buffers_release, .flush = tracing_buffers_flush, .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, .mmap = tracing_buffers_mmap, }; static ssize_t tracing_stats_read(struct file *filp, char __user *ubuf, size_t count, loff_t *ppos) { struct inode *inode = file_inode(filp); struct trace_array *tr = inode->i_private; struct array_buffer *trace_buf = &tr->array_buffer; int cpu = tracing_get_cpu(inode); struct trace_seq *s; unsigned long cnt; unsigned long long t; unsigned long usec_rem; s = kmalloc(sizeof(*s), GFP_KERNEL); if (!s) return -ENOMEM; trace_seq_init(s); cnt = ring_buffer_entries_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "entries: %ld\n", cnt); cnt = ring_buffer_overrun_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "overrun: %ld\n", cnt); cnt = ring_buffer_commit_overrun_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "commit overrun: %ld\n", cnt); cnt = ring_buffer_bytes_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "bytes: %ld\n", cnt); if (trace_clocks[tr->clock_id].in_ns) { /* local or global for trace_clock */ t = ns2usecs(ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); usec_rem = do_div(t, USEC_PER_SEC); trace_seq_printf(s, "oldest event ts: %5llu.%06lu\n", t, usec_rem); t = ns2usecs(ring_buffer_time_stamp(trace_buf->buffer)); usec_rem = do_div(t, USEC_PER_SEC); trace_seq_printf(s, "now ts: %5llu.%06lu\n", t, usec_rem); } else { /* counter or tsc mode for trace_clock */ trace_seq_printf(s, "oldest event ts: %llu\n", ring_buffer_oldest_event_ts(trace_buf->buffer, cpu)); trace_seq_printf(s, "now ts: %llu\n", ring_buffer_time_stamp(trace_buf->buffer)); } cnt = ring_buffer_dropped_events_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "dropped events: %ld\n", cnt); cnt = ring_buffer_read_events_cpu(trace_buf->buffer, cpu); trace_seq_printf(s, "read events: %ld\n", cnt); count = simple_read_from_buffer(ubuf, count, ppos, s->buffer, trace_seq_used(s)); kfree(s); return count; } static const struct file_operations tracing_stats_fops = { .open = tracing_open_generic_tr, .read = tracing_stats_read, .llseek = generic_file_llseek, .release = tracing_release_generic_tr, }; #ifdef CONFIG_DYNAMIC_FTRACE static ssize_t tracing_read_dyn_info(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { ssize_t ret; char *buf; int r; /* 512 should be plenty to hold the amount needed */ #define DYN_INFO_BUF_SIZE 512 buf = kmalloc(DYN_INFO_BUF_SIZE, GFP_KERNEL); if (!buf) return -ENOMEM; r = scnprintf(buf, DYN_INFO_BUF_SIZE, "%ld pages:%ld groups: %ld\n" "ftrace boot update time = %llu (ns)\n" "ftrace module total update time = %llu (ns)\n", ftrace_update_tot_cnt, ftrace_number_of_pages, ftrace_number_of_groups, ftrace_update_time, ftrace_total_mod_time); ret = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); kfree(buf); return ret; } static const struct file_operations tracing_dyn_info_fops = { .open = tracing_open_generic, .read = tracing_read_dyn_info, .llseek = generic_file_llseek, }; #endif /* CONFIG_DYNAMIC_FTRACE */ #if defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) static void ftrace_snapshot(unsigned long ip, unsigned long parent_ip, struct trace_array *tr, struct ftrace_probe_ops *ops, void *data) { tracing_snapshot_instance(tr); } static void ftrace_count_snapshot(unsigned long ip, unsigned long parent_ip, struct trace_array *tr, struct ftrace_probe_ops *ops, void *data) { struct ftrace_func_mapper *mapper = data; long *count = NULL; if (mapper) count = (long *)ftrace_func_mapper_find_ip(mapper, ip); if (count) { if (*count <= 0) return; (*count)--; } tracing_snapshot_instance(tr); } static int ftrace_snapshot_print(struct seq_file *m, unsigned long ip, struct ftrace_probe_ops *ops, void *data) { struct ftrace_func_mapper *mapper = data; long *count = NULL; seq_printf(m, "%ps:", (void *)ip); seq_puts(m, "snapshot"); if (mapper) count = (long *)ftrace_func_mapper_find_ip(mapper, ip); if (count) seq_printf(m, ":count=%ld\n", *count); else seq_puts(m, ":unlimited\n"); return 0; } static int ftrace_snapshot_init(struct ftrace_probe_ops *ops, struct trace_array *tr, unsigned long ip, void *init_data, void **data) { struct ftrace_func_mapper *mapper = *data; if (!mapper) { mapper = allocate_ftrace_func_mapper(); if (!mapper) return -ENOMEM; *data = mapper; } return ftrace_func_mapper_add_ip(mapper, ip, init_data); } static void ftrace_snapshot_free(struct ftrace_probe_ops *ops, struct trace_array *tr, unsigned long ip, void *data) { struct ftrace_func_mapper *mapper = data; if (!ip) { if (!mapper) return; free_ftrace_func_mapper(mapper, NULL); return; } ftrace_func_mapper_remove_ip(mapper, ip); } static struct ftrace_probe_ops snapshot_probe_ops = { .func = ftrace_snapshot, .print = ftrace_snapshot_print, }; static struct ftrace_probe_ops snapshot_count_probe_ops = { .func = ftrace_count_snapshot, .print = ftrace_snapshot_print, .init = ftrace_snapshot_init, .free = ftrace_snapshot_free, }; static int ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash, char *glob, char *cmd, char *param, int enable) { struct ftrace_probe_ops *ops; void *count = (void *)-1; char *number; int ret; if (!tr) return -ENODEV; /* hash funcs only work with set_ftrace_filter */ if (!enable) return -EINVAL; ops = param ? &snapshot_count_probe_ops : &snapshot_probe_ops; if (glob[0] == '!') { ret = unregister_ftrace_function_probe_func(glob+1, tr, ops); if (!ret) tracing_disarm_snapshot(tr); return ret; } if (!param) goto out_reg; number = strsep(¶m, ":"); if (!strlen(number)) goto out_reg; /* * We use the callback data field (which is a pointer) * as our counter. */ ret = kstrtoul(number, 0, (unsigned long *)&count); if (ret) return ret; out_reg: ret = tracing_arm_snapshot(tr); if (ret < 0) return ret; ret = register_ftrace_function_probe(glob, tr, ops, count); if (ret < 0) tracing_disarm_snapshot(tr); return ret < 0 ? ret : 0; } static struct ftrace_func_command ftrace_snapshot_cmd = { .name = "snapshot", .func = ftrace_trace_snapshot_callback, }; static __init int register_snapshot_cmd(void) { return register_ftrace_command(&ftrace_snapshot_cmd); } #else static inline __init int register_snapshot_cmd(void) { return 0; } #endif /* defined(CONFIG_TRACER_SNAPSHOT) && defined(CONFIG_DYNAMIC_FTRACE) */ static struct dentry *tracing_get_dentry(struct trace_array *tr) { /* Top directory uses NULL as the parent */ if (tr->flags & TRACE_ARRAY_FL_GLOBAL) return NULL; if (WARN_ON(!tr->dir)) return ERR_PTR(-ENODEV); /* All sub buffers have a descriptor */ return tr->dir; } static struct dentry *tracing_dentry_percpu(struct trace_array *tr, int cpu) { struct dentry *d_tracer; if (tr->percpu_dir) return tr->percpu_dir; d_tracer = tracing_get_dentry(tr); if (IS_ERR(d_tracer)) return NULL; tr->percpu_dir = tracefs_create_dir("per_cpu", d_tracer); MEM_FAIL(!tr->percpu_dir, "Could not create tracefs directory 'per_cpu/%d'\n", cpu); return tr->percpu_dir; } static struct dentry * trace_create_cpu_file(const char *name, umode_t mode, struct dentry *parent, void *data, long cpu, const struct file_operations *fops) { struct dentry *ret = trace_create_file(name, mode, parent, data, fops); if (ret) /* See tracing_get_cpu() */ d_inode(ret)->i_cdev = (void *)(cpu + 1); return ret; } static void tracing_init_tracefs_percpu(struct trace_array *tr, long cpu) { struct dentry *d_percpu = tracing_dentry_percpu(tr, cpu); struct dentry *d_cpu; char cpu_dir[30]; /* 30 characters should be more than enough */ if (!d_percpu) return; snprintf(cpu_dir, 30, "cpu%ld", cpu); d_cpu = tracefs_create_dir(cpu_dir, d_percpu); if (!d_cpu) { pr_warn("Could not create tracefs '%s' entry\n", cpu_dir); return; } /* per cpu trace_pipe */ trace_create_cpu_file("trace_pipe", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_pipe_fops); /* per cpu trace */ trace_create_cpu_file("trace", TRACE_MODE_WRITE, d_cpu, tr, cpu, &tracing_fops); trace_create_cpu_file("trace_pipe_raw", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_buffers_fops); trace_create_cpu_file("stats", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_stats_fops); trace_create_cpu_file("buffer_size_kb", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_entries_fops); if (tr->range_addr_start) trace_create_cpu_file("buffer_meta", TRACE_MODE_READ, d_cpu, tr, cpu, &tracing_buffer_meta_fops); #ifdef CONFIG_TRACER_SNAPSHOT if (!tr->range_addr_start) { trace_create_cpu_file("snapshot", TRACE_MODE_WRITE, d_cpu, tr, cpu, &snapshot_fops); trace_create_cpu_file("snapshot_raw", TRACE_MODE_READ, d_cpu, tr, cpu, &snapshot_raw_fops); } #endif } #ifdef CONFIG_FTRACE_SELFTEST /* Let selftest have access to static functions in this file */ #include "trace_selftest.c" #endif static ssize_t trace_options_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_option_dentry *topt = filp->private_data; char *buf; if (topt->flags->val & topt->opt->bit) buf = "1\n"; else buf = "0\n"; return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); } static ssize_t trace_options_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_option_dentry *topt = filp->private_data; unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; if (val != 0 && val != 1) return -EINVAL; if (!!(topt->flags->val & topt->opt->bit) != val) { guard(mutex)(&trace_types_lock); ret = __set_tracer_option(topt->tr, topt->flags, topt->opt, !val); if (ret) return ret; } *ppos += cnt; return cnt; } static int tracing_open_options(struct inode *inode, struct file *filp) { struct trace_option_dentry *topt = inode->i_private; int ret; ret = tracing_check_open_get_tr(topt->tr); if (ret) return ret; filp->private_data = inode->i_private; return 0; } static int tracing_release_options(struct inode *inode, struct file *file) { struct trace_option_dentry *topt = file->private_data; trace_array_put(topt->tr); return 0; } static const struct file_operations trace_options_fops = { .open = tracing_open_options, .read = trace_options_read, .write = trace_options_write, .llseek = generic_file_llseek, .release = tracing_release_options, }; /* * In order to pass in both the trace_array descriptor as well as the index * to the flag that the trace option file represents, the trace_array * has a character array of trace_flags_index[], which holds the index * of the bit for the flag it represents. index[0] == 0, index[1] == 1, etc. * The address of this character array is passed to the flag option file * read/write callbacks. * * In order to extract both the index and the trace_array descriptor, * get_tr_index() uses the following algorithm. * * idx = *ptr; * * As the pointer itself contains the address of the index (remember * index[1] == 1). * * Then to get the trace_array descriptor, by subtracting that index * from the ptr, we get to the start of the index itself. * * ptr - idx == &index[0] * * Then a simple container_of() from that pointer gets us to the * trace_array descriptor. */ static void get_tr_index(void *data, struct trace_array **ptr, unsigned int *pindex) { *pindex = *(unsigned char *)data; *ptr = container_of(data - *pindex, struct trace_array, trace_flags_index); } static ssize_t trace_options_core_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { void *tr_index = filp->private_data; struct trace_array *tr; unsigned int index; char *buf; get_tr_index(tr_index, &tr, &index); if (tr->trace_flags & (1 << index)) buf = "1\n"; else buf = "0\n"; return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2); } static ssize_t trace_options_core_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { void *tr_index = filp->private_data; struct trace_array *tr; unsigned int index; unsigned long val; int ret; get_tr_index(tr_index, &tr, &index); ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; if (val != 0 && val != 1) return -EINVAL; mutex_lock(&event_mutex); mutex_lock(&trace_types_lock); ret = set_tracer_flag(tr, 1 << index, val); mutex_unlock(&trace_types_lock); mutex_unlock(&event_mutex); if (ret < 0) return ret; *ppos += cnt; return cnt; } static const struct file_operations trace_options_core_fops = { .open = tracing_open_generic, .read = trace_options_core_read, .write = trace_options_core_write, .llseek = generic_file_llseek, }; struct dentry *trace_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { struct dentry *ret; ret = tracefs_create_file(name, mode, parent, data, fops); if (!ret) pr_warn("Could not create tracefs '%s' entry\n", name); return ret; } static struct dentry *trace_options_init_dentry(struct trace_array *tr) { struct dentry *d_tracer; if (tr->options) return tr->options; d_tracer = tracing_get_dentry(tr); if (IS_ERR(d_tracer)) return NULL; tr->options = tracefs_create_dir("options", d_tracer); if (!tr->options) { pr_warn("Could not create tracefs directory 'options'\n"); return NULL; } return tr->options; } static void create_trace_option_file(struct trace_array *tr, struct trace_option_dentry *topt, struct tracer_flags *flags, struct tracer_opt *opt) { struct dentry *t_options; t_options = trace_options_init_dentry(tr); if (!t_options) return; topt->flags = flags; topt->opt = opt; topt->tr = tr; topt->entry = trace_create_file(opt->name, TRACE_MODE_WRITE, t_options, topt, &trace_options_fops); } static void create_trace_option_files(struct trace_array *tr, struct tracer *tracer) { struct trace_option_dentry *topts; struct trace_options *tr_topts; struct tracer_flags *flags; struct tracer_opt *opts; int cnt; int i; if (!tracer) return; flags = tracer->flags; if (!flags || !flags->opts) return; /* * If this is an instance, only create flags for tracers * the instance may have. */ if (!trace_ok_for_array(tracer, tr)) return; for (i = 0; i < tr->nr_topts; i++) { /* Make sure there's no duplicate flags. */ if (WARN_ON_ONCE(tr->topts[i].tracer->flags == tracer->flags)) return; } opts = flags->opts; for (cnt = 0; opts[cnt].name; cnt++) ; topts = kcalloc(cnt + 1, sizeof(*topts), GFP_KERNEL); if (!topts) return; tr_topts = krealloc(tr->topts, sizeof(*tr->topts) * (tr->nr_topts + 1), GFP_KERNEL); if (!tr_topts) { kfree(topts); return; } tr->topts = tr_topts; tr->topts[tr->nr_topts].tracer = tracer; tr->topts[tr->nr_topts].topts = topts; tr->nr_topts++; for (cnt = 0; opts[cnt].name; cnt++) { create_trace_option_file(tr, &topts[cnt], flags, &opts[cnt]); MEM_FAIL(topts[cnt].entry == NULL, "Failed to create trace option: %s", opts[cnt].name); } } static struct dentry * create_trace_option_core_file(struct trace_array *tr, const char *option, long index) { struct dentry *t_options; t_options = trace_options_init_dentry(tr); if (!t_options) return NULL; return trace_create_file(option, TRACE_MODE_WRITE, t_options, (void *)&tr->trace_flags_index[index], &trace_options_core_fops); } static void create_trace_options_dir(struct trace_array *tr) { struct dentry *t_options; bool top_level = tr == &global_trace; int i; t_options = trace_options_init_dentry(tr); if (!t_options) return; for (i = 0; trace_options[i]; i++) { if (top_level || !((1 << i) & TOP_LEVEL_TRACE_FLAGS)) create_trace_option_core_file(tr, trace_options[i], i); } } static ssize_t rb_simple_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; char buf[64]; int r; r = tracer_tracing_is_on(tr); r = sprintf(buf, "%d\n", r); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static ssize_t rb_simple_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; struct trace_buffer *buffer = tr->array_buffer.buffer; unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; if (buffer) { guard(mutex)(&trace_types_lock); if (!!val == tracer_tracing_is_on(tr)) { val = 0; /* do nothing */ } else if (val) { tracer_tracing_on(tr); if (tr->current_trace->start) tr->current_trace->start(tr); } else { tracer_tracing_off(tr); if (tr->current_trace->stop) tr->current_trace->stop(tr); /* Wake up any waiters */ ring_buffer_wake_waiters(buffer, RING_BUFFER_ALL_CPUS); } } (*ppos)++; return cnt; } static const struct file_operations rb_simple_fops = { .open = tracing_open_generic_tr, .read = rb_simple_read, .write = rb_simple_write, .release = tracing_release_generic_tr, .llseek = default_llseek, }; static ssize_t buffer_percent_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; char buf[64]; int r; r = tr->buffer_percent; r = sprintf(buf, "%d\n", r); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static ssize_t buffer_percent_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; unsigned long val; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; if (val > 100) return -EINVAL; tr->buffer_percent = val; (*ppos)++; return cnt; } static const struct file_operations buffer_percent_fops = { .open = tracing_open_generic_tr, .read = buffer_percent_read, .write = buffer_percent_write, .release = tracing_release_generic_tr, .llseek = default_llseek, }; static ssize_t buffer_subbuf_size_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; size_t size; char buf[64]; int order; int r; order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); size = (PAGE_SIZE << order) / 1024; r = sprintf(buf, "%zd\n", size); return simple_read_from_buffer(ubuf, cnt, ppos, buf, r); } static ssize_t buffer_subbuf_size_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { struct trace_array *tr = filp->private_data; unsigned long val; int old_order; int order; int pages; int ret; ret = kstrtoul_from_user(ubuf, cnt, 10, &val); if (ret) return ret; val *= 1024; /* value passed in is in KB */ pages = DIV_ROUND_UP(val, PAGE_SIZE); order = fls(pages - 1); /* limit between 1 and 128 system pages */ if (order < 0 || order > 7) return -EINVAL; /* Do not allow tracing while changing the order of the ring buffer */ tracing_stop_tr(tr); old_order = ring_buffer_subbuf_order_get(tr->array_buffer.buffer); if (old_order == order) goto out; ret = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, order); if (ret) goto out; #ifdef CONFIG_TRACER_MAX_TRACE if (!tr->allocated_snapshot) goto out_max; ret = ring_buffer_subbuf_order_set(tr->max_buffer.buffer, order); if (ret) { /* Put back the old order */ cnt = ring_buffer_subbuf_order_set(tr->array_buffer.buffer, old_order); if (WARN_ON_ONCE(cnt)) { /* * AARGH! We are left with different orders! * The max buffer is our "snapshot" buffer. * When a tracer needs a snapshot (one of the * latency tracers), it swaps the max buffer * with the saved snap shot. We succeeded to * update the order of the main buffer, but failed to * update the order of the max buffer. But when we tried * to reset the main buffer to the original size, we * failed there too. This is very unlikely to * happen, but if it does, warn and kill all * tracing. */ tracing_disabled = 1; } goto out; } out_max: #endif (*ppos)++; out: if (ret) cnt = ret; tracing_start_tr(tr); return cnt; } static const struct file_operations buffer_subbuf_size_fops = { .open = tracing_open_generic_tr, .read = buffer_subbuf_size_read, .write = buffer_subbuf_size_write, .release = tracing_release_generic_tr, .llseek = default_llseek, }; static struct dentry *trace_instance_dir; static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer); #ifdef CONFIG_MODULES static int make_mod_delta(struct module *mod, void *data) { struct trace_module_delta *module_delta; struct trace_scratch *tscratch; struct trace_mod_entry *entry; struct trace_array *tr = data; int i; tscratch = tr->scratch; module_delta = READ_ONCE(tr->module_delta); for (i = 0; i < tscratch->nr_entries; i++) { entry = &tscratch->entries[i]; if (strcmp(mod->name, entry->mod_name)) continue; if (mod->state == MODULE_STATE_GOING) module_delta->delta[i] = 0; else module_delta->delta[i] = (unsigned long)mod->mem[MOD_TEXT].base - entry->mod_addr; break; } return 0; } #else static int make_mod_delta(struct module *mod, void *data) { return 0; } #endif static int mod_addr_comp(const void *a, const void *b, const void *data) { const struct trace_mod_entry *e1 = a; const struct trace_mod_entry *e2 = b; return e1->mod_addr > e2->mod_addr ? 1 : -1; } static void setup_trace_scratch(struct trace_array *tr, struct trace_scratch *tscratch, unsigned int size) { struct trace_module_delta *module_delta; struct trace_mod_entry *entry; int i, nr_entries; if (!tscratch) return; tr->scratch = tscratch; tr->scratch_size = size; if (tscratch->text_addr) tr->text_delta = (unsigned long)_text - tscratch->text_addr; if (struct_size(tscratch, entries, tscratch->nr_entries) > size) goto reset; /* Check if each module name is a valid string */ for (i = 0; i < tscratch->nr_entries; i++) { int n; entry = &tscratch->entries[i]; for (n = 0; n < MODULE_NAME_LEN; n++) { if (entry->mod_name[n] == '\0') break; if (!isprint(entry->mod_name[n])) goto reset; } if (n == MODULE_NAME_LEN) goto reset; } /* Sort the entries so that we can find appropriate module from address. */ nr_entries = tscratch->nr_entries; sort_r(tscratch->entries, nr_entries, sizeof(struct trace_mod_entry), mod_addr_comp, NULL, NULL); if (IS_ENABLED(CONFIG_MODULES)) { module_delta = kzalloc(struct_size(module_delta, delta, nr_entries), GFP_KERNEL); if (!module_delta) { pr_info("module_delta allocation failed. Not able to decode module address."); goto reset; } init_rcu_head(&module_delta->rcu); } else module_delta = NULL; WRITE_ONCE(tr->module_delta, module_delta); /* Scan modules to make text delta for modules. */ module_for_each_mod(make_mod_delta, tr); /* Set trace_clock as the same of the previous boot. */ if (tscratch->clock_id != tr->clock_id) { if (tscratch->clock_id >= ARRAY_SIZE(trace_clocks) || tracing_set_clock(tr, trace_clocks[tscratch->clock_id].name) < 0) { pr_info("the previous trace_clock info is not valid."); goto reset; } } return; reset: /* Invalid trace modules */ memset(tscratch, 0, size); } static int allocate_trace_buffer(struct trace_array *tr, struct array_buffer *buf, int size) { enum ring_buffer_flags rb_flags; struct trace_scratch *tscratch; unsigned int scratch_size = 0; rb_flags = tr->trace_flags & TRACE_ITER_OVERWRITE ? RB_FL_OVERWRITE : 0; buf->tr = tr; if (tr->range_addr_start && tr->range_addr_size) { /* Add scratch buffer to handle 128 modules */ buf->buffer = ring_buffer_alloc_range(size, rb_flags, 0, tr->range_addr_start, tr->range_addr_size, struct_size(tscratch, entries, 128)); tscratch = ring_buffer_meta_scratch(buf->buffer, &scratch_size); setup_trace_scratch(tr, tscratch, scratch_size); /* * This is basically the same as a mapped buffer, * with the same restrictions. */ tr->mapped++; } else { buf->buffer = ring_buffer_alloc(size, rb_flags); } if (!buf->buffer) return -ENOMEM; buf->data = alloc_percpu(struct trace_array_cpu); if (!buf->data) { ring_buffer_free(buf->buffer); buf->buffer = NULL; return -ENOMEM; } /* Allocate the first page for all buffers */ set_buffer_entries(&tr->array_buffer, ring_buffer_size(tr->array_buffer.buffer, 0)); return 0; } static void free_trace_buffer(struct array_buffer *buf) { if (buf->buffer) { ring_buffer_free(buf->buffer); buf->buffer = NULL; free_percpu(buf->data); buf->data = NULL; } } static int allocate_trace_buffers(struct trace_array *tr, int size) { int ret; ret = allocate_trace_buffer(tr, &tr->array_buffer, size); if (ret) return ret; #ifdef CONFIG_TRACER_MAX_TRACE /* Fix mapped buffer trace arrays do not have snapshot buffers */ if (tr->range_addr_start) return 0; ret = allocate_trace_buffer(tr, &tr->max_buffer, allocate_snapshot ? size : 1); if (MEM_FAIL(ret, "Failed to allocate trace buffer\n")) { free_trace_buffer(&tr->array_buffer); return -ENOMEM; } tr->allocated_snapshot = allocate_snapshot; allocate_snapshot = false; #endif return 0; } static void free_trace_buffers(struct trace_array *tr) { if (!tr) return; free_trace_buffer(&tr->array_buffer); kfree(tr->module_delta); #ifdef CONFIG_TRACER_MAX_TRACE free_trace_buffer(&tr->max_buffer); #endif } static void init_trace_flags_index(struct trace_array *tr) { int i; /* Used by the trace options files */ for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) tr->trace_flags_index[i] = i; } static void __update_tracer_options(struct trace_array *tr) { struct tracer *t; for (t = trace_types; t; t = t->next) add_tracer_options(tr, t); } static void update_tracer_options(struct trace_array *tr) { guard(mutex)(&trace_types_lock); tracer_options_updated = true; __update_tracer_options(tr); } /* Must have trace_types_lock held */ struct trace_array *trace_array_find(const char *instance) { struct trace_array *tr, *found = NULL; list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (tr->name && strcmp(tr->name, instance) == 0) { found = tr; break; } } return found; } struct trace_array *trace_array_find_get(const char *instance) { struct trace_array *tr; guard(mutex)(&trace_types_lock); tr = trace_array_find(instance); if (tr) tr->ref++; return tr; } static int trace_array_create_dir(struct trace_array *tr) { int ret; tr->dir = tracefs_create_dir(tr->name, trace_instance_dir); if (!tr->dir) return -EINVAL; ret = event_trace_add_tracer(tr->dir, tr); if (ret) { tracefs_remove(tr->dir); return ret; } init_tracer_tracefs(tr, tr->dir); __update_tracer_options(tr); return ret; } static struct trace_array * trace_array_create_systems(const char *name, const char *systems, unsigned long range_addr_start, unsigned long range_addr_size) { struct trace_array *tr; int ret; ret = -ENOMEM; tr = kzalloc(sizeof(*tr), GFP_KERNEL); if (!tr) return ERR_PTR(ret); tr->name = kstrdup(name, GFP_KERNEL); if (!tr->name) goto out_free_tr; if (!alloc_cpumask_var(&tr->tracing_cpumask, GFP_KERNEL)) goto out_free_tr; if (!zalloc_cpumask_var(&tr->pipe_cpumask, GFP_KERNEL)) goto out_free_tr; if (systems) { tr->system_names = kstrdup_const(systems, GFP_KERNEL); if (!tr->system_names) goto out_free_tr; } /* Only for boot up memory mapped ring buffers */ tr->range_addr_start = range_addr_start; tr->range_addr_size = range_addr_size; tr->trace_flags = global_trace.trace_flags & ~ZEROED_TRACE_FLAGS; cpumask_copy(tr->tracing_cpumask, cpu_all_mask); raw_spin_lock_init(&tr->start_lock); tr->max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; #ifdef CONFIG_TRACER_MAX_TRACE spin_lock_init(&tr->snapshot_trigger_lock); #endif tr->current_trace = &nop_trace; INIT_LIST_HEAD(&tr->systems); INIT_LIST_HEAD(&tr->events); INIT_LIST_HEAD(&tr->hist_vars); INIT_LIST_HEAD(&tr->err_log); INIT_LIST_HEAD(&tr->marker_list); #ifdef CONFIG_MODULES INIT_LIST_HEAD(&tr->mod_events); #endif if (allocate_trace_buffers(tr, trace_buf_size) < 0) goto out_free_tr; /* The ring buffer is defaultly expanded */ trace_set_ring_buffer_expanded(tr); if (ftrace_allocate_ftrace_ops(tr) < 0) goto out_free_tr; ftrace_init_trace_array(tr); init_trace_flags_index(tr); if (trace_instance_dir) { ret = trace_array_create_dir(tr); if (ret) goto out_free_tr; } else __trace_early_add_events(tr); list_add(&tr->list, &ftrace_trace_arrays); tr->ref++; return tr; out_free_tr: ftrace_free_ftrace_ops(tr); free_trace_buffers(tr); free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); kfree_const(tr->system_names); kfree(tr->range_name); kfree(tr->name); kfree(tr); return ERR_PTR(ret); } static struct trace_array *trace_array_create(const char *name) { return trace_array_create_systems(name, NULL, 0, 0); } static int instance_mkdir(const char *name) { struct trace_array *tr; int ret; guard(mutex)(&event_mutex); guard(mutex)(&trace_types_lock); ret = -EEXIST; if (trace_array_find(name)) return -EEXIST; tr = trace_array_create(name); ret = PTR_ERR_OR_ZERO(tr); return ret; } #ifdef CONFIG_MMU static u64 map_pages(unsigned long start, unsigned long size) { unsigned long vmap_start, vmap_end; struct vm_struct *area; int ret; area = get_vm_area(size, VM_IOREMAP); if (!area) return 0; vmap_start = (unsigned long) area->addr; vmap_end = vmap_start + size; ret = vmap_page_range(vmap_start, vmap_end, start, pgprot_nx(PAGE_KERNEL)); if (ret < 0) { free_vm_area(area); return 0; } return (u64)vmap_start; } #else static inline u64 map_pages(unsigned long start, unsigned long size) { return 0; } #endif /** * trace_array_get_by_name - Create/Lookup a trace array, given its name. * @name: The name of the trace array to be looked up/created. * @systems: A list of systems to create event directories for (NULL for all) * * Returns pointer to trace array with given name. * NULL, if it cannot be created. * * NOTE: This function increments the reference counter associated with the * trace array returned. This makes sure it cannot be freed while in use. * Use trace_array_put() once the trace array is no longer needed. * If the trace_array is to be freed, trace_array_destroy() needs to * be called after the trace_array_put(), or simply let user space delete * it from the tracefs instances directory. But until the * trace_array_put() is called, user space can not delete it. * */ struct trace_array *trace_array_get_by_name(const char *name, const char *systems) { struct trace_array *tr; guard(mutex)(&event_mutex); guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (tr->name && strcmp(tr->name, name) == 0) { tr->ref++; return tr; } } tr = trace_array_create_systems(name, systems, 0, 0); if (IS_ERR(tr)) tr = NULL; else tr->ref++; return tr; } EXPORT_SYMBOL_GPL(trace_array_get_by_name); static int __remove_instance(struct trace_array *tr) { int i; /* Reference counter for a newly created trace array = 1. */ if (tr->ref > 1 || (tr->current_trace && tr->trace_ref)) return -EBUSY; list_del(&tr->list); /* Disable all the flags that were enabled coming in */ for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) { if ((1 << i) & ZEROED_TRACE_FLAGS) set_tracer_flag(tr, 1 << i, 0); } if (printk_trace == tr) update_printk_trace(&global_trace); if (update_marker_trace(tr, 0)) synchronize_rcu(); tracing_set_nop(tr); clear_ftrace_function_probes(tr); event_trace_del_tracer(tr); ftrace_clear_pids(tr); ftrace_destroy_function_files(tr); tracefs_remove(tr->dir); free_percpu(tr->last_func_repeats); free_trace_buffers(tr); clear_tracing_err_log(tr); if (tr->range_name) { reserve_mem_release_by_name(tr->range_name); kfree(tr->range_name); } for (i = 0; i < tr->nr_topts; i++) { kfree(tr->topts[i].topts); } kfree(tr->topts); free_cpumask_var(tr->pipe_cpumask); free_cpumask_var(tr->tracing_cpumask); kfree_const(tr->system_names); kfree(tr->name); kfree(tr); return 0; } int trace_array_destroy(struct trace_array *this_tr) { struct trace_array *tr; if (!this_tr) return -EINVAL; guard(mutex)(&event_mutex); guard(mutex)(&trace_types_lock); /* Making sure trace array exists before destroying it. */ list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (tr == this_tr) return __remove_instance(tr); } return -ENODEV; } EXPORT_SYMBOL_GPL(trace_array_destroy); static int instance_rmdir(const char *name) { struct trace_array *tr; guard(mutex)(&event_mutex); guard(mutex)(&trace_types_lock); tr = trace_array_find(name); if (!tr) return -ENODEV; return __remove_instance(tr); } static __init void create_trace_instances(struct dentry *d_tracer) { struct trace_array *tr; trace_instance_dir = tracefs_create_instance_dir("instances", d_tracer, instance_mkdir, instance_rmdir); if (MEM_FAIL(!trace_instance_dir, "Failed to create instances directory\n")) return; guard(mutex)(&event_mutex); guard(mutex)(&trace_types_lock); list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (!tr->name) continue; if (MEM_FAIL(trace_array_create_dir(tr) < 0, "Failed to create instance directory\n")) return; } } static void init_tracer_tracefs(struct trace_array *tr, struct dentry *d_tracer) { int cpu; trace_create_file("available_tracers", TRACE_MODE_READ, d_tracer, tr, &show_traces_fops); trace_create_file("current_tracer", TRACE_MODE_WRITE, d_tracer, tr, &set_tracer_fops); trace_create_file("tracing_cpumask", TRACE_MODE_WRITE, d_tracer, tr, &tracing_cpumask_fops); trace_create_file("trace_options", TRACE_MODE_WRITE, d_tracer, tr, &tracing_iter_fops); trace_create_file("trace", TRACE_MODE_WRITE, d_tracer, tr, &tracing_fops); trace_create_file("trace_pipe", TRACE_MODE_READ, d_tracer, tr, &tracing_pipe_fops); trace_create_file("buffer_size_kb", TRACE_MODE_WRITE, d_tracer, tr, &tracing_entries_fops); trace_create_file("buffer_total_size_kb", TRACE_MODE_READ, d_tracer, tr, &tracing_total_entries_fops); trace_create_file("free_buffer", 0200, d_tracer, tr, &tracing_free_buffer_fops); trace_create_file("trace_marker", 0220, d_tracer, tr, &tracing_mark_fops); tr->trace_marker_file = __find_event_file(tr, "ftrace", "print"); trace_create_file("trace_marker_raw", 0220, d_tracer, tr, &tracing_mark_raw_fops); trace_create_file("trace_clock", TRACE_MODE_WRITE, d_tracer, tr, &trace_clock_fops); trace_create_file("tracing_on", TRACE_MODE_WRITE, d_tracer, tr, &rb_simple_fops); trace_create_file("timestamp_mode", TRACE_MODE_READ, d_tracer, tr, &trace_time_stamp_mode_fops); tr->buffer_percent = 50; trace_create_file("buffer_percent", TRACE_MODE_WRITE, d_tracer, tr, &buffer_percent_fops); trace_create_file("buffer_subbuf_size_kb", TRACE_MODE_WRITE, d_tracer, tr, &buffer_subbuf_size_fops); create_trace_options_dir(tr); #ifdef CONFIG_TRACER_MAX_TRACE trace_create_maxlat_file(tr, d_tracer); #endif if (ftrace_create_function_files(tr, d_tracer)) MEM_FAIL(1, "Could not allocate function filter files"); if (tr->range_addr_start) { trace_create_file("last_boot_info", TRACE_MODE_READ, d_tracer, tr, &last_boot_fops); #ifdef CONFIG_TRACER_SNAPSHOT } else { trace_create_file("snapshot", TRACE_MODE_WRITE, d_tracer, tr, &snapshot_fops); #endif } trace_create_file("error_log", TRACE_MODE_WRITE, d_tracer, tr, &tracing_err_log_fops); for_each_tracing_cpu(cpu) tracing_init_tracefs_percpu(tr, cpu); ftrace_init_tracefs(tr, d_tracer); } #ifdef CONFIG_TRACEFS_AUTOMOUNT_DEPRECATED static struct vfsmount *trace_automount(struct dentry *mntpt, void *ingore) { struct vfsmount *mnt; struct file_system_type *type; struct fs_context *fc; int ret; /* * To maintain backward compatibility for tools that mount * debugfs to get to the tracing facility, tracefs is automatically * mounted to the debugfs/tracing directory. */ type = get_fs_type("tracefs"); if (!type) return NULL; fc = fs_context_for_submount(type, mntpt); put_filesystem(type); if (IS_ERR(fc)) return ERR_CAST(fc); pr_warn("NOTICE: Automounting of tracing to debugfs is deprecated and will be removed in 2030\n"); ret = vfs_parse_fs_string(fc, "source", "tracefs", strlen("tracefs")); if (!ret) mnt = fc_mount(fc); else mnt = ERR_PTR(ret); put_fs_context(fc); return mnt; } #endif /** * tracing_init_dentry - initialize top level trace array * * This is called when creating files or directories in the tracing * directory. It is called via fs_initcall() by any of the boot up code * and expects to return the dentry of the top level tracing directory. */ int tracing_init_dentry(void) { struct trace_array *tr = &global_trace; if (security_locked_down(LOCKDOWN_TRACEFS)) { pr_warn("Tracing disabled due to lockdown\n"); return -EPERM; } /* The top level trace array uses NULL as parent */ if (tr->dir) return 0; if (WARN_ON(!tracefs_initialized())) return -ENODEV; #ifdef CONFIG_TRACEFS_AUTOMOUNT_DEPRECATED /* * As there may still be users that expect the tracing * files to exist in debugfs/tracing, we must automount * the tracefs file system there, so older tools still * work with the newer kernel. */ tr->dir = debugfs_create_automount("tracing", NULL, trace_automount, NULL); #endif return 0; } extern struct trace_eval_map *__start_ftrace_eval_maps[]; extern struct trace_eval_map *__stop_ftrace_eval_maps[]; static struct workqueue_struct *eval_map_wq __initdata; static struct work_struct eval_map_work __initdata; static struct work_struct tracerfs_init_work __initdata; static void __init eval_map_work_func(struct work_struct *work) { int len; len = __stop_ftrace_eval_maps - __start_ftrace_eval_maps; trace_event_update_with_eval_map(NULL, __start_ftrace_eval_maps, len); } static int __init trace_eval_init(void) { INIT_WORK(&eval_map_work, eval_map_work_func); eval_map_wq = alloc_workqueue("eval_map_wq", WQ_UNBOUND, 0); if (!eval_map_wq) { pr_err("Unable to allocate eval_map_wq\n"); /* Do work here */ eval_map_work_func(&eval_map_work); return -ENOMEM; } queue_work(eval_map_wq, &eval_map_work); return 0; } subsys_initcall(trace_eval_init); static int __init trace_eval_sync(void) { /* Make sure the eval map updates are finished */ if (eval_map_wq) destroy_workqueue(eval_map_wq); return 0; } late_initcall_sync(trace_eval_sync); #ifdef CONFIG_MODULES bool module_exists(const char *module) { /* All modules have the symbol __this_module */ static const char this_mod[] = "__this_module"; char modname[MODULE_NAME_LEN + sizeof(this_mod) + 2]; unsigned long val; int n; n = snprintf(modname, sizeof(modname), "%s:%s", module, this_mod); if (n > sizeof(modname) - 1) return false; val = module_kallsyms_lookup_name(modname); return val != 0; } static void trace_module_add_evals(struct module *mod) { /* * Modules with bad taint do not have events created, do * not bother with enums either. */ if (trace_module_has_bad_taint(mod)) return; /* Even if no trace_evals, this need to sanitize field types. */ trace_event_update_with_eval_map(mod, mod->trace_evals, mod->num_trace_evals); } #ifdef CONFIG_TRACE_EVAL_MAP_FILE static void trace_module_remove_evals(struct module *mod) { union trace_eval_map_item *map; union trace_eval_map_item **last = &trace_eval_maps; if (!mod->num_trace_evals) return; guard(mutex)(&trace_eval_mutex); map = trace_eval_maps; while (map) { if (map->head.mod == mod) break; map = trace_eval_jmp_to_tail(map); last = &map->tail.next; map = map->tail.next; } if (!map) return; *last = trace_eval_jmp_to_tail(map)->tail.next; kfree(map); } #else static inline void trace_module_remove_evals(struct module *mod) { } #endif /* CONFIG_TRACE_EVAL_MAP_FILE */ static void trace_module_record(struct module *mod, bool add) { struct trace_array *tr; unsigned long flags; list_for_each_entry(tr, &ftrace_trace_arrays, list) { flags = tr->flags & (TRACE_ARRAY_FL_BOOT | TRACE_ARRAY_FL_LAST_BOOT); /* Update any persistent trace array that has already been started */ if (flags == TRACE_ARRAY_FL_BOOT && add) { guard(mutex)(&scratch_mutex); save_mod(mod, tr); } else if (flags & TRACE_ARRAY_FL_LAST_BOOT) { /* Update delta if the module loaded in previous boot */ make_mod_delta(mod, tr); } } } static int trace_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; switch (val) { case MODULE_STATE_COMING: trace_module_add_evals(mod); trace_module_record(mod, true); break; case MODULE_STATE_GOING: trace_module_remove_evals(mod); trace_module_record(mod, false); break; } return NOTIFY_OK; } static struct notifier_block trace_module_nb = { .notifier_call = trace_module_notify, .priority = 0, }; #endif /* CONFIG_MODULES */ static __init void tracer_init_tracefs_work_func(struct work_struct *work) { event_trace_init(); init_tracer_tracefs(&global_trace, NULL); ftrace_init_tracefs_toplevel(&global_trace, NULL); trace_create_file("tracing_thresh", TRACE_MODE_WRITE, NULL, &global_trace, &tracing_thresh_fops); trace_create_file("README", TRACE_MODE_READ, NULL, NULL, &tracing_readme_fops); trace_create_file("saved_cmdlines", TRACE_MODE_READ, NULL, NULL, &tracing_saved_cmdlines_fops); trace_create_file("saved_cmdlines_size", TRACE_MODE_WRITE, NULL, NULL, &tracing_saved_cmdlines_size_fops); trace_create_file("saved_tgids", TRACE_MODE_READ, NULL, NULL, &tracing_saved_tgids_fops); trace_create_eval_file(NULL); #ifdef CONFIG_MODULES register_module_notifier(&trace_module_nb); #endif #ifdef CONFIG_DYNAMIC_FTRACE trace_create_file("dyn_ftrace_total_info", TRACE_MODE_READ, NULL, NULL, &tracing_dyn_info_fops); #endif create_trace_instances(NULL); update_tracer_options(&global_trace); } static __init int tracer_init_tracefs(void) { int ret; trace_access_lock_init(); ret = tracing_init_dentry(); if (ret) return 0; if (eval_map_wq) { INIT_WORK(&tracerfs_init_work, tracer_init_tracefs_work_func); queue_work(eval_map_wq, &tracerfs_init_work); } else { tracer_init_tracefs_work_func(NULL); } rv_init_interface(); return 0; } fs_initcall(tracer_init_tracefs); static int trace_die_panic_handler(struct notifier_block *self, unsigned long ev, void *unused); static struct notifier_block trace_panic_notifier = { .notifier_call = trace_die_panic_handler, .priority = INT_MAX - 1, }; static struct notifier_block trace_die_notifier = { .notifier_call = trace_die_panic_handler, .priority = INT_MAX - 1, }; /* * The idea is to execute the following die/panic callback early, in order * to avoid showing irrelevant information in the trace (like other panic * notifier functions); we are the 2nd to run, after hung_task/rcu_stall * warnings get disabled (to prevent potential log flooding). */ static int trace_die_panic_handler(struct notifier_block *self, unsigned long ev, void *unused) { if (!ftrace_dump_on_oops_enabled()) return NOTIFY_DONE; /* The die notifier requires DIE_OOPS to trigger */ if (self == &trace_die_notifier && ev != DIE_OOPS) return NOTIFY_DONE; ftrace_dump(DUMP_PARAM); return NOTIFY_DONE; } /* * printk is set to max of 1024, we really don't need it that big. * Nothing should be printing 1000 characters anyway. */ #define TRACE_MAX_PRINT 1000 /* * Define here KERN_TRACE so that we have one place to modify * it if we decide to change what log level the ftrace dump * should be at. */ #define KERN_TRACE KERN_EMERG void trace_printk_seq(struct trace_seq *s) { /* Probably should print a warning here. */ if (s->seq.len >= TRACE_MAX_PRINT) s->seq.len = TRACE_MAX_PRINT; /* * More paranoid code. Although the buffer size is set to * PAGE_SIZE, and TRACE_MAX_PRINT is 1000, this is just * an extra layer of protection. */ if (WARN_ON_ONCE(s->seq.len >= s->seq.size)) s->seq.len = s->seq.size - 1; /* should be zero ended, but we are paranoid. */ s->buffer[s->seq.len] = 0; printk(KERN_TRACE "%s", s->buffer); trace_seq_init(s); } static void trace_init_iter(struct trace_iterator *iter, struct trace_array *tr) { iter->tr = tr; iter->trace = iter->tr->current_trace; iter->cpu_file = RING_BUFFER_ALL_CPUS; iter->array_buffer = &tr->array_buffer; if (iter->trace && iter->trace->open) iter->trace->open(iter); /* Annotate start of buffers if we had overruns */ if (ring_buffer_overruns(iter->array_buffer->buffer)) iter->iter_flags |= TRACE_FILE_ANNOTATE; /* Output in nanoseconds only if we are using a clock in nanoseconds. */ if (trace_clocks[iter->tr->clock_id].in_ns) iter->iter_flags |= TRACE_FILE_TIME_IN_NS; /* Can not use kmalloc for iter.temp and iter.fmt */ iter->temp = static_temp_buf; iter->temp_size = STATIC_TEMP_BUF_SIZE; iter->fmt = static_fmt_buf; iter->fmt_size = STATIC_FMT_BUF_SIZE; } void trace_init_global_iter(struct trace_iterator *iter) { trace_init_iter(iter, &global_trace); } static void ftrace_dump_one(struct trace_array *tr, enum ftrace_dump_mode dump_mode) { /* use static because iter can be a bit big for the stack */ static struct trace_iterator iter; unsigned int old_userobj; unsigned long flags; int cnt = 0; /* * Always turn off tracing when we dump. * We don't need to show trace output of what happens * between multiple crashes. * * If the user does a sysrq-z, then they can re-enable * tracing with echo 1 > tracing_on. */ tracer_tracing_off(tr); local_irq_save(flags); /* Simulate the iterator */ trace_init_iter(&iter, tr); /* While dumping, do not allow the buffer to be enable */ tracer_tracing_disable(tr); old_userobj = tr->trace_flags & TRACE_ITER_SYM_USEROBJ; /* don't look at user memory in panic mode */ tr->trace_flags &= ~TRACE_ITER_SYM_USEROBJ; if (dump_mode == DUMP_ORIG) iter.cpu_file = raw_smp_processor_id(); else iter.cpu_file = RING_BUFFER_ALL_CPUS; if (tr == &global_trace) printk(KERN_TRACE "Dumping ftrace buffer:\n"); else printk(KERN_TRACE "Dumping ftrace instance %s buffer:\n", tr->name); /* Did function tracer already get disabled? */ if (ftrace_is_dead()) { printk("# WARNING: FUNCTION TRACING IS CORRUPTED\n"); printk("# MAY BE MISSING FUNCTION EVENTS\n"); } /* * We need to stop all tracing on all CPUS to read * the next buffer. This is a bit expensive, but is * not done often. We fill all what we can read, * and then release the locks again. */ while (!trace_empty(&iter)) { if (!cnt) printk(KERN_TRACE "---------------------------------\n"); cnt++; trace_iterator_reset(&iter); iter.iter_flags |= TRACE_FILE_LAT_FMT; if (trace_find_next_entry_inc(&iter) != NULL) { int ret; ret = print_trace_line(&iter); if (ret != TRACE_TYPE_NO_CONSUME) trace_consume(&iter); trace_printk_seq(&iter.seq); } touch_nmi_watchdog(); } if (!cnt) printk(KERN_TRACE " (ftrace buffer empty)\n"); else printk(KERN_TRACE "---------------------------------\n"); tr->trace_flags |= old_userobj; tracer_tracing_enable(tr); local_irq_restore(flags); } static void ftrace_dump_by_param(void) { bool first_param = true; char dump_param[MAX_TRACER_SIZE]; char *buf, *token, *inst_name; struct trace_array *tr; strscpy(dump_param, ftrace_dump_on_oops, MAX_TRACER_SIZE); buf = dump_param; while ((token = strsep(&buf, ",")) != NULL) { if (first_param) { first_param = false; if (!strcmp("0", token)) continue; else if (!strcmp("1", token)) { ftrace_dump_one(&global_trace, DUMP_ALL); continue; } else if (!strcmp("2", token) || !strcmp("orig_cpu", token)) { ftrace_dump_one(&global_trace, DUMP_ORIG); continue; } } inst_name = strsep(&token, "="); tr = trace_array_find(inst_name); if (!tr) { printk(KERN_TRACE "Instance %s not found\n", inst_name); continue; } if (token && (!strcmp("2", token) || !strcmp("orig_cpu", token))) ftrace_dump_one(tr, DUMP_ORIG); else ftrace_dump_one(tr, DUMP_ALL); } } void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { static atomic_t dump_running; /* Only allow one dump user at a time. */ if (atomic_inc_return(&dump_running) != 1) { atomic_dec(&dump_running); return; } switch (oops_dump_mode) { case DUMP_ALL: ftrace_dump_one(&global_trace, DUMP_ALL); break; case DUMP_ORIG: ftrace_dump_one(&global_trace, DUMP_ORIG); break; case DUMP_PARAM: ftrace_dump_by_param(); break; case DUMP_NONE: break; default: printk(KERN_TRACE "Bad dumping mode, switching to all CPUs dump\n"); ftrace_dump_one(&global_trace, DUMP_ALL); } atomic_dec(&dump_running); } EXPORT_SYMBOL_GPL(ftrace_dump); #define WRITE_BUFSIZE 4096 ssize_t trace_parse_run_command(struct file *file, const char __user *buffer, size_t count, loff_t *ppos, int (*createfn)(const char *)) { char *kbuf __free(kfree) = NULL; char *buf, *tmp; int ret = 0; size_t done = 0; size_t size; kbuf = kmalloc(WRITE_BUFSIZE, GFP_KERNEL); if (!kbuf) return -ENOMEM; while (done < count) { size = count - done; if (size >= WRITE_BUFSIZE) size = WRITE_BUFSIZE - 1; if (copy_from_user(kbuf, buffer + done, size)) return -EFAULT; kbuf[size] = '\0'; buf = kbuf; do { tmp = strchr(buf, '\n'); if (tmp) { *tmp = '\0'; size = tmp - buf + 1; } else { size = strlen(buf); if (done + size < count) { if (buf != kbuf) break; /* This can accept WRITE_BUFSIZE - 2 ('\n' + '\0') */ pr_warn("Line length is too long: Should be less than %d\n", WRITE_BUFSIZE - 2); return -EINVAL; } } done += size; /* Remove comments */ tmp = strchr(buf, '#'); if (tmp) *tmp = '\0'; ret = createfn(buf); if (ret) return ret; buf += size; } while (done < count); } return done; } #ifdef CONFIG_TRACER_MAX_TRACE __init static bool tr_needs_alloc_snapshot(const char *name) { char *test; int len = strlen(name); bool ret; if (!boot_snapshot_index) return false; if (strncmp(name, boot_snapshot_info, len) == 0 && boot_snapshot_info[len] == '\t') return true; test = kmalloc(strlen(name) + 3, GFP_KERNEL); if (!test) return false; sprintf(test, "\t%s\t", name); ret = strstr(boot_snapshot_info, test) == NULL; kfree(test); return ret; } __init static void do_allocate_snapshot(const char *name) { if (!tr_needs_alloc_snapshot(name)) return; /* * When allocate_snapshot is set, the next call to * allocate_trace_buffers() (called by trace_array_get_by_name()) * will allocate the snapshot buffer. That will alse clear * this flag. */ allocate_snapshot = true; } #else static inline void do_allocate_snapshot(const char *name) { } #endif __init static void enable_instances(void) { struct trace_array *tr; bool memmap_area = false; char *curr_str; char *name; char *str; char *tok; /* A tab is always appended */ boot_instance_info[boot_instance_index - 1] = '\0'; str = boot_instance_info; while ((curr_str = strsep(&str, "\t"))) { phys_addr_t start = 0; phys_addr_t size = 0; unsigned long addr = 0; bool traceprintk = false; bool traceoff = false; char *flag_delim; char *addr_delim; char *rname __free(kfree) = NULL; tok = strsep(&curr_str, ","); flag_delim = strchr(tok, '^'); addr_delim = strchr(tok, '@'); if (addr_delim) *addr_delim++ = '\0'; if (flag_delim) *flag_delim++ = '\0'; name = tok; if (flag_delim) { char *flag; while ((flag = strsep(&flag_delim, "^"))) { if (strcmp(flag, "traceoff") == 0) { traceoff = true; } else if ((strcmp(flag, "printk") == 0) || (strcmp(flag, "traceprintk") == 0) || (strcmp(flag, "trace_printk") == 0)) { traceprintk = true; } else { pr_info("Tracing: Invalid instance flag '%s' for %s\n", flag, name); } } } tok = addr_delim; if (tok && isdigit(*tok)) { start = memparse(tok, &tok); if (!start) { pr_warn("Tracing: Invalid boot instance address for %s\n", name); continue; } if (*tok != ':') { pr_warn("Tracing: No size specified for instance %s\n", name); continue; } tok++; size = memparse(tok, &tok); if (!size) { pr_warn("Tracing: Invalid boot instance size for %s\n", name); continue; } memmap_area = true; } else if (tok) { if (!reserve_mem_find_by_name(tok, &start, &size)) { start = 0; pr_warn("Failed to map boot instance %s to %s\n", name, tok); continue; } rname = kstrdup(tok, GFP_KERNEL); } if (start) { /* Start and size must be page aligned */ if (start & ~PAGE_MASK) { pr_warn("Tracing: mapping start addr %pa is not page aligned\n", &start); continue; } if (size & ~PAGE_MASK) { pr_warn("Tracing: mapping size %pa is not page aligned\n", &size); continue; } if (memmap_area) addr = map_pages(start, size); else addr = (unsigned long)phys_to_virt(start); if (addr) { pr_info("Tracing: mapped boot instance %s at physical memory %pa of size 0x%lx\n", name, &start, (unsigned long)size); } else { pr_warn("Tracing: Failed to map boot instance %s\n", name); continue; } } else { /* Only non mapped buffers have snapshot buffers */ if (IS_ENABLED(CONFIG_TRACER_MAX_TRACE)) do_allocate_snapshot(name); } tr = trace_array_create_systems(name, NULL, addr, size); if (IS_ERR(tr)) { pr_warn("Tracing: Failed to create instance buffer %s\n", curr_str); continue; } if (traceoff) tracer_tracing_off(tr); if (traceprintk) update_printk_trace(tr); /* * memmap'd buffers can not be freed. */ if (memmap_area) { tr->flags |= TRACE_ARRAY_FL_MEMMAP; tr->ref++; } if (start) { tr->flags |= TRACE_ARRAY_FL_BOOT | TRACE_ARRAY_FL_LAST_BOOT; tr->range_name = no_free_ptr(rname); } while ((tok = strsep(&curr_str, ","))) { early_enable_events(tr, tok, true); } } } __init static int tracer_alloc_buffers(void) { int ring_buf_size; int ret = -ENOMEM; if (security_locked_down(LOCKDOWN_TRACEFS)) { pr_warn("Tracing disabled due to lockdown\n"); return -EPERM; } /* * Make sure we don't accidentally add more trace options * than we have bits for. */ BUILD_BUG_ON(TRACE_ITER_LAST_BIT > TRACE_FLAGS_MAX_SIZE); if (!alloc_cpumask_var(&tracing_buffer_mask, GFP_KERNEL)) return -ENOMEM; if (!alloc_cpumask_var(&global_trace.tracing_cpumask, GFP_KERNEL)) goto out_free_buffer_mask; /* Only allocate trace_printk buffers if a trace_printk exists */ if (&__stop___trace_bprintk_fmt != &__start___trace_bprintk_fmt) /* Must be called before global_trace.buffer is allocated */ trace_printk_init_buffers(); /* To save memory, keep the ring buffer size to its minimum */ if (global_trace.ring_buffer_expanded) ring_buf_size = trace_buf_size; else ring_buf_size = 1; cpumask_copy(tracing_buffer_mask, cpu_possible_mask); cpumask_copy(global_trace.tracing_cpumask, cpu_all_mask); raw_spin_lock_init(&global_trace.start_lock); /* * The prepare callbacks allocates some memory for the ring buffer. We * don't free the buffer if the CPU goes down. If we were to free * the buffer, then the user would lose any trace that was in the * buffer. The memory will be removed once the "instance" is removed. */ ret = cpuhp_setup_state_multi(CPUHP_TRACE_RB_PREPARE, "trace/RB:prepare", trace_rb_cpu_prepare, NULL); if (ret < 0) goto out_free_cpumask; /* Used for event triggers */ ret = -ENOMEM; temp_buffer = ring_buffer_alloc(PAGE_SIZE, RB_FL_OVERWRITE); if (!temp_buffer) goto out_rm_hp_state; if (trace_create_savedcmd() < 0) goto out_free_temp_buffer; if (!zalloc_cpumask_var(&global_trace.pipe_cpumask, GFP_KERNEL)) goto out_free_savedcmd; /* TODO: make the number of buffers hot pluggable with CPUS */ if (allocate_trace_buffers(&global_trace, ring_buf_size) < 0) { MEM_FAIL(1, "tracer: failed to allocate ring buffer!\n"); goto out_free_pipe_cpumask; } if (global_trace.buffer_disabled) tracing_off(); if (trace_boot_clock) { ret = tracing_set_clock(&global_trace, trace_boot_clock); if (ret < 0) pr_warn("Trace clock %s not defined, going back to default\n", trace_boot_clock); } /* * register_tracer() might reference current_trace, so it * needs to be set before we register anything. This is * just a bootstrap of current_trace anyway. */ global_trace.current_trace = &nop_trace; global_trace.max_lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED; #ifdef CONFIG_TRACER_MAX_TRACE spin_lock_init(&global_trace.snapshot_trigger_lock); #endif ftrace_init_global_array_ops(&global_trace); #ifdef CONFIG_MODULES INIT_LIST_HEAD(&global_trace.mod_events); #endif init_trace_flags_index(&global_trace); register_tracer(&nop_trace); /* Function tracing may start here (via kernel command line) */ init_function_trace(); /* All seems OK, enable tracing */ tracing_disabled = 0; atomic_notifier_chain_register(&panic_notifier_list, &trace_panic_notifier); register_die_notifier(&trace_die_notifier); global_trace.flags = TRACE_ARRAY_FL_GLOBAL; INIT_LIST_HEAD(&global_trace.systems); INIT_LIST_HEAD(&global_trace.events); INIT_LIST_HEAD(&global_trace.hist_vars); INIT_LIST_HEAD(&global_trace.err_log); list_add(&global_trace.marker_list, &marker_copies); list_add(&global_trace.list, &ftrace_trace_arrays); apply_trace_boot_options(); register_snapshot_cmd(); return 0; out_free_pipe_cpumask: free_cpumask_var(global_trace.pipe_cpumask); out_free_savedcmd: trace_free_saved_cmdlines_buffer(); out_free_temp_buffer: ring_buffer_free(temp_buffer); out_rm_hp_state: cpuhp_remove_multi_state(CPUHP_TRACE_RB_PREPARE); out_free_cpumask: free_cpumask_var(global_trace.tracing_cpumask); out_free_buffer_mask: free_cpumask_var(tracing_buffer_mask); return ret; } #ifdef CONFIG_FUNCTION_TRACER /* Used to set module cached ftrace filtering at boot up */ __init struct trace_array *trace_get_global_array(void) { return &global_trace; } #endif void __init ftrace_boot_snapshot(void) { #ifdef CONFIG_TRACER_MAX_TRACE struct trace_array *tr; if (!snapshot_at_boot) return; list_for_each_entry(tr, &ftrace_trace_arrays, list) { if (!tr->allocated_snapshot) continue; tracing_snapshot_instance(tr); trace_array_puts(tr, "** Boot snapshot taken **\n"); } #endif } void __init early_trace_init(void) { if (tracepoint_printk) { tracepoint_print_iter = kzalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL); if (MEM_FAIL(!tracepoint_print_iter, "Failed to allocate trace iterator\n")) tracepoint_printk = 0; else static_key_enable(&tracepoint_printk_key.key); } tracer_alloc_buffers(); init_events(); } void __init trace_init(void) { trace_event_init(); if (boot_instance_index) enable_instances(); } __init static void clear_boot_tracer(void) { /* * The default tracer at boot buffer is an init section. * This function is called in lateinit. If we did not * find the boot tracer, then clear it out, to prevent * later registration from accessing the buffer that is * about to be freed. */ if (!default_bootup_tracer) return; printk(KERN_INFO "ftrace bootup tracer '%s' not registered.\n", default_bootup_tracer); default_bootup_tracer = NULL; } #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK __init static void tracing_set_default_clock(void) { /* sched_clock_stable() is determined in late_initcall */ if (!trace_boot_clock && !sched_clock_stable()) { if (security_locked_down(LOCKDOWN_TRACEFS)) { pr_warn("Can not set tracing clock due to lockdown\n"); return; } printk(KERN_WARNING "Unstable clock detected, switching default tracing clock to \"global\"\n" "If you want to keep using the local clock, then add:\n" " \"trace_clock=local\"\n" "on the kernel command line\n"); tracing_set_clock(&global_trace, "global"); } } #else static inline void tracing_set_default_clock(void) { } #endif __init static int late_trace_init(void) { if (tracepoint_printk && tracepoint_printk_stop_on_boot) { static_key_disable(&tracepoint_printk_key.key); tracepoint_printk = 0; } if (traceoff_after_boot) tracing_off(); tracing_set_default_clock(); clear_boot_tracer(); return 0; } late_initcall_sync(late_trace_init); |
| 449 535 554 116 343 351 350 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_UNALIGNED_H #define __LINUX_UNALIGNED_H /* * This is the most generic implementation of unaligned accesses * and should work almost anywhere. */ #include <linux/unaligned/packed_struct.h> #include <asm/byteorder.h> #include <vdso/unaligned.h> #define get_unaligned(ptr) __get_unaligned_t(typeof(*(ptr)), (ptr)) #define put_unaligned(val, ptr) __put_unaligned_t(typeof(*(ptr)), (val), (ptr)) static inline u16 get_unaligned_le16(const void *p) { return le16_to_cpu(__get_unaligned_t(__le16, p)); } static inline u32 get_unaligned_le32(const void *p) { return le32_to_cpu(__get_unaligned_t(__le32, p)); } static inline u64 get_unaligned_le64(const void *p) { return le64_to_cpu(__get_unaligned_t(__le64, p)); } static inline void put_unaligned_le16(u16 val, void *p) { __put_unaligned_t(__le16, cpu_to_le16(val), p); } static inline void put_unaligned_le32(u32 val, void *p) { __put_unaligned_t(__le32, cpu_to_le32(val), p); } static inline void put_unaligned_le64(u64 val, void *p) { __put_unaligned_t(__le64, cpu_to_le64(val), p); } static inline u16 get_unaligned_be16(const void *p) { return be16_to_cpu(__get_unaligned_t(__be16, p)); } static inline u32 get_unaligned_be32(const void *p) { return be32_to_cpu(__get_unaligned_t(__be32, p)); } static inline u64 get_unaligned_be64(const void *p) { return be64_to_cpu(__get_unaligned_t(__be64, p)); } static inline void put_unaligned_be16(u16 val, void *p) { __put_unaligned_t(__be16, cpu_to_be16(val), p); } static inline void put_unaligned_be32(u32 val, void *p) { __put_unaligned_t(__be32, cpu_to_be32(val), p); } static inline void put_unaligned_be64(u64 val, void *p) { __put_unaligned_t(__be64, cpu_to_be64(val), p); } static inline u32 __get_unaligned_be24(const u8 *p) { return p[0] << 16 | p[1] << 8 | p[2]; } static inline u32 get_unaligned_be24(const void *p) { return __get_unaligned_be24(p); } static inline u32 __get_unaligned_le24(const u8 *p) { return p[0] | p[1] << 8 | p[2] << 16; } static inline u32 get_unaligned_le24(const void *p) { return __get_unaligned_le24(p); } static inline void __put_unaligned_be24(const u32 val, u8 *p) { *p++ = (val >> 16) & 0xff; *p++ = (val >> 8) & 0xff; *p++ = val & 0xff; } static inline void put_unaligned_be24(const u32 val, void *p) { __put_unaligned_be24(val, p); } static inline void __put_unaligned_le24(const u32 val, u8 *p) { *p++ = val & 0xff; *p++ = (val >> 8) & 0xff; *p++ = (val >> 16) & 0xff; } static inline void put_unaligned_le24(const u32 val, void *p) { __put_unaligned_le24(val, p); } static inline void __put_unaligned_be48(const u64 val, u8 *p) { *p++ = (val >> 40) & 0xff; *p++ = (val >> 32) & 0xff; *p++ = (val >> 24) & 0xff; *p++ = (val >> 16) & 0xff; *p++ = (val >> 8) & 0xff; *p++ = val & 0xff; } static inline void put_unaligned_be48(const u64 val, void *p) { __put_unaligned_be48(val, p); } static inline u64 __get_unaligned_be48(const u8 *p) { return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | p[3] << 16 | p[4] << 8 | p[5]; } static inline u64 get_unaligned_be48(const void *p) { return __get_unaligned_be48(p); } #endif /* __LINUX_UNALIGNED_H */ |
| 3 2 1 2 1 2 1 1 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * virtio-fs: Virtio Filesystem * Copyright (C) 2018 Red Hat, Inc. */ #include <linux/fs.h> #include <linux/dax.h> #include <linux/pci.h> #include <linux/interrupt.h> #include <linux/group_cpus.h> #include <linux/memremap.h> #include <linux/module.h> #include <linux/virtio.h> #include <linux/virtio_fs.h> #include <linux/delay.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/highmem.h> #include <linux/cleanup.h> #include <linux/uio.h> #include "fuse_i.h" /* Used to help calculate the FUSE connection's max_pages limit for a request's * size. Parts of the struct fuse_req are sliced into scattergather lists in * addition to the pages used, so this can help account for that overhead. */ #define FUSE_HEADER_OVERHEAD 4 /* List of virtio-fs device instances and a lock for the list. Also provides * mutual exclusion in device removal and mounting path */ static DEFINE_MUTEX(virtio_fs_mutex); static LIST_HEAD(virtio_fs_instances); /* The /sys/fs/virtio_fs/ kset */ static struct kset *virtio_fs_kset; enum { VQ_HIPRIO, VQ_REQUEST }; #define VQ_NAME_LEN 24 /* Per-virtqueue state */ struct virtio_fs_vq { spinlock_t lock; struct virtqueue *vq; /* protected by ->lock */ struct work_struct done_work; struct list_head queued_reqs; struct list_head end_reqs; /* End these requests */ struct work_struct dispatch_work; struct fuse_dev *fud; bool connected; long in_flight; struct completion in_flight_zero; /* No inflight requests */ struct kobject *kobj; char name[VQ_NAME_LEN]; } ____cacheline_aligned_in_smp; /* A virtio-fs device instance */ struct virtio_fs { struct kobject kobj; struct kobject *mqs_kobj; struct list_head list; /* on virtio_fs_instances */ char *tag; struct virtio_fs_vq *vqs; unsigned int nvqs; /* number of virtqueues */ unsigned int num_request_queues; /* number of request queues */ struct dax_device *dax_dev; unsigned int *mq_map; /* index = cpu id, value = request vq id */ /* DAX memory window where file contents are mapped */ void *window_kaddr; phys_addr_t window_phys_addr; size_t window_len; }; struct virtio_fs_forget_req { struct fuse_in_header ih; struct fuse_forget_in arg; }; struct virtio_fs_forget { /* This request can be temporarily queued on virt queue */ struct list_head list; struct virtio_fs_forget_req req; }; struct virtio_fs_req_work { struct fuse_req *req; struct virtio_fs_vq *fsvq; struct work_struct done_work; }; static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, struct fuse_req *req, bool in_flight, gfp_t gfp); static const struct constant_table dax_param_enums[] = { {"always", FUSE_DAX_ALWAYS }, {"never", FUSE_DAX_NEVER }, {"inode", FUSE_DAX_INODE_USER }, {} }; enum { OPT_DAX, OPT_DAX_ENUM, }; static const struct fs_parameter_spec virtio_fs_parameters[] = { fsparam_flag("dax", OPT_DAX), fsparam_enum("dax", OPT_DAX_ENUM, dax_param_enums), {} }; static int virtio_fs_parse_param(struct fs_context *fsc, struct fs_parameter *param) { struct fs_parse_result result; struct fuse_fs_context *ctx = fsc->fs_private; int opt; opt = fs_parse(fsc, virtio_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case OPT_DAX: ctx->dax_mode = FUSE_DAX_ALWAYS; break; case OPT_DAX_ENUM: ctx->dax_mode = result.uint_32; break; default: return -EINVAL; } return 0; } static void virtio_fs_free_fsc(struct fs_context *fsc) { struct fuse_fs_context *ctx = fsc->fs_private; kfree(ctx); } static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq) { struct virtio_fs *fs = vq->vdev->priv; return &fs->vqs[vq->index]; } /* Should be called with fsvq->lock held. */ static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq) { fsvq->in_flight++; } /* Should be called with fsvq->lock held. */ static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq) { WARN_ON(fsvq->in_flight <= 0); fsvq->in_flight--; if (!fsvq->in_flight) complete(&fsvq->in_flight_zero); } static ssize_t tag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct virtio_fs *fs = container_of(kobj, struct virtio_fs, kobj); return sysfs_emit(buf, "%s\n", fs->tag); } static struct kobj_attribute virtio_fs_tag_attr = __ATTR_RO(tag); static struct attribute *virtio_fs_attrs[] = { &virtio_fs_tag_attr.attr, NULL }; ATTRIBUTE_GROUPS(virtio_fs); static void virtio_fs_ktype_release(struct kobject *kobj) { struct virtio_fs *vfs = container_of(kobj, struct virtio_fs, kobj); kfree(vfs->mq_map); kfree(vfs->vqs); kfree(vfs); } static const struct kobj_type virtio_fs_ktype = { .release = virtio_fs_ktype_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = virtio_fs_groups, }; static struct virtio_fs_vq *virtio_fs_kobj_to_vq(struct virtio_fs *fs, struct kobject *kobj) { int i; for (i = 0; i < fs->nvqs; i++) { if (kobj == fs->vqs[i].kobj) return &fs->vqs[i]; } return NULL; } static ssize_t name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct virtio_fs *fs = container_of(kobj->parent->parent, struct virtio_fs, kobj); struct virtio_fs_vq *fsvq = virtio_fs_kobj_to_vq(fs, kobj); if (!fsvq) return -EINVAL; return sysfs_emit(buf, "%s\n", fsvq->name); } static struct kobj_attribute virtio_fs_vq_name_attr = __ATTR_RO(name); static ssize_t cpu_list_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct virtio_fs *fs = container_of(kobj->parent->parent, struct virtio_fs, kobj); struct virtio_fs_vq *fsvq = virtio_fs_kobj_to_vq(fs, kobj); unsigned int cpu, qid; const size_t size = PAGE_SIZE - 1; bool first = true; int ret = 0, pos = 0; if (!fsvq) return -EINVAL; qid = fsvq->vq->index; for (cpu = 0; cpu < nr_cpu_ids; cpu++) { if (qid < VQ_REQUEST || (fs->mq_map[cpu] == qid)) { if (first) ret = snprintf(buf + pos, size - pos, "%u", cpu); else ret = snprintf(buf + pos, size - pos, ", %u", cpu); if (ret >= size - pos) break; first = false; pos += ret; } } ret = snprintf(buf + pos, size + 1 - pos, "\n"); return pos + ret; } static struct kobj_attribute virtio_fs_vq_cpu_list_attr = __ATTR_RO(cpu_list); static struct attribute *virtio_fs_vq_attrs[] = { &virtio_fs_vq_name_attr.attr, &virtio_fs_vq_cpu_list_attr.attr, NULL }; static struct attribute_group virtio_fs_vq_attr_group = { .attrs = virtio_fs_vq_attrs, }; /* Make sure virtiofs_mutex is held */ static void virtio_fs_put_locked(struct virtio_fs *fs) { lockdep_assert_held(&virtio_fs_mutex); kobject_put(&fs->kobj); } static void virtio_fs_put(struct virtio_fs *fs) { mutex_lock(&virtio_fs_mutex); virtio_fs_put_locked(fs); mutex_unlock(&virtio_fs_mutex); } static void virtio_fs_fiq_release(struct fuse_iqueue *fiq) { struct virtio_fs *vfs = fiq->priv; virtio_fs_put(vfs); } static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq) { WARN_ON(fsvq->in_flight < 0); /* Wait for in flight requests to finish.*/ spin_lock(&fsvq->lock); if (fsvq->in_flight) { /* We are holding virtio_fs_mutex. There should not be any * waiters waiting for completion. */ reinit_completion(&fsvq->in_flight_zero); spin_unlock(&fsvq->lock); wait_for_completion(&fsvq->in_flight_zero); } else { spin_unlock(&fsvq->lock); } flush_work(&fsvq->done_work); flush_work(&fsvq->dispatch_work); } static void virtio_fs_drain_all_queues_locked(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; int i; for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; virtio_fs_drain_queue(fsvq); } } static void virtio_fs_drain_all_queues(struct virtio_fs *fs) { /* Provides mutual exclusion between ->remove and ->kill_sb * paths. We don't want both of these draining queue at the * same time. Current completion logic reinits completion * and that means there should not be any other thread * doing reinit or waiting for completion already. */ mutex_lock(&virtio_fs_mutex); virtio_fs_drain_all_queues_locked(fs); mutex_unlock(&virtio_fs_mutex); } static void virtio_fs_start_all_queues(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; int i; for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; spin_lock(&fsvq->lock); fsvq->connected = true; spin_unlock(&fsvq->lock); } } static void virtio_fs_delete_queues_sysfs(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; int i; for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; kobject_put(fsvq->kobj); } } static int virtio_fs_add_queues_sysfs(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; char buff[12]; int i, j, ret; for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; sprintf(buff, "%d", i); fsvq->kobj = kobject_create_and_add(buff, fs->mqs_kobj); if (!fs->mqs_kobj) { ret = -ENOMEM; goto out_del; } ret = sysfs_create_group(fsvq->kobj, &virtio_fs_vq_attr_group); if (ret) { kobject_put(fsvq->kobj); goto out_del; } } return 0; out_del: for (j = 0; j < i; j++) { fsvq = &fs->vqs[j]; kobject_put(fsvq->kobj); } return ret; } /* Add a new instance to the list or return -EEXIST if tag name exists*/ static int virtio_fs_add_instance(struct virtio_device *vdev, struct virtio_fs *fs) { struct virtio_fs *fs2; int ret; mutex_lock(&virtio_fs_mutex); list_for_each_entry(fs2, &virtio_fs_instances, list) { if (strcmp(fs->tag, fs2->tag) == 0) { mutex_unlock(&virtio_fs_mutex); return -EEXIST; } } /* Use the virtio_device's index as a unique identifier, there is no * need to allocate our own identifiers because the virtio_fs instance * is only visible to userspace as long as the underlying virtio_device * exists. */ fs->kobj.kset = virtio_fs_kset; ret = kobject_add(&fs->kobj, NULL, "%d", vdev->index); if (ret < 0) goto out_unlock; fs->mqs_kobj = kobject_create_and_add("mqs", &fs->kobj); if (!fs->mqs_kobj) { ret = -ENOMEM; goto out_del; } ret = sysfs_create_link(&fs->kobj, &vdev->dev.kobj, "device"); if (ret < 0) goto out_put; ret = virtio_fs_add_queues_sysfs(fs); if (ret) goto out_remove; list_add_tail(&fs->list, &virtio_fs_instances); mutex_unlock(&virtio_fs_mutex); kobject_uevent(&fs->kobj, KOBJ_ADD); return 0; out_remove: sysfs_remove_link(&fs->kobj, "device"); out_put: kobject_put(fs->mqs_kobj); out_del: kobject_del(&fs->kobj); out_unlock: mutex_unlock(&virtio_fs_mutex); return ret; } /* Return the virtio_fs with a given tag, or NULL */ static struct virtio_fs *virtio_fs_find_instance(const char *tag) { struct virtio_fs *fs; mutex_lock(&virtio_fs_mutex); list_for_each_entry(fs, &virtio_fs_instances, list) { if (strcmp(fs->tag, tag) == 0) { kobject_get(&fs->kobj); goto found; } } fs = NULL; /* not found */ found: mutex_unlock(&virtio_fs_mutex); return fs; } static void virtio_fs_free_devs(struct virtio_fs *fs) { unsigned int i; for (i = 0; i < fs->nvqs; i++) { struct virtio_fs_vq *fsvq = &fs->vqs[i]; if (!fsvq->fud) continue; fuse_dev_free(fsvq->fud); fsvq->fud = NULL; } } /* Read filesystem name from virtio config into fs->tag (must kfree()). */ static int virtio_fs_read_tag(struct virtio_device *vdev, struct virtio_fs *fs) { char tag_buf[sizeof_field(struct virtio_fs_config, tag)]; char *end; size_t len; virtio_cread_bytes(vdev, offsetof(struct virtio_fs_config, tag), &tag_buf, sizeof(tag_buf)); end = memchr(tag_buf, '\0', sizeof(tag_buf)); if (end == tag_buf) return -EINVAL; /* empty tag */ if (!end) end = &tag_buf[sizeof(tag_buf)]; len = end - tag_buf; fs->tag = devm_kmalloc(&vdev->dev, len + 1, GFP_KERNEL); if (!fs->tag) return -ENOMEM; memcpy(fs->tag, tag_buf, len); fs->tag[len] = '\0'; /* While the VIRTIO specification allows any character, newlines are * awkward on mount(8) command-lines and cause problems in the sysfs * "tag" attr and uevent TAG= properties. Forbid them. */ if (strchr(fs->tag, '\n')) { dev_dbg(&vdev->dev, "refusing virtiofs tag with newline character\n"); return -EINVAL; } dev_info(&vdev->dev, "discovered new tag: %s\n", fs->tag); return 0; } /* Work function for hiprio completion */ static void virtio_fs_hiprio_done_work(struct work_struct *work) { struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, done_work); struct virtqueue *vq = fsvq->vq; /* Free completed FUSE_FORGET requests */ spin_lock(&fsvq->lock); do { unsigned int len; void *req; virtqueue_disable_cb(vq); while ((req = virtqueue_get_buf(vq, &len)) != NULL) { kfree(req); dec_in_flight_req(fsvq); } } while (!virtqueue_enable_cb(vq)); if (!list_empty(&fsvq->queued_reqs)) schedule_work(&fsvq->dispatch_work); spin_unlock(&fsvq->lock); } static void virtio_fs_request_dispatch_work(struct work_struct *work) { struct fuse_req *req; struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, dispatch_work); int ret; pr_debug("virtio-fs: worker %s called.\n", __func__); while (1) { spin_lock(&fsvq->lock); req = list_first_entry_or_null(&fsvq->end_reqs, struct fuse_req, list); if (!req) { spin_unlock(&fsvq->lock); break; } list_del_init(&req->list); spin_unlock(&fsvq->lock); fuse_request_end(req); } /* Dispatch pending requests */ while (1) { unsigned int flags; spin_lock(&fsvq->lock); req = list_first_entry_or_null(&fsvq->queued_reqs, struct fuse_req, list); if (!req) { spin_unlock(&fsvq->lock); return; } list_del_init(&req->list); spin_unlock(&fsvq->lock); flags = memalloc_nofs_save(); ret = virtio_fs_enqueue_req(fsvq, req, true, GFP_KERNEL); memalloc_nofs_restore(flags); if (ret < 0) { if (ret == -ENOSPC) { spin_lock(&fsvq->lock); list_add_tail(&req->list, &fsvq->queued_reqs); spin_unlock(&fsvq->lock); return; } req->out.h.error = ret; spin_lock(&fsvq->lock); dec_in_flight_req(fsvq); spin_unlock(&fsvq->lock); pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret); fuse_request_end(req); } } } /* * Returns 1 if queue is full and sender should wait a bit before sending * next request, 0 otherwise. */ static int send_forget_request(struct virtio_fs_vq *fsvq, struct virtio_fs_forget *forget, bool in_flight) { struct scatterlist sg; struct virtqueue *vq; int ret = 0; bool notify; struct virtio_fs_forget_req *req = &forget->req; spin_lock(&fsvq->lock); if (!fsvq->connected) { if (in_flight) dec_in_flight_req(fsvq); kfree(forget); goto out; } sg_init_one(&sg, req, sizeof(*req)); vq = fsvq->vq; dev_dbg(&vq->vdev->dev, "%s\n", __func__); ret = virtqueue_add_outbuf(vq, &sg, 1, forget, GFP_ATOMIC); if (ret < 0) { if (ret == -ENOSPC) { pr_debug("virtio-fs: Could not queue FORGET: err=%d. Will try later\n", ret); list_add_tail(&forget->list, &fsvq->queued_reqs); if (!in_flight) inc_in_flight_req(fsvq); /* Queue is full */ ret = 1; } else { pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n", ret); kfree(forget); if (in_flight) dec_in_flight_req(fsvq); } goto out; } if (!in_flight) inc_in_flight_req(fsvq); notify = virtqueue_kick_prepare(vq); spin_unlock(&fsvq->lock); if (notify) virtqueue_notify(vq); return ret; out: spin_unlock(&fsvq->lock); return ret; } static void virtio_fs_hiprio_dispatch_work(struct work_struct *work) { struct virtio_fs_forget *forget; struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, dispatch_work); pr_debug("virtio-fs: worker %s called.\n", __func__); while (1) { spin_lock(&fsvq->lock); forget = list_first_entry_or_null(&fsvq->queued_reqs, struct virtio_fs_forget, list); if (!forget) { spin_unlock(&fsvq->lock); return; } list_del(&forget->list); spin_unlock(&fsvq->lock); if (send_forget_request(fsvq, forget, true)) return; } } /* Allocate and copy args into req->argbuf */ static int copy_args_to_argbuf(struct fuse_req *req, gfp_t gfp) { struct fuse_args *args = req->args; unsigned int offset = 0; unsigned int num_in; unsigned int num_out; unsigned int len; unsigned int i; num_in = args->in_numargs - args->in_pages; num_out = args->out_numargs - args->out_pages; len = fuse_len_args(num_in, (struct fuse_arg *) args->in_args) + fuse_len_args(num_out, args->out_args); req->argbuf = kmalloc(len, gfp); if (!req->argbuf) return -ENOMEM; for (i = 0; i < num_in; i++) { memcpy(req->argbuf + offset, args->in_args[i].value, args->in_args[i].size); offset += args->in_args[i].size; } return 0; } /* Copy args out of and free req->argbuf */ static void copy_args_from_argbuf(struct fuse_args *args, struct fuse_req *req) { unsigned int remaining; unsigned int offset; unsigned int num_in; unsigned int num_out; unsigned int i; remaining = req->out.h.len - sizeof(req->out.h); num_in = args->in_numargs - args->in_pages; num_out = args->out_numargs - args->out_pages; offset = fuse_len_args(num_in, (struct fuse_arg *)args->in_args); for (i = 0; i < num_out; i++) { unsigned int argsize = args->out_args[i].size; if (args->out_argvar && i == args->out_numargs - 1 && argsize > remaining) { argsize = remaining; } memcpy(args->out_args[i].value, req->argbuf + offset, argsize); offset += argsize; if (i != args->out_numargs - 1) remaining -= argsize; } /* Store the actual size of the variable-length arg */ if (args->out_argvar) args->out_args[args->out_numargs - 1].size = remaining; kfree(req->argbuf); req->argbuf = NULL; } /* Work function for request completion */ static void virtio_fs_request_complete(struct fuse_req *req, struct virtio_fs_vq *fsvq) { struct fuse_pqueue *fpq = &fsvq->fud->pq; struct fuse_args *args; struct fuse_args_pages *ap; unsigned int len, i, thislen; struct folio *folio; /* * TODO verify that server properly follows FUSE protocol * (oh.uniq, oh.len) */ args = req->args; copy_args_from_argbuf(args, req); if (args->out_pages && args->page_zeroing) { len = args->out_args[args->out_numargs - 1].size; ap = container_of(args, typeof(*ap), args); for (i = 0; i < ap->num_folios; i++) { thislen = ap->descs[i].length; if (len < thislen) { WARN_ON(ap->descs[i].offset); folio = ap->folios[i]; folio_zero_segment(folio, len, thislen); len = 0; } else { len -= thislen; } } } spin_lock(&fpq->lock); clear_bit(FR_SENT, &req->flags); spin_unlock(&fpq->lock); fuse_request_end(req); spin_lock(&fsvq->lock); dec_in_flight_req(fsvq); spin_unlock(&fsvq->lock); } static void virtio_fs_complete_req_work(struct work_struct *work) { struct virtio_fs_req_work *w = container_of(work, typeof(*w), done_work); virtio_fs_request_complete(w->req, w->fsvq); kfree(w); } static void virtio_fs_requests_done_work(struct work_struct *work) { struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, done_work); struct fuse_pqueue *fpq = &fsvq->fud->pq; struct virtqueue *vq = fsvq->vq; struct fuse_req *req; struct fuse_req *next; unsigned int len; LIST_HEAD(reqs); /* Collect completed requests off the virtqueue */ spin_lock(&fsvq->lock); do { virtqueue_disable_cb(vq); while ((req = virtqueue_get_buf(vq, &len)) != NULL) { spin_lock(&fpq->lock); list_move_tail(&req->list, &reqs); spin_unlock(&fpq->lock); } } while (!virtqueue_enable_cb(vq)); spin_unlock(&fsvq->lock); /* End requests */ list_for_each_entry_safe(req, next, &reqs, list) { list_del_init(&req->list); /* blocking async request completes in a worker context */ if (req->args->may_block) { struct virtio_fs_req_work *w; w = kzalloc(sizeof(*w), GFP_NOFS | __GFP_NOFAIL); INIT_WORK(&w->done_work, virtio_fs_complete_req_work); w->fsvq = fsvq; w->req = req; schedule_work(&w->done_work); } else { virtio_fs_request_complete(req, fsvq); } } /* Try to push previously queued requests, as the queue might no longer be full */ spin_lock(&fsvq->lock); if (!list_empty(&fsvq->queued_reqs)) schedule_work(&fsvq->dispatch_work); spin_unlock(&fsvq->lock); } static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *fs) { const struct cpumask *mask, *masks; unsigned int q, cpu, nr_masks; /* First attempt to map using existing transport layer affinities * e.g. PCIe MSI-X */ if (!vdev->config->get_vq_affinity) goto fallback; for (q = 0; q < fs->num_request_queues; q++) { mask = vdev->config->get_vq_affinity(vdev, VQ_REQUEST + q); if (!mask) goto fallback; for_each_cpu(cpu, mask) fs->mq_map[cpu] = q + VQ_REQUEST; } return; fallback: /* Attempt to map evenly in groups over the CPUs */ masks = group_cpus_evenly(fs->num_request_queues, &nr_masks); /* If even this fails we default to all CPUs use first request queue */ if (!masks) { for_each_possible_cpu(cpu) fs->mq_map[cpu] = VQ_REQUEST; return; } for (q = 0; q < fs->num_request_queues; q++) { for_each_cpu(cpu, &masks[q % nr_masks]) fs->mq_map[cpu] = q + VQ_REQUEST; } kfree(masks); } /* Virtqueue interrupt handler */ static void virtio_fs_vq_done(struct virtqueue *vq) { struct virtio_fs_vq *fsvq = vq_to_fsvq(vq); dev_dbg(&vq->vdev->dev, "%s %s\n", __func__, fsvq->name); schedule_work(&fsvq->done_work); } static void virtio_fs_init_vq(struct virtio_fs_vq *fsvq, char *name, int vq_type) { strscpy(fsvq->name, name, VQ_NAME_LEN); spin_lock_init(&fsvq->lock); INIT_LIST_HEAD(&fsvq->queued_reqs); INIT_LIST_HEAD(&fsvq->end_reqs); init_completion(&fsvq->in_flight_zero); if (vq_type == VQ_REQUEST) { INIT_WORK(&fsvq->done_work, virtio_fs_requests_done_work); INIT_WORK(&fsvq->dispatch_work, virtio_fs_request_dispatch_work); } else { INIT_WORK(&fsvq->done_work, virtio_fs_hiprio_done_work); INIT_WORK(&fsvq->dispatch_work, virtio_fs_hiprio_dispatch_work); } } /* Initialize virtqueues */ static int virtio_fs_setup_vqs(struct virtio_device *vdev, struct virtio_fs *fs) { struct virtqueue_info *vqs_info; struct virtqueue **vqs; /* Specify pre_vectors to ensure that the queues before the * request queues (e.g. hiprio) don't claim any of the CPUs in * the multi-queue mapping and interrupt affinities */ struct irq_affinity desc = { .pre_vectors = VQ_REQUEST }; unsigned int i; int ret = 0; virtio_cread_le(vdev, struct virtio_fs_config, num_request_queues, &fs->num_request_queues); if (fs->num_request_queues == 0) return -EINVAL; /* Truncate nr of request queues to nr_cpu_id */ fs->num_request_queues = min_t(unsigned int, fs->num_request_queues, nr_cpu_ids); fs->nvqs = VQ_REQUEST + fs->num_request_queues; fs->vqs = kcalloc(fs->nvqs, sizeof(fs->vqs[VQ_HIPRIO]), GFP_KERNEL); if (!fs->vqs) return -ENOMEM; vqs = kmalloc_array(fs->nvqs, sizeof(vqs[VQ_HIPRIO]), GFP_KERNEL); fs->mq_map = kcalloc_node(nr_cpu_ids, sizeof(*fs->mq_map), GFP_KERNEL, dev_to_node(&vdev->dev)); vqs_info = kcalloc(fs->nvqs, sizeof(*vqs_info), GFP_KERNEL); if (!vqs || !vqs_info || !fs->mq_map) { ret = -ENOMEM; goto out; } /* Initialize the hiprio/forget request virtqueue */ vqs_info[VQ_HIPRIO].callback = virtio_fs_vq_done; virtio_fs_init_vq(&fs->vqs[VQ_HIPRIO], "hiprio", VQ_HIPRIO); vqs_info[VQ_HIPRIO].name = fs->vqs[VQ_HIPRIO].name; /* Initialize the requests virtqueues */ for (i = VQ_REQUEST; i < fs->nvqs; i++) { char vq_name[VQ_NAME_LEN]; snprintf(vq_name, VQ_NAME_LEN, "requests.%u", i - VQ_REQUEST); virtio_fs_init_vq(&fs->vqs[i], vq_name, VQ_REQUEST); vqs_info[i].callback = virtio_fs_vq_done; vqs_info[i].name = fs->vqs[i].name; } ret = virtio_find_vqs(vdev, fs->nvqs, vqs, vqs_info, &desc); if (ret < 0) goto out; for (i = 0; i < fs->nvqs; i++) fs->vqs[i].vq = vqs[i]; virtio_fs_start_all_queues(fs); out: kfree(vqs_info); kfree(vqs); if (ret) { kfree(fs->vqs); kfree(fs->mq_map); } return ret; } /* Free virtqueues (device must already be reset) */ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev) { vdev->config->del_vqs(vdev); } /* Map a window offset to a page frame number. The window offset will have * been produced by .iomap_begin(), which maps a file offset to a window * offset. */ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, enum dax_access_mode mode, void **kaddr, unsigned long *pfn) { struct virtio_fs *fs = dax_get_private(dax_dev); phys_addr_t offset = PFN_PHYS(pgoff); size_t max_nr_pages = fs->window_len / PAGE_SIZE - pgoff; if (kaddr) *kaddr = fs->window_kaddr + offset; if (pfn) *pfn = fs->window_phys_addr + offset; return nr_pages > max_nr_pages ? max_nr_pages : nr_pages; } static int virtio_fs_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff, size_t nr_pages) { long rc; void *kaddr; rc = dax_direct_access(dax_dev, pgoff, nr_pages, DAX_ACCESS, &kaddr, NULL); if (rc < 0) return dax_mem2blk_err(rc); memset(kaddr, 0, nr_pages << PAGE_SHIFT); dax_flush(dax_dev, kaddr, nr_pages << PAGE_SHIFT); return 0; } static const struct dax_operations virtio_fs_dax_ops = { .direct_access = virtio_fs_direct_access, .zero_page_range = virtio_fs_zero_page_range, }; static void virtio_fs_cleanup_dax(void *data) { struct dax_device *dax_dev = data; kill_dax(dax_dev); put_dax(dax_dev); } DEFINE_FREE(cleanup_dax, struct dax_dev *, if (!IS_ERR_OR_NULL(_T)) virtio_fs_cleanup_dax(_T)) static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs) { struct dax_device *dax_dev __free(cleanup_dax) = NULL; struct virtio_shm_region cache_reg; struct dev_pagemap *pgmap; bool have_cache; if (!IS_ENABLED(CONFIG_FUSE_DAX)) return 0; dax_dev = alloc_dax(fs, &virtio_fs_dax_ops); if (IS_ERR(dax_dev)) { int rc = PTR_ERR(dax_dev); return rc == -EOPNOTSUPP ? 0 : rc; } /* Get cache region */ have_cache = virtio_get_shm_region(vdev, &cache_reg, (u8)VIRTIO_FS_SHMCAP_ID_CACHE); if (!have_cache) { dev_notice(&vdev->dev, "%s: No cache capability\n", __func__); return 0; } if (!devm_request_mem_region(&vdev->dev, cache_reg.addr, cache_reg.len, dev_name(&vdev->dev))) { dev_warn(&vdev->dev, "could not reserve region addr=0x%llx len=0x%llx\n", cache_reg.addr, cache_reg.len); return -EBUSY; } dev_notice(&vdev->dev, "Cache len: 0x%llx @ 0x%llx\n", cache_reg.len, cache_reg.addr); pgmap = devm_kzalloc(&vdev->dev, sizeof(*pgmap), GFP_KERNEL); if (!pgmap) return -ENOMEM; pgmap->type = MEMORY_DEVICE_FS_DAX; /* Ideally we would directly use the PCI BAR resource but * devm_memremap_pages() wants its own copy in pgmap. So * initialize a struct resource from scratch (only the start * and end fields will be used). */ pgmap->range = (struct range) { .start = (phys_addr_t) cache_reg.addr, .end = (phys_addr_t) cache_reg.addr + cache_reg.len - 1, }; pgmap->nr_range = 1; fs->window_kaddr = devm_memremap_pages(&vdev->dev, pgmap); if (IS_ERR(fs->window_kaddr)) return PTR_ERR(fs->window_kaddr); fs->window_phys_addr = (phys_addr_t) cache_reg.addr; fs->window_len = (phys_addr_t) cache_reg.len; dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n", __func__, fs->window_kaddr, cache_reg.addr, cache_reg.len); fs->dax_dev = no_free_ptr(dax_dev); return devm_add_action_or_reset(&vdev->dev, virtio_fs_cleanup_dax, fs->dax_dev); } static int virtio_fs_probe(struct virtio_device *vdev) { struct virtio_fs *fs; int ret; fs = kzalloc(sizeof(*fs), GFP_KERNEL); if (!fs) return -ENOMEM; kobject_init(&fs->kobj, &virtio_fs_ktype); vdev->priv = fs; ret = virtio_fs_read_tag(vdev, fs); if (ret < 0) goto out; ret = virtio_fs_setup_vqs(vdev, fs); if (ret < 0) goto out; virtio_fs_map_queues(vdev, fs); ret = virtio_fs_setup_dax(vdev, fs); if (ret < 0) goto out_vqs; /* Bring the device online in case the filesystem is mounted and * requests need to be sent before we return. */ virtio_device_ready(vdev); ret = virtio_fs_add_instance(vdev, fs); if (ret < 0) goto out_vqs; return 0; out_vqs: virtio_reset_device(vdev); virtio_fs_cleanup_vqs(vdev); out: vdev->priv = NULL; kobject_put(&fs->kobj); return ret; } static void virtio_fs_stop_all_queues(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; int i; for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; spin_lock(&fsvq->lock); fsvq->connected = false; spin_unlock(&fsvq->lock); } } static void virtio_fs_remove(struct virtio_device *vdev) { struct virtio_fs *fs = vdev->priv; mutex_lock(&virtio_fs_mutex); /* This device is going away. No one should get new reference */ list_del_init(&fs->list); virtio_fs_delete_queues_sysfs(fs); sysfs_remove_link(&fs->kobj, "device"); kobject_put(fs->mqs_kobj); kobject_del(&fs->kobj); virtio_fs_stop_all_queues(fs); virtio_fs_drain_all_queues_locked(fs); virtio_reset_device(vdev); virtio_fs_cleanup_vqs(vdev); vdev->priv = NULL; /* Put device reference on virtio_fs object */ virtio_fs_put_locked(fs); mutex_unlock(&virtio_fs_mutex); } #ifdef CONFIG_PM_SLEEP static int virtio_fs_freeze(struct virtio_device *vdev) { /* TODO need to save state here */ pr_warn("virtio-fs: suspend/resume not yet supported\n"); return -EOPNOTSUPP; } static int virtio_fs_restore(struct virtio_device *vdev) { /* TODO need to restore state here */ return 0; } #endif /* CONFIG_PM_SLEEP */ static const struct virtio_device_id id_table[] = { { VIRTIO_ID_FS, VIRTIO_DEV_ANY_ID }, {}, }; static const unsigned int feature_table[] = {}; static struct virtio_driver virtio_fs_driver = { .driver.name = KBUILD_MODNAME, .id_table = id_table, .feature_table = feature_table, .feature_table_size = ARRAY_SIZE(feature_table), .probe = virtio_fs_probe, .remove = virtio_fs_remove, #ifdef CONFIG_PM_SLEEP .freeze = virtio_fs_freeze, .restore = virtio_fs_restore, #endif }; static void virtio_fs_send_forget(struct fuse_iqueue *fiq, struct fuse_forget_link *link) { struct virtio_fs_forget *forget; struct virtio_fs_forget_req *req; struct virtio_fs *fs = fiq->priv; struct virtio_fs_vq *fsvq = &fs->vqs[VQ_HIPRIO]; u64 unique = fuse_get_unique(fiq); /* Allocate a buffer for the request */ forget = kmalloc(sizeof(*forget), GFP_NOFS | __GFP_NOFAIL); req = &forget->req; req->ih = (struct fuse_in_header){ .opcode = FUSE_FORGET, .nodeid = link->forget_one.nodeid, .unique = unique, .len = sizeof(*req), }; req->arg = (struct fuse_forget_in){ .nlookup = link->forget_one.nlookup, }; send_forget_request(fsvq, forget, false); kfree(link); } static void virtio_fs_send_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req) { /* * TODO interrupts. * * Normal fs operations on a local filesystems aren't interruptible. * Exceptions are blocking lock operations; for example fcntl(F_SETLKW) * with shared lock between host and guest. */ } /* Count number of scatter-gather elements required */ static unsigned int sg_count_fuse_folios(struct fuse_folio_desc *folio_descs, unsigned int num_folios, unsigned int total_len) { unsigned int i; unsigned int this_len; for (i = 0; i < num_folios && total_len; i++) { this_len = min(folio_descs[i].length, total_len); total_len -= this_len; } return i; } /* Return the number of scatter-gather list elements required */ static unsigned int sg_count_fuse_req(struct fuse_req *req) { struct fuse_args *args = req->args; struct fuse_args_pages *ap = container_of(args, typeof(*ap), args); unsigned int size, total_sgs = 1 /* fuse_in_header */; if (args->in_numargs - args->in_pages) total_sgs += 1; if (args->in_pages) { size = args->in_args[args->in_numargs - 1].size; total_sgs += sg_count_fuse_folios(ap->descs, ap->num_folios, size); } if (!test_bit(FR_ISREPLY, &req->flags)) return total_sgs; total_sgs += 1 /* fuse_out_header */; if (args->out_numargs - args->out_pages) total_sgs += 1; if (args->out_pages) { size = args->out_args[args->out_numargs - 1].size; total_sgs += sg_count_fuse_folios(ap->descs, ap->num_folios, size); } return total_sgs; } /* Add folios to scatter-gather list and return number of elements used */ static unsigned int sg_init_fuse_folios(struct scatterlist *sg, struct folio **folios, struct fuse_folio_desc *folio_descs, unsigned int num_folios, unsigned int total_len) { unsigned int i; unsigned int this_len; for (i = 0; i < num_folios && total_len; i++) { sg_init_table(&sg[i], 1); this_len = min(folio_descs[i].length, total_len); sg_set_folio(&sg[i], folios[i], this_len, folio_descs[i].offset); total_len -= this_len; } return i; } /* Add args to scatter-gather list and return number of elements used */ static unsigned int sg_init_fuse_args(struct scatterlist *sg, struct fuse_req *req, struct fuse_arg *args, unsigned int numargs, bool argpages, void *argbuf, unsigned int *len_used) { struct fuse_args_pages *ap = container_of(req->args, typeof(*ap), args); unsigned int total_sgs = 0; unsigned int len; len = fuse_len_args(numargs - argpages, args); if (len) sg_init_one(&sg[total_sgs++], argbuf, len); if (argpages) total_sgs += sg_init_fuse_folios(&sg[total_sgs], ap->folios, ap->descs, ap->num_folios, args[numargs - 1].size); if (len_used) *len_used = len; return total_sgs; } /* Add a request to a virtqueue and kick the device */ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, struct fuse_req *req, bool in_flight, gfp_t gfp) { /* requests need at least 4 elements */ struct scatterlist *stack_sgs[6]; struct scatterlist stack_sg[ARRAY_SIZE(stack_sgs)]; struct scatterlist **sgs = stack_sgs; struct scatterlist *sg = stack_sg; struct virtqueue *vq; struct fuse_args *args = req->args; unsigned int argbuf_used = 0; unsigned int out_sgs = 0; unsigned int in_sgs = 0; unsigned int total_sgs; unsigned int i; int ret; bool notify; struct fuse_pqueue *fpq; /* Does the sglist fit on the stack? */ total_sgs = sg_count_fuse_req(req); if (total_sgs > ARRAY_SIZE(stack_sgs)) { sgs = kmalloc_array(total_sgs, sizeof(sgs[0]), gfp); sg = kmalloc_array(total_sgs, sizeof(sg[0]), gfp); if (!sgs || !sg) { ret = -ENOMEM; goto out; } } /* Use a bounce buffer since stack args cannot be mapped */ ret = copy_args_to_argbuf(req, gfp); if (ret < 0) goto out; /* Request elements */ sg_init_one(&sg[out_sgs++], &req->in.h, sizeof(req->in.h)); out_sgs += sg_init_fuse_args(&sg[out_sgs], req, (struct fuse_arg *)args->in_args, args->in_numargs, args->in_pages, req->argbuf, &argbuf_used); /* Reply elements */ if (test_bit(FR_ISREPLY, &req->flags)) { sg_init_one(&sg[out_sgs + in_sgs++], &req->out.h, sizeof(req->out.h)); in_sgs += sg_init_fuse_args(&sg[out_sgs + in_sgs], req, args->out_args, args->out_numargs, args->out_pages, req->argbuf + argbuf_used, NULL); } WARN_ON(out_sgs + in_sgs != total_sgs); for (i = 0; i < total_sgs; i++) sgs[i] = &sg[i]; spin_lock(&fsvq->lock); if (!fsvq->connected) { spin_unlock(&fsvq->lock); ret = -ENOTCONN; goto out; } vq = fsvq->vq; ret = virtqueue_add_sgs(vq, sgs, out_sgs, in_sgs, req, GFP_ATOMIC); if (ret < 0) { spin_unlock(&fsvq->lock); goto out; } /* Request successfully sent. */ fpq = &fsvq->fud->pq; spin_lock(&fpq->lock); list_add_tail(&req->list, fpq->processing); spin_unlock(&fpq->lock); set_bit(FR_SENT, &req->flags); /* matches barrier in request_wait_answer() */ smp_mb__after_atomic(); if (!in_flight) inc_in_flight_req(fsvq); notify = virtqueue_kick_prepare(vq); spin_unlock(&fsvq->lock); if (notify) virtqueue_notify(vq); out: if (ret < 0 && req->argbuf) { kfree(req->argbuf); req->argbuf = NULL; } if (sgs != stack_sgs) { kfree(sgs); kfree(sg); } return ret; } static void virtio_fs_send_req(struct fuse_iqueue *fiq, struct fuse_req *req) { unsigned int queue_id; struct virtio_fs *fs; struct virtio_fs_vq *fsvq; int ret; if (req->in.h.opcode != FUSE_NOTIFY_REPLY) req->in.h.unique = fuse_get_unique(fiq); clear_bit(FR_PENDING, &req->flags); fs = fiq->priv; queue_id = fs->mq_map[raw_smp_processor_id()]; pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u queue_id %u\n", __func__, req->in.h.opcode, req->in.h.unique, req->in.h.nodeid, req->in.h.len, fuse_len_args(req->args->out_numargs, req->args->out_args), queue_id); fsvq = &fs->vqs[queue_id]; ret = virtio_fs_enqueue_req(fsvq, req, false, GFP_ATOMIC); if (ret < 0) { if (ret == -ENOSPC) { /* * Virtqueue full. Retry submission from worker * context as we might be holding fc->bg_lock. */ spin_lock(&fsvq->lock); list_add_tail(&req->list, &fsvq->queued_reqs); inc_in_flight_req(fsvq); spin_unlock(&fsvq->lock); return; } req->out.h.error = ret; pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret); /* Can't end request in submission context. Use a worker */ spin_lock(&fsvq->lock); list_add_tail(&req->list, &fsvq->end_reqs); schedule_work(&fsvq->dispatch_work); spin_unlock(&fsvq->lock); return; } } static const struct fuse_iqueue_ops virtio_fs_fiq_ops = { .send_forget = virtio_fs_send_forget, .send_interrupt = virtio_fs_send_interrupt, .send_req = virtio_fs_send_req, .release = virtio_fs_fiq_release, }; static inline void virtio_fs_ctx_set_defaults(struct fuse_fs_context *ctx) { ctx->rootmode = S_IFDIR; ctx->default_permissions = 1; ctx->allow_other = 1; ctx->max_read = UINT_MAX; ctx->blksize = 512; ctx->destroy = true; ctx->no_control = true; ctx->no_force_umount = true; } static int virtio_fs_fill_super(struct super_block *sb, struct fs_context *fsc) { struct fuse_mount *fm = get_fuse_mount_super(sb); struct fuse_conn *fc = fm->fc; struct virtio_fs *fs = fc->iq.priv; struct fuse_fs_context *ctx = fsc->fs_private; unsigned int i; int err; virtio_fs_ctx_set_defaults(ctx); mutex_lock(&virtio_fs_mutex); /* After holding mutex, make sure virtiofs device is still there. * Though we are holding a reference to it, drive ->remove might * still have cleaned up virtual queues. In that case bail out. */ err = -EINVAL; if (list_empty(&fs->list)) { pr_info("virtio-fs: tag <%s> not found\n", fs->tag); goto err; } err = -ENOMEM; /* Allocate fuse_dev for hiprio and notification queues */ for (i = 0; i < fs->nvqs; i++) { struct virtio_fs_vq *fsvq = &fs->vqs[i]; fsvq->fud = fuse_dev_alloc(); if (!fsvq->fud) goto err_free_fuse_devs; } /* virtiofs allocates and installs its own fuse devices */ ctx->fudptr = NULL; if (ctx->dax_mode != FUSE_DAX_NEVER) { if (ctx->dax_mode == FUSE_DAX_ALWAYS && !fs->dax_dev) { err = -EINVAL; pr_err("virtio-fs: dax can't be enabled as filesystem" " device does not support it.\n"); goto err_free_fuse_devs; } ctx->dax_dev = fs->dax_dev; } err = fuse_fill_super_common(sb, ctx); if (err < 0) goto err_free_fuse_devs; for (i = 0; i < fs->nvqs; i++) { struct virtio_fs_vq *fsvq = &fs->vqs[i]; fuse_dev_install(fsvq->fud, fc); } /* Previous unmount will stop all queues. Start these again */ virtio_fs_start_all_queues(fs); fuse_send_init(fm); mutex_unlock(&virtio_fs_mutex); return 0; err_free_fuse_devs: virtio_fs_free_devs(fs); err: mutex_unlock(&virtio_fs_mutex); return err; } static void virtio_fs_conn_destroy(struct fuse_mount *fm) { struct fuse_conn *fc = fm->fc; struct virtio_fs *vfs = fc->iq.priv; struct virtio_fs_vq *fsvq = &vfs->vqs[VQ_HIPRIO]; /* Stop dax worker. Soon evict_inodes() will be called which * will free all memory ranges belonging to all inodes. */ if (IS_ENABLED(CONFIG_FUSE_DAX)) fuse_dax_cancel_work(fc); /* Stop forget queue. Soon destroy will be sent */ spin_lock(&fsvq->lock); fsvq->connected = false; spin_unlock(&fsvq->lock); virtio_fs_drain_all_queues(vfs); fuse_conn_destroy(fm); /* fuse_conn_destroy() must have sent destroy. Stop all queues * and drain one more time and free fuse devices. Freeing fuse * devices will drop their reference on fuse_conn and that in * turn will drop its reference on virtio_fs object. */ virtio_fs_stop_all_queues(vfs); virtio_fs_drain_all_queues(vfs); virtio_fs_free_devs(vfs); } static void virtio_kill_sb(struct super_block *sb) { struct fuse_mount *fm = get_fuse_mount_super(sb); bool last; /* If mount failed, we can still be called without any fc */ if (sb->s_root) { last = fuse_mount_remove(fm); if (last) virtio_fs_conn_destroy(fm); } kill_anon_super(sb); fuse_mount_destroy(fm); } static int virtio_fs_test_super(struct super_block *sb, struct fs_context *fsc) { struct fuse_mount *fsc_fm = fsc->s_fs_info; struct fuse_mount *sb_fm = get_fuse_mount_super(sb); return fsc_fm->fc->iq.priv == sb_fm->fc->iq.priv; } static int virtio_fs_get_tree(struct fs_context *fsc) { struct virtio_fs *fs; struct super_block *sb; struct fuse_conn *fc = NULL; struct fuse_mount *fm; unsigned int virtqueue_size; int err = -EIO; if (!fsc->source) return invalf(fsc, "No source specified"); /* This gets a reference on virtio_fs object. This ptr gets installed * in fc->iq->priv. Once fuse_conn is going away, it calls ->put() * to drop the reference to this object. */ fs = virtio_fs_find_instance(fsc->source); if (!fs) { pr_info("virtio-fs: tag <%s> not found\n", fsc->source); return -EINVAL; } virtqueue_size = virtqueue_get_vring_size(fs->vqs[VQ_REQUEST].vq); if (WARN_ON(virtqueue_size <= FUSE_HEADER_OVERHEAD)) goto out_err; err = -ENOMEM; fc = kzalloc(sizeof(struct fuse_conn), GFP_KERNEL); if (!fc) goto out_err; fm = kzalloc(sizeof(struct fuse_mount), GFP_KERNEL); if (!fm) goto out_err; fuse_conn_init(fc, fm, fsc->user_ns, &virtio_fs_fiq_ops, fs); fc->release = fuse_free_conn; fc->delete_stale = true; fc->auto_submounts = true; fc->sync_fs = true; fc->use_pages_for_kvec_io = true; /* Tell FUSE to split requests that exceed the virtqueue's size */ fc->max_pages_limit = min_t(unsigned int, fc->max_pages_limit, virtqueue_size - FUSE_HEADER_OVERHEAD); fsc->s_fs_info = fm; sb = sget_fc(fsc, virtio_fs_test_super, set_anon_super_fc); if (fsc->s_fs_info) fuse_mount_destroy(fm); if (IS_ERR(sb)) return PTR_ERR(sb); if (!sb->s_root) { err = virtio_fs_fill_super(sb, fsc); if (err) { deactivate_locked_super(sb); return err; } sb->s_flags |= SB_ACTIVE; } WARN_ON(fsc->root); fsc->root = dget(sb->s_root); return 0; out_err: kfree(fc); virtio_fs_put(fs); return err; } static const struct fs_context_operations virtio_fs_context_ops = { .free = virtio_fs_free_fsc, .parse_param = virtio_fs_parse_param, .get_tree = virtio_fs_get_tree, }; static int virtio_fs_init_fs_context(struct fs_context *fsc) { struct fuse_fs_context *ctx; if (fsc->purpose == FS_CONTEXT_FOR_SUBMOUNT) return fuse_init_fs_context_submount(fsc); ctx = kzalloc(sizeof(struct fuse_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; fsc->fs_private = ctx; fsc->ops = &virtio_fs_context_ops; return 0; } static struct file_system_type virtio_fs_type = { .owner = THIS_MODULE, .name = "virtiofs", .init_fs_context = virtio_fs_init_fs_context, .kill_sb = virtio_kill_sb, .fs_flags = FS_ALLOW_IDMAP, }; static int virtio_fs_uevent(const struct kobject *kobj, struct kobj_uevent_env *env) { const struct virtio_fs *fs = container_of(kobj, struct virtio_fs, kobj); add_uevent_var(env, "TAG=%s", fs->tag); return 0; } static const struct kset_uevent_ops virtio_fs_uevent_ops = { .uevent = virtio_fs_uevent, }; static int __init virtio_fs_sysfs_init(void) { virtio_fs_kset = kset_create_and_add("virtiofs", &virtio_fs_uevent_ops, fs_kobj); if (!virtio_fs_kset) return -ENOMEM; return 0; } static void virtio_fs_sysfs_exit(void) { kset_unregister(virtio_fs_kset); virtio_fs_kset = NULL; } static int __init virtio_fs_init(void) { int ret; ret = virtio_fs_sysfs_init(); if (ret < 0) return ret; ret = register_virtio_driver(&virtio_fs_driver); if (ret < 0) goto sysfs_exit; ret = register_filesystem(&virtio_fs_type); if (ret < 0) goto unregister_virtio_driver; return 0; unregister_virtio_driver: unregister_virtio_driver(&virtio_fs_driver); sysfs_exit: virtio_fs_sysfs_exit(); return ret; } module_init(virtio_fs_init); static void __exit virtio_fs_exit(void) { unregister_filesystem(&virtio_fs_type); unregister_virtio_driver(&virtio_fs_driver); virtio_fs_sysfs_exit(); } module_exit(virtio_fs_exit); MODULE_AUTHOR("Stefan Hajnoczi <stefanha@redhat.com>"); MODULE_DESCRIPTION("Virtio Filesystem"); MODULE_LICENSE("GPL"); MODULE_ALIAS_FS(KBUILD_MODNAME); MODULE_DEVICE_TABLE(virtio, id_table); |
| 10 12 7 8 2 4 4 4 9 1 1 12 1 1 5186 5 5196 3 3 1 2 5161 5160 5159 5162 5164 5167 8 21 1 2 2 1 1 38 21 22 9 13 13 13 3 3 3 3 3 3 3 3 3 3 13 13 13 3 3 3 3 3 10 13 13 4 4 4 3 3 3 3 3 3 3 3 2 3 3 3 3 3 3 3 3 3 3 3 3 179 89 2 3 81 80 78 80 80 14 14 14 2 2 10 9 8 9 8 8 2 8 9 10 15 10 6 15 10 6 2 14 15 2 2 2 2 2 2 2 10 2 8 4 4 8 6 78 81 80 8 2 1 1 1 1 1 1 12 176 176 174 177 175 175 175 3 3 8 11 1 10 11 28 28 10 10 1 9 28 27 28 28 28 3 2 3 2 3 3 3 3 3 2 3 2 3 3 3 3 3 3 4 2 3 3 4 3 3 3 1 3 2 3 5 5 3 2 1 1 5 5 4 3 4 3 3 3 3 2 3 3 3 3 3 3 5 5 5 3 3 3 3 3 1 2 3 3 3 1 2 3 3 3 3 2 3 3 3 1 2 3 3 3 3 3 3 3 1 1 1 1 2 2 2 2 2 11 11 11 11 2 2 2 1 9 10 10 9 10 10 9 10 6 6 10 10 10 10 2 8 8 10 9 2 2 2 2 2 2 2 2 2 1 2 2 1 1 2 1 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 6 6 5 2 2 2 23 24 1 23 16 6 6 1 3 1 1 1 1 5 4 5 3 1 17 13 2 1 1 8 8 4 10 10 10 10 10 10 10 10 8 2 1 2 2 38 51 38 40 43 33 40 29 39 29 11 11 11 10 11 11 9 9 2 2 2 2 6 6 2 5 4 2 2 2 6 6 6 4 4 4 4 5 6 6 4 4 3 4 3 4 5 1 2 2 6 5 6 6 4 6 5 4 3 2 1 3 3 3 3 4 4 1 2 2 2 3 1 1 1 1 1 1 1 1 1 1 1 2 8 8 8 7 8 8 8 4 8 8 8 8 8 7 7 8 8 6 2 8 8 8 4 4 8 6 8 8 8 8 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 6 6 6 6 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 | /* * Generic process-grouping system. * * Based originally on the cpuset system, extracted by Paul Menage * Copyright (C) 2006 Google, Inc * * Notifications support * Copyright (C) 2009 Nokia Corporation * Author: Kirill A. Shutemov * * Copyright notices from the original cpuset code: * -------------------------------------------------- * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2006 Silicon Graphics, Inc. * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * --------------------------------------------------- * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "cgroup-internal.h" #include <linux/bpf-cgroup.h> #include <linux/cred.h> #include <linux/errno.h> #include <linux/init_task.h> #include <linux/kernel.h> #include <linux/magic.h> #include <linux/mutex.h> #include <linux/mount.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/percpu-rwsem.h> #include <linux/string.h> #include <linux/hashtable.h> #include <linux/idr.h> #include <linux/kthread.h> #include <linux/atomic.h> #include <linux/cpuset.h> #include <linux/proc_ns.h> #include <linux/nsproxy.h> #include <linux/file.h> #include <linux/fs_parser.h> #include <linux/sched/cputime.h> #include <linux/sched/deadline.h> #include <linux/psi.h> #include <net/sock.h> #define CREATE_TRACE_POINTS #include <trace/events/cgroup.h> #define CGROUP_FILE_NAME_MAX (MAX_CGROUP_TYPE_NAMELEN + \ MAX_CFTYPE_NAME + 2) /* let's not notify more than 100 times per second */ #define CGROUP_FILE_NOTIFY_MIN_INTV DIV_ROUND_UP(HZ, 100) /* * To avoid confusing the compiler (and generating warnings) with code * that attempts to access what would be a 0-element array (i.e. sized * to a potentially empty array when CGROUP_SUBSYS_COUNT == 0), this * constant expression can be added. */ #define CGROUP_HAS_SUBSYS_CONFIG (CGROUP_SUBSYS_COUNT > 0) /* * cgroup_mutex is the master lock. Any modification to cgroup or its * hierarchy must be performed while holding it. * * css_set_lock protects task->cgroups pointer, the list of css_set * objects, and the chain of tasks off each css_set. * * These locks are exported if CONFIG_PROVE_RCU so that accessors in * cgroup.h can use them for lockdep annotations. */ DEFINE_MUTEX(cgroup_mutex); DEFINE_SPINLOCK(css_set_lock); #if (defined CONFIG_PROVE_RCU || defined CONFIG_LOCKDEP) EXPORT_SYMBOL_GPL(cgroup_mutex); EXPORT_SYMBOL_GPL(css_set_lock); #endif struct blocking_notifier_head cgroup_lifetime_notifier = BLOCKING_NOTIFIER_INIT(cgroup_lifetime_notifier); DEFINE_SPINLOCK(trace_cgroup_path_lock); char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; static bool cgroup_debug __read_mostly; /* * Protects cgroup_idr and css_idr so that IDs can be released without * grabbing cgroup_mutex. */ static DEFINE_SPINLOCK(cgroup_idr_lock); /* * Protects cgroup_file->kn for !self csses. It synchronizes notifications * against file removal/re-creation across css hiding. */ static DEFINE_SPINLOCK(cgroup_file_kn_lock); DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem); #define cgroup_assert_mutex_or_rcu_locked() \ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ !lockdep_is_held(&cgroup_mutex), \ "cgroup_mutex or RCU read lock required"); /* * cgroup destruction makes heavy use of work items and there can be a lot * of concurrent destructions. Use a separate workqueue so that cgroup * destruction work items don't end up filling up max_active of system_wq * which may lead to deadlock. */ static struct workqueue_struct *cgroup_destroy_wq; /* generate an array of cgroup subsystem pointers */ #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys, struct cgroup_subsys *cgroup_subsys[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS /* array of cgroup subsystem names */ #define SUBSYS(_x) [_x ## _cgrp_id] = #_x, static const char *cgroup_subsys_name[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS /* array of static_keys for cgroup_subsys_enabled() and cgroup_subsys_on_dfl() */ #define SUBSYS(_x) \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_enabled_key); \ DEFINE_STATIC_KEY_TRUE(_x ## _cgrp_subsys_on_dfl_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_enabled_key); \ EXPORT_SYMBOL_GPL(_x ## _cgrp_subsys_on_dfl_key); #include <linux/cgroup_subsys.h> #undef SUBSYS #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_enabled_key, static struct static_key_true *cgroup_subsys_enabled_key[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys_on_dfl_key, static struct static_key_true *cgroup_subsys_on_dfl_key[] = { #include <linux/cgroup_subsys.h> }; #undef SUBSYS static DEFINE_PER_CPU(struct css_rstat_cpu, root_rstat_cpu); static DEFINE_PER_CPU(struct cgroup_rstat_base_cpu, root_rstat_base_cpu); /* the default hierarchy */ struct cgroup_root cgrp_dfl_root = { .cgrp.self.rstat_cpu = &root_rstat_cpu, .cgrp.rstat_base_cpu = &root_rstat_base_cpu, }; EXPORT_SYMBOL_GPL(cgrp_dfl_root); /* * The default hierarchy always exists but is hidden until mounted for the * first time. This is for backward compatibility. */ bool cgrp_dfl_visible; /* some controllers are not supported in the default hierarchy */ static u16 cgrp_dfl_inhibit_ss_mask; /* some controllers are implicitly enabled on the default hierarchy */ static u16 cgrp_dfl_implicit_ss_mask; /* some controllers can be threaded on the default hierarchy */ static u16 cgrp_dfl_threaded_ss_mask; /* The list of hierarchy roots */ LIST_HEAD(cgroup_roots); static int cgroup_root_count; /* hierarchy ID allocation and mapping, protected by cgroup_mutex */ static DEFINE_IDR(cgroup_hierarchy_idr); /* * Assign a monotonically increasing serial number to csses. It guarantees * cgroups with bigger numbers are newer than those with smaller numbers. * Also, as csses are always appended to the parent's ->children list, it * guarantees that sibling csses are always sorted in the ascending serial * number order on the list. Protected by cgroup_mutex. */ static u64 css_serial_nr_next = 1; /* * These bitmasks identify subsystems with specific features to avoid * having to do iterative checks repeatedly. */ static u16 have_fork_callback __read_mostly; static u16 have_exit_callback __read_mostly; static u16 have_release_callback __read_mostly; static u16 have_canfork_callback __read_mostly; static bool have_favordynmods __ro_after_init = IS_ENABLED(CONFIG_CGROUP_FAVOR_DYNMODS); /* cgroup namespace for init task */ struct cgroup_namespace init_cgroup_ns = { .ns.count = REFCOUNT_INIT(2), .user_ns = &init_user_ns, .ns.ops = &cgroupns_operations, .ns.inum = PROC_CGROUP_INIT_INO, .root_cset = &init_css_set, }; static struct file_system_type cgroup2_fs_type; static struct cftype cgroup_base_files[]; static struct cftype cgroup_psi_files[]; /* cgroup optional features */ enum cgroup_opt_features { #ifdef CONFIG_PSI OPT_FEATURE_PRESSURE, #endif OPT_FEATURE_COUNT }; static const char *cgroup_opt_feature_names[OPT_FEATURE_COUNT] = { #ifdef CONFIG_PSI "pressure", #endif }; static u16 cgroup_feature_disable_mask __read_mostly; static int cgroup_apply_control(struct cgroup *cgrp); static void cgroup_finalize_control(struct cgroup *cgrp, int ret); static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task); static int cgroup_destroy_locked(struct cgroup *cgrp); static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss); static void css_release(struct percpu_ref *ref); static void kill_css(struct cgroup_subsys_state *css); static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add); #ifdef CONFIG_DEBUG_CGROUP_REF #define CGROUP_REF_FN_ATTRS noinline #define CGROUP_REF_EXPORT(fn) EXPORT_SYMBOL_GPL(fn); #include <linux/cgroup_refcnt.h> #endif /** * cgroup_ssid_enabled - cgroup subsys enabled test by subsys ID * @ssid: subsys ID of interest * * cgroup_subsys_enabled() can only be used with literal subsys names which * is fine for individual subsystems but unsuitable for cgroup core. This * is slower static_key_enabled() based test indexed by @ssid. */ bool cgroup_ssid_enabled(int ssid) { if (!CGROUP_HAS_SUBSYS_CONFIG) return false; return static_key_enabled(cgroup_subsys_enabled_key[ssid]); } /** * cgroup_on_dfl - test whether a cgroup is on the default hierarchy * @cgrp: the cgroup of interest * * The default hierarchy is the v2 interface of cgroup and this function * can be used to test whether a cgroup is on the default hierarchy for * cases where a subsystem should behave differently depending on the * interface version. * * List of changed behaviors: * * - Mount options "noprefix", "xattr", "clone_children", "release_agent" * and "name" are disallowed. * * - When mounting an existing superblock, mount options should match. * * - rename(2) is disallowed. * * - "tasks" is removed. Everything should be at process granularity. Use * "cgroup.procs" instead. * * - "cgroup.procs" is not sorted. pids will be unique unless they got * recycled in-between reads. * * - "release_agent" and "notify_on_release" are removed. Replacement * notification mechanism will be implemented. * * - "cgroup.clone_children" is removed. * * - "cgroup.subtree_populated" is available. Its value is 0 if the cgroup * and its descendants contain no task; otherwise, 1. The file also * generates kernfs notification which can be monitored through poll and * [di]notify when the value of the file changes. * * - cpuset: tasks will be kept in empty cpusets when hotplug happens and * take masks of ancestors with non-empty cpus/mems, instead of being * moved to an ancestor. * * - cpuset: a task can be moved into an empty cpuset, and again it takes * masks of ancestors. * * - blkcg: blk-throttle becomes properly hierarchical. */ bool cgroup_on_dfl(const struct cgroup *cgrp) { return cgrp->root == &cgrp_dfl_root; } /* IDR wrappers which synchronize using cgroup_idr_lock */ static int cgroup_idr_alloc(struct idr *idr, void *ptr, int start, int end, gfp_t gfp_mask) { int ret; idr_preload(gfp_mask); spin_lock_bh(&cgroup_idr_lock); ret = idr_alloc(idr, ptr, start, end, gfp_mask & ~__GFP_DIRECT_RECLAIM); spin_unlock_bh(&cgroup_idr_lock); idr_preload_end(); return ret; } static void *cgroup_idr_replace(struct idr *idr, void *ptr, int id) { void *ret; spin_lock_bh(&cgroup_idr_lock); ret = idr_replace(idr, ptr, id); spin_unlock_bh(&cgroup_idr_lock); return ret; } static void cgroup_idr_remove(struct idr *idr, int id) { spin_lock_bh(&cgroup_idr_lock); idr_remove(idr, id); spin_unlock_bh(&cgroup_idr_lock); } static bool cgroup_has_tasks(struct cgroup *cgrp) { return cgrp->nr_populated_csets; } static bool cgroup_is_threaded(struct cgroup *cgrp) { return cgrp->dom_cgrp != cgrp; } /* can @cgrp host both domain and threaded children? */ static bool cgroup_is_mixable(struct cgroup *cgrp) { /* * Root isn't under domain level resource control exempting it from * the no-internal-process constraint, so it can serve as a thread * root and a parent of resource domains at the same time. */ return !cgroup_parent(cgrp); } /* can @cgrp become a thread root? Should always be true for a thread root */ static bool cgroup_can_be_thread_root(struct cgroup *cgrp) { /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return true; /* domain roots can't be nested under threaded */ if (cgroup_is_threaded(cgrp)) return false; /* can only have either domain or threaded children */ if (cgrp->nr_populated_domain_children) return false; /* and no domain controllers can be enabled */ if (cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return false; return true; } /* is @cgrp root of a threaded subtree? */ static bool cgroup_is_thread_root(struct cgroup *cgrp) { /* thread root should be a domain */ if (cgroup_is_threaded(cgrp)) return false; /* a domain w/ threaded children is a thread root */ if (cgrp->nr_threaded_children) return true; /* * A domain which has tasks and explicit threaded controllers * enabled is a thread root. */ if (cgroup_has_tasks(cgrp) && (cgrp->subtree_control & cgrp_dfl_threaded_ss_mask)) return true; return false; } /* a domain which isn't connected to the root w/o brekage can't be used */ static bool cgroup_is_valid_domain(struct cgroup *cgrp) { /* the cgroup itself can be a thread root */ if (cgroup_is_threaded(cgrp)) return false; /* but the ancestors can't be unless mixable */ while ((cgrp = cgroup_parent(cgrp))) { if (!cgroup_is_mixable(cgrp) && cgroup_is_thread_root(cgrp)) return false; if (cgroup_is_threaded(cgrp)) return false; } return true; } /* subsystems visibly enabled on a cgroup */ static u16 cgroup_control(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); u16 root_ss_mask = cgrp->root->subsys_mask; if (parent) { u16 ss_mask = parent->subtree_control; /* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; } if (cgroup_on_dfl(cgrp)) root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask | cgrp_dfl_implicit_ss_mask); return root_ss_mask; } /* subsystems enabled on a cgroup */ static u16 cgroup_ss_mask(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); if (parent) { u16 ss_mask = parent->subtree_ss_mask; /* threaded cgroups can only have threaded controllers */ if (cgroup_is_threaded(cgrp)) ss_mask &= cgrp_dfl_threaded_ss_mask; return ss_mask; } return cgrp->root->subsys_mask; } /** * cgroup_css - obtain a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Return @cgrp's css (cgroup_subsys_state) associated with @ss. This * function must be called either under cgroup_mutex or rcu_read_lock() and * the caller is responsible for pinning the returned css if it wants to * keep accessing it outside the said locks. This function may return * %NULL if @cgrp doesn't have @subsys_id enabled. */ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { if (CGROUP_HAS_SUBSYS_CONFIG && ss) return rcu_dereference_check(cgrp->subsys[ss->id], lockdep_is_held(&cgroup_mutex)); else return &cgrp->self; } /** * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * * Similar to cgroup_css() but returns the effective css, which is defined * as the matching css of the nearest ancestor including self which has @ss * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); if (!ss) return &cgrp->self; /* * This function is used while updating css associations and thus * can't test the csses directly. Test ss_mask. */ while (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) { cgrp = cgroup_parent(cgrp); if (!cgrp) return NULL; } return cgroup_css(cgrp, ss); } /** * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * * The returned css is not guaranteed to be online, and therefore it is the * callers responsibility to try get a reference for it. */ struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL; do { css = cgroup_css(cgrp, ss); if (css) return css; cgrp = cgroup_parent(cgrp); } while (cgrp); return init_css_set.subsys[ss->id]; } /** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get the effective css of @cgrp for @ss. The effective css is * defined as the matching css of the nearest ancestor including self which * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, * the root css is returned, so this function always returns a valid css. * The returned css must be put using css_put(). */ struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; if (!CGROUP_HAS_SUBSYS_CONFIG) return NULL; rcu_read_lock(); do { css = cgroup_css(cgrp, ss); if (css && css_tryget_online(css)) goto out_unlock; cgrp = cgroup_parent(cgrp); } while (cgrp); css = init_css_set.subsys[ss->id]; css_get(css); out_unlock: rcu_read_unlock(); return css; } EXPORT_SYMBOL_GPL(cgroup_get_e_css); static void cgroup_get_live(struct cgroup *cgrp) { WARN_ON_ONCE(cgroup_is_dead(cgrp)); cgroup_get(cgrp); } /** * __cgroup_task_count - count the number of tasks in a cgroup. The caller * is responsible for taking the css_set_lock. * @cgrp: the cgroup in question */ int __cgroup_task_count(const struct cgroup *cgrp) { int count = 0; struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) count += link->cset->nr_tasks; return count; } /** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question */ int cgroup_task_count(const struct cgroup *cgrp) { int count; spin_lock_irq(&css_set_lock); count = __cgroup_task_count(cgrp); spin_unlock_irq(&css_set_lock); return count; } static struct cgroup *kn_priv(struct kernfs_node *kn) { struct kernfs_node *parent; /* * The parent can not be replaced due to KERNFS_ROOT_INVARIANT_PARENT. * Therefore it is always safe to dereference this pointer outside of a * RCU section. */ parent = rcu_dereference_check(kn->__parent, kernfs_root_flags(kn) & KERNFS_ROOT_INVARIANT_PARENT); return parent->priv; } struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); /* * This is open and unprotected implementation of cgroup_css(). * seq_css() is only called from a kernfs file operation which has * an active reference on the file. Because all the subsystem * files are drained before a css is disassociated with a cgroup, * the matching css from the cgroup's subsys table is guaranteed to * be and stay valid until the enclosing operation is complete. */ if (CGROUP_HAS_SUBSYS_CONFIG && cft->ss) return rcu_dereference_raw(cgrp->subsys[cft->ss->id]); else return &cgrp->self; } EXPORT_SYMBOL_GPL(of_css); /** * for_each_css - iterate all css's of a cgroup * @css: the iteration cursor * @ssid: the index of the subsystem, CGROUP_SUBSYS_COUNT after reaching the end * @cgrp: the target cgroup to iterate css's of * * Should be called under cgroup_mutex. */ #define for_each_css(css, ssid, cgrp) \ for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ if (!((css) = rcu_dereference_check( \ (cgrp)->subsys[(ssid)], \ lockdep_is_held(&cgroup_mutex)))) { } \ else /** * do_each_subsys_mask - filter for_each_subsys with a bitmask * @ss: the iteration cursor * @ssid: the index of @ss, CGROUP_SUBSYS_COUNT after reaching the end * @ss_mask: the bitmask * * The block will only run for cases where the ssid-th bit (1 << ssid) of * @ss_mask is set. */ #define do_each_subsys_mask(ss, ssid, ss_mask) do { \ unsigned long __ss_mask = (ss_mask); \ if (!CGROUP_HAS_SUBSYS_CONFIG) { \ (ssid) = 0; \ break; \ } \ for_each_set_bit(ssid, &__ss_mask, CGROUP_SUBSYS_COUNT) { \ (ss) = cgroup_subsys[ssid]; \ { #define while_each_subsys_mask() \ } \ } \ } while (false) /* iterate over child cgrps, lock should be held throughout iteration */ #define cgroup_for_each_live_child(child, cgrp) \ list_for_each_entry((child), &(cgrp)->self.children, self.sibling) \ if (({ lockdep_assert_held(&cgroup_mutex); \ cgroup_is_dead(child); })) \ ; \ else /* walk live descendants in pre order */ #define cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) \ css_for_each_descendant_pre((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* walk live descendants in postorder */ #define cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) \ css_for_each_descendant_post((d_css), cgroup_css((cgrp), NULL)) \ if (({ lockdep_assert_held(&cgroup_mutex); \ (dsct) = (d_css)->cgroup; \ cgroup_is_dead(dsct); })) \ ; \ else /* * The default css_set - used by init and its children prior to any * hierarchies being mounted. It contains a pointer to the root state * for each subsystem. Also used to anchor the list of css_sets. Not * reference-counted, to improve performance when child cgroups * haven't been created. */ struct css_set init_css_set = { .refcount = REFCOUNT_INIT(1), .dom_cset = &init_css_set, .tasks = LIST_HEAD_INIT(init_css_set.tasks), .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), .dying_tasks = LIST_HEAD_INIT(init_css_set.dying_tasks), .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .mg_src_preload_node = LIST_HEAD_INIT(init_css_set.mg_src_preload_node), .mg_dst_preload_node = LIST_HEAD_INIT(init_css_set.mg_dst_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), /* * The following field is re-initialized when this cset gets linked * in cgroup_init(). However, let's initialize the field * statically too so that the default cgroup can be accessed safely * early during boot. */ .dfl_cgrp = &cgrp_dfl_root.cgrp, }; static int css_set_count = 1; /* 1 for init_css_set */ static bool css_set_threaded(struct css_set *cset) { return cset->dom_cset != cset; } /** * css_set_populated - does a css_set contain any tasks? * @cset: target css_set * * css_set_populated() should be the same as !!cset->nr_tasks at steady * state. However, css_set_populated() can be called while a task is being * added to or removed from the linked list before the nr_tasks is * properly updated. Hence, we can't just look at ->nr_tasks here. */ static bool css_set_populated(struct css_set *cset) { lockdep_assert_held(&css_set_lock); return !list_empty(&cset->tasks) || !list_empty(&cset->mg_tasks); } /** * cgroup_update_populated - update the populated count of a cgroup * @cgrp: the target cgroup * @populated: inc or dec populated count * * One of the css_sets associated with @cgrp is either getting its first * task or losing the last. Update @cgrp->nr_populated_* accordingly. The * count is propagated towards root so that a given cgroup's * nr_populated_children is zero iff none of its descendants contain any * tasks. * * @cgrp's interface file "cgroup.populated" is zero if both * @cgrp->nr_populated_csets and @cgrp->nr_populated_children are zero and * 1 otherwise. When the sum changes from or to zero, userland is notified * that the content of the interface file has changed. This can be used to * detect when @cgrp and its descendants become populated or empty. */ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) { struct cgroup *child = NULL; int adj = populated ? 1 : -1; lockdep_assert_held(&css_set_lock); do { bool was_populated = cgroup_is_populated(cgrp); if (!child) { cgrp->nr_populated_csets += adj; } else { if (cgroup_is_threaded(child)) cgrp->nr_populated_threaded_children += adj; else cgrp->nr_populated_domain_children += adj; } if (was_populated == cgroup_is_populated(cgrp)) break; cgroup1_check_for_release(cgrp); TRACE_CGROUP_PATH(notify_populated, cgrp, cgroup_is_populated(cgrp)); cgroup_file_notify(&cgrp->events_file); child = cgrp; cgrp = cgroup_parent(cgrp); } while (cgrp); } /** * css_set_update_populated - update populated state of a css_set * @cset: target css_set * @populated: whether @cset is populated or depopulated * * @cset is either getting the first task or losing the last. Update the * populated counters of all associated cgroups accordingly. */ static void css_set_update_populated(struct css_set *cset, bool populated) { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) cgroup_update_populated(link->cgrp, populated); } /* * @task is leaving, advance task iterators which are pointing to it so * that they can resume at the next position. Advancing an iterator might * remove it from the list, use safe walk. See css_task_iter_skip() for * details. */ static void css_set_skip_task_iters(struct css_set *cset, struct task_struct *task) { struct css_task_iter *it, *pos; list_for_each_entry_safe(it, pos, &cset->task_iters, iters_node) css_task_iter_skip(it, task); } /** * css_set_move_task - move a task from one css_set to another * @task: task being moved * @from_cset: css_set @task currently belongs to (may be NULL) * @to_cset: new css_set @task is being moved to (may be NULL) * @use_mg_tasks: move to @to_cset->mg_tasks instead of ->tasks * * Move @task from @from_cset to @to_cset. If @task didn't belong to any * css_set, @from_cset can be NULL. If @task is being disassociated * instead of moved, @to_cset can be NULL. * * This function automatically handles populated counter updates and * css_task_iter adjustments but the caller is responsible for managing * @from_cset and @to_cset's reference counts. */ static void css_set_move_task(struct task_struct *task, struct css_set *from_cset, struct css_set *to_cset, bool use_mg_tasks) { lockdep_assert_held(&css_set_lock); if (to_cset && !css_set_populated(to_cset)) css_set_update_populated(to_cset, true); if (from_cset) { WARN_ON_ONCE(list_empty(&task->cg_list)); css_set_skip_task_iters(from_cset, task); list_del_init(&task->cg_list); if (!css_set_populated(from_cset)) css_set_update_populated(from_cset, false); } else { WARN_ON_ONCE(!list_empty(&task->cg_list)); } if (to_cset) { /* * We are synchronized through cgroup_threadgroup_rwsem * against PF_EXITING setting such that we can't race * against cgroup_exit()/cgroup_free() dropping the css_set. */ WARN_ON_ONCE(task->flags & PF_EXITING); cgroup_move_task(task, to_cset); list_add_tail(&task->cg_list, use_mg_tasks ? &to_cset->mg_tasks : &to_cset->tasks); } } /* * hash table for cgroup groups. This improves the performance to find * an existing css_set. This hash doesn't (currently) take into * account cgroups in empty hierarchies. */ #define CSS_SET_HASH_BITS 7 static DEFINE_HASHTABLE(css_set_table, CSS_SET_HASH_BITS); static unsigned long css_set_hash(struct cgroup_subsys_state **css) { unsigned long key = 0UL; struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) key += (unsigned long)css[i]; key = (key >> 16) ^ key; return key; } void put_css_set_locked(struct css_set *cset) { struct cgrp_cset_link *link, *tmp_link; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&css_set_lock); if (!refcount_dec_and_test(&cset->refcount)) return; WARN_ON_ONCE(!list_empty(&cset->threaded_csets)); /* This css_set is dead. Unlink it and release cgroup and css refs */ for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); css_put(cset->subsys[ssid]); } hash_del(&cset->hlist); css_set_count--; list_for_each_entry_safe(link, tmp_link, &cset->cgrp_links, cgrp_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); if (cgroup_parent(link->cgrp)) cgroup_put(link->cgrp); kfree(link); } if (css_set_threaded(cset)) { list_del(&cset->threaded_csets_node); put_css_set_locked(cset->dom_cset); } kfree_rcu(cset, rcu_head); } /** * compare_css_sets - helper function for find_existing_css_set(). * @cset: candidate css_set being tested * @old_cset: existing css_set for a task * @new_cgrp: cgroup that's being entered by the task * @template: desired set of css pointers in css_set (pre-calculated) * * Returns true if "cset" matches "old_cset" except for the hierarchy * which "new_cgrp" belongs to, for which it should match "new_cgrp". */ static bool compare_css_sets(struct css_set *cset, struct css_set *old_cset, struct cgroup *new_cgrp, struct cgroup_subsys_state *template[]) { struct cgroup *new_dfl_cgrp; struct list_head *l1, *l2; /* * On the default hierarchy, there can be csets which are * associated with the same set of cgroups but different csses. * Let's first ensure that csses match. */ if (memcmp(template, cset->subsys, sizeof(cset->subsys))) return false; /* @cset's domain should match the default cgroup's */ if (cgroup_on_dfl(new_cgrp)) new_dfl_cgrp = new_cgrp; else new_dfl_cgrp = old_cset->dfl_cgrp; if (new_dfl_cgrp->dom_cgrp != cset->dom_cset->dfl_cgrp) return false; /* * Compare cgroup pointers in order to distinguish between * different cgroups in hierarchies. As different cgroups may * share the same effective css, this comparison is always * necessary. */ l1 = &cset->cgrp_links; l2 = &old_cset->cgrp_links; while (1) { struct cgrp_cset_link *link1, *link2; struct cgroup *cgrp1, *cgrp2; l1 = l1->next; l2 = l2->next; /* See if we reached the end - both lists are equal length. */ if (l1 == &cset->cgrp_links) { BUG_ON(l2 != &old_cset->cgrp_links); break; } else { BUG_ON(l2 == &old_cset->cgrp_links); } /* Locate the cgroups associated with these links. */ link1 = list_entry(l1, struct cgrp_cset_link, cgrp_link); link2 = list_entry(l2, struct cgrp_cset_link, cgrp_link); cgrp1 = link1->cgrp; cgrp2 = link2->cgrp; /* Hierarchies should be linked in the same order. */ BUG_ON(cgrp1->root != cgrp2->root); /* * If this hierarchy is the hierarchy of the cgroup * that's changing, then we need to check that this * css_set points to the new cgroup; if it's any other * hierarchy, then this css_set should point to the * same cgroup as the old css_set. */ if (cgrp1->root == new_cgrp->root) { if (cgrp1 != new_cgrp) return false; } else { if (cgrp1 != cgrp2) return false; } } return true; } /** * find_existing_css_set - init css array and find the matching css_set * @old_cset: the css_set that we're using before the cgroup transition * @cgrp: the cgroup that we're moving into * @template: out param for the new set of csses, should be clear on entry */ static struct css_set *find_existing_css_set(struct css_set *old_cset, struct cgroup *cgrp, struct cgroup_subsys_state **template) { struct cgroup_root *root = cgrp->root; struct cgroup_subsys *ss; struct css_set *cset; unsigned long key; int i; /* * Build the set of subsystem state objects that we want to see in the * new css_set. While subsystems can change globally, the entries here * won't change, so no need for locking. */ for_each_subsys(ss, i) { if (root->subsys_mask & (1UL << i)) { /* * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ template[i] = cgroup_e_css_by_mask(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want * to change the css. */ template[i] = old_cset->subsys[i]; } } key = css_set_hash(template); hash_for_each_possible(css_set_table, cset, hlist, key) { if (!compare_css_sets(cset, old_cset, cgrp, template)) continue; /* This css_set matches what we need */ return cset; } /* No existing cgroup group matched */ return NULL; } static void free_cgrp_cset_links(struct list_head *links_to_free) { struct cgrp_cset_link *link, *tmp_link; list_for_each_entry_safe(link, tmp_link, links_to_free, cset_link) { list_del(&link->cset_link); kfree(link); } } /** * allocate_cgrp_cset_links - allocate cgrp_cset_links * @count: the number of links to allocate * @tmp_links: list_head the allocated links are put on * * Allocate @count cgrp_cset_link structures and chain them on @tmp_links * through ->cset_link. Returns 0 on success or -errno. */ static int allocate_cgrp_cset_links(int count, struct list_head *tmp_links) { struct cgrp_cset_link *link; int i; INIT_LIST_HEAD(tmp_links); for (i = 0; i < count; i++) { link = kzalloc(sizeof(*link), GFP_KERNEL); if (!link) { free_cgrp_cset_links(tmp_links); return -ENOMEM; } list_add(&link->cset_link, tmp_links); } return 0; } /** * link_css_set - a helper function to link a css_set to a cgroup * @tmp_links: cgrp_cset_link objects allocated by allocate_cgrp_cset_links() * @cset: the css_set to be linked * @cgrp: the destination cgroup */ static void link_css_set(struct list_head *tmp_links, struct css_set *cset, struct cgroup *cgrp) { struct cgrp_cset_link *link; BUG_ON(list_empty(tmp_links)); if (cgroup_on_dfl(cgrp)) cset->dfl_cgrp = cgrp; link = list_first_entry(tmp_links, struct cgrp_cset_link, cset_link); link->cset = cset; link->cgrp = cgrp; /* * Always add links to the tail of the lists so that the lists are * in chronological order. */ list_move_tail(&link->cset_link, &cgrp->cset_links); list_add_tail(&link->cgrp_link, &cset->cgrp_links); if (cgroup_parent(cgrp)) cgroup_get_live(cgrp); } /** * find_css_set - return a new css_set with one cgroup updated * @old_cset: the baseline css_set * @cgrp: the cgroup to be updated * * Return a new css_set that's equivalent to @old_cset, but with @cgrp * substituted into the appropriate hierarchy. */ static struct css_set *find_css_set(struct css_set *old_cset, struct cgroup *cgrp) { struct cgroup_subsys_state *template[CGROUP_SUBSYS_COUNT] = { }; struct css_set *cset; struct list_head tmp_links; struct cgrp_cset_link *link; struct cgroup_subsys *ss; unsigned long key; int ssid; lockdep_assert_held(&cgroup_mutex); /* First see if we already have a cgroup group that matches * the desired set */ spin_lock_irq(&css_set_lock); cset = find_existing_css_set(old_cset, cgrp, template); if (cset) get_css_set(cset); spin_unlock_irq(&css_set_lock); if (cset) return cset; cset = kzalloc(sizeof(*cset), GFP_KERNEL); if (!cset) return NULL; /* Allocate all the cgrp_cset_link objects that we'll need */ if (allocate_cgrp_cset_links(cgroup_root_count, &tmp_links) < 0) { kfree(cset); return NULL; } refcount_set(&cset->refcount, 1); cset->dom_cset = cset; INIT_LIST_HEAD(&cset->tasks); INIT_LIST_HEAD(&cset->mg_tasks); INIT_LIST_HEAD(&cset->dying_tasks); INIT_LIST_HEAD(&cset->task_iters); INIT_LIST_HEAD(&cset->threaded_csets); INIT_HLIST_NODE(&cset->hlist); INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->mg_src_preload_node); INIT_LIST_HEAD(&cset->mg_dst_preload_node); INIT_LIST_HEAD(&cset->mg_node); /* Copy the set of subsystem state objects generated in * find_existing_css_set() */ memcpy(cset->subsys, template, sizeof(cset->subsys)); spin_lock_irq(&css_set_lock); /* Add reference counts and links from the new css_set. */ list_for_each_entry(link, &old_cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == cgrp->root) c = cgrp; link_css_set(&tmp_links, cset, c); } BUG_ON(!list_empty(&tmp_links)); css_set_count++; /* Add @cset to the hash table */ key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cset->subsys[ssid]; list_add_tail(&cset->e_cset_node[ssid], &css->cgroup->e_csets[ssid]); css_get(css); } spin_unlock_irq(&css_set_lock); /* * If @cset should be threaded, look up the matching dom_cset and * link them up. We first fully initialize @cset then look for the * dom_cset. It's simpler this way and safe as @cset is guaranteed * to stay empty until we return. */ if (cgroup_is_threaded(cset->dfl_cgrp)) { struct css_set *dcset; dcset = find_css_set(cset, cset->dfl_cgrp->dom_cgrp); if (!dcset) { put_css_set(cset); return NULL; } spin_lock_irq(&css_set_lock); cset->dom_cset = dcset; list_add_tail(&cset->threaded_csets_node, &dcset->threaded_csets); spin_unlock_irq(&css_set_lock); } return cset; } struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root) { struct cgroup *root_cgrp = kernfs_root_to_node(kf_root)->priv; return root_cgrp->root; } void cgroup_favor_dynmods(struct cgroup_root *root, bool favor) { bool favoring = root->flags & CGRP_ROOT_FAVOR_DYNMODS; /* see the comment above CGRP_ROOT_FAVOR_DYNMODS definition */ if (favor && !favoring) { rcu_sync_enter(&cgroup_threadgroup_rwsem.rss); root->flags |= CGRP_ROOT_FAVOR_DYNMODS; } else if (!favor && favoring) { rcu_sync_exit(&cgroup_threadgroup_rwsem.rss); root->flags &= ~CGRP_ROOT_FAVOR_DYNMODS; } } static int cgroup_init_root_id(struct cgroup_root *root) { int id; lockdep_assert_held(&cgroup_mutex); id = idr_alloc_cyclic(&cgroup_hierarchy_idr, root, 0, 0, GFP_KERNEL); if (id < 0) return id; root->hierarchy_id = id; return 0; } static void cgroup_exit_root_id(struct cgroup_root *root) { lockdep_assert_held(&cgroup_mutex); idr_remove(&cgroup_hierarchy_idr, root->hierarchy_id); } void cgroup_free_root(struct cgroup_root *root) { kfree_rcu(root, rcu); } static void cgroup_destroy_root(struct cgroup_root *root) { struct cgroup *cgrp = &root->cgrp; struct cgrp_cset_link *link, *tmp_link; int ret; trace_cgroup_destroy_root(root); cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); BUG_ON(atomic_read(&root->nr_cgrps)); BUG_ON(!list_empty(&cgrp->self.children)); ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier, CGROUP_LIFETIME_OFFLINE, cgrp); WARN_ON_ONCE(notifier_to_errno(ret)); /* Rebind all subsystems back to the default hierarchy */ WARN_ON(rebind_subsystems(&cgrp_dfl_root, root->subsys_mask)); /* * Release all the links from cset_links to this hierarchy's * root cgroup */ spin_lock_irq(&css_set_lock); list_for_each_entry_safe(link, tmp_link, &cgrp->cset_links, cset_link) { list_del(&link->cset_link); list_del(&link->cgrp_link); kfree(link); } spin_unlock_irq(&css_set_lock); WARN_ON_ONCE(list_empty(&root->root_list)); list_del_rcu(&root->root_list); cgroup_root_count--; if (!have_favordynmods) cgroup_favor_dynmods(root, false); cgroup_exit_root_id(root); cgroup_unlock(); kernfs_destroy_root(root->kf_root); cgroup_free_root(root); } /* * Returned cgroup is without refcount but it's valid as long as cset pins it. */ static inline struct cgroup *__cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { struct cgroup *res_cgroup = NULL; if (cset == &init_css_set) { res_cgroup = &root->cgrp; } else if (root == &cgrp_dfl_root) { res_cgroup = cset->dfl_cgrp; } else { struct cgrp_cset_link *link; lockdep_assert_held(&css_set_lock); list_for_each_entry(link, &cset->cgrp_links, cgrp_link) { struct cgroup *c = link->cgrp; if (c->root == root) { res_cgroup = c; break; } } } /* * If cgroup_mutex is not held, the cgrp_cset_link will be freed * before we remove the cgroup root from the root_list. Consequently, * when accessing a cgroup root, the cset_link may have already been * freed, resulting in a NULL res_cgroup. However, by holding the * cgroup_mutex, we ensure that res_cgroup can't be NULL. * If we don't hold cgroup_mutex in the caller, we must do the NULL * check. */ return res_cgroup; } /* * look up cgroup associated with current task's cgroup namespace on the * specified hierarchy */ static struct cgroup * current_cgns_cgroup_from_root(struct cgroup_root *root) { struct cgroup *res = NULL; struct css_set *cset; lockdep_assert_held(&css_set_lock); rcu_read_lock(); cset = current->nsproxy->cgroup_ns->root_cset; res = __cset_cgroup_from_root(cset, root); rcu_read_unlock(); /* * The namespace_sem is held by current, so the root cgroup can't * be umounted. Therefore, we can ensure that the res is non-NULL. */ WARN_ON_ONCE(!res); return res; } /* * Look up cgroup associated with current task's cgroup namespace on the default * hierarchy. * * Unlike current_cgns_cgroup_from_root(), this doesn't need locks: * - Internal rcu_read_lock is unnecessary because we don't dereference any rcu * pointers. * - css_set_lock is not needed because we just read cset->dfl_cgrp. * - As a bonus returned cgrp is pinned with the current because it cannot * switch cgroup_ns asynchronously. */ static struct cgroup *current_cgns_cgroup_dfl(void) { struct css_set *cset; if (current->nsproxy) { cset = current->nsproxy->cgroup_ns->root_cset; return __cset_cgroup_from_root(cset, &cgrp_dfl_root); } else { /* * NOTE: This function may be called from bpf_cgroup_from_id() * on a task which has already passed exit_task_namespaces() and * nsproxy == NULL. Fall back to cgrp_dfl_root which will make all * cgroups visible for lookups. */ return &cgrp_dfl_root.cgrp; } } /* look up cgroup associated with given css_set on the specified hierarchy */ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, struct cgroup_root *root) { lockdep_assert_held(&css_set_lock); return __cset_cgroup_from_root(cset, root); } /* * Return the cgroup for "task" from the given hierarchy. Must be * called with css_set_lock held to prevent task's groups from being modified. * Must be called with either cgroup_mutex or rcu read lock to prevent the * cgroup root from being destroyed. */ struct cgroup *task_cgroup_from_root(struct task_struct *task, struct cgroup_root *root) { /* * No need to lock the task - since we hold css_set_lock the * task can't change groups. */ return cset_cgroup_from_root(task_css_set(task), root); } /* * A task must hold cgroup_mutex to modify cgroups. * * Any task can increment and decrement the count field without lock. * So in general, code holding cgroup_mutex can't rely on the count * field not changing. However, if the count goes to zero, then only * cgroup_attach_task() can increment it again. Because a count of zero * means that no tasks are currently attached, therefore there is no * way a task attached to that cgroup can fork (the other way to * increment the count). So code holding cgroup_mutex can safely * assume that if the count is zero, it will stay zero. Similarly, if * a task holds cgroup_mutex on a cgroup with zero count, it * knows that the cgroup won't be removed, as cgroup_rmdir() * needs that mutex. * * A cgroup can only be deleted if both its 'count' of using tasks * is zero, and its list of 'children' cgroups is empty. Since all * tasks in the system use _some_ cgroup, and since there is always at * least one task in the system (init, pid == 1), therefore, root cgroup * always has either children cgroups and/or using tasks. So we don't * need a special hack to ensure that root cgroup cannot be deleted. * * P.S. One more locking exception. RCU is used to guard the * update of a tasks cgroup pointer by cgroup_attach_task() */ static struct kernfs_syscall_ops cgroup_kf_syscall_ops; static char *cgroup_file_name(struct cgroup *cgrp, const struct cftype *cft, char *buf) { struct cgroup_subsys *ss = cft->ss; if (cft->ss && !(cft->flags & CFTYPE_NO_PREFIX) && !(cgrp->root->flags & CGRP_ROOT_NOPREFIX)) { const char *dbg = (cft->flags & CFTYPE_DEBUG) ? ".__DEBUG__." : ""; snprintf(buf, CGROUP_FILE_NAME_MAX, "%s%s.%s", dbg, cgroup_on_dfl(cgrp) ? ss->name : ss->legacy_name, cft->name); } else { strscpy(buf, cft->name, CGROUP_FILE_NAME_MAX); } return buf; } /** * cgroup_file_mode - deduce file mode of a control file * @cft: the control file in question * * S_IRUGO for read, S_IWUSR for write. */ static umode_t cgroup_file_mode(const struct cftype *cft) { umode_t mode = 0; if (cft->read_u64 || cft->read_s64 || cft->seq_show) mode |= S_IRUGO; if (cft->write_u64 || cft->write_s64 || cft->write) { if (cft->flags & CFTYPE_WORLD_WRITABLE) mode |= S_IWUGO; else mode |= S_IWUSR; } return mode; } /** * cgroup_calc_subtree_ss_mask - calculate subtree_ss_mask * @subtree_control: the new subtree_control mask to consider * @this_ss_mask: available subsystems * * On the default hierarchy, a subsystem may request other subsystems to be * enabled together through its ->depends_on mask. In such cases, more * subsystems than specified in "cgroup.subtree_control" may be enabled. * * This function calculates which subsystems need to be enabled if * @subtree_control is to be applied while restricted to @this_ss_mask. */ static u16 cgroup_calc_subtree_ss_mask(u16 subtree_control, u16 this_ss_mask) { u16 cur_ss_mask = subtree_control; struct cgroup_subsys *ss; int ssid; lockdep_assert_held(&cgroup_mutex); cur_ss_mask |= cgrp_dfl_implicit_ss_mask; while (true) { u16 new_ss_mask = cur_ss_mask; do_each_subsys_mask(ss, ssid, cur_ss_mask) { new_ss_mask |= ss->depends_on; } while_each_subsys_mask(); /* * Mask out subsystems which aren't available. This can * happen only if some depended-upon subsystems were bound * to non-default hierarchies. */ new_ss_mask &= this_ss_mask; if (new_ss_mask == cur_ss_mask) break; cur_ss_mask = new_ss_mask; } return cur_ss_mask; } /** * cgroup_kn_unlock - unlocking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * * This helper undoes cgroup_kn_lock_live() and should be invoked before * the method finishes if locking succeeded. Note that once this function * returns the cgroup returned by cgroup_kn_lock_live() may become * inaccessible any time. If the caller intends to continue to access the * cgroup, it should pin it before invoking this function. */ void cgroup_kn_unlock(struct kernfs_node *kn) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn_priv(kn); cgroup_unlock(); kernfs_unbreak_active_protection(kn); cgroup_put(cgrp); } /** * cgroup_kn_lock_live - locking helper for cgroup kernfs methods * @kn: the kernfs_node being serviced * @drain_offline: perform offline draining on the cgroup * * This helper is to be used by a cgroup kernfs method currently servicing * @kn. It breaks the active protection, performs cgroup locking and * verifies that the associated cgroup is alive. Returns the cgroup if * alive; otherwise, %NULL. A successful return should be undone by a * matching cgroup_kn_unlock() invocation. If @drain_offline is %true, the * cgroup is drained of offlining csses before return. * * Any cgroup kernfs method implementation which requires locking the * associated cgroup should use this helper. It avoids nesting cgroup * locking under kernfs active protection and allows all kernfs operations * including self-removal. */ struct cgroup *cgroup_kn_lock_live(struct kernfs_node *kn, bool drain_offline) { struct cgroup *cgrp; if (kernfs_type(kn) == KERNFS_DIR) cgrp = kn->priv; else cgrp = kn_priv(kn); /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. cgroup liveliness check alone provides enough * protection against removal. Ensure @cgrp stays accessible and * break the active_ref protection. */ if (!cgroup_tryget(cgrp)) return NULL; kernfs_break_active_protection(kn); if (drain_offline) cgroup_lock_and_drain_offline(cgrp); else cgroup_lock(); if (!cgroup_is_dead(cgrp)) return cgrp; cgroup_kn_unlock(kn); return NULL; } static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; lockdep_assert_held(&cgroup_mutex); if (cft->file_offset) { struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); struct cgroup_file *cfile = (void *)css + cft->file_offset; spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = NULL; spin_unlock_irq(&cgroup_file_kn_lock); timer_delete_sync(&cfile->notify_timer); } kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); } /** * css_clear_dir - remove subsys files in a cgroup directory * @css: target css */ static void css_clear_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts; if (!(css->flags & CSS_VISIBLE)) return; css->flags &= ~CSS_VISIBLE; if (css_is_self(css)) { if (cgroup_on_dfl(cgrp)) { cgroup_addrm_files(css, cgrp, cgroup_base_files, false); if (cgroup_psi_enabled()) cgroup_addrm_files(css, cgrp, cgroup_psi_files, false); } else { cgroup_addrm_files(css, cgrp, cgroup1_base_files, false); } } else { list_for_each_entry(cfts, &css->ss->cfts, node) cgroup_addrm_files(css, cgrp, cfts, false); } } /** * css_populate_dir - create subsys files in a cgroup directory * @css: target css * * On failure, no file is added. */ static int css_populate_dir(struct cgroup_subsys_state *css) { struct cgroup *cgrp = css->cgroup; struct cftype *cfts, *failed_cfts; int ret; if (css->flags & CSS_VISIBLE) return 0; if (css_is_self(css)) { if (cgroup_on_dfl(cgrp)) { ret = cgroup_addrm_files(css, cgrp, cgroup_base_files, true); if (ret < 0) return ret; if (cgroup_psi_enabled()) { ret = cgroup_addrm_files(css, cgrp, cgroup_psi_files, true); if (ret < 0) { cgroup_addrm_files(css, cgrp, cgroup_base_files, false); return ret; } } } else { ret = cgroup_addrm_files(css, cgrp, cgroup1_base_files, true); if (ret < 0) return ret; } } else { list_for_each_entry(cfts, &css->ss->cfts, node) { ret = cgroup_addrm_files(css, cgrp, cfts, true); if (ret < 0) { failed_cfts = cfts; goto err; } } } css->flags |= CSS_VISIBLE; return 0; err: list_for_each_entry(cfts, &css->ss->cfts, node) { if (cfts == failed_cfts) break; cgroup_addrm_files(css, cgrp, cfts, false); } return ret; } int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask) { struct cgroup *dcgrp = &dst_root->cgrp; struct cgroup_subsys *ss; int ssid, ret; u16 dfl_disable_ss_mask = 0; lockdep_assert_held(&cgroup_mutex); do_each_subsys_mask(ss, ssid, ss_mask) { /* * If @ss has non-root csses attached to it, can't move. * If @ss is an implicit controller, it is exempt from this * rule and can be stolen. */ if (css_next_child(NULL, cgroup_css(&ss->root->cgrp, ss)) && !ss->implicit_on_dfl) return -EBUSY; /* can't move between two non-dummy roots either */ if (ss->root != &cgrp_dfl_root && dst_root != &cgrp_dfl_root) return -EBUSY; /* * Collect ssid's that need to be disabled from default * hierarchy. */ if (ss->root == &cgrp_dfl_root) dfl_disable_ss_mask |= 1 << ssid; } while_each_subsys_mask(); if (dfl_disable_ss_mask) { struct cgroup *scgrp = &cgrp_dfl_root.cgrp; /* * Controllers from default hierarchy that need to be rebound * are all disabled together in one go. */ cgrp_dfl_root.subsys_mask &= ~dfl_disable_ss_mask; WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); } do_each_subsys_mask(ss, ssid, ss_mask) { struct cgroup_root *src_root = ss->root; struct cgroup *scgrp = &src_root->cgrp; struct cgroup_subsys_state *css = cgroup_css(scgrp, ss); struct css_set *cset, *cset_pos; struct css_task_iter *it; WARN_ON(!css || cgroup_css(dcgrp, ss)); if (src_root != &cgrp_dfl_root) { /* disable from the source */ src_root->subsys_mask &= ~(1 << ssid); WARN_ON(cgroup_apply_control(scgrp)); cgroup_finalize_control(scgrp, 0); } /* rebind */ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL); rcu_assign_pointer(dcgrp->subsys[ssid], css); ss->root = dst_root; spin_lock_irq(&css_set_lock); css->cgroup = dcgrp; WARN_ON(!list_empty(&dcgrp->e_csets[ss->id])); list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id], e_cset_node[ss->id]) { list_move_tail(&cset->e_cset_node[ss->id], &dcgrp->e_csets[ss->id]); /* * all css_sets of scgrp together in same order to dcgrp, * patch in-flight iterators to preserve correct iteration. * since the iterator is always advanced right away and * finished when it->cset_pos meets it->cset_head, so only * update it->cset_head is enough here. */ list_for_each_entry(it, &cset->task_iters, iters_node) if (it->cset_head == &scgrp->e_csets[ss->id]) it->cset_head = &dcgrp->e_csets[ss->id]; } spin_unlock_irq(&css_set_lock); /* default hierarchy doesn't enable controllers by default */ dst_root->subsys_mask |= 1 << ssid; if (dst_root == &cgrp_dfl_root) { static_branch_enable(cgroup_subsys_on_dfl_key[ssid]); } else { dcgrp->subtree_control |= 1 << ssid; static_branch_disable(cgroup_subsys_on_dfl_key[ssid]); } ret = cgroup_apply_control(dcgrp); if (ret) pr_warn("partial failure to rebind %s controller (err=%d)\n", ss->name, ret); if (ss->bind) ss->bind(css); } while_each_subsys_mask(); kernfs_activate(dcgrp->kn); return 0; } int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, struct kernfs_root *kf_root) { int len = 0; char *buf = NULL; struct cgroup_root *kf_cgroot = cgroup_root_from_kf(kf_root); struct cgroup *ns_cgroup; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) return -ENOMEM; spin_lock_irq(&css_set_lock); ns_cgroup = current_cgns_cgroup_from_root(kf_cgroot); len = kernfs_path_from_node(kf_node, ns_cgroup->kn, buf, PATH_MAX); spin_unlock_irq(&css_set_lock); if (len == -E2BIG) len = -ERANGE; else if (len > 0) { seq_escape(sf, buf, " \t\n\\"); len = 0; } kfree(buf); return len; } enum cgroup2_param { Opt_nsdelegate, Opt_favordynmods, Opt_memory_localevents, Opt_memory_recursiveprot, Opt_memory_hugetlb_accounting, Opt_pids_localevents, nr__cgroup2_params }; static const struct fs_parameter_spec cgroup2_fs_parameters[] = { fsparam_flag("nsdelegate", Opt_nsdelegate), fsparam_flag("favordynmods", Opt_favordynmods), fsparam_flag("memory_localevents", Opt_memory_localevents), fsparam_flag("memory_recursiveprot", Opt_memory_recursiveprot), fsparam_flag("memory_hugetlb_accounting", Opt_memory_hugetlb_accounting), fsparam_flag("pids_localevents", Opt_pids_localevents), {} }; static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct fs_parse_result result; int opt; opt = fs_parse(fc, cgroup2_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_nsdelegate: ctx->flags |= CGRP_ROOT_NS_DELEGATE; return 0; case Opt_favordynmods: ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; return 0; case Opt_memory_localevents: ctx->flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; return 0; case Opt_memory_recursiveprot: ctx->flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; return 0; case Opt_memory_hugetlb_accounting: ctx->flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; return 0; case Opt_pids_localevents: ctx->flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS; return 0; } return -EINVAL; } struct cgroup_of_peak *of_peak(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; return &ctx->peak; } static void apply_cgroup_root_flags(unsigned int root_flags) { if (current->nsproxy->cgroup_ns == &init_cgroup_ns) { if (root_flags & CGRP_ROOT_NS_DELEGATE) cgrp_dfl_root.flags |= CGRP_ROOT_NS_DELEGATE; else cgrp_dfl_root.flags &= ~CGRP_ROOT_NS_DELEGATE; cgroup_favor_dynmods(&cgrp_dfl_root, root_flags & CGRP_ROOT_FAVOR_DYNMODS); if (root_flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_LOCAL_EVENTS; if (root_flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_RECURSIVE_PROT; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_RECURSIVE_PROT; if (root_flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING) cgrp_dfl_root.flags |= CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; else cgrp_dfl_root.flags &= ~CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING; if (root_flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) cgrp_dfl_root.flags |= CGRP_ROOT_PIDS_LOCAL_EVENTS; else cgrp_dfl_root.flags &= ~CGRP_ROOT_PIDS_LOCAL_EVENTS; } } static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { if (cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) seq_puts(seq, ",nsdelegate"); if (cgrp_dfl_root.flags & CGRP_ROOT_FAVOR_DYNMODS) seq_puts(seq, ",favordynmods"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) seq_puts(seq, ",memory_localevents"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_RECURSIVE_PROT) seq_puts(seq, ",memory_recursiveprot"); if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING) seq_puts(seq, ",memory_hugetlb_accounting"); if (cgrp_dfl_root.flags & CGRP_ROOT_PIDS_LOCAL_EVENTS) seq_puts(seq, ",pids_localevents"); return 0; } static int cgroup_reconfigure(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); apply_cgroup_root_flags(ctx->flags); return 0; } static void init_cgroup_housekeeping(struct cgroup *cgrp) { struct cgroup_subsys *ss; int ssid; INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); cgrp->self.cgroup = cgrp; cgrp->self.flags |= CSS_ONLINE; cgrp->dom_cgrp = cgrp; cgrp->max_descendants = INT_MAX; cgrp->max_depth = INT_MAX; prev_cputime_init(&cgrp->prev_cputime); for_each_subsys(ss, ssid) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); #ifdef CONFIG_CGROUP_BPF for (int i = 0; i < ARRAY_SIZE(cgrp->bpf.revisions); i++) cgrp->bpf.revisions[i] = 1; #endif init_waitqueue_head(&cgrp->offline_waitq); INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } void init_cgroup_root(struct cgroup_fs_context *ctx) { struct cgroup_root *root = ctx->root; struct cgroup *cgrp = &root->cgrp; INIT_LIST_HEAD_RCU(&root->root_list); atomic_set(&root->nr_cgrps, 1); cgrp->root = root; init_cgroup_housekeeping(cgrp); /* DYNMODS must be modified through cgroup_favor_dynmods() */ root->flags = ctx->flags & ~CGRP_ROOT_FAVOR_DYNMODS; if (ctx->release_agent) strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX); if (ctx->name) strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN); if (ctx->cpuset_clone_children) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); } int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask) { LIST_HEAD(tmp_links); struct cgroup *root_cgrp = &root->cgrp; struct kernfs_syscall_ops *kf_sops; struct css_set *cset; int i, ret; lockdep_assert_held(&cgroup_mutex); ret = percpu_ref_init(&root_cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out; /* * We're accessing css_set_count without locking css_set_lock here, * but that's OK - it can only be increased by someone holding * cgroup_lock, and that's us. Later rebinding may disable * controllers on the default hierarchy and thus create new csets, * which can't be more than the existing ones. Allocate 2x. */ ret = allocate_cgrp_cset_links(2 * css_set_count, &tmp_links); if (ret) goto cancel_ref; ret = cgroup_init_root_id(root); if (ret) goto cancel_ref; kf_sops = root == &cgrp_dfl_root ? &cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops; root->kf_root = kernfs_create_root(kf_sops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_SUPPORT_EXPORTOP | KERNFS_ROOT_SUPPORT_USER_XATTR | KERNFS_ROOT_INVARIANT_PARENT, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); goto exit_root_id; } root_cgrp->kn = kernfs_root_to_node(root->kf_root); WARN_ON_ONCE(cgroup_ino(root_cgrp) != 1); root_cgrp->ancestors[0] = root_cgrp; ret = css_populate_dir(&root_cgrp->self); if (ret) goto destroy_root; ret = css_rstat_init(&root_cgrp->self); if (ret) goto destroy_root; ret = rebind_subsystems(root, ss_mask); if (ret) goto exit_stats; ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier, CGROUP_LIFETIME_ONLINE, root_cgrp); WARN_ON_ONCE(notifier_to_errno(ret)); trace_cgroup_setup_root(root); /* * There must be no failure case after here, since rebinding takes * care of subsystems' refcounts, which are explicitly dropped in * the failure exit path. */ list_add_rcu(&root->root_list, &cgroup_roots); cgroup_root_count++; /* * Link the root cgroup in this hierarchy into all the css_set * objects. */ spin_lock_irq(&css_set_lock); hash_for_each(css_set_table, i, cset, hlist) { link_css_set(&tmp_links, cset, root_cgrp); if (css_set_populated(cset)) cgroup_update_populated(root_cgrp, true); } spin_unlock_irq(&css_set_lock); BUG_ON(!list_empty(&root_cgrp->self.children)); BUG_ON(atomic_read(&root->nr_cgrps) != 1); ret = 0; goto out; exit_stats: css_rstat_exit(&root_cgrp->self); destroy_root: kernfs_destroy_root(root->kf_root); root->kf_root = NULL; exit_root_id: cgroup_exit_root_id(root); cancel_ref: percpu_ref_exit(&root_cgrp->self.refcnt); out: free_cgrp_cset_links(&tmp_links); return ret; } int cgroup_do_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; ctx->kfc.root = ctx->root->kf_root; if (fc->fs_type == &cgroup2_fs_type) ctx->kfc.magic = CGROUP2_SUPER_MAGIC; else ctx->kfc.magic = CGROUP_SUPER_MAGIC; ret = kernfs_get_tree(fc); /* * In non-init cgroup namespace, instead of root cgroup's dentry, * we return the dentry corresponding to the cgroupns->root_cgrp. */ if (!ret && ctx->ns != &init_cgroup_ns) { struct dentry *nsdentry; struct super_block *sb = fc->root->d_sb; struct cgroup *cgrp; cgroup_lock(); spin_lock_irq(&css_set_lock); cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root); spin_unlock_irq(&css_set_lock); cgroup_unlock(); nsdentry = kernfs_node_dentry(cgrp->kn, sb); dput(fc->root); if (IS_ERR(nsdentry)) { deactivate_locked_super(sb); ret = PTR_ERR(nsdentry); nsdentry = NULL; } fc->root = nsdentry; } if (!ctx->kfc.new_sb_created) cgroup_put(&ctx->root->cgrp); return ret; } /* * Destroy a cgroup filesystem context. */ static void cgroup_fs_context_free(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); kfree(ctx->name); kfree(ctx->release_agent); put_cgroup_ns(ctx->ns); kernfs_free_fs_context(fc); kfree(ctx); } static int cgroup_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; WRITE_ONCE(cgrp_dfl_visible, true); cgroup_get_live(&cgrp_dfl_root.cgrp); ctx->root = &cgrp_dfl_root; ret = cgroup_do_get_tree(fc); if (!ret) apply_cgroup_root_flags(ctx->flags); return ret; } static const struct fs_context_operations cgroup_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup2_parse_param, .get_tree = cgroup_get_tree, .reconfigure = cgroup_reconfigure, }; static const struct fs_context_operations cgroup1_fs_context_ops = { .free = cgroup_fs_context_free, .parse_param = cgroup1_parse_param, .get_tree = cgroup1_get_tree, .reconfigure = cgroup1_reconfigure, }; /* * Initialise the cgroup filesystem creation/reconfiguration context. Notably, * we select the namespace we're going to use. */ static int cgroup_init_fs_context(struct fs_context *fc) { struct cgroup_fs_context *ctx; ctx = kzalloc(sizeof(struct cgroup_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); fc->fs_private = &ctx->kfc; if (fc->fs_type == &cgroup2_fs_type) fc->ops = &cgroup_fs_context_ops; else fc->ops = &cgroup1_fs_context_ops; put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->ns->user_ns); fc->global = true; if (have_favordynmods) ctx->flags |= CGRP_ROOT_FAVOR_DYNMODS; return 0; } static void cgroup_kill_sb(struct super_block *sb) { struct kernfs_root *kf_root = kernfs_root_from_sb(sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); /* * If @root doesn't have any children, start killing it. * This prevents new mounts by disabling percpu_ref_tryget_live(). * * And don't kill the default root. */ if (list_empty(&root->cgrp.self.children) && root != &cgrp_dfl_root && !percpu_ref_is_dying(&root->cgrp.self.refcnt)) percpu_ref_kill(&root->cgrp.self.refcnt); cgroup_put(&root->cgrp); kernfs_kill_sb(sb); } struct file_system_type cgroup_fs_type = { .name = "cgroup", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup1_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; static struct file_system_type cgroup2_fs_type = { .name = "cgroup2", .init_fs_context = cgroup_init_fs_context, .parameters = cgroup2_fs_parameters, .kill_sb = cgroup_kill_sb, .fs_flags = FS_USERNS_MOUNT, }; #ifdef CONFIG_CPUSETS_V1 enum cpuset_param { Opt_cpuset_v2_mode, }; static const struct fs_parameter_spec cpuset_fs_parameters[] = { fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), {} }; static int cpuset_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct fs_parse_result result; int opt; opt = fs_parse(fc, cpuset_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_cpuset_v2_mode: ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; return 0; } return -EINVAL; } static const struct fs_context_operations cpuset_fs_context_ops = { .get_tree = cgroup1_get_tree, .free = cgroup_fs_context_free, .parse_param = cpuset_parse_param, }; /* * This is ugly, but preserves the userspace API for existing cpuset * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead */ static int cpuset_init_fs_context(struct fs_context *fc) { char *agent = kstrdup("/sbin/cpuset_release_agent", GFP_USER); struct cgroup_fs_context *ctx; int err; err = cgroup_init_fs_context(fc); if (err) { kfree(agent); return err; } fc->ops = &cpuset_fs_context_ops; ctx = cgroup_fc2context(fc); ctx->subsys_mask = 1 << cpuset_cgrp_id; ctx->flags |= CGRP_ROOT_NOPREFIX; ctx->release_agent = agent; get_filesystem(&cgroup_fs_type); put_filesystem(fc->fs_type); fc->fs_type = &cgroup_fs_type; return 0; } static struct file_system_type cpuset_fs_type = { .name = "cpuset", .init_fs_context = cpuset_init_fs_context, .parameters = cpuset_fs_parameters, .fs_flags = FS_USERNS_MOUNT, }; #endif int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { struct cgroup *root = cset_cgroup_from_root(ns->root_cset, cgrp->root); return kernfs_path_from_node(cgrp->kn, root->kn, buf, buflen); } int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { int ret; cgroup_lock(); spin_lock_irq(&css_set_lock); ret = cgroup_path_ns_locked(cgrp, buf, buflen, ns); spin_unlock_irq(&css_set_lock); cgroup_unlock(); return ret; } EXPORT_SYMBOL_GPL(cgroup_path_ns); /** * cgroup_attach_lock - Lock for ->attach() * @lock_threadgroup: whether to down_write cgroup_threadgroup_rwsem * * cgroup migration sometimes needs to stabilize threadgroups against forks and * exits by write-locking cgroup_threadgroup_rwsem. However, some ->attach() * implementations (e.g. cpuset), also need to disable CPU hotplug. * Unfortunately, letting ->attach() operations acquire cpus_read_lock() can * lead to deadlocks. * * Bringing up a CPU may involve creating and destroying tasks which requires * read-locking threadgroup_rwsem, so threadgroup_rwsem nests inside * cpus_read_lock(). If we call an ->attach() which acquires the cpus lock while * write-locking threadgroup_rwsem, the locking order is reversed and we end up * waiting for an on-going CPU hotplug operation which in turn is waiting for * the threadgroup_rwsem to be released to create new tasks. For more details: * * http://lkml.kernel.org/r/20220711174629.uehfmqegcwn2lqzu@wubuntu * * Resolve the situation by always acquiring cpus_read_lock() before optionally * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that * CPU hotplug is disabled on entry. */ void cgroup_attach_lock(bool lock_threadgroup) { cpus_read_lock(); if (lock_threadgroup) percpu_down_write(&cgroup_threadgroup_rwsem); } /** * cgroup_attach_unlock - Undo cgroup_attach_lock() * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem */ void cgroup_attach_unlock(bool lock_threadgroup) { if (lock_threadgroup) percpu_up_write(&cgroup_threadgroup_rwsem); cpus_read_unlock(); } /** * cgroup_migrate_add_task - add a migration target task to a migration context * @task: target task * @mgctx: target migration context * * Add @task, which is a migration target, to @mgctx->tset. This function * becomes noop if @task doesn't need to be migrated. @task's css_set * should have been added as a migration source and @task->cg_list will be * moved from the css_set's tasks list to mg_tasks one. */ static void cgroup_migrate_add_task(struct task_struct *task, struct cgroup_mgctx *mgctx) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* @task either already exited or can't exit until the end */ if (task->flags & PF_EXITING) return; /* cgroup_threadgroup_rwsem protects racing against forks */ WARN_ON_ONCE(list_empty(&task->cg_list)); cset = task_css_set(task); if (!cset->mg_src_cgrp) return; mgctx->tset.nr_tasks++; list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, &mgctx->tset.src_csets); if (list_empty(&cset->mg_dst_cset->mg_node)) list_add_tail(&cset->mg_dst_cset->mg_node, &mgctx->tset.dst_csets); } /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; return cgroup_taskset_next(tset, dst_cssp); } /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; while (CGROUP_HAS_SUBSYS_CONFIG && &cset->mg_node != tset->csets) { if (!task) task = list_first_entry(&cset->mg_tasks, struct task_struct, cg_list); else task = list_next_entry(task, cg_list); if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; /* * This function may be called both before and * after cgroup_migrate_execute(). The two cases * can be distinguished by looking at whether @cset * has its ->mg_dst_cset set. */ if (cset->mg_dst_cset) *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; else *dst_cssp = cset->subsys[tset->ssid]; return task; } cset = list_next_entry(cset, mg_node); task = NULL; } return NULL; } /** * cgroup_migrate_execute - migrate a taskset * @mgctx: migration context * * Migrate tasks in @mgctx as setup by migration preparation functions. * This function fails iff one of the ->can_attach callbacks fails and * guarantees that either all or none of the tasks in @mgctx are migrated. * @mgctx is consumed regardless of success. */ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) { struct cgroup_taskset *tset = &mgctx->tset; struct cgroup_subsys *ss; struct task_struct *task, *tmp_task; struct css_set *cset, *tmp_cset; int ssid, failed_ssid, ret; /* check that we can legitimately attach to the cgroup */ if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->can_attach) { tset->ssid = ssid; ret = ss->can_attach(tset); if (ret) { failed_ssid = ssid; goto out_cancel_attach; } } } while_each_subsys_mask(); } /* * Now that we're guaranteed success, proceed to move all tasks to * the new cgroup. There are no failure cases after here, so this * is the commit point. */ spin_lock_irq(&css_set_lock); list_for_each_entry(cset, &tset->src_csets, mg_node) { list_for_each_entry_safe(task, tmp_task, &cset->mg_tasks, cg_list) { struct css_set *from_cset = task_css_set(task); struct css_set *to_cset = cset->mg_dst_cset; get_css_set(to_cset); to_cset->nr_tasks++; css_set_move_task(task, from_cset, to_cset, true); from_cset->nr_tasks--; /* * If the source or destination cgroup is frozen, * the task might require to change its state. */ cgroup_freezer_migrate_task(task, from_cset->dfl_cgrp, to_cset->dfl_cgrp); put_css_set_locked(from_cset); } } spin_unlock_irq(&css_set_lock); /* * Migration is committed, all target tasks are now on dst_csets. * Nothing is sensitive to fork() after this point. Notify * controllers that migration is complete. */ tset->csets = &tset->dst_csets; if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ss->attach) { tset->ssid = ssid; ss->attach(tset); } } while_each_subsys_mask(); } ret = 0; goto out_release_tset; out_cancel_attach: if (tset->nr_tasks) { do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { if (ssid == failed_ssid) break; if (ss->cancel_attach) { tset->ssid = ssid; ss->cancel_attach(tset); } } while_each_subsys_mask(); } out_release_tset: spin_lock_irq(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); list_for_each_entry_safe(cset, tmp_cset, &tset->src_csets, mg_node) { list_splice_tail_init(&cset->mg_tasks, &cset->tasks); list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); /* * Re-initialize the cgroup_taskset structure in case it is reused * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() * iteration. */ tset->nr_tasks = 0; tset->csets = &tset->src_csets; return ret; } /** * cgroup_migrate_vet_dst - verify whether a cgroup can be migration destination * @dst_cgrp: destination cgroup to test * * On the default hierarchy, except for the mixable, (possible) thread root * and threaded cgroups, subtree_control must be zero for migration * destination cgroups with tasks so that child cgroups don't compete * against tasks. */ int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp) { /* v1 doesn't have any restriction */ if (!cgroup_on_dfl(dst_cgrp)) return 0; /* verify @dst_cgrp can host resources */ if (!cgroup_is_valid_domain(dst_cgrp->dom_cgrp)) return -EOPNOTSUPP; /* * If @dst_cgrp is already or can become a thread root or is * threaded, it doesn't matter. */ if (cgroup_can_be_thread_root(dst_cgrp) || cgroup_is_threaded(dst_cgrp)) return 0; /* apply no-internal-process constraint */ if (dst_cgrp->subtree_control) return -EBUSY; return 0; } /** * cgroup_migrate_finish - cleanup after attach * @mgctx: migration context * * Undo cgroup_migrate_add_src() and cgroup_migrate_prepare_dst(). See * those functions for details. */ void cgroup_migrate_finish(struct cgroup_mgctx *mgctx) { struct css_set *cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_src_preload_node); put_css_set_locked(cset); } list_for_each_entry_safe(cset, tmp_cset, &mgctx->preloaded_dst_csets, mg_dst_preload_node) { cset->mg_src_cgrp = NULL; cset->mg_dst_cgrp = NULL; cset->mg_dst_cset = NULL; list_del_init(&cset->mg_dst_preload_node); put_css_set_locked(cset); } spin_unlock_irq(&css_set_lock); } /** * cgroup_migrate_add_src - add a migration source css_set * @src_cset: the source css_set to add * @dst_cgrp: the destination cgroup * @mgctx: migration context * * Tasks belonging to @src_cset are about to be migrated to @dst_cgrp. Pin * @src_cset and add it to @mgctx->src_csets, which should later be cleaned * up by cgroup_migrate_finish(). * * This function may be called without holding cgroup_threadgroup_rwsem * even if the target is a process. Threads may be created and destroyed * but as long as cgroup_mutex is not dropped, no new css_set can be put * into play and the preloaded css_sets are guaranteed to cover all * migrations. */ void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx) { struct cgroup *src_cgrp; lockdep_assert_held(&cgroup_mutex); lockdep_assert_held(&css_set_lock); /* * If ->dead, @src_set is associated with one or more dead cgroups * and doesn't contain any migratable tasks. Ignore it early so * that the rest of migration path doesn't get confused by it. */ if (src_cset->dead) return; if (!list_empty(&src_cset->mg_src_preload_node)) return; src_cgrp = cset_cgroup_from_root(src_cset, dst_cgrp->root); WARN_ON(src_cset->mg_src_cgrp); WARN_ON(src_cset->mg_dst_cgrp); WARN_ON(!list_empty(&src_cset->mg_tasks)); WARN_ON(!list_empty(&src_cset->mg_node)); src_cset->mg_src_cgrp = src_cgrp; src_cset->mg_dst_cgrp = dst_cgrp; get_css_set(src_cset); list_add_tail(&src_cset->mg_src_preload_node, &mgctx->preloaded_src_csets); } /** * cgroup_migrate_prepare_dst - prepare destination css_sets for migration * @mgctx: migration context * * Tasks are about to be moved and all the source css_sets have been * preloaded to @mgctx->preloaded_src_csets. This function looks up and * pins all destination css_sets, links each to its source, and append them * to @mgctx->preloaded_dst_csets. * * This function must be called after cgroup_migrate_add_src() has been * called on each migration source css_set. After migration is performed * using cgroup_migrate(), cgroup_migrate_finish() must be called on * @mgctx. */ int cgroup_migrate_prepare_dst(struct cgroup_mgctx *mgctx) { struct css_set *src_cset, *tmp_cset; lockdep_assert_held(&cgroup_mutex); /* look up the dst cset for each src cset and link it to src */ list_for_each_entry_safe(src_cset, tmp_cset, &mgctx->preloaded_src_csets, mg_src_preload_node) { struct css_set *dst_cset; struct cgroup_subsys *ss; int ssid; dst_cset = find_css_set(src_cset, src_cset->mg_dst_cgrp); if (!dst_cset) return -ENOMEM; WARN_ON_ONCE(src_cset->mg_dst_cset || dst_cset->mg_dst_cset); /* * If src cset equals dst, it's noop. Drop the src. * cgroup_migrate() will skip the cset too. Note that we * can't handle src == dst as some nodes are used by both. */ if (src_cset == dst_cset) { src_cset->mg_src_cgrp = NULL; src_cset->mg_dst_cgrp = NULL; list_del_init(&src_cset->mg_src_preload_node); put_css_set(src_cset); put_css_set(dst_cset); continue; } src_cset->mg_dst_cset = dst_cset; if (list_empty(&dst_cset->mg_dst_preload_node)) list_add_tail(&dst_cset->mg_dst_preload_node, &mgctx->preloaded_dst_csets); else put_css_set(dst_cset); for_each_subsys(ss, ssid) if (src_cset->subsys[ssid] != dst_cset->subsys[ssid]) mgctx->ss_mask |= 1 << ssid; } return 0; } /** * cgroup_migrate - migrate a process or task to a cgroup * @leader: the leader of the process or the task to migrate * @threadgroup: whether @leader points to the whole process or a single task * @mgctx: migration context * * Migrate a process or task denoted by @leader. If migrating a process, * the caller must be holding cgroup_threadgroup_rwsem. The caller is also * responsible for invoking cgroup_migrate_add_src() and * cgroup_migrate_prepare_dst() on the targets before invoking this * function and following up with cgroup_migrate_finish(). * * As long as a controller's ->can_attach() doesn't fail, this function is * guaranteed to succeed. This means that, excluding ->can_attach() * failure, when migrating multiple targets, the success or failure can be * decided for all targets by invoking group_migrate_prepare_dst() before * actually starting migrating. */ int cgroup_migrate(struct task_struct *leader, bool threadgroup, struct cgroup_mgctx *mgctx) { struct task_struct *task; /* * The following thread iteration should be inside an RCU critical * section to prevent tasks from being freed while taking the snapshot. * spin_lock_irq() implies RCU critical section here. */ spin_lock_irq(&css_set_lock); task = leader; do { cgroup_migrate_add_task(task, mgctx); if (!threadgroup) break; } while_each_thread(leader, task); spin_unlock_irq(&css_set_lock); return cgroup_migrate_execute(mgctx); } /** * cgroup_attach_task - attach a task or a whole threadgroup to a cgroup * @dst_cgrp: the cgroup to attach to * @leader: the task or the leader of the threadgroup to be attached * @threadgroup: attach the whole threadgroup? * * Call holding cgroup_mutex and cgroup_threadgroup_rwsem. */ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup) { DEFINE_CGROUP_MGCTX(mgctx); struct task_struct *task; int ret = 0; /* look up all src csets */ spin_lock_irq(&css_set_lock); rcu_read_lock(); task = leader; do { cgroup_migrate_add_src(task_css_set(task), dst_cgrp, &mgctx); if (!threadgroup) break; } while_each_thread(leader, task); rcu_read_unlock(); spin_unlock_irq(&css_set_lock); /* prepare dst csets and commit */ ret = cgroup_migrate_prepare_dst(&mgctx); if (!ret) ret = cgroup_migrate(leader, threadgroup, &mgctx); cgroup_migrate_finish(&mgctx); if (!ret) TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup); return ret; } struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup, bool *threadgroup_locked) { struct task_struct *tsk; pid_t pid; if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) return ERR_PTR(-EINVAL); /* * If we migrate a single thread, we don't care about threadgroup * stability. If the thread is `current`, it won't exit(2) under our * hands or change PID through exec(2). We exclude * cgroup_update_dfl_csses and other cgroup_{proc,thread}s_write * callers by cgroup_mutex. * Therefore, we can skip the global lock. */ lockdep_assert_held(&cgroup_mutex); *threadgroup_locked = pid || threadgroup; cgroup_attach_lock(*threadgroup_locked); rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { tsk = ERR_PTR(-ESRCH); goto out_unlock_threadgroup; } } else { tsk = current; } if (threadgroup) tsk = tsk->group_leader; /* * kthreads may acquire PF_NO_SETAFFINITY during initialization. * If userland migrates such a kthread to a non-root cgroup, it can * become trapped in a cpuset, or RT kthread may be born in a * cgroup with no rt_runtime allocated. Just say no. */ if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) { tsk = ERR_PTR(-EINVAL); goto out_unlock_threadgroup; } get_task_struct(tsk); goto out_unlock_rcu; out_unlock_threadgroup: cgroup_attach_unlock(*threadgroup_locked); *threadgroup_locked = false; out_unlock_rcu: rcu_read_unlock(); return tsk; } void cgroup_procs_write_finish(struct task_struct *task, bool threadgroup_locked) { struct cgroup_subsys *ss; int ssid; /* release reference from cgroup_procs_write_start() */ put_task_struct(task); cgroup_attach_unlock(threadgroup_locked); for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); } static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) { struct cgroup_subsys *ss; bool printed = false; int ssid; do_each_subsys_mask(ss, ssid, ss_mask) { if (printed) seq_putc(seq, ' '); seq_puts(seq, ss->name); printed = true; } while_each_subsys_mask(); if (printed) seq_putc(seq, '\n'); } /* show controllers which are enabled from the parent */ static int cgroup_controllers_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgroup_control(cgrp)); return 0; } /* show controllers which are enabled for a given cgroup's children */ static int cgroup_subtree_control_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; cgroup_print_ss_mask(seq, cgrp->subtree_control); return 0; } /** * cgroup_update_dfl_csses - update css assoc of a subtree in default hierarchy * @cgrp: root of the subtree to update csses for * * @cgrp's control masks have changed and its subtree's css associations * need to be updated accordingly. This function looks up all css_sets * which are attached to the subtree, creates the matching updated css_sets * and migrates the tasks to the new ones. */ static int cgroup_update_dfl_csses(struct cgroup *cgrp) { DEFINE_CGROUP_MGCTX(mgctx); struct cgroup_subsys_state *d_css; struct cgroup *dsct; struct css_set *src_cset; bool has_tasks; int ret; lockdep_assert_held(&cgroup_mutex); /* look up all csses currently attached to @cgrp's subtree */ spin_lock_irq(&css_set_lock); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { struct cgrp_cset_link *link; /* * As cgroup_update_dfl_csses() is only called by * cgroup_apply_control(). The csses associated with the * given cgrp will not be affected by changes made to * its subtree_control file. We can skip them. */ if (dsct == cgrp) continue; list_for_each_entry(link, &dsct->cset_links, cset_link) cgroup_migrate_add_src(link->cset, dsct, &mgctx); } spin_unlock_irq(&css_set_lock); /* * We need to write-lock threadgroup_rwsem while migrating tasks. * However, if there are no source csets for @cgrp, changing its * controllers isn't gonna produce any task migrations and the * write-locking can be skipped safely. */ has_tasks = !list_empty(&mgctx.preloaded_src_csets); cgroup_attach_lock(has_tasks); /* NULL dst indicates self on default hierarchy */ ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_finish; spin_lock_irq(&css_set_lock); list_for_each_entry(src_cset, &mgctx.preloaded_src_csets, mg_src_preload_node) { struct task_struct *task, *ntask; /* all tasks in src_csets need to be migrated */ list_for_each_entry_safe(task, ntask, &src_cset->tasks, cg_list) cgroup_migrate_add_task(task, &mgctx); } spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_execute(&mgctx); out_finish: cgroup_migrate_finish(&mgctx); cgroup_attach_unlock(has_tasks); return ret; } /** * cgroup_lock_and_drain_offline - lock cgroup_mutex and drain offlined csses * @cgrp: root of the target subtree * * Because css offlining is asynchronous, userland may try to re-enable a * controller while the previous css is still around. This function grabs * cgroup_mutex and drains the previous css instances of @cgrp's subtree. */ void cgroup_lock_and_drain_offline(struct cgroup *cgrp) __acquires(&cgroup_mutex) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; restart: cgroup_lock(); cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); DEFINE_WAIT(wait); if (!css || !percpu_ref_is_dying(&css->refcnt)) continue; cgroup_get_live(dsct); prepare_to_wait(&dsct->offline_waitq, &wait, TASK_UNINTERRUPTIBLE); cgroup_unlock(); schedule(); finish_wait(&dsct->offline_waitq, &wait); cgroup_put(dsct); goto restart; } } } /** * cgroup_save_control - save control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Save ->subtree_control, ->subtree_ss_mask and ->dom_cgrp to the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_save_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->old_subtree_control = dsct->subtree_control; dsct->old_subtree_ss_mask = dsct->subtree_ss_mask; dsct->old_dom_cgrp = dsct->dom_cgrp; } } /** * cgroup_propagate_control - refresh control masks of a subtree * @cgrp: root of the target subtree * * For @cgrp and its subtree, ensure ->subtree_ss_mask matches * ->subtree_control and propagate controller availability through the * subtree so that descendants don't have unavailable controllers enabled. */ static void cgroup_propagate_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { dsct->subtree_control &= cgroup_control(dsct); dsct->subtree_ss_mask = cgroup_calc_subtree_ss_mask(dsct->subtree_control, cgroup_ss_mask(dsct)); } } /** * cgroup_restore_control - restore control masks and dom_cgrp of a subtree * @cgrp: root of the target subtree * * Restore ->subtree_control, ->subtree_ss_mask and ->dom_cgrp from the * respective old_ prefixed fields for @cgrp's subtree including @cgrp * itself. */ static void cgroup_restore_control(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { dsct->subtree_control = dsct->old_subtree_control; dsct->subtree_ss_mask = dsct->old_subtree_ss_mask; dsct->dom_cgrp = dsct->old_dom_cgrp; } } static bool css_visible(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; if (cgroup_control(cgrp) & (1 << ss->id)) return true; if (!(cgroup_ss_mask(cgrp) & (1 << ss->id))) return false; return cgroup_on_dfl(cgrp) && ss->implicit_on_dfl; } /** * cgroup_apply_control_enable - enable or show csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and create new csses or make the existing ones * visible. A css is created invisible if it's being implicitly enabled * through dependency. An invisible css is made visible when the userland * explicitly enables it. * * Returns 0 on success, -errno on failure. On failure, csses which have * been processed already aren't cleaned up. The caller is responsible for * cleaning up with cgroup_apply_control_disable(). */ static int cgroup_apply_control_enable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid, ret; cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); if (!(cgroup_ss_mask(dsct) & (1 << ss->id))) continue; if (!css) { css = css_create(dsct, ss); if (IS_ERR(css)) return PTR_ERR(css); } WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); if (css_visible(css)) { ret = css_populate_dir(css); if (ret) return ret; } } } return 0; } /** * cgroup_apply_control_disable - kill or hide csses according to control * @cgrp: root of the target subtree * * Walk @cgrp's subtree and kill and hide csses so that they match * cgroup_ss_mask() and cgroup_visible_mask(). * * A css is hidden when the userland requests it to be disabled while other * subsystems are still depending on it. The css must not actively control * resources and be in the vanilla state if it's made visible again later. * Controllers which may be depended upon should provide ->css_reset() for * this purpose. */ static void cgroup_apply_control_disable(struct cgroup *cgrp) { struct cgroup *dsct; struct cgroup_subsys_state *d_css; struct cgroup_subsys *ss; int ssid; cgroup_for_each_live_descendant_post(dsct, d_css, cgrp) { for_each_subsys(ss, ssid) { struct cgroup_subsys_state *css = cgroup_css(dsct, ss); if (!css) continue; WARN_ON_ONCE(percpu_ref_is_dying(&css->refcnt)); if (css->parent && !(cgroup_ss_mask(dsct) & (1 << ss->id))) { kill_css(css); } else if (!css_visible(css)) { css_clear_dir(css); if (ss->css_reset) ss->css_reset(css); } } } } /** * cgroup_apply_control - apply control mask updates to the subtree * @cgrp: root of the target subtree * * subsystems can be enabled and disabled in a subtree using the following * steps. * * 1. Call cgroup_save_control() to stash the current state. * 2. Update ->subtree_control masks in the subtree as desired. * 3. Call cgroup_apply_control() to apply the changes. * 4. Optionally perform other related operations. * 5. Call cgroup_finalize_control() to finish up. * * This function implements step 3 and propagates the mask changes * throughout @cgrp's subtree, updates csses accordingly and perform * process migrations. */ static int cgroup_apply_control(struct cgroup *cgrp) { int ret; cgroup_propagate_control(cgrp); ret = cgroup_apply_control_enable(cgrp); if (ret) return ret; /* * At this point, cgroup_e_css_by_mask() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ return cgroup_update_dfl_csses(cgrp); } /** * cgroup_finalize_control - finalize control mask update * @cgrp: root of the target subtree * @ret: the result of the update * * Finalize control mask update. See cgroup_apply_control() for more info. */ static void cgroup_finalize_control(struct cgroup *cgrp, int ret) { if (ret) { cgroup_restore_control(cgrp); cgroup_propagate_control(cgrp); } cgroup_apply_control_disable(cgrp); } static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u16 enable) { u16 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask; /* if nothing is getting enabled, nothing to worry about */ if (!enable) return 0; /* can @cgrp host any resources? */ if (!cgroup_is_valid_domain(cgrp->dom_cgrp)) return -EOPNOTSUPP; /* mixables don't care */ if (cgroup_is_mixable(cgrp)) return 0; if (domain_enable) { /* can't enable domain controllers inside a thread subtree */ if (cgroup_is_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return -EOPNOTSUPP; } else { /* * Threaded controllers can handle internal competitions * and are always allowed inside a (prospective) thread * subtree. */ if (cgroup_can_be_thread_root(cgrp) || cgroup_is_threaded(cgrp)) return 0; } /* * Controllers can't be enabled for a cgroup with tasks to avoid * child cgroups competing against tasks. */ if (cgroup_has_tasks(cgrp)) return -EBUSY; return 0; } /* change the enabled child controllers for a cgroup in the default hierarchy */ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { u16 enable = 0, disable = 0; struct cgroup *cgrp, *child; struct cgroup_subsys *ss; char *tok; int ssid, ret; /* * Parse input - space separated list of subsystem names prefixed * with either + or -. */ buf = strstrip(buf); while ((tok = strsep(&buf, " "))) { if (tok[0] == '\0') continue; do_each_subsys_mask(ss, ssid, ~cgrp_dfl_inhibit_ss_mask) { if (!cgroup_ssid_enabled(ssid) || strcmp(tok + 1, ss->name)) continue; if (*tok == '+') { enable |= 1 << ssid; disable &= ~(1 << ssid); } else if (*tok == '-') { disable |= 1 << ssid; enable &= ~(1 << ssid); } else { return -EINVAL; } break; } while_each_subsys_mask(); if (ssid == CGROUP_SUBSYS_COUNT) return -EINVAL; } cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENODEV; for_each_subsys(ss, ssid) { if (enable & (1 << ssid)) { if (cgrp->subtree_control & (1 << ssid)) { enable &= ~(1 << ssid); continue; } if (!(cgroup_control(cgrp) & (1 << ssid))) { ret = -ENOENT; goto out_unlock; } } else if (disable & (1 << ssid)) { if (!(cgrp->subtree_control & (1 << ssid))) { disable &= ~(1 << ssid); continue; } /* a child has it enabled? */ cgroup_for_each_live_child(child, cgrp) { if (child->subtree_control & (1 << ssid)) { ret = -EBUSY; goto out_unlock; } } } } if (!enable && !disable) { ret = 0; goto out_unlock; } ret = cgroup_vet_subtree_control_enable(cgrp, enable); if (ret) goto out_unlock; /* save and update control masks and prepare csses */ cgroup_save_control(cgrp); cgrp->subtree_control |= enable; cgrp->subtree_control &= ~disable; ret = cgroup_apply_control(cgrp); cgroup_finalize_control(cgrp, ret); if (ret) goto out_unlock; kernfs_activate(cgrp->kn); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } /** * cgroup_enable_threaded - make @cgrp threaded * @cgrp: the target cgroup * * Called when "threaded" is written to the cgroup.type interface file and * tries to make @cgrp threaded and join the parent's resource domain. * This function is never called on the root cgroup as cgroup.type doesn't * exist on it. */ static int cgroup_enable_threaded(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup *dom_cgrp = parent->dom_cgrp; struct cgroup *dsct; struct cgroup_subsys_state *d_css; int ret; lockdep_assert_held(&cgroup_mutex); /* noop if already threaded */ if (cgroup_is_threaded(cgrp)) return 0; /* * If @cgroup is populated or has domain controllers enabled, it * can't be switched. While the below cgroup_can_be_thread_root() * test can catch the same conditions, that's only when @parent is * not mixable, so let's check it explicitly. */ if (cgroup_is_populated(cgrp) || cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) return -EOPNOTSUPP; /* we're joining the parent's domain, ensure its validity */ if (!cgroup_is_valid_domain(dom_cgrp) || !cgroup_can_be_thread_root(dom_cgrp)) return -EOPNOTSUPP; /* * The following shouldn't cause actual migrations and should * always succeed. */ cgroup_save_control(cgrp); cgroup_for_each_live_descendant_pre(dsct, d_css, cgrp) if (dsct == cgrp || cgroup_is_threaded(dsct)) dsct->dom_cgrp = dom_cgrp; ret = cgroup_apply_control(cgrp); if (!ret) parent->nr_threaded_children++; cgroup_finalize_control(cgrp, ret); return ret; } static int cgroup_type_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; if (cgroup_is_threaded(cgrp)) seq_puts(seq, "threaded\n"); else if (!cgroup_is_valid_domain(cgrp)) seq_puts(seq, "domain invalid\n"); else if (cgroup_is_thread_root(cgrp)) seq_puts(seq, "domain threaded\n"); else seq_puts(seq, "domain\n"); return 0; } static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; int ret; /* only switching to threaded mode is supported */ if (strcmp(strstrip(buf), "threaded")) return -EINVAL; /* drain dying csses before we re-apply (threaded) subtree control */ cgrp = cgroup_kn_lock_live(of->kn, true); if (!cgrp) return -ENOENT; /* threaded can only be enabled */ ret = cgroup_enable_threaded(cgrp); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static int cgroup_max_descendants_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; int descendants = READ_ONCE(cgrp->max_descendants); if (descendants == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", descendants); return 0; } static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; int descendants; ssize_t ret; buf = strstrip(buf); if (!strcmp(buf, "max")) { descendants = INT_MAX; } else { ret = kstrtoint(buf, 0, &descendants); if (ret) return ret; } if (descendants < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgrp->max_descendants = descendants; cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_max_depth_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; int depth = READ_ONCE(cgrp->max_depth); if (depth == INT_MAX) seq_puts(seq, "max\n"); else seq_printf(seq, "%d\n", depth); return 0; } static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; ssize_t ret; int depth; buf = strstrip(buf); if (!strcmp(buf, "max")) { depth = INT_MAX; } else { ret = kstrtoint(buf, 0, &depth); if (ret) return ret; } if (depth < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgrp->max_depth = depth; cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_events_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; seq_printf(seq, "populated %d\n", cgroup_is_populated(cgrp)); seq_printf(seq, "frozen %d\n", test_bit(CGRP_FROZEN, &cgrp->flags)); return 0; } static int cgroup_stat_show(struct seq_file *seq, void *v) { struct cgroup *cgroup = seq_css(seq)->cgroup; struct cgroup_subsys_state *css; int dying_cnt[CGROUP_SUBSYS_COUNT]; int ssid; seq_printf(seq, "nr_descendants %d\n", cgroup->nr_descendants); /* * Show the number of live and dying csses associated with each of * non-inhibited cgroup subsystems that is bound to cgroup v2. * * Without proper lock protection, racing is possible. So the * numbers may not be consistent when that happens. */ rcu_read_lock(); for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) { dying_cnt[ssid] = -1; if ((BIT(ssid) & cgrp_dfl_inhibit_ss_mask) || (cgroup_subsys[ssid]->root != &cgrp_dfl_root)) continue; css = rcu_dereference_raw(cgroup->subsys[ssid]); dying_cnt[ssid] = cgroup->nr_dying_subsys[ssid]; seq_printf(seq, "nr_subsys_%s %d\n", cgroup_subsys[ssid]->name, css ? (css->nr_descendants + 1) : 0); } seq_printf(seq, "nr_dying_descendants %d\n", cgroup->nr_dying_descendants); for (ssid = 0; ssid < CGROUP_SUBSYS_COUNT; ssid++) { if (dying_cnt[ssid] >= 0) seq_printf(seq, "nr_dying_subsys_%s %d\n", cgroup_subsys[ssid]->name, dying_cnt[ssid]); } rcu_read_unlock(); return 0; } #ifdef CONFIG_CGROUP_SCHED /** * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest * * Find and get @cgrp's css associated with @ss. If the css doesn't exist * or is offline, %NULL is returned. */ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup_subsys_state *css; rcu_read_lock(); css = cgroup_css(cgrp, ss); if (css && !css_tryget_online(css)) css = NULL; rcu_read_unlock(); return css; } static int cgroup_extra_stat_show(struct seq_file *seq, int ssid) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct cgroup_subsys *ss = cgroup_subsys[ssid]; struct cgroup_subsys_state *css; int ret; if (!ss->css_extra_stat_show) return 0; css = cgroup_tryget_css(cgrp, ss); if (!css) return 0; ret = ss->css_extra_stat_show(seq, css); css_put(css); return ret; } static int cgroup_local_stat_show(struct seq_file *seq, struct cgroup *cgrp, int ssid) { struct cgroup_subsys *ss = cgroup_subsys[ssid]; struct cgroup_subsys_state *css; int ret; if (!ss->css_local_stat_show) return 0; css = cgroup_tryget_css(cgrp, ss); if (!css) return 0; ret = ss->css_local_stat_show(seq, css); css_put(css); return ret; } #endif static int cpu_stat_show(struct seq_file *seq, void *v) { int ret = 0; cgroup_base_stat_cputime_show(seq); #ifdef CONFIG_CGROUP_SCHED ret = cgroup_extra_stat_show(seq, cpu_cgrp_id); #endif return ret; } static int cpu_local_stat_show(struct seq_file *seq, void *v) { struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup; int ret = 0; #ifdef CONFIG_CGROUP_SCHED ret = cgroup_local_stat_show(seq, cgrp, cpu_cgrp_id); #endif return ret; } #ifdef CONFIG_PSI static int cgroup_io_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IO); } static int cgroup_memory_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_MEM); } static int cgroup_cpu_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_CPU); } static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, enum psi_res res) { struct cgroup_file_ctx *ctx = of->priv; struct psi_trigger *new; struct cgroup *cgrp; struct psi_group *psi; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; cgroup_get(cgrp); cgroup_kn_unlock(of->kn); /* Allow only one trigger per file descriptor */ if (ctx->psi.trigger) { cgroup_put(cgrp); return -EBUSY; } psi = cgroup_psi(cgrp); new = psi_trigger_create(psi, buf, res, of->file, of); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); } smp_store_release(&ctx->psi.trigger, new); cgroup_put(cgrp); return nbytes; } static ssize_t cgroup_io_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_IO); } static ssize_t cgroup_memory_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_MEM); } static ssize_t cgroup_cpu_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_CPU); } #ifdef CONFIG_IRQ_TIME_ACCOUNTING static int cgroup_irq_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); return psi_show(seq, psi, PSI_IRQ); } static ssize_t cgroup_irq_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return pressure_write(of, buf, nbytes, PSI_IRQ); } #endif static int cgroup_pressure_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; struct psi_group *psi = cgroup_psi(cgrp); seq_printf(seq, "%d\n", psi->enabled); return 0; } static ssize_t cgroup_pressure_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { ssize_t ret; int enable; struct cgroup *cgrp; struct psi_group *psi; ret = kstrtoint(strstrip(buf), 0, &enable); if (ret) return ret; if (enable < 0 || enable > 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; psi = cgroup_psi(cgrp); if (psi->enabled != enable) { int i; /* show or hide {cpu,memory,io,irq}.pressure files */ for (i = 0; i < NR_PSI_RESOURCES; i++) cgroup_file_show(&cgrp->psi_files[i], enable); psi->enabled = enable; if (enable) psi_cgroup_restart(psi); } cgroup_kn_unlock(of->kn); return nbytes; } static __poll_t cgroup_pressure_poll(struct kernfs_open_file *of, poll_table *pt) { struct cgroup_file_ctx *ctx = of->priv; return psi_trigger_poll(&ctx->psi.trigger, of->file, pt); } static void cgroup_pressure_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; psi_trigger_destroy(ctx->psi.trigger); } bool cgroup_psi_enabled(void) { if (static_branch_likely(&psi_disabled)) return false; return (cgroup_feature_disable_mask & (1 << OPT_FEATURE_PRESSURE)) == 0; } #else /* CONFIG_PSI */ bool cgroup_psi_enabled(void) { return false; } #endif /* CONFIG_PSI */ static int cgroup_freeze_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; seq_printf(seq, "%d\n", cgrp->freezer.freeze); return 0; } static ssize_t cgroup_freeze_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; ssize_t ret; int freeze; ret = kstrtoint(strstrip(buf), 0, &freeze); if (ret) return ret; if (freeze < 0 || freeze > 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; cgroup_freeze(cgrp, freeze); cgroup_kn_unlock(of->kn); return nbytes; } static void __cgroup_kill(struct cgroup *cgrp) { struct css_task_iter it; struct task_struct *task; lockdep_assert_held(&cgroup_mutex); spin_lock_irq(&css_set_lock); cgrp->kill_seq++; spin_unlock_irq(&css_set_lock); css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED, &it); while ((task = css_task_iter_next(&it))) { /* Ignore kernel threads here. */ if (task->flags & PF_KTHREAD) continue; /* Skip tasks that are already dying. */ if (__fatal_signal_pending(task)) continue; send_sig(SIGKILL, task, 0); } css_task_iter_end(&it); } static void cgroup_kill(struct cgroup *cgrp) { struct cgroup_subsys_state *css; struct cgroup *dsct; lockdep_assert_held(&cgroup_mutex); cgroup_for_each_live_descendant_pre(dsct, css, cgrp) __cgroup_kill(dsct); } static ssize_t cgroup_kill_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { ssize_t ret = 0; int kill; struct cgroup *cgrp; ret = kstrtoint(strstrip(buf), 0, &kill); if (ret) return ret; if (kill != 1) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENOENT; /* * Killing is a process directed operation, i.e. the whole thread-group * is taken down so act like we do for cgroup.procs and only make this * writable in non-threaded cgroups. */ if (cgroup_is_threaded(cgrp)) ret = -EOPNOTSUPP; else cgroup_kill(cgrp); cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx; int ret; ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->ns = current->nsproxy->cgroup_ns; get_cgroup_ns(ctx->ns); of->priv = ctx; if (!cft->open) return 0; ret = cft->open(of); if (ret) { put_cgroup_ns(ctx->ns); kfree(ctx); } return ret; } static void cgroup_file_release(struct kernfs_open_file *of) { struct cftype *cft = of_cft(of); struct cgroup_file_ctx *ctx = of->priv; if (cft->release) cft->release(of); put_cgroup_ns(ctx->ns); kfree(ctx); } static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = kn_priv(of->kn); struct cftype *cft = of_cft(of); struct cgroup_subsys_state *css; int ret; if (!nbytes) return 0; /* * If namespaces are delegation boundaries, disallow writes to * files in an non-init namespace root from inside the namespace * except for the files explicitly marked delegatable - * eg. cgroup.procs, cgroup.threads and cgroup.subtree_control. */ if ((cgrp->root->flags & CGRP_ROOT_NS_DELEGATE) && !(cft->flags & CFTYPE_NS_DELEGATABLE) && ctx->ns != &init_cgroup_ns && ctx->ns->root_cset->dfl_cgrp == cgrp) return -EPERM; if (cft->write) return cft->write(of, buf, nbytes, off); /* * kernfs guarantees that a file isn't deleted with operations in * flight, which means that the matching css is and stays alive and * doesn't need to be pinned. The RCU locking is not necessary * either. It's just for the convenience of using cgroup_css(). */ rcu_read_lock(); css = cgroup_css(cgrp, cft->ss); rcu_read_unlock(); if (cft->write_u64) { unsigned long long v; ret = kstrtoull(buf, 0, &v); if (!ret) ret = cft->write_u64(css, cft, v); } else if (cft->write_s64) { long long v; ret = kstrtoll(buf, 0, &v); if (!ret) ret = cft->write_s64(css, cft, v); } else { ret = -EINVAL; } return ret ?: nbytes; } static __poll_t cgroup_file_poll(struct kernfs_open_file *of, poll_table *pt) { struct cftype *cft = of_cft(of); if (cft->poll) return cft->poll(of, pt); return kernfs_generic_poll(of, pt); } static void *cgroup_seqfile_start(struct seq_file *seq, loff_t *ppos) { return seq_cft(seq)->seq_start(seq, ppos); } static void *cgroup_seqfile_next(struct seq_file *seq, void *v, loff_t *ppos) { return seq_cft(seq)->seq_next(seq, v, ppos); } static void cgroup_seqfile_stop(struct seq_file *seq, void *v) { if (seq_cft(seq)->seq_stop) seq_cft(seq)->seq_stop(seq, v); } static int cgroup_seqfile_show(struct seq_file *m, void *arg) { struct cftype *cft = seq_cft(m); struct cgroup_subsys_state *css = seq_css(m); if (cft->seq_show) return cft->seq_show(m, arg); if (cft->read_u64) seq_printf(m, "%llu\n", cft->read_u64(css, cft)); else if (cft->read_s64) seq_printf(m, "%lld\n", cft->read_s64(css, cft)); else return -EINVAL; return 0; } static struct kernfs_ops cgroup_kf_single_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_show = cgroup_seqfile_show, }; static struct kernfs_ops cgroup_kf_ops = { .atomic_write_len = PAGE_SIZE, .open = cgroup_file_open, .release = cgroup_file_release, .write = cgroup_file_write, .poll = cgroup_file_poll, .seq_start = cgroup_seqfile_start, .seq_next = cgroup_seqfile_next, .seq_stop = cgroup_seqfile_stop, .seq_show = cgroup_seqfile_show, }; static void cgroup_file_notify_timer(struct timer_list *timer) { cgroup_file_notify(container_of(timer, struct cgroup_file, notify_timer)); } static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype *cft) { char name[CGROUP_FILE_NAME_MAX]; struct kernfs_node *kn; struct lock_class_key *key = NULL; #ifdef CONFIG_DEBUG_LOCK_ALLOC key = &cft->lockdep_key; #endif kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name), cgroup_file_mode(cft), current_fsuid(), current_fsgid(), 0, cft->kf_ops, cft, NULL, key); if (IS_ERR(kn)) return PTR_ERR(kn); if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; timer_setup(&cfile->notify_timer, cgroup_file_notify_timer, 0); spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; spin_unlock_irq(&cgroup_file_kn_lock); } return 0; } /** * cgroup_addrm_files - add or remove files to a cgroup directory * @css: the target css * @cgrp: the target cgroup (usually css->cgroup) * @cfts: array of cftypes to be added * @is_add: whether to add or remove * * Depending on @is_add, add or remove files defined by @cfts on @cgrp. * For removals, this function never fails. */ static int cgroup_addrm_files(struct cgroup_subsys_state *css, struct cgroup *cgrp, struct cftype cfts[], bool is_add) { struct cftype *cft, *cft_end = NULL; int ret = 0; lockdep_assert_held(&cgroup_mutex); restart: for (cft = cfts; cft != cft_end && cft->name[0] != '\0'; cft++) { /* does cft->flags tell us to skip this file on @cgrp? */ if ((cft->flags & __CFTYPE_ONLY_ON_DFL) && !cgroup_on_dfl(cgrp)) continue; if ((cft->flags & __CFTYPE_NOT_ON_DFL) && cgroup_on_dfl(cgrp)) continue; if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_ONLY_ON_ROOT) && cgroup_parent(cgrp)) continue; if ((cft->flags & CFTYPE_DEBUG) && !cgroup_debug) continue; if (is_add) { ret = cgroup_add_file(css, cgrp, cft); if (ret) { pr_warn("%s: failed to add %s, err=%d\n", __func__, cft->name, ret); cft_end = cft; is_add = false; goto restart; } } else { cgroup_rm_file(cgrp, cft); } } return ret; } static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) { struct cgroup_subsys *ss = cfts[0].ss; struct cgroup *root = &ss->root->cgrp; struct cgroup_subsys_state *css; int ret = 0; lockdep_assert_held(&cgroup_mutex); /* add/rm files for all cgroups created before */ css_for_each_descendant_pre(css, cgroup_css(root, ss)) { struct cgroup *cgrp = css->cgroup; if (!(css->flags & CSS_VISIBLE)) continue; ret = cgroup_addrm_files(css, cgrp, cfts, is_add); if (ret) break; } if (is_add && !ret) kernfs_activate(root->kn); return ret; } static void cgroup_exit_cftypes(struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft->name[0] != '\0'; cft++) { /* free copy for custom atomic_write_len, see init_cftypes() */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) kfree(cft->kf_ops); cft->kf_ops = NULL; cft->ss = NULL; /* revert flags set by cgroup core while adding @cfts */ cft->flags &= ~(__CFTYPE_ONLY_ON_DFL | __CFTYPE_NOT_ON_DFL | __CFTYPE_ADDED); } } static int cgroup_init_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; int ret = 0; for (cft = cfts; cft->name[0] != '\0'; cft++) { struct kernfs_ops *kf_ops; WARN_ON(cft->ss || cft->kf_ops); if (cft->flags & __CFTYPE_ADDED) { ret = -EBUSY; break; } if (cft->seq_start) kf_ops = &cgroup_kf_ops; else kf_ops = &cgroup_kf_single_ops; /* * Ugh... if @cft wants a custom max_write_len, we need to * make a copy of kf_ops to set its atomic_write_len. */ if (cft->max_write_len && cft->max_write_len != PAGE_SIZE) { kf_ops = kmemdup(kf_ops, sizeof(*kf_ops), GFP_KERNEL); if (!kf_ops) { ret = -ENOMEM; break; } kf_ops->atomic_write_len = cft->max_write_len; } cft->kf_ops = kf_ops; cft->ss = ss; cft->flags |= __CFTYPE_ADDED; } if (ret) cgroup_exit_cftypes(cfts); return ret; } static void cgroup_rm_cftypes_locked(struct cftype *cfts) { lockdep_assert_held(&cgroup_mutex); list_del(&cfts->node); cgroup_apply_cftypes(cfts, false); cgroup_exit_cftypes(cfts); } /** * cgroup_rm_cftypes - remove an array of cftypes from a subsystem * @cfts: zero-length name terminated array of cftypes * * Unregister @cfts. Files described by @cfts are removed from all * existing cgroups and all future cgroups won't have them either. This * function can be called anytime whether @cfts' subsys is attached or not. * * Returns 0 on successful unregistration, -ENOENT if @cfts is not * registered. */ int cgroup_rm_cftypes(struct cftype *cfts) { if (!cfts || cfts[0].name[0] == '\0') return 0; if (!(cfts[0].flags & __CFTYPE_ADDED)) return -ENOENT; cgroup_lock(); cgroup_rm_cftypes_locked(cfts); cgroup_unlock(); return 0; } /** * cgroup_add_cftypes - add an array of cftypes to a subsystem * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Register @cfts to @ss. Files described by @cfts are created for all * existing cgroups to which @ss is attached and all future cgroups will * have them too. This function can be called anytime whether @ss is * attached or not. * * Returns 0 on successful registration, -errno on failure. Note that this * function currently returns 0 as long as @cfts registration is successful * even if some file creation attempts on existing cgroups fail. */ int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { int ret; if (!cgroup_ssid_enabled(ss->id)) return 0; if (!cfts || cfts[0].name[0] == '\0') return 0; ret = cgroup_init_cftypes(ss, cfts); if (ret) return ret; cgroup_lock(); list_add_tail(&cfts->node, &ss->cfts); ret = cgroup_apply_cftypes(cfts, true); if (ret) cgroup_rm_cftypes_locked(cfts); cgroup_unlock(); return ret; } /** * cgroup_add_dfl_cftypes - add an array of cftypes for default hierarchy * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the default hierarchy. */ int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_ONLY_ON_DFL; return cgroup_add_cftypes(ss, cfts); } /** * cgroup_add_legacy_cftypes - add an array of cftypes for legacy hierarchies * @ss: target cgroup subsystem * @cfts: zero-length name terminated array of cftypes * * Similar to cgroup_add_cftypes() but the added files are only used for * the legacy hierarchies. */ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype *cft; for (cft = cfts; cft && cft->name[0] != '\0'; cft++) cft->flags |= __CFTYPE_NOT_ON_DFL; return cgroup_add_cftypes(ss, cfts); } /** * cgroup_file_notify - generate a file modified event for a cgroup_file * @cfile: target cgroup_file * * @cfile must have been obtained by setting cftype->file_offset. */ void cgroup_file_notify(struct cgroup_file *cfile) { unsigned long flags; spin_lock_irqsave(&cgroup_file_kn_lock, flags); if (cfile->kn) { unsigned long last = cfile->notified_at; unsigned long next = last + CGROUP_FILE_NOTIFY_MIN_INTV; if (time_in_range(jiffies, last, next)) { timer_reduce(&cfile->notify_timer, next); } else { kernfs_notify(cfile->kn); cfile->notified_at = jiffies; } } spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); } /** * cgroup_file_show - show or hide a hidden cgroup file * @cfile: target cgroup_file obtained by setting cftype->file_offset * @show: whether to show or hide */ void cgroup_file_show(struct cgroup_file *cfile, bool show) { struct kernfs_node *kn; spin_lock_irq(&cgroup_file_kn_lock); kn = cfile->kn; kernfs_get(kn); spin_unlock_irq(&cgroup_file_kn_lock); if (kn) kernfs_show(kn, show); kernfs_put(kn); } /** * css_next_child - find the next child of a given css * @pos: the current position (%NULL to initiate traversal) * @parent: css whose children to walk * * This function returns the next child of @parent and should be called * under either cgroup_mutex or RCU read lock. The only requirement is * that @parent and @pos are accessible. The next sibling is guaranteed to * be returned regardless of their states. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *parent) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* * @pos could already have been unlinked from the sibling list. * Once a cgroup is removed, its ->sibling.next is no longer * updated when its next sibling changes. CSS_RELEASED is set when * @pos is taken off list, at which time its next pointer is valid, * and, as releases are serialized, the one pointed to by the next * pointer is guaranteed to not have started release yet. This * implies that if we observe !CSS_RELEASED on @pos in this RCU * critical section, the one pointed to by its next pointer is * guaranteed to not have finished its RCU grace period even if we * have dropped rcu_read_lock() in-between iterations. * * If @pos has CSS_RELEASED set, its next pointer can't be * dereferenced; however, as each css is given a monotonically * increasing unique serial number and always appended to the * sibling list, the next one can be found by walking the parent's * children until the first css with higher serial number than * @pos's. While this path can be slower, it happens iff iteration * races against release and the race window is very small. */ if (!pos) { next = list_entry_rcu(parent->children.next, struct cgroup_subsys_state, sibling); } else if (likely(!(pos->flags & CSS_RELEASED))) { next = list_entry_rcu(pos->sibling.next, struct cgroup_subsys_state, sibling); } else { list_for_each_entry_rcu(next, &parent->children, sibling, lockdep_is_held(&cgroup_mutex)) if (next->serial_nr > pos->serial_nr) break; } /* * @next, if not pointing to the head, can be dereferenced and is * the next sibling. */ if (&next->sibling != &parent->children) return next; return NULL; } /** * css_next_descendant_pre - find the next descendant for pre-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_pre(). Find the next descendant * to visit for pre-order traversal of @root's descendants. @root is * included in the iteration and the first node to be visited. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct next descendant as long as both @pos * and @root are accessible and @pos is a descendant of @root. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_pre(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit @root */ if (!pos) return root; /* visit the first child if exists */ next = css_next_child(NULL, pos); if (next) return next; /* no child, visit my or the closest ancestor's next sibling */ while (pos != root) { next = css_next_child(pos, pos->parent); if (next) return next; pos = pos->parent; } return NULL; } EXPORT_SYMBOL_GPL(css_next_descendant_pre); /** * css_rightmost_descendant - return the rightmost descendant of a css * @pos: css of interest * * Return the rightmost descendant of @pos. If there's no descendant, @pos * is returned. This can be used during pre-order traversal to skip * subtree of @pos. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct rightmost descendant as long as @pos * is accessible. */ struct cgroup_subsys_state * css_rightmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last, *tmp; cgroup_assert_mutex_or_rcu_locked(); do { last = pos; /* ->prev isn't RCU safe, walk ->next till the end */ pos = NULL; css_for_each_child(tmp, last) pos = tmp; } while (pos); return last; } static struct cgroup_subsys_state * css_leftmost_descendant(struct cgroup_subsys_state *pos) { struct cgroup_subsys_state *last; do { last = pos; pos = css_next_child(NULL, pos); } while (pos); return last; } /** * css_next_descendant_post - find the next descendant for post-order walk * @pos: the current position (%NULL to initiate traversal) * @root: css whose descendants to walk * * To be used by css_for_each_descendant_post(). 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. * * While this function requires cgroup_mutex or RCU read locking, it * doesn't require the whole traversal to be contained in a single critical * section. Additionally, it isn't necessary to hold onto a reference to @pos. * This function will return the correct next descendant as long as both @pos * and @cgroup are accessible and @pos is a descendant of @cgroup. * * If a subsystem synchronizes ->css_online() and the start of iteration, a * css which finished ->css_online() is guaranteed to be visible in the * future iterations and will stay visible until the last reference is put. * A css which hasn't finished ->css_online() or already finished * ->css_offline() may show up during traversal. It's each subsystem's * responsibility to synchronize against on/offlining. */ struct cgroup_subsys_state * css_next_descendant_post(struct cgroup_subsys_state *pos, struct cgroup_subsys_state *root) { struct cgroup_subsys_state *next; cgroup_assert_mutex_or_rcu_locked(); /* if first iteration, visit leftmost descendant which may be @root */ if (!pos) return css_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 */ next = css_next_child(pos, pos->parent); if (next) return css_leftmost_descendant(next); /* no sibling left, visit parent */ return pos->parent; } /** * css_has_online_children - does a css have online children * @css: the target css * * Returns %true if @css has any online children; otherwise, %false. This * function can be called from any context but the caller is responsible * for synchronizing against on/offlining as necessary. */ bool css_has_online_children(struct cgroup_subsys_state *css) { struct cgroup_subsys_state *child; bool ret = false; rcu_read_lock(); css_for_each_child(child, css) { if (child->flags & CSS_ONLINE) { ret = true; break; } } rcu_read_unlock(); return ret; } static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it) { struct list_head *l; struct cgrp_cset_link *link; struct css_set *cset; lockdep_assert_held(&css_set_lock); /* find the next threaded cset */ if (it->tcset_pos) { l = it->tcset_pos->next; if (l != it->tcset_head) { it->tcset_pos = l; return container_of(l, struct css_set, threaded_csets_node); } it->tcset_pos = NULL; } /* find the next cset */ l = it->cset_pos; l = l->next; if (l == it->cset_head) { it->cset_pos = NULL; return NULL; } if (it->ss) { cset = container_of(l, struct css_set, e_cset_node[it->ss->id]); } else { link = list_entry(l, struct cgrp_cset_link, cset_link); cset = link->cset; } it->cset_pos = l; /* initialize threaded css_set walking */ if (it->flags & CSS_TASK_ITER_THREADED) { if (it->cur_dcset) put_css_set_locked(it->cur_dcset); it->cur_dcset = cset; get_css_set(cset); it->tcset_head = &cset->threaded_csets; it->tcset_pos = &cset->threaded_csets; } return cset; } /** * css_task_iter_advance_css_set - advance a task iterator to the next css_set * @it: the iterator to advance * * Advance @it to the next css_set to walk. */ static void css_task_iter_advance_css_set(struct css_task_iter *it) { struct css_set *cset; lockdep_assert_held(&css_set_lock); /* Advance to the next non-empty css_set and find first non-empty tasks list*/ while ((cset = css_task_iter_next_css_set(it))) { if (!list_empty(&cset->tasks)) { it->cur_tasks_head = &cset->tasks; break; } else if (!list_empty(&cset->mg_tasks)) { it->cur_tasks_head = &cset->mg_tasks; break; } else if (!list_empty(&cset->dying_tasks)) { it->cur_tasks_head = &cset->dying_tasks; break; } } if (!cset) { it->task_pos = NULL; return; } it->task_pos = it->cur_tasks_head->next; /* * We don't keep css_sets locked across iteration steps and thus * need to take steps to ensure that iteration can be resumed after * the lock is re-acquired. Iteration is performed at two levels - * css_sets and tasks in them. * * Once created, a css_set never leaves its cgroup lists, so a * pinned css_set is guaranteed to stay put and we can resume * iteration afterwards. * * Tasks may leave @cset across iteration steps. This is resolved * by registering each iterator with the css_set currently being * walked and making css_set_move_task() advance iterators whose * next task is leaving. */ if (it->cur_cset) { list_del(&it->iters_node); put_css_set_locked(it->cur_cset); } get_css_set(cset); it->cur_cset = cset; list_add(&it->iters_node, &cset->task_iters); } static void css_task_iter_skip(struct css_task_iter *it, struct task_struct *task) { lockdep_assert_held(&css_set_lock); if (it->task_pos == &task->cg_list) { it->task_pos = it->task_pos->next; it->flags |= CSS_TASK_ITER_SKIPPED; } } static void css_task_iter_advance(struct css_task_iter *it) { struct task_struct *task; lockdep_assert_held(&css_set_lock); repeat: if (it->task_pos) { /* * Advance iterator to find next entry. We go through cset * tasks, mg_tasks and dying_tasks, when consumed we move onto * the next cset. */ if (it->flags & CSS_TASK_ITER_SKIPPED) it->flags &= ~CSS_TASK_ITER_SKIPPED; else it->task_pos = it->task_pos->next; if (it->task_pos == &it->cur_cset->tasks) { it->cur_tasks_head = &it->cur_cset->mg_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->mg_tasks) { it->cur_tasks_head = &it->cur_cset->dying_tasks; it->task_pos = it->cur_tasks_head->next; } if (it->task_pos == &it->cur_cset->dying_tasks) css_task_iter_advance_css_set(it); } else { /* called from start, proceed to the first cset */ css_task_iter_advance_css_set(it); } if (!it->task_pos) return; task = list_entry(it->task_pos, struct task_struct, cg_list); if (it->flags & CSS_TASK_ITER_PROCS) { /* if PROCS, skip over tasks which aren't group leaders */ if (!thread_group_leader(task)) goto repeat; /* and dying leaders w/o live member threads */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks && !atomic_read(&task->signal->live)) goto repeat; } else { /* skip all dying ones */ if (it->cur_tasks_head == &it->cur_cset->dying_tasks) goto repeat; } } /** * css_task_iter_start - initiate task iteration * @css: the css to walk tasks of * @flags: CSS_TASK_ITER_* flags * @it: the task iterator to use * * Initiate iteration through the tasks of @css. The caller can call * css_task_iter_next() to walk through the tasks until the function * returns NULL. On completion of iteration, css_task_iter_end() must be * called. */ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { unsigned long irqflags; memset(it, 0, sizeof(*it)); spin_lock_irqsave(&css_set_lock, irqflags); it->ss = css->ss; it->flags = flags; if (CGROUP_HAS_SUBSYS_CONFIG && it->ss) it->cset_pos = &css->cgroup->e_csets[css->ss->id]; else it->cset_pos = &css->cgroup->cset_links; it->cset_head = it->cset_pos; css_task_iter_advance(it); spin_unlock_irqrestore(&css_set_lock, irqflags); } /** * css_task_iter_next - return the next task for the iterator * @it: the task iterator being iterated * * The "next" function for task iteration. @it should have been * initialized via css_task_iter_start(). Returns NULL when the iteration * reaches the end. */ struct task_struct *css_task_iter_next(struct css_task_iter *it) { unsigned long irqflags; if (it->cur_task) { put_task_struct(it->cur_task); it->cur_task = NULL; } spin_lock_irqsave(&css_set_lock, irqflags); /* @it may be half-advanced by skips, finish advancing */ if (it->flags & CSS_TASK_ITER_SKIPPED) css_task_iter_advance(it); if (it->task_pos) { it->cur_task = list_entry(it->task_pos, struct task_struct, cg_list); get_task_struct(it->cur_task); css_task_iter_advance(it); } spin_unlock_irqrestore(&css_set_lock, irqflags); return it->cur_task; } /** * css_task_iter_end - finish task iteration * @it: the task iterator to finish * * Finish task iteration started by css_task_iter_start(). */ void css_task_iter_end(struct css_task_iter *it) { unsigned long irqflags; if (it->cur_cset) { spin_lock_irqsave(&css_set_lock, irqflags); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); spin_unlock_irqrestore(&css_set_lock, irqflags); } if (it->cur_dcset) put_css_set(it->cur_dcset); if (it->cur_task) put_task_struct(it->cur_task); } static void cgroup_procs_release(struct kernfs_open_file *of) { struct cgroup_file_ctx *ctx = of->priv; if (ctx->procs.started) css_task_iter_end(&ctx->procs.iter); } static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; if (pos) (*pos)++; return css_task_iter_next(&ctx->procs.iter); } static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, unsigned int iter_flags) { struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_file_ctx *ctx = of->priv; struct css_task_iter *it = &ctx->procs.iter; /* * When a seq_file is seeked, it's always traversed sequentially * from position 0, so we can simply keep iterating on !0 *pos. */ if (!ctx->procs.started) { if (WARN_ON_ONCE((*pos))) return ERR_PTR(-EINVAL); css_task_iter_start(&cgrp->self, iter_flags, it); ctx->procs.started = true; } else if (!(*pos)) { css_task_iter_end(it); css_task_iter_start(&cgrp->self, iter_flags, it); } else return it->cur_task; return cgroup_procs_next(s, NULL, NULL); } static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) { struct cgroup *cgrp = seq_css(s)->cgroup; /* * All processes of a threaded subtree belong to the domain cgroup * of the subtree. Only threads can be distributed across the * subtree. Reject reads on cgroup.procs in the subtree proper. * They're always empty anyway. */ if (cgroup_is_threaded(cgrp)) return ERR_PTR(-EOPNOTSUPP); return __cgroup_procs_start(s, pos, CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED); } static int cgroup_procs_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", task_pid_vnr(v)); return 0; } static int cgroup_may_write(const struct cgroup *cgrp, struct super_block *sb) { int ret; struct inode *inode; lockdep_assert_held(&cgroup_mutex); inode = kernfs_get_inode(sb, cgrp->procs_file.kn); if (!inode) return -ENOMEM; ret = inode_permission(&nop_mnt_idmap, inode, MAY_WRITE); iput(inode); return ret; } static int cgroup_procs_write_permission(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, struct cgroup_namespace *ns) { struct cgroup *com_cgrp = src_cgrp; int ret; lockdep_assert_held(&cgroup_mutex); /* find the common ancestor */ while (!cgroup_is_descendant(dst_cgrp, com_cgrp)) com_cgrp = cgroup_parent(com_cgrp); /* %current should be authorized to migrate to the common ancestor */ ret = cgroup_may_write(com_cgrp, sb); if (ret) return ret; /* * If namespaces are delegation boundaries, %current must be able * to see both source and destination cgroups from its namespace. */ if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) && (!cgroup_is_descendant(src_cgrp, ns->root_cset->dfl_cgrp) || !cgroup_is_descendant(dst_cgrp, ns->root_cset->dfl_cgrp))) return -ENOENT; return 0; } static int cgroup_attach_permissions(struct cgroup *src_cgrp, struct cgroup *dst_cgrp, struct super_block *sb, bool threadgroup, struct cgroup_namespace *ns) { int ret = 0; ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, sb, ns); if (ret) return ret; ret = cgroup_migrate_vet_dst(dst_cgrp); if (ret) return ret; if (!threadgroup && (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp)) ret = -EOPNOTSUPP; return ret; } static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, bool threadgroup) { struct cgroup_file_ctx *ctx = of->priv; struct cgroup *src_cgrp, *dst_cgrp; struct task_struct *task; const struct cred *saved_cred; ssize_t ret; bool threadgroup_locked; dst_cgrp = cgroup_kn_lock_live(of->kn, false); if (!dst_cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup, &threadgroup_locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; /* find the source cgroup */ spin_lock_irq(&css_set_lock); src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); spin_unlock_irq(&css_set_lock); /* * Process and thread migrations follow same delegation rule. Check * permissions using the credentials from file open to protect against * inherited fd attacks. */ saved_cred = override_creds(of->file->f_cred); ret = cgroup_attach_permissions(src_cgrp, dst_cgrp, of->file->f_path.dentry->d_sb, threadgroup, ctx->ns); revert_creds(saved_cred); if (ret) goto out_finish; ret = cgroup_attach_task(dst_cgrp, task, threadgroup); out_finish: cgroup_procs_write_finish(task, threadgroup_locked); out_unlock: cgroup_kn_unlock(of->kn); return ret; } static ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, true) ?: nbytes; } static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) { return __cgroup_procs_start(s, pos, 0); } static ssize_t cgroup_threads_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup_procs_write(of, buf, false) ?: nbytes; } /* cgroup core interface files for the default hierarchy */ static struct cftype cgroup_base_files[] = { { .name = "cgroup.type", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_type_show, .write = cgroup_type_write, }, { .name = "cgroup.procs", .flags = CFTYPE_NS_DELEGATABLE, .file_offset = offsetof(struct cgroup, procs_file), .release = cgroup_procs_release, .seq_start = cgroup_procs_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_procs_write, }, { .name = "cgroup.threads", .flags = CFTYPE_NS_DELEGATABLE, .release = cgroup_procs_release, .seq_start = cgroup_threads_start, .seq_next = cgroup_procs_next, .seq_show = cgroup_procs_show, .write = cgroup_threads_write, }, { .name = "cgroup.controllers", .seq_show = cgroup_controllers_show, }, { .name = "cgroup.subtree_control", .flags = CFTYPE_NS_DELEGATABLE, .seq_show = cgroup_subtree_control_show, .write = cgroup_subtree_control_write, }, { .name = "cgroup.events", .flags = CFTYPE_NOT_ON_ROOT, .file_offset = offsetof(struct cgroup, events_file), .seq_show = cgroup_events_show, }, { .name = "cgroup.max.descendants", .seq_show = cgroup_max_descendants_show, .write = cgroup_max_descendants_write, }, { .name = "cgroup.max.depth", .seq_show = cgroup_max_depth_show, .write = cgroup_max_depth_write, }, { .name = "cgroup.stat", .seq_show = cgroup_stat_show, }, { .name = "cgroup.freeze", .flags = CFTYPE_NOT_ON_ROOT, .seq_show = cgroup_freeze_show, .write = cgroup_freeze_write, }, { .name = "cgroup.kill", .flags = CFTYPE_NOT_ON_ROOT, .write = cgroup_kill_write, }, { .name = "cpu.stat", .seq_show = cpu_stat_show, }, { .name = "cpu.stat.local", .seq_show = cpu_local_stat_show, }, { } /* terminate */ }; static struct cftype cgroup_psi_files[] = { #ifdef CONFIG_PSI { .name = "io.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IO]), .seq_show = cgroup_io_pressure_show, .write = cgroup_io_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "memory.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_MEM]), .seq_show = cgroup_memory_pressure_show, .write = cgroup_memory_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, { .name = "cpu.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_CPU]), .seq_show = cgroup_cpu_pressure_show, .write = cgroup_cpu_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #ifdef CONFIG_IRQ_TIME_ACCOUNTING { .name = "irq.pressure", .file_offset = offsetof(struct cgroup, psi_files[PSI_IRQ]), .seq_show = cgroup_irq_pressure_show, .write = cgroup_irq_pressure_write, .poll = cgroup_pressure_poll, .release = cgroup_pressure_release, }, #endif { .name = "cgroup.pressure", .seq_show = cgroup_pressure_show, .write = cgroup_pressure_write, }, #endif /* CONFIG_PSI */ { } /* terminate */ }; /* * css destruction is four-stage process. * * 1. Destruction starts. Killing of the percpu_ref is initiated. * Implemented in kill_css(). * * 2. When the percpu_ref is confirmed to be visible as killed on all CPUs * and thus css_tryget_online() is guaranteed to fail, the css can be * offlined by invoking offline_css(). After offlining, the base ref is * put. Implemented in css_killed_work_fn(). * * 3. When the percpu_ref reaches zero, the only possible remaining * accessors are inside RCU read sections. css_release() schedules the * RCU callback. * * 4. After the grace period, the css can be freed. Implemented in * css_free_rwork_fn(). * * It is actually hairier because both step 2 and 4 require process context * and thus involve punting to css->destroy_work adding two additional * steps to the already complex sequence. */ static void css_free_rwork_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(to_rcu_work(work), struct cgroup_subsys_state, destroy_rwork); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; percpu_ref_exit(&css->refcnt); css_rstat_exit(css); if (!css_is_self(css)) { /* css free path */ struct cgroup_subsys_state *parent = css->parent; int id = css->id; ss->css_free(css); cgroup_idr_remove(&ss->css_idr, id); cgroup_put(cgrp); if (parent) css_put(parent); } else { /* cgroup free path */ atomic_dec(&cgrp->root->nr_cgrps); if (!cgroup_on_dfl(cgrp)) cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); bpf_cgrp_storage_free(cgrp); if (cgroup_parent(cgrp)) { /* * We get a ref to the parent, and put the ref when * this cgroup is being freed, so it's guaranteed * that the parent won't be destroyed before its * children. */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); psi_cgroup_free(cgrp); kfree(cgrp); } else { /* * This is root cgroup's refcnt reaching zero, * which indicates that the root should be * released. */ cgroup_destroy_root(cgrp->root); } } } static void css_release_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; cgroup_lock(); css->flags |= CSS_RELEASED; list_del_rcu(&css->sibling); if (!css_is_self(css)) { struct cgroup *parent_cgrp; css_rstat_flush(css); cgroup_idr_replace(&ss->css_idr, NULL, css->id); if (ss->css_released) ss->css_released(css); cgrp->nr_dying_subsys[ss->id]--; /* * When a css is released and ready to be freed, its * nr_descendants must be zero. However, the corresponding * cgrp->nr_dying_subsys[ss->id] may not be 0 if a subsystem * is activated and deactivated multiple times with one or * more of its previous activation leaving behind dying csses. */ WARN_ON_ONCE(css->nr_descendants); parent_cgrp = cgroup_parent(cgrp); while (parent_cgrp) { parent_cgrp->nr_dying_subsys[ss->id]--; parent_cgrp = cgroup_parent(parent_cgrp); } } else { struct cgroup *tcgrp; /* cgroup release path */ TRACE_CGROUP_PATH(release, cgrp); css_rstat_flush(&cgrp->self); spin_lock_irq(&css_set_lock); for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) tcgrp->nr_dying_descendants--; spin_unlock_irq(&css_set_lock); /* * There are two control paths which try to determine * cgroup from dentry without going through kernfs - * cgroupstats_build() and css_tryget_online_from_dir(). * Those are supported by RCU protecting clearing of * cgrp->kn->priv backpointer. */ if (cgrp->kn) RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); } cgroup_unlock(); INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); } static void css_release(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); INIT_WORK(&css->destroy_work, css_release_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } static void init_and_link_css(struct cgroup_subsys_state *css, struct cgroup_subsys *ss, struct cgroup *cgrp) { lockdep_assert_held(&cgroup_mutex); cgroup_get_live(cgrp); memset(css, 0, sizeof(*css)); css->cgroup = cgrp; css->ss = ss; css->id = -1; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); css->serial_nr = css_serial_nr_next++; atomic_set(&css->online_cnt, 0); if (cgroup_parent(cgrp)) { css->parent = cgroup_css(cgroup_parent(cgrp), ss); css_get(css->parent); } BUG_ON(cgroup_css(cgrp, ss)); } /* invoke ->css_online() on a new CSS and mark it online if successful */ static int online_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; int ret = 0; lockdep_assert_held(&cgroup_mutex); if (ss->css_online) ret = ss->css_online(css); if (!ret) { css->flags |= CSS_ONLINE; rcu_assign_pointer(css->cgroup->subsys[ss->id], css); atomic_inc(&css->online_cnt); if (css->parent) { atomic_inc(&css->parent->online_cnt); while ((css = css->parent)) css->nr_descendants++; } } return ret; } /* if the CSS is online, invoke ->css_offline() on it and mark it offline */ static void offline_css(struct cgroup_subsys_state *css) { struct cgroup_subsys *ss = css->ss; lockdep_assert_held(&cgroup_mutex); if (!(css->flags & CSS_ONLINE)) return; if (ss->css_offline) ss->css_offline(css); css->flags &= ~CSS_ONLINE; RCU_INIT_POINTER(css->cgroup->subsys[ss->id], NULL); wake_up_all(&css->cgroup->offline_waitq); css->cgroup->nr_dying_subsys[ss->id]++; /* * Parent css and cgroup cannot be freed until after the freeing * of child css, see css_free_rwork_fn(). */ while ((css = css->parent)) { css->nr_descendants--; css->cgroup->nr_dying_subsys[ss->id]++; } } /** * css_create - create a cgroup_subsys_state * @cgrp: the cgroup new css will be associated with * @ss: the subsys of new css * * Create a new css associated with @cgrp - @ss pair. On success, the new * css is online and installed in @cgrp. This function doesn't create the * interface files. Returns 0 on success, -errno on failure. */ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp, struct cgroup_subsys *ss) { struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *parent_css = cgroup_css(parent, ss); struct cgroup_subsys_state *css; int err; lockdep_assert_held(&cgroup_mutex); css = ss->css_alloc(parent_css); if (!css) css = ERR_PTR(-ENOMEM); if (IS_ERR(css)) return css; init_and_link_css(css, ss, cgrp); err = percpu_ref_init(&css->refcnt, css_release, 0, GFP_KERNEL); if (err) goto err_free_css; err = cgroup_idr_alloc(&ss->css_idr, NULL, 2, 0, GFP_KERNEL); if (err < 0) goto err_free_css; css->id = err; err = css_rstat_init(css); if (err) goto err_free_css; /* @css is ready to be brought online now, make it visible */ list_add_tail_rcu(&css->sibling, &parent_css->children); cgroup_idr_replace(&ss->css_idr, css, css->id); err = online_css(css); if (err) goto err_list_del; return css; err_list_del: list_del_rcu(&css->sibling); err_free_css: INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn); queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork); return ERR_PTR(err); } /* * The returned cgroup is fully initialized including its control mask, but * it doesn't have the control mask applied. */ static struct cgroup *cgroup_create(struct cgroup *parent, const char *name, umode_t mode) { struct cgroup_root *root = parent->root; struct cgroup *cgrp, *tcgrp; struct kernfs_node *kn; int i, level = parent->level + 1; int ret; /* allocate the cgroup and its ID, 0 is reserved for the root */ cgrp = kzalloc(struct_size(cgrp, ancestors, (level + 1)), GFP_KERNEL); if (!cgrp) return ERR_PTR(-ENOMEM); ret = percpu_ref_init(&cgrp->self.refcnt, css_release, 0, GFP_KERNEL); if (ret) goto out_free_cgrp; /* create the directory */ kn = kernfs_create_dir_ns(parent->kn, name, mode, current_fsuid(), current_fsgid(), cgrp, NULL); if (IS_ERR(kn)) { ret = PTR_ERR(kn); goto out_cancel_ref; } cgrp->kn = kn; init_cgroup_housekeeping(cgrp); cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; /* * Now that init_cgroup_housekeeping() has been called and cgrp->self * is setup, it is safe to perform rstat initialization on it. */ ret = css_rstat_init(&cgrp->self); if (ret) goto out_kernfs_remove; ret = psi_cgroup_alloc(cgrp); if (ret) goto out_stat_exit; for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) cgrp->ancestors[tcgrp->level] = tcgrp; /* * New cgroup inherits effective freeze counter, and * if the parent has to be frozen, the child has too. */ cgrp->freezer.e_freeze = parent->freezer.e_freeze; if (cgrp->freezer.e_freeze) { /* * Set the CGRP_FREEZE flag, so when a process will be * attached to the child cgroup, it will become frozen. * At this point the new cgroup is unpopulated, so we can * consider it frozen immediately. */ set_bit(CGRP_FREEZE, &cgrp->flags); set_bit(CGRP_FROZEN, &cgrp->flags); } if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &parent->flags)) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &cgrp->flags); cgrp->self.serial_nr = css_serial_nr_next++; ret = blocking_notifier_call_chain_robust(&cgroup_lifetime_notifier, CGROUP_LIFETIME_ONLINE, CGROUP_LIFETIME_OFFLINE, cgrp); ret = notifier_to_errno(ret); if (ret) goto out_psi_free; /* allocation complete, commit to creation */ spin_lock_irq(&css_set_lock); for (i = 0; i < level; i++) { tcgrp = cgrp->ancestors[i]; tcgrp->nr_descendants++; /* * If the new cgroup is frozen, all ancestor cgroups get a new * frozen descendant, but their state can't change because of * this. */ if (cgrp->freezer.e_freeze) tcgrp->freezer.nr_frozen_descendants++; } spin_unlock_irq(&css_set_lock); list_add_tail_rcu(&cgrp->self.sibling, &cgroup_parent(cgrp)->self.children); atomic_inc(&root->nr_cgrps); cgroup_get_live(parent); /* * On the default hierarchy, a child doesn't automatically inherit * subtree_control from the parent. Each is configured manually. */ if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); cgroup_propagate_control(cgrp); return cgrp; out_psi_free: psi_cgroup_free(cgrp); out_stat_exit: css_rstat_exit(&cgrp->self); out_kernfs_remove: kernfs_remove(cgrp->kn); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: kfree(cgrp); return ERR_PTR(ret); } static bool cgroup_check_hierarchy_limits(struct cgroup *parent) { struct cgroup *cgroup; int ret = false; int level = 0; lockdep_assert_held(&cgroup_mutex); for (cgroup = parent; cgroup; cgroup = cgroup_parent(cgroup)) { if (cgroup->nr_descendants >= cgroup->max_descendants) goto fail; if (level >= cgroup->max_depth) goto fail; level++; } ret = true; fail: return ret; } int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(name, '\n')) return -EINVAL; parent = cgroup_kn_lock_live(parent_kn, false); if (!parent) return -ENODEV; if (!cgroup_check_hierarchy_limits(parent)) { ret = -EAGAIN; goto out_unlock; } cgrp = cgroup_create(parent, name, mode); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); goto out_unlock; } /* * This extra ref will be put in css_free_rwork_fn() and guarantees * that @cgrp->kn is always accessible. */ kernfs_get(cgrp->kn); ret = css_populate_dir(&cgrp->self); if (ret) goto out_destroy; ret = cgroup_apply_control_enable(cgrp); if (ret) goto out_destroy; TRACE_CGROUP_PATH(mkdir, cgrp); /* let's create and online css's */ kernfs_activate(cgrp->kn); ret = 0; goto out_unlock; out_destroy: cgroup_destroy_locked(cgrp); out_unlock: cgroup_kn_unlock(parent_kn); return ret; } /* * This is called when the refcnt of a css is confirmed to be killed. * css_tryget_online() is now guaranteed to fail. Tell the subsystem to * initiate destruction and put the css ref from kill_css(). */ static void css_killed_work_fn(struct work_struct *work) { struct cgroup_subsys_state *css = container_of(work, struct cgroup_subsys_state, destroy_work); cgroup_lock(); do { offline_css(css); css_put(css); /* @css can't go away while we're holding cgroup_mutex */ css = css->parent; } while (css && atomic_dec_and_test(&css->online_cnt)); cgroup_unlock(); } /* css kill confirmation processing requires process context, bounce */ static void css_killed_ref_fn(struct percpu_ref *ref) { struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); if (atomic_dec_and_test(&css->online_cnt)) { INIT_WORK(&css->destroy_work, css_killed_work_fn); queue_work(cgroup_destroy_wq, &css->destroy_work); } } /** * kill_css - destroy a css * @css: css to destroy * * This function initiates destruction of @css by removing cgroup interface * files and putting its base reference. ->css_offline() will be invoked * asynchronously once css_tryget_online() is guaranteed to fail and when * the reference count reaches zero, @css will be released. */ static void kill_css(struct cgroup_subsys_state *css) { lockdep_assert_held(&cgroup_mutex); if (css->flags & CSS_DYING) return; /* * Call css_killed(), if defined, before setting the CSS_DYING flag */ if (css->ss->css_killed) css->ss->css_killed(css); css->flags |= CSS_DYING; /* * This must happen before css is disassociated with its cgroup. * See seq_css() for details. */ css_clear_dir(css); /* * Killing would put the base ref, but we need to keep it alive * until after ->css_offline(). */ css_get(css); /* * cgroup core guarantees that, by the time ->css_offline() is * invoked, no new css reference will be given out via * css_tryget_online(). We can't simply call percpu_ref_kill() and * proceed to offlining css's because percpu_ref_kill() doesn't * guarantee that the ref is seen as killed on all CPUs on return. * * Use percpu_ref_kill_and_confirm() to get notifications as each * css is confirmed to be seen as killed on all CPUs. */ percpu_ref_kill_and_confirm(&css->refcnt, css_killed_ref_fn); } /** * cgroup_destroy_locked - the first stage of cgroup destruction * @cgrp: cgroup to be destroyed * * css's make use of percpu refcnts whose killing latency shouldn't be * exposed to userland and are RCU protected. Also, cgroup core needs to * guarantee that css_tryget_online() won't succeed by the time * ->css_offline() is invoked. To satisfy all the requirements, * destruction is implemented in the following two steps. * * s1. Verify @cgrp can be destroyed and mark it dying. Remove all * userland visible parts and start killing the percpu refcnts of * css's. Set up so that the next stage will be kicked off once all * the percpu refcnts are confirmed to be killed. * * s2. Invoke ->css_offline(), mark the cgroup dead and proceed with the * rest of destruction. Once all cgroup references are gone, the * cgroup is RCU-freed. * * This function implements s1. After this step, @cgrp is gone as far as * the userland is concerned and a new cgroup with the same name may be * created. As cgroup doesn't care about the names internally, this * doesn't cause any problem. */ static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { struct cgroup *tcgrp, *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; int ssid, ret; lockdep_assert_held(&cgroup_mutex); /* * Only migration can raise populated from zero and we're already * holding cgroup_mutex. */ if (cgroup_is_populated(cgrp)) return -EBUSY; /* * Make sure there's no live children. We can't test emptiness of * ->self.children as dead children linger on it while being * drained; otherwise, "rmdir parent/child parent" may fail. */ if (css_has_online_children(&cgrp->self)) return -EBUSY; /* * Mark @cgrp and the associated csets dead. The former prevents * further task migration and child creation by disabling * cgroup_kn_lock_live(). The latter makes the csets ignored by * the migration path. */ cgrp->self.flags &= ~CSS_ONLINE; spin_lock_irq(&css_set_lock); list_for_each_entry(link, &cgrp->cset_links, cset_link) link->cset->dead = true; spin_unlock_irq(&css_set_lock); /* initiate massacre of all css's */ for_each_css(css, ssid, cgrp) kill_css(css); /* clear and remove @cgrp dir, @cgrp has an extra ref on its kn */ css_clear_dir(&cgrp->self); kernfs_remove(cgrp->kn); if (cgroup_is_threaded(cgrp)) parent->nr_threaded_children--; spin_lock_irq(&css_set_lock); for (tcgrp = parent; tcgrp; tcgrp = cgroup_parent(tcgrp)) { tcgrp->nr_descendants--; tcgrp->nr_dying_descendants++; /* * If the dying cgroup is frozen, decrease frozen descendants * counters of ancestor cgroups. */ if (test_bit(CGRP_FROZEN, &cgrp->flags)) tcgrp->freezer.nr_frozen_descendants--; } spin_unlock_irq(&css_set_lock); cgroup1_check_for_release(parent); ret = blocking_notifier_call_chain(&cgroup_lifetime_notifier, CGROUP_LIFETIME_OFFLINE, cgrp); WARN_ON_ONCE(notifier_to_errno(ret)); /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); return 0; }; int cgroup_rmdir(struct kernfs_node *kn) { struct cgroup *cgrp; int ret = 0; cgrp = cgroup_kn_lock_live(kn, false); if (!cgrp) return 0; ret = cgroup_destroy_locked(cgrp); if (!ret) TRACE_CGROUP_PATH(rmdir, cgrp); cgroup_kn_unlock(kn); return ret; } static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { .show_options = cgroup_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) { struct cgroup_subsys_state *css; pr_debug("Initializing cgroup subsys %s\n", ss->name); cgroup_lock(); idr_init(&ss->css_idr); INIT_LIST_HEAD(&ss->cfts); /* Create the root cgroup state for this subsystem */ ss->root = &cgrp_dfl_root; css = ss->css_alloc(NULL); /* We don't handle early failures gracefully */ BUG_ON(IS_ERR(css)); init_and_link_css(css, ss, &cgrp_dfl_root.cgrp); /* * Root csses are never destroyed and we can't initialize * percpu_ref during early init. Disable refcnting. */ css->flags |= CSS_NO_REF; if (early) { /* allocation can't be done safely during early init */ css->id = 1; } else { css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); BUG_ON(ss_rstat_init(ss)); BUG_ON(css_rstat_init(css)); } /* Update the init_css_set to contain a subsys * pointer to this state - since the subsystem is * newly registered, all tasks and hence the * init_css_set is in the subsystem's root cgroup. */ init_css_set.subsys[ss->id] = css; have_fork_callback |= (bool)ss->fork << ss->id; have_exit_callback |= (bool)ss->exit << ss->id; have_release_callback |= (bool)ss->release << ss->id; have_canfork_callback |= (bool)ss->can_fork << ss->id; /* At system boot, before all subsystems have been * registered, no tasks have been forked, so we don't * need to invoke fork callbacks here. */ BUG_ON(!list_empty(&init_task.tasks)); BUG_ON(online_css(css)); cgroup_unlock(); } /** * cgroup_init_early - cgroup initialization at system boot * * Initialize cgroups at system boot, and initialize any * subsystems that request early init. */ int __init cgroup_init_early(void) { static struct cgroup_fs_context __initdata ctx; struct cgroup_subsys *ss; int i; ctx.root = &cgrp_dfl_root; init_cgroup_root(&ctx); cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF; RCU_INIT_POINTER(init_task.cgroups, &init_css_set); for_each_subsys(ss, i) { WARN(!ss->css_alloc || !ss->css_free || ss->name || ss->id, "invalid cgroup_subsys %d:%s css_alloc=%p css_free=%p id:name=%d:%s\n", i, cgroup_subsys_name[i], ss->css_alloc, ss->css_free, ss->id, ss->name); WARN(strlen(cgroup_subsys_name[i]) > MAX_CGROUP_TYPE_NAMELEN, "cgroup_subsys_name %s too long\n", cgroup_subsys_name[i]); WARN(ss->early_init && ss->css_rstat_flush, "cgroup rstat cannot be used with early init subsystem\n"); ss->id = i; ss->name = cgroup_subsys_name[i]; if (!ss->legacy_name) ss->legacy_name = cgroup_subsys_name[i]; if (ss->early_init) cgroup_init_subsys(ss, true); } return 0; } /** * cgroup_init - cgroup initialization * * Register cgroup filesystem and /proc file, and initialize * any subsystems that didn't request early init. */ int __init cgroup_init(void) { struct cgroup_subsys *ss; int ssid; BUILD_BUG_ON(CGROUP_SUBSYS_COUNT > 16); BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup_psi_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files)); BUG_ON(ss_rstat_init(NULL)); get_user_ns(init_cgroup_ns.user_ns); cgroup_lock(); /* * Add init_css_set to the hash table so that dfl_root can link to * it during init. */ hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); cgroup_bpf_lifetime_notifier_init(); BUG_ON(cgroup_setup_root(&cgrp_dfl_root, 0)); cgroup_unlock(); for_each_subsys(ss, ssid) { if (ss->early_init) { struct cgroup_subsys_state *css = init_css_set.subsys[ss->id]; css->id = cgroup_idr_alloc(&ss->css_idr, css, 1, 2, GFP_KERNEL); BUG_ON(css->id < 0); } else { cgroup_init_subsys(ss, false); } list_add_tail(&init_css_set.e_cset_node[ssid], &cgrp_dfl_root.cgrp.e_csets[ssid]); /* * Setting dfl_root subsys_mask needs to consider the * disabled flag and cftype registration needs kmalloc, * both of which aren't available during early_init. */ if (!cgroup_ssid_enabled(ssid)) continue; if (cgroup1_ssid_disabled(ssid)) pr_info("Disabling %s control group subsystem in v1 mounts\n", ss->legacy_name); cgrp_dfl_root.subsys_mask |= 1 << ss->id; /* implicit controllers must be threaded too */ WARN_ON(ss->implicit_on_dfl && !ss->threaded); if (ss->implicit_on_dfl) cgrp_dfl_implicit_ss_mask |= 1 << ss->id; else if (!ss->dfl_cftypes) cgrp_dfl_inhibit_ss_mask |= 1 << ss->id; if (ss->threaded) cgrp_dfl_threaded_ss_mask |= 1 << ss->id; if (ss->dfl_cftypes == ss->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); } else { WARN_ON(cgroup_add_dfl_cftypes(ss, ss->dfl_cftypes)); WARN_ON(cgroup_add_legacy_cftypes(ss, ss->legacy_cftypes)); } if (ss->bind) ss->bind(init_css_set.subsys[ssid]); cgroup_lock(); css_populate_dir(init_css_set.subsys[ssid]); cgroup_unlock(); } /* init_css_set.subsys[] has been updated, re-hash */ hash_del(&init_css_set.hlist); hash_add(css_set_table, &init_css_set.hlist, css_set_hash(init_css_set.subsys)); WARN_ON(sysfs_create_mount_point(fs_kobj, "cgroup")); WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show)); #ifdef CONFIG_CPUSETS_V1 WARN_ON(register_filesystem(&cpuset_fs_type)); #endif return 0; } static int __init cgroup_wq_init(void) { /* * There isn't much point in executing destruction path in * parallel. Good chunk is serialized with cgroup_mutex anyway. * Use 1 for @max_active. * * We would prefer to do this in cgroup_init() above, but that * is called before init_workqueues(): so leave this until after. */ cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); BUG_ON(!cgroup_destroy_wq); return 0; } core_initcall(cgroup_wq_init); void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen) { struct kernfs_node *kn; kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return; kernfs_path(kn, buf, buflen); kernfs_put(kn); } /* * cgroup_get_from_id : get the cgroup associated with cgroup id * @id: cgroup id * On success return the cgrp or ERR_PTR on failure * Only cgroups within current task's cgroup NS are valid. */ struct cgroup *cgroup_get_from_id(u64 id) { struct kernfs_node *kn; struct cgroup *cgrp, *root_cgrp; kn = kernfs_find_and_get_node_by_id(cgrp_dfl_root.kf_root, id); if (!kn) return ERR_PTR(-ENOENT); if (kernfs_type(kn) != KERNFS_DIR) { kernfs_put(kn); return ERR_PTR(-ENOENT); } rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp && !cgroup_tryget(cgrp)) cgrp = NULL; rcu_read_unlock(); kernfs_put(kn); if (!cgrp) return ERR_PTR(-ENOENT); root_cgrp = current_cgns_cgroup_dfl(); if (!cgroup_is_descendant(cgrp, root_cgrp)) { cgroup_put(cgrp); return ERR_PTR(-ENOENT); } return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_id); /* * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy * - Used for /proc/<pid>/cgroup. */ int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; int retval; struct cgroup_root *root; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; rcu_read_lock(); spin_lock_irq(&css_set_lock); for_each_root(root) { struct cgroup_subsys *ss; struct cgroup *cgrp; int ssid, count = 0; if (root == &cgrp_dfl_root && !READ_ONCE(cgrp_dfl_visible)) continue; cgrp = task_cgroup_from_root(tsk, root); /* The root has already been unmounted. */ if (!cgrp) continue; seq_printf(m, "%d:", root->hierarchy_id); if (root != &cgrp_dfl_root) for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_printf(m, "%s%s", count++ ? "," : "", ss->legacy_name); if (strlen(root->name)) seq_printf(m, "%sname=%s", count ? "," : "", root->name); seq_putc(m, ':'); /* * On traditional hierarchies, all zombie tasks show up as * belonging to the root cgroup. On the default hierarchy, * while a zombie doesn't show up in "cgroup.procs" and * thus can't be migrated, its /proc/PID/cgroup keeps * reporting the cgroup it belonged to before exiting. If * the cgroup is removed before the zombie is reaped, * " (deleted)" is appended to the cgroup path. */ if (cgroup_on_dfl(cgrp) || !(tsk->flags & PF_EXITING)) { retval = cgroup_path_ns_locked(cgrp, buf, PATH_MAX, current->nsproxy->cgroup_ns); if (retval == -E2BIG) retval = -ENAMETOOLONG; if (retval < 0) goto out_unlock; seq_puts(m, buf); } else { seq_puts(m, "/"); } if (cgroup_on_dfl(cgrp) && cgroup_is_dead(cgrp)) seq_puts(m, " (deleted)\n"); else seq_putc(m, '\n'); } retval = 0; out_unlock: spin_unlock_irq(&css_set_lock); rcu_read_unlock(); kfree(buf); out: return retval; } /** * cgroup_fork - initialize cgroup related fields during copy_process() * @child: pointer to task_struct of forking parent process. * * A task is associated with the init_css_set until cgroup_post_fork() * attaches it to the target css_set. */ void cgroup_fork(struct task_struct *child) { RCU_INIT_POINTER(child->cgroups, &init_css_set); INIT_LIST_HEAD(&child->cg_list); } /** * cgroup_v1v2_get_from_file - get a cgroup pointer from a file pointer * @f: file corresponding to cgroup_dir * * Find the cgroup from a file pointer associated with a cgroup directory. * Returns a pointer to the cgroup on success. ERR_PTR is returned if the * cgroup cannot be found. */ static struct cgroup *cgroup_v1v2_get_from_file(struct file *f) { struct cgroup_subsys_state *css; css = css_tryget_online_from_dir(f->f_path.dentry, NULL); if (IS_ERR(css)) return ERR_CAST(css); return css->cgroup; } /** * cgroup_get_from_file - same as cgroup_v1v2_get_from_file, but only supports * cgroup2. * @f: file corresponding to cgroup2_dir */ static struct cgroup *cgroup_get_from_file(struct file *f) { struct cgroup *cgrp = cgroup_v1v2_get_from_file(f); if (IS_ERR(cgrp)) return ERR_CAST(cgrp); if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp; } /** * cgroup_css_set_fork - find or create a css_set for a child process * @kargs: the arguments passed to create the child process * * This functions finds or creates a new css_set which the child * process will be attached to in cgroup_post_fork(). By default, * the child process will be given the same css_set as its parent. * * If CLONE_INTO_CGROUP is specified this function will try to find an * existing css_set which includes the requested cgroup and if not create * a new css_set that the child will be attached to later. If this function * succeeds it will hold cgroup_threadgroup_rwsem on return. If * CLONE_INTO_CGROUP is requested this function will grab cgroup mutex * before grabbing cgroup_threadgroup_rwsem and will hold a reference * to the target cgroup. */ static int cgroup_css_set_fork(struct kernel_clone_args *kargs) __acquires(&cgroup_mutex) __acquires(&cgroup_threadgroup_rwsem) { int ret; struct cgroup *dst_cgrp = NULL; struct css_set *cset; struct super_block *sb; if (kargs->flags & CLONE_INTO_CGROUP) cgroup_lock(); cgroup_threadgroup_change_begin(current); spin_lock_irq(&css_set_lock); cset = task_css_set(current); get_css_set(cset); if (kargs->cgrp) kargs->kill_seq = kargs->cgrp->kill_seq; else kargs->kill_seq = cset->dfl_cgrp->kill_seq; spin_unlock_irq(&css_set_lock); if (!(kargs->flags & CLONE_INTO_CGROUP)) { kargs->cset = cset; return 0; } CLASS(fd_raw, f)(kargs->cgroup); if (fd_empty(f)) { ret = -EBADF; goto err; } sb = fd_file(f)->f_path.dentry->d_sb; dst_cgrp = cgroup_get_from_file(fd_file(f)); if (IS_ERR(dst_cgrp)) { ret = PTR_ERR(dst_cgrp); dst_cgrp = NULL; goto err; } if (cgroup_is_dead(dst_cgrp)) { ret = -ENODEV; goto err; } /* * Verify that we the target cgroup is writable for us. This is * usually done by the vfs layer but since we're not going through * the vfs layer here we need to do it "manually". */ ret = cgroup_may_write(dst_cgrp, sb); if (ret) goto err; /* * Spawning a task directly into a cgroup works by passing a file * descriptor to the target cgroup directory. This can even be an O_PATH * file descriptor. But it can never be a cgroup.procs file descriptor. * This was done on purpose so spawning into a cgroup could be * conceptualized as an atomic * * fd = openat(dfd_cgroup, "cgroup.procs", ...); * write(fd, <child-pid>, ...); * * sequence, i.e. it's a shorthand for the caller opening and writing * cgroup.procs of the cgroup indicated by @dfd_cgroup. This allows us * to always use the caller's credentials. */ ret = cgroup_attach_permissions(cset->dfl_cgrp, dst_cgrp, sb, !(kargs->flags & CLONE_THREAD), current->nsproxy->cgroup_ns); if (ret) goto err; kargs->cset = find_css_set(cset, dst_cgrp); if (!kargs->cset) { ret = -ENOMEM; goto err; } put_css_set(cset); kargs->cgrp = dst_cgrp; return ret; err: cgroup_threadgroup_change_end(current); cgroup_unlock(); if (dst_cgrp) cgroup_put(dst_cgrp); put_css_set(cset); if (kargs->cset) put_css_set(kargs->cset); return ret; } /** * cgroup_css_set_put_fork - drop references we took during fork * @kargs: the arguments passed to create the child process * * Drop references to the prepared css_set and target cgroup if * CLONE_INTO_CGROUP was requested. */ static void cgroup_css_set_put_fork(struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { struct cgroup *cgrp = kargs->cgrp; struct css_set *cset = kargs->cset; cgroup_threadgroup_change_end(current); if (cset) { put_css_set(cset); kargs->cset = NULL; } if (kargs->flags & CLONE_INTO_CGROUP) { cgroup_unlock(); if (cgrp) { cgroup_put(cgrp); kargs->cgrp = NULL; } } } /** * cgroup_can_fork - called on a new task before the process is exposed * @child: the child process * @kargs: the arguments passed to create the child process * * This prepares a new css_set for the child process which the child will * be attached to in cgroup_post_fork(). * This calls the subsystem can_fork() callbacks. If the cgroup_can_fork() * callback returns an error, the fork aborts with that error code. This * allows for a cgroup subsystem to conditionally allow or deny new forks. */ int cgroup_can_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i, j, ret; ret = cgroup_css_set_fork(kargs); if (ret) return ret; do_each_subsys_mask(ss, i, have_canfork_callback) { ret = ss->can_fork(child, kargs->cset); if (ret) goto out_revert; } while_each_subsys_mask(); return 0; out_revert: for_each_subsys(ss, j) { if (j >= i) break; if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); } cgroup_css_set_put_fork(kargs); return ret; } /** * cgroup_cancel_fork - called if a fork failed after cgroup_can_fork() * @child: the child process * @kargs: the arguments passed to create the child process * * This calls the cancel_fork() callbacks if a fork failed *after* * cgroup_can_fork() succeeded and cleans up references we took to * prepare a new css_set for the child process in cgroup_can_fork(). */ void cgroup_cancel_fork(struct task_struct *child, struct kernel_clone_args *kargs) { struct cgroup_subsys *ss; int i; for_each_subsys(ss, i) if (ss->cancel_fork) ss->cancel_fork(child, kargs->cset); cgroup_css_set_put_fork(kargs); } /** * cgroup_post_fork - finalize cgroup setup for the child process * @child: the child process * @kargs: the arguments passed to create the child process * * Attach the child process to its css_set calling the subsystem fork() * callbacks. */ void cgroup_post_fork(struct task_struct *child, struct kernel_clone_args *kargs) __releases(&cgroup_threadgroup_rwsem) __releases(&cgroup_mutex) { unsigned int cgrp_kill_seq = 0; unsigned long cgrp_flags = 0; bool kill = false; struct cgroup_subsys *ss; struct css_set *cset; int i; cset = kargs->cset; kargs->cset = NULL; spin_lock_irq(&css_set_lock); /* init tasks are special, only link regular threads */ if (likely(child->pid)) { if (kargs->cgrp) { cgrp_flags = kargs->cgrp->flags; cgrp_kill_seq = kargs->cgrp->kill_seq; } else { cgrp_flags = cset->dfl_cgrp->flags; cgrp_kill_seq = cset->dfl_cgrp->kill_seq; } WARN_ON_ONCE(!list_empty(&child->cg_list)); cset->nr_tasks++; css_set_move_task(child, NULL, cset, false); } else { put_css_set(cset); cset = NULL; } if (!(child->flags & PF_KTHREAD)) { if (unlikely(test_bit(CGRP_FREEZE, &cgrp_flags))) { /* * If the cgroup has to be frozen, the new task has * too. Let's set the JOBCTL_TRAP_FREEZE jobctl bit to * get the task into the frozen state. */ spin_lock(&child->sighand->siglock); WARN_ON_ONCE(child->frozen); child->jobctl |= JOBCTL_TRAP_FREEZE; spin_unlock(&child->sighand->siglock); /* * Calling cgroup_update_frozen() isn't required here, * because it will be called anyway a bit later from * do_freezer_trap(). So we avoid cgroup's transient * switch from the frozen state and back. */ } /* * If the cgroup is to be killed notice it now and take the * child down right after we finished preparing it for * userspace. */ kill = kargs->kill_seq != cgrp_kill_seq; } spin_unlock_irq(&css_set_lock); /* * Call ss->fork(). This must happen after @child is linked on * css_set; otherwise, @child might change state between ->fork() * and addition to css_set. */ do_each_subsys_mask(ss, i, have_fork_callback) { ss->fork(child); } while_each_subsys_mask(); /* Make the new cset the root_cset of the new cgroup namespace. */ if (kargs->flags & CLONE_NEWCGROUP) { struct css_set *rcset = child->nsproxy->cgroup_ns->root_cset; get_css_set(cset); child->nsproxy->cgroup_ns->root_cset = cset; put_css_set(rcset); } /* Cgroup has to be killed so take down child immediately. */ if (unlikely(kill)) do_send_sig_info(SIGKILL, SEND_SIG_NOINFO, child, PIDTYPE_TGID); cgroup_css_set_put_fork(kargs); } /** * cgroup_exit - detach cgroup from exiting task * @tsk: pointer to task_struct of exiting process * * Description: Detach cgroup from @tsk. * */ void cgroup_exit(struct task_struct *tsk) { struct cgroup_subsys *ss; struct css_set *cset; int i; spin_lock_irq(&css_set_lock); WARN_ON_ONCE(list_empty(&tsk->cg_list)); cset = task_css_set(tsk); css_set_move_task(tsk, cset, NULL, false); cset->nr_tasks--; /* matches the signal->live check in css_task_iter_advance() */ if (thread_group_leader(tsk) && atomic_read(&tsk->signal->live)) list_add_tail(&tsk->cg_list, &cset->dying_tasks); if (dl_task(tsk)) dec_dl_tasks_cs(tsk); WARN_ON_ONCE(cgroup_task_frozen(tsk)); if (unlikely(!(tsk->flags & PF_KTHREAD) && test_bit(CGRP_FREEZE, &task_dfl_cgroup(tsk)->flags))) cgroup_update_frozen(task_dfl_cgroup(tsk)); spin_unlock_irq(&css_set_lock); /* see cgroup_post_fork() for details */ do_each_subsys_mask(ss, i, have_exit_callback) { ss->exit(tsk); } while_each_subsys_mask(); } void cgroup_release(struct task_struct *task) { struct cgroup_subsys *ss; int ssid; do_each_subsys_mask(ss, ssid, have_release_callback) { ss->release(task); } while_each_subsys_mask(); if (!list_empty(&task->cg_list)) { spin_lock_irq(&css_set_lock); css_set_skip_task_iters(task_css_set(task), task); list_del_init(&task->cg_list); spin_unlock_irq(&css_set_lock); } } void cgroup_free(struct task_struct *task) { struct css_set *cset = task_css_set(task); put_css_set(cset); } static int __init cgroup_disable(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; static_branch_disable(cgroup_subsys_enabled_key[i]); pr_info("Disabling %s control group subsystem\n", ss->name); } for (i = 0; i < OPT_FEATURE_COUNT; i++) { if (strcmp(token, cgroup_opt_feature_names[i])) continue; cgroup_feature_disable_mask |= 1 << i; pr_info("Disabling %s control group feature\n", cgroup_opt_feature_names[i]); break; } } return 1; } __setup("cgroup_disable=", cgroup_disable); void __init __weak enable_debug_cgroup(void) { } static int __init enable_cgroup_debug(char *str) { cgroup_debug = true; enable_debug_cgroup(); return 1; } __setup("cgroup_debug", enable_cgroup_debug); static int __init cgroup_favordynmods_setup(char *str) { return (kstrtobool(str, &have_favordynmods) == 0); } __setup("cgroup_favordynmods=", cgroup_favordynmods_setup); /** * css_tryget_online_from_dir - get corresponding css from a cgroup dentry * @dentry: directory dentry of interest * @ss: subsystem of interest * * If @dentry is a directory for a cgroup which has @ss enabled on it, try * to get the corresponding css and return it. If such css doesn't exist * or can't be pinned, an ERR_PTR value is returned. */ struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, struct cgroup_subsys *ss) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct file_system_type *s_type = dentry->d_sb->s_type; struct cgroup_subsys_state *css = NULL; struct cgroup *cgrp; /* is @dentry a cgroup dir? */ if ((s_type != &cgroup_fs_type && s_type != &cgroup2_fs_type) || !kn || kernfs_type(kn) != KERNFS_DIR) return ERR_PTR(-EBADF); rcu_read_lock(); /* * This path doesn't originate from kernfs and @kn could already * have been or be removed at any point. @kn->priv is RCU * protected for this access. See css_release_work_fn() for details. */ cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (cgrp) css = cgroup_css(cgrp, ss); if (!css || !css_tryget_online(css)) css = ERR_PTR(-ENOENT); rcu_read_unlock(); return css; } /** * css_from_id - lookup css by id * @id: the cgroup id * @ss: cgroup subsys to be looked into * * Returns the css if there's valid one with @id, otherwise returns NULL. * Should be called under rcu_read_lock(). */ struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss) { WARN_ON_ONCE(!rcu_read_lock_held()); return idr_find(&ss->css_idr, id); } /** * cgroup_get_from_path - lookup and get a cgroup from its default hierarchy path * @path: path on the default hierarchy * * Find the cgroup at @path on the default hierarchy, increment its * reference count and return it. Returns pointer to the found cgroup on * success, ERR_PTR(-ENOENT) if @path doesn't exist or if the cgroup has already * been released and ERR_PTR(-ENOTDIR) if @path points to a non-directory. */ struct cgroup *cgroup_get_from_path(const char *path) { struct kernfs_node *kn; struct cgroup *cgrp = ERR_PTR(-ENOENT); struct cgroup *root_cgrp; root_cgrp = current_cgns_cgroup_dfl(); kn = kernfs_walk_and_get(root_cgrp->kn, path); if (!kn) goto out; if (kernfs_type(kn) != KERNFS_DIR) { cgrp = ERR_PTR(-ENOTDIR); goto out_kernfs; } rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || !cgroup_tryget(cgrp)) cgrp = ERR_PTR(-ENOENT); rcu_read_unlock(); out_kernfs: kernfs_put(kn); out: return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_path); /** * cgroup_v1v2_get_from_fd - get a cgroup pointer from a fd * @fd: fd obtained by open(cgroup_dir) * * Find the cgroup from a fd which should be obtained * by opening a cgroup directory. Returns a pointer to the * cgroup on success. ERR_PTR is returned if the cgroup * cannot be found. */ struct cgroup *cgroup_v1v2_get_from_fd(int fd) { CLASS(fd_raw, f)(fd); if (fd_empty(f)) return ERR_PTR(-EBADF); return cgroup_v1v2_get_from_file(fd_file(f)); } /** * cgroup_get_from_fd - same as cgroup_v1v2_get_from_fd, but only supports * cgroup2. * @fd: fd obtained by open(cgroup2_dir) */ struct cgroup *cgroup_get_from_fd(int fd) { struct cgroup *cgrp = cgroup_v1v2_get_from_fd(fd); if (IS_ERR(cgrp)) return ERR_CAST(cgrp); if (!cgroup_on_dfl(cgrp)) { cgroup_put(cgrp); return ERR_PTR(-EBADF); } return cgrp; } EXPORT_SYMBOL_GPL(cgroup_get_from_fd); static u64 power_of_ten(int power) { u64 v = 1; while (power--) v *= 10; return v; } /** * cgroup_parse_float - parse a floating number * @input: input string * @dec_shift: number of decimal digits to shift * @v: output * * Parse a decimal floating point number in @input and store the result in * @v with decimal point right shifted @dec_shift times. For example, if * @input is "12.3456" and @dec_shift is 3, *@v will be set to 12345. * Returns 0 on success, -errno otherwise. * * There's nothing cgroup specific about this function except that it's * currently the only user. */ int cgroup_parse_float(const char *input, unsigned dec_shift, s64 *v) { s64 whole, frac = 0; int fstart = 0, fend = 0, flen; if (!sscanf(input, "%lld.%n%lld%n", &whole, &fstart, &frac, &fend)) return -EINVAL; if (frac < 0) return -EINVAL; flen = fend > fstart ? fend - fstart : 0; if (flen < dec_shift) frac *= power_of_ten(dec_shift - flen); else frac = DIV_ROUND_CLOSEST_ULL(frac, power_of_ten(flen - dec_shift)); *v = whole * power_of_ten(dec_shift) + frac; return 0; } /* * sock->sk_cgrp_data handling. For more info, see sock_cgroup_data * definition in cgroup-defs.h. */ #ifdef CONFIG_SOCK_CGROUP_DATA void cgroup_sk_alloc(struct sock_cgroup_data *skcd) { struct cgroup *cgroup; rcu_read_lock(); /* Don't associate the sock with unrelated interrupted task's cgroup. */ if (in_interrupt()) { cgroup = &cgrp_dfl_root.cgrp; cgroup_get(cgroup); goto out; } while (true) { struct css_set *cset; cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { cgroup = cset->dfl_cgrp; break; } cpu_relax(); } out: skcd->cgroup = cgroup; cgroup_bpf_get(cgroup); rcu_read_unlock(); } void cgroup_sk_clone(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); /* * We might be cloning a socket which is left in an empty * cgroup and the cgroup might have already been rmdir'd. * Don't use cgroup_get_live(). */ cgroup_get(cgrp); cgroup_bpf_get(cgrp); } void cgroup_sk_free(struct sock_cgroup_data *skcd) { struct cgroup *cgrp = sock_cgroup_ptr(skcd); cgroup_bpf_put(cgrp); cgroup_put(cgrp); } #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_SYSFS static ssize_t show_delegatable_files(struct cftype *files, char *buf, ssize_t size, const char *prefix) { struct cftype *cft; ssize_t ret = 0; for (cft = files; cft && cft->name[0] != '\0'; cft++) { if (!(cft->flags & CFTYPE_NS_DELEGATABLE)) continue; if (prefix) ret += snprintf(buf + ret, size - ret, "%s.", prefix); ret += snprintf(buf + ret, size - ret, "%s\n", cft->name); if (WARN_ON(ret >= size)) break; } return ret; } static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct cgroup_subsys *ss; int ssid; ssize_t ret = 0; ret = show_delegatable_files(cgroup_base_files, buf + ret, PAGE_SIZE - ret, NULL); if (cgroup_psi_enabled()) ret += show_delegatable_files(cgroup_psi_files, buf + ret, PAGE_SIZE - ret, NULL); for_each_subsys(ss, ssid) ret += show_delegatable_files(ss->dfl_cftypes, buf + ret, PAGE_SIZE - ret, cgroup_subsys_name[ssid]); return ret; } static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate); static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE, "nsdelegate\n" "favordynmods\n" "memory_localevents\n" "memory_recursiveprot\n" "memory_hugetlb_accounting\n" "pids_localevents\n"); } static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features); static struct attribute *cgroup_sysfs_attrs[] = { &cgroup_delegate_attr.attr, &cgroup_features_attr.attr, NULL, }; static const struct attribute_group cgroup_sysfs_attr_group = { .attrs = cgroup_sysfs_attrs, .name = "cgroup", }; static int __init cgroup_sysfs_init(void) { return sysfs_create_group(kernel_kobj, &cgroup_sysfs_attr_group); } subsys_initcall(cgroup_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 33 33 33 1 1 1 1 2 34 2 26 26 25 1 24 24 24 34 34 1 1 32 2 2 1 1 3 21 5 9 8 16 16 1 16 3 3 3 3 3 3 1 1 1 3 3 3 1 2 4 4 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2017 Red Hat, Inc. */ #include <linux/cred.h> #include <linux/file.h> #include <linux/mount.h> #include <linux/xattr.h> #include <linux/uio.h> #include <linux/uaccess.h> #include <linux/security.h> #include <linux/fs.h> #include <linux/backing-file.h> #include "overlayfs.h" static char ovl_whatisit(struct inode *inode, struct inode *realinode) { if (realinode != ovl_inode_upper(inode)) return 'l'; if (ovl_has_upperdata(inode)) return 'u'; else return 'm'; } static struct file *ovl_open_realfile(const struct file *file, const struct path *realpath) { struct inode *realinode = d_inode(realpath->dentry); struct inode *inode = file_inode(file); struct mnt_idmap *real_idmap; struct file *realfile; const struct cred *old_cred; int flags = file->f_flags | OVL_OPEN_FLAGS; int acc_mode = ACC_MODE(flags); int err; if (flags & O_APPEND) acc_mode |= MAY_APPEND; old_cred = ovl_override_creds(inode->i_sb); real_idmap = mnt_idmap(realpath->mnt); err = inode_permission(real_idmap, realinode, MAY_OPEN | acc_mode); if (err) { realfile = ERR_PTR(err); } else { if (!inode_owner_or_capable(real_idmap, realinode)) flags &= ~O_NOATIME; realfile = backing_file_open(file_user_path(file), flags, realpath, current_cred()); } ovl_revert_creds(old_cred); pr_debug("open(%p[%pD2/%c], 0%o) -> (%p, 0%o)\n", file, file, ovl_whatisit(inode, realinode), file->f_flags, realfile, IS_ERR(realfile) ? 0 : realfile->f_flags); return realfile; } #define OVL_SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT) static int ovl_change_flags(struct file *file, unsigned int flags) { struct inode *inode = file_inode(file); int err; flags &= OVL_SETFL_MASK; if (((flags ^ file->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; if ((flags & O_DIRECT) && !(file->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; if (file->f_op->check_flags) { err = file->f_op->check_flags(flags); if (err) return err; } spin_lock(&file->f_lock); file->f_flags = (file->f_flags & ~OVL_SETFL_MASK) | flags; file->f_iocb_flags = iocb_flags(file); spin_unlock(&file->f_lock); return 0; } struct ovl_file { struct file *realfile; struct file *upperfile; }; struct ovl_file *ovl_file_alloc(struct file *realfile) { struct ovl_file *of = kzalloc(sizeof(struct ovl_file), GFP_KERNEL); if (unlikely(!of)) return NULL; of->realfile = realfile; return of; } void ovl_file_free(struct ovl_file *of) { fput(of->realfile); if (of->upperfile) fput(of->upperfile); kfree(of); } static bool ovl_is_real_file(const struct file *realfile, const struct path *realpath) { return file_inode(realfile) == d_inode(realpath->dentry); } static struct file *ovl_real_file_path(const struct file *file, struct path *realpath) { struct ovl_file *of = file->private_data; struct file *realfile = of->realfile; if (WARN_ON_ONCE(!realpath->dentry)) return ERR_PTR(-EIO); /* * If the realfile that we want is not where the data used to be at * open time, either we'd been copied up, or it's an fsync of a * metacopied file. We need the upperfile either way, so see if it * is already opened and if it is not then open and store it. */ if (unlikely(!ovl_is_real_file(realfile, realpath))) { struct file *upperfile = READ_ONCE(of->upperfile); struct file *old; if (!upperfile) { /* Nobody opened upperfile yet */ upperfile = ovl_open_realfile(file, realpath); if (IS_ERR(upperfile)) return upperfile; /* Store the upperfile for later */ old = cmpxchg_release(&of->upperfile, NULL, upperfile); if (old) { /* Someone opened upperfile before us */ fput(upperfile); upperfile = old; } } /* * Stored file must be from the right inode, unless someone's * been corrupting the upper layer. */ if (WARN_ON_ONCE(!ovl_is_real_file(upperfile, realpath))) return ERR_PTR(-EIO); realfile = upperfile; } /* Did the flags change since open? */ if (unlikely((file->f_flags ^ realfile->f_flags) & ~OVL_OPEN_FLAGS)) { int err = ovl_change_flags(realfile, file->f_flags); if (err) return ERR_PTR(err); } return realfile; } static struct file *ovl_real_file(const struct file *file) { struct dentry *dentry = file_dentry(file); struct path realpath; int err; if (d_is_dir(dentry)) { struct file *f = ovl_dir_real_file(file, false); if (WARN_ON_ONCE(!f)) return ERR_PTR(-EIO); return f; } /* lazy lookup and verify of lowerdata */ err = ovl_verify_lowerdata(dentry); if (err) return ERR_PTR(err); ovl_path_realdata(dentry, &realpath); return ovl_real_file_path(file, &realpath); } static int ovl_open(struct inode *inode, struct file *file) { struct dentry *dentry = file_dentry(file); struct file *realfile; struct path realpath; struct ovl_file *of; int err; /* lazy lookup and verify lowerdata */ err = ovl_verify_lowerdata(dentry); if (err) return err; err = ovl_maybe_copy_up(dentry, file->f_flags); if (err) return err; /* No longer need these flags, so don't pass them on to underlying fs */ file->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC); ovl_path_realdata(dentry, &realpath); if (!realpath.dentry) return -EIO; realfile = ovl_open_realfile(file, &realpath); if (IS_ERR(realfile)) return PTR_ERR(realfile); of = ovl_file_alloc(realfile); if (!of) { fput(realfile); return -ENOMEM; } file->private_data = of; return 0; } static int ovl_release(struct inode *inode, struct file *file) { ovl_file_free(file->private_data); return 0; } static loff_t ovl_llseek(struct file *file, loff_t offset, int whence) { struct inode *inode = file_inode(file); struct file *realfile; const struct cred *old_cred; loff_t ret; /* * The two special cases below do not need to involve real fs, * so we can optimizing concurrent callers. */ if (offset == 0) { if (whence == SEEK_CUR) return file->f_pos; if (whence == SEEK_SET) return vfs_setpos(file, 0, 0); } realfile = ovl_real_file(file); if (IS_ERR(realfile)) return PTR_ERR(realfile); /* * Overlay file f_pos is the master copy that is preserved * through copy up and modified on read/write, but only real * fs knows how to SEEK_HOLE/SEEK_DATA and real fs may impose * limitations that are more strict than ->s_maxbytes for specific * files, so we use the real file to perform seeks. */ ovl_inode_lock(inode); realfile->f_pos = file->f_pos; old_cred = ovl_override_creds(inode->i_sb); ret = vfs_llseek(realfile, offset, whence); ovl_revert_creds(old_cred); file->f_pos = realfile->f_pos; ovl_inode_unlock(inode); return ret; } static void ovl_file_modified(struct file *file) { /* Update size/mtime */ ovl_copyattr(file_inode(file)); } static void ovl_file_end_write(struct kiocb *iocb, ssize_t ret) { ovl_file_modified(iocb->ki_filp); } static void ovl_file_accessed(struct file *file) { struct inode *inode, *upperinode; struct timespec64 ctime, uctime; struct timespec64 mtime, umtime; if (file->f_flags & O_NOATIME) return; inode = file_inode(file); upperinode = ovl_inode_upper(inode); if (!upperinode) return; ctime = inode_get_ctime(inode); uctime = inode_get_ctime(upperinode); mtime = inode_get_mtime(inode); umtime = inode_get_mtime(upperinode); if ((!timespec64_equal(&mtime, &umtime)) || !timespec64_equal(&ctime, &uctime)) { inode_set_mtime_to_ts(inode, inode_get_mtime(upperinode)); inode_set_ctime_to_ts(inode, uctime); } touch_atime(&file->f_path); } static ssize_t ovl_read_iter(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct file *realfile; struct backing_file_ctx ctx = { .cred = ovl_creds(file_inode(file)->i_sb), .accessed = ovl_file_accessed, }; if (!iov_iter_count(iter)) return 0; realfile = ovl_real_file(file); if (IS_ERR(realfile)) return PTR_ERR(realfile); return backing_file_read_iter(realfile, iter, iocb, iocb->ki_flags, &ctx); } static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct inode *inode = file_inode(file); struct file *realfile; ssize_t ret; int ifl = iocb->ki_flags; struct backing_file_ctx ctx = { .cred = ovl_creds(inode->i_sb), .end_write = ovl_file_end_write, }; if (!iov_iter_count(iter)) return 0; inode_lock(inode); /* Update mode */ ovl_copyattr(inode); realfile = ovl_real_file(file); ret = PTR_ERR(realfile); if (IS_ERR(realfile)) goto out_unlock; if (!ovl_should_sync(OVL_FS(inode->i_sb))) ifl &= ~(IOCB_DSYNC | IOCB_SYNC); /* * Overlayfs doesn't support deferred completions, don't copy * this property in case it is set by the issuer. */ ifl &= ~IOCB_DIO_CALLER_COMP; ret = backing_file_write_iter(realfile, iter, iocb, ifl, &ctx); out_unlock: inode_unlock(inode); return ret; } static ssize_t ovl_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct file *realfile; ssize_t ret; struct backing_file_ctx ctx = { .cred = ovl_creds(file_inode(in)->i_sb), .accessed = ovl_file_accessed, }; struct kiocb iocb; realfile = ovl_real_file(in); if (IS_ERR(realfile)) return PTR_ERR(realfile); init_sync_kiocb(&iocb, in); iocb.ki_pos = *ppos; ret = backing_file_splice_read(realfile, &iocb, pipe, len, flags, &ctx); *ppos = iocb.ki_pos; return ret; } /* * Calling iter_file_splice_write() directly from overlay's f_op may deadlock * due to lock order inversion between pipe->mutex in iter_file_splice_write() * and file_start_write(realfile) in ovl_write_iter(). * * So do everything ovl_write_iter() does and call iter_file_splice_write() on * the real file. */ static ssize_t ovl_splice_write(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { struct file *realfile; struct inode *inode = file_inode(out); ssize_t ret; struct backing_file_ctx ctx = { .cred = ovl_creds(inode->i_sb), .end_write = ovl_file_end_write, }; struct kiocb iocb; inode_lock(inode); /* Update mode */ ovl_copyattr(inode); realfile = ovl_real_file(out); ret = PTR_ERR(realfile); if (IS_ERR(realfile)) goto out_unlock; init_sync_kiocb(&iocb, out); iocb.ki_pos = *ppos; ret = backing_file_splice_write(pipe, realfile, &iocb, len, flags, &ctx); *ppos = iocb.ki_pos; out_unlock: inode_unlock(inode); return ret; } static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct dentry *dentry = file_dentry(file); enum ovl_path_type type; struct path upperpath; struct file *upperfile; const struct cred *old_cred; int ret; ret = ovl_sync_status(OVL_FS(file_inode(file)->i_sb)); if (ret <= 0) return ret; /* Don't sync lower file for fear of receiving EROFS error */ type = ovl_path_type(dentry); if (!OVL_TYPE_UPPER(type) || (datasync && OVL_TYPE_MERGE(type))) return 0; ovl_path_upper(dentry, &upperpath); upperfile = ovl_real_file_path(file, &upperpath); if (IS_ERR(upperfile)) return PTR_ERR(upperfile); old_cred = ovl_override_creds(file_inode(file)->i_sb); ret = vfs_fsync_range(upperfile, start, end, datasync); ovl_revert_creds(old_cred); return ret; } static int ovl_mmap(struct file *file, struct vm_area_struct *vma) { struct ovl_file *of = file->private_data; struct backing_file_ctx ctx = { .cred = ovl_creds(file_inode(file)->i_sb), .accessed = ovl_file_accessed, }; return backing_file_mmap(of->realfile, vma, &ctx); } static long ovl_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct file *realfile; const struct cred *old_cred; int ret; inode_lock(inode); /* Update mode */ ovl_copyattr(inode); ret = file_remove_privs(file); if (ret) goto out_unlock; realfile = ovl_real_file(file); ret = PTR_ERR(realfile); if (IS_ERR(realfile)) goto out_unlock; old_cred = ovl_override_creds(file_inode(file)->i_sb); ret = vfs_fallocate(realfile, mode, offset, len); ovl_revert_creds(old_cred); /* Update size */ ovl_file_modified(file); out_unlock: inode_unlock(inode); return ret; } static int ovl_fadvise(struct file *file, loff_t offset, loff_t len, int advice) { struct file *realfile; const struct cred *old_cred; int ret; realfile = ovl_real_file(file); if (IS_ERR(realfile)) return PTR_ERR(realfile); old_cred = ovl_override_creds(file_inode(file)->i_sb); ret = vfs_fadvise(realfile, offset, len, advice); ovl_revert_creds(old_cred); return ret; } enum ovl_copyop { OVL_COPY, OVL_CLONE, OVL_DEDUPE, }; static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int flags, enum ovl_copyop op) { struct inode *inode_out = file_inode(file_out); struct file *realfile_in, *realfile_out; const struct cred *old_cred; loff_t ret; inode_lock(inode_out); if (op != OVL_DEDUPE) { /* Update mode */ ovl_copyattr(inode_out); ret = file_remove_privs(file_out); if (ret) goto out_unlock; } realfile_out = ovl_real_file(file_out); ret = PTR_ERR(realfile_out); if (IS_ERR(realfile_out)) goto out_unlock; realfile_in = ovl_real_file(file_in); ret = PTR_ERR(realfile_in); if (IS_ERR(realfile_in)) goto out_unlock; old_cred = ovl_override_creds(file_inode(file_out)->i_sb); switch (op) { case OVL_COPY: ret = vfs_copy_file_range(realfile_in, pos_in, realfile_out, pos_out, len, flags); break; case OVL_CLONE: ret = vfs_clone_file_range(realfile_in, pos_in, realfile_out, pos_out, len, flags); break; case OVL_DEDUPE: ret = vfs_dedupe_file_range_one(realfile_in, pos_in, realfile_out, pos_out, len, flags); break; } ovl_revert_creds(old_cred); /* Update size */ ovl_file_modified(file_out); out_unlock: inode_unlock(inode_out); return ret; } static ssize_t ovl_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) { return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, flags, OVL_COPY); } static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags) { enum ovl_copyop op; if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; if (remap_flags & REMAP_FILE_DEDUP) op = OVL_DEDUPE; else op = OVL_CLONE; /* * Don't copy up because of a dedupe request, this wouldn't make sense * most of the time (data would be duplicated instead of deduplicated). */ if (op == OVL_DEDUPE && (!ovl_inode_upper(file_inode(file_in)) || !ovl_inode_upper(file_inode(file_out)))) return -EPERM; return ovl_copyfile(file_in, pos_in, file_out, pos_out, len, remap_flags, op); } static int ovl_flush(struct file *file, fl_owner_t id) { struct file *realfile; const struct cred *old_cred; int err = 0; realfile = ovl_real_file(file); if (IS_ERR(realfile)) return PTR_ERR(realfile); if (realfile->f_op->flush) { old_cred = ovl_override_creds(file_inode(file)->i_sb); err = realfile->f_op->flush(realfile, id); ovl_revert_creds(old_cred); } return err; } const struct file_operations ovl_file_operations = { .open = ovl_open, .release = ovl_release, .llseek = ovl_llseek, .read_iter = ovl_read_iter, .write_iter = ovl_write_iter, .fsync = ovl_fsync, .mmap = ovl_mmap, .fallocate = ovl_fallocate, .fadvise = ovl_fadvise, .flush = ovl_flush, .splice_read = ovl_splice_read, .splice_write = ovl_splice_write, .copy_file_range = ovl_copy_file_range, .remap_file_range = ovl_remap_file_range, }; |
| 4 4 2 2 2 2 4 4 4 4 4 4 4 4 4 4 4 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET An implementation of the SOCKET network access protocol. * * Version: @(#)socket.c 1.1.93 18/02/95 * * Authors: Orest Zborowski, <obz@Kodak.COM> * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Fixes: * Anonymous : NOTSOCK/BADF cleanup. Error fix in * shutdown() * Alan Cox : verify_area() fixes * Alan Cox : Removed DDI * Jonathan Kamens : SOCK_DGRAM reconnect bug * Alan Cox : Moved a load of checks to the very * top level. * Alan Cox : Move address structures to/from user * mode above the protocol layers. * Rob Janssen : Allow 0 length sends. * Alan Cox : Asynchronous I/O support (cribbed from the * tty drivers). * Niibe Yutaka : Asynchronous I/O for writes (4.4BSD style) * Jeff Uphoff : Made max number of sockets command-line * configurable. * Matti Aarnio : Made the number of sockets dynamic, * to be allocated when needed, and mr. * Uphoff's max is used as max to be * allowed to allocate. * Linus : Argh. removed all the socket allocation * altogether: it's in the inode now. * Alan Cox : Made sock_alloc()/sock_release() public * for NetROM and future kernel nfsd type * stuff. * Alan Cox : sendmsg/recvmsg basics. * Tom Dyas : Export net symbols. * Marcin Dalecki : Fixed problems with CONFIG_NET="n". * Alan Cox : Added thread locking to sys_* calls * for sockets. May have errors at the * moment. * Kevin Buhr : Fixed the dumb errors in the above. * Andi Kleen : Some small cleanups, optimizations, * and fixed a copy_from_user() bug. * Tigran Aivazian : sys_send(args) calls sys_sendto(args, NULL, 0) * Tigran Aivazian : Made listen(2) backlog sanity checks * protocol-independent * * This module is effectively the top level interface to the BSD socket * paradigm. * * Based upon Swansea University Computer Society NET3.039 */ #include <linux/bpf-cgroup.h> #include <linux/ethtool.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/file.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/interrupt.h> #include <linux/thread_info.h> #include <linux/rcupdate.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/mutex.h> #include <linux/if_bridge.h> #include <linux/if_vlan.h> #include <linux/ptp_classify.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/cache.h> #include <linux/module.h> #include <linux/highmem.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/compat.h> #include <linux/kmod.h> #include <linux/audit.h> #include <linux/wireless.h> #include <linux/nsproxy.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/nospec.h> #include <linux/indirect_call_wrapper.h> #include <linux/io_uring/net.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <net/compat.h> #include <net/wext.h> #include <net/cls_cgroup.h> #include <net/sock.h> #include <linux/netfilter.h> #include <linux/if_tun.h> #include <linux/ipv6_route.h> #include <linux/route.h> #include <linux/termios.h> #include <linux/sockios.h> #include <net/busy_poll.h> #include <linux/errqueue.h> #include <linux/ptp_clock_kernel.h> #include <trace/events/sock.h> #include "core/dev.h" #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; #endif static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to); static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from); static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait); static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); static void sock_splice_eof(struct file *file); #ifdef CONFIG_PROC_FS static void sock_show_fdinfo(struct seq_file *m, struct file *f) { struct socket *sock = f->private_data; const struct proto_ops *ops = READ_ONCE(sock->ops); if (ops->show_fdinfo) ops->show_fdinfo(m, sock); } #else #define sock_show_fdinfo NULL #endif /* * Socket files have a set of 'special' operations as well as the generic file ones. These don't appear * in the operation structures but are done directly via the socketcall() multiplexor. */ static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, .read_iter = sock_read_iter, .write_iter = sock_write_iter, .poll = sock_poll, .unlocked_ioctl = sock_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = compat_sock_ioctl, #endif .uring_cmd = io_uring_cmd_sock, .mmap = sock_mmap, .release = sock_close, .fasync = sock_fasync, .splice_write = splice_to_socket, .splice_read = sock_splice_read, .splice_eof = sock_splice_eof, .show_fdinfo = sock_show_fdinfo, }; static const char * const pf_family_names[] = { [PF_UNSPEC] = "PF_UNSPEC", [PF_UNIX] = "PF_UNIX/PF_LOCAL", [PF_INET] = "PF_INET", [PF_AX25] = "PF_AX25", [PF_IPX] = "PF_IPX", [PF_APPLETALK] = "PF_APPLETALK", [PF_NETROM] = "PF_NETROM", [PF_BRIDGE] = "PF_BRIDGE", [PF_ATMPVC] = "PF_ATMPVC", [PF_X25] = "PF_X25", [PF_INET6] = "PF_INET6", [PF_ROSE] = "PF_ROSE", [PF_DECnet] = "PF_DECnet", [PF_NETBEUI] = "PF_NETBEUI", [PF_SECURITY] = "PF_SECURITY", [PF_KEY] = "PF_KEY", [PF_NETLINK] = "PF_NETLINK/PF_ROUTE", [PF_PACKET] = "PF_PACKET", [PF_ASH] = "PF_ASH", [PF_ECONET] = "PF_ECONET", [PF_ATMSVC] = "PF_ATMSVC", [PF_RDS] = "PF_RDS", [PF_SNA] = "PF_SNA", [PF_IRDA] = "PF_IRDA", [PF_PPPOX] = "PF_PPPOX", [PF_WANPIPE] = "PF_WANPIPE", [PF_LLC] = "PF_LLC", [PF_IB] = "PF_IB", [PF_MPLS] = "PF_MPLS", [PF_CAN] = "PF_CAN", [PF_TIPC] = "PF_TIPC", [PF_BLUETOOTH] = "PF_BLUETOOTH", [PF_IUCV] = "PF_IUCV", [PF_RXRPC] = "PF_RXRPC", [PF_ISDN] = "PF_ISDN", [PF_PHONET] = "PF_PHONET", [PF_IEEE802154] = "PF_IEEE802154", [PF_CAIF] = "PF_CAIF", [PF_ALG] = "PF_ALG", [PF_NFC] = "PF_NFC", [PF_VSOCK] = "PF_VSOCK", [PF_KCM] = "PF_KCM", [PF_QIPCRTR] = "PF_QIPCRTR", [PF_SMC] = "PF_SMC", [PF_XDP] = "PF_XDP", [PF_MCTP] = "PF_MCTP", }; /* * The protocol list. Each protocol is registered in here. */ static DEFINE_SPINLOCK(net_family_lock); static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly; /* * Support routines. * Move socket addresses back and forth across the kernel/user * divide and look after the messy bits. */ /** * move_addr_to_kernel - copy a socket address into kernel space * @uaddr: Address in user space * @kaddr: Address in kernel space * @ulen: Length in user space * * The address is copied into kernel space. If the provided address is * too long an error code of -EINVAL is returned. If the copy gives * invalid addresses -EFAULT is returned. On a success 0 is returned. */ int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr) { if (ulen < 0 || ulen > sizeof(struct sockaddr_storage)) return -EINVAL; if (ulen == 0) return 0; if (copy_from_user(kaddr, uaddr, ulen)) return -EFAULT; return audit_sockaddr(ulen, kaddr); } /** * move_addr_to_user - copy an address to user space * @kaddr: kernel space address * @klen: length of address in kernel * @uaddr: user space address * @ulen: pointer to user length field * * The value pointed to by ulen on entry is the buffer length available. * This is overwritten with the buffer space used. -EINVAL is returned * if an overlong buffer is specified or a negative buffer size. -EFAULT * is returned if either the buffer or the length field are not * accessible. * After copying the data up to the limit the user specifies, the true * length of the data is written over the length limit the user * specified. Zero is returned for a success. */ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen, void __user *uaddr, int __user *ulen) { int err; int len; BUG_ON(klen > sizeof(struct sockaddr_storage)); err = get_user(len, ulen); if (err) return err; if (len > klen) len = klen; if (len < 0) return -EINVAL; if (len) { if (audit_sockaddr(klen, kaddr)) return -ENOMEM; if (copy_to_user(uaddr, kaddr, len)) return -EFAULT; } /* * "fromlen shall refer to the value before truncation.." * 1003.1g */ return __put_user(klen, ulen); } static struct kmem_cache *sock_inode_cachep __ro_after_init; static struct inode *sock_alloc_inode(struct super_block *sb) { struct socket_alloc *ei; ei = alloc_inode_sb(sb, sock_inode_cachep, GFP_KERNEL); if (!ei) return NULL; init_waitqueue_head(&ei->socket.wq.wait); ei->socket.wq.fasync_list = NULL; ei->socket.wq.flags = 0; ei->socket.state = SS_UNCONNECTED; ei->socket.flags = 0; ei->socket.ops = NULL; ei->socket.sk = NULL; ei->socket.file = NULL; return &ei->vfs_inode; } static void sock_free_inode(struct inode *inode) { struct socket_alloc *ei; ei = container_of(inode, struct socket_alloc, vfs_inode); kmem_cache_free(sock_inode_cachep, ei); } static void init_once(void *foo) { struct socket_alloc *ei = (struct socket_alloc *)foo; inode_init_once(&ei->vfs_inode); } static void init_inodecache(void) { sock_inode_cachep = kmem_cache_create("sock_inode_cache", sizeof(struct socket_alloc), 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT), init_once); BUG_ON(sock_inode_cachep == NULL); } static const struct super_operations sockfs_ops = { .alloc_inode = sock_alloc_inode, .free_inode = sock_free_inode, .statfs = simple_statfs, }; /* * sockfs_dname() is called from d_path(). */ static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(buffer, buflen, "socket:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations sockfs_dentry_operations = { .d_dname = sockfs_dname, }; static int sockfs_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *suffix, void *value, size_t size) { if (value) { if (dentry->d_name.len + 1 > size) return -ERANGE; memcpy(value, dentry->d_name.name, dentry->d_name.len + 1); } return dentry->d_name.len + 1; } #define XATTR_SOCKPROTONAME_SUFFIX "sockprotoname" #define XATTR_NAME_SOCKPROTONAME (XATTR_SYSTEM_PREFIX XATTR_SOCKPROTONAME_SUFFIX) #define XATTR_NAME_SOCKPROTONAME_LEN (sizeof(XATTR_NAME_SOCKPROTONAME)-1) static const struct xattr_handler sockfs_xattr_handler = { .name = XATTR_NAME_SOCKPROTONAME, .get = sockfs_xattr_get, }; static int sockfs_security_xattr_set(const struct xattr_handler *handler, struct mnt_idmap *idmap, struct dentry *dentry, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) { /* Handled by LSM. */ return -EAGAIN; } static const struct xattr_handler sockfs_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, .set = sockfs_security_xattr_set, }; static const struct xattr_handler * const sockfs_xattr_handlers[] = { &sockfs_xattr_handler, &sockfs_security_xattr_handler, NULL }; static int sockfs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, SOCKFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &sockfs_ops; ctx->dops = &sockfs_dentry_operations; ctx->xattr = sockfs_xattr_handlers; return 0; } static struct vfsmount *sock_mnt __read_mostly; static struct file_system_type sock_fs_type = { .name = "sockfs", .init_fs_context = sockfs_init_fs_context, .kill_sb = kill_anon_super, }; /* * Obtains the first available file descriptor and sets it up for use. * * These functions create file structures and maps them to fd space * of the current process. On success it returns file descriptor * and file struct implicitly stored in sock->file. * Note that another thread may close file descriptor before we return * from this function. We use the fact that now we do not refer * to socket after mapping. If one day we will need it, this * function will increment ref. count on file by 1. * * In any case returned fd MAY BE not valid! * This race condition is unavoidable * with shared fd spaces, we cannot solve it inside kernel, * but we take care of internal coherence yet. */ /** * sock_alloc_file - Bind a &socket to a &file * @sock: socket * @flags: file status flags * @dname: protocol name * * Returns the &file bound with @sock, implicitly storing it * in sock->file. If dname is %NULL, sets to "". * * On failure @sock is released, and an ERR pointer is returned. * * This function uses GFP_KERNEL internally. */ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) { struct file *file; if (!dname) dname = sock->sk ? sock->sk->sk_prot_creator->name : ""; file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname, O_RDWR | (flags & O_NONBLOCK), &socket_file_ops); if (IS_ERR(file)) { sock_release(sock); return file; } file->f_mode |= FMODE_NOWAIT; sock->file = file; file->private_data = sock; stream_open(SOCK_INODE(sock), file); /* * Disable permission and pre-content events, but enable legacy * inotify events for legacy users. */ file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM); return file; } EXPORT_SYMBOL(sock_alloc_file); static int sock_map_fd(struct socket *sock, int flags) { struct file *newfile; int fd = get_unused_fd_flags(flags); if (unlikely(fd < 0)) { sock_release(sock); return fd; } newfile = sock_alloc_file(sock, flags, NULL); if (!IS_ERR(newfile)) { fd_install(fd, newfile); return fd; } put_unused_fd(fd); return PTR_ERR(newfile); } /** * sock_from_file - Return the &socket bounded to @file. * @file: file * * On failure returns %NULL. */ struct socket *sock_from_file(struct file *file) { if (likely(file->f_op == &socket_file_ops)) return file->private_data; /* set in sock_alloc_file */ return NULL; } EXPORT_SYMBOL(sock_from_file); /** * sockfd_lookup - Go from a file number to its socket slot * @fd: file handle * @err: pointer to an error code return * * The file handle passed in is locked and the socket it is bound * to is returned. If an error occurs the err pointer is overwritten * with a negative errno code and NULL is returned. The function checks * for both invalid handles and passing a handle which is not a socket. * * On a success the socket object pointer is returned. */ struct socket *sockfd_lookup(int fd, int *err) { struct file *file; struct socket *sock; file = fget(fd); if (!file) { *err = -EBADF; return NULL; } sock = sock_from_file(file); if (!sock) { *err = -ENOTSOCK; fput(file); } return sock; } EXPORT_SYMBOL(sockfd_lookup); static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, size_t size) { ssize_t len; ssize_t used = 0; len = security_inode_listsecurity(d_inode(dentry), buffer, size); if (len < 0) return len; used += len; if (buffer) { if (size < used) return -ERANGE; buffer += len; } len = (XATTR_NAME_SOCKPROTONAME_LEN + 1); used += len; if (buffer) { if (size < used) return -ERANGE; memcpy(buffer, XATTR_NAME_SOCKPROTONAME, len); buffer += len; } return used; } static int sockfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *iattr) { int err = simple_setattr(&nop_mnt_idmap, dentry, iattr); if (!err && (iattr->ia_valid & ATTR_UID)) { struct socket *sock = SOCKET_I(d_inode(dentry)); if (sock->sk) { /* Paired with READ_ONCE() in sk_uid() */ WRITE_ONCE(sock->sk->sk_uid, iattr->ia_uid); } else { err = -ENOENT; } } return err; } static const struct inode_operations sockfs_inode_ops = { .listxattr = sockfs_listxattr, .setattr = sockfs_setattr, }; /** * sock_alloc - allocate a socket * * Allocate a new inode and socket object. The two are bound together * and initialised. The socket is then returned. If we are out of inodes * NULL is returned. This functions uses GFP_KERNEL internally. */ struct socket *sock_alloc(void) { struct inode *inode; struct socket *sock; inode = new_inode_pseudo(sock_mnt->mnt_sb); if (!inode) return NULL; sock = SOCKET_I(inode); inode->i_ino = get_next_ino(); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_op = &sockfs_inode_ops; return sock; } EXPORT_SYMBOL(sock_alloc); static void __sock_release(struct socket *sock, struct inode *inode) { const struct proto_ops *ops = READ_ONCE(sock->ops); if (ops) { struct module *owner = ops->owner; if (inode) inode_lock(inode); ops->release(sock); sock->sk = NULL; if (inode) inode_unlock(inode); sock->ops = NULL; module_put(owner); } if (sock->wq.fasync_list) pr_err("%s: fasync list not empty!\n", __func__); if (!sock->file) { iput(SOCK_INODE(sock)); return; } sock->file = NULL; } /** * sock_release - close a socket * @sock: socket to close * * The socket is released from the protocol stack if it has a release * callback, and the inode is then released if the socket is bound to * an inode not a file. */ void sock_release(struct socket *sock) { __sock_release(sock, NULL); } EXPORT_SYMBOL(sock_release); void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags) { u8 flags = *tx_flags; if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) flags |= SKBTX_HW_TSTAMP_NOBPF; if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE) flags |= SKBTX_SW_TSTAMP; if (tsflags & SOF_TIMESTAMPING_TX_SCHED) flags |= SKBTX_SCHED_TSTAMP; if (tsflags & SOF_TIMESTAMPING_TX_COMPLETION) flags |= SKBTX_COMPLETION_TSTAMP; *tx_flags = flags; } EXPORT_SYMBOL(__sock_tx_timestamp); INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *, size_t)); INDIRECT_CALLABLE_DECLARE(int inet6_sendmsg(struct socket *, struct msghdr *, size_t)); static noinline void call_trace_sock_send_length(struct sock *sk, int ret, int flags) { trace_sock_send_length(sk, ret, 0); } static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->sendmsg, inet6_sendmsg, inet_sendmsg, sock, msg, msg_data_left(msg)); BUG_ON(ret == -EIOCBQUEUED); if (trace_sock_send_length_enabled()) call_trace_sock_send_length(sock->sk, ret, 0); return ret; } static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) { int err = security_socket_sendmsg(sock, msg, msg_data_left(msg)); return err ?: sock_sendmsg_nosec(sock, msg); } /** * sock_sendmsg - send a message through @sock * @sock: socket * @msg: message to send * * Sends @msg through @sock, passing through LSM. * Returns the number of bytes sent, or an error code. */ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; struct sockaddr_storage address; int save_len = msg->msg_namelen; int ret; if (msg->msg_name) { memcpy(&address, msg->msg_name, msg->msg_namelen); msg->msg_name = &address; } ret = __sock_sendmsg(sock, msg); msg->msg_name = save_addr; msg->msg_namelen = save_len; return ret; } EXPORT_SYMBOL(sock_sendmsg); /** * kernel_sendmsg - send a message through @sock (kernel-space) * @sock: socket * @msg: message header * @vec: kernel vec * @num: vec array length * @size: total message data size * * Builds the message data with @vec and sends it through @sock. * Returns the number of bytes sent, or an error code. */ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { iov_iter_kvec(&msg->msg_iter, ITER_SOURCE, vec, num, size); return sock_sendmsg(sock, msg); } EXPORT_SYMBOL(kernel_sendmsg); static bool skb_is_err_queue(const struct sk_buff *skb) { /* pkt_type of skbs enqueued on the error queue are set to * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do * in recvmsg, since skbs received on a local socket will never * have a pkt_type of PACKET_OUTGOING. */ return skb->pkt_type == PACKET_OUTGOING; } /* On transmit, software and hardware timestamps are returned independently. * As the two skb clones share the hardware timestamp, which may be updated * before the software timestamp is received, a hardware TX timestamp may be * returned only if there is no software TX timestamp. Ignore false software * timestamps, which may be made in the __sock_recv_timestamp() call when the * option SO_TIMESTAMP_OLD(NS) is enabled on the socket, even when the skb has a * hardware timestamp. */ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) { return skb->tstamp && !false_tstamp && skb_is_err_queue(skb); } static ktime_t get_timestamp(struct sock *sk, struct sk_buff *skb, int *if_index) { bool cycles = READ_ONCE(sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); struct net_device *orig_dev; ktime_t hwtstamp; rcu_read_lock(); orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); if (orig_dev) { *if_index = orig_dev->ifindex; hwtstamp = netdev_get_tstamp(orig_dev, shhwtstamps, cycles); } else { hwtstamp = shhwtstamps->hwtstamp; } rcu_read_unlock(); return hwtstamp; } static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb, int if_index) { struct scm_ts_pktinfo ts_pktinfo; struct net_device *orig_dev; if (!skb_mac_header_was_set(skb)) return; memset(&ts_pktinfo, 0, sizeof(ts_pktinfo)); if (!if_index) { rcu_read_lock(); orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); if (orig_dev) if_index = orig_dev->ifindex; rcu_read_unlock(); } ts_pktinfo.if_index = if_index; ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb); put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO, sizeof(ts_pktinfo), &ts_pktinfo); } bool skb_has_tx_timestamp(struct sk_buff *skb, const struct sock *sk) { const struct sock_exterr_skb *serr = SKB_EXT_ERR(skb); u32 tsflags = READ_ONCE(sk->sk_tsflags); if (serr->ee.ee_errno != ENOMSG || serr->ee.ee_origin != SO_EE_ORIGIN_TIMESTAMPING) return false; /* software time stamp available and wanted */ if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && skb->tstamp) return true; /* hardware time stamps available and wanted */ return (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && skb_hwtstamps(skb)->hwtstamp; } int skb_get_tx_timestamp(struct sk_buff *skb, struct sock *sk, struct timespec64 *ts) { u32 tsflags = READ_ONCE(sk->sk_tsflags); ktime_t hwtstamp; int if_index = 0; if ((tsflags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb->tstamp, ts)) return SOF_TIMESTAMPING_TX_SOFTWARE; if (!(tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) || skb_is_swtx_tstamp(skb, false)) return -ENOENT; if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) hwtstamp = get_timestamp(sk, skb, &if_index); else hwtstamp = skb_hwtstamps(skb)->hwtstamp; if (tsflags & SOF_TIMESTAMPING_BIND_PHC) hwtstamp = ptp_convert_timestamp(&hwtstamp, READ_ONCE(sk->sk_bind_phc)); if (!ktime_to_timespec64_cond(hwtstamp, ts)) return -ENOENT; return SOF_TIMESTAMPING_TX_HARDWARE; } /* * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP) */ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); struct scm_timestamping_internal tss; int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); int if_index; ktime_t hwtstamp; u32 tsflags; /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ if (need_software_tstamp && skb->tstamp == 0) { __net_timestamp(skb); false_tstamp = 1; } if (need_software_tstamp) { if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { struct __kernel_sock_timeval tv; skb_get_new_timestamp(skb, &tv); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(tv), &tv); } else { struct __kernel_old_timeval tv; skb_get_timestamp(skb, &tv); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } } else { if (new_tstamp) { struct __kernel_timespec ts; skb_get_new_timestampns(skb, &ts); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(ts), &ts); } else { struct __kernel_old_timespec ts; skb_get_timestampns(skb, &ts); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts), &ts); } } } memset(&tss, 0, sizeof(tss)); tsflags = READ_ONCE(sk->sk_tsflags); if ((tsflags & SOF_TIMESTAMPING_SOFTWARE && (tsflags & SOF_TIMESTAMPING_RX_SOFTWARE || skb_is_err_queue(skb) || !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) && ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && (tsflags & SOF_TIMESTAMPING_RAW_HARDWARE && (tsflags & SOF_TIMESTAMPING_RX_HARDWARE || skb_is_err_queue(skb) || !(tsflags & SOF_TIMESTAMPING_OPT_RX_FILTER))) && !skb_is_swtx_tstamp(skb, false_tstamp)) { if_index = 0; if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NETDEV) hwtstamp = get_timestamp(sk, skb, &if_index); else hwtstamp = shhwtstamps->hwtstamp; if (tsflags & SOF_TIMESTAMPING_BIND_PHC) hwtstamp = ptp_convert_timestamp(&hwtstamp, READ_ONCE(sk->sk_bind_phc)); if (ktime_to_timespec64_cond(hwtstamp, tss.ts + 2)) { empty = 0; if ((tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && !skb_is_err_queue(skb)) put_ts_pktinfo(msg, skb, if_index); } } if (!empty) { if (sock_flag(sk, SOCK_TSTAMP_NEW)) put_cmsg_scm_timestamping64(msg, &tss); else put_cmsg_scm_timestamping(msg, &tss); if (skb_is_err_queue(skb) && skb->len && SKB_EXT_ERR(skb)->opt_stats) put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS, skb->len, skb->data); } } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); #ifdef CONFIG_WIRELESS void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int ack; if (!sock_flag(sk, SOCK_WIFI_STATUS)) return; if (!skb->wifi_acked_valid) return; ack = skb->wifi_acked; put_cmsg(msg, SOL_SOCKET, SCM_WIFI_STATUS, sizeof(ack), &ack); } EXPORT_SYMBOL_GPL(__sock_recv_wifi_status); #endif static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && SOCK_SKB_CB(skb)->dropcount) put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL, sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount); } static void sock_recv_mark(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { if (sock_flag(sk, SOCK_RCVMARK) && skb) { /* We must use a bounce buffer for CONFIG_HARDENED_USERCOPY=y */ __u32 mark = skb->mark; put_cmsg(msg, SOL_SOCKET, SO_MARK, sizeof(__u32), &mark); } } static void sock_recv_priority(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { if (sock_flag(sk, SOCK_RCVPRIORITY) && skb) { __u32 priority = skb->priority; put_cmsg(msg, SOL_SOCKET, SO_PRIORITY, sizeof(__u32), &priority); } } void __sock_recv_cmsgs(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { sock_recv_timestamp(msg, sk, skb); sock_recv_drops(msg, sk, skb); sock_recv_mark(msg, sk, skb); sock_recv_priority(msg, sk, skb); } EXPORT_SYMBOL_GPL(__sock_recv_cmsgs); INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *, size_t, int)); INDIRECT_CALLABLE_DECLARE(int inet6_recvmsg(struct socket *, struct msghdr *, size_t, int)); static noinline void call_trace_sock_recv_length(struct sock *sk, int ret, int flags) { trace_sock_recv_length(sk, ret, flags); } static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, int flags) { int ret = INDIRECT_CALL_INET(READ_ONCE(sock->ops)->recvmsg, inet6_recvmsg, inet_recvmsg, sock, msg, msg_data_left(msg), flags); if (trace_sock_recv_length_enabled()) call_trace_sock_recv_length(sock->sk, ret, flags); return ret; } /** * sock_recvmsg - receive a message from @sock * @sock: socket * @msg: message to receive * @flags: message flags * * Receives @msg from @sock, passing through LSM. Returns the total number * of bytes received, or an error. */ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags) { int err = security_socket_recvmsg(sock, msg, msg_data_left(msg), flags); return err ?: sock_recvmsg_nosec(sock, msg, flags); } EXPORT_SYMBOL(sock_recvmsg); /** * kernel_recvmsg - Receive a message from a socket (kernel space) * @sock: The socket to receive the message from * @msg: Received message * @vec: Input s/g array for message data * @num: Size of input s/g array * @size: Number of bytes to read * @flags: Message flags (MSG_DONTWAIT, etc...) * * On return the msg structure contains the scatter/gather array passed in the * vec argument. The array is modified so that it consists of the unfilled * portion of the original array. * * The returned value is the total number of bytes received, or an error. */ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { msg->msg_control_is_user = false; iov_iter_kvec(&msg->msg_iter, ITER_DEST, vec, num, size); return sock_recvmsg(sock, msg, flags); } EXPORT_SYMBOL(kernel_recvmsg); static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct socket *sock = file->private_data; const struct proto_ops *ops; ops = READ_ONCE(sock->ops); if (unlikely(!ops->splice_read)) return copy_splice_read(file, ppos, pipe, len, flags); return ops->splice_read(sock, ppos, pipe, len, flags); } static void sock_splice_eof(struct file *file) { struct socket *sock = file->private_data; const struct proto_ops *ops; ops = READ_ONCE(sock->ops); if (ops->splice_eof) ops->splice_eof(sock); } static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; struct msghdr msg = {.msg_iter = *to, .msg_iocb = iocb}; ssize_t res; if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (iocb->ki_pos != 0) return -ESPIPE; if (!iov_iter_count(to)) /* Match SYS5 behaviour */ return 0; res = sock_recvmsg(sock, &msg, msg.msg_flags); *to = msg.msg_iter; return res; } static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; struct msghdr msg = {.msg_iter = *from, .msg_iocb = iocb}; ssize_t res; if (iocb->ki_pos != 0) return -ESPIPE; if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } /* * Atomic setting of ioctl hooks to avoid race * with module unload. */ static DEFINE_MUTEX(br_ioctl_mutex); static int (*br_ioctl_hook)(struct net *net, unsigned int cmd, void __user *uarg); void brioctl_set(int (*hook)(struct net *net, unsigned int cmd, void __user *uarg)) { mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; mutex_unlock(&br_ioctl_mutex); } EXPORT_SYMBOL(brioctl_set); int br_ioctl_call(struct net *net, unsigned int cmd, void __user *uarg) { int err = -ENOPKG; if (!br_ioctl_hook) request_module("bridge"); mutex_lock(&br_ioctl_mutex); if (br_ioctl_hook) err = br_ioctl_hook(net, cmd, uarg); mutex_unlock(&br_ioctl_mutex); return err; } static DEFINE_MUTEX(vlan_ioctl_mutex); static int (*vlan_ioctl_hook) (struct net *, void __user *arg); void vlan_ioctl_set(int (*hook) (struct net *, void __user *)) { mutex_lock(&vlan_ioctl_mutex); vlan_ioctl_hook = hook; mutex_unlock(&vlan_ioctl_mutex); } EXPORT_SYMBOL(vlan_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, unsigned int cmd, unsigned long arg) { const struct proto_ops *ops = READ_ONCE(sock->ops); struct ifreq ifr; bool need_copyout; int err; void __user *argp = (void __user *)arg; void __user *data; err = ops->ioctl(sock, cmd, arg); /* * If this ioctl is unknown try to hand it down * to the NIC driver. */ if (err != -ENOIOCTLCMD) return err; if (!is_socket_ioctl_cmd(cmd)) return -ENOTTY; if (get_user_ifreq(&ifr, &data, argp)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); if (!err && need_copyout) if (put_user_ifreq(&ifr, argp)) return -EFAULT; return err; } /* * With an ioctl, arg may well be a user mode pointer, but we don't know * what to do with it - that's up to the protocol still. */ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { const struct proto_ops *ops; struct socket *sock; struct sock *sk; void __user *argp = (void __user *)arg; int pid, err; struct net *net; sock = file->private_data; ops = READ_ONCE(sock->ops); sk = sock->sk; net = sock_net(sk); if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) { struct ifreq ifr; void __user *data; bool need_copyout; if (get_user_ifreq(&ifr, &data, argp)) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, data, &need_copyout); if (!err && need_copyout) if (put_user_ifreq(&ifr, argp)) return -EFAULT; } else #ifdef CONFIG_WEXT_CORE if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { err = wext_handle_ioctl(net, cmd, argp); } else #endif switch (cmd) { case FIOSETOWN: case SIOCSPGRP: err = -EFAULT; if (get_user(pid, (int __user *)argp)) break; err = f_setown(sock->file, pid, 1); break; case FIOGETOWN: case SIOCGPGRP: err = put_user(f_getown(sock->file), (int __user *)argp); break; case SIOCGIFBR: case SIOCSIFBR: case SIOCBRADDBR: case SIOCBRDELBR: case SIOCBRADDIF: case SIOCBRDELIF: err = br_ioctl_call(net, cmd, argp); break; case SIOCGIFVLAN: case SIOCSIFVLAN: err = -ENOPKG; if (!vlan_ioctl_hook) request_module("8021q"); mutex_lock(&vlan_ioctl_mutex); if (vlan_ioctl_hook) err = vlan_ioctl_hook(net, argp); mutex_unlock(&vlan_ioctl_mutex); break; case SIOCGSKNS: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = open_related_ns(&net->ns, get_net_ns); break; case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: if (!ops->gettstamp) { err = -ENOIOCTLCMD; break; } err = ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !IS_ENABLED(CONFIG_64BIT)); break; case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: if (!ops->gettstamp) { err = -ENOIOCTLCMD; break; } err = ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_NEW, false); break; case SIOCGIFCONF: err = dev_ifconf(net, argp); break; default: err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; } /** * sock_create_lite - creates a socket * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * Creates a new socket and assigns it to @res, passing through LSM. * The new socket initialization is not complete, see kernel_accept(). * Returns 0 or an error. On failure @res is set to %NULL. * This function internally uses GFP_KERNEL. */ int sock_create_lite(int family, int type, int protocol, struct socket **res) { int err; struct socket *sock = NULL; err = security_socket_create(family, type, protocol, 1); if (err) goto out; sock = sock_alloc(); if (!sock) { err = -ENOMEM; goto out; } sock->type = type; err = security_socket_post_create(sock, family, type, protocol, 1); if (err) goto out_release; out: *res = sock; return err; out_release: sock_release(sock); sock = NULL; goto out; } EXPORT_SYMBOL(sock_create_lite); /* No kernel lock held - perfect */ static __poll_t sock_poll(struct file *file, poll_table *wait) { struct socket *sock = file->private_data; const struct proto_ops *ops = READ_ONCE(sock->ops); __poll_t events = poll_requested_events(wait), flag = 0; if (!ops->poll) return 0; if (sk_can_busy_loop(sock->sk)) { /* poll once if requested by the syscall */ if (events & POLL_BUSY_LOOP) sk_busy_loop(sock->sk, 1); /* if this socket can poll_ll, tell the system call */ flag = POLL_BUSY_LOOP; } return ops->poll(file, sock, wait) | flag; } static int sock_mmap(struct file *file, struct vm_area_struct *vma) { struct socket *sock = file->private_data; return READ_ONCE(sock->ops)->mmap(file, sock, vma); } static int sock_close(struct inode *inode, struct file *filp) { __sock_release(SOCKET_I(inode), inode); return 0; } /* * Update the socket async list * * Fasync_list locking strategy. * * 1. fasync_list is modified only under process context socket lock * i.e. under semaphore. * 2. fasync_list is used under read_lock(&sk->sk_callback_lock) * or under socket lock */ static int sock_fasync(int fd, struct file *filp, int on) { struct socket *sock = filp->private_data; struct sock *sk = sock->sk; struct socket_wq *wq = &sock->wq; if (sk == NULL) return -EINVAL; lock_sock(sk); fasync_helper(fd, filp, on, &wq->fasync_list); if (!wq->fasync_list) sock_reset_flag(sk, SOCK_FASYNC); else sock_set_flag(sk, SOCK_FASYNC); release_sock(sk); return 0; } /* This function may be called only under rcu_lock */ int sock_wake_async(struct socket_wq *wq, int how, int band) { if (!wq || !wq->fasync_list) return -1; switch (how) { case SOCK_WAKE_WAITD: if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags)) break; goto call_kill; case SOCK_WAKE_SPACE: if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags)) break; fallthrough; case SOCK_WAKE_IO: call_kill: kill_fasync(&wq->fasync_list, SIGIO, band); break; case SOCK_WAKE_URG: kill_fasync(&wq->fasync_list, SIGURG, band); } return 0; } EXPORT_SYMBOL(sock_wake_async); /** * __sock_create - creates a socket * @net: net namespace * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * @kern: boolean for kernel space sockets * * Creates a new socket and assigns it to @res, passing through LSM. * Returns 0 or an error. On failure @res is set to %NULL. @kern must * be set to true if the socket resides in kernel space. * This function internally uses GFP_KERNEL. */ int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { int err; struct socket *sock; const struct net_proto_family *pf; /* * Check protocol is in range */ if (family < 0 || family >= NPROTO) return -EAFNOSUPPORT; if (type < 0 || type >= SOCK_MAX) return -EINVAL; /* Compatibility. This uglymoron is moved from INET layer to here to avoid deadlock in module load. */ if (family == PF_INET && type == SOCK_PACKET) { pr_info_once("%s uses obsolete (PF_INET,SOCK_PACKET)\n", current->comm); family = PF_PACKET; } err = security_socket_create(family, type, protocol, kern); if (err) return err; /* * Allocate the socket and allow the family to set things up. if * the protocol is 0, the family is instructed to select an appropriate * default. */ sock = sock_alloc(); if (!sock) { net_warn_ratelimited("socket: no more sockets\n"); return -ENFILE; /* Not exactly a match, but its the closest posix thing */ } sock->type = type; #ifdef CONFIG_MODULES /* Attempt to load a protocol module if the find failed. * * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user * requested real, full-featured networking support upon configuration. * Otherwise module support will break! */ if (rcu_access_pointer(net_families[family]) == NULL) request_module("net-pf-%d", family); #endif rcu_read_lock(); pf = rcu_dereference(net_families[family]); err = -EAFNOSUPPORT; if (!pf) goto out_release; /* * We will call the ->create function, that possibly is in a loadable * module, so we have to bump that loadable module refcnt first. */ if (!try_module_get(pf->owner)) goto out_release; /* Now protected by module ref count */ rcu_read_unlock(); err = pf->create(net, sock, protocol, kern); if (err < 0) { /* ->create should release the allocated sock->sk object on error * and make sure sock->sk is set to NULL to avoid use-after-free */ DEBUG_NET_WARN_ONCE(sock->sk, "%ps must clear sock->sk on failure, family: %d, type: %d, protocol: %d\n", pf->create, family, type, protocol); goto out_module_put; } /* * Now to bump the refcnt of the [loadable] module that owns this * socket at sock_release time we decrement its refcnt. */ if (!try_module_get(sock->ops->owner)) goto out_module_busy; /* * Now that we're done with the ->create function, the [loadable] * module can have its refcnt decremented */ module_put(pf->owner); err = security_socket_post_create(sock, family, type, protocol, kern); if (err) goto out_sock_release; *res = sock; return 0; out_module_busy: err = -EAFNOSUPPORT; out_module_put: sock->ops = NULL; module_put(pf->owner); out_sock_release: sock_release(sock); return err; out_release: rcu_read_unlock(); goto out_sock_release; } EXPORT_SYMBOL(__sock_create); /** * sock_create - creates a socket * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * A wrapper around __sock_create(). * Returns 0 or an error. This function internally uses GFP_KERNEL. */ int sock_create(int family, int type, int protocol, struct socket **res) { return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0); } EXPORT_SYMBOL(sock_create); /** * sock_create_kern - creates a socket (kernel space) * @net: net namespace * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * A wrapper around __sock_create(). * Returns 0 or an error. This function internally uses GFP_KERNEL. */ int sock_create_kern(struct net *net, int family, int type, int protocol, struct socket **res) { return __sock_create(net, family, type, protocol, res, 1); } EXPORT_SYMBOL(sock_create_kern); static struct socket *__sys_socket_create(int family, int type, int protocol) { struct socket *sock; int retval; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); if ((type & ~SOCK_TYPE_MASK) & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return ERR_PTR(-EINVAL); type &= SOCK_TYPE_MASK; retval = sock_create(family, type, protocol, &sock); if (retval < 0) return ERR_PTR(retval); return sock; } struct file *__sys_socket_file(int family, int type, int protocol) { struct socket *sock; int flags; sock = __sys_socket_create(family, type, protocol); if (IS_ERR(sock)) return ERR_CAST(sock); flags = type & ~SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_alloc_file(sock, flags, NULL); } /* A hook for bpf progs to attach to and update socket protocol. * * A static noinline declaration here could cause the compiler to * optimize away the function. A global noinline declaration will * keep the definition, but may optimize away the callsite. * Therefore, __weak is needed to ensure that the call is still * emitted, by telling the compiler that we don't know what the * function might eventually be. */ __bpf_hook_start(); __weak noinline int update_socket_protocol(int family, int type, int protocol) { return protocol; } __bpf_hook_end(); int __sys_socket(int family, int type, int protocol) { struct socket *sock; int flags; sock = __sys_socket_create(family, type, update_socket_protocol(family, type, protocol)); if (IS_ERR(sock)) return PTR_ERR(sock); flags = type & ~SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); } SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) { return __sys_socket(family, type, protocol); } /* * Create a pair of connected sockets. */ int __sys_socketpair(int family, int type, int protocol, int __user *usockvec) { struct socket *sock1, *sock2; int fd1, fd2, err; struct file *newfile1, *newfile2; int flags; flags = type & ~SOCK_TYPE_MASK; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; type &= SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; /* * reserve descriptors and make sure we won't fail * to return them to userland. */ fd1 = get_unused_fd_flags(flags); if (unlikely(fd1 < 0)) return fd1; fd2 = get_unused_fd_flags(flags); if (unlikely(fd2 < 0)) { put_unused_fd(fd1); return fd2; } err = put_user(fd1, &usockvec[0]); if (err) goto out; err = put_user(fd2, &usockvec[1]); if (err) goto out; /* * Obtain the first socket and check if the underlying protocol * supports the socketpair call. */ err = sock_create(family, type, protocol, &sock1); if (unlikely(err < 0)) goto out; err = sock_create(family, type, protocol, &sock2); if (unlikely(err < 0)) { sock_release(sock1); goto out; } err = security_socket_socketpair(sock1, sock2); if (unlikely(err)) { sock_release(sock2); sock_release(sock1); goto out; } err = READ_ONCE(sock1->ops)->socketpair(sock1, sock2); if (unlikely(err < 0)) { sock_release(sock2); sock_release(sock1); goto out; } newfile1 = sock_alloc_file(sock1, flags, NULL); if (IS_ERR(newfile1)) { err = PTR_ERR(newfile1); sock_release(sock2); goto out; } newfile2 = sock_alloc_file(sock2, flags, NULL); if (IS_ERR(newfile2)) { err = PTR_ERR(newfile2); fput(newfile1); goto out; } audit_fd_pair(fd1, fd2); fd_install(fd1, newfile1); fd_install(fd2, newfile2); return 0; out: put_unused_fd(fd2); put_unused_fd(fd1); return err; } SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, int __user *, usockvec) { return __sys_socketpair(family, type, protocol, usockvec); } int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, int addrlen) { int err; err = security_socket_bind(sock, (struct sockaddr *)address, addrlen); if (!err) err = READ_ONCE(sock->ops)->bind(sock, (struct sockaddr *)address, addrlen); return err; } /* * Bind a name to a socket. Nothing much to do here since it's * the protocol's responsibility to handle the local address. * * We move the socket address to kernel space before we call * the protocol layer (having also checked the address is ok). */ int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) { struct socket *sock; struct sockaddr_storage address; CLASS(fd, f)(fd); int err; if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; err = move_addr_to_kernel(umyaddr, addrlen, &address); if (unlikely(err)) return err; return __sys_bind_socket(sock, &address, addrlen); } SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) { return __sys_bind(fd, umyaddr, addrlen); } /* * Perform a listen. Basically, we allow the protocol to do anything * necessary for a listen, and if that works, we mark the socket as * ready for listening. */ int __sys_listen_socket(struct socket *sock, int backlog) { int somaxconn, err; somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); if ((unsigned int)backlog > somaxconn) backlog = somaxconn; err = security_socket_listen(sock, backlog); if (!err) err = READ_ONCE(sock->ops)->listen(sock, backlog); return err; } int __sys_listen(int fd, int backlog) { CLASS(fd, f)(fd); struct socket *sock; if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return __sys_listen_socket(sock, backlog); } SYSCALL_DEFINE2(listen, int, fd, int, backlog) { return __sys_listen(fd, backlog); } struct file *do_accept(struct file *file, struct proto_accept_arg *arg, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; int err, len; struct sockaddr_storage address; const struct proto_ops *ops; sock = sock_from_file(file); if (!sock) return ERR_PTR(-ENOTSOCK); newsock = sock_alloc(); if (!newsock) return ERR_PTR(-ENFILE); ops = READ_ONCE(sock->ops); newsock->type = sock->type; newsock->ops = ops; /* * We don't need try_module_get here, as the listening socket (sock) * has the protocol module (sock->ops->owner) held. */ __module_get(ops->owner); newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); if (IS_ERR(newfile)) return newfile; err = security_socket_accept(sock, newsock); if (err) goto out_fd; arg->flags |= sock->file->f_flags; err = ops->accept(sock, newsock, arg); if (err < 0) goto out_fd; if (upeer_sockaddr) { len = ops->getname(newsock, (struct sockaddr *)&address, 2); if (len < 0) { err = -ECONNABORTED; goto out_fd; } err = move_addr_to_user(&address, len, upeer_sockaddr, upeer_addrlen); if (err < 0) goto out_fd; } /* File flags are not inherited via accept() unlike another OSes. */ return newfile; out_fd: fput(newfile); return ERR_PTR(err); } static int __sys_accept4_file(struct file *file, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { struct proto_accept_arg arg = { }; struct file *newfile; int newfd; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; newfd = get_unused_fd_flags(flags); if (unlikely(newfd < 0)) return newfd; newfile = do_accept(file, &arg, upeer_sockaddr, upeer_addrlen, flags); if (IS_ERR(newfile)) { put_unused_fd(newfd); return PTR_ERR(newfile); } fd_install(newfd, newfile); return newfd; } /* * For accept, we attempt to create a new socket, set up the link * with the client, wake up the client, then return the new * connected fd. We collect the address of the connector in kernel * space and move it to user at the very end. This is unclean because * we open the socket then return an error. * * 1003.1g adds the ability to recvmsg() to query connection pending * status to recvmsg. We need to add that support in a way thats * clean when we restructure accept also. */ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return __sys_accept4_file(fd_file(f), upeer_sockaddr, upeer_addrlen, flags); } SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen, int, flags) { return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, flags); } SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen) { return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0); } /* * Attempt to connect to a socket with the server address. The address * is in user space so we verify it is OK and move it to kernel space. * * For 1003.1g we need to add clean support for a bind to AF_UNSPEC to * break bindings * * NOTE: 1003.1g draft 6.3 is broken with respect to AX.25/NetROM and * other SEQPACKET protocols that take time to connect() as it doesn't * include the -EINPROGRESS status for such sockets. */ int __sys_connect_file(struct file *file, struct sockaddr_storage *address, int addrlen, int file_flags) { struct socket *sock; int err; sock = sock_from_file(file); if (!sock) { err = -ENOTSOCK; goto out; } err = security_socket_connect(sock, (struct sockaddr *)address, addrlen); if (err) goto out; err = READ_ONCE(sock->ops)->connect(sock, (struct sockaddr *)address, addrlen, sock->file->f_flags | file_flags); out: return err; } int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) { struct sockaddr_storage address; CLASS(fd, f)(fd); int ret; if (fd_empty(f)) return -EBADF; ret = move_addr_to_kernel(uservaddr, addrlen, &address); if (ret) return ret; return __sys_connect_file(fd_file(f), &address, addrlen, 0); } SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, int, addrlen) { return __sys_connect(fd, uservaddr, addrlen); } /* * Get the local address ('name') of a socket object. Move the obtained * name to user space. */ int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len) { struct socket *sock; struct sockaddr_storage address; CLASS(fd, f)(fd); int err; if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; err = security_socket_getsockname(sock); if (err) return err; err = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 0); if (err < 0) return err; /* "err" is actually length in this case */ return move_addr_to_user(&address, err, usockaddr, usockaddr_len); } SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len) { return __sys_getsockname(fd, usockaddr, usockaddr_len); } /* * Get the remote address ('name') of a socket object. Move the obtained * name to user space. */ int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len) { struct socket *sock; struct sockaddr_storage address; CLASS(fd, f)(fd); int err; if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; err = security_socket_getpeername(sock); if (err) return err; err = READ_ONCE(sock->ops)->getname(sock, (struct sockaddr *)&address, 1); if (err < 0) return err; /* "err" is actually length in this case */ return move_addr_to_user(&address, err, usockaddr, usockaddr_len); } SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len) { return __sys_getpeername(fd, usockaddr, usockaddr_len); } /* * Send a datagram to a given address. We move the address into kernel * space and check the user space data area is readable before invoking * the protocol. */ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len) { struct socket *sock; struct sockaddr_storage address; int err; struct msghdr msg; err = import_ubuf(ITER_SOURCE, buff, len, &msg.msg_iter); if (unlikely(err)) return err; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; msg.msg_name = NULL; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; msg.msg_ubuf = NULL; if (addr) { err = move_addr_to_kernel(addr, addr_len, &address); if (err < 0) return err; msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = addr_len; } flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; return __sock_sendmsg(sock, &msg); } SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len) { return __sys_sendto(fd, buff, len, flags, addr, addr_len); } /* * Send a datagram down a socket. */ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, unsigned int, flags) { return __sys_sendto(fd, buff, len, flags, NULL, 0); } /* * Receive a frame from the socket and optionally record the address of the * sender. We verify the buffers are writable and if needed move the * sender address from kernel to user space. */ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, struct sockaddr __user *addr, int __user *addr_len) { struct sockaddr_storage address; struct msghdr msg = { /* Save some cycles and don't copy the address if not needed */ .msg_name = addr ? (struct sockaddr *)&address : NULL, }; struct socket *sock; int err, err2; err = import_ubuf(ITER_DEST, ubuf, size, &msg.msg_iter); if (unlikely(err)) return err; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, flags); if (err >= 0 && addr != NULL) { err2 = move_addr_to_user(&address, msg.msg_namelen, addr, addr_len); if (err2 < 0) err = err2; } return err; } SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, unsigned int, flags, struct sockaddr __user *, addr, int __user *, addr_len) { return __sys_recvfrom(fd, ubuf, size, flags, addr, addr_len); } /* * Receive a datagram from a socket. */ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, unsigned int, flags) { return __sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } static bool sock_use_custom_sol_socket(const struct socket *sock) { return test_bit(SOCK_CUSTOM_SOCKOPT, &sock->flags); } int do_sock_setsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, int optlen) { const struct proto_ops *ops; char *kernel_optval = NULL; int err; if (optlen < 0) return -EINVAL; err = security_socket_setsockopt(sock, level, optname); if (err) goto out_put; if (!compat) err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname, optval, &optlen, &kernel_optval); if (err < 0) goto out_put; if (err > 0) { err = 0; goto out_put; } if (kernel_optval) optval = KERNEL_SOCKPTR(kernel_optval); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET && !sock_use_custom_sol_socket(sock)) err = sock_setsockopt(sock, level, optname, optval, optlen); else if (unlikely(!ops->setsockopt)) err = -EOPNOTSUPP; else err = ops->setsockopt(sock, level, optname, optval, optlen); kfree(kernel_optval); out_put: return err; } EXPORT_SYMBOL(do_sock_setsockopt); /* Set a socket option. Because we don't know the option lengths we have * to pass the user mode parameter for the protocols to sort out. */ int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval, int optlen) { sockptr_t optval = USER_SOCKPTR(user_optval); bool compat = in_compat_syscall(); struct socket *sock; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return do_sock_setsockopt(sock, compat, level, optname, optval, optlen); } SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, char __user *, optval, int, optlen) { return __sys_setsockopt(fd, level, optname, optval, optlen); } INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level, int optname)); int do_sock_getsockopt(struct socket *sock, bool compat, int level, int optname, sockptr_t optval, sockptr_t optlen) { int max_optlen __maybe_unused = 0; const struct proto_ops *ops; int err; err = security_socket_getsockopt(sock, level, optname); if (err) return err; if (!compat) copy_from_sockptr(&max_optlen, optlen, sizeof(int)); ops = READ_ONCE(sock->ops); if (level == SOL_SOCKET) { err = sk_getsockopt(sock->sk, level, optname, optval, optlen); } else if (unlikely(!ops->getsockopt)) { err = -EOPNOTSUPP; } else { if (WARN_ONCE(optval.is_kernel || optlen.is_kernel, "Invalid argument type")) return -EOPNOTSUPP; err = ops->getsockopt(sock, level, optname, optval.user, optlen.user); } if (!compat) err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, optval, optlen, max_optlen, err); return err; } EXPORT_SYMBOL(do_sock_getsockopt); /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. */ int __sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) { struct socket *sock; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return do_sock_getsockopt(sock, in_compat_syscall(), level, optname, USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); } SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, char __user *, optval, int __user *, optlen) { return __sys_getsockopt(fd, level, optname, optval, optlen); } /* * Shutdown a socket. */ int __sys_shutdown_sock(struct socket *sock, int how) { int err; err = security_socket_shutdown(sock, how); if (!err) err = READ_ONCE(sock->ops)->shutdown(sock, how); return err; } int __sys_shutdown(int fd, int how) { struct socket *sock; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return __sys_shutdown_sock(sock, how); } SYSCALL_DEFINE2(shutdown, int, fd, int, how) { return __sys_shutdown(fd, how); } /* A couple of helpful macros for getting the address of the 32/64 bit * fields which are the same type (int / unsigned) on our platforms. */ #define COMPAT_MSG(msg, member) ((MSG_CMSG_COMPAT & flags) ? &msg##_compat->member : &msg->member) #define COMPAT_NAMELEN(msg) COMPAT_MSG(msg, msg_namelen) #define COMPAT_FLAGS(msg) COMPAT_MSG(msg, msg_flags) struct used_address { struct sockaddr_storage name; unsigned int name_len; }; int __copy_msghdr(struct msghdr *kmsg, struct user_msghdr *msg, struct sockaddr __user **save_addr) { ssize_t err; kmsg->msg_control_is_user = true; kmsg->msg_get_inq = 0; kmsg->msg_control_user = msg->msg_control; kmsg->msg_controllen = msg->msg_controllen; kmsg->msg_flags = msg->msg_flags; kmsg->msg_namelen = msg->msg_namelen; if (!msg->msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) return -EINVAL; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); if (save_addr) *save_addr = msg->msg_name; if (msg->msg_name && kmsg->msg_namelen) { if (!save_addr) { err = move_addr_to_kernel(msg->msg_name, kmsg->msg_namelen, kmsg->msg_name); if (err < 0) return err; } } else { kmsg->msg_name = NULL; kmsg->msg_namelen = 0; } if (msg->msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; kmsg->msg_ubuf = NULL; return 0; } static int copy_msghdr_from_user(struct msghdr *kmsg, struct user_msghdr __user *umsg, struct sockaddr __user **save_addr, struct iovec **iov) { struct user_msghdr msg; ssize_t err; if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; err = __copy_msghdr(kmsg, &msg, save_addr); if (err) return err; err = import_iovec(save_addr ? ITER_DEST : ITER_SOURCE, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); return err < 0 ? err : 0; } static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address, unsigned int allowed_msghdr_flags) { unsigned char ctl[sizeof(struct cmsghdr) + 20] __aligned(sizeof(__kernel_size_t)); /* 20 is size of ipv6_pktinfo */ unsigned char *ctl_buf = ctl; int ctl_len; ssize_t err; err = -ENOBUFS; if (msg_sys->msg_controllen > INT_MAX) goto out; flags |= (msg_sys->msg_flags & allowed_msghdr_flags); ctl_len = msg_sys->msg_controllen; if ((MSG_CMSG_COMPAT & flags) && ctl_len) { err = cmsghdr_from_user_compat_to_kern(msg_sys, sock->sk, ctl, sizeof(ctl)); if (err) goto out; ctl_buf = msg_sys->msg_control; ctl_len = msg_sys->msg_controllen; } else if (ctl_len) { BUILD_BUG_ON(sizeof(struct cmsghdr) != CMSG_ALIGN(sizeof(struct cmsghdr))); if (ctl_len > sizeof(ctl)) { ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL); if (ctl_buf == NULL) goto out; } err = -EFAULT; if (copy_from_user(ctl_buf, msg_sys->msg_control_user, ctl_len)) goto out_freectl; msg_sys->msg_control = ctl_buf; msg_sys->msg_control_is_user = false; } flags &= ~MSG_INTERNAL_SENDMSG_FLAGS; msg_sys->msg_flags = flags; if (sock->file->f_flags & O_NONBLOCK) msg_sys->msg_flags |= MSG_DONTWAIT; /* * If this is sendmmsg() and current destination address is same as * previously succeeded address, omit asking LSM's decision. * used_address->name_len is initialized to UINT_MAX so that the first * destination address never matches. */ if (used_address && msg_sys->msg_name && used_address->name_len == msg_sys->msg_namelen && !memcmp(&used_address->name, msg_sys->msg_name, used_address->name_len)) { err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. */ if (used_address && err >= 0) { used_address->name_len = msg_sys->msg_namelen; if (msg_sys->msg_name) memcpy(&used_address->name, msg_sys->msg_name, used_address->name_len); } out_freectl: if (ctl_buf != ctl) sock_kfree_s(sock->sk, ctl_buf, ctl_len); out: return err; } static int sendmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct iovec **iov) { int err; if (flags & MSG_CMSG_COMPAT) { struct compat_msghdr __user *msg_compat; msg_compat = (struct compat_msghdr __user *) umsg; err = get_compat_msghdr(msg, msg_compat, NULL, iov); } else { err = copy_msghdr_from_user(msg, umsg, NULL, iov); } if (err < 0) return err; return 0; } static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address, unsigned int allowed_msghdr_flags) { struct sockaddr_storage address; struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; ssize_t err; msg_sys->msg_name = &address; err = sendmsg_copy_msghdr(msg_sys, msg, flags, &iov); if (err < 0) return err; err = ____sys_sendmsg(sock, msg_sys, flags, used_address, allowed_msghdr_flags); kfree(iov); return err; } /* * BSD sendmsg interface */ long __sys_sendmsg_sock(struct socket *sock, struct msghdr *msg, unsigned int flags) { return ____sys_sendmsg(sock, msg, flags, NULL, 0); } long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat) { struct msghdr msg_sys; struct socket *sock; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0); } SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { return __sys_sendmsg(fd, msg, flags, true); } /* * Linux sendmmsg interface */ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat) { int err, datagrams; struct socket *sock; struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct used_address used_address; unsigned int oflags = flags; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; if (vlen > UIO_MAXIOV) vlen = UIO_MAXIOV; datagrams = 0; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; used_address.name_len = UINT_MAX; entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; err = 0; flags |= MSG_BATCH; while (datagrams < vlen) { if (datagrams == vlen - 1) flags = oflags; if (MSG_CMSG_COMPAT & flags) { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)compat_entry, &msg_sys, flags, &used_address, MSG_EOR); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)entry, &msg_sys, flags, &used_address, MSG_EOR); if (err < 0) break; err = put_user(err, &entry->msg_len); ++entry; } if (err) break; ++datagrams; if (msg_data_left(&msg_sys)) break; cond_resched(); } /* We only return an error if no datagrams were able to be sent */ if (datagrams != 0) return datagrams; return err; } SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags) { return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } static int recvmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct sockaddr __user **uaddr, struct iovec **iov) { ssize_t err; if (MSG_CMSG_COMPAT & flags) { struct compat_msghdr __user *msg_compat; msg_compat = (struct compat_msghdr __user *) umsg; err = get_compat_msghdr(msg, msg_compat, uaddr, iov); } else { err = copy_msghdr_from_user(msg, umsg, uaddr, iov); } if (err < 0) return err; return 0; } static int ____sys_recvmsg(struct socket *sock, struct msghdr *msg_sys, struct user_msghdr __user *msg, struct sockaddr __user *uaddr, unsigned int flags, int nosec) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *) msg; int __user *uaddr_len = COMPAT_NAMELEN(msg); struct sockaddr_storage addr; unsigned long cmsg_ptr; int len; ssize_t err; msg_sys->msg_name = &addr; cmsg_ptr = (unsigned long)msg_sys->msg_control; msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); /* We assume all kernel code knows the size of sockaddr_storage */ msg_sys->msg_namelen = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; if (unlikely(nosec)) err = sock_recvmsg_nosec(sock, msg_sys, flags); else err = sock_recvmsg(sock, msg_sys, flags); if (err < 0) goto out; len = err; if (uaddr != NULL) { err = move_addr_to_user(&addr, msg_sys->msg_namelen, uaddr, uaddr_len); if (err < 0) goto out; } err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT), COMPAT_FLAGS(msg)); if (err) goto out; if (MSG_CMSG_COMPAT & flags) err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg_compat->msg_controllen); else err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg->msg_controllen); if (err) goto out; err = len; out: return err; } static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, int nosec) { struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; /* user mode address pointers */ struct sockaddr __user *uaddr; ssize_t err; err = recvmsg_copy_msghdr(msg_sys, msg, flags, &uaddr, &iov); if (err < 0) return err; err = ____sys_recvmsg(sock, msg_sys, msg, uaddr, flags, nosec); kfree(iov); return err; } /* * BSD recvmsg interface */ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg, struct user_msghdr __user *umsg, struct sockaddr __user *uaddr, unsigned int flags) { return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0); } long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat) { struct msghdr msg_sys; struct socket *sock; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; return ___sys_recvmsg(sock, msg, &msg_sys, flags, 0); } SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { return __sys_recvmsg(fd, msg, flags, true); } /* * Linux recvmmsg interface */ static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct timespec64 *timeout) { int err = 0, datagrams; struct socket *sock; struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct timespec64 end_time; struct timespec64 timeout64; if (timeout && poll_select_set_timeout(&end_time, timeout->tv_sec, timeout->tv_nsec)) return -EINVAL; datagrams = 0; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; sock = sock_from_file(fd_file(f)); if (unlikely(!sock)) return -ENOTSOCK; if (likely(!(flags & MSG_ERRQUEUE))) { err = sock_error(sock->sk); if (err) return err; } entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; while (datagrams < vlen) { /* * No need to ask LSM for more than the first datagram. */ if (MSG_CMSG_COMPAT & flags) { err = ___sys_recvmsg(sock, (struct user_msghdr __user *)compat_entry, &msg_sys, flags & ~MSG_WAITFORONE, datagrams); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = ___sys_recvmsg(sock, (struct user_msghdr __user *)entry, &msg_sys, flags & ~MSG_WAITFORONE, datagrams); if (err < 0) break; err = put_user(err, &entry->msg_len); ++entry; } if (err) break; ++datagrams; /* MSG_WAITFORONE turns on MSG_DONTWAIT after one packet */ if (flags & MSG_WAITFORONE) flags |= MSG_DONTWAIT; if (timeout) { ktime_get_ts64(&timeout64); *timeout = timespec64_sub(end_time, timeout64); if (timeout->tv_sec < 0) { timeout->tv_sec = timeout->tv_nsec = 0; break; } /* Timeout, return less than vlen datagrams */ if (timeout->tv_nsec == 0 && timeout->tv_sec == 0) break; } /* Out of band data, return right away */ if (msg_sys.msg_flags & MSG_OOB) break; cond_resched(); } if (err == 0) return datagrams; if (datagrams == 0) return err; /* * We may return less entries than requested (vlen) if the * sock is non block and there aren't enough datagrams... */ if (err != -EAGAIN) { /* * ... or if recvmsg returns an error after we * received some datagrams, where we record the * error to return on the next call or if the * app asks about it using getsockopt(SO_ERROR). */ WRITE_ONCE(sock->sk->sk_err, -err); } return datagrams; } int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct __kernel_timespec __user *timeout, struct old_timespec32 __user *timeout32) { int datagrams; struct timespec64 timeout_sys; if (timeout && get_timespec64(&timeout_sys, timeout)) return -EFAULT; if (timeout32 && get_old_timespec32(&timeout_sys, timeout32)) return -EFAULT; if (!timeout && !timeout32) return do_recvmmsg(fd, mmsg, vlen, flags, NULL); datagrams = do_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys); if (datagrams <= 0) return datagrams; if (timeout && put_timespec64(&timeout_sys, timeout)) datagrams = -EFAULT; if (timeout32 && put_old_timespec32(&timeout_sys, timeout32)) datagrams = -EFAULT; return datagrams; } SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct __kernel_timespec __user *, timeout) { if (flags & MSG_CMSG_COMPAT) return -EINVAL; return __sys_recvmmsg(fd, mmsg, vlen, flags, timeout, NULL); } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE5(recvmmsg_time32, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct old_timespec32 __user *, timeout) { if (flags & MSG_CMSG_COMPAT) return -EINVAL; return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL, timeout); } #endif #ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) static const unsigned char nargs[21] = { AL(0), AL(3), AL(3), AL(3), AL(2), AL(3), AL(3), AL(3), AL(4), AL(4), AL(4), AL(6), AL(6), AL(2), AL(5), AL(5), AL(3), AL(3), AL(4), AL(5), AL(4) }; #undef AL /* * System call vectors. * * Argument checking cleaned up. Saved 20% in size. * This function doesn't need to set the kernel lock because * it is set by the callees. */ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) { unsigned long a[AUDITSC_ARGS]; unsigned long a0, a1; int err; unsigned int len; if (call < 1 || call > SYS_SENDMMSG) return -EINVAL; call = array_index_nospec(call, SYS_SENDMMSG + 1); len = nargs[call]; if (len > sizeof(a)) return -EINVAL; /* copy_from_user should be SMP safe. */ if (copy_from_user(a, args, len)) return -EFAULT; err = audit_socketcall(nargs[call] / sizeof(unsigned long), a); if (err) return err; a0 = a[0]; a1 = a[1]; switch (call) { case SYS_SOCKET: err = __sys_socket(a0, a1, a[2]); break; case SYS_BIND: err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_CONNECT: err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_LISTEN: err = __sys_listen(a0, a1); break; case SYS_ACCEPT: err = __sys_accept4(a0, (struct sockaddr __user *)a1, (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = __sys_getsockname(a0, (struct sockaddr __user *)a1, (int __user *)a[2]); break; case SYS_GETPEERNAME: err = __sys_getpeername(a0, (struct sockaddr __user *)a1, (int __user *)a[2]); break; case SYS_SOCKETPAIR: err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]); break; case SYS_SEND: err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], NULL, 0); break; case SYS_SENDTO: err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], (struct sockaddr __user *)a[4], a[5]); break; case SYS_RECV: err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], NULL, NULL); break; case SYS_RECVFROM: err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], (struct sockaddr __user *)a[4], (int __user *)a[5]); break; case SYS_SHUTDOWN: err = __sys_shutdown(a0, a1); break; case SYS_SETSOCKOPT: err = __sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]); break; case SYS_GETSOCKOPT: err = __sys_getsockopt(a0, a1, a[2], (char __user *)a[3], (int __user *)a[4]); break; case SYS_SENDMSG: err = __sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2], true); break; case SYS_SENDMMSG: err = __sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], true); break; case SYS_RECVMSG: err = __sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2], true); break; case SYS_RECVMMSG: if (IS_ENABLED(CONFIG_64BIT)) err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], (struct __kernel_timespec __user *)a[4], NULL); else err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], NULL, (struct old_timespec32 __user *)a[4]); break; case SYS_ACCEPT4: err = __sys_accept4(a0, (struct sockaddr __user *)a1, (int __user *)a[2], a[3]); break; default: err = -EINVAL; break; } return err; } #endif /* __ARCH_WANT_SYS_SOCKETCALL */ /** * sock_register - add a socket protocol handler * @ops: description of protocol * * This function is called by a protocol handler that wants to * advertise its address family, and have it linked into the * socket interface. The value ops->family corresponds to the * socket system call protocol family. */ int sock_register(const struct net_proto_family *ops) { int err; if (ops->family >= NPROTO) { pr_crit("protocol %d >= NPROTO(%d)\n", ops->family, NPROTO); return -ENOBUFS; } spin_lock(&net_family_lock); if (rcu_dereference_protected(net_families[ops->family], lockdep_is_held(&net_family_lock))) err = -EEXIST; else { rcu_assign_pointer(net_families[ops->family], ops); err = 0; } spin_unlock(&net_family_lock); pr_info("NET: Registered %s protocol family\n", pf_family_names[ops->family]); return err; } EXPORT_SYMBOL(sock_register); /** * sock_unregister - remove a protocol handler * @family: protocol family to remove * * This function is called by a protocol handler that wants to * remove its address family, and have it unlinked from the * new socket creation. * * If protocol handler is a module, then it can use module reference * counts to protect against new references. If protocol handler is not * a module then it needs to provide its own protection in * the ops->create routine. */ void sock_unregister(int family) { BUG_ON(family < 0 || family >= NPROTO); spin_lock(&net_family_lock); RCU_INIT_POINTER(net_families[family], NULL); spin_unlock(&net_family_lock); synchronize_rcu(); pr_info("NET: Unregistered %s protocol family\n", pf_family_names[family]); } EXPORT_SYMBOL(sock_unregister); bool sock_is_registered(int family) { return family < NPROTO && rcu_access_pointer(net_families[family]); } static int __init sock_init(void) { int err; /* * Initialize the network sysctl infrastructure. */ err = net_sysctl_init(); if (err) goto out; /* * Initialize skbuff SLAB cache */ skb_init(); /* * Initialize the protocols module. */ init_inodecache(); err = register_filesystem(&sock_fs_type); if (err) goto out; sock_mnt = kern_mount(&sock_fs_type); if (IS_ERR(sock_mnt)) { err = PTR_ERR(sock_mnt); goto out_mount; } /* The real protocol initialization is performed in later initcalls. */ #ifdef CONFIG_NETFILTER err = netfilter_init(); if (err) goto out; #endif ptp_classifier_init(); out: return err; out_mount: unregister_filesystem(&sock_fs_type); goto out; } core_initcall(sock_init); /* early initcall */ #ifdef CONFIG_PROC_FS void socket_seq_show(struct seq_file *seq) { seq_printf(seq, "sockets: used %d\n", sock_inuse_get(seq->private)); } #endif /* CONFIG_PROC_FS */ /* Handle the fact that while struct ifreq has the same *layout* on * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, * which are handled elsewhere, it still has different *size* due to * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, * resulting in struct ifreq being 32 and 40 bytes respectively). * As a result, if the struct happens to be at the end of a page and * the next page isn't readable/writable, we get a fault. To prevent * that, copy back and forth to the full size. */ int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg) { if (in_compat_syscall()) { struct compat_ifreq *ifr32 = (struct compat_ifreq *)ifr; memset(ifr, 0, sizeof(*ifr)); if (copy_from_user(ifr32, arg, sizeof(*ifr32))) return -EFAULT; if (ifrdata) *ifrdata = compat_ptr(ifr32->ifr_data); return 0; } if (copy_from_user(ifr, arg, sizeof(*ifr))) return -EFAULT; if (ifrdata) *ifrdata = ifr->ifr_data; return 0; } EXPORT_SYMBOL(get_user_ifreq); int put_user_ifreq(struct ifreq *ifr, void __user *arg) { size_t size = sizeof(*ifr); if (in_compat_syscall()) size = sizeof(struct compat_ifreq); if (copy_to_user(arg, ifr, size)) return -EFAULT; return 0; } EXPORT_SYMBOL(put_user_ifreq); #ifdef CONFIG_COMPAT static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) { compat_uptr_t uptr32; struct ifreq ifr; void __user *saved; int err; if (get_user_ifreq(&ifr, NULL, uifr32)) return -EFAULT; if (get_user(uptr32, &uifr32->ifr_settings.ifs_ifsu)) return -EFAULT; saved = ifr.ifr_settings.ifs_ifsu.raw_hdlc; ifr.ifr_settings.ifs_ifsu.raw_hdlc = compat_ptr(uptr32); err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL, NULL); if (!err) { ifr.ifr_settings.ifs_ifsu.raw_hdlc = saved; if (put_user_ifreq(&ifr, uifr32)) err = -EFAULT; } return err; } /* Handle ioctls that use ifreq::ifr_data and just need struct ifreq converted */ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct compat_ifreq __user *u_ifreq32) { struct ifreq ifreq; void __user *data; if (!is_socket_ioctl_cmd(cmd)) return -ENOTTY; if (get_user_ifreq(&ifreq, &data, u_ifreq32)) return -EFAULT; ifreq.ifr_data = data; return dev_ioctl(net, cmd, &ifreq, data, NULL); } static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; struct net *net = sock_net(sk); const struct proto_ops *ops; if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) return sock_ioctl(file, cmd, (unsigned long)argp); switch (cmd) { case SIOCWANDEV: return compat_siocwandev(net, argp); case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: ops = READ_ONCE(sock->ops); if (!ops->gettstamp) return -ENOIOCTLCMD; return ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !COMPAT_USE_64BIT_TIME); case SIOCETHTOOL: case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: case SIOCGHWTSTAMP: return compat_ifr_data_ioctl(net, cmd, argp); case FIOSETOWN: case SIOCSPGRP: case FIOGETOWN: case SIOCGPGRP: case SIOCBRADDBR: case SIOCBRDELBR: case SIOCBRADDIF: case SIOCBRDELIF: case SIOCGIFVLAN: case SIOCSIFVLAN: case SIOCGSKNS: case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: case SIOCGIFCONF: case SIOCSIFBR: case SIOCGIFBR: return sock_ioctl(file, cmd, arg); case SIOCGIFFLAGS: case SIOCSIFFLAGS: case SIOCGIFMAP: case SIOCSIFMAP: case SIOCGIFMETRIC: case SIOCSIFMETRIC: case SIOCGIFMTU: case SIOCSIFMTU: case SIOCGIFMEM: case SIOCSIFMEM: case SIOCGIFHWADDR: case SIOCSIFHWADDR: case SIOCADDMULTI: case SIOCDELMULTI: case SIOCGIFINDEX: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCSIFHWBROADCAST: case SIOCDIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCSIFPFLAGS: case SIOCGIFPFLAGS: case SIOCGIFTXQLEN: case SIOCSIFTXQLEN: case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: case SIOCSARP: case SIOCGARP: case SIOCDARP: case SIOCOUTQ: case SIOCOUTQNSD: case SIOCATMARK: return sock_do_ioctl(net, sock, cmd, arg); } return -ENOIOCTLCMD; } static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct socket *sock = file->private_data; const struct proto_ops *ops = READ_ONCE(sock->ops); int ret = -ENOIOCTLCMD; struct sock *sk; struct net *net; sk = sock->sk; net = sock_net(sk); if (ops->compat_ioctl) ret = ops->compat_ioctl(sock, cmd, arg); if (ret == -ENOIOCTLCMD && (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)) ret = compat_wext_handle_ioctl(net, cmd, arg); if (ret == -ENOIOCTLCMD) ret = compat_sock_ioctl_trans(file, sock, cmd, arg); return ret; } #endif /** * kernel_bind - bind an address to a socket (kernel space) * @sock: socket * @addr: address * @addrlen: length of address * * Returns 0 or an error. */ int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { struct sockaddr_storage address; memcpy(&address, addr, addrlen); return READ_ONCE(sock->ops)->bind(sock, (struct sockaddr *)&address, addrlen); } EXPORT_SYMBOL(kernel_bind); /** * kernel_listen - move socket to listening state (kernel space) * @sock: socket * @backlog: pending connections queue size * * Returns 0 or an error. */ int kernel_listen(struct socket *sock, int backlog) { return READ_ONCE(sock->ops)->listen(sock, backlog); } EXPORT_SYMBOL(kernel_listen); /** * kernel_accept - accept a connection (kernel space) * @sock: listening socket * @newsock: new connected socket * @flags: flags * * @flags must be SOCK_CLOEXEC, SOCK_NONBLOCK or 0. * If it fails, @newsock is guaranteed to be %NULL. * Returns 0 or an error. */ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) { struct sock *sk = sock->sk; const struct proto_ops *ops = READ_ONCE(sock->ops); struct proto_accept_arg arg = { .flags = flags, .kern = true, }; int err; err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol, newsock); if (err < 0) goto done; err = ops->accept(sock, *newsock, &arg); if (err < 0) { sock_release(*newsock); *newsock = NULL; goto done; } (*newsock)->ops = ops; __module_get(ops->owner); done: return err; } EXPORT_SYMBOL(kernel_accept); /** * kernel_connect - connect a socket (kernel space) * @sock: socket * @addr: address * @addrlen: address length * @flags: flags (O_NONBLOCK, ...) * * For datagram sockets, @addr is the address to which datagrams are sent * by default, and the only address from which datagrams are received. * For stream sockets, attempts to connect to @addr. * Returns 0 or an error code. */ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags) { struct sockaddr_storage address; memcpy(&address, addr, addrlen); return READ_ONCE(sock->ops)->connect(sock, (struct sockaddr *)&address, addrlen, flags); } EXPORT_SYMBOL(kernel_connect); /** * kernel_getsockname - get the address which the socket is bound (kernel space) * @sock: socket * @addr: address holder * * Fills the @addr pointer with the address which the socket is bound. * Returns the length of the address in bytes or an error code. */ int kernel_getsockname(struct socket *sock, struct sockaddr *addr) { return READ_ONCE(sock->ops)->getname(sock, addr, 0); } EXPORT_SYMBOL(kernel_getsockname); /** * kernel_getpeername - get the address which the socket is connected (kernel space) * @sock: socket * @addr: address holder * * Fills the @addr pointer with the address which the socket is connected. * Returns the length of the address in bytes or an error code. */ int kernel_getpeername(struct socket *sock, struct sockaddr *addr) { return READ_ONCE(sock->ops)->getname(sock, addr, 1); } EXPORT_SYMBOL(kernel_getpeername); /** * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket * @how: connection part * * Returns 0 or an error. */ int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) { return READ_ONCE(sock->ops)->shutdown(sock, how); } EXPORT_SYMBOL(kernel_sock_shutdown); /** * kernel_sock_ip_overhead - returns the IP overhead imposed by a socket * @sk: socket * * This routine returns the IP overhead imposed by a socket i.e. * the length of the underlying IP header, depending on whether * this is an IPv4 or IPv6 socket and the length from IP options turned * on at the socket. Assumes that the caller has a lock on the socket. */ u32 kernel_sock_ip_overhead(struct sock *sk) { struct inet_sock *inet; struct ip_options_rcu *opt; u32 overhead = 0; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *np; struct ipv6_txoptions *optv6 = NULL; #endif /* IS_ENABLED(CONFIG_IPV6) */ if (!sk) return overhead; switch (sk->sk_family) { case AF_INET: inet = inet_sk(sk); overhead += sizeof(struct iphdr); opt = rcu_dereference_protected(inet->inet_opt, sock_owned_by_user(sk)); if (opt) overhead += opt->opt.optlen; return overhead; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: np = inet6_sk(sk); overhead += sizeof(struct ipv6hdr); if (np) optv6 = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); if (optv6) overhead += (optv6->opt_flen + optv6->opt_nflen); return overhead; #endif /* IS_ENABLED(CONFIG_IPV6) */ default: /* Returns 0 overhead if the socket is not ipv4 or ipv6 */ return overhead; } } EXPORT_SYMBOL(kernel_sock_ip_overhead); |
| 119 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "alloc_background.h" #include "alloc_foreground.h" #include "backpointers.h" #include "bkey_buf.h" #include "btree_gc.h" #include "btree_io.h" #include "btree_update.h" #include "btree_update_interior.h" #include "btree_write_buffer.h" #include "compress.h" #include "disk_groups.h" #include "ec.h" #include "errcode.h" #include "error.h" #include "inode.h" #include "io_read.h" #include "io_write.h" #include "journal_reclaim.h" #include "keylist.h" #include "move.h" #include "rebalance.h" #include "reflink.h" #include "replicas.h" #include "snapshot.h" #include "super-io.h" #include "trace.h" #include <linux/ioprio.h> #include <linux/kthread.h> const char * const bch2_data_ops_strs[] = { #define x(t, n, ...) [n] = #t, BCH_DATA_OPS() #undef x NULL }; struct evacuate_bucket_arg { struct bpos bucket; int gen; struct data_update_opts data_opts; }; static bool evacuate_bucket_pred(struct bch_fs *, void *, enum btree_id, struct bkey_s_c, struct bch_io_opts *, struct data_update_opts *); static noinline void trace_io_move2(struct bch_fs *c, struct bkey_s_c k, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); prt_newline(&buf); bch2_data_update_opts_to_text(&buf, c, io_opts, data_opts); trace_io_move(c, buf.buf); printbuf_exit(&buf); } static noinline void trace_io_move_read2(struct bch_fs *c, struct bkey_s_c k) { struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); trace_io_move_read(c, buf.buf); printbuf_exit(&buf); } static noinline void trace_io_move_pred2(struct bch_fs *c, struct bkey_s_c k, struct bch_io_opts *io_opts, struct data_update_opts *data_opts, move_pred_fn pred, void *_arg, bool p) { struct printbuf buf = PRINTBUF; prt_printf(&buf, "%ps: %u", pred, p); if (pred == evacuate_bucket_pred) { struct evacuate_bucket_arg *arg = _arg; prt_printf(&buf, " gen=%u", arg->gen); } prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, k); prt_newline(&buf); bch2_data_update_opts_to_text(&buf, c, io_opts, data_opts); trace_io_move_pred(c, buf.buf); printbuf_exit(&buf); } static noinline void trace_io_move_evacuate_bucket2(struct bch_fs *c, struct bpos bucket, int gen) { struct printbuf buf = PRINTBUF; prt_printf(&buf, "bucket: "); bch2_bpos_to_text(&buf, bucket); prt_printf(&buf, " gen: %i\n", gen); trace_io_move_evacuate_bucket(c, buf.buf); printbuf_exit(&buf); } struct moving_io { struct list_head read_list; struct list_head io_list; struct move_bucket *b; struct closure cl; bool read_completed; unsigned read_sectors; unsigned write_sectors; struct data_update write; }; static void move_free(struct moving_io *io) { struct moving_context *ctxt = io->write.ctxt; if (io->b) atomic_dec(&io->b->count); mutex_lock(&ctxt->lock); list_del(&io->io_list); wake_up(&ctxt->wait); mutex_unlock(&ctxt->lock); if (!io->write.data_opts.scrub) { bch2_data_update_exit(&io->write); } else { bch2_bio_free_pages_pool(io->write.op.c, &io->write.op.wbio.bio); kfree(io->write.bvecs); } kfree(io); } static void move_write_done(struct bch_write_op *op) { struct moving_io *io = container_of(op, struct moving_io, write.op); struct bch_fs *c = op->c; struct moving_context *ctxt = io->write.ctxt; if (op->error) { if (trace_io_move_write_fail_enabled()) { struct printbuf buf = PRINTBUF; bch2_write_op_to_text(&buf, op); trace_io_move_write_fail(c, buf.buf); printbuf_exit(&buf); } this_cpu_inc(c->counters[BCH_COUNTER_io_move_write_fail]); ctxt->write_error = true; } atomic_sub(io->write_sectors, &ctxt->write_sectors); atomic_dec(&ctxt->write_ios); move_free(io); closure_put(&ctxt->cl); } static void move_write(struct moving_io *io) { struct bch_fs *c = io->write.op.c; struct moving_context *ctxt = io->write.ctxt; struct bch_read_bio *rbio = &io->write.rbio; if (ctxt->stats) { if (rbio->bio.bi_status) atomic64_add(io->write.rbio.bvec_iter.bi_size >> 9, &ctxt->stats->sectors_error_uncorrected); else if (rbio->saw_error) atomic64_add(io->write.rbio.bvec_iter.bi_size >> 9, &ctxt->stats->sectors_error_corrected); } /* * If the extent has been bitrotted, we're going to have to give it a * new checksum in order to move it - but the poison bit will ensure * that userspace still gets the appropriate error. */ if (unlikely(rbio->ret == -BCH_ERR_data_read_csum_err && (bch2_bkey_extent_flags(bkey_i_to_s_c(io->write.k.k)) & BIT_ULL(BCH_EXTENT_FLAG_poisoned)))) { struct bch_extent_crc_unpacked crc = rbio->pick.crc; struct nonce nonce = extent_nonce(rbio->version, crc); rbio->pick.crc.csum = bch2_checksum_bio(c, rbio->pick.crc.csum_type, nonce, &rbio->bio); rbio->ret = 0; } if (unlikely(rbio->ret || io->write.data_opts.scrub)) { move_free(io); return; } if (trace_io_move_write_enabled()) { struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(io->write.k.k)); trace_io_move_write(c, buf.buf); printbuf_exit(&buf); } closure_get(&io->write.ctxt->cl); atomic_add(io->write_sectors, &io->write.ctxt->write_sectors); atomic_inc(&io->write.ctxt->write_ios); bch2_data_update_read_done(&io->write); } struct moving_io *bch2_moving_ctxt_next_pending_write(struct moving_context *ctxt) { struct moving_io *io = list_first_entry_or_null(&ctxt->reads, struct moving_io, read_list); return io && io->read_completed ? io : NULL; } static void move_read_endio(struct bio *bio) { struct moving_io *io = container_of(bio, struct moving_io, write.rbio.bio); struct moving_context *ctxt = io->write.ctxt; atomic_sub(io->read_sectors, &ctxt->read_sectors); atomic_dec(&ctxt->read_ios); io->read_completed = true; wake_up(&ctxt->wait); closure_put(&ctxt->cl); } void bch2_moving_ctxt_do_pending_writes(struct moving_context *ctxt) { struct moving_io *io; while ((io = bch2_moving_ctxt_next_pending_write(ctxt))) { bch2_trans_unlock_long(ctxt->trans); list_del(&io->read_list); move_write(io); } } void bch2_move_ctxt_wait_for_io(struct moving_context *ctxt) { unsigned sectors_pending = atomic_read(&ctxt->write_sectors); move_ctxt_wait_event(ctxt, !atomic_read(&ctxt->write_sectors) || atomic_read(&ctxt->write_sectors) != sectors_pending); } void bch2_moving_ctxt_flush_all(struct moving_context *ctxt) { move_ctxt_wait_event(ctxt, list_empty(&ctxt->reads)); bch2_trans_unlock_long(ctxt->trans); closure_sync(&ctxt->cl); } void bch2_moving_ctxt_exit(struct moving_context *ctxt) { struct bch_fs *c = ctxt->trans->c; bch2_moving_ctxt_flush_all(ctxt); EBUG_ON(atomic_read(&ctxt->write_sectors)); EBUG_ON(atomic_read(&ctxt->write_ios)); EBUG_ON(atomic_read(&ctxt->read_sectors)); EBUG_ON(atomic_read(&ctxt->read_ios)); mutex_lock(&c->moving_context_lock); list_del(&ctxt->list); mutex_unlock(&c->moving_context_lock); /* * Generally, releasing a transaction within a transaction restart means * an unhandled transaction restart: but this can happen legitimately * within the move code, e.g. when bch2_move_ratelimit() tells us to * exit before we've retried */ bch2_trans_begin(ctxt->trans); bch2_trans_put(ctxt->trans); memset(ctxt, 0, sizeof(*ctxt)); } void bch2_moving_ctxt_init(struct moving_context *ctxt, struct bch_fs *c, struct bch_ratelimit *rate, struct bch_move_stats *stats, struct write_point_specifier wp, bool wait_on_copygc) { memset(ctxt, 0, sizeof(*ctxt)); ctxt->trans = bch2_trans_get(c); ctxt->fn = (void *) _RET_IP_; ctxt->rate = rate; ctxt->stats = stats; ctxt->wp = wp; ctxt->wait_on_copygc = wait_on_copygc; closure_init_stack(&ctxt->cl); mutex_init(&ctxt->lock); INIT_LIST_HEAD(&ctxt->reads); INIT_LIST_HEAD(&ctxt->ios); init_waitqueue_head(&ctxt->wait); mutex_lock(&c->moving_context_lock); list_add(&ctxt->list, &c->moving_context_list); mutex_unlock(&c->moving_context_lock); } void bch2_move_stats_exit(struct bch_move_stats *stats, struct bch_fs *c) { trace_move_data(c, stats); } void bch2_move_stats_init(struct bch_move_stats *stats, const char *name) { memset(stats, 0, sizeof(*stats)); stats->data_type = BCH_DATA_user; scnprintf(stats->name, sizeof(stats->name), "%s", name); } int bch2_move_extent(struct moving_context *ctxt, struct move_bucket *bucket_in_flight, struct btree_iter *iter, struct bkey_s_c k, struct bch_io_opts io_opts, struct data_update_opts data_opts) { struct btree_trans *trans = ctxt->trans; struct bch_fs *c = trans->c; int ret = -ENOMEM; if (trace_io_move_enabled()) trace_io_move2(c, k, &io_opts, &data_opts); this_cpu_add(c->counters[BCH_COUNTER_io_move], k.k->size); if (ctxt->stats) ctxt->stats->pos = BBPOS(iter->btree_id, iter->pos); bch2_data_update_opts_normalize(k, &data_opts); if (!data_opts.rewrite_ptrs && !data_opts.extra_replicas && !data_opts.scrub) { if (data_opts.kill_ptrs) return bch2_extent_drop_ptrs(trans, iter, k, &io_opts, &data_opts); return 0; } struct moving_io *io = allocate_dropping_locks(trans, ret, kzalloc(sizeof(struct moving_io), _gfp)); if (!io) goto err; if (ret) goto err_free; INIT_LIST_HEAD(&io->io_list); io->write.ctxt = ctxt; io->read_sectors = k.k->size; io->write_sectors = k.k->size; if (!data_opts.scrub) { ret = bch2_data_update_init(trans, iter, ctxt, &io->write, ctxt->wp, &io_opts, data_opts, iter->btree_id, k); if (ret) goto err_free; io->write.op.end_io = move_write_done; } else { bch2_bkey_buf_init(&io->write.k); bch2_bkey_buf_reassemble(&io->write.k, c, k); io->write.op.c = c; io->write.data_opts = data_opts; bch2_trans_unlock(trans); ret = bch2_data_update_bios_init(&io->write, c, &io_opts); if (ret) goto err_free; } io->write.rbio.bio.bi_end_io = move_read_endio; io->write.rbio.bio.bi_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0); if (ctxt->rate) bch2_ratelimit_increment(ctxt->rate, k.k->size); if (ctxt->stats) { atomic64_inc(&ctxt->stats->keys_moved); atomic64_add(k.k->size, &ctxt->stats->sectors_moved); } if (bucket_in_flight) { io->b = bucket_in_flight; atomic_inc(&io->b->count); } if (trace_io_move_read_enabled()) trace_io_move_read2(c, k); mutex_lock(&ctxt->lock); atomic_add(io->read_sectors, &ctxt->read_sectors); atomic_inc(&ctxt->read_ios); list_add_tail(&io->read_list, &ctxt->reads); list_add_tail(&io->io_list, &ctxt->ios); mutex_unlock(&ctxt->lock); /* * dropped by move_read_endio() - guards against use after free of * ctxt when doing wakeup */ closure_get(&ctxt->cl); __bch2_read_extent(trans, &io->write.rbio, io->write.rbio.bio.bi_iter, bkey_start_pos(k.k), iter->btree_id, k, 0, NULL, BCH_READ_last_fragment, data_opts.scrub ? data_opts.read_dev : -1); return 0; err_free: kfree(io); err: if (bch2_err_matches(ret, EROFS) || bch2_err_matches(ret, BCH_ERR_transaction_restart)) return ret; count_event(c, io_move_start_fail); if (trace_io_move_start_fail_enabled()) { struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); prt_str(&buf, ": "); prt_str(&buf, bch2_err_str(ret)); trace_io_move_start_fail(c, buf.buf); printbuf_exit(&buf); } if (bch2_err_matches(ret, BCH_ERR_data_update_done)) return 0; return ret; } struct bch_io_opts *bch2_move_get_io_opts(struct btree_trans *trans, struct per_snapshot_io_opts *io_opts, struct bpos extent_pos, /* extent_iter, extent_k may be in reflink btree */ struct btree_iter *extent_iter, struct bkey_s_c extent_k) { struct bch_fs *c = trans->c; u32 restart_count = trans->restart_count; struct bch_io_opts *opts_ret = &io_opts->fs_io_opts; int ret = 0; if (extent_iter->min_depth) return opts_ret; if (extent_k.k->type == KEY_TYPE_reflink_v) goto out; if (io_opts->cur_inum != extent_pos.inode) { io_opts->d.nr = 0; ret = for_each_btree_key(trans, iter, BTREE_ID_inodes, POS(0, extent_pos.inode), BTREE_ITER_all_snapshots, k, ({ if (k.k->p.offset != extent_pos.inode) break; if (!bkey_is_inode(k.k)) continue; struct bch_inode_unpacked inode; _ret3 = bch2_inode_unpack(k, &inode); if (_ret3) break; struct snapshot_io_opts_entry e = { .snapshot = k.k->p.snapshot }; bch2_inode_opts_get(&e.io_opts, trans->c, &inode); darray_push(&io_opts->d, e); })); io_opts->cur_inum = extent_pos.inode; } ret = ret ?: trans_was_restarted(trans, restart_count); if (ret) return ERR_PTR(ret); if (extent_k.k->p.snapshot) darray_for_each(io_opts->d, i) if (bch2_snapshot_is_ancestor(c, extent_k.k->p.snapshot, i->snapshot)) { opts_ret = &i->io_opts; break; } out: ret = bch2_get_update_rebalance_opts(trans, opts_ret, extent_iter, extent_k); if (ret) return ERR_PTR(ret); return opts_ret; } int bch2_move_get_io_opts_one(struct btree_trans *trans, struct bch_io_opts *io_opts, struct btree_iter *extent_iter, struct bkey_s_c extent_k) { struct bch_fs *c = trans->c; *io_opts = bch2_opts_to_inode_opts(c->opts); /* reflink btree? */ if (!extent_k.k->p.inode) goto out; struct btree_iter inode_iter; struct bkey_s_c inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes, SPOS(0, extent_k.k->p.inode, extent_k.k->p.snapshot), BTREE_ITER_cached); int ret = bkey_err(inode_k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) return ret; if (!ret && bkey_is_inode(inode_k.k)) { struct bch_inode_unpacked inode; bch2_inode_unpack(inode_k, &inode); bch2_inode_opts_get(io_opts, c, &inode); } bch2_trans_iter_exit(trans, &inode_iter); /* seem to be spinning here? */ out: return bch2_get_update_rebalance_opts(trans, io_opts, extent_iter, extent_k); } int bch2_move_ratelimit(struct moving_context *ctxt) { struct bch_fs *c = ctxt->trans->c; bool is_kthread = current->flags & PF_KTHREAD; u64 delay; if (ctxt->wait_on_copygc && c->copygc_running) { bch2_moving_ctxt_flush_all(ctxt); wait_event_killable(c->copygc_running_wq, !c->copygc_running || (is_kthread && kthread_should_stop())); } do { delay = ctxt->rate ? bch2_ratelimit_delay(ctxt->rate) : 0; if (is_kthread && kthread_should_stop()) return 1; if (delay) move_ctxt_wait_event_timeout(ctxt, freezing(current) || (is_kthread && kthread_should_stop()), delay); if (unlikely(freezing(current))) { bch2_moving_ctxt_flush_all(ctxt); try_to_freeze(); } } while (delay); /* * XXX: these limits really ought to be per device, SSDs and hard drives * will want different limits */ move_ctxt_wait_event(ctxt, atomic_read(&ctxt->write_sectors) < c->opts.move_bytes_in_flight >> 9 && atomic_read(&ctxt->read_sectors) < c->opts.move_bytes_in_flight >> 9 && atomic_read(&ctxt->write_ios) < c->opts.move_ios_in_flight && atomic_read(&ctxt->read_ios) < c->opts.move_ios_in_flight); return 0; } /* * Move requires non extents iterators, and there's also no need for it to * signal indirect_extent_missing_error: */ static struct bkey_s_c bch2_lookup_indirect_extent_for_move(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_reflink_p p) { if (unlikely(REFLINK_P_ERROR(p.v))) return bkey_s_c_null; struct bpos reflink_pos = POS(0, REFLINK_P_IDX(p.v)); bch2_trans_iter_init(trans, iter, BTREE_ID_reflink, reflink_pos, BTREE_ITER_not_extents); struct bkey_s_c k = bch2_btree_iter_peek(trans, iter); if (!k.k || bkey_err(k)) { bch2_trans_iter_exit(trans, iter); return k; } if (bkey_lt(reflink_pos, bkey_start_pos(k.k))) { bch2_trans_iter_exit(trans, iter); return bkey_s_c_null; } return k; } int bch2_move_data_btree(struct moving_context *ctxt, struct bpos start, struct bpos end, move_pred_fn pred, void *arg, enum btree_id btree_id, unsigned level) { struct btree_trans *trans = ctxt->trans; struct bch_fs *c = trans->c; struct per_snapshot_io_opts snapshot_io_opts; struct bch_io_opts *io_opts; struct bkey_buf sk; struct btree_iter iter, reflink_iter = {}; struct bkey_s_c k; struct data_update_opts data_opts; /* * If we're moving a single file, also process reflinked data it points * to (this includes propagating changed io_opts from the inode to the * extent): */ bool walk_indirect = start.inode == end.inode; int ret = 0, ret2; per_snapshot_io_opts_init(&snapshot_io_opts, c); bch2_bkey_buf_init(&sk); if (ctxt->stats) { ctxt->stats->data_type = BCH_DATA_user; ctxt->stats->pos = BBPOS(btree_id, start); } retry_root: bch2_trans_begin(trans); if (level == bch2_btree_id_root(c, btree_id)->level + 1) { bch2_trans_node_iter_init(trans, &iter, btree_id, start, 0, level - 1, BTREE_ITER_prefetch| BTREE_ITER_not_extents| BTREE_ITER_all_snapshots); struct btree *b = bch2_btree_iter_peek_node(trans, &iter); ret = PTR_ERR_OR_ZERO(b); if (ret) goto root_err; if (b != btree_node_root(c, b)) { bch2_trans_iter_exit(trans, &iter); goto retry_root; } k = bkey_i_to_s_c(&b->key); io_opts = bch2_move_get_io_opts(trans, &snapshot_io_opts, iter.pos, &iter, k); ret = PTR_ERR_OR_ZERO(io_opts); if (ret) goto root_err; memset(&data_opts, 0, sizeof(data_opts)); if (!pred(c, arg, iter.btree_id, k, io_opts, &data_opts)) goto out; if (!data_opts.scrub) ret = bch2_btree_node_rewrite_pos(trans, btree_id, level, k.k->p, data_opts.target, 0); else ret = bch2_btree_node_scrub(trans, btree_id, level, k, data_opts.read_dev); root_err: if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) { bch2_trans_iter_exit(trans, &iter); goto retry_root; } goto out; } bch2_trans_node_iter_init(trans, &iter, btree_id, start, 0, level, BTREE_ITER_prefetch| BTREE_ITER_not_extents| BTREE_ITER_all_snapshots); if (ctxt->rate) bch2_ratelimit_reset(ctxt->rate); while (!bch2_move_ratelimit(ctxt)) { struct btree_iter *extent_iter = &iter; bch2_trans_begin(trans); k = bch2_btree_iter_peek(trans, &iter); if (!k.k) break; ret = bkey_err(k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) break; if (bkey_gt(bkey_start_pos(k.k), end)) break; if (ctxt->stats) ctxt->stats->pos = BBPOS(iter.btree_id, iter.pos); if (walk_indirect && k.k->type == KEY_TYPE_reflink_p && REFLINK_P_MAY_UPDATE_OPTIONS(bkey_s_c_to_reflink_p(k).v)) { struct bkey_s_c_reflink_p p = bkey_s_c_to_reflink_p(k); bch2_trans_iter_exit(trans, &reflink_iter); k = bch2_lookup_indirect_extent_for_move(trans, &reflink_iter, p); ret = bkey_err(k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) break; if (!k.k) goto next_nondata; /* * XXX: reflink pointers may point to multiple indirect * extents, so don't advance past the entire reflink * pointer - need to fixup iter->k */ extent_iter = &reflink_iter; } if (!bkey_extent_is_direct_data(k.k)) goto next_nondata; io_opts = bch2_move_get_io_opts(trans, &snapshot_io_opts, iter.pos, extent_iter, k); ret = PTR_ERR_OR_ZERO(io_opts); if (ret) continue; memset(&data_opts, 0, sizeof(data_opts)); if (!pred(c, arg, extent_iter->btree_id, k, io_opts, &data_opts)) goto next; /* * The iterator gets unlocked by __bch2_read_extent - need to * save a copy of @k elsewhere: */ bch2_bkey_buf_reassemble(&sk, c, k); k = bkey_i_to_s_c(sk.k); if (!level) ret2 = bch2_move_extent(ctxt, NULL, extent_iter, k, *io_opts, data_opts); else if (!data_opts.scrub) ret2 = bch2_btree_node_rewrite_pos(trans, btree_id, level, k.k->p, data_opts.target, 0); else ret2 = bch2_btree_node_scrub(trans, btree_id, level, k, data_opts.read_dev); if (ret2) { if (bch2_err_matches(ret2, BCH_ERR_transaction_restart)) continue; if (bch2_err_matches(ret2, ENOMEM)) { /* memory allocation failure, wait for some IO to finish */ bch2_move_ctxt_wait_for_io(ctxt); continue; } /* XXX signal failure */ goto next; } next: if (ctxt->stats) atomic64_add(k.k->size, &ctxt->stats->sectors_seen); next_nondata: if (!bch2_btree_iter_advance(trans, &iter)) break; } out: bch2_trans_iter_exit(trans, &reflink_iter); bch2_trans_iter_exit(trans, &iter); bch2_bkey_buf_exit(&sk, c); per_snapshot_io_opts_exit(&snapshot_io_opts); return ret; } int __bch2_move_data(struct moving_context *ctxt, struct bbpos start, struct bbpos end, move_pred_fn pred, void *arg) { struct bch_fs *c = ctxt->trans->c; enum btree_id id; int ret = 0; for (id = start.btree; id <= min_t(unsigned, end.btree, btree_id_nr_alive(c) - 1); id++) { ctxt->stats->pos = BBPOS(id, POS_MIN); if (!btree_type_has_ptrs(id) || !bch2_btree_id_root(c, id)->b) continue; ret = bch2_move_data_btree(ctxt, id == start.btree ? start.pos : POS_MIN, id == end.btree ? end.pos : POS_MAX, pred, arg, id, 0); if (ret) break; } return ret; } int bch2_move_data(struct bch_fs *c, struct bbpos start, struct bbpos end, struct bch_ratelimit *rate, struct bch_move_stats *stats, struct write_point_specifier wp, bool wait_on_copygc, move_pred_fn pred, void *arg) { struct moving_context ctxt; bch2_moving_ctxt_init(&ctxt, c, rate, stats, wp, wait_on_copygc); int ret = __bch2_move_data(&ctxt, start, end, pred, arg); bch2_moving_ctxt_exit(&ctxt); return ret; } static int __bch2_move_data_phys(struct moving_context *ctxt, struct move_bucket *bucket_in_flight, unsigned dev, u64 bucket_start, u64 bucket_end, unsigned data_types, bool copygc, move_pred_fn pred, void *arg) { struct btree_trans *trans = ctxt->trans; struct bch_fs *c = trans->c; bool is_kthread = current->flags & PF_KTHREAD; struct bch_io_opts io_opts = bch2_opts_to_inode_opts(c->opts); struct btree_iter iter = {}, bp_iter = {}; struct bkey_buf sk; struct bkey_s_c k; struct bkey_buf last_flushed; u64 check_mismatch_done = bucket_start; int ret = 0; struct bch_dev *ca = bch2_dev_tryget(c, dev); if (!ca) return 0; bucket_end = min(bucket_end, ca->mi.nbuckets); struct bpos bp_start = bucket_pos_to_bp_start(ca, POS(dev, bucket_start)); struct bpos bp_end = bucket_pos_to_bp_end(ca, POS(dev, bucket_end)); bch2_bkey_buf_init(&last_flushed); bkey_init(&last_flushed.k->k); bch2_bkey_buf_init(&sk); /* * We're not run in a context that handles transaction restarts: */ bch2_trans_begin(trans); bch2_trans_iter_init(trans, &bp_iter, BTREE_ID_backpointers, bp_start, 0); ret = bch2_btree_write_buffer_tryflush(trans); if (!bch2_err_matches(ret, EROFS)) bch_err_msg(c, ret, "flushing btree write buffer"); if (ret) goto err; while (!(ret = bch2_move_ratelimit(ctxt))) { if (is_kthread && kthread_should_stop()) break; bch2_trans_begin(trans); k = bch2_btree_iter_peek(trans, &bp_iter); ret = bkey_err(k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) goto err; if (!k.k || bkey_gt(k.k->p, bp_end)) break; if (check_mismatch_done < bp_pos_to_bucket(ca, k.k->p).offset) { while (check_mismatch_done < bp_pos_to_bucket(ca, k.k->p).offset) { bch2_check_bucket_backpointer_mismatch(trans, ca, check_mismatch_done++, copygc, &last_flushed); } continue; } if (k.k->type != KEY_TYPE_backpointer) goto next; struct bkey_s_c_backpointer bp = bkey_s_c_to_backpointer(k); if (ctxt->stats) ctxt->stats->offset = bp.k->p.offset >> MAX_EXTENT_COMPRESS_RATIO_SHIFT; if (!(data_types & BIT(bp.v->data_type))) goto next; if (!bp.v->level && bp.v->btree_id == BTREE_ID_stripes) goto next; k = bch2_backpointer_get_key(trans, bp, &iter, 0, &last_flushed); ret = bkey_err(k); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) goto err; if (!k.k) goto next; if (!bp.v->level) { ret = bch2_move_get_io_opts_one(trans, &io_opts, &iter, k); if (ret) { bch2_trans_iter_exit(trans, &iter); continue; } } struct data_update_opts data_opts = {}; bool p = pred(c, arg, bp.v->btree_id, k, &io_opts, &data_opts); if (trace_io_move_pred_enabled()) trace_io_move_pred2(c, k, &io_opts, &data_opts, pred, arg, p); if (!p) { bch2_trans_iter_exit(trans, &iter); goto next; } if (data_opts.scrub && !bch2_dev_idx_is_online(c, data_opts.read_dev)) { bch2_trans_iter_exit(trans, &iter); ret = bch_err_throw(c, device_offline); break; } bch2_bkey_buf_reassemble(&sk, c, k); k = bkey_i_to_s_c(sk.k); /* move_extent will drop locks */ unsigned sectors = bp.v->bucket_len; if (!bp.v->level) ret = bch2_move_extent(ctxt, bucket_in_flight, &iter, k, io_opts, data_opts); else if (!data_opts.scrub) ret = bch2_btree_node_rewrite_pos(trans, bp.v->btree_id, bp.v->level, k.k->p, data_opts.target, 0); else ret = bch2_btree_node_scrub(trans, bp.v->btree_id, bp.v->level, k, data_opts.read_dev); bch2_trans_iter_exit(trans, &iter); if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret == -ENOMEM) { /* memory allocation failure, wait for some IO to finish */ bch2_move_ctxt_wait_for_io(ctxt); continue; } if (ret) goto err; if (ctxt->stats) atomic64_add(sectors, &ctxt->stats->sectors_seen); next: bch2_btree_iter_advance(trans, &bp_iter); } while (check_mismatch_done < bucket_end) bch2_check_bucket_backpointer_mismatch(trans, ca, check_mismatch_done++, copygc, &last_flushed); err: bch2_trans_iter_exit(trans, &bp_iter); bch2_bkey_buf_exit(&sk, c); bch2_bkey_buf_exit(&last_flushed, c); bch2_dev_put(ca); return ret; } int bch2_move_data_phys(struct bch_fs *c, unsigned dev, u64 start, u64 end, unsigned data_types, struct bch_ratelimit *rate, struct bch_move_stats *stats, struct write_point_specifier wp, bool wait_on_copygc, move_pred_fn pred, void *arg) { struct moving_context ctxt; bch2_trans_run(c, bch2_btree_write_buffer_flush_sync(trans)); bch2_moving_ctxt_init(&ctxt, c, rate, stats, wp, wait_on_copygc); if (ctxt.stats) { ctxt.stats->phys = true; ctxt.stats->data_type = (int) DATA_PROGRESS_DATA_TYPE_phys; } int ret = __bch2_move_data_phys(&ctxt, NULL, dev, start, end, data_types, false, pred, arg); bch2_moving_ctxt_exit(&ctxt); return ret; } static bool evacuate_bucket_pred(struct bch_fs *c, void *_arg, enum btree_id btree, struct bkey_s_c k, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { struct evacuate_bucket_arg *arg = _arg; *data_opts = arg->data_opts; unsigned i = 0; bkey_for_each_ptr(bch2_bkey_ptrs_c(k), ptr) { if (ptr->dev == arg->bucket.inode && (arg->gen < 0 || arg->gen == ptr->gen) && !ptr->cached) data_opts->rewrite_ptrs |= BIT(i); i++; } return data_opts->rewrite_ptrs != 0; } int bch2_evacuate_bucket(struct moving_context *ctxt, struct move_bucket *bucket_in_flight, struct bpos bucket, int gen, struct data_update_opts data_opts) { struct bch_fs *c = ctxt->trans->c; struct evacuate_bucket_arg arg = { bucket, gen, data_opts, }; count_event(c, io_move_evacuate_bucket); if (trace_io_move_evacuate_bucket_enabled()) trace_io_move_evacuate_bucket2(c, bucket, gen); return __bch2_move_data_phys(ctxt, bucket_in_flight, bucket.inode, bucket.offset, bucket.offset + 1, ~0, true, evacuate_bucket_pred, &arg); } typedef bool (*move_btree_pred)(struct bch_fs *, void *, struct btree *, struct bch_io_opts *, struct data_update_opts *); static int bch2_move_btree(struct bch_fs *c, struct bbpos start, struct bbpos end, move_btree_pred pred, void *arg, struct bch_move_stats *stats) { bool kthread = (current->flags & PF_KTHREAD) != 0; struct bch_io_opts io_opts = bch2_opts_to_inode_opts(c->opts); struct moving_context ctxt; struct btree_trans *trans; struct btree_iter iter; struct btree *b; enum btree_id btree; struct data_update_opts data_opts; int ret = 0; bch2_moving_ctxt_init(&ctxt, c, NULL, stats, writepoint_ptr(&c->btree_write_point), true); trans = ctxt.trans; stats->data_type = BCH_DATA_btree; for (btree = start.btree; btree <= min_t(unsigned, end.btree, btree_id_nr_alive(c) - 1); btree ++) { stats->pos = BBPOS(btree, POS_MIN); if (!bch2_btree_id_root(c, btree)->b) continue; bch2_trans_node_iter_init(trans, &iter, btree, POS_MIN, 0, 0, BTREE_ITER_prefetch); retry: ret = 0; while (bch2_trans_begin(trans), (b = bch2_btree_iter_peek_node(trans, &iter)) && !(ret = PTR_ERR_OR_ZERO(b))) { if (kthread && kthread_should_stop()) break; if ((cmp_int(btree, end.btree) ?: bpos_cmp(b->key.k.p, end.pos)) > 0) break; stats->pos = BBPOS(iter.btree_id, iter.pos); if (!pred(c, arg, b, &io_opts, &data_opts)) goto next; ret = bch2_btree_node_rewrite(trans, &iter, b, 0, 0) ?: ret; if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) continue; if (ret) break; next: bch2_btree_iter_next_node(trans, &iter); } if (bch2_err_matches(ret, BCH_ERR_transaction_restart)) goto retry; bch2_trans_iter_exit(trans, &iter); if (kthread && kthread_should_stop()) break; } bch_err_fn(c, ret); bch2_moving_ctxt_exit(&ctxt); bch2_btree_interior_updates_flush(c); return ret; } static bool rereplicate_pred(struct bch_fs *c, void *arg, enum btree_id btree, struct bkey_s_c k, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { unsigned nr_good = bch2_bkey_durability(c, k); unsigned replicas = bkey_is_btree_ptr(k.k) ? c->opts.metadata_replicas : io_opts->data_replicas; guard(rcu)(); struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); unsigned i = 0; bkey_for_each_ptr(ptrs, ptr) { struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev); if (!ptr->cached && (!ca || !ca->mi.durability)) data_opts->kill_ptrs |= BIT(i); i++; } if (!data_opts->kill_ptrs && (!nr_good || nr_good >= replicas)) return false; data_opts->target = 0; data_opts->extra_replicas = replicas - nr_good; data_opts->btree_insert_flags = 0; return true; } static bool migrate_pred(struct bch_fs *c, void *arg, enum btree_id btree, struct bkey_s_c k, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); struct bch_ioctl_data *op = arg; unsigned i = 0; data_opts->rewrite_ptrs = 0; data_opts->target = 0; data_opts->extra_replicas = 0; data_opts->btree_insert_flags = 0; bkey_for_each_ptr(ptrs, ptr) { if (ptr->dev == op->migrate.dev) data_opts->rewrite_ptrs |= 1U << i; i++; } return data_opts->rewrite_ptrs != 0; } static bool rereplicate_btree_pred(struct bch_fs *c, void *arg, struct btree *b, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { return rereplicate_pred(c, arg, b->c.btree_id, bkey_i_to_s_c(&b->key), io_opts, data_opts); } /* * Ancient versions of bcachefs produced packed formats which could represent * keys that the in memory format cannot represent; this checks for those * formats so we can get rid of them. */ static bool bformat_needs_redo(struct bkey_format *f) { for (unsigned i = 0; i < f->nr_fields; i++) if (bch2_bkey_format_field_overflows(f, i)) return true; return false; } static bool rewrite_old_nodes_pred(struct bch_fs *c, void *arg, struct btree *b, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { if (b->version_ondisk != c->sb.version || btree_node_need_rewrite(b) || bformat_needs_redo(&b->format)) { data_opts->target = 0; data_opts->extra_replicas = 0; data_opts->btree_insert_flags = 0; return true; } return false; } int bch2_scan_old_btree_nodes(struct bch_fs *c, struct bch_move_stats *stats) { int ret; ret = bch2_move_btree(c, BBPOS_MIN, BBPOS_MAX, rewrite_old_nodes_pred, c, stats); if (!ret) { mutex_lock(&c->sb_lock); c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_extents_above_btree_updates_done); c->disk_sb.sb->compat[0] |= cpu_to_le64(1ULL << BCH_COMPAT_bformat_overflow_done); c->disk_sb.sb->version_min = c->disk_sb.sb->version; bch2_write_super(c); mutex_unlock(&c->sb_lock); } bch_err_fn(c, ret); return ret; } static bool drop_extra_replicas_pred(struct bch_fs *c, void *arg, enum btree_id btree, struct bkey_s_c k, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { unsigned durability = bch2_bkey_durability(c, k); unsigned replicas = bkey_is_btree_ptr(k.k) ? c->opts.metadata_replicas : io_opts->data_replicas; const union bch_extent_entry *entry; struct extent_ptr_decoded p; unsigned i = 0; guard(rcu)(); bkey_for_each_ptr_decode(k.k, bch2_bkey_ptrs_c(k), p, entry) { unsigned d = bch2_extent_ptr_durability(c, &p); if (d && durability - d >= replicas) { data_opts->kill_ptrs |= BIT(i); durability -= d; } i++; } return data_opts->kill_ptrs != 0; } static bool drop_extra_replicas_btree_pred(struct bch_fs *c, void *arg, struct btree *b, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { return drop_extra_replicas_pred(c, arg, b->c.btree_id, bkey_i_to_s_c(&b->key), io_opts, data_opts); } static bool scrub_pred(struct bch_fs *c, void *_arg, enum btree_id btree, struct bkey_s_c k, struct bch_io_opts *io_opts, struct data_update_opts *data_opts) { struct bch_ioctl_data *arg = _arg; if (k.k->type != KEY_TYPE_btree_ptr_v2) { struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); const union bch_extent_entry *entry; struct extent_ptr_decoded p; bkey_for_each_ptr_decode(k.k, ptrs, p, entry) if (p.ptr.dev == arg->migrate.dev) { if (!p.crc.csum_type) return false; break; } } data_opts->scrub = true; data_opts->read_dev = arg->migrate.dev; return true; } int bch2_data_job(struct bch_fs *c, struct bch_move_stats *stats, struct bch_ioctl_data op) { struct bbpos start = BBPOS(op.start_btree, op.start_pos); struct bbpos end = BBPOS(op.end_btree, op.end_pos); int ret = 0; if (op.op >= BCH_DATA_OP_NR) return -EINVAL; bch2_move_stats_init(stats, bch2_data_ops_strs[op.op]); switch (op.op) { case BCH_DATA_OP_scrub: /* * prevent tests from spuriously failing, make sure we see all * btree nodes that need to be repaired */ bch2_btree_interior_updates_flush(c); ret = bch2_move_data_phys(c, op.scrub.dev, 0, U64_MAX, op.scrub.data_types, NULL, stats, writepoint_hashed((unsigned long) current), false, scrub_pred, &op) ?: ret; break; case BCH_DATA_OP_rereplicate: stats->data_type = BCH_DATA_journal; ret = bch2_journal_flush_device_pins(&c->journal, -1); ret = bch2_move_btree(c, start, end, rereplicate_btree_pred, c, stats) ?: ret; ret = bch2_move_data(c, start, end, NULL, stats, writepoint_hashed((unsigned long) current), true, rereplicate_pred, c) ?: ret; ret = bch2_replicas_gc2(c) ?: ret; break; case BCH_DATA_OP_migrate: if (op.migrate.dev >= c->sb.nr_devices) return -EINVAL; stats->data_type = BCH_DATA_journal; ret = bch2_journal_flush_device_pins(&c->journal, op.migrate.dev); ret = bch2_move_data_phys(c, op.migrate.dev, 0, U64_MAX, ~0, NULL, stats, writepoint_hashed((unsigned long) current), true, migrate_pred, &op) ?: ret; bch2_btree_interior_updates_flush(c); ret = bch2_replicas_gc2(c) ?: ret; break; case BCH_DATA_OP_rewrite_old_nodes: ret = bch2_scan_old_btree_nodes(c, stats); break; case BCH_DATA_OP_drop_extra_replicas: ret = bch2_move_btree(c, start, end, drop_extra_replicas_btree_pred, c, stats) ?: ret; ret = bch2_move_data(c, start, end, NULL, stats, writepoint_hashed((unsigned long) current), true, drop_extra_replicas_pred, c) ?: ret; ret = bch2_replicas_gc2(c) ?: ret; break; default: ret = -EINVAL; } bch2_move_stats_exit(stats, c); return ret; } void bch2_move_stats_to_text(struct printbuf *out, struct bch_move_stats *stats) { prt_printf(out, "%s: data type==", stats->name); bch2_prt_data_type(out, stats->data_type); prt_str(out, " pos="); bch2_bbpos_to_text(out, stats->pos); prt_newline(out); printbuf_indent_add(out, 2); prt_printf(out, "keys moved:\t%llu\n", atomic64_read(&stats->keys_moved)); prt_printf(out, "keys raced:\t%llu\n", atomic64_read(&stats->keys_raced)); prt_printf(out, "bytes seen:\t"); prt_human_readable_u64(out, atomic64_read(&stats->sectors_seen) << 9); prt_newline(out); prt_printf(out, "bytes moved:\t"); prt_human_readable_u64(out, atomic64_read(&stats->sectors_moved) << 9); prt_newline(out); prt_printf(out, "bytes raced:\t"); prt_human_readable_u64(out, atomic64_read(&stats->sectors_raced) << 9); prt_newline(out); printbuf_indent_sub(out, 2); } static void bch2_moving_ctxt_to_text(struct printbuf *out, struct bch_fs *c, struct moving_context *ctxt) { if (!out->nr_tabstops) printbuf_tabstop_push(out, 32); bch2_move_stats_to_text(out, ctxt->stats); printbuf_indent_add(out, 2); prt_printf(out, "reads: ios %u/%u sectors %u/%u\n", atomic_read(&ctxt->read_ios), c->opts.move_ios_in_flight, atomic_read(&ctxt->read_sectors), c->opts.move_bytes_in_flight >> 9); prt_printf(out, "writes: ios %u/%u sectors %u/%u\n", atomic_read(&ctxt->write_ios), c->opts.move_ios_in_flight, atomic_read(&ctxt->write_sectors), c->opts.move_bytes_in_flight >> 9); printbuf_indent_add(out, 2); mutex_lock(&ctxt->lock); struct moving_io *io; list_for_each_entry(io, &ctxt->ios, io_list) bch2_data_update_inflight_to_text(out, &io->write); mutex_unlock(&ctxt->lock); printbuf_indent_sub(out, 4); } void bch2_fs_moving_ctxts_to_text(struct printbuf *out, struct bch_fs *c) { struct moving_context *ctxt; mutex_lock(&c->moving_context_lock); list_for_each_entry(ctxt, &c->moving_context_list, list) bch2_moving_ctxt_to_text(out, c, ctxt); mutex_unlock(&c->moving_context_lock); } void bch2_fs_move_init(struct bch_fs *c) { INIT_LIST_HEAD(&c->moving_context_list); mutex_init(&c->moving_context_lock); } |
| 779 1468 779 303 1468 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 */ #ifndef _LINUX_IVERSION_H #define _LINUX_IVERSION_H #include <linux/fs.h> /* * The inode->i_version field: * --------------------------- * The change attribute (i_version) is mandated by NFSv4 and is mostly for * knfsd, but is also used for other purposes (e.g. IMA). The i_version must * appear larger to observers if there was an explicit change to the inode's * data or metadata since it was last queried. * * An explicit change is one that would ordinarily result in a change to the * inode status change time (aka ctime). i_version must appear to change, even * if the ctime does not (since the whole point is to avoid missing updates due * to timestamp granularity). If POSIX or other relevant spec mandates that the * ctime must change due to an operation, then the i_version counter must be * incremented as well. * * Making the i_version update completely atomic with the operation itself would * be prohibitively expensive. Traditionally the kernel has updated the times on * directories after an operation that changes its contents. For regular files, * the ctime is usually updated before the data is copied into the cache for a * write. This means that there is a window of time when an observer can * associate a new timestamp with old file contents. Since the purpose of the * i_version is to allow for better cache coherency, the i_version must always * be updated after the results of the operation are visible. Updating it before * and after a change is also permitted. (Note that no filesystems currently do * this. Fixing that is a work-in-progress). * * Observers see the i_version as a 64-bit number that never decreases. If it * remains the same since it was last checked, then nothing has changed in the * inode. If it's different then something has changed. Observers cannot infer * anything about the nature or magnitude of the changes from the value, only * that the inode has changed in some fashion. * * Not all filesystems properly implement the i_version counter. Subsystems that * want to use i_version field on an inode should first check whether the * filesystem sets the SB_I_VERSION flag (usually via the IS_I_VERSION macro). * * Those that set SB_I_VERSION will automatically have their i_version counter * incremented on writes to normal files. If the SB_I_VERSION is not set, then * the VFS will not touch it on writes, and the filesystem can use it how it * wishes. Note that the filesystem is always responsible for updating the * i_version on namespace changes in directories (mkdir, rmdir, unlink, etc.). * We consider these sorts of filesystems to have a kernel-managed i_version. * * It may be impractical for filesystems to keep i_version updates atomic with * respect to the changes that cause them. They should, however, guarantee * that i_version updates are never visible before the changes that caused * them. Also, i_version updates should never be delayed longer than it takes * the original change to reach disk. * * This implementation uses the low bit in the i_version field as a flag to * track when the value has been queried. If it has not been queried since it * was last incremented, we can skip the increment in most cases. * * In the event that we're updating the ctime, we will usually go ahead and * bump the i_version anyway. Since that has to go to stable storage in some * fashion, we might as well increment it as well. * * With this implementation, the value should always appear to observers to * increase over time if the file has changed. It's recommended to use * inode_eq_iversion() helper to compare values. * * Note that some filesystems (e.g. NFS and AFS) just use the field to store * a server-provided value (for the most part). For that reason, those * filesystems do not set SB_I_VERSION. These filesystems are considered to * have a self-managed i_version. * * Persistently storing the i_version * ---------------------------------- * Queries of the i_version field are not gated on them hitting the backing * store. It's always possible that the host could crash after allowing * a query of the value but before it has made it to disk. * * To mitigate this problem, filesystems should always use * inode_set_iversion_queried when loading an existing inode from disk. This * ensures that the next attempted inode increment will result in the value * changing. * * Storing the value to disk therefore does not count as a query, so those * filesystems should use inode_peek_iversion to grab the value to be stored. * There is no need to flag the value as having been queried in that case. */ /* * We borrow the lowest bit in the i_version to use as a flag to tell whether * it has been queried since we last incremented it. If it has, then we must * increment it on the next change. After that, we can clear the flag and * avoid incrementing it again until it has again been queried. */ #define I_VERSION_QUERIED_SHIFT (1) #define I_VERSION_QUERIED (1ULL << (I_VERSION_QUERIED_SHIFT - 1)) #define I_VERSION_INCREMENT (1ULL << I_VERSION_QUERIED_SHIFT) /** * inode_set_iversion_raw - set i_version to the specified raw value * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val. This function is for use by * filesystems that self-manage the i_version. * * For example, the NFS client stores its NFSv4 change attribute in this way, * and the AFS client stores the data_version from the server here. */ static inline void inode_set_iversion_raw(struct inode *inode, u64 val) { atomic64_set(&inode->i_version, val); } /** * inode_peek_iversion_raw - grab a "raw" iversion value * @inode: inode from which i_version should be read * * Grab a "raw" inode->i_version value and return it. The i_version is not * flagged or converted in any way. This is mostly used to access a self-managed * i_version. * * With those filesystems, we want to treat the i_version as an entirely * opaque value. */ static inline u64 inode_peek_iversion_raw(const struct inode *inode) { return atomic64_read(&inode->i_version); } /** * inode_set_max_iversion_raw - update i_version new value is larger * @inode: inode to set * @val: new i_version to set * * Some self-managed filesystems (e.g Ceph) will only update the i_version * value if the new value is larger than the one we already have. */ static inline void inode_set_max_iversion_raw(struct inode *inode, u64 val) { u64 cur = inode_peek_iversion_raw(inode); do { if (cur > val) break; } while (!atomic64_try_cmpxchg(&inode->i_version, &cur, val)); } /** * inode_set_iversion - set i_version to a particular value * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val. This function is for filesystems with * a kernel-managed i_version, for initializing a newly-created inode from * scratch. * * In this case, we do not set the QUERIED flag since we know that this value * has never been queried. */ static inline void inode_set_iversion(struct inode *inode, u64 val) { inode_set_iversion_raw(inode, val << I_VERSION_QUERIED_SHIFT); } /** * inode_set_iversion_queried - set i_version to a particular value as quereied * @inode: inode to set * @val: new i_version value to set * * Set @inode's i_version field to @val, and flag it for increment on the next * change. * * Filesystems that persistently store the i_version on disk should use this * when loading an existing inode from disk. * * When loading in an i_version value from a backing store, we can't be certain * that it wasn't previously viewed before being stored. Thus, we must assume * that it was, to ensure that we don't end up handing out the same value for * different versions of the same inode. */ static inline void inode_set_iversion_queried(struct inode *inode, u64 val) { inode_set_iversion_raw(inode, (val << I_VERSION_QUERIED_SHIFT) | I_VERSION_QUERIED); } bool inode_maybe_inc_iversion(struct inode *inode, bool force); /** * inode_inc_iversion - forcibly increment i_version * @inode: inode that needs to be updated * * Forcbily increment the i_version field. This always results in a change to * the observable value. */ static inline void inode_inc_iversion(struct inode *inode) { inode_maybe_inc_iversion(inode, true); } /** * inode_iversion_need_inc - is the i_version in need of being incremented? * @inode: inode to check * * Returns whether the inode->i_version counter needs incrementing on the next * change. Just fetch the value and check the QUERIED flag. */ static inline bool inode_iversion_need_inc(struct inode *inode) { return inode_peek_iversion_raw(inode) & I_VERSION_QUERIED; } /** * inode_inc_iversion_raw - forcibly increment raw i_version * @inode: inode that needs to be updated * * Forcbily increment the raw i_version field. This always results in a change * to the raw value. * * NFS will use the i_version field to store the value from the server. It * mostly treats it as opaque, but in the case where it holds a write * delegation, it must increment the value itself. This function does that. */ static inline void inode_inc_iversion_raw(struct inode *inode) { atomic64_inc(&inode->i_version); } /** * inode_peek_iversion - read i_version without flagging it to be incremented * @inode: inode from which i_version should be read * * Read the inode i_version counter for an inode without registering it as a * query. * * This is typically used by local filesystems that need to store an i_version * on disk. In that situation, it's not necessary to flag it as having been * viewed, as the result won't be used to gauge changes from that point. */ static inline u64 inode_peek_iversion(const struct inode *inode) { return inode_peek_iversion_raw(inode) >> I_VERSION_QUERIED_SHIFT; } /* * For filesystems without any sort of change attribute, the best we can * do is fake one up from the ctime: */ static inline u64 time_to_chattr(const struct timespec64 *t) { u64 chattr = t->tv_sec; chattr <<= 32; chattr += t->tv_nsec; return chattr; } u64 inode_query_iversion(struct inode *inode); /** * inode_eq_iversion_raw - check whether the raw i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * * Compare the current raw i_version counter with a previous one. Returns true * if they are the same or false if they are different. */ static inline bool inode_eq_iversion_raw(const struct inode *inode, u64 old) { return inode_peek_iversion_raw(inode) == old; } /** * inode_eq_iversion - check whether the i_version counter has changed * @inode: inode to check * @old: old value to check against its i_version * * Compare an i_version counter with a previous one. Returns true if they are * the same, and false if they are different. * * Note that we don't need to set the QUERIED flag in this case, as the value * in the inode is not being recorded for later use. */ static inline bool inode_eq_iversion(const struct inode *inode, u64 old) { return inode_peek_iversion(inode) == old; } #endif |
| 16 308 10 5 277 15 27 16 315 221 170 63 18 15 109 484 483 12 32 300 321 200 248 6 193 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * */ // clang-format off #ifndef _LINUX_NTFS3_NTFS_FS_H #define _LINUX_NTFS3_NTFS_FS_H #include <linux/blkdev.h> #include <linux/buffer_head.h> #include <linux/fs.h> #include <linux/highmem.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/mutex.h> #include <linux/page-flags.h> #include <linux/pagemap.h> #include <linux/rbtree.h> #include <linux/rwsem.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/time64.h> #include <linux/types.h> #include <linux/uidgid.h> #include <asm/div64.h> #include <asm/page.h> #include "debug.h" #include "ntfs.h" struct dentry; struct fiemap_extent_info; struct user_namespace; struct page; struct writeback_control; enum utf16_endian; #define MINUS_ONE_T ((size_t)(-1)) /* Biggest MFT / smallest cluster */ #define MAXIMUM_BYTES_PER_MFT 4096 #define MAXIMUM_SHIFT_BYTES_PER_MFT 12 #define NTFS_BLOCKS_PER_MFT_RECORD (MAXIMUM_BYTES_PER_MFT / 512) #define MAXIMUM_BYTES_PER_INDEX 4096 #define MAXIMUM_SHIFT_BYTES_PER_INDEX 12 #define NTFS_BLOCKS_PER_INODE (MAXIMUM_BYTES_PER_INDEX / 512) /* NTFS specific error code when fixup failed. */ #define E_NTFS_FIXUP 555 /* NTFS specific error code about resident->nonresident. */ #define E_NTFS_NONRESIDENT 556 /* NTFS specific error code about punch hole. */ #define E_NTFS_NOTALIGNED 557 /* NTFS specific error code when on-disk struct is corrupted. */ #define E_NTFS_CORRUPT 558 /* sbi->flags */ #define NTFS_FLAGS_NODISCARD 0x00000001 /* ntfs in shutdown state. */ #define NTFS_FLAGS_SHUTDOWN_BIT 0x00000002 /* == 4*/ /* Set when LogFile is replaying. */ #define NTFS_FLAGS_LOG_REPLAYING 0x00000008 /* Set when we changed first MFT's which copy must be updated in $MftMirr. */ #define NTFS_FLAGS_MFTMIRR 0x00001000 #define NTFS_FLAGS_NEED_REPLAY 0x04000000 /* ni->ni_flags */ /* * Data attribute is external compressed (LZX/Xpress) * 1 - WOF_COMPRESSION_XPRESS4K * 2 - WOF_COMPRESSION_XPRESS8K * 3 - WOF_COMPRESSION_XPRESS16K * 4 - WOF_COMPRESSION_LZX32K */ #define NI_FLAG_COMPRESSED_MASK 0x0000000f /* Data attribute is deduplicated. */ #define NI_FLAG_DEDUPLICATED 0x00000010 #define NI_FLAG_EA 0x00000020 #define NI_FLAG_DIR 0x00000040 #define NI_FLAG_RESIDENT 0x00000080 #define NI_FLAG_UPDATE_PARENT 0x00000100 // clang-format on struct ntfs_mount_options { char *nls_name; struct nls_table *nls; kuid_t fs_uid; kgid_t fs_gid; u16 fs_fmask_inv; u16 fs_dmask_inv; unsigned fmask : 1; /* fmask was set. */ unsigned dmask : 1; /*dmask was set. */ unsigned sys_immutable : 1; /* Immutable system files. */ unsigned discard : 1; /* Issue discard requests on deletions. */ unsigned sparse : 1; /* Create sparse files. */ unsigned showmeta : 1; /* Show meta files. */ unsigned nohidden : 1; /* Do not show hidden files. */ unsigned hide_dot_files : 1; /* Set hidden flag on dot files. */ unsigned windows_names : 1; /* Disallow names forbidden by Windows. */ unsigned force : 1; /* RW mount dirty volume. */ unsigned prealloc : 1; /* Preallocate space when file is growing. */ unsigned nocase : 1; /* case insensitive. */ }; /* Special value to unpack and deallocate. */ #define RUN_DEALLOCATE ((struct runs_tree *)(size_t)1) /* TODO: Use rb tree instead of array. */ struct runs_tree { struct ntfs_run *runs; size_t count; /* Currently used size a ntfs_run storage. */ size_t allocated; /* Currently allocated ntfs_run storage size. */ }; struct ntfs_buffers { /* Biggest MFT / smallest cluster = 4096 / 512 = 8 */ /* Biggest index / smallest cluster = 4096 / 512 = 8 */ struct buffer_head *bh[PAGE_SIZE >> SECTOR_SHIFT]; u32 bytes; u32 nbufs; u32 off; }; enum ALLOCATE_OPT { ALLOCATE_DEF = 0, // Allocate all clusters. ALLOCATE_MFT = 1, // Allocate for MFT. ALLOCATE_ZERO = 2, // Zeroout new allocated clusters }; enum bitmap_mutex_classes { BITMAP_MUTEX_CLUSTERS = 0, BITMAP_MUTEX_MFT = 1, }; struct wnd_bitmap { struct super_block *sb; struct rw_semaphore rw_lock; struct runs_tree run; size_t nbits; size_t total_zeroes; // Total number of free bits. u16 *free_bits; // Free bits in each window. size_t nwnd; u32 bits_last; // Bits in last window. struct rb_root start_tree; // Extents, sorted by 'start'. struct rb_root count_tree; // Extents, sorted by 'count + start'. size_t count; // Extents count. /* * -1 Tree is activated but not updated (too many fragments). * 0 - Tree is not activated. * 1 - Tree is activated and updated. */ int uptodated; size_t extent_min; // Minimal extent used while building. size_t extent_max; // Upper estimate of biggest free block. /* Zone [bit, end) */ size_t zone_bit; size_t zone_end; bool inited; }; typedef int (*NTFS_CMP_FUNC)(const void *key1, size_t len1, const void *key2, size_t len2, const void *param); enum index_mutex_classed { INDEX_MUTEX_I30 = 0, INDEX_MUTEX_SII = 1, INDEX_MUTEX_SDH = 2, INDEX_MUTEX_SO = 3, INDEX_MUTEX_SQ = 4, INDEX_MUTEX_SR = 5, INDEX_MUTEX_TOTAL }; /* ntfs_index - Allocation unit inside directory. */ struct ntfs_index { struct runs_tree bitmap_run; struct runs_tree alloc_run; /* read/write access to 'bitmap_run'/'alloc_run' while ntfs_readdir */ struct rw_semaphore run_lock; /*TODO: Remove 'cmp'. */ NTFS_CMP_FUNC cmp; u8 index_bits; // log2(root->index_block_size) u8 idx2vbn_bits; // log2(root->index_block_clst) u8 vbn2vbo_bits; // index_block_size < cluster? 9 : cluster_bits u8 type; // index_mutex_classed }; /* Minimum MFT zone. */ #define NTFS_MIN_MFT_ZONE 100 /* Step to increase the MFT. */ #define NTFS_MFT_INCREASE_STEP 1024 /* Ntfs file system in-core superblock data. */ struct ntfs_sb_info { struct super_block *sb; u32 discard_granularity; u64 discard_granularity_mask_inv; // ~(discard_granularity_mask_inv-1) u32 cluster_size; // bytes per cluster u32 cluster_mask; // == cluster_size - 1 u64 cluster_mask_inv; // ~(cluster_size - 1) u32 block_mask; // sb->s_blocksize - 1 u32 blocks_per_cluster; // cluster_size / sb->s_blocksize u32 record_size; u32 index_size; u8 cluster_bits; u8 record_bits; u64 maxbytes; // Maximum size for normal files. u64 maxbytes_sparse; // Maximum size for sparse file. unsigned long flags; // See NTFS_FLAGS_ CLST zone_max; // Maximum MFT zone length in clusters CLST bad_clusters; // The count of marked bad clusters. u16 max_bytes_per_attr; // Maximum attribute size in record. u16 attr_size_tr; // Attribute size threshold (320 bytes). /* Records in $Extend. */ CLST objid_no; CLST quota_no; CLST reparse_no; CLST usn_jrnl_no; struct ATTR_DEF_ENTRY *def_table; // Attribute definition table. u32 def_entries; u32 ea_max_size; struct MFT_REC *new_rec; u16 *upcase; struct { u64 lbo, lbo2; struct ntfs_inode *ni; struct wnd_bitmap bitmap; // $MFT::Bitmap /* * MFT records [11-24) used to expand MFT itself. * They always marked as used in $MFT::Bitmap * 'reserved_bitmap' contains real bitmap of these records. */ ulong reserved_bitmap; // Bitmap of used records [11 - 24) size_t next_free; // The next record to allocate from size_t used; // MFT valid size in records. u32 recs_mirr; // Number of records in MFTMirr u8 next_reserved; u8 reserved_bitmap_inited; } mft; struct { struct wnd_bitmap bitmap; // $Bitmap::Data CLST next_free_lcn; } used; struct { u64 size; // In bytes. u64 blocks; // In blocks. u64 ser_num; struct ntfs_inode *ni; __le16 flags; // Cached current VOLUME_INFO::flags, VOLUME_FLAG_DIRTY. u8 major_ver; u8 minor_ver; char label[256]; bool real_dirty; // Real fs state. } volume; struct { struct ntfs_index index_sii; struct ntfs_index index_sdh; struct ntfs_inode *ni; u32 next_id; u64 next_off; __le32 def_security_id; } security; struct { struct ntfs_index index_r; struct ntfs_inode *ni; u64 max_size; // 16K } reparse; struct { struct ntfs_index index_o; struct ntfs_inode *ni; } objid; struct { struct mutex mtx_lznt; struct lznt *lznt; #ifdef CONFIG_NTFS3_LZX_XPRESS struct mutex mtx_xpress; struct xpress_decompressor *xpress; struct mutex mtx_lzx; struct lzx_decompressor *lzx; #endif } compress; struct ntfs_mount_options *options; struct ratelimit_state msg_ratelimit; struct proc_dir_entry *procdir; }; /* One MFT record(usually 1024 bytes), consists of attributes. */ struct mft_inode { struct rb_node node; struct ntfs_sb_info *sbi; struct MFT_REC *mrec; struct ntfs_buffers nb; CLST rno; bool dirty; }; /* Nested class for ntfs_inode::ni_lock. */ enum ntfs_inode_mutex_lock_class { NTFS_INODE_MUTEX_DIRTY = 1, NTFS_INODE_MUTEX_SECURITY, NTFS_INODE_MUTEX_OBJID, NTFS_INODE_MUTEX_REPARSE, NTFS_INODE_MUTEX_NORMAL, NTFS_INODE_MUTEX_PARENT, NTFS_INODE_MUTEX_PARENT2, }; /* * struct ntfs_inode * * Ntfs inode - extends linux inode. consists of one or more MFT inodes. */ struct ntfs_inode { struct mft_inode mi; // base record /* * Valid size: [0 - i_valid) - these range in file contains valid data. * Range [i_valid - inode->i_size) - contains 0. * Usually i_valid <= inode->i_size. */ u64 i_valid; struct timespec64 i_crtime; struct mutex ni_lock; /* File attributes from std. */ enum FILE_ATTRIBUTE std_fa; __le32 std_security_id; /* * Tree of mft_inode. * Not empty when primary MFT record (usually 1024 bytes) can't save all attributes * e.g. file becomes too fragmented or contains a lot of names. */ struct rb_root mi_tree; /* * This member is used in ntfs_readdir to ensure that all subrecords are loaded */ u8 mi_loaded; /* * Use this field to avoid any write(s). * If inode is bad during initialization - use make_bad_inode * If inode is bad during operations - use this field */ u8 ni_bad; union { struct ntfs_index dir; struct { struct rw_semaphore run_lock; struct runs_tree run; #ifdef CONFIG_NTFS3_LZX_XPRESS struct folio *offs_folio; #endif } file; }; struct { struct runs_tree run; struct ATTR_LIST_ENTRY *le; // 1K aligned memory. size_t size; bool dirty; } attr_list; size_t ni_flags; // NI_FLAG_XXX struct inode vfs_inode; }; struct indx_node { struct ntfs_buffers nb; struct INDEX_BUFFER *index; }; struct ntfs_fnd { int level; struct indx_node *nodes[20]; struct NTFS_DE *de[20]; struct NTFS_DE *root_de; }; enum REPARSE_SIGN { REPARSE_NONE = 0, REPARSE_COMPRESSED = 1, REPARSE_DEDUPLICATED = 2, REPARSE_LINK = 3 }; /* Functions from attrib.c */ int attr_allocate_clusters(struct ntfs_sb_info *sbi, struct runs_tree *run, CLST vcn, CLST lcn, CLST len, CLST *pre_alloc, enum ALLOCATE_OPT opt, CLST *alen, const size_t fr, CLST *new_lcn, CLST *new_len); int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr, struct ATTR_LIST_ENTRY *le, struct mft_inode *mi, u64 new_size, struct runs_tree *run, struct ATTRIB **ins_attr, struct page *page); int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct runs_tree *run, u64 new_size, const u64 *new_valid, bool keep_prealloc, struct ATTRIB **ret); int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn, CLST *len, bool *new, bool zero); int attr_data_read_resident(struct ntfs_inode *ni, struct folio *folio); int attr_data_write_resident(struct ntfs_inode *ni, struct folio *folio); int attr_load_runs_vcn(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct runs_tree *run, CLST vcn); int attr_load_runs_range(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct runs_tree *run, u64 from, u64 to); int attr_wof_frame_info(struct ntfs_inode *ni, struct ATTRIB *attr, struct runs_tree *run, u64 frame, u64 frames, u8 frame_bits, u32 *ondisk_size, u64 *vbo_data); int attr_is_frame_compressed(struct ntfs_inode *ni, struct ATTRIB *attr, CLST frame, CLST *clst_data, struct runs_tree *run); int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size, u64 new_valid); int attr_collapse_range(struct ntfs_inode *ni, u64 vbo, u64 bytes); int attr_insert_range(struct ntfs_inode *ni, u64 vbo, u64 bytes); int attr_punch_hole(struct ntfs_inode *ni, u64 vbo, u64 bytes, u32 *frame_size); int attr_force_nonresident(struct ntfs_inode *ni); /* Functions from attrlist.c */ void al_destroy(struct ntfs_inode *ni); bool al_verify(struct ntfs_inode *ni); int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr); struct ATTR_LIST_ENTRY *al_enumerate(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le); struct ATTR_LIST_ENTRY *al_find_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, const struct ATTRIB *attr); struct ATTR_LIST_ENTRY *al_find_ex(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le, enum ATTR_TYPE type, const __le16 *name, u8 name_len, const CLST *vcn); int al_add_le(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, CLST svcn, __le16 id, const struct MFT_REF *ref, struct ATTR_LIST_ENTRY **new_le); bool al_remove_le(struct ntfs_inode *ni, struct ATTR_LIST_ENTRY *le); int al_update(struct ntfs_inode *ni, int sync); static inline size_t al_aligned(size_t size) { return size_add(size, 1023) & ~(size_t)1023; } /* Globals from bitfunc.c */ bool are_bits_clear(const void *map, size_t bit, size_t nbits); bool are_bits_set(const void *map, size_t bit, size_t nbits); size_t get_set_bits_ex(const void *map, size_t bit, size_t nbits); /* Globals from dir.c */ int ntfs_utf16_to_nls(struct ntfs_sb_info *sbi, const __le16 *name, u32 len, u8 *buf, int buf_len); int ntfs_nls_to_utf16(struct ntfs_sb_info *sbi, const u8 *name, u32 name_len, struct cpu_str *uni, u32 max_ulen, enum utf16_endian endian); struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni, struct ntfs_fnd *fnd); bool dir_is_empty(struct inode *dir); extern const struct file_operations ntfs_dir_operations; extern const struct file_operations ntfs_legacy_dir_operations; /* Globals from file.c */ int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, u32 flags); int ntfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); int ntfs_file_open(struct inode *inode, struct file *file); int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); long ntfs_ioctl(struct file *filp, u32 cmd, unsigned long arg); long ntfs_compat_ioctl(struct file *filp, u32 cmd, unsigned long arg); extern const struct inode_operations ntfs_special_inode_operations; extern const struct inode_operations ntfs_file_inode_operations; extern const struct file_operations ntfs_file_operations; extern const struct file_operations ntfs_legacy_file_operations; /* Globals from frecord.c */ void ni_remove_mi(struct ntfs_inode *ni, struct mft_inode *mi); struct ATTR_STD_INFO *ni_std(struct ntfs_inode *ni); struct ATTR_STD_INFO5 *ni_std5(struct ntfs_inode *ni); void ni_clear(struct ntfs_inode *ni); int ni_load_mi_ex(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi); int ni_load_mi(struct ntfs_inode *ni, const struct ATTR_LIST_ENTRY *le, struct mft_inode **mi); struct ATTRIB *ni_find_attr(struct ntfs_inode *ni, struct ATTRIB *attr, struct ATTR_LIST_ENTRY **entry_o, enum ATTR_TYPE type, const __le16 *name, u8 name_len, const CLST *vcn, struct mft_inode **mi); struct ATTRIB *ni_enum_attr_ex(struct ntfs_inode *ni, struct ATTRIB *attr, struct ATTR_LIST_ENTRY **le, struct mft_inode **mi); int ni_load_all_mi(struct ntfs_inode *ni); bool ni_add_subrecord(struct ntfs_inode *ni, CLST rno, struct mft_inode **mi); int ni_remove_attr(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, bool base_only, const __le16 *id); int ni_create_attr_list(struct ntfs_inode *ni); int ni_expand_list(struct ntfs_inode *ni); int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type, const __le16 *name, u8 name_len, const struct runs_tree *run, CLST svcn, CLST len, __le16 flags, struct ATTRIB **new_attr, struct mft_inode **mi, struct ATTR_LIST_ENTRY **le); int ni_insert_resident(struct ntfs_inode *ni, u32 data_size, enum ATTR_TYPE type, const __le16 *name, u8 name_len, struct ATTRIB **new_attr, struct mft_inode **mi, struct ATTR_LIST_ENTRY **le); void ni_remove_attr_le(struct ntfs_inode *ni, struct ATTRIB *attr, struct mft_inode *mi, struct ATTR_LIST_ENTRY *le); int ni_delete_all(struct ntfs_inode *ni); struct ATTR_FILE_NAME *ni_fname_name(struct ntfs_inode *ni, const struct le_str *uni, const struct MFT_REF *home, struct mft_inode **mi, struct ATTR_LIST_ENTRY **entry); struct ATTR_FILE_NAME *ni_fname_type(struct ntfs_inode *ni, u8 name_type, struct mft_inode **mi, struct ATTR_LIST_ENTRY **entry); int ni_new_attr_flags(struct ntfs_inode *ni, enum FILE_ATTRIBUTE new_fa); enum REPARSE_SIGN ni_parse_reparse(struct ntfs_inode *ni, struct ATTRIB *attr, struct REPARSE_DATA_BUFFER *buffer); int ni_write_inode(struct inode *inode, int sync, const char *hint); #define _ni_write_inode(i, w) ni_write_inode(i, w, __func__) int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo, __u64 vbo, __u64 len); int ni_readpage_cmpr(struct ntfs_inode *ni, struct folio *folio); int ni_decompress_file(struct ntfs_inode *ni); int ni_read_frame(struct ntfs_inode *ni, u64 frame_vbo, struct page **pages, u32 pages_per_frame); int ni_write_frame(struct ntfs_inode *ni, struct page **pages, u32 pages_per_frame); int ni_remove_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, struct NTFS_DE *de, struct NTFS_DE **de2, int *undo_step); bool ni_remove_name_undo(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, struct NTFS_DE *de, struct NTFS_DE *de2, int undo_step); int ni_add_name(struct ntfs_inode *dir_ni, struct ntfs_inode *ni, struct NTFS_DE *de); int ni_rename(struct ntfs_inode *dir_ni, struct ntfs_inode *new_dir_ni, struct ntfs_inode *ni, struct NTFS_DE *de, struct NTFS_DE *new_de); bool ni_is_dirty(struct inode *inode); /* Globals from fslog.c */ bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes); int log_replay(struct ntfs_inode *ni, bool *initialized); /* Globals from fsntfs.c */ struct buffer_head *ntfs_bread(struct super_block *sb, sector_t block); bool ntfs_fix_pre_write(struct NTFS_RECORD_HEADER *rhdr, size_t bytes); int ntfs_fix_post_read(struct NTFS_RECORD_HEADER *rhdr, size_t bytes, bool simple); int ntfs_extend_init(struct ntfs_sb_info *sbi); int ntfs_loadlog_and_replay(struct ntfs_inode *ni, struct ntfs_sb_info *sbi); int ntfs_look_for_free_space(struct ntfs_sb_info *sbi, CLST lcn, CLST len, CLST *new_lcn, CLST *new_len, enum ALLOCATE_OPT opt); bool ntfs_check_for_free_space(struct ntfs_sb_info *sbi, CLST clen, CLST mlen); int ntfs_look_free_mft(struct ntfs_sb_info *sbi, CLST *rno, bool mft, struct ntfs_inode *ni, struct mft_inode **mi); void ntfs_mark_rec_free(struct ntfs_sb_info *sbi, CLST rno, bool is_mft); int ntfs_clear_mft_tail(struct ntfs_sb_info *sbi, size_t from, size_t to); int ntfs_refresh_zone(struct ntfs_sb_info *sbi); void ntfs_update_mftmirr(struct ntfs_sb_info *sbi, int wait); void ntfs_bad_inode(struct inode *inode, const char *hint); #define _ntfs_bad_inode(i) ntfs_bad_inode(i, __func__) enum NTFS_DIRTY_FLAGS { NTFS_DIRTY_CLEAR = 0, NTFS_DIRTY_DIRTY = 1, NTFS_DIRTY_ERROR = 2, }; int ntfs_set_state(struct ntfs_sb_info *sbi, enum NTFS_DIRTY_FLAGS dirty); int ntfs_sb_write(struct super_block *sb, u64 lbo, size_t bytes, const void *buffer, int wait); int ntfs_sb_write_run(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, const void *buf, size_t bytes, int sync); struct buffer_head *ntfs_bread_run(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo); int ntfs_read_run_nb(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, void *buf, u32 bytes, struct ntfs_buffers *nb); int ntfs_read_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, struct NTFS_RECORD_HEADER *rhdr, u32 bytes, struct ntfs_buffers *nb); int ntfs_get_bh(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, u32 bytes, struct ntfs_buffers *nb); int ntfs_write_bh(struct ntfs_sb_info *sbi, struct NTFS_RECORD_HEADER *rhdr, struct ntfs_buffers *nb, int sync); int ntfs_bio_pages(struct ntfs_sb_info *sbi, const struct runs_tree *run, struct page **pages, u32 nr_pages, u64 vbo, u32 bytes, enum req_op op); int ntfs_bio_fill_1(struct ntfs_sb_info *sbi, const struct runs_tree *run); int ntfs_vbo_to_lbo(struct ntfs_sb_info *sbi, const struct runs_tree *run, u64 vbo, u64 *lbo, u64 *bytes); struct ntfs_inode *ntfs_new_inode(struct ntfs_sb_info *sbi, CLST nRec, enum RECORD_FLAG flag); extern const u8 s_default_security[0x50]; bool is_sd_valid(const struct SECURITY_DESCRIPTOR_RELATIVE *sd, u32 len); int ntfs_security_init(struct ntfs_sb_info *sbi); int ntfs_get_security_by_id(struct ntfs_sb_info *sbi, __le32 security_id, struct SECURITY_DESCRIPTOR_RELATIVE **sd, size_t *size); int ntfs_insert_security(struct ntfs_sb_info *sbi, const struct SECURITY_DESCRIPTOR_RELATIVE *sd, u32 size, __le32 *security_id, bool *inserted); int ntfs_reparse_init(struct ntfs_sb_info *sbi); int ntfs_objid_init(struct ntfs_sb_info *sbi); int ntfs_objid_remove(struct ntfs_sb_info *sbi, struct GUID *guid); int ntfs_insert_reparse(struct ntfs_sb_info *sbi, __le32 rtag, const struct MFT_REF *ref); int ntfs_remove_reparse(struct ntfs_sb_info *sbi, __le32 rtag, const struct MFT_REF *ref); void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim); int run_deallocate(struct ntfs_sb_info *sbi, const struct runs_tree *run, bool trim); bool valid_windows_name(struct ntfs_sb_info *sbi, const struct le_str *name); int ntfs_set_label(struct ntfs_sb_info *sbi, u8 *label, int len); /* Globals from index.c */ int indx_used_bit(struct ntfs_index *indx, struct ntfs_inode *ni, size_t *bit); void fnd_clear(struct ntfs_fnd *fnd); static inline struct ntfs_fnd *fnd_get(void) { return kzalloc(sizeof(struct ntfs_fnd), GFP_NOFS); } static inline void fnd_put(struct ntfs_fnd *fnd) { if (fnd) { fnd_clear(fnd); kfree(fnd); } } void indx_clear(struct ntfs_index *idx); int indx_init(struct ntfs_index *indx, struct ntfs_sb_info *sbi, const struct ATTRIB *attr, enum index_mutex_classed type); struct INDEX_ROOT *indx_get_root(struct ntfs_index *indx, struct ntfs_inode *ni, struct ATTRIB **attr, struct mft_inode **mi); int indx_read(struct ntfs_index *idx, struct ntfs_inode *ni, CLST vbn, struct indx_node **node); int indx_find(struct ntfs_index *indx, struct ntfs_inode *dir, const struct INDEX_ROOT *root, const void *Key, size_t KeyLen, const void *param, int *diff, struct NTFS_DE **entry, struct ntfs_fnd *fnd); int indx_find_sort(struct ntfs_index *indx, struct ntfs_inode *ni, const struct INDEX_ROOT *root, struct NTFS_DE **entry, struct ntfs_fnd *fnd); int indx_find_raw(struct ntfs_index *indx, struct ntfs_inode *ni, const struct INDEX_ROOT *root, struct NTFS_DE **entry, size_t *off, struct ntfs_fnd *fnd); int indx_insert_entry(struct ntfs_index *indx, struct ntfs_inode *ni, const struct NTFS_DE *new_de, const void *param, struct ntfs_fnd *fnd, bool undo); int indx_delete_entry(struct ntfs_index *indx, struct ntfs_inode *ni, const void *key, u32 key_len, const void *param); int indx_update_dup(struct ntfs_inode *ni, struct ntfs_sb_info *sbi, const struct ATTR_FILE_NAME *fname, const struct NTFS_DUP_INFO *dup, int sync); /* Globals from inode.c */ struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref, const struct cpu_str *name); int ntfs_set_size(struct inode *inode, u64 new_size); int ntfs_get_block(struct inode *inode, sector_t vbn, struct buffer_head *bh_result, int create); int ntfs_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, u32 len, struct folio **foliop, void **fsdata); int ntfs_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, u32 len, u32 copied, struct folio *folio, void *fsdata); int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc); int ntfs_sync_inode(struct inode *inode); int inode_read_data(struct inode *inode, void *data, size_t bytes); int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const struct cpu_str *uni, umode_t mode, dev_t dev, const char *symname, u32 size, struct ntfs_fnd *fnd); int ntfs_link_inode(struct inode *inode, struct dentry *dentry); int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry); void ntfs_evict_inode(struct inode *inode); extern const struct inode_operations ntfs_link_inode_operations; extern const struct address_space_operations ntfs_aops; extern const struct address_space_operations ntfs_aops_cmpr; /* Globals from name_i.c */ int fill_name_de(struct ntfs_sb_info *sbi, void *buf, const struct qstr *name, const struct cpu_str *uni); struct dentry *ntfs3_get_parent(struct dentry *child); extern const struct inode_operations ntfs_dir_inode_operations; extern const struct inode_operations ntfs_special_inode_operations; extern const struct dentry_operations ntfs_dentry_ops; /* Globals from record.c */ int mi_get(struct ntfs_sb_info *sbi, CLST rno, struct mft_inode **mi); void mi_put(struct mft_inode *mi); int mi_init(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno); int mi_read(struct mft_inode *mi, bool is_mft); struct ATTRIB *mi_enum_attr(struct ntfs_inode *ni, struct mft_inode *mi, struct ATTRIB *attr); struct ATTRIB *mi_find_attr(struct ntfs_inode *ni, struct mft_inode *mi, struct ATTRIB *attr, enum ATTR_TYPE type, const __le16 *name, u8 name_len, const __le16 *id); static inline struct ATTRIB *rec_find_attr_le(struct ntfs_inode *ni, struct mft_inode *rec, struct ATTR_LIST_ENTRY *le) { return mi_find_attr(ni, rec, NULL, le->type, le_name(le), le->name_len, &le->id); } int mi_write(struct mft_inode *mi, int wait); int mi_format_new(struct mft_inode *mi, struct ntfs_sb_info *sbi, CLST rno, __le16 flags, bool is_mft); struct ATTRIB *mi_insert_attr(struct ntfs_inode *ni, struct mft_inode *mi, enum ATTR_TYPE type, const __le16 *name, u8 name_len, u32 asize, u16 name_off); bool mi_remove_attr(struct ntfs_inode *ni, struct mft_inode *mi, struct ATTRIB *attr); bool mi_resize_attr(struct mft_inode *mi, struct ATTRIB *attr, int bytes); int mi_pack_runs(struct mft_inode *mi, struct ATTRIB *attr, struct runs_tree *run, CLST len); static inline bool mi_is_ref(const struct mft_inode *mi, const struct MFT_REF *ref) { if (le32_to_cpu(ref->low) != mi->rno) return false; if (ref->seq != mi->mrec->seq) return false; #ifdef CONFIG_NTFS3_64BIT_CLUSTER return le16_to_cpu(ref->high) == (mi->rno >> 32); #else return !ref->high; #endif } static inline void mi_get_ref(const struct mft_inode *mi, struct MFT_REF *ref) { ref->low = cpu_to_le32(mi->rno); #ifdef CONFIG_NTFS3_64BIT_CLUSTER ref->high = cpu_to_le16(mi->rno >> 32); #else ref->high = 0; #endif ref->seq = mi->mrec->seq; } /* Globals from run.c */ bool run_lookup_entry(const struct runs_tree *run, CLST vcn, CLST *lcn, CLST *len, size_t *index); void run_truncate(struct runs_tree *run, CLST vcn); void run_truncate_head(struct runs_tree *run, CLST vcn); void run_truncate_around(struct runs_tree *run, CLST vcn); bool run_add_entry(struct runs_tree *run, CLST vcn, CLST lcn, CLST len, bool is_mft); bool run_collapse_range(struct runs_tree *run, CLST vcn, CLST len); bool run_insert_range(struct runs_tree *run, CLST vcn, CLST len); bool run_get_entry(const struct runs_tree *run, size_t index, CLST *vcn, CLST *lcn, CLST *len); bool run_is_mapped_full(const struct runs_tree *run, CLST svcn, CLST evcn); int run_pack(const struct runs_tree *run, CLST svcn, CLST len, u8 *run_buf, u32 run_buf_size, CLST *packed_vcns); int run_unpack(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, CLST svcn, CLST evcn, CLST vcn, const u8 *run_buf, int run_buf_size); #ifdef NTFS3_CHECK_FREE_CLST int run_unpack_ex(struct runs_tree *run, struct ntfs_sb_info *sbi, CLST ino, CLST svcn, CLST evcn, CLST vcn, const u8 *run_buf, int run_buf_size); #else #define run_unpack_ex run_unpack #endif int run_get_highest_vcn(CLST vcn, const u8 *run_buf, u64 *highest_vcn); int run_clone(const struct runs_tree *run, struct runs_tree *new_run); /* Globals from super.c */ void *ntfs_set_shared(void *ptr, u32 bytes); void *ntfs_put_shared(void *ptr); void ntfs_unmap_meta(struct super_block *sb, CLST lcn, CLST len); int ntfs_discard(struct ntfs_sb_info *sbi, CLST Lcn, CLST Len); /* Globals from bitmap.c*/ int __init ntfs3_init_bitmap(void); void ntfs3_exit_bitmap(void); void wnd_close(struct wnd_bitmap *wnd); static inline size_t wnd_zeroes(const struct wnd_bitmap *wnd) { return wnd->total_zeroes; } int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits); int wnd_set_free(struct wnd_bitmap *wnd, size_t bit, size_t bits); int wnd_set_used(struct wnd_bitmap *wnd, size_t bit, size_t bits); int wnd_set_used_safe(struct wnd_bitmap *wnd, size_t bit, size_t bits, size_t *done); bool wnd_is_free(struct wnd_bitmap *wnd, size_t bit, size_t bits); bool wnd_is_used(struct wnd_bitmap *wnd, size_t bit, size_t bits); /* Possible values for 'flags' 'wnd_find'. */ #define BITMAP_FIND_MARK_AS_USED 0x01 #define BITMAP_FIND_FULL 0x02 size_t wnd_find(struct wnd_bitmap *wnd, size_t to_alloc, size_t hint, size_t flags, size_t *allocated); int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits); void wnd_zone_set(struct wnd_bitmap *wnd, size_t Lcn, size_t Len); int ntfs_trim_fs(struct ntfs_sb_info *sbi, struct fstrim_range *range); void ntfs_bitmap_set_le(void *map, unsigned int start, int len); void ntfs_bitmap_clear_le(void *map, unsigned int start, int len); unsigned int ntfs_bitmap_weight_le(const void *bitmap, int bits); /* Globals from upcase.c */ int ntfs_cmp_names(const __le16 *s1, size_t l1, const __le16 *s2, size_t l2, const u16 *upcase, bool bothcase); int ntfs_cmp_names_cpu(const struct cpu_str *uni1, const struct le_str *uni2, const u16 *upcase, bool bothcase); unsigned long ntfs_names_hash(const u16 *name, size_t len, const u16 *upcase, unsigned long hash); /* globals from xattr.c */ #ifdef CONFIG_NTFS3_FS_POSIX_ACL struct posix_acl *ntfs_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, int type); int ntfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, struct posix_acl *acl, int type); int ntfs_init_acl(struct mnt_idmap *idmap, struct inode *inode, struct inode *dir); #else #define ntfs_get_acl NULL #define ntfs_set_acl NULL #endif int ntfs_acl_chmod(struct mnt_idmap *idmap, struct dentry *dentry); ssize_t ntfs_listxattr(struct dentry *dentry, char *buffer, size_t size); extern const struct xattr_handler *const ntfs_xattr_handlers[]; int ntfs_save_wsl_perm(struct inode *inode, __le32 *ea_size); void ntfs_get_wsl_perm(struct inode *inode); /* globals from lznt.c */ struct lznt *get_lznt_ctx(int level); size_t compress_lznt(const void *uncompressed, size_t uncompressed_size, void *compressed, size_t compressed_size, struct lznt *ctx); ssize_t decompress_lznt(const void *compressed, size_t compressed_size, void *uncompressed, size_t uncompressed_size); static inline bool is_ntfs3(struct ntfs_sb_info *sbi) { return sbi->volume.major_ver >= 3; } /* (sb->s_flags & SB_ACTIVE) */ static inline bool is_mounted(struct ntfs_sb_info *sbi) { return !!sbi->sb->s_root; } static inline bool ntfs_is_meta_file(struct ntfs_sb_info *sbi, CLST rno) { return rno < MFT_REC_FREE || rno == sbi->objid_no || rno == sbi->quota_no || rno == sbi->reparse_no || rno == sbi->usn_jrnl_no; } static inline size_t wnd_zone_bit(const struct wnd_bitmap *wnd) { return wnd->zone_bit; } static inline size_t wnd_zone_len(const struct wnd_bitmap *wnd) { return wnd->zone_end - wnd->zone_bit; } static inline void run_init(struct runs_tree *run) { run->runs = NULL; run->count = 0; run->allocated = 0; } static inline struct runs_tree *run_alloc(void) { return kzalloc(sizeof(struct runs_tree), GFP_NOFS); } static inline void run_close(struct runs_tree *run) { kvfree(run->runs); memset(run, 0, sizeof(*run)); } static inline void run_free(struct runs_tree *run) { if (run) { kvfree(run->runs); kfree(run); } } static inline bool run_is_empty(struct runs_tree *run) { return !run->count; } /* NTFS uses quad aligned bitmaps. */ static inline size_t ntfs3_bitmap_size(size_t bits) { return BITS_TO_U64(bits) * sizeof(u64); } #define _100ns2seconds 10000000 #define SecondsToStartOf1970 0x00000002B6109100 #define NTFS_TIME_GRAN 100 /* * kernel2nt - Converts in-memory kernel timestamp into nt time. */ static inline __le64 kernel2nt(const struct timespec64 *ts) { // 10^7 units of 100 nanoseconds one second return cpu_to_le64(_100ns2seconds * (ts->tv_sec + SecondsToStartOf1970) + ts->tv_nsec / NTFS_TIME_GRAN); } /* * nt2kernel - Converts on-disk nt time into kernel timestamp. */ static inline void nt2kernel(const __le64 tm, struct timespec64 *ts) { u64 t = le64_to_cpu(tm) - _100ns2seconds * SecondsToStartOf1970; // WARNING: do_div changes its first argument(!) ts->tv_nsec = do_div(t, _100ns2seconds) * 100; ts->tv_sec = t; } static inline struct ntfs_sb_info *ntfs_sb(struct super_block *sb) { return sb->s_fs_info; } static inline int ntfs3_forced_shutdown(struct super_block *sb) { return test_bit(NTFS_FLAGS_SHUTDOWN_BIT, &ntfs_sb(sb)->flags); } /* * ntfs_up_cluster - Align up on cluster boundary. */ static inline u64 ntfs_up_cluster(const struct ntfs_sb_info *sbi, u64 size) { return (size + sbi->cluster_mask) & sbi->cluster_mask_inv; } /* * ntfs_up_block - Align up on cluster boundary. */ static inline u64 ntfs_up_block(const struct super_block *sb, u64 size) { return (size + sb->s_blocksize - 1) & ~(u64)(sb->s_blocksize - 1); } static inline CLST bytes_to_cluster(const struct ntfs_sb_info *sbi, u64 size) { return (size + sbi->cluster_mask) >> sbi->cluster_bits; } static inline u64 bytes_to_block(const struct super_block *sb, u64 size) { return (size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; } static inline struct ntfs_inode *ntfs_i(struct inode *inode) { return container_of(inode, struct ntfs_inode, vfs_inode); } static inline bool is_compressed(const struct ntfs_inode *ni) { return (ni->std_fa & FILE_ATTRIBUTE_COMPRESSED) || (ni->ni_flags & NI_FLAG_COMPRESSED_MASK); } static inline bool is_bad_ni(const struct ntfs_inode *ni) { return ni->ni_bad; } static inline int ni_ext_compress_bits(const struct ntfs_inode *ni) { return 0xb + (ni->ni_flags & NI_FLAG_COMPRESSED_MASK); } /* Bits - 0xc, 0xd, 0xe, 0xf, 0x10 */ static inline void ni_set_ext_compress_bits(struct ntfs_inode *ni, u8 bits) { ni->ni_flags |= (bits - 0xb) & NI_FLAG_COMPRESSED_MASK; } static inline bool is_dedup(const struct ntfs_inode *ni) { return ni->ni_flags & NI_FLAG_DEDUPLICATED; } static inline bool is_encrypted(const struct ntfs_inode *ni) { return ni->std_fa & FILE_ATTRIBUTE_ENCRYPTED; } static inline bool is_sparsed(const struct ntfs_inode *ni) { return ni->std_fa & FILE_ATTRIBUTE_SPARSE_FILE; } static inline int is_resident(struct ntfs_inode *ni) { return ni->ni_flags & NI_FLAG_RESIDENT; } static inline void le16_sub_cpu(__le16 *var, u16 val) { *var = cpu_to_le16(le16_to_cpu(*var) - val); } static inline void le32_sub_cpu(__le32 *var, u32 val) { *var = cpu_to_le32(le32_to_cpu(*var) - val); } static inline void nb_put(struct ntfs_buffers *nb) { u32 i, nbufs = nb->nbufs; if (!nbufs) return; for (i = 0; i < nbufs; i++) put_bh(nb->bh[i]); nb->nbufs = 0; } static inline void put_indx_node(struct indx_node *in) { if (!in) return; kfree(in->index); nb_put(&in->nb); kfree(in); } static inline void mi_clear(struct mft_inode *mi) { nb_put(&mi->nb); kfree(mi->mrec); mi->mrec = NULL; } static inline void ni_lock(struct ntfs_inode *ni) { mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_NORMAL); } static inline void ni_lock_dir(struct ntfs_inode *ni) { mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_PARENT); } static inline void ni_lock_dir2(struct ntfs_inode *ni) { mutex_lock_nested(&ni->ni_lock, NTFS_INODE_MUTEX_PARENT2); } static inline void ni_unlock(struct ntfs_inode *ni) { mutex_unlock(&ni->ni_lock); } static inline int ni_trylock(struct ntfs_inode *ni) { return mutex_trylock(&ni->ni_lock); } static inline int attr_load_runs_attr(struct ntfs_inode *ni, struct ATTRIB *attr, struct runs_tree *run, CLST vcn) { return attr_load_runs_vcn(ni, attr->type, attr_name(attr), attr->name_len, run, vcn); } static inline void le64_sub_cpu(__le64 *var, u64 val) { *var = cpu_to_le64(le64_to_cpu(*var) - val); } #if IS_ENABLED(CONFIG_NTFS_FS) bool is_legacy_ntfs(struct super_block *sb); #else static inline bool is_legacy_ntfs(struct super_block *sb) { return false; } #endif #endif /* _LINUX_NTFS3_NTFS_FS_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Verification of builtin signatures * * Copyright 2019 Google LLC */ /* * This file implements verification of fs-verity builtin signatures. Please * take great care before using this feature. It is not the only way to do * signatures with fs-verity, and the alternatives (such as userspace signature * verification, and IMA appraisal) can be much better. For details about the * limitations of this feature, see Documentation/filesystems/fsverity.rst. */ #include "fsverity_private.h" #include <linux/cred.h> #include <linux/key.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/verification.h> /* * /proc/sys/fs/verity/require_signatures * If 1, all verity files must have a valid builtin signature. */ int fsverity_require_signatures; /* * Keyring that contains the trusted X.509 certificates. * * Only root (kuid=0) can modify this. Also, root may use * keyctl_restrict_keyring() to prevent any more additions. */ static struct key *fsverity_keyring; /** * fsverity_verify_signature() - check a verity file's signature * @vi: the file's fsverity_info * @signature: the file's built-in signature * @sig_size: size of signature in bytes, or 0 if no signature * * If the file includes a signature of its fs-verity file digest, verify it * against the certificates in the fs-verity keyring. Note that signatures * are verified regardless of the state of the 'fsverity_require_signatures' * variable and the LSM subsystem relies on this behavior to help enforce * file integrity policies. Please discuss changes with the LSM list * (thank you!). * * Return: 0 on success (signature valid or not required); -errno on failure */ int fsverity_verify_signature(const struct fsverity_info *vi, const u8 *signature, size_t sig_size) { const struct inode *inode = vi->inode; const struct fsverity_hash_alg *hash_alg = vi->tree_params.hash_alg; struct fsverity_formatted_digest *d; int err; if (sig_size == 0) { if (fsverity_require_signatures) { fsverity_err(inode, "require_signatures=1, rejecting unsigned file!"); return -EPERM; } return 0; } if (fsverity_keyring->keys.nr_leaves_on_tree == 0) { /* * The ".fs-verity" keyring is empty, due to builtin signatures * being supported by the kernel but not actually being used. * In this case, verify_pkcs7_signature() would always return an * error, usually ENOKEY. It could also be EBADMSG if the * PKCS#7 is malformed, but that isn't very important to * distinguish. So, just skip to ENOKEY to avoid the attack * surface of the PKCS#7 parser, which would otherwise be * reachable by any task able to execute FS_IOC_ENABLE_VERITY. */ fsverity_err(inode, "fs-verity keyring is empty, rejecting signed file!"); return -ENOKEY; } d = kzalloc(sizeof(*d) + hash_alg->digest_size, GFP_KERNEL); if (!d) return -ENOMEM; memcpy(d->magic, "FSVerity", 8); d->digest_algorithm = cpu_to_le16(hash_alg - fsverity_hash_algs); d->digest_size = cpu_to_le16(hash_alg->digest_size); memcpy(d->digest, vi->file_digest, hash_alg->digest_size); err = verify_pkcs7_signature(d, sizeof(*d) + hash_alg->digest_size, signature, sig_size, fsverity_keyring, VERIFYING_UNSPECIFIED_SIGNATURE, NULL, NULL); kfree(d); if (err) { if (err == -ENOKEY) fsverity_err(inode, "File's signing cert isn't in the fs-verity keyring"); else if (err == -EKEYREJECTED) fsverity_err(inode, "Incorrect file signature"); else if (err == -EBADMSG) fsverity_err(inode, "Malformed file signature"); else fsverity_err(inode, "Error %d verifying file signature", err); return err; } err = security_inode_setintegrity(inode, LSM_INT_FSVERITY_BUILTINSIG_VALID, signature, sig_size); if (err) { fsverity_err(inode, "Error %d exposing file signature to LSMs", err); return err; } return 0; } void __init fsverity_init_signature(void) { fsverity_keyring = keyring_alloc(".fs-verity", KUIDT_INIT(0), KGIDT_INIT(0), current_cred(), KEY_POS_SEARCH | KEY_USR_VIEW | KEY_USR_READ | KEY_USR_WRITE | KEY_USR_SEARCH | KEY_USR_SETATTR, KEY_ALLOC_NOT_IN_QUOTA, NULL, NULL); if (IS_ERR(fsverity_keyring)) panic("failed to allocate \".fs-verity\" keyring"); } |
| 6 7 6 3 1 6 6 1 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 | /* * videobuf2-core.h - Video Buffer 2 Core Framework * * Copyright (C) 2010 Samsung Electronics * * Author: Pawel Osciak <pawel@osciak.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation. */ #ifndef _MEDIA_VIDEOBUF2_CORE_H #define _MEDIA_VIDEOBUF2_CORE_H #include <linux/mm_types.h> #include <linux/mutex.h> #include <linux/poll.h> #include <linux/dma-buf.h> #include <linux/bitops.h> #include <media/media-request.h> #include <media/frame_vector.h> #define VB2_MAX_FRAME (32) #define VB2_MAX_PLANES (8) /** * enum vb2_memory - type of memory model used to make the buffers visible * on userspace. * * @VB2_MEMORY_UNKNOWN: Buffer status is unknown or it is not used yet on * userspace. * @VB2_MEMORY_MMAP: The buffers are allocated by the Kernel and it is * memory mapped via mmap() ioctl. This model is * also used when the user is using the buffers via * read() or write() system calls. * @VB2_MEMORY_USERPTR: The buffers was allocated in userspace and it is * memory mapped via mmap() ioctl. * @VB2_MEMORY_DMABUF: The buffers are passed to userspace via DMA buffer. */ enum vb2_memory { VB2_MEMORY_UNKNOWN = 0, VB2_MEMORY_MMAP = 1, VB2_MEMORY_USERPTR = 2, VB2_MEMORY_DMABUF = 4, }; struct vb2_fileio_data; struct vb2_threadio_data; struct vb2_buffer; /** * struct vb2_mem_ops - memory handling/memory allocator operations. * @alloc: allocate video memory and, optionally, allocator private data, * return ERR_PTR() on failure or a pointer to allocator private, * per-buffer data on success; the returned private structure * will then be passed as @buf_priv argument to other ops in this * structure. The size argument to this function shall be * *page aligned*. * @put: inform the allocator that the buffer will no longer be used; * usually will result in the allocator freeing the buffer (if * no other users of this buffer are present); the @buf_priv * argument is the allocator private per-buffer structure * previously returned from the alloc callback. * @get_dmabuf: acquire userspace memory for a hardware operation; used for * DMABUF memory types. * @get_userptr: acquire userspace memory for a hardware operation; used for * USERPTR memory types; vaddr is the address passed to the * videobuf2 layer when queuing a video buffer of USERPTR type; * should return an allocator private per-buffer structure * associated with the buffer on success, ERR_PTR() on failure; * the returned private structure will then be passed as @buf_priv * argument to other ops in this structure. * @put_userptr: inform the allocator that a USERPTR buffer will no longer * be used. * @prepare: called every time the buffer is passed from userspace to the * driver, useful for cache synchronisation, optional. * @finish: called every time the buffer is passed back from the driver * to the userspace, also optional. * @attach_dmabuf: attach a shared &struct dma_buf for a hardware operation; * used for DMABUF memory types; dev is the alloc device * dbuf is the shared dma_buf; returns ERR_PTR() on failure; * allocator private per-buffer structure on success; * this needs to be used for further accesses to the buffer. * @detach_dmabuf: inform the exporter of the buffer that the current DMABUF * buffer is no longer used; the @buf_priv argument is the * allocator private per-buffer structure previously returned * from the attach_dmabuf callback. * @map_dmabuf: request for access to the dmabuf from allocator; the allocator * of dmabuf is informed that this driver is going to use the * dmabuf. * @unmap_dmabuf: releases access control to the dmabuf - allocator is notified * that this driver is done using the dmabuf for now. * @vaddr: return a kernel virtual address to a given memory buffer * associated with the passed private structure or NULL if no * such mapping exists. * @cookie: return allocator specific cookie for a given memory buffer * associated with the passed private structure or NULL if not * available. * @num_users: return the current number of users of a memory buffer; * return 1 if the videobuf2 layer (or actually the driver using * it) is the only user. * @mmap: setup a userspace mapping for a given memory buffer under * the provided virtual memory region. * * Those operations are used by the videobuf2 core to implement the memory * handling/memory allocators for each type of supported streaming I/O method. * * .. note:: * #) Required ops for USERPTR types: get_userptr, put_userptr. * * #) Required ops for MMAP types: alloc, put, num_users, mmap. * * #) Required ops for read/write access types: alloc, put, num_users, vaddr. * * #) Required ops for DMABUF types: attach_dmabuf, detach_dmabuf, * map_dmabuf, unmap_dmabuf. */ struct vb2_mem_ops { void *(*alloc)(struct vb2_buffer *vb, struct device *dev, unsigned long size); void (*put)(void *buf_priv); struct dma_buf *(*get_dmabuf)(struct vb2_buffer *vb, void *buf_priv, unsigned long flags); void *(*get_userptr)(struct vb2_buffer *vb, struct device *dev, unsigned long vaddr, unsigned long size); void (*put_userptr)(void *buf_priv); void (*prepare)(void *buf_priv); void (*finish)(void *buf_priv); void *(*attach_dmabuf)(struct vb2_buffer *vb, struct device *dev, struct dma_buf *dbuf, unsigned long size); void (*detach_dmabuf)(void *buf_priv); int (*map_dmabuf)(void *buf_priv); void (*unmap_dmabuf)(void *buf_priv); void *(*vaddr)(struct vb2_buffer *vb, void *buf_priv); void *(*cookie)(struct vb2_buffer *vb, void *buf_priv); unsigned int (*num_users)(void *buf_priv); int (*mmap)(void *buf_priv, struct vm_area_struct *vma); }; /** * struct vb2_plane - plane information. * @mem_priv: private data with this plane. * @dbuf: dma_buf - shared buffer object. * @dbuf_mapped: flag to show whether dbuf is mapped or not * @dbuf_duplicated: boolean to show whether dbuf is duplicated with a * previous plane of the buffer. * @bytesused: number of bytes occupied by data in the plane (payload). * @length: size of this plane (NOT the payload) in bytes. The maximum * valid size is MAX_UINT - PAGE_SIZE. * @min_length: minimum required size of this plane (NOT the payload) in bytes. * @length is always greater or equal to @min_length, and like * @length, it is limited to MAX_UINT - PAGE_SIZE. * @m: Union with memtype-specific data. * @m.offset: when memory in the associated struct vb2_buffer is * %VB2_MEMORY_MMAP, equals the offset from the start of * the device memory for this plane (or is a "cookie" that * should be passed to mmap() called on the video node). * @m.userptr: when memory is %VB2_MEMORY_USERPTR, a userspace pointer * pointing to this plane. * @m.fd: when memory is %VB2_MEMORY_DMABUF, a userspace file * descriptor associated with this plane. * @data_offset: offset in the plane to the start of data; usually 0, * unless there is a header in front of the data. * * Should contain enough information to be able to cover all the fields * of &struct v4l2_plane at videodev2.h. */ struct vb2_plane { void *mem_priv; struct dma_buf *dbuf; unsigned int dbuf_mapped; bool dbuf_duplicated; unsigned int bytesused; unsigned int length; unsigned int min_length; union { unsigned int offset; unsigned long userptr; int fd; } m; unsigned int data_offset; }; /** * enum vb2_io_modes - queue access methods. * @VB2_MMAP: driver supports MMAP with streaming API. * @VB2_USERPTR: driver supports USERPTR with streaming API. * @VB2_READ: driver supports read() style access. * @VB2_WRITE: driver supports write() style access. * @VB2_DMABUF: driver supports DMABUF with streaming API. */ enum vb2_io_modes { VB2_MMAP = BIT(0), VB2_USERPTR = BIT(1), VB2_READ = BIT(2), VB2_WRITE = BIT(3), VB2_DMABUF = BIT(4), }; /** * enum vb2_buffer_state - current video buffer state. * @VB2_BUF_STATE_DEQUEUED: buffer under userspace control. * @VB2_BUF_STATE_IN_REQUEST: buffer is queued in media request. * @VB2_BUF_STATE_PREPARING: buffer is being prepared in videobuf2. * @VB2_BUF_STATE_QUEUED: buffer queued in videobuf2, but not in driver. * @VB2_BUF_STATE_ACTIVE: buffer queued in driver and possibly used * in a hardware operation. * @VB2_BUF_STATE_DONE: buffer returned from driver to videobuf2, but * not yet dequeued to userspace. * @VB2_BUF_STATE_ERROR: same as above, but the operation on the buffer * has ended with an error, which will be reported * to the userspace when it is dequeued. */ enum vb2_buffer_state { VB2_BUF_STATE_DEQUEUED, VB2_BUF_STATE_IN_REQUEST, VB2_BUF_STATE_PREPARING, VB2_BUF_STATE_QUEUED, VB2_BUF_STATE_ACTIVE, VB2_BUF_STATE_DONE, VB2_BUF_STATE_ERROR, }; struct vb2_queue; /** * struct vb2_buffer - represents a video buffer. * @vb2_queue: pointer to &struct vb2_queue with the queue to * which this driver belongs. * @index: id number of the buffer. * @type: buffer type. * @memory: the method, in which the actual data is passed. * @num_planes: number of planes in the buffer * on an internal driver queue. * @timestamp: frame timestamp in ns. * @request: the request this buffer is associated with. * @req_obj: used to bind this buffer to a request. This * request object has a refcount. */ struct vb2_buffer { struct vb2_queue *vb2_queue; unsigned int index; unsigned int type; unsigned int memory; unsigned int num_planes; u64 timestamp; struct media_request *request; struct media_request_object req_obj; /* private: internal use only * * state: current buffer state; do not change * synced: this buffer has been synced for DMA, i.e. the * 'prepare' memop was called. It is cleared again * after the 'finish' memop is called. * prepared: this buffer has been prepared, i.e. the * buf_prepare op was called. It is cleared again * after the 'buf_finish' op is called. * copied_timestamp: the timestamp of this capture buffer was copied * from an output buffer. * skip_cache_sync_on_prepare: when set buffer's ->prepare() function * skips cache sync/invalidation. * skip_cache_sync_on_finish: when set buffer's ->finish() function * skips cache sync/invalidation. * planes: per-plane information; do not change * queued_entry: entry on the queued buffers list, which holds * all buffers queued from userspace * done_entry: entry on the list that stores all buffers ready * to be dequeued to userspace */ enum vb2_buffer_state state; unsigned int synced:1; unsigned int prepared:1; unsigned int copied_timestamp:1; unsigned int skip_cache_sync_on_prepare:1; unsigned int skip_cache_sync_on_finish:1; struct vb2_plane planes[VB2_MAX_PLANES]; struct list_head queued_entry; struct list_head done_entry; #ifdef CONFIG_VIDEO_ADV_DEBUG /* * Counters for how often these buffer-related ops are * called. Used to check for unbalanced ops. */ u32 cnt_mem_alloc; u32 cnt_mem_put; u32 cnt_mem_get_dmabuf; u32 cnt_mem_get_userptr; u32 cnt_mem_put_userptr; u32 cnt_mem_prepare; u32 cnt_mem_finish; u32 cnt_mem_attach_dmabuf; u32 cnt_mem_detach_dmabuf; u32 cnt_mem_map_dmabuf; u32 cnt_mem_unmap_dmabuf; u32 cnt_mem_vaddr; u32 cnt_mem_cookie; u32 cnt_mem_num_users; u32 cnt_mem_mmap; u32 cnt_buf_out_validate; u32 cnt_buf_init; u32 cnt_buf_prepare; u32 cnt_buf_finish; u32 cnt_buf_cleanup; u32 cnt_buf_queue; u32 cnt_buf_request_complete; /* This counts the number of calls to vb2_buffer_done() */ u32 cnt_buf_done; #endif }; /** * struct vb2_ops - driver-specific callbacks. * * These operations are not called from interrupt context except where * mentioned specifically. * * @queue_setup: called from VIDIOC_REQBUFS() and VIDIOC_CREATE_BUFS() * handlers before memory allocation. It can be called * twice: if the original number of requested buffers * could not be allocated, then it will be called a * second time with the actually allocated number of * buffers to verify if that is OK. * The driver should return the required number of buffers * in \*num_buffers, the required number of planes per * buffer in \*num_planes, the size of each plane should be * set in the sizes\[\] array and optional per-plane * allocator specific device in the alloc_devs\[\] array. * When called from VIDIOC_REQBUFS(), \*num_planes == 0, * the driver has to use the currently configured format to * determine the plane sizes and \*num_buffers is the total * number of buffers that are being allocated. When called * from VIDIOC_CREATE_BUFS(), \*num_planes != 0 and it * describes the requested number of planes and sizes\[\] * contains the requested plane sizes. In this case * \*num_buffers are being allocated additionally to * the buffers already allocated. If either \*num_planes * or the requested sizes are invalid callback must return %-EINVAL. * @wait_prepare: release any locks taken while calling vb2 functions; * it is called before an ioctl needs to wait for a new * buffer to arrive; required to avoid a deadlock in * blocking access type. * @wait_finish: reacquire all locks released in the previous callback; * required to continue operation after sleeping while * waiting for a new buffer to arrive. * @buf_out_validate: called when the output buffer is prepared or queued * to a request; drivers can use this to validate * userspace-provided information; this is required only * for OUTPUT queues. * @buf_init: called once after allocating a buffer (in MMAP case) * or after acquiring a new USERPTR buffer; drivers may * perform additional buffer-related initialization; * initialization failure (return != 0) will prevent * queue setup from completing successfully; optional. * @buf_prepare: called every time the buffer is queued from userspace * and from the VIDIOC_PREPARE_BUF() ioctl; drivers may * perform any initialization required before each * hardware operation in this callback; drivers can * access/modify the buffer here as it is still synced for * the CPU; drivers that support VIDIOC_CREATE_BUFS() must * also validate the buffer size; if an error is returned, * the buffer will not be queued in driver; optional. * @buf_finish: called before every dequeue of the buffer back to * userspace; the buffer is synced for the CPU, so drivers * can access/modify the buffer contents; drivers may * perform any operations required before userspace * accesses the buffer; optional. The buffer state can be * one of the following: %DONE and %ERROR occur while * streaming is in progress, and the %PREPARED state occurs * when the queue has been canceled and all pending * buffers are being returned to their default %DEQUEUED * state. Typically you only have to do something if the * state is %VB2_BUF_STATE_DONE, since in all other cases * the buffer contents will be ignored anyway. * @buf_cleanup: called once before the buffer is freed; drivers may * perform any additional cleanup; optional. * @prepare_streaming: called once to prepare for 'streaming' state; this is * where validation can be done to verify everything is * okay and streaming resources can be claimed. It is * called when the VIDIOC_STREAMON ioctl is called. The * actual streaming starts when @start_streaming is called. * Optional. * @start_streaming: called once to enter 'streaming' state; the driver may * receive buffers with @buf_queue callback * before @start_streaming is called; the driver gets the * number of already queued buffers in count parameter; * driver can return an error if hardware fails, in that * case all buffers that have been already given by * the @buf_queue callback are to be returned by the driver * by calling vb2_buffer_done() with %VB2_BUF_STATE_QUEUED. * If you need a minimum number of buffers before you can * start streaming, then set * &vb2_queue->min_queued_buffers. If that is non-zero * then @start_streaming won't be called until at least * that many buffers have been queued up by userspace. * @stop_streaming: called when 'streaming' state must be disabled; driver * should stop any DMA transactions or wait until they * finish and give back all buffers it got from &buf_queue * callback by calling vb2_buffer_done() with either * %VB2_BUF_STATE_DONE or %VB2_BUF_STATE_ERROR; may use * vb2_wait_for_all_buffers() function * @unprepare_streaming:called as counterpart to @prepare_streaming; any claimed * streaming resources can be released here. It is * called when the VIDIOC_STREAMOFF ioctls is called or * when the streaming filehandle is closed. Optional. * @buf_queue: passes buffer vb to the driver; driver may start * hardware operation on this buffer; driver should give * the buffer back by calling vb2_buffer_done() function; * it is always called after calling VIDIOC_STREAMON() * ioctl; might be called before @start_streaming callback * if user pre-queued buffers before calling * VIDIOC_STREAMON(). * @buf_request_complete: a buffer that was never queued to the driver but is * associated with a queued request was canceled. * The driver will have to mark associated objects in the * request as completed; required if requests are * supported. */ struct vb2_ops { int (*queue_setup)(struct vb2_queue *q, unsigned int *num_buffers, unsigned int *num_planes, unsigned int sizes[], struct device *alloc_devs[]); void (*wait_prepare)(struct vb2_queue *q); void (*wait_finish)(struct vb2_queue *q); int (*buf_out_validate)(struct vb2_buffer *vb); int (*buf_init)(struct vb2_buffer *vb); int (*buf_prepare)(struct vb2_buffer *vb); void (*buf_finish)(struct vb2_buffer *vb); void (*buf_cleanup)(struct vb2_buffer *vb); int (*prepare_streaming)(struct vb2_queue *q); int (*start_streaming)(struct vb2_queue *q, unsigned int count); void (*stop_streaming)(struct vb2_queue *q); void (*unprepare_streaming)(struct vb2_queue *q); void (*buf_queue)(struct vb2_buffer *vb); void (*buf_request_complete)(struct vb2_buffer *vb); }; /** * struct vb2_buf_ops - driver-specific callbacks. * * @verify_planes_array: Verify that a given user space structure contains * enough planes for the buffer. This is called * for each dequeued buffer. * @init_buffer: given a &vb2_buffer initialize the extra data after * struct vb2_buffer. * For V4L2 this is a &struct vb2_v4l2_buffer. * @fill_user_buffer: given a &vb2_buffer fill in the userspace structure. * For V4L2 this is a &struct v4l2_buffer. * @fill_vb2_buffer: given a userspace structure, fill in the &vb2_buffer. * If the userspace structure is invalid, then this op * will return an error. * @copy_timestamp: copy the timestamp from a userspace structure to * the &struct vb2_buffer. */ struct vb2_buf_ops { int (*verify_planes_array)(struct vb2_buffer *vb, const void *pb); void (*init_buffer)(struct vb2_buffer *vb); void (*fill_user_buffer)(struct vb2_buffer *vb, void *pb); int (*fill_vb2_buffer)(struct vb2_buffer *vb, struct vb2_plane *planes); void (*copy_timestamp)(struct vb2_buffer *vb, const void *pb); }; /** * struct vb2_queue - a videobuf2 queue. * * @type: private buffer type whose content is defined by the vb2-core * caller. For example, for V4L2, it should match * the types defined on &enum v4l2_buf_type. * @io_modes: supported io methods (see &enum vb2_io_modes). * @dev: device to use for the default allocation context if the driver * doesn't fill in the @alloc_devs array. * @dma_attrs: DMA attributes to use for the DMA. * @bidirectional: when this flag is set the DMA direction for the buffers of * this queue will be overridden with %DMA_BIDIRECTIONAL direction. * This is useful in cases where the hardware (firmware) writes to * a buffer which is mapped as read (%DMA_TO_DEVICE), or reads from * buffer which is mapped for write (%DMA_FROM_DEVICE) in order * to satisfy some internal hardware restrictions or adds a padding * needed by the processing algorithm. In case the DMA mapping is * not bidirectional but the hardware (firmware) trying to access * the buffer (in the opposite direction) this could lead to an * IOMMU protection faults. * @fileio_read_once: report EOF after reading the first buffer * @fileio_write_immediately: queue buffer after each write() call * @allow_zero_bytesused: allow bytesused == 0 to be passed to the driver * @quirk_poll_must_check_waiting_for_buffers: Return %EPOLLERR at poll when QBUF * has not been called. This is a vb1 idiom that has been adopted * also by vb2. * @supports_requests: this queue supports the Request API. * @requires_requests: this queue requires the Request API. If this is set to 1, * then supports_requests must be set to 1 as well. * @uses_qbuf: qbuf was used directly for this queue. Set to 1 the first * time this is called. Set to 0 when the queue is canceled. * If this is 1, then you cannot queue buffers from a request. * @uses_requests: requests are used for this queue. Set to 1 the first time * a request is queued. Set to 0 when the queue is canceled. * If this is 1, then you cannot queue buffers directly. * @allow_cache_hints: when set user-space can pass cache management hints in * order to skip cache flush/invalidation on ->prepare() or/and * ->finish(). * @non_coherent_mem: when set queue will attempt to allocate buffers using * non-coherent memory. * @lock: pointer to a mutex that protects the &struct vb2_queue. The * driver can set this to a mutex to let the v4l2 core serialize * the queuing ioctls. If the driver wants to handle locking * itself, then this should be set to NULL. This lock is not used * by the videobuf2 core API. * @owner: The filehandle that 'owns' the buffers, i.e. the filehandle * that called reqbufs, create_buffers or started fileio. * This field is not used by the videobuf2 core API, but it allows * drivers to easily associate an owner filehandle with the queue. * @ops: driver-specific callbacks * @mem_ops: memory allocator specific callbacks * @buf_ops: callbacks to deliver buffer information. * between user-space and kernel-space. * @drv_priv: driver private data. * @subsystem_flags: Flags specific to the subsystem (V4L2/DVB/etc.). Not used * by the vb2 core. * @buf_struct_size: size of the driver-specific buffer structure; * "0" indicates the driver doesn't want to use a custom buffer * structure type. In that case a subsystem-specific struct * will be used (in the case of V4L2 that is * ``sizeof(struct vb2_v4l2_buffer)``). The first field of the * driver-specific buffer structure must be the subsystem-specific * struct (vb2_v4l2_buffer in the case of V4L2). * @timestamp_flags: Timestamp flags; ``V4L2_BUF_FLAG_TIMESTAMP_*`` and * ``V4L2_BUF_FLAG_TSTAMP_SRC_*`` * @gfp_flags: additional gfp flags used when allocating the buffers. * Typically this is 0, but it may be e.g. %GFP_DMA or %__GFP_DMA32 * to force the buffer allocation to a specific memory zone. * @min_queued_buffers: the minimum number of queued buffers needed before * @start_streaming can be called. Used when a DMA engine * cannot be started unless at least this number of buffers * have been queued into the driver. * VIDIOC_REQBUFS will ensure at least @min_queued_buffers + 1 * buffers will be allocated. Note that VIDIOC_CREATE_BUFS will not * modify the requested buffer count. * @min_reqbufs_allocation: the minimum number of buffers to be allocated when * calling VIDIOC_REQBUFS. Note that VIDIOC_CREATE_BUFS will *not* * modify the requested buffer count and does not use this field. * Drivers can set this if there has to be a certain number of * buffers available for the hardware to work effectively. * This allows calling VIDIOC_REQBUFS with a buffer count of 1 and * it will be automatically adjusted to a workable buffer count. * If set, then @min_reqbufs_allocation must be larger than * @min_queued_buffers + 1. * If this field is > 3, then it is highly recommended that the * driver implements the V4L2_CID_MIN_BUFFERS_FOR_CAPTURE/OUTPUT * control. * @alloc_devs: &struct device memory type/allocator-specific per-plane device */ /* * Private elements (won't appear at the uAPI book): * @mmap_lock: private mutex used when buffers are allocated/freed/mmapped * @memory: current memory type used * @dma_dir: DMA mapping direction. * @bufs: videobuf2 buffer structures. If it is non-NULL then * bufs_bitmap is also non-NULL. * @bufs_bitmap: bitmap tracking whether each bufs[] entry is used * @max_num_buffers: upper limit of number of allocated/used buffers. * If set to 0 v4l2 core will change it VB2_MAX_FRAME * for backward compatibility. * @queued_list: list of buffers currently queued from userspace * @queued_count: number of buffers queued and ready for streaming. * @owned_by_drv_count: number of buffers owned by the driver * @done_list: list of buffers ready to be dequeued to userspace * @done_lock: lock to protect done_list list * @done_wq: waitqueue for processes waiting for buffers ready to be dequeued * @streaming: current streaming state * @start_streaming_called: @start_streaming was called successfully and we * started streaming. * @error: a fatal error occurred on the queue * @waiting_for_buffers: used in poll() to check if vb2 is still waiting for * buffers. Only set for capture queues if qbuf has not yet been * called since poll() needs to return %EPOLLERR in that situation. * @waiting_in_dqbuf: set by the core for the duration of a blocking DQBUF, when * it has to wait for a buffer to become available with vb2_queue->lock * released. Used to prevent destroying the queue by other threads. * @is_multiplanar: set if buffer type is multiplanar * @is_output: set if buffer type is output * @is_busy: set if at least one buffer has been allocated at some time. * @copy_timestamp: set if vb2-core should set timestamps * @last_buffer_dequeued: used in poll() and DQBUF to immediately return if the * last decoded buffer was already dequeued. Set for capture queues * when a buffer with the %V4L2_BUF_FLAG_LAST is dequeued. * @fileio: file io emulator internal data, used only if emulator is active * @threadio: thread io internal data, used only if thread is active * @name: queue name, used for logging purpose. Initialized automatically * if left empty by drivers. */ struct vb2_queue { unsigned int type; unsigned int io_modes; struct device *dev; unsigned long dma_attrs; unsigned int bidirectional:1; unsigned int fileio_read_once:1; unsigned int fileio_write_immediately:1; unsigned int allow_zero_bytesused:1; unsigned int quirk_poll_must_check_waiting_for_buffers:1; unsigned int supports_requests:1; unsigned int requires_requests:1; unsigned int uses_qbuf:1; unsigned int uses_requests:1; unsigned int allow_cache_hints:1; unsigned int non_coherent_mem:1; struct mutex *lock; void *owner; const struct vb2_ops *ops; const struct vb2_mem_ops *mem_ops; const struct vb2_buf_ops *buf_ops; void *drv_priv; u32 subsystem_flags; unsigned int buf_struct_size; u32 timestamp_flags; gfp_t gfp_flags; u32 min_queued_buffers; u32 min_reqbufs_allocation; struct device *alloc_devs[VB2_MAX_PLANES]; /* private: internal use only */ struct mutex mmap_lock; unsigned int memory; enum dma_data_direction dma_dir; struct vb2_buffer **bufs; unsigned long *bufs_bitmap; unsigned int max_num_buffers; struct list_head queued_list; unsigned int queued_count; atomic_t owned_by_drv_count; struct list_head done_list; spinlock_t done_lock; wait_queue_head_t done_wq; unsigned int streaming:1; unsigned int start_streaming_called:1; unsigned int error:1; unsigned int waiting_for_buffers:1; unsigned int waiting_in_dqbuf:1; unsigned int is_multiplanar:1; unsigned int is_output:1; unsigned int is_busy:1; unsigned int copy_timestamp:1; unsigned int last_buffer_dequeued:1; struct vb2_fileio_data *fileio; struct vb2_threadio_data *threadio; char name[32]; #ifdef CONFIG_VIDEO_ADV_DEBUG /* * Counters for how often these queue-related ops are * called. Used to check for unbalanced ops. */ u32 cnt_queue_setup; u32 cnt_wait_prepare; u32 cnt_wait_finish; u32 cnt_prepare_streaming; u32 cnt_start_streaming; u32 cnt_stop_streaming; u32 cnt_unprepare_streaming; #endif }; /** * vb2_queue_allows_cache_hints() - Return true if the queue allows cache * and memory consistency hints. * * @q: pointer to &struct vb2_queue with videobuf2 queue */ static inline bool vb2_queue_allows_cache_hints(struct vb2_queue *q) { return q->allow_cache_hints && q->memory == VB2_MEMORY_MMAP; } /** * vb2_plane_vaddr() - Return a kernel virtual address of a given plane. * @vb: pointer to &struct vb2_buffer to which the plane in * question belongs to. * @plane_no: plane number for which the address is to be returned. * * This function returns a kernel virtual address of a given plane if * such a mapping exist, NULL otherwise. */ void *vb2_plane_vaddr(struct vb2_buffer *vb, unsigned int plane_no); /** * vb2_plane_cookie() - Return allocator specific cookie for the given plane. * @vb: pointer to &struct vb2_buffer to which the plane in * question belongs to. * @plane_no: plane number for which the cookie is to be returned. * * This function returns an allocator specific cookie for a given plane if * available, NULL otherwise. The allocator should provide some simple static * inline function, which would convert this cookie to the allocator specific * type that can be used directly by the driver to access the buffer. This can * be for example physical address, pointer to scatter list or IOMMU mapping. */ void *vb2_plane_cookie(struct vb2_buffer *vb, unsigned int plane_no); /** * vb2_buffer_done() - inform videobuf2 that an operation on a buffer * is finished. * @vb: pointer to &struct vb2_buffer to be used. * @state: state of the buffer, as defined by &enum vb2_buffer_state. * Either %VB2_BUF_STATE_DONE if the operation finished * successfully, %VB2_BUF_STATE_ERROR if the operation finished * with an error or %VB2_BUF_STATE_QUEUED. * * This function should be called by the driver after a hardware operation on * a buffer is finished and the buffer may be returned to userspace. The driver * cannot use this buffer anymore until it is queued back to it by videobuf * by the means of &vb2_ops->buf_queue callback. Only buffers previously queued * to the driver by &vb2_ops->buf_queue can be passed to this function. * * While streaming a buffer can only be returned in state DONE or ERROR. * The &vb2_ops->start_streaming op can also return them in case the DMA engine * cannot be started for some reason. In that case the buffers should be * returned with state QUEUED to put them back into the queue. */ void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state); /** * vb2_discard_done() - discard all buffers marked as DONE. * @q: pointer to &struct vb2_queue with videobuf2 queue. * * This function is intended to be used with suspend/resume operations. It * discards all 'done' buffers as they would be too old to be requested after * resume. * * Drivers must stop the hardware and synchronize with interrupt handlers and/or * delayed works before calling this function to make sure no buffer will be * touched by the driver and/or hardware. */ void vb2_discard_done(struct vb2_queue *q); /** * vb2_wait_for_all_buffers() - wait until all buffers are given back to vb2. * @q: pointer to &struct vb2_queue with videobuf2 queue. * * This function will wait until all buffers that have been given to the driver * by &vb2_ops->buf_queue are given back to vb2 with vb2_buffer_done(). It * doesn't call &vb2_ops->wait_prepare/&vb2_ops->wait_finish pair. * It is intended to be called with all locks taken, for example from * &vb2_ops->stop_streaming callback. */ int vb2_wait_for_all_buffers(struct vb2_queue *q); /** * vb2_core_querybuf() - query video buffer information. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @vb: pointer to struct &vb2_buffer. * @pb: buffer struct passed from userspace. * * Videobuf2 core helper to implement VIDIOC_QUERYBUF() operation. It is called * internally by VB2 by an API-specific handler, like ``videobuf2-v4l2.h``. * * The passed buffer should have been verified. * * This function fills the relevant information for the userspace. * * Return: returns zero on success; an error code otherwise. */ void vb2_core_querybuf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb); /** * vb2_core_reqbufs() - Initiate streaming. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @memory: memory type, as defined by &enum vb2_memory. * @flags: auxiliary queue/buffer management flags. Currently, the only * used flag is %V4L2_MEMORY_FLAG_NON_COHERENT. * @count: requested buffer count. * * Videobuf2 core helper to implement VIDIOC_REQBUF() operation. It is called * internally by VB2 by an API-specific handler, like ``videobuf2-v4l2.h``. * * This function: * * #) verifies streaming parameters passed from the userspace; * #) sets up the queue; * #) negotiates number of buffers and planes per buffer with the driver * to be used during streaming; * #) allocates internal buffer structures (&struct vb2_buffer), according to * the agreed parameters; * #) for MMAP memory type, allocates actual video memory, using the * memory handling/allocation routines provided during queue initialization. * * If req->count is 0, all the memory will be freed instead. * * If the queue has been allocated previously by a previous vb2_core_reqbufs() * call and the queue is not busy, memory will be reallocated. * * Return: returns zero on success; an error code otherwise. */ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, unsigned int flags, unsigned int *count); /** * vb2_core_create_bufs() - Allocate buffers and any required auxiliary structs * @q: pointer to &struct vb2_queue with videobuf2 queue. * @memory: memory type, as defined by &enum vb2_memory. * @flags: auxiliary queue/buffer management flags. * @count: requested buffer count. * @requested_planes: number of planes requested. * @requested_sizes: array with the size of the planes. * @first_index: index of the first created buffer, all allocated buffers have * indices in the range [first_index..first_index+count-1] * * Videobuf2 core helper to implement VIDIOC_CREATE_BUFS() operation. It is * called internally by VB2 by an API-specific handler, like * ``videobuf2-v4l2.h``. * * This function: * * #) verifies parameter sanity; * #) calls the &vb2_ops->queue_setup queue operation; * #) performs any necessary memory allocations. * * Return: returns zero on success; an error code otherwise. */ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, unsigned int flags, unsigned int *count, unsigned int requested_planes, const unsigned int requested_sizes[], unsigned int *first_index); /** * vb2_core_prepare_buf() - Pass ownership of a buffer from userspace * to the kernel. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @vb: pointer to struct &vb2_buffer. * @pb: buffer structure passed from userspace to * &v4l2_ioctl_ops->vidioc_prepare_buf handler in driver. * * Videobuf2 core helper to implement VIDIOC_PREPARE_BUF() operation. It is * called internally by VB2 by an API-specific handler, like * ``videobuf2-v4l2.h``. * * The passed buffer should have been verified. * * This function calls vb2_ops->buf_prepare callback in the driver * (if provided), in which driver-specific buffer initialization can * be performed. * * Return: returns zero on success; an error code otherwise. */ int vb2_core_prepare_buf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb); /** * vb2_core_remove_bufs() - * @q: pointer to &struct vb2_queue with videobuf2 queue. * @start: first index of the range of buffers to remove. * @count: number of buffers to remove. * * Return: returns zero on success; an error code otherwise. */ int vb2_core_remove_bufs(struct vb2_queue *q, unsigned int start, unsigned int count); /** * vb2_core_qbuf() - Queue a buffer from userspace * * @q: pointer to &struct vb2_queue with videobuf2 queue. * @vb: pointer to struct &vb2_buffer. * @pb: buffer structure passed from userspace to * v4l2_ioctl_ops->vidioc_qbuf handler in driver * @req: pointer to &struct media_request, may be NULL. * * Videobuf2 core helper to implement VIDIOC_QBUF() operation. It is called * internally by VB2 by an API-specific handler, like ``videobuf2-v4l2.h``. * * This function: * * #) If @req is non-NULL, then the buffer will be bound to this * media request and it returns. The buffer will be prepared and * queued to the driver (i.e. the next two steps) when the request * itself is queued. * #) if necessary, calls &vb2_ops->buf_prepare callback in the driver * (if provided), in which driver-specific buffer initialization can * be performed; * #) if streaming is on, queues the buffer in driver by the means of * &vb2_ops->buf_queue callback for processing. * * Return: returns zero on success; an error code otherwise. */ int vb2_core_qbuf(struct vb2_queue *q, struct vb2_buffer *vb, void *pb, struct media_request *req); /** * vb2_core_dqbuf() - Dequeue a buffer to the userspace * @q: pointer to &struct vb2_queue with videobuf2 queue * @pindex: pointer to the buffer index. May be NULL * @pb: buffer structure passed from userspace to * v4l2_ioctl_ops->vidioc_dqbuf handler in driver. * @nonblocking: if true, this call will not sleep waiting for a buffer if no * buffers ready for dequeuing are present. Normally the driver * would be passing (file->f_flags & O_NONBLOCK) here. * * Videobuf2 core helper to implement VIDIOC_DQBUF() operation. It is called * internally by VB2 by an API-specific handler, like ``videobuf2-v4l2.h``. * * This function: * * #) calls buf_finish callback in the driver (if provided), in which * driver can perform any additional operations that may be required before * returning the buffer to userspace, such as cache sync, * #) the buffer struct members are filled with relevant information for * the userspace. * * Return: returns zero on success; an error code otherwise. */ int vb2_core_dqbuf(struct vb2_queue *q, unsigned int *pindex, void *pb, bool nonblocking); /** * vb2_core_streamon() - Implements VB2 stream ON logic * * @q: pointer to &struct vb2_queue with videobuf2 queue * @type: type of the queue to be started. * For V4L2, this is defined by &enum v4l2_buf_type type. * * Videobuf2 core helper to implement VIDIOC_STREAMON() operation. It is called * internally by VB2 by an API-specific handler, like ``videobuf2-v4l2.h``. * * Return: returns zero on success; an error code otherwise. */ int vb2_core_streamon(struct vb2_queue *q, unsigned int type); /** * vb2_core_streamoff() - Implements VB2 stream OFF logic * * @q: pointer to &struct vb2_queue with videobuf2 queue * @type: type of the queue to be started. * For V4L2, this is defined by &enum v4l2_buf_type type. * * Videobuf2 core helper to implement VIDIOC_STREAMOFF() operation. It is * called internally by VB2 by an API-specific handler, like * ``videobuf2-v4l2.h``. * * Return: returns zero on success; an error code otherwise. */ int vb2_core_streamoff(struct vb2_queue *q, unsigned int type); /** * vb2_core_expbuf() - Export a buffer as a file descriptor. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @fd: pointer to the file descriptor associated with DMABUF * (set by driver). * @type: buffer type. * @vb: pointer to struct &vb2_buffer. * @plane: index of the plane to be exported, 0 for single plane queues * @flags: file flags for newly created file, as defined at * include/uapi/asm-generic/fcntl.h. * Currently, the only used flag is %O_CLOEXEC. * is supported, refer to manual of open syscall for more details. * * * Videobuf2 core helper to implement VIDIOC_EXPBUF() operation. It is called * internally by VB2 by an API-specific handler, like ``videobuf2-v4l2.h``. * * Return: returns zero on success; an error code otherwise. */ int vb2_core_expbuf(struct vb2_queue *q, int *fd, unsigned int type, struct vb2_buffer *vb, unsigned int plane, unsigned int flags); /** * vb2_core_queue_init() - initialize a videobuf2 queue * @q: pointer to &struct vb2_queue with videobuf2 queue. * This structure should be allocated in driver * * The &vb2_queue structure should be allocated by the driver. The driver is * responsible of clearing it's content and setting initial values for some * required entries before calling this function. * * .. note:: * * The following fields at @q should be set before calling this function: * &vb2_queue->ops, &vb2_queue->mem_ops, &vb2_queue->type. */ int vb2_core_queue_init(struct vb2_queue *q); /** * vb2_core_queue_release() - stop streaming, release the queue and free memory * @q: pointer to &struct vb2_queue with videobuf2 queue. * * This function stops streaming and performs necessary clean ups, including * freeing video buffer memory. The driver is responsible for freeing * the &struct vb2_queue itself. */ void vb2_core_queue_release(struct vb2_queue *q); /** * vb2_queue_error() - signal a fatal error on the queue * @q: pointer to &struct vb2_queue with videobuf2 queue. * * Flag that a fatal unrecoverable error has occurred and wake up all processes * waiting on the queue. Polling will now set %EPOLLERR and queuing and dequeuing * buffers will return %-EIO. * * The error flag will be cleared when canceling the queue, either from * vb2_streamoff() or vb2_queue_release(). Drivers should thus not call this * function before starting the stream, otherwise the error flag will remain set * until the queue is released when closing the device node. */ void vb2_queue_error(struct vb2_queue *q); /** * vb2_mmap() - map video buffers into application address space. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @vma: pointer to &struct vm_area_struct with the vma passed * to the mmap file operation handler in the driver. * * Should be called from mmap file operation handler of a driver. * This function maps one plane of one of the available video buffers to * userspace. To map whole video memory allocated on reqbufs, this function * has to be called once per each plane per each buffer previously allocated. * * When the userspace application calls mmap, it passes to it an offset returned * to it earlier by the means of &v4l2_ioctl_ops->vidioc_querybuf handler. * That offset acts as a "cookie", which is then used to identify the plane * to be mapped. * * This function finds a plane with a matching offset and a mapping is performed * by the means of a provided memory operation. * * The return values from this function are intended to be directly returned * from the mmap handler in driver. */ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma); #ifndef CONFIG_MMU /** * vb2_get_unmapped_area - map video buffers into application address space. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @addr: memory address. * @len: buffer size. * @pgoff: page offset. * @flags: memory flags. * * This function is used in noMMU platforms to propose address mapping * for a given buffer. It's intended to be used as a handler for the * &file_operations->get_unmapped_area operation. * * This is called by the mmap() syscall routines will call this * to get a proposed address for the mapping, when ``!CONFIG_MMU``. */ unsigned long vb2_get_unmapped_area(struct vb2_queue *q, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #endif /** * vb2_core_poll() - implements poll syscall() logic. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @file: &struct file argument passed to the poll * file operation handler. * @wait: &poll_table wait argument passed to the poll * file operation handler. * * This function implements poll file operation handler for a driver. * For CAPTURE queues, if a buffer is ready to be dequeued, the userspace will * be informed that the file descriptor of a video device is available for * reading. * For OUTPUT queues, if a buffer is ready to be dequeued, the file descriptor * will be reported as available for writing. * * The return values from this function are intended to be directly returned * from poll handler in driver. */ __poll_t vb2_core_poll(struct vb2_queue *q, struct file *file, poll_table *wait); /** * vb2_read() - implements read() syscall logic. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @data: pointed to target userspace buffer * @count: number of bytes to read * @ppos: file handle position tracking pointer * @nonblock: mode selector (1 means blocking calls, 0 means nonblocking) */ size_t vb2_read(struct vb2_queue *q, char __user *data, size_t count, loff_t *ppos, int nonblock); /** * vb2_write() - implements write() syscall logic. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @data: pointed to target userspace buffer * @count: number of bytes to write * @ppos: file handle position tracking pointer * @nonblock: mode selector (1 means blocking calls, 0 means nonblocking) */ size_t vb2_write(struct vb2_queue *q, const char __user *data, size_t count, loff_t *ppos, int nonblock); /** * typedef vb2_thread_fnc - callback function for use with vb2_thread. * * @vb: pointer to struct &vb2_buffer. * @priv: pointer to a private data. * * This is called whenever a buffer is dequeued in the thread. */ typedef int (*vb2_thread_fnc)(struct vb2_buffer *vb, void *priv); /** * vb2_thread_start() - start a thread for the given queue. * @q: pointer to &struct vb2_queue with videobuf2 queue. * @fnc: &vb2_thread_fnc callback function. * @priv: priv pointer passed to the callback function. * @thread_name:the name of the thread. This will be prefixed with "vb2-". * * This starts a thread that will queue and dequeue until an error occurs * or vb2_thread_stop() is called. * * .. attention:: * * This function should not be used for anything else but the videobuf2-dvb * support. If you think you have another good use-case for this, then please * contact the linux-media mailing list first. */ int vb2_thread_start(struct vb2_queue *q, vb2_thread_fnc fnc, void *priv, const char *thread_name); /** * vb2_thread_stop() - stop the thread for the given queue. * @q: pointer to &struct vb2_queue with videobuf2 queue. */ int vb2_thread_stop(struct vb2_queue *q); /** * vb2_is_streaming() - return streaming status of the queue. * @q: pointer to &struct vb2_queue with videobuf2 queue. */ static inline bool vb2_is_streaming(struct vb2_queue *q) { return q->streaming; } /** * vb2_fileio_is_active() - return true if fileio is active. * @q: pointer to &struct vb2_queue with videobuf2 queue. * * This returns true if read() or write() is used to stream the data * as opposed to stream I/O. This is almost never an important distinction, * except in rare cases. One such case is that using read() or write() to * stream a format using %V4L2_FIELD_ALTERNATE is not allowed since there * is no way you can pass the field information of each buffer to/from * userspace. A driver that supports this field format should check for * this in the &vb2_ops->queue_setup op and reject it if this function returns * true. */ static inline bool vb2_fileio_is_active(struct vb2_queue *q) { return q->fileio; } /** * vb2_get_num_buffers() - get the number of buffer in a queue * @q: pointer to &struct vb2_queue with videobuf2 queue. */ static inline unsigned int vb2_get_num_buffers(struct vb2_queue *q) { if (q->bufs_bitmap) return bitmap_weight(q->bufs_bitmap, q->max_num_buffers); return 0; } /** * vb2_is_busy() - return busy status of the queue. * @q: pointer to &struct vb2_queue with videobuf2 queue. * * This function checks if queue has any buffers allocated. */ static inline bool vb2_is_busy(struct vb2_queue *q) { return !!q->is_busy; } /** * vb2_get_drv_priv() - return driver private data associated with the queue. * @q: pointer to &struct vb2_queue with videobuf2 queue. */ static inline void *vb2_get_drv_priv(struct vb2_queue *q) { return q->drv_priv; } /** * vb2_set_plane_payload() - set bytesused for the plane @plane_no. * @vb: pointer to &struct vb2_buffer to which the plane in * question belongs to. * @plane_no: plane number for which payload should be set. * @size: payload in bytes. */ static inline void vb2_set_plane_payload(struct vb2_buffer *vb, unsigned int plane_no, unsigned long size) { /* * size must never be larger than the buffer length, so * warn and clamp to the buffer length if that's the case. */ if (plane_no < vb->num_planes) { if (WARN_ON_ONCE(size > vb->planes[plane_no].length)) size = vb->planes[plane_no].length; vb->planes[plane_no].bytesused = size; } } /** * vb2_get_plane_payload() - get bytesused for the plane plane_no * @vb: pointer to &struct vb2_buffer to which the plane in * question belongs to. * @plane_no: plane number for which payload should be set. */ static inline unsigned long vb2_get_plane_payload(struct vb2_buffer *vb, unsigned int plane_no) { if (plane_no < vb->num_planes) return vb->planes[plane_no].bytesused; return 0; } /** * vb2_plane_size() - return plane size in bytes. * @vb: pointer to &struct vb2_buffer to which the plane in * question belongs to. * @plane_no: plane number for which size should be returned. */ static inline unsigned long vb2_plane_size(struct vb2_buffer *vb, unsigned int plane_no) { if (plane_no < vb->num_planes) return vb->planes[plane_no].length; return 0; } /** * vb2_start_streaming_called() - return streaming status of driver. * @q: pointer to &struct vb2_queue with videobuf2 queue. */ static inline bool vb2_start_streaming_called(struct vb2_queue *q) { return q->start_streaming_called; } /** * vb2_clear_last_buffer_dequeued() - clear last buffer dequeued flag of queue. * @q: pointer to &struct vb2_queue with videobuf2 queue. */ static inline void vb2_clear_last_buffer_dequeued(struct vb2_queue *q) { q->last_buffer_dequeued = false; } /** * vb2_get_buffer() - get a buffer from a queue * @q: pointer to &struct vb2_queue with videobuf2 queue. * @index: buffer index * * This function obtains a buffer from a queue, by its index. * Keep in mind that there is no refcounting involved in this * operation, so the buffer lifetime should be taken into * consideration. */ static inline struct vb2_buffer *vb2_get_buffer(struct vb2_queue *q, unsigned int index) { if (!q->bufs) return NULL; if (index >= q->max_num_buffers) return NULL; if (test_bit(index, q->bufs_bitmap)) return q->bufs[index]; return NULL; } /* * The following functions are not part of the vb2 core API, but are useful * functions for videobuf2-*. */ /** * vb2_buffer_in_use() - return true if the buffer is in use and * the queue cannot be freed (by the means of VIDIOC_REQBUFS(0)) call. * * @vb: buffer for which plane size should be returned. * @q: pointer to &struct vb2_queue with videobuf2 queue. */ bool vb2_buffer_in_use(struct vb2_queue *q, struct vb2_buffer *vb); /** * vb2_verify_memory_type() - Check whether the memory type and buffer type * passed to a buffer operation are compatible with the queue. * * @q: pointer to &struct vb2_queue with videobuf2 queue. * @memory: memory model, as defined by enum &vb2_memory. * @type: private buffer type whose content is defined by the vb2-core * caller. For example, for V4L2, it should match * the types defined on enum &v4l2_buf_type. */ int vb2_verify_memory_type(struct vb2_queue *q, enum vb2_memory memory, unsigned int type); /** * vb2_request_object_is_buffer() - return true if the object is a buffer * * @obj: the request object. */ bool vb2_request_object_is_buffer(struct media_request_object *obj); /** * vb2_request_buffer_cnt() - return the number of buffers in the request * * @req: the request. */ unsigned int vb2_request_buffer_cnt(struct media_request *req); #endif /* _MEDIA_VIDEOBUF2_CORE_H */ |
| 12 12 12 535 533 11 529 529 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 | // SPDX-License-Identifier: GPL-2.0 /* * This file contains functions which manage clock event devices. * * Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de> * Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar * Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner */ #include <linux/clockchips.h> #include <linux/hrtimer.h> #include <linux/init.h> #include <linux/module.h> #include <linux/smp.h> #include <linux/device.h> #include "tick-internal.h" /* The registered clock event devices */ static LIST_HEAD(clockevent_devices); static LIST_HEAD(clockevents_released); /* Protection for the above */ static DEFINE_RAW_SPINLOCK(clockevents_lock); /* Protection for unbind operations */ static DEFINE_MUTEX(clockevents_mutex); struct ce_unbind { struct clock_event_device *ce; int res; }; static u64 cev_delta2ns(unsigned long latch, struct clock_event_device *evt, bool ismax) { u64 clc = (u64) latch << evt->shift; u64 rnd; if (WARN_ON(!evt->mult)) evt->mult = 1; rnd = (u64) evt->mult - 1; /* * Upper bound sanity check. If the backwards conversion is * not equal latch, we know that the above shift overflowed. */ if ((clc >> evt->shift) != (u64)latch) clc = ~0ULL; /* * Scaled math oddities: * * For mult <= (1 << shift) we can safely add mult - 1 to * prevent integer rounding loss. So the backwards conversion * from nsec to device ticks will be correct. * * For mult > (1 << shift), i.e. device frequency is > 1GHz we * need to be careful. Adding mult - 1 will result in a value * which when converted back to device ticks can be larger * than latch by up to (mult - 1) >> shift. For the min_delta * calculation we still want to apply this in order to stay * above the minimum device ticks limit. For the upper limit * we would end up with a latch value larger than the upper * limit of the device, so we omit the add to stay below the * device upper boundary. * * Also omit the add if it would overflow the u64 boundary. */ if ((~0ULL - clc > rnd) && (!ismax || evt->mult <= (1ULL << evt->shift))) clc += rnd; do_div(clc, evt->mult); /* Deltas less than 1usec are pointless noise */ return clc > 1000 ? clc : 1000; } /** * clockevent_delta2ns - Convert a latch value (device ticks) to nanoseconds * @latch: value to convert * @evt: pointer to clock event device descriptor * * Math helper, returns latch value converted to nanoseconds (bound checked) */ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) { return cev_delta2ns(latch, evt, false); } EXPORT_SYMBOL_GPL(clockevent_delta2ns); static int __clockevents_switch_state(struct clock_event_device *dev, enum clock_event_state state) { if (dev->features & CLOCK_EVT_FEAT_DUMMY) return 0; /* Transition with new state-specific callbacks */ switch (state) { case CLOCK_EVT_STATE_DETACHED: /* The clockevent device is getting replaced. Shut it down. */ case CLOCK_EVT_STATE_SHUTDOWN: if (dev->set_state_shutdown) return dev->set_state_shutdown(dev); return 0; case CLOCK_EVT_STATE_PERIODIC: /* Core internal bug */ if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC)) return -ENOSYS; if (dev->set_state_periodic) return dev->set_state_periodic(dev); return 0; case CLOCK_EVT_STATE_ONESHOT: /* Core internal bug */ if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return -ENOSYS; if (dev->set_state_oneshot) return dev->set_state_oneshot(dev); return 0; case CLOCK_EVT_STATE_ONESHOT_STOPPED: /* Core internal bug */ if (WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n", clockevent_get_state(dev))) return -EINVAL; if (dev->set_state_oneshot_stopped) return dev->set_state_oneshot_stopped(dev); else return -ENOSYS; default: return -ENOSYS; } } /** * clockevents_switch_state - set the operating state of a clock event device * @dev: device to modify * @state: new state * * Must be called with interrupts disabled ! */ void clockevents_switch_state(struct clock_event_device *dev, enum clock_event_state state) { if (clockevent_get_state(dev) != state) { if (__clockevents_switch_state(dev, state)) return; clockevent_set_state(dev, state); /* * A nsec2cyc multiplicator of 0 is invalid and we'd crash * on it, so fix it up and emit a warning: */ if (clockevent_state_oneshot(dev)) { if (WARN_ON(!dev->mult)) dev->mult = 1; } } } /** * clockevents_shutdown - shutdown the device and clear next_event * @dev: device to shutdown */ void clockevents_shutdown(struct clock_event_device *dev) { clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN); dev->next_event = KTIME_MAX; } /** * clockevents_tick_resume - Resume the tick device before using it again * @dev: device to resume */ int clockevents_tick_resume(struct clock_event_device *dev) { int ret = 0; if (dev->tick_resume) ret = dev->tick_resume(dev); return ret; } #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST /* Limit min_delta to a jiffy */ #define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) /** * clockevents_increase_min_delta - raise minimum delta of a clock event device * @dev: device to increase the minimum delta * * Returns 0 on success, -ETIME when the minimum delta reached the limit. */ static int clockevents_increase_min_delta(struct clock_event_device *dev) { /* Nothing to do if we already reached the limit */ if (dev->min_delta_ns >= MIN_DELTA_LIMIT) { printk_deferred(KERN_WARNING "CE: Reprogramming failure. Giving up\n"); dev->next_event = KTIME_MAX; return -ETIME; } if (dev->min_delta_ns < 5000) dev->min_delta_ns = 5000; else dev->min_delta_ns += dev->min_delta_ns >> 1; if (dev->min_delta_ns > MIN_DELTA_LIMIT) dev->min_delta_ns = MIN_DELTA_LIMIT; printk_deferred(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n", dev->name ? dev->name : "?", (unsigned long long) dev->min_delta_ns); return 0; } /** * clockevents_program_min_delta - Set clock event device to the minimum delay. * @dev: device to program * * Returns 0 on success, -ETIME when the retry loop failed. */ static int clockevents_program_min_delta(struct clock_event_device *dev) { unsigned long long clc; int64_t delta; int i; for (i = 0;;) { delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); if (clockevent_state_shutdown(dev)) return 0; dev->retries++; clc = ((unsigned long long) delta * dev->mult) >> dev->shift; if (dev->set_next_event((unsigned long) clc, dev) == 0) return 0; if (++i > 2) { /* * We tried 3 times to program the device with the * given min_delta_ns. Try to increase the minimum * delta, if that fails as well get out of here. */ if (clockevents_increase_min_delta(dev)) return -ETIME; i = 0; } } } #else /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */ /** * clockevents_program_min_delta - Set clock event device to the minimum delay. * @dev: device to program * * Returns 0 on success, -ETIME when the retry loop failed. */ static int clockevents_program_min_delta(struct clock_event_device *dev) { unsigned long long clc; int64_t delta = 0; int i; for (i = 0; i < 10; i++) { delta += dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); if (clockevent_state_shutdown(dev)) return 0; dev->retries++; clc = ((unsigned long long) delta * dev->mult) >> dev->shift; if (dev->set_next_event((unsigned long) clc, dev) == 0) return 0; } return -ETIME; } #endif /* CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST */ /** * clockevents_program_event - Reprogram the clock event device. * @dev: device to program * @expires: absolute expiry time (monotonic clock) * @force: program minimum delay if expires can not be set * * Returns 0 on success, -ETIME when the event is in the past. */ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, bool force) { unsigned long long clc; int64_t delta; int rc; if (WARN_ON_ONCE(expires < 0)) return -ETIME; dev->next_event = expires; if (clockevent_state_shutdown(dev)) return 0; /* We must be in ONESHOT state here */ WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n", clockevent_get_state(dev)); /* Shortcut for clockevent devices that can deal with ktime. */ if (dev->features & CLOCK_EVT_FEAT_KTIME) return dev->set_next_ktime(expires, dev); delta = ktime_to_ns(ktime_sub(expires, ktime_get())); if (delta <= 0) return force ? clockevents_program_min_delta(dev) : -ETIME; delta = min(delta, (int64_t) dev->max_delta_ns); delta = max(delta, (int64_t) dev->min_delta_ns); clc = ((unsigned long long) delta * dev->mult) >> dev->shift; rc = dev->set_next_event((unsigned long) clc, dev); return (rc && force) ? clockevents_program_min_delta(dev) : rc; } /* * Called after a clockevent has been added which might * have replaced a current regular or broadcast device. A * released normal device might be a suitable replacement * for the current broadcast device. Similarly a released * broadcast device might be a suitable replacement for a * normal device. */ static void clockevents_notify_released(void) { struct clock_event_device *dev; /* * Keep iterating as long as tick_check_new_device() * replaces a device. */ while (!list_empty(&clockevents_released)) { dev = list_entry(clockevents_released.next, struct clock_event_device, list); list_move(&dev->list, &clockevent_devices); tick_check_new_device(dev); } } /* * Try to install a replacement clock event device */ static int clockevents_replace(struct clock_event_device *ced) { struct clock_event_device *dev, *newdev = NULL; list_for_each_entry(dev, &clockevent_devices, list) { if (dev == ced || !clockevent_state_detached(dev)) continue; if (!tick_check_replacement(newdev, dev)) continue; if (!try_module_get(dev->owner)) continue; if (newdev) module_put(newdev->owner); newdev = dev; } if (newdev) { tick_install_replacement(newdev); list_del_init(&ced->list); } return newdev ? 0 : -EBUSY; } /* * Called with clockevents_mutex and clockevents_lock held */ static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) { /* Fast track. Device is unused */ if (clockevent_state_detached(ced)) { list_del_init(&ced->list); return 0; } return ced == per_cpu(tick_cpu_device, cpu).evtdev ? -EAGAIN : -EBUSY; } /* * SMP function call to unbind a device */ static void __clockevents_unbind(void *arg) { struct ce_unbind *cu = arg; int res; raw_spin_lock(&clockevents_lock); res = __clockevents_try_unbind(cu->ce, smp_processor_id()); if (res == -EAGAIN) res = clockevents_replace(cu->ce); cu->res = res; raw_spin_unlock(&clockevents_lock); } /* * Issues smp function call to unbind a per cpu device. Called with * clockevents_mutex held. */ static int clockevents_unbind(struct clock_event_device *ced, int cpu) { struct ce_unbind cu = { .ce = ced, .res = -ENODEV }; smp_call_function_single(cpu, __clockevents_unbind, &cu, 1); return cu.res; } /* * Unbind a clockevents device. */ int clockevents_unbind_device(struct clock_event_device *ced, int cpu) { int ret; mutex_lock(&clockevents_mutex); ret = clockevents_unbind(ced, cpu); mutex_unlock(&clockevents_mutex); return ret; } EXPORT_SYMBOL_GPL(clockevents_unbind_device); /** * clockevents_register_device - register a clock event device * @dev: device to register */ void clockevents_register_device(struct clock_event_device *dev) { unsigned long flags; /* Initialize state to DETACHED */ clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED); if (!dev->cpumask) { WARN_ON(num_possible_cpus() > 1); dev->cpumask = cpumask_of(smp_processor_id()); } if (dev->cpumask == cpu_all_mask) { WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n", dev->name); dev->cpumask = cpu_possible_mask; } raw_spin_lock_irqsave(&clockevents_lock, flags); list_add(&dev->list, &clockevent_devices); tick_check_new_device(dev); clockevents_notify_released(); raw_spin_unlock_irqrestore(&clockevents_lock, flags); } EXPORT_SYMBOL_GPL(clockevents_register_device); static void clockevents_config(struct clock_event_device *dev, u32 freq) { u64 sec; if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return; /* * Calculate the maximum number of seconds we can sleep. Limit * to 10 minutes for hardware which can program more than * 32bit ticks so we still get reasonable conversion values. */ sec = dev->max_delta_ticks; do_div(sec, freq); if (!sec) sec = 1; else if (sec > 600 && dev->max_delta_ticks > UINT_MAX) sec = 600; clockevents_calc_mult_shift(dev, freq, sec); dev->min_delta_ns = cev_delta2ns(dev->min_delta_ticks, dev, false); dev->max_delta_ns = cev_delta2ns(dev->max_delta_ticks, dev, true); } /** * clockevents_config_and_register - Configure and register a clock event device * @dev: device to register * @freq: The clock frequency * @min_delta: The minimum clock ticks to program in oneshot mode * @max_delta: The maximum clock ticks to program in oneshot mode * * min/max_delta can be 0 for devices which do not support oneshot mode. */ void clockevents_config_and_register(struct clock_event_device *dev, u32 freq, unsigned long min_delta, unsigned long max_delta) { dev->min_delta_ticks = min_delta; dev->max_delta_ticks = max_delta; clockevents_config(dev, freq); clockevents_register_device(dev); } EXPORT_SYMBOL_GPL(clockevents_config_and_register); int __clockevents_update_freq(struct clock_event_device *dev, u32 freq) { clockevents_config(dev, freq); if (clockevent_state_oneshot(dev)) return clockevents_program_event(dev, dev->next_event, false); if (clockevent_state_periodic(dev)) return __clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC); return 0; } /** * clockevents_update_freq - Update frequency and reprogram a clock event device. * @dev: device to modify * @freq: new device frequency * * Reconfigure and reprogram a clock event device in oneshot * mode. Must be called on the cpu for which the device delivers per * cpu timer events. If called for the broadcast device the core takes * care of serialization. * * Returns 0 on success, -ETIME when the event is in the past. */ int clockevents_update_freq(struct clock_event_device *dev, u32 freq) { unsigned long flags; int ret; local_irq_save(flags); ret = tick_broadcast_update_freq(dev, freq); if (ret == -ENODEV) ret = __clockevents_update_freq(dev, freq); local_irq_restore(flags); return ret; } /* * Noop handler when we shut down an event device */ void clockevents_handle_noop(struct clock_event_device *dev) { } /** * clockevents_exchange_device - release and request clock devices * @old: device to release (can be NULL) * @new: device to request (can be NULL) * * Called from various tick functions with clockevents_lock held and * interrupts disabled. */ void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new) { /* * Caller releases a clock event device. We queue it into the * released list and do a notify add later. */ if (old) { module_put(old->owner); clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED); list_move(&old->list, &clockevents_released); } if (new) { BUG_ON(!clockevent_state_detached(new)); clockevents_shutdown(new); } } /** * clockevents_suspend - suspend clock devices */ void clockevents_suspend(void) { struct clock_event_device *dev; list_for_each_entry_reverse(dev, &clockevent_devices, list) if (dev->suspend && !clockevent_state_detached(dev)) dev->suspend(dev); } /** * clockevents_resume - resume clock devices */ void clockevents_resume(void) { struct clock_event_device *dev; list_for_each_entry(dev, &clockevent_devices, list) if (dev->resume && !clockevent_state_detached(dev)) dev->resume(dev); } #ifdef CONFIG_HOTPLUG_CPU /** * tick_offline_cpu - Shutdown all clock events related * to this CPU and take it out of the * broadcast mechanism. * @cpu: The outgoing CPU * * Called by the dying CPU during teardown. */ void tick_offline_cpu(unsigned int cpu) { struct clock_event_device *dev, *tmp; raw_spin_lock(&clockevents_lock); tick_broadcast_offline(cpu); tick_shutdown(cpu); /* * Unregister the clock event devices which were * released above. */ list_for_each_entry_safe(dev, tmp, &clockevents_released, list) list_del(&dev->list); /* * Now check whether the CPU has left unused per cpu devices */ list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) { if (cpumask_test_cpu(cpu, dev->cpumask) && cpumask_weight(dev->cpumask) == 1 && !tick_is_broadcast_device(dev)) { BUG_ON(!clockevent_state_detached(dev)); list_del(&dev->list); } } raw_spin_unlock(&clockevents_lock); } #endif #ifdef CONFIG_SYSFS static const struct bus_type clockevents_subsys = { .name = "clockevents", .dev_name = "clockevent", }; static DEFINE_PER_CPU(struct device, tick_percpu_dev); static struct tick_device *tick_get_tick_dev(struct device *dev); static ssize_t current_device_show(struct device *dev, struct device_attribute *attr, char *buf) { struct tick_device *td; ssize_t count = 0; raw_spin_lock_irq(&clockevents_lock); td = tick_get_tick_dev(dev); if (td && td->evtdev) count = sysfs_emit(buf, "%s\n", td->evtdev->name); raw_spin_unlock_irq(&clockevents_lock); return count; } static DEVICE_ATTR_RO(current_device); /* We don't support the abomination of removable broadcast devices */ static ssize_t unbind_device_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { char name[CS_NAME_LEN]; ssize_t ret = sysfs_get_uname(buf, name, count); struct clock_event_device *ce = NULL, *iter; if (ret < 0) return ret; ret = -ENODEV; mutex_lock(&clockevents_mutex); raw_spin_lock_irq(&clockevents_lock); list_for_each_entry(iter, &clockevent_devices, list) { if (!strcmp(iter->name, name)) { ret = __clockevents_try_unbind(iter, dev->id); ce = iter; break; } } raw_spin_unlock_irq(&clockevents_lock); /* * We hold clockevents_mutex, so ce can't go away */ if (ret == -EAGAIN) ret = clockevents_unbind(ce, dev->id); mutex_unlock(&clockevents_mutex); return ret ? ret : count; } static DEVICE_ATTR_WO(unbind_device); #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST static struct device tick_bc_dev = { .init_name = "broadcast", .id = 0, .bus = &clockevents_subsys, }; static struct tick_device *tick_get_tick_dev(struct device *dev) { return dev == &tick_bc_dev ? tick_get_broadcast_device() : &per_cpu(tick_cpu_device, dev->id); } static __init int tick_broadcast_init_sysfs(void) { int err = device_register(&tick_bc_dev); if (!err) err = device_create_file(&tick_bc_dev, &dev_attr_current_device); return err; } #else static struct tick_device *tick_get_tick_dev(struct device *dev) { return &per_cpu(tick_cpu_device, dev->id); } static inline int tick_broadcast_init_sysfs(void) { return 0; } #endif static int __init tick_init_sysfs(void) { int cpu; for_each_possible_cpu(cpu) { struct device *dev = &per_cpu(tick_percpu_dev, cpu); int err; dev->id = cpu; dev->bus = &clockevents_subsys; err = device_register(dev); if (!err) err = device_create_file(dev, &dev_attr_current_device); if (!err) err = device_create_file(dev, &dev_attr_unbind_device); if (err) return err; } return tick_broadcast_init_sysfs(); } static int __init clockevents_init_sysfs(void) { int err = subsys_system_register(&clockevents_subsys, NULL); if (!err) err = tick_init_sysfs(); return err; } device_initcall(clockevents_init_sysfs); #endif /* SYSFS */ |
| 18 18 18 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | /* * linux/fs/nls/nls_iso8859-6.c * * Charset iso8859-6 translation tables. * Generated automatically from the Unicode and charset * tables from the Unicode Organization (www.unicode.org). * The Unicode to charset table has only exact mappings. */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/nls.h> #include <linux/errno.h> static const wchar_t charset2uni[256] = { /* 0x00*/ 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0005, 0x0006, 0x0007, 0x0008, 0x0009, 0x000a, 0x000b, 0x000c, 0x000d, 0x000e, 0x000f, /* 0x10*/ 0x0010, 0x0011, 0x0012, 0x0013, 0x0014, 0x0015, 0x0016, 0x0017, 0x0018, 0x0019, 0x001a, 0x001b, 0x001c, 0x001d, 0x001e, 0x001f, /* 0x20*/ 0x0020, 0x0021, 0x0022, 0x0023, 0x0024, 0x0025, 0x0026, 0x0027, 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f, /* 0x30*/ 0x0660, 0x0661, 0x0662, 0x0663, 0x0664, 0x0665, 0x0666, 0x0667, 0x0668, 0x0669, 0x003a, 0x003b, 0x003c, 0x003d, 0x003e, 0x003f, /* 0x40*/ 0x0040, 0x0041, 0x0042, 0x0043, 0x0044, 0x0045, 0x0046, 0x0047, 0x0048, 0x0049, 0x004a, 0x004b, 0x004c, 0x004d, 0x004e, 0x004f, /* 0x50*/ 0x0050, 0x0051, 0x0052, 0x0053, 0x0054, 0x0055, 0x0056, 0x0057, 0x0058, 0x0059, 0x005a, 0x005b, 0x005c, 0x005d, 0x005e, 0x005f, /* 0x60*/ 0x0060, 0x0061, 0x0062, 0x0063, 0x0064, 0x0065, 0x0066, 0x0067, 0x0068, 0x0069, 0x006a, 0x006b, 0x006c, 0x006d, 0x006e, 0x006f, /* 0x70*/ 0x0070, 0x0071, 0x0072, 0x0073, 0x0074, 0x0075, 0x0076, 0x0077, 0x0078, 0x0079, 0x007a, 0x007b, 0x007c, 0x007d, 0x007e, 0x007f, /* 0x80*/ 0x0080, 0x0081, 0x0082, 0x0083, 0x0084, 0x0085, 0x0086, 0x0087, 0x0088, 0x0089, 0x008a, 0x008b, 0x008c, 0x008d, 0x008e, 0x008f, /* 0x90*/ 0x0090, 0x0091, 0x0092, 0x0093, 0x0094, 0x0095, 0x0096, 0x0097, 0x0098, 0x0099, 0x009a, 0x009b, 0x009c, 0x009d, 0x009e, 0x009f, /* 0xa0*/ 0x00a0, 0x0000, 0x0000, 0x0000, 0x00a4, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x060c, 0x00ad, 0x0000, 0x0000, /* 0xb0*/ 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x061b, 0x0000, 0x0000, 0x0000, 0x061f, /* 0xc0*/ 0x0000, 0x0621, 0x0622, 0x0623, 0x0624, 0x0625, 0x0626, 0x0627, 0x0628, 0x0629, 0x062a, 0x062b, 0x062c, 0x062d, 0x062e, 0x062f, /* 0xd0*/ 0x0630, 0x0631, 0x0632, 0x0633, 0x0634, 0x0635, 0x0636, 0x0637, 0x0638, 0x0639, 0x063a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, /* 0xe0*/ 0x0640, 0x0641, 0x0642, 0x0643, 0x0644, 0x0645, 0x0646, 0x0647, 0x0648, 0x0649, 0x064a, 0x064b, 0x064c, 0x064d, 0x064e, 0x064f, /* 0xf0*/ 0x0650, 0x0651, 0x0652, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, }; static const unsigned char page00[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x30-0x37 */ 0x00, 0x00, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0xad, 0x00, 0x00, /* 0xa8-0xaf */ }; static const unsigned char page06[256] = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x00-0x07 */ 0x00, 0x00, 0x00, 0x00, 0xac, 0x00, 0x00, 0x00, /* 0x08-0x0f */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x10-0x17 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0xbf, /* 0x18-0x1f */ 0x00, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0x20-0x27 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0x28-0x2f */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0x30-0x37 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x38-0x3f */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0x40-0x47 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0x48-0x4f */ 0xf0, 0xf1, 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x50-0x57 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x58-0x5f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x60-0x67 */ 0x38, 0x39, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0x68-0x6f */ }; static const unsigned char *const page_uni2charset[256] = { page00, NULL, NULL, NULL, NULL, NULL, page06, NULL, }; static const unsigned char charset2lower[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x40-0x47 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x48-0x4f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x50-0x57 */ 0x78, 0x79, 0x7a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, /* 0x60-0x67 */ 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f, /* 0x68-0x6f */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, /* 0x70-0x77 */ 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0xac, 0xad, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0xbf, /* 0xb8-0xbf */ 0x00, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf8-0xff */ }; static const unsigned char charset2upper[256] = { 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, /* 0x00-0x07 */ 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f, /* 0x08-0x0f */ 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, /* 0x10-0x17 */ 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, /* 0x18-0x1f */ 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, /* 0x20-0x27 */ 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, /* 0x28-0x2f */ 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, /* 0x30-0x37 */ 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, /* 0x38-0x3f */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x40-0x47 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x48-0x4f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x50-0x57 */ 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f, /* 0x58-0x5f */ 0x60, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, /* 0x60-0x67 */ 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f, /* 0x68-0x6f */ 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, /* 0x70-0x77 */ 0x58, 0x59, 0x5a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f, /* 0x78-0x7f */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, /* 0x80-0x87 */ 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f, /* 0x88-0x8f */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, /* 0x90-0x97 */ 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, /* 0x98-0x9f */ 0xa0, 0x00, 0x00, 0x00, 0xa4, 0x00, 0x00, 0x00, /* 0xa0-0xa7 */ 0x00, 0x00, 0x00, 0x00, 0xac, 0xad, 0x00, 0x00, /* 0xa8-0xaf */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xb0-0xb7 */ 0x00, 0x00, 0x00, 0xbb, 0x00, 0x00, 0x00, 0xbf, /* 0xb8-0xbf */ 0x00, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, /* 0xc0-0xc7 */ 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf, /* 0xc8-0xcf */ 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, /* 0xd0-0xd7 */ 0xd8, 0xd9, 0xda, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xd8-0xdf */ 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, /* 0xe0-0xe7 */ 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, /* 0xe8-0xef */ 0xf0, 0xf1, 0xf2, 0x00, 0x00, 0x00, 0x00, 0x00, /* 0xf0-0xf7 */ }; static int uni2char(wchar_t uni, unsigned char *out, int boundlen) { const unsigned char *uni2charset; unsigned char cl = uni & 0x00ff; unsigned char ch = (uni & 0xff00) >> 8; if (boundlen <= 0) return -ENAMETOOLONG; uni2charset = page_uni2charset[ch]; if (uni2charset && uni2charset[cl]) out[0] = uni2charset[cl]; else return -EINVAL; return 1; } static int char2uni(const unsigned char *rawstring, int boundlen, wchar_t *uni) { *uni = charset2uni[*rawstring]; if (*uni == 0x0000) return -EINVAL; return 1; } static struct nls_table table = { .charset = "iso8859-6", .uni2char = uni2char, .char2uni = char2uni, .charset2lower = charset2lower, .charset2upper = charset2upper, }; static int __init init_nls_iso8859_6(void) { return register_nls(&table); } static void __exit exit_nls_iso8859_6(void) { unregister_nls(&table); } module_init(init_nls_iso8859_6) module_exit(exit_nls_iso8859_6) MODULE_DESCRIPTION("NLS ISO 8859-6 (Arabic)"); MODULE_LICENSE("Dual BSD/GPL"); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * (C) 2001 Clemson University and The University of Chicago * * Changes by Acxiom Corporation to add protocol version to kernel * communication, Copyright Acxiom Corporation, 2005. * * See COPYING in top-level directory. */ #include "protocol.h" #include "orangefs-kernel.h" #include "orangefs-dev-proto.h" #include "orangefs-bufmap.h" #include "orangefs-debugfs.h" #include <linux/debugfs.h> #include <linux/slab.h> /* this file implements the /dev/pvfs2-req device node */ uint32_t orangefs_userspace_version; static int open_access_count; static DEFINE_MUTEX(devreq_mutex); #define DUMP_DEVICE_ERROR() \ do { \ gossip_err("*****************************************************\n");\ gossip_err("ORANGEFS Device Error: You cannot open the device file "); \ gossip_err("\n/dev/%s more than once. Please make sure that\nthere " \ "are no ", ORANGEFS_REQDEVICE_NAME); \ gossip_err("instances of a program using this device\ncurrently " \ "running. (You must verify this!)\n"); \ gossip_err("For example, you can use the lsof program as follows:\n");\ gossip_err("'lsof | grep %s' (run this as root)\n", \ ORANGEFS_REQDEVICE_NAME); \ gossip_err(" open_access_count = %d\n", open_access_count); \ gossip_err("*****************************************************\n");\ } while (0) static int hash_func(__u64 tag, int table_size) { return do_div(tag, (unsigned int)table_size); } static void orangefs_devreq_add_op(struct orangefs_kernel_op_s *op) { int index = hash_func(op->tag, hash_table_size); list_add_tail(&op->list, &orangefs_htable_ops_in_progress[index]); } /* * find the op with this tag and remove it from the in progress * hash table. */ static struct orangefs_kernel_op_s *orangefs_devreq_remove_op(__u64 tag) { struct orangefs_kernel_op_s *op, *next; int index; index = hash_func(tag, hash_table_size); spin_lock(&orangefs_htable_ops_in_progress_lock); list_for_each_entry_safe(op, next, &orangefs_htable_ops_in_progress[index], list) { if (op->tag == tag && !op_state_purged(op) && !op_state_given_up(op)) { list_del_init(&op->list); spin_unlock(&orangefs_htable_ops_in_progress_lock); return op; } } spin_unlock(&orangefs_htable_ops_in_progress_lock); return NULL; } /* Returns whether any FS are still pending remounted */ static int mark_all_pending_mounts(void) { int unmounted = 1; struct orangefs_sb_info_s *orangefs_sb = NULL; spin_lock(&orangefs_superblocks_lock); list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) { /* All of these file system require a remount */ orangefs_sb->mount_pending = 1; unmounted = 0; } spin_unlock(&orangefs_superblocks_lock); return unmounted; } /* * Determine if a given file system needs to be remounted or not * Returns -1 on error * 0 if already mounted * 1 if needs remount */ static int fs_mount_pending(__s32 fsid) { int mount_pending = -1; struct orangefs_sb_info_s *orangefs_sb = NULL; spin_lock(&orangefs_superblocks_lock); list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) { if (orangefs_sb->fs_id == fsid) { mount_pending = orangefs_sb->mount_pending; break; } } spin_unlock(&orangefs_superblocks_lock); return mount_pending; } static int orangefs_devreq_open(struct inode *inode, struct file *file) { int ret = -EINVAL; /* in order to ensure that the filesystem driver sees correct UIDs */ if (file->f_cred->user_ns != &init_user_ns) { gossip_err("%s: device cannot be opened outside init_user_ns\n", __func__); goto out; } if (!(file->f_flags & O_NONBLOCK)) { gossip_err("%s: device cannot be opened in blocking mode\n", __func__); goto out; } ret = -EACCES; gossip_debug(GOSSIP_DEV_DEBUG, "client-core: opening device\n"); mutex_lock(&devreq_mutex); if (open_access_count == 0) { open_access_count = 1; ret = 0; } else { DUMP_DEVICE_ERROR(); } mutex_unlock(&devreq_mutex); out: gossip_debug(GOSSIP_DEV_DEBUG, "pvfs2-client-core: open device complete (ret = %d)\n", ret); return ret; } /* Function for read() callers into the device */ static ssize_t orangefs_devreq_read(struct file *file, char __user *buf, size_t count, loff_t *offset) { struct orangefs_kernel_op_s *op, *temp; __s32 proto_ver = ORANGEFS_KERNEL_PROTO_VERSION; static __s32 magic = ORANGEFS_DEVREQ_MAGIC; struct orangefs_kernel_op_s *cur_op; unsigned long ret; /* We do not support blocking IO. */ if (!(file->f_flags & O_NONBLOCK)) { gossip_err("%s: blocking read from client-core.\n", __func__); return -EINVAL; } /* * The client will do an ioctl to find MAX_DEV_REQ_UPSIZE, then * always read with that size buffer. */ if (count != MAX_DEV_REQ_UPSIZE) { gossip_err("orangefs: client-core tried to read wrong size\n"); return -EINVAL; } /* Check for an empty list before locking. */ if (list_empty(&orangefs_request_list)) return -EAGAIN; restart: cur_op = NULL; /* Get next op (if any) from top of list. */ spin_lock(&orangefs_request_list_lock); list_for_each_entry_safe(op, temp, &orangefs_request_list, list) { __s32 fsid; /* This lock is held past the end of the loop when we break. */ spin_lock(&op->lock); if (unlikely(op_state_purged(op) || op_state_given_up(op))) { spin_unlock(&op->lock); continue; } fsid = fsid_of_op(op); if (fsid != ORANGEFS_FS_ID_NULL) { int ret; /* Skip ops whose filesystem needs to be mounted. */ ret = fs_mount_pending(fsid); if (ret == 1) { gossip_debug(GOSSIP_DEV_DEBUG, "%s: mount pending, skipping op tag " "%llu %s\n", __func__, llu(op->tag), get_opname_string(op)); spin_unlock(&op->lock); continue; /* * Skip ops whose filesystem we don't know about unless * it is being mounted or unmounted. It is possible for * a filesystem we don't know about to be unmounted if * it fails to mount in the kernel after userspace has * been sent the mount request. */ /* XXX: is there a better way to detect this? */ } else if (ret == -1 && !(op->upcall.type == ORANGEFS_VFS_OP_FS_MOUNT || op->upcall.type == ORANGEFS_VFS_OP_GETATTR || op->upcall.type == ORANGEFS_VFS_OP_FS_UMOUNT)) { gossip_debug(GOSSIP_DEV_DEBUG, "orangefs: skipping op tag %llu %s\n", llu(op->tag), get_opname_string(op)); gossip_err( "orangefs: ERROR: fs_mount_pending %d\n", fsid); spin_unlock(&op->lock); continue; } } /* * Either this op does not pertain to a filesystem, is mounting * a filesystem, or pertains to a mounted filesystem. Let it * through. */ cur_op = op; break; } /* * At this point we either have a valid op and can continue or have not * found an op and must ask the client to try again later. */ if (!cur_op) { spin_unlock(&orangefs_request_list_lock); return -EAGAIN; } gossip_debug(GOSSIP_DEV_DEBUG, "%s: reading op tag %llu %s\n", __func__, llu(cur_op->tag), get_opname_string(cur_op)); /* * Such an op should never be on the list in the first place. If so, we * will abort. */ if (op_state_in_progress(cur_op) || op_state_serviced(cur_op)) { gossip_err("orangefs: ERROR: Current op already queued.\n"); list_del_init(&cur_op->list); spin_unlock(&cur_op->lock); spin_unlock(&orangefs_request_list_lock); return -EAGAIN; } list_del_init(&cur_op->list); spin_unlock(&orangefs_request_list_lock); spin_unlock(&cur_op->lock); /* Push the upcall out. */ ret = copy_to_user(buf, &proto_ver, sizeof(__s32)); if (ret != 0) goto error; ret = copy_to_user(buf + sizeof(__s32), &magic, sizeof(__s32)); if (ret != 0) goto error; ret = copy_to_user(buf + 2 * sizeof(__s32), &cur_op->tag, sizeof(__u64)); if (ret != 0) goto error; ret = copy_to_user(buf + 2 * sizeof(__s32) + sizeof(__u64), &cur_op->upcall, sizeof(struct orangefs_upcall_s)); if (ret != 0) goto error; spin_lock(&orangefs_htable_ops_in_progress_lock); spin_lock(&cur_op->lock); if (unlikely(op_state_given_up(cur_op))) { spin_unlock(&cur_op->lock); spin_unlock(&orangefs_htable_ops_in_progress_lock); complete(&cur_op->waitq); goto restart; } /* * Set the operation to be in progress and move it between lists since * it has been sent to the client. */ set_op_state_inprogress(cur_op); gossip_debug(GOSSIP_DEV_DEBUG, "%s: 1 op:%s: op_state:%d: process:%s:\n", __func__, get_opname_string(cur_op), cur_op->op_state, current->comm); orangefs_devreq_add_op(cur_op); spin_unlock(&cur_op->lock); spin_unlock(&orangefs_htable_ops_in_progress_lock); /* The client only asks to read one size buffer. */ return MAX_DEV_REQ_UPSIZE; error: /* * We were unable to copy the op data to the client. Put the op back in * list. If client has crashed, the op will be purged later when the * device is released. */ gossip_err("orangefs: Failed to copy data to user space\n"); spin_lock(&orangefs_request_list_lock); spin_lock(&cur_op->lock); if (likely(!op_state_given_up(cur_op))) { set_op_state_waiting(cur_op); gossip_debug(GOSSIP_DEV_DEBUG, "%s: 2 op:%s: op_state:%d: process:%s:\n", __func__, get_opname_string(cur_op), cur_op->op_state, current->comm); list_add(&cur_op->list, &orangefs_request_list); spin_unlock(&cur_op->lock); } else { spin_unlock(&cur_op->lock); complete(&cur_op->waitq); } spin_unlock(&orangefs_request_list_lock); return -EFAULT; } /* * Function for writev() callers into the device. * * Userspace should have written: * - __u32 version * - __u32 magic * - __u64 tag * - struct orangefs_downcall_s * - trailer buffer (in the case of READDIR operations) */ static ssize_t orangefs_devreq_write_iter(struct kiocb *iocb, struct iov_iter *iter) { ssize_t ret; struct orangefs_kernel_op_s *op = NULL; struct { __u32 version; __u32 magic; __u64 tag; } head; int total = ret = iov_iter_count(iter); int downcall_size = sizeof(struct orangefs_downcall_s); int head_size = sizeof(head); gossip_debug(GOSSIP_DEV_DEBUG, "%s: total:%d: ret:%zd:\n", __func__, total, ret); if (total < MAX_DEV_REQ_DOWNSIZE) { gossip_err("%s: total:%d: must be at least:%u:\n", __func__, total, (unsigned int) MAX_DEV_REQ_DOWNSIZE); return -EFAULT; } if (!copy_from_iter_full(&head, head_size, iter)) { gossip_err("%s: failed to copy head.\n", __func__); return -EFAULT; } if (head.version < ORANGEFS_MINIMUM_USERSPACE_VERSION) { gossip_err("%s: userspace claims version" "%d, minimum version required: %d.\n", __func__, head.version, ORANGEFS_MINIMUM_USERSPACE_VERSION); return -EPROTO; } if (head.magic != ORANGEFS_DEVREQ_MAGIC) { gossip_err("Error: Device magic number does not match.\n"); return -EPROTO; } if (!orangefs_userspace_version) { orangefs_userspace_version = head.version; } else if (orangefs_userspace_version != head.version) { gossip_err("Error: userspace version changes\n"); return -EPROTO; } /* remove the op from the in progress hash table */ op = orangefs_devreq_remove_op(head.tag); if (!op) { gossip_debug(GOSSIP_DEV_DEBUG, "%s: No one's waiting for tag %llu\n", __func__, llu(head.tag)); return ret; } if (!copy_from_iter_full(&op->downcall, downcall_size, iter)) { gossip_err("%s: failed to copy downcall.\n", __func__); goto Efault; } if (op->downcall.status) goto wakeup; /* * We've successfully peeled off the head and the downcall. * Something has gone awry if total doesn't equal the * sum of head_size, downcall_size and trailer_size. */ if ((head_size + downcall_size + op->downcall.trailer_size) != total) { gossip_err("%s: funky write, head_size:%d" ": downcall_size:%d: trailer_size:%lld" ": total size:%d:\n", __func__, head_size, downcall_size, op->downcall.trailer_size, total); goto Efault; } /* Only READDIR operations should have trailers. */ if ((op->downcall.type != ORANGEFS_VFS_OP_READDIR) && (op->downcall.trailer_size != 0)) { gossip_err("%s: %x operation with trailer.", __func__, op->downcall.type); goto Efault; } /* READDIR operations should always have trailers. */ if ((op->downcall.type == ORANGEFS_VFS_OP_READDIR) && (op->downcall.trailer_size == 0)) { gossip_err("%s: %x operation with no trailer.", __func__, op->downcall.type); goto Efault; } if (op->downcall.type != ORANGEFS_VFS_OP_READDIR) goto wakeup; op->downcall.trailer_buf = vzalloc(op->downcall.trailer_size); if (!op->downcall.trailer_buf) goto Enomem; if (!copy_from_iter_full(op->downcall.trailer_buf, op->downcall.trailer_size, iter)) { gossip_err("%s: failed to copy trailer.\n", __func__); vfree(op->downcall.trailer_buf); goto Efault; } wakeup: /* * Return to vfs waitqueue, and back to service_operation * through wait_for_matching_downcall. */ spin_lock(&op->lock); if (unlikely(op_is_cancel(op))) { spin_unlock(&op->lock); put_cancel(op); } else if (unlikely(op_state_given_up(op))) { spin_unlock(&op->lock); complete(&op->waitq); } else { set_op_state_serviced(op); gossip_debug(GOSSIP_DEV_DEBUG, "%s: op:%s: op_state:%d: process:%s:\n", __func__, get_opname_string(op), op->op_state, current->comm); spin_unlock(&op->lock); } return ret; Efault: op->downcall.status = -(ORANGEFS_ERROR_BIT | 9); ret = -EFAULT; goto wakeup; Enomem: op->downcall.status = -(ORANGEFS_ERROR_BIT | 8); ret = -ENOMEM; goto wakeup; } /* * NOTE: gets called when the last reference to this device is dropped. * Using the open_access_count variable, we enforce a reference count * on this file so that it can be opened by only one process at a time. * the devreq_mutex is used to make sure all i/o has completed * before we call orangefs_bufmap_finalize, and similar such tricky * situations */ static int orangefs_devreq_release(struct inode *inode, struct file *file) { int unmounted = 0; gossip_debug(GOSSIP_DEV_DEBUG, "%s:pvfs2-client-core: exiting, closing device\n", __func__); mutex_lock(&devreq_mutex); orangefs_bufmap_finalize(); open_access_count = -1; unmounted = mark_all_pending_mounts(); gossip_debug(GOSSIP_DEV_DEBUG, "ORANGEFS Device Close: Filesystem(s) %s\n", (unmounted ? "UNMOUNTED" : "MOUNTED")); purge_waiting_ops(); purge_inprogress_ops(); orangefs_bufmap_run_down(); gossip_debug(GOSSIP_DEV_DEBUG, "pvfs2-client-core: device close complete\n"); open_access_count = 0; orangefs_userspace_version = 0; mutex_unlock(&devreq_mutex); return 0; } int is_daemon_in_service(void) { int in_service; /* * What this function does is checks if client-core is alive * based on the access count we maintain on the device. */ mutex_lock(&devreq_mutex); in_service = open_access_count == 1 ? 0 : -EIO; mutex_unlock(&devreq_mutex); return in_service; } bool __is_daemon_in_service(void) { return open_access_count == 1; } static inline long check_ioctl_command(unsigned int command) { /* Check for valid ioctl codes */ if (_IOC_TYPE(command) != ORANGEFS_DEV_MAGIC) { gossip_err("device ioctl magic numbers don't match! Did you rebuild pvfs2-client-core/libpvfs2? [cmd %x, magic %x != %x]\n", command, _IOC_TYPE(command), ORANGEFS_DEV_MAGIC); return -EINVAL; } /* and valid ioctl commands */ if (_IOC_NR(command) >= ORANGEFS_DEV_MAXNR || _IOC_NR(command) <= 0) { gossip_err("Invalid ioctl command number [%d >= %d]\n", _IOC_NR(command), ORANGEFS_DEV_MAXNR); return -ENOIOCTLCMD; } return 0; } static long dispatch_ioctl_command(unsigned int command, unsigned long arg) { static __s32 magic = ORANGEFS_DEVREQ_MAGIC; static __s32 max_up_size = MAX_DEV_REQ_UPSIZE; static __s32 max_down_size = MAX_DEV_REQ_DOWNSIZE; struct ORANGEFS_dev_map_desc user_desc; int ret = 0; int upstream_kmod = 1; struct orangefs_sb_info_s *orangefs_sb; /* mtmoore: add locking here */ switch (command) { case ORANGEFS_DEV_GET_MAGIC: return ((put_user(magic, (__s32 __user *) arg) == -EFAULT) ? -EIO : 0); case ORANGEFS_DEV_GET_MAX_UPSIZE: return ((put_user(max_up_size, (__s32 __user *) arg) == -EFAULT) ? -EIO : 0); case ORANGEFS_DEV_GET_MAX_DOWNSIZE: return ((put_user(max_down_size, (__s32 __user *) arg) == -EFAULT) ? -EIO : 0); case ORANGEFS_DEV_MAP: ret = copy_from_user(&user_desc, (struct ORANGEFS_dev_map_desc __user *) arg, sizeof(struct ORANGEFS_dev_map_desc)); /* WTF -EIO and not -EFAULT? */ return ret ? -EIO : orangefs_bufmap_initialize(&user_desc); case ORANGEFS_DEV_REMOUNT_ALL: gossip_debug(GOSSIP_DEV_DEBUG, "%s: got ORANGEFS_DEV_REMOUNT_ALL\n", __func__); /* * remount all mounted orangefs volumes to regain the lost * dynamic mount tables (if any) -- NOTE: this is done * without keeping the superblock list locked due to the * upcall/downcall waiting. also, the request mutex is * used to ensure that no operations will be serviced until * all of the remounts are serviced (to avoid ops between * mounts to fail) */ ret = mutex_lock_interruptible(&orangefs_request_mutex); if (ret < 0) return ret; gossip_debug(GOSSIP_DEV_DEBUG, "%s: priority remount in progress\n", __func__); spin_lock(&orangefs_superblocks_lock); list_for_each_entry(orangefs_sb, &orangefs_superblocks, list) { /* * We have to drop the spinlock, so entries can be * removed. They can't be freed, though, so we just * keep the forward pointers and zero the back ones - * that way we can get to the rest of the list. */ if (!orangefs_sb->list.prev) continue; gossip_debug(GOSSIP_DEV_DEBUG, "%s: Remounting SB %p\n", __func__, orangefs_sb); spin_unlock(&orangefs_superblocks_lock); ret = orangefs_remount(orangefs_sb); spin_lock(&orangefs_superblocks_lock); if (ret) { gossip_debug(GOSSIP_DEV_DEBUG, "SB %p remount failed\n", orangefs_sb); break; } } spin_unlock(&orangefs_superblocks_lock); gossip_debug(GOSSIP_DEV_DEBUG, "%s: priority remount complete\n", __func__); mutex_unlock(&orangefs_request_mutex); return ret; case ORANGEFS_DEV_UPSTREAM: ret = copy_to_user((void __user *)arg, &upstream_kmod, sizeof(upstream_kmod)); if (ret != 0) return -EIO; else return ret; case ORANGEFS_DEV_CLIENT_MASK: return orangefs_debugfs_new_client_mask((void __user *)arg); case ORANGEFS_DEV_CLIENT_STRING: return orangefs_debugfs_new_client_string((void __user *)arg); case ORANGEFS_DEV_DEBUG: return orangefs_debugfs_new_debug((void __user *)arg); default: return -ENOIOCTLCMD; } return -ENOIOCTLCMD; } static long orangefs_devreq_ioctl(struct file *file, unsigned int command, unsigned long arg) { long ret; /* Check for properly constructed commands */ ret = check_ioctl_command(command); if (ret < 0) return (int)ret; return (int)dispatch_ioctl_command(command, arg); } #ifdef CONFIG_COMPAT /* CONFIG_COMPAT is in .config */ /* Compat structure for the ORANGEFS_DEV_MAP ioctl */ struct ORANGEFS_dev_map_desc32 { compat_uptr_t ptr; __s32 total_size; __s32 size; __s32 count; }; /* * 32 bit user-space apps' ioctl handlers when kernel modules * is compiled as a 64 bit one */ static long orangefs_devreq_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long args) { long ret; /* Check for properly constructed commands */ ret = check_ioctl_command(cmd); if (ret < 0) return ret; if (cmd == ORANGEFS_DEV_MAP) { struct ORANGEFS_dev_map_desc desc; struct ORANGEFS_dev_map_desc32 d32; if (copy_from_user(&d32, (void __user *)args, sizeof(d32))) return -EFAULT; desc.ptr = compat_ptr(d32.ptr); desc.total_size = d32.total_size; desc.size = d32.size; desc.count = d32.count; return orangefs_bufmap_initialize(&desc); } /* no other ioctl requires translation */ return dispatch_ioctl_command(cmd, args); } #endif /* CONFIG_COMPAT is in .config */ static __poll_t orangefs_devreq_poll(struct file *file, struct poll_table_struct *poll_table) { __poll_t poll_revent_mask = 0; poll_wait(file, &orangefs_request_list_waitq, poll_table); if (!list_empty(&orangefs_request_list)) poll_revent_mask |= EPOLLIN; return poll_revent_mask; } /* the assigned character device major number */ static int orangefs_dev_major; static const struct file_operations orangefs_devreq_file_operations = { .owner = THIS_MODULE, .read = orangefs_devreq_read, .write_iter = orangefs_devreq_write_iter, .open = orangefs_devreq_open, .release = orangefs_devreq_release, .unlocked_ioctl = orangefs_devreq_ioctl, #ifdef CONFIG_COMPAT /* CONFIG_COMPAT is in .config */ .compat_ioctl = orangefs_devreq_compat_ioctl, #endif .poll = orangefs_devreq_poll }; /* * Initialize orangefs device specific state: * Must be called at module load time only */ int orangefs_dev_init(void) { /* register orangefs-req device */ orangefs_dev_major = register_chrdev(0, ORANGEFS_REQDEVICE_NAME, &orangefs_devreq_file_operations); if (orangefs_dev_major < 0) { gossip_debug(GOSSIP_DEV_DEBUG, "Failed to register /dev/%s (error %d)\n", ORANGEFS_REQDEVICE_NAME, orangefs_dev_major); return orangefs_dev_major; } gossip_debug(GOSSIP_DEV_DEBUG, "*** /dev/%s character device registered ***\n", ORANGEFS_REQDEVICE_NAME); gossip_debug(GOSSIP_DEV_DEBUG, "'mknod /dev/%s c %d 0'.\n", ORANGEFS_REQDEVICE_NAME, orangefs_dev_major); return 0; } void orangefs_dev_cleanup(void) { unregister_chrdev(orangefs_dev_major, ORANGEFS_REQDEVICE_NAME); gossip_debug(GOSSIP_DEV_DEBUG, "*** /dev/%s character device unregistered ***\n", ORANGEFS_REQDEVICE_NAME); } |
| 2 1 60 60 13 13 13 13 13 13 13 13 13 61 1 60 60 47 13 13 13 60 9 9 9 9 9 8 1 14 1 2 5 6 1 1 9 7 2 1 7 3 39 1 1 32 19 11 2 31 7 39 33 8 38 35 2 33 2 1 28 5 32 32 20 32 1 6 20 6 19 7 14 1 4 2 2 4 4 5 1 4 1 1 2 6 11 11 1 1 2 1 24 14 6 5 16 3 1 1 11 11 48 39 9 43 1 42 41 39 26 19 1 1 10 1 1 1 1 1 2 1 1 1 1 1 1 1 5 1 1 1 1 2 25 29 2 1 1 1 2 1 1 1 4 1 1 3 1 1 15 17 1 16 1 11 2 1 14 1 3 1 4 4 14 3 10 2 1 38 6 3 1 3 1 6 1 3 1 8 1 1 1 2 3 1 12 6 1 15 1 1 1 4 1 3 4 6 278 282 57 382 97 284 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/ioctl.c * * Copyright (C) 1993, 1994, 1995 * Remy Card (card@masi.ibp.fr) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) */ #include <linux/fs.h> #include <linux/capability.h> #include <linux/time.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/random.h> #include <linux/uaccess.h> #include <linux/delay.h> #include <linux/iversion.h> #include <linux/fileattr.h> #include <linux/uuid.h> #include "ext4_jbd2.h" #include "ext4.h" #include <linux/fsmap.h> #include "fsmap.h" #include <trace/events/ext4.h> typedef void ext4_update_sb_callback(struct ext4_super_block *es, const void *arg); /* * Superblock modification callback function for changing file system * label */ static void ext4_sb_setlabel(struct ext4_super_block *es, const void *arg) { /* Sanity check, this should never happen */ BUILD_BUG_ON(sizeof(es->s_volume_name) < EXT4_LABEL_MAX); memcpy(es->s_volume_name, (char *)arg, EXT4_LABEL_MAX); } /* * Superblock modification callback function for changing file system * UUID. */ static void ext4_sb_setuuid(struct ext4_super_block *es, const void *arg) { memcpy(es->s_uuid, (__u8 *)arg, UUID_SIZE); } static int ext4_update_primary_sb(struct super_block *sb, handle_t *handle, ext4_update_sb_callback func, const void *arg) { int err = 0; struct ext4_sb_info *sbi = EXT4_SB(sb); struct buffer_head *bh = sbi->s_sbh; struct ext4_super_block *es = sbi->s_es; trace_ext4_update_sb(sb, bh->b_blocknr, 1); BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); if (err) goto out_err; lock_buffer(bh); func(es, arg); ext4_superblock_csum_set(sb); unlock_buffer(bh); if (buffer_write_io_error(bh) || !buffer_uptodate(bh)) { ext4_msg(sbi->s_sb, KERN_ERR, "previous I/O error to " "superblock detected"); clear_buffer_write_io_error(bh); set_buffer_uptodate(bh); } err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) goto out_err; err = sync_dirty_buffer(bh); out_err: ext4_std_error(sb, err); return err; } /* * Update one backup superblock in the group 'grp' using the callback * function 'func' and argument 'arg'. If the handle is NULL the * modification is not journalled. * * Returns: 0 when no modification was done (no superblock in the group) * 1 when the modification was successful * <0 on error */ static int ext4_update_backup_sb(struct super_block *sb, handle_t *handle, ext4_group_t grp, ext4_update_sb_callback func, const void *arg) { int err = 0; ext4_fsblk_t sb_block; struct buffer_head *bh; unsigned long offset = 0; struct ext4_super_block *es; if (!ext4_bg_has_super(sb, grp)) return 0; /* * For the group 0 there is always 1k padding, so we have * either adjust offset, or sb_block depending on blocksize */ if (grp == 0) { sb_block = 1 * EXT4_MIN_BLOCK_SIZE; offset = do_div(sb_block, sb->s_blocksize); } else { sb_block = ext4_group_first_block_no(sb, grp); offset = 0; } trace_ext4_update_sb(sb, sb_block, handle ? 1 : 0); bh = ext4_sb_bread(sb, sb_block, 0); if (IS_ERR(bh)) return PTR_ERR(bh); if (handle) { BUFFER_TRACE(bh, "get_write_access"); err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE); if (err) goto out_bh; } es = (struct ext4_super_block *) (bh->b_data + offset); lock_buffer(bh); if (ext4_has_feature_metadata_csum(sb) && es->s_checksum != ext4_superblock_csum(es)) { ext4_msg(sb, KERN_ERR, "Invalid checksum for backup " "superblock %llu", sb_block); unlock_buffer(bh); goto out_bh; } func(es, arg); if (ext4_has_feature_metadata_csum(sb)) es->s_checksum = ext4_superblock_csum(es); set_buffer_uptodate(bh); unlock_buffer(bh); if (handle) { err = ext4_handle_dirty_metadata(handle, NULL, bh); if (err) goto out_bh; } else { BUFFER_TRACE(bh, "marking dirty"); mark_buffer_dirty(bh); } err = sync_dirty_buffer(bh); out_bh: brelse(bh); ext4_std_error(sb, err); return (err) ? err : 1; } /* * Update primary and backup superblocks using the provided function * func and argument arg. * * Only the primary superblock and at most two backup superblock * modifications are journalled; the rest is modified without journal. * This is safe because e2fsck will re-write them if there is a problem, * and we're very unlikely to ever need more than two backups. */ static int ext4_update_superblocks_fn(struct super_block *sb, ext4_update_sb_callback func, const void *arg) { handle_t *handle; ext4_group_t ngroups; unsigned int three = 1; unsigned int five = 5; unsigned int seven = 7; int err = 0, ret, i; ext4_group_t grp, primary_grp; struct ext4_sb_info *sbi = EXT4_SB(sb); /* * We can't update superblocks while the online resize is running */ if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING, &sbi->s_ext4_flags)) { ext4_msg(sb, KERN_ERR, "Can't modify superblock while" "performing online resize"); return -EBUSY; } /* * We're only going to update primary superblock and two * backup superblocks in this transaction. */ handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 3); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto out; } /* Update primary superblock */ err = ext4_update_primary_sb(sb, handle, func, arg); if (err) { ext4_msg(sb, KERN_ERR, "Failed to update primary " "superblock"); goto out_journal; } primary_grp = ext4_get_group_number(sb, sbi->s_sbh->b_blocknr); ngroups = ext4_get_groups_count(sb); /* * Update backup superblocks. We have to start from group 0 * because it might not be where the primary superblock is * if the fs is mounted with -o sb=<backup_sb_block> */ i = 0; grp = 0; while (grp < ngroups) { /* Skip primary superblock */ if (grp == primary_grp) goto next_grp; ret = ext4_update_backup_sb(sb, handle, grp, func, arg); if (ret < 0) { /* Ignore bad checksum; try to update next sb */ if (ret == -EFSBADCRC) goto next_grp; err = ret; goto out_journal; } i += ret; if (handle && i > 1) { /* * We're only journalling primary superblock and * two backup superblocks; the rest is not * journalled. */ err = ext4_journal_stop(handle); if (err) goto out; handle = NULL; } next_grp: grp = ext4_list_backups(sb, &three, &five, &seven); } out_journal: if (handle) { ret = ext4_journal_stop(handle); if (ret && !err) err = ret; } out: clear_bit_unlock(EXT4_FLAGS_RESIZING, &sbi->s_ext4_flags); smp_mb__after_atomic(); return err ? err : 0; } /* * Swap memory between @a and @b for @len bytes. * * @a: pointer to first memory area * @b: pointer to second memory area * @len: number of bytes to swap * */ static void memswap(void *a, void *b, size_t len) { unsigned char *ap, *bp; ap = (unsigned char *)a; bp = (unsigned char *)b; while (len-- > 0) { swap(*ap, *bp); ap++; bp++; } } /* * Swap i_data and associated attributes between @inode1 and @inode2. * This function is used for the primary swap between inode1 and inode2 * and also to revert this primary swap in case of errors. * * Therefore you have to make sure, that calling this method twice * will revert all changes. * * @inode1: pointer to first inode * @inode2: pointer to second inode */ static void swap_inode_data(struct inode *inode1, struct inode *inode2) { loff_t isize; struct ext4_inode_info *ei1; struct ext4_inode_info *ei2; unsigned long tmp; struct timespec64 ts1, ts2; ei1 = EXT4_I(inode1); ei2 = EXT4_I(inode2); swap(inode1->i_version, inode2->i_version); ts1 = inode_get_atime(inode1); ts2 = inode_get_atime(inode2); inode_set_atime_to_ts(inode1, ts2); inode_set_atime_to_ts(inode2, ts1); ts1 = inode_get_mtime(inode1); ts2 = inode_get_mtime(inode2); inode_set_mtime_to_ts(inode1, ts2); inode_set_mtime_to_ts(inode2, ts1); memswap(ei1->i_data, ei2->i_data, sizeof(ei1->i_data)); tmp = ei1->i_flags & EXT4_FL_SHOULD_SWAP; ei1->i_flags = (ei2->i_flags & EXT4_FL_SHOULD_SWAP) | (ei1->i_flags & ~EXT4_FL_SHOULD_SWAP); ei2->i_flags = tmp | (ei2->i_flags & ~EXT4_FL_SHOULD_SWAP); swap(ei1->i_disksize, ei2->i_disksize); ext4_es_remove_extent(inode1, 0, EXT_MAX_BLOCKS); ext4_es_remove_extent(inode2, 0, EXT_MAX_BLOCKS); isize = i_size_read(inode1); i_size_write(inode1, i_size_read(inode2)); i_size_write(inode2, isize); } void ext4_reset_inode_seed(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); __le32 inum = cpu_to_le32(inode->i_ino); __le32 gen = cpu_to_le32(inode->i_generation); __u32 csum; if (!ext4_has_feature_metadata_csum(inode->i_sb)) return; csum = ext4_chksum(sbi->s_csum_seed, (__u8 *)&inum, sizeof(inum)); ei->i_csum_seed = ext4_chksum(csum, (__u8 *)&gen, sizeof(gen)); } /* * Swap the information from the given @inode and the inode * EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other * important fields of the inodes. * * @sb: the super block of the filesystem * @idmap: idmap of the mount the inode was found from * @inode: the inode to swap with EXT4_BOOT_LOADER_INO * */ static long swap_inode_boot_loader(struct super_block *sb, struct mnt_idmap *idmap, struct inode *inode) { handle_t *handle; int err; struct inode *inode_bl; struct ext4_inode_info *ei_bl; qsize_t size, size_bl, diff; blkcnt_t blocks; unsigned short bytes; inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL | EXT4_IGET_BAD); if (IS_ERR(inode_bl)) return PTR_ERR(inode_bl); ei_bl = EXT4_I(inode_bl); /* Protect orig inodes against a truncate and make sure, * that only 1 swap_inode_boot_loader is running. */ lock_two_nondirectories(inode, inode_bl); if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) || IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) || (EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) || ext4_has_inline_data(inode)) { err = -EINVAL; goto journal_err_out; } if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) || !inode_owner_or_capable(idmap, inode) || !capable(CAP_SYS_ADMIN)) { err = -EPERM; goto journal_err_out; } filemap_invalidate_lock(inode->i_mapping); err = filemap_write_and_wait(inode->i_mapping); if (err) goto err_out; err = filemap_write_and_wait(inode_bl->i_mapping); if (err) goto err_out; /* Wait for all existing dio workers */ inode_dio_wait(inode); inode_dio_wait(inode_bl); truncate_inode_pages(&inode->i_data, 0); truncate_inode_pages(&inode_bl->i_data, 0); handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2); if (IS_ERR(handle)) { err = -EINVAL; goto err_out; } ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_SWAP_BOOT, handle); /* Protect extent tree against block allocations via delalloc */ ext4_double_down_write_data_sem(inode, inode_bl); if (is_bad_inode(inode_bl) || !S_ISREG(inode_bl->i_mode)) { /* this inode has never been used as a BOOT_LOADER */ set_nlink(inode_bl, 1); i_uid_write(inode_bl, 0); i_gid_write(inode_bl, 0); inode_bl->i_flags = 0; ei_bl->i_flags = 0; inode_set_iversion(inode_bl, 1); i_size_write(inode_bl, 0); EXT4_I(inode_bl)->i_disksize = inode_bl->i_size; inode_bl->i_mode = S_IFREG; if (ext4_has_feature_extents(sb)) { ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS); ext4_ext_tree_init(handle, inode_bl); } else memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data)); } err = dquot_initialize(inode); if (err) goto err_out1; size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes; size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes; diff = size - size_bl; swap_inode_data(inode, inode_bl); inode_set_ctime_current(inode); inode_set_ctime_current(inode_bl); inode_inc_iversion(inode); inode->i_generation = get_random_u32(); inode_bl->i_generation = get_random_u32(); ext4_reset_inode_seed(inode); ext4_reset_inode_seed(inode_bl); ext4_discard_preallocations(inode); err = ext4_mark_inode_dirty(handle, inode); if (err < 0) { /* No need to update quota information. */ ext4_warning(inode->i_sb, "couldn't mark inode #%lu dirty (err %d)", inode->i_ino, err); /* Revert all changes: */ swap_inode_data(inode, inode_bl); ext4_mark_inode_dirty(handle, inode); goto err_out1; } blocks = inode_bl->i_blocks; bytes = inode_bl->i_bytes; inode_bl->i_blocks = inode->i_blocks; inode_bl->i_bytes = inode->i_bytes; err = ext4_mark_inode_dirty(handle, inode_bl); if (err < 0) { /* No need to update quota information. */ ext4_warning(inode_bl->i_sb, "couldn't mark inode #%lu dirty (err %d)", inode_bl->i_ino, err); goto revert; } /* Bootloader inode should not be counted into quota information. */ if (diff > 0) dquot_free_space(inode, diff); else err = dquot_alloc_space(inode, -1 * diff); if (err < 0) { revert: /* Revert all changes: */ inode_bl->i_blocks = blocks; inode_bl->i_bytes = bytes; swap_inode_data(inode, inode_bl); ext4_mark_inode_dirty(handle, inode); ext4_mark_inode_dirty(handle, inode_bl); } err_out1: ext4_journal_stop(handle); ext4_double_up_write_data_sem(inode, inode_bl); err_out: filemap_invalidate_unlock(inode->i_mapping); journal_err_out: unlock_two_nondirectories(inode, inode_bl); iput(inode_bl); return err; } /* * If immutable is set and we are not clearing it, we're not allowed to change * anything else in the inode. Don't error out if we're only trying to set * immutable on an immutable file. */ static int ext4_ioctl_check_immutable(struct inode *inode, __u32 new_projid, unsigned int flags) { struct ext4_inode_info *ei = EXT4_I(inode); unsigned int oldflags = ei->i_flags; if (!(oldflags & EXT4_IMMUTABLE_FL) || !(flags & EXT4_IMMUTABLE_FL)) return 0; if ((oldflags & ~EXT4_IMMUTABLE_FL) != (flags & ~EXT4_IMMUTABLE_FL)) return -EPERM; if (ext4_has_feature_project(inode->i_sb) && __kprojid_val(ei->i_projid) != new_projid) return -EPERM; return 0; } static void ext4_dax_dontcache(struct inode *inode, unsigned int flags) { struct ext4_inode_info *ei = EXT4_I(inode); if (S_ISDIR(inode->i_mode)) return; if (test_opt2(inode->i_sb, DAX_NEVER) || test_opt(inode->i_sb, DAX_ALWAYS)) return; if ((ei->i_flags ^ flags) & EXT4_DAX_FL) d_mark_dontcache(inode); } static bool dax_compatible(struct inode *inode, unsigned int oldflags, unsigned int flags) { /* Allow the DAX flag to be changed on inline directories */ if (S_ISDIR(inode->i_mode)) { flags &= ~EXT4_INLINE_DATA_FL; oldflags &= ~EXT4_INLINE_DATA_FL; } if (flags & EXT4_DAX_FL) { if ((oldflags & EXT4_DAX_MUT_EXCL) || ext4_test_inode_state(inode, EXT4_STATE_VERITY_IN_PROGRESS)) { return false; } } if ((flags & EXT4_DAX_MUT_EXCL) && (oldflags & EXT4_DAX_FL)) return false; return true; } static int ext4_ioctl_setflags(struct inode *inode, unsigned int flags) { struct ext4_inode_info *ei = EXT4_I(inode); handle_t *handle = NULL; int err = -EPERM, migrate = 0; struct ext4_iloc iloc; unsigned int oldflags, mask, i; struct super_block *sb = inode->i_sb; /* Is it quota file? Do not allow user to mess with it */ if (ext4_is_quota_file(inode)) goto flags_out; oldflags = ei->i_flags; /* * The JOURNAL_DATA flag can only be changed by * the relevant capability. */ if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { if (!capable(CAP_SYS_RESOURCE)) goto flags_out; } if (!dax_compatible(inode, oldflags, flags)) { err = -EOPNOTSUPP; goto flags_out; } if ((flags ^ oldflags) & EXT4_EXTENTS_FL) migrate = 1; if ((flags ^ oldflags) & EXT4_CASEFOLD_FL) { if (!ext4_has_feature_casefold(sb)) { err = -EOPNOTSUPP; goto flags_out; } if (!S_ISDIR(inode->i_mode)) { err = -ENOTDIR; goto flags_out; } if (!ext4_empty_dir(inode)) { err = -ENOTEMPTY; goto flags_out; } } /* * Wait for all pending directio and then flush all the dirty pages * for this file. The flush marks all the pages readonly, so any * subsequent attempt to write to the file (particularly mmap pages) * will come through the filesystem and fail. */ if (S_ISREG(inode->i_mode) && !IS_IMMUTABLE(inode) && (flags & EXT4_IMMUTABLE_FL)) { inode_dio_wait(inode); err = filemap_write_and_wait(inode->i_mapping); if (err) goto flags_out; } handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto flags_out; } if (IS_SYNC(inode)) ext4_handle_sync(handle); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto flags_err; ext4_dax_dontcache(inode, flags); for (i = 0, mask = 1; i < 32; i++, mask <<= 1) { if (!(mask & EXT4_FL_USER_MODIFIABLE)) continue; /* These flags get special treatment later */ if (mask == EXT4_JOURNAL_DATA_FL || mask == EXT4_EXTENTS_FL) continue; if (mask & flags) ext4_set_inode_flag(inode, i); else ext4_clear_inode_flag(inode, i); } ext4_set_inode_flags(inode, false); inode_set_ctime_current(inode); inode_inc_iversion(inode); err = ext4_mark_iloc_dirty(handle, inode, &iloc); flags_err: ext4_journal_stop(handle); if (err) goto flags_out; if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) { /* * Changes to the journaling mode can cause unsafe changes to * S_DAX if the inode is DAX */ if (IS_DAX(inode)) { err = -EBUSY; goto flags_out; } err = ext4_change_inode_journal_flag(inode, flags & EXT4_JOURNAL_DATA_FL); if (err) goto flags_out; } if (migrate) { if (flags & EXT4_EXTENTS_FL) err = ext4_ext_migrate(inode); else err = ext4_ind_migrate(inode); } flags_out: return err; } #ifdef CONFIG_QUOTA static int ext4_ioctl_setproject(struct inode *inode, __u32 projid) { struct super_block *sb = inode->i_sb; struct ext4_inode_info *ei = EXT4_I(inode); int err, rc; handle_t *handle; kprojid_t kprojid; struct ext4_iloc iloc; struct ext4_inode *raw_inode; struct dquot *transfer_to[MAXQUOTAS] = { }; if (!ext4_has_feature_project(sb)) { if (projid != EXT4_DEF_PROJID) return -EOPNOTSUPP; else return 0; } if (EXT4_INODE_SIZE(sb) <= EXT4_GOOD_OLD_INODE_SIZE) return -EOPNOTSUPP; kprojid = make_kprojid(&init_user_ns, (projid_t)projid); if (projid_eq(kprojid, EXT4_I(inode)->i_projid)) return 0; err = -EPERM; /* Is it quota file? Do not allow user to mess with it */ if (ext4_is_quota_file(inode)) return err; err = dquot_initialize(inode); if (err) return err; err = ext4_get_inode_loc(inode, &iloc); if (err) return err; raw_inode = ext4_raw_inode(&iloc); if (!EXT4_FITS_IN_INODE(raw_inode, ei, i_projid)) { err = ext4_expand_extra_isize(inode, EXT4_SB(sb)->s_want_extra_isize, &iloc); if (err) return err; } else { brelse(iloc.bh); } handle = ext4_journal_start(inode, EXT4_HT_QUOTA, EXT4_QUOTA_INIT_BLOCKS(sb) + EXT4_QUOTA_DEL_BLOCKS(sb) + 3); if (IS_ERR(handle)) return PTR_ERR(handle); err = ext4_reserve_inode_write(handle, inode, &iloc); if (err) goto out_stop; transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid)); if (!IS_ERR(transfer_to[PRJQUOTA])) { /* __dquot_transfer() calls back ext4_get_inode_usage() which * counts xattr inode references. */ down_read(&EXT4_I(inode)->xattr_sem); err = __dquot_transfer(inode, transfer_to); up_read(&EXT4_I(inode)->xattr_sem); dqput(transfer_to[PRJQUOTA]); if (err) goto out_dirty; } EXT4_I(inode)->i_projid = kprojid; inode_set_ctime_current(inode); inode_inc_iversion(inode); out_dirty: rc = ext4_mark_iloc_dirty(handle, inode, &iloc); if (!err) err = rc; out_stop: ext4_journal_stop(handle); return err; } #else static int ext4_ioctl_setproject(struct inode *inode, __u32 projid) { if (projid != EXT4_DEF_PROJID) return -EOPNOTSUPP; return 0; } #endif int ext4_force_shutdown(struct super_block *sb, u32 flags) { struct ext4_sb_info *sbi = EXT4_SB(sb); int ret; if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH) return -EINVAL; if (ext4_forced_shutdown(sb)) return 0; ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags); trace_ext4_shutdown(sb, flags); switch (flags) { case EXT4_GOING_FLAGS_DEFAULT: ret = bdev_freeze(sb->s_bdev); if (ret) return ret; set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); bdev_thaw(sb->s_bdev); break; case EXT4_GOING_FLAGS_LOGFLUSH: set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) { (void) ext4_force_commit(sb); jbd2_journal_abort(sbi->s_journal, -ESHUTDOWN); } break; case EXT4_GOING_FLAGS_NOLOGFLUSH: set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags); if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) jbd2_journal_abort(sbi->s_journal, -ESHUTDOWN); break; default: return -EINVAL; } clear_opt(sb, DISCARD); return 0; } static int ext4_ioctl_shutdown(struct super_block *sb, unsigned long arg) { u32 flags; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (get_user(flags, (__u32 __user *)arg)) return -EFAULT; return ext4_force_shutdown(sb, flags); } struct getfsmap_info { struct super_block *gi_sb; struct fsmap_head __user *gi_data; unsigned int gi_idx; __u32 gi_last_flags; }; static int ext4_getfsmap_format(struct ext4_fsmap *xfm, void *priv) { struct getfsmap_info *info = priv; struct fsmap fm; trace_ext4_getfsmap_mapping(info->gi_sb, xfm); info->gi_last_flags = xfm->fmr_flags; ext4_fsmap_from_internal(info->gi_sb, &fm, xfm); if (copy_to_user(&info->gi_data->fmh_recs[info->gi_idx++], &fm, sizeof(struct fsmap))) return -EFAULT; return 0; } static int ext4_ioc_getfsmap(struct super_block *sb, struct fsmap_head __user *arg) { struct getfsmap_info info = { NULL }; struct ext4_fsmap_head xhead = {0}; struct fsmap_head head; bool aborted = false; int error; if (copy_from_user(&head, arg, sizeof(struct fsmap_head))) return -EFAULT; if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) || memchr_inv(head.fmh_keys[0].fmr_reserved, 0, sizeof(head.fmh_keys[0].fmr_reserved)) || memchr_inv(head.fmh_keys[1].fmr_reserved, 0, sizeof(head.fmh_keys[1].fmr_reserved))) return -EINVAL; /* * ext4 doesn't report file extents at all, so the only valid * file offsets are the magic ones (all zeroes or all ones). */ if (head.fmh_keys[0].fmr_offset || (head.fmh_keys[1].fmr_offset != 0 && head.fmh_keys[1].fmr_offset != -1ULL)) return -EINVAL; xhead.fmh_iflags = head.fmh_iflags; xhead.fmh_count = head.fmh_count; ext4_fsmap_to_internal(sb, &xhead.fmh_keys[0], &head.fmh_keys[0]); ext4_fsmap_to_internal(sb, &xhead.fmh_keys[1], &head.fmh_keys[1]); trace_ext4_getfsmap_low_key(sb, &xhead.fmh_keys[0]); trace_ext4_getfsmap_high_key(sb, &xhead.fmh_keys[1]); info.gi_sb = sb; info.gi_data = arg; error = ext4_getfsmap(sb, &xhead, ext4_getfsmap_format, &info); if (error == EXT4_QUERY_RANGE_ABORT) aborted = true; else if (error) return error; /* If we didn't abort, set the "last" flag in the last fmx */ if (!aborted && info.gi_idx) { info.gi_last_flags |= FMR_OF_LAST; if (copy_to_user(&info.gi_data->fmh_recs[info.gi_idx - 1].fmr_flags, &info.gi_last_flags, sizeof(info.gi_last_flags))) return -EFAULT; } /* copy back header */ head.fmh_entries = xhead.fmh_entries; head.fmh_oflags = xhead.fmh_oflags; if (copy_to_user(arg, &head, sizeof(struct fsmap_head))) return -EFAULT; return 0; } static long ext4_ioctl_group_add(struct file *file, struct ext4_new_group_data *input) { struct super_block *sb = file_inode(file)->i_sb; int err, err2=0; err = ext4_resize_begin(sb); if (err) return err; if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); err = -EOPNOTSUPP; goto group_add_out; } err = mnt_want_write_file(file); if (err) goto group_add_out; err = ext4_group_add(sb, input); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(file); if (!err && ext4_has_group_desc_csum(sb) && test_opt(sb, INIT_INODE_TABLE)) err = ext4_register_li_request(sb, input->group); group_add_out: err2 = ext4_resize_end(sb, false); if (err == 0) err = err2; return err; } int ext4_fileattr_get(struct dentry *dentry, struct file_kattr *fa) { struct inode *inode = d_inode(dentry); struct ext4_inode_info *ei = EXT4_I(inode); u32 flags = ei->i_flags & EXT4_FL_USER_VISIBLE; if (S_ISREG(inode->i_mode)) flags &= ~FS_PROJINHERIT_FL; fileattr_fill_flags(fa, flags); if (ext4_has_feature_project(inode->i_sb)) fa->fsx_projid = from_kprojid(&init_user_ns, ei->i_projid); return 0; } int ext4_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct file_kattr *fa) { struct inode *inode = d_inode(dentry); u32 flags = fa->flags; int err = -EOPNOTSUPP; if (flags & ~EXT4_FL_USER_VISIBLE) goto out; /* * chattr(1) grabs flags via GETFLAGS, modifies the result and * passes that to SETFLAGS. So we cannot easily make SETFLAGS * more restrictive than just silently masking off visible but * not settable flags as we always did. */ flags &= EXT4_FL_USER_MODIFIABLE; if (ext4_mask_flags(inode->i_mode, flags) != flags) goto out; err = ext4_ioctl_check_immutable(inode, fa->fsx_projid, flags); if (err) goto out; err = ext4_ioctl_setflags(inode, flags); if (err) goto out; err = ext4_ioctl_setproject(inode, fa->fsx_projid); out: return err; } /* So that the fiemap access checks can't overflow on 32 bit machines. */ #define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) static int ext4_ioctl_get_es_cache(struct file *filp, unsigned long arg) { struct fiemap fiemap; struct fiemap __user *ufiemap = (struct fiemap __user *) arg; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); int error; if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) return -EFAULT; if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; error = ext4_get_es_cache(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) error = -EFAULT; return error; } static int ext4_ioctl_checkpoint(struct file *filp, unsigned long arg) { int err = 0; __u32 flags = 0; unsigned int flush_flags = 0; struct super_block *sb = file_inode(filp)->i_sb; if (copy_from_user(&flags, (__u32 __user *)arg, sizeof(__u32))) return -EFAULT; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* check for invalid bits set */ if ((flags & ~EXT4_IOC_CHECKPOINT_FLAG_VALID) || ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && (flags & JBD2_JOURNAL_FLUSH_ZEROOUT))) return -EINVAL; if (!EXT4_SB(sb)->s_journal) return -ENODEV; if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && !bdev_max_discard_sectors(EXT4_SB(sb)->s_journal->j_dev)) return -EOPNOTSUPP; if (flags & EXT4_IOC_CHECKPOINT_FLAG_DRY_RUN) return 0; if (flags & EXT4_IOC_CHECKPOINT_FLAG_DISCARD) flush_flags |= JBD2_JOURNAL_FLUSH_DISCARD; if (flags & EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT) { flush_flags |= JBD2_JOURNAL_FLUSH_ZEROOUT; pr_info_ratelimited("warning: checkpointing journal with EXT4_IOC_CHECKPOINT_FLAG_ZEROOUT can be slow"); } jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err = jbd2_journal_flush(EXT4_SB(sb)->s_journal, flush_flags); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); return err; } static int ext4_ioctl_setlabel(struct file *filp, const char __user *user_label) { size_t len; int ret = 0; char new_label[EXT4_LABEL_MAX + 1]; struct super_block *sb = file_inode(filp)->i_sb; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * Copy the maximum length allowed for ext4 label with one more to * find the required terminating null byte in order to test the * label length. The on disk label doesn't need to be null terminated. */ if (copy_from_user(new_label, user_label, EXT4_LABEL_MAX + 1)) return -EFAULT; len = strnlen(new_label, EXT4_LABEL_MAX + 1); if (len > EXT4_LABEL_MAX) return -EINVAL; /* * Clear the buffer after the new label */ memset(new_label + len, 0, EXT4_LABEL_MAX - len); ret = mnt_want_write_file(filp); if (ret) return ret; ret = ext4_update_superblocks_fn(sb, ext4_sb_setlabel, new_label); mnt_drop_write_file(filp); return ret; } static int ext4_ioctl_getlabel(struct ext4_sb_info *sbi, char __user *user_label) { char label[EXT4_LABEL_MAX + 1]; /* * EXT4_LABEL_MAX must always be smaller than FSLABEL_MAX because * FSLABEL_MAX must include terminating null byte, while s_volume_name * does not have to. */ BUILD_BUG_ON(EXT4_LABEL_MAX >= FSLABEL_MAX); lock_buffer(sbi->s_sbh); memtostr_pad(label, sbi->s_es->s_volume_name); unlock_buffer(sbi->s_sbh); if (copy_to_user(user_label, label, sizeof(label))) return -EFAULT; return 0; } static int ext4_ioctl_getuuid(struct ext4_sb_info *sbi, struct fsuuid __user *ufsuuid) { struct fsuuid fsuuid; __u8 uuid[UUID_SIZE]; if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid))) return -EFAULT; if (fsuuid.fsu_len == 0) { fsuuid.fsu_len = UUID_SIZE; if (copy_to_user(&ufsuuid->fsu_len, &fsuuid.fsu_len, sizeof(fsuuid.fsu_len))) return -EFAULT; return 0; } if (fsuuid.fsu_len < UUID_SIZE || fsuuid.fsu_flags != 0) return -EINVAL; lock_buffer(sbi->s_sbh); memcpy(uuid, sbi->s_es->s_uuid, UUID_SIZE); unlock_buffer(sbi->s_sbh); fsuuid.fsu_len = UUID_SIZE; if (copy_to_user(ufsuuid, &fsuuid, sizeof(fsuuid)) || copy_to_user(&ufsuuid->fsu_uuid[0], uuid, UUID_SIZE)) return -EFAULT; return 0; } static int ext4_ioctl_setuuid(struct file *filp, const struct fsuuid __user *ufsuuid) { int ret = 0; struct super_block *sb = file_inode(filp)->i_sb; struct fsuuid fsuuid; __u8 uuid[UUID_SIZE]; if (!capable(CAP_SYS_ADMIN)) return -EPERM; /* * If any checksums (group descriptors or metadata) are being used * then the checksum seed feature is required to change the UUID. */ if (((ext4_has_feature_gdt_csum(sb) || ext4_has_feature_metadata_csum(sb)) && !ext4_has_feature_csum_seed(sb)) || ext4_has_feature_stable_inodes(sb)) return -EOPNOTSUPP; if (copy_from_user(&fsuuid, ufsuuid, sizeof(fsuuid))) return -EFAULT; if (fsuuid.fsu_len != UUID_SIZE || fsuuid.fsu_flags != 0) return -EINVAL; if (copy_from_user(uuid, &ufsuuid->fsu_uuid[0], UUID_SIZE)) return -EFAULT; ret = mnt_want_write_file(filp); if (ret) return ret; ret = ext4_update_superblocks_fn(sb, ext4_sb_setuuid, &uuid); mnt_drop_write_file(filp); return ret; } static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; struct mnt_idmap *idmap = file_mnt_idmap(filp); ext4_debug("cmd = %u, arg = %lu\n", cmd, arg); switch (cmd) { case FS_IOC_GETFSMAP: return ext4_ioc_getfsmap(sb, (void __user *)arg); case EXT4_IOC_GETVERSION: case EXT4_IOC_GETVERSION_OLD: return put_user(inode->i_generation, (int __user *) arg); case EXT4_IOC_SETVERSION: case EXT4_IOC_SETVERSION_OLD: { handle_t *handle; struct ext4_iloc iloc; __u32 generation; int err; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; if (ext4_has_feature_metadata_csum(inode->i_sb)) { ext4_warning(sb, "Setting inode version is not " "supported with metadata_csum enabled."); return -ENOTTY; } err = mnt_want_write_file(filp); if (err) return err; if (get_user(generation, (int __user *) arg)) { err = -EFAULT; goto setversion_out; } inode_lock(inode); handle = ext4_journal_start(inode, EXT4_HT_INODE, 1); if (IS_ERR(handle)) { err = PTR_ERR(handle); goto unlock_out; } err = ext4_reserve_inode_write(handle, inode, &iloc); if (err == 0) { inode_set_ctime_current(inode); inode_inc_iversion(inode); inode->i_generation = generation; err = ext4_mark_iloc_dirty(handle, inode, &iloc); } ext4_journal_stop(handle); unlock_out: inode_unlock(inode); setversion_out: mnt_drop_write_file(filp); return err; } case EXT4_IOC_GROUP_EXTEND: { ext4_fsblk_t n_blocks_count; int err, err2=0; err = ext4_resize_begin(sb); if (err) return err; if (get_user(n_blocks_count, (__u32 __user *)arg)) { err = -EFAULT; goto group_extend_out; } if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online resizing not supported with bigalloc"); err = -EOPNOTSUPP; goto group_extend_out; } err = mnt_want_write_file(filp); if (err) goto group_extend_out; err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count); if (EXT4_SB(sb)->s_journal) { jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(filp); group_extend_out: err2 = ext4_resize_end(sb, false); if (err == 0) err = err2; return err; } case EXT4_IOC_MOVE_EXT: { struct move_extent me; int err; if (!(filp->f_mode & FMODE_READ) || !(filp->f_mode & FMODE_WRITE)) return -EBADF; if (copy_from_user(&me, (struct move_extent __user *)arg, sizeof(me))) return -EFAULT; me.moved_len = 0; CLASS(fd, donor)(me.donor_fd); if (fd_empty(donor)) return -EBADF; if (!(fd_file(donor)->f_mode & FMODE_WRITE)) return -EBADF; if (ext4_has_feature_bigalloc(sb)) { ext4_msg(sb, KERN_ERR, "Online defrag not supported with bigalloc"); return -EOPNOTSUPP; } else if (IS_DAX(inode)) { ext4_msg(sb, KERN_ERR, "Online defrag not supported with DAX"); return -EOPNOTSUPP; } err = mnt_want_write_file(filp); if (err) return err; err = ext4_move_extents(filp, fd_file(donor), me.orig_start, me.donor_start, me.len, &me.moved_len); mnt_drop_write_file(filp); if (copy_to_user((struct move_extent __user *)arg, &me, sizeof(me))) err = -EFAULT; return err; } case EXT4_IOC_GROUP_ADD: { struct ext4_new_group_data input; if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg, sizeof(input))) return -EFAULT; return ext4_ioctl_group_add(filp, &input); } case EXT4_IOC_MIGRATE: { int err; if (!inode_owner_or_capable(idmap, inode)) return -EACCES; err = mnt_want_write_file(filp); if (err) return err; /* * inode_mutex prevent write and truncate on the file. * Read still goes through. We take i_data_sem in * ext4_ext_swap_inode_data before we switch the * inode format to prevent read. */ inode_lock((inode)); err = ext4_ext_migrate(inode); inode_unlock((inode)); mnt_drop_write_file(filp); return err; } case EXT4_IOC_ALLOC_DA_BLKS: { int err; if (!inode_owner_or_capable(idmap, inode)) return -EACCES; err = mnt_want_write_file(filp); if (err) return err; err = ext4_alloc_da_blocks(inode); mnt_drop_write_file(filp); return err; } case EXT4_IOC_SWAP_BOOT: { int err; if (!(filp->f_mode & FMODE_WRITE)) return -EBADF; err = mnt_want_write_file(filp); if (err) return err; err = swap_inode_boot_loader(sb, idmap, inode); mnt_drop_write_file(filp); return err; } case EXT4_IOC_RESIZE_FS: { ext4_fsblk_t n_blocks_count; int err = 0, err2 = 0; ext4_group_t o_group = EXT4_SB(sb)->s_groups_count; if (copy_from_user(&n_blocks_count, (__u64 __user *)arg, sizeof(__u64))) { return -EFAULT; } err = ext4_resize_begin(sb); if (err) return err; err = mnt_want_write_file(filp); if (err) goto resizefs_out; err = ext4_resize_fs(sb, n_blocks_count); if (EXT4_SB(sb)->s_journal) { ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_RESIZE, NULL); jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal); err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal, 0); jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal); } if (err == 0) err = err2; mnt_drop_write_file(filp); if (!err && (o_group < EXT4_SB(sb)->s_groups_count) && ext4_has_group_desc_csum(sb) && test_opt(sb, INIT_INODE_TABLE)) err = ext4_register_li_request(sb, o_group); resizefs_out: err2 = ext4_resize_end(sb, true); if (err == 0) err = err2; return err; } case FITRIM: { struct fstrim_range range; int ret = 0; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!bdev_max_discard_sectors(sb->s_bdev)) return -EOPNOTSUPP; /* * We haven't replayed the journal, so we cannot use our * block-bitmap-guided storage zapping commands. */ if (test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) return -EROFS; if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range))) return -EFAULT; ret = ext4_trim_fs(sb, &range); if (ret < 0) return ret; if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range))) return -EFAULT; return 0; } case EXT4_IOC_PRECACHE_EXTENTS: { int ret; inode_lock_shared(inode); ret = ext4_ext_precache(inode); inode_unlock_shared(inode); return ret; } case FS_IOC_SET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_set_policy(filp, (const void __user *)arg); case FS_IOC_GET_ENCRYPTION_PWSALT: return ext4_ioctl_get_encryption_pwsalt(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_POLICY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_policy(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_POLICY_EX: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_policy_ex(filp, (void __user *)arg); case FS_IOC_ADD_ENCRYPTION_KEY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_add_key(filp, (void __user *)arg); case FS_IOC_REMOVE_ENCRYPTION_KEY: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_remove_key(filp, (void __user *)arg); case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_remove_key_all_users(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_KEY_STATUS: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_key_status(filp, (void __user *)arg); case FS_IOC_GET_ENCRYPTION_NONCE: if (!ext4_has_feature_encrypt(sb)) return -EOPNOTSUPP; return fscrypt_ioctl_get_nonce(filp, (void __user *)arg); case EXT4_IOC_CLEAR_ES_CACHE: { if (!inode_owner_or_capable(idmap, inode)) return -EACCES; ext4_clear_inode_es(inode); return 0; } case EXT4_IOC_GETSTATE: { __u32 state = 0; if (ext4_test_inode_state(inode, EXT4_STATE_EXT_PRECACHED)) state |= EXT4_STATE_FLAG_EXT_PRECACHED; if (ext4_test_inode_state(inode, EXT4_STATE_NEW)) state |= EXT4_STATE_FLAG_NEW; if (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) state |= EXT4_STATE_FLAG_NEWENTRY; if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) state |= EXT4_STATE_FLAG_DA_ALLOC_CLOSE; return put_user(state, (__u32 __user *) arg); } case EXT4_IOC_GET_ES_CACHE: return ext4_ioctl_get_es_cache(filp, arg); case EXT4_IOC_SHUTDOWN: return ext4_ioctl_shutdown(sb, arg); case FS_IOC_ENABLE_VERITY: if (!ext4_has_feature_verity(sb)) return -EOPNOTSUPP; return fsverity_ioctl_enable(filp, (const void __user *)arg); case FS_IOC_MEASURE_VERITY: if (!ext4_has_feature_verity(sb)) return -EOPNOTSUPP; return fsverity_ioctl_measure(filp, (void __user *)arg); case FS_IOC_READ_VERITY_METADATA: if (!ext4_has_feature_verity(sb)) return -EOPNOTSUPP; return fsverity_ioctl_read_metadata(filp, (const void __user *)arg); case EXT4_IOC_CHECKPOINT: return ext4_ioctl_checkpoint(filp, arg); case FS_IOC_GETFSLABEL: return ext4_ioctl_getlabel(EXT4_SB(sb), (void __user *)arg); case FS_IOC_SETFSLABEL: return ext4_ioctl_setlabel(filp, (const void __user *)arg); case EXT4_IOC_GETFSUUID: return ext4_ioctl_getuuid(EXT4_SB(sb), (void __user *)arg); case EXT4_IOC_SETFSUUID: return ext4_ioctl_setuuid(filp, (const void __user *)arg); default: return -ENOTTY; } } long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { return __ext4_ioctl(filp, cmd, arg); } #ifdef CONFIG_COMPAT long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { /* These are just misnamed, they actually get/put from/to user an int */ switch (cmd) { case EXT4_IOC32_GETVERSION: cmd = EXT4_IOC_GETVERSION; break; case EXT4_IOC32_SETVERSION: cmd = EXT4_IOC_SETVERSION; break; case EXT4_IOC32_GROUP_EXTEND: cmd = EXT4_IOC_GROUP_EXTEND; break; case EXT4_IOC32_GETVERSION_OLD: cmd = EXT4_IOC_GETVERSION_OLD; break; case EXT4_IOC32_SETVERSION_OLD: cmd = EXT4_IOC_SETVERSION_OLD; break; case EXT4_IOC32_GETRSVSZ: cmd = EXT4_IOC_GETRSVSZ; break; case EXT4_IOC32_SETRSVSZ: cmd = EXT4_IOC_SETRSVSZ; break; case EXT4_IOC32_GROUP_ADD: { struct compat_ext4_new_group_input __user *uinput; struct ext4_new_group_data input; int err; uinput = compat_ptr(arg); err = get_user(input.group, &uinput->group); err |= get_user(input.block_bitmap, &uinput->block_bitmap); err |= get_user(input.inode_bitmap, &uinput->inode_bitmap); err |= get_user(input.inode_table, &uinput->inode_table); err |= get_user(input.blocks_count, &uinput->blocks_count); err |= get_user(input.reserved_blocks, &uinput->reserved_blocks); if (err) return -EFAULT; return ext4_ioctl_group_add(file, &input); } case EXT4_IOC_MOVE_EXT: case EXT4_IOC_RESIZE_FS: case FITRIM: case EXT4_IOC_PRECACHE_EXTENTS: case FS_IOC_SET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_PWSALT: case FS_IOC_GET_ENCRYPTION_POLICY: case FS_IOC_GET_ENCRYPTION_POLICY_EX: case FS_IOC_ADD_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY: case FS_IOC_REMOVE_ENCRYPTION_KEY_ALL_USERS: case FS_IOC_GET_ENCRYPTION_KEY_STATUS: case FS_IOC_GET_ENCRYPTION_NONCE: case EXT4_IOC_SHUTDOWN: case FS_IOC_GETFSMAP: case FS_IOC_ENABLE_VERITY: case FS_IOC_MEASURE_VERITY: case FS_IOC_READ_VERITY_METADATA: case EXT4_IOC_CLEAR_ES_CACHE: case EXT4_IOC_GETSTATE: case EXT4_IOC_GET_ES_CACHE: case EXT4_IOC_CHECKPOINT: case FS_IOC_GETFSLABEL: case FS_IOC_SETFSLABEL: case EXT4_IOC_GETFSUUID: case EXT4_IOC_SETFSUUID: break; default: return -ENOIOCTLCMD; } return ext4_ioctl(file, cmd, (unsigned long) compat_ptr(arg)); } #endif static void set_overhead(struct ext4_super_block *es, const void *arg) { es->s_overhead_clusters = cpu_to_le32(*((unsigned long *) arg)); } int ext4_update_overhead(struct super_block *sb, bool force) { struct ext4_sb_info *sbi = EXT4_SB(sb); if (ext4_emergency_state(sb) || sb_rdonly(sb)) return 0; if (!force && (sbi->s_overhead == 0 || sbi->s_overhead == le32_to_cpu(sbi->s_es->s_overhead_clusters))) return 0; return ext4_update_superblocks_fn(sb, set_overhead, &sbi->s_overhead); } |
| 2 1 1 5 5 7 9 3 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * OSS compatible sequencer driver * * registration of device and proc * * Copyright (C) 1998,99 Takashi Iwai <tiwai@suse.de> */ #include <linux/init.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/compat.h> #include <sound/core.h> #include <sound/minors.h> #include <sound/initval.h> #include "seq_oss_device.h" #include "seq_oss_synth.h" /* * module option */ MODULE_AUTHOR("Takashi Iwai <tiwai@suse.de>"); MODULE_DESCRIPTION("OSS-compatible sequencer module"); MODULE_LICENSE("GPL"); /* Takashi says this is really only for sound-service-0-, but this is OK. */ MODULE_ALIAS_SNDRV_MINOR(SNDRV_MINOR_OSS_SEQUENCER); MODULE_ALIAS_SNDRV_MINOR(SNDRV_MINOR_OSS_MUSIC); /* * prototypes */ static int register_device(void); static void unregister_device(void); #ifdef CONFIG_SND_PROC_FS static int register_proc(void); static void unregister_proc(void); #else static inline int register_proc(void) { return 0; } static inline void unregister_proc(void) {} #endif static int odev_open(struct inode *inode, struct file *file); static int odev_release(struct inode *inode, struct file *file); static ssize_t odev_read(struct file *file, char __user *buf, size_t count, loff_t *offset); static ssize_t odev_write(struct file *file, const char __user *buf, size_t count, loff_t *offset); static long odev_ioctl(struct file *file, unsigned int cmd, unsigned long arg); static __poll_t odev_poll(struct file *file, poll_table * wait); /* * module interface */ static struct snd_seq_driver seq_oss_synth_driver = { .driver = { .name = KBUILD_MODNAME, .probe = snd_seq_oss_synth_probe, .remove = snd_seq_oss_synth_remove, }, .id = SNDRV_SEQ_DEV_ID_OSS, .argsize = sizeof(struct snd_seq_oss_reg), }; static int __init alsa_seq_oss_init(void) { int rc; rc = register_device(); if (rc < 0) goto error; rc = register_proc(); if (rc < 0) { unregister_device(); goto error; } rc = snd_seq_oss_create_client(); if (rc < 0) { unregister_proc(); unregister_device(); goto error; } rc = snd_seq_driver_register(&seq_oss_synth_driver); if (rc < 0) { snd_seq_oss_delete_client(); unregister_proc(); unregister_device(); goto error; } /* success */ snd_seq_oss_synth_init(); error: return rc; } static void __exit alsa_seq_oss_exit(void) { snd_seq_driver_unregister(&seq_oss_synth_driver); snd_seq_oss_delete_client(); unregister_proc(); unregister_device(); } module_init(alsa_seq_oss_init) module_exit(alsa_seq_oss_exit) /* * ALSA minor device interface */ static DEFINE_MUTEX(register_mutex); static int odev_open(struct inode *inode, struct file *file) { int level, rc; if (iminor(inode) == SNDRV_MINOR_OSS_MUSIC) level = SNDRV_SEQ_OSS_MODE_MUSIC; else level = SNDRV_SEQ_OSS_MODE_SYNTH; mutex_lock(®ister_mutex); rc = snd_seq_oss_open(file, level); mutex_unlock(®ister_mutex); return rc; } static int odev_release(struct inode *inode, struct file *file) { struct seq_oss_devinfo *dp; dp = file->private_data; if (!dp) return 0; mutex_lock(®ister_mutex); snd_seq_oss_release(dp); mutex_unlock(®ister_mutex); return 0; } static ssize_t odev_read(struct file *file, char __user *buf, size_t count, loff_t *offset) { struct seq_oss_devinfo *dp; dp = file->private_data; if (snd_BUG_ON(!dp)) return -ENXIO; return snd_seq_oss_read(dp, buf, count); } static ssize_t odev_write(struct file *file, const char __user *buf, size_t count, loff_t *offset) { struct seq_oss_devinfo *dp; dp = file->private_data; if (snd_BUG_ON(!dp)) return -ENXIO; return snd_seq_oss_write(dp, buf, count, file); } static long odev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct seq_oss_devinfo *dp; long rc; dp = file->private_data; if (snd_BUG_ON(!dp)) return -ENXIO; if (cmd != SNDCTL_SEQ_SYNC && mutex_lock_interruptible(®ister_mutex)) return -ERESTARTSYS; rc = snd_seq_oss_ioctl(dp, cmd, arg); if (cmd != SNDCTL_SEQ_SYNC) mutex_unlock(®ister_mutex); return rc; } #ifdef CONFIG_COMPAT static long odev_ioctl_compat(struct file *file, unsigned int cmd, unsigned long arg) { return odev_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } #else #define odev_ioctl_compat NULL #endif static __poll_t odev_poll(struct file *file, poll_table * wait) { struct seq_oss_devinfo *dp; dp = file->private_data; if (snd_BUG_ON(!dp)) return EPOLLERR; return snd_seq_oss_poll(dp, file, wait); } /* * registration of sequencer minor device */ static const struct file_operations seq_oss_f_ops = { .owner = THIS_MODULE, .read = odev_read, .write = odev_write, .open = odev_open, .release = odev_release, .poll = odev_poll, .unlocked_ioctl = odev_ioctl, .compat_ioctl = odev_ioctl_compat, .llseek = noop_llseek, }; static int __init register_device(void) { int rc; mutex_lock(®ister_mutex); rc = snd_register_oss_device(SNDRV_OSS_DEVICE_TYPE_SEQUENCER, NULL, 0, &seq_oss_f_ops, NULL); if (rc < 0) { pr_err("ALSA: seq_oss: can't register device seq\n"); mutex_unlock(®ister_mutex); return rc; } rc = snd_register_oss_device(SNDRV_OSS_DEVICE_TYPE_MUSIC, NULL, 0, &seq_oss_f_ops, NULL); if (rc < 0) { pr_err("ALSA: seq_oss: can't register device music\n"); snd_unregister_oss_device(SNDRV_OSS_DEVICE_TYPE_SEQUENCER, NULL, 0); mutex_unlock(®ister_mutex); return rc; } mutex_unlock(®ister_mutex); return 0; } static void unregister_device(void) { mutex_lock(®ister_mutex); if (snd_unregister_oss_device(SNDRV_OSS_DEVICE_TYPE_MUSIC, NULL, 0) < 0) pr_err("ALSA: seq_oss: error unregister device music\n"); if (snd_unregister_oss_device(SNDRV_OSS_DEVICE_TYPE_SEQUENCER, NULL, 0) < 0) pr_err("ALSA: seq_oss: error unregister device seq\n"); mutex_unlock(®ister_mutex); } /* * /proc interface */ #ifdef CONFIG_SND_PROC_FS static struct snd_info_entry *info_entry; static void info_read(struct snd_info_entry *entry, struct snd_info_buffer *buf) { mutex_lock(®ister_mutex); snd_iprintf(buf, "OSS sequencer emulation version %s\n", SNDRV_SEQ_OSS_VERSION_STR); snd_seq_oss_system_info_read(buf); snd_seq_oss_synth_info_read(buf); snd_seq_oss_midi_info_read(buf); mutex_unlock(®ister_mutex); } static int __init register_proc(void) { struct snd_info_entry *entry; entry = snd_info_create_module_entry(THIS_MODULE, SNDRV_SEQ_OSS_PROCNAME, snd_seq_root); if (entry == NULL) return -ENOMEM; entry->content = SNDRV_INFO_CONTENT_TEXT; entry->private_data = NULL; entry->c.text.read = info_read; if (snd_info_register(entry) < 0) { snd_info_free_entry(entry); return -ENOMEM; } info_entry = entry; return 0; } static void unregister_proc(void) { snd_info_free_entry(info_entry); info_entry = NULL; } #endif /* CONFIG_SND_PROC_FS */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PROJID_H #define _LINUX_PROJID_H /* * A set of types for the internal kernel types representing project ids. * * The types defined in this header allow distinguishing which project ids in * the kernel are values used by userspace and which project id 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/types.h> struct user_namespace; extern struct user_namespace init_user_ns; typedef __kernel_uid32_t projid_t; typedef struct { projid_t val; } kprojid_t; static inline projid_t __kprojid_val(kprojid_t projid) { return projid.val; } #define KPROJIDT_INIT(value) (kprojid_t){ value } #define INVALID_PROJID KPROJIDT_INIT(-1) #define OVERFLOW_PROJID 65534 static inline bool projid_eq(kprojid_t left, kprojid_t right) { return __kprojid_val(left) == __kprojid_val(right); } static inline bool projid_lt(kprojid_t left, kprojid_t right) { return __kprojid_val(left) < __kprojid_val(right); } static inline bool projid_valid(kprojid_t projid) { return !projid_eq(projid, INVALID_PROJID); } #ifdef CONFIG_USER_NS extern kprojid_t make_kprojid(struct user_namespace *from, projid_t projid); extern projid_t from_kprojid(struct user_namespace *to, kprojid_t projid); extern projid_t from_kprojid_munged(struct user_namespace *to, kprojid_t projid); static inline bool kprojid_has_mapping(struct user_namespace *ns, kprojid_t projid) { return from_kprojid(ns, projid) != (projid_t)-1; } #else static inline kprojid_t make_kprojid(struct user_namespace *from, projid_t projid) { return KPROJIDT_INIT(projid); } static inline projid_t from_kprojid(struct user_namespace *to, kprojid_t kprojid) { return __kprojid_val(kprojid); } static inline projid_t from_kprojid_munged(struct user_namespace *to, kprojid_t kprojid) { projid_t projid = from_kprojid(to, kprojid); if (projid == (projid_t)-1) projid = OVERFLOW_PROJID; return projid; } static inline bool kprojid_has_mapping(struct user_namespace *ns, kprojid_t projid) { return true; } #endif /* CONFIG_USER_NS */ #endif /* _LINUX_PROJID_H */ |
| 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 | /* * 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(sizeof(*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(sizeof(*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(sizeof(*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(sizeof(*ndev_work), GFP_KERNEL); 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(sizeof(*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); } |
| 118 65 213 212 214 210 210 212 211 213 213 209 209 211 209 210 210 211 210 212 213 211 211 212 211 210 210 210 209 208 210 3 211 210 209 210 2 214 2 1 211 214 214 211 212 209 212 213 1 58 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_FORMAT_H #define _BCACHEFS_FORMAT_H /* * bcachefs on disk data structures * * OVERVIEW: * * There are three main types of on disk data structures in bcachefs (this is * reduced from 5 in bcache) * * - superblock * - journal * - btree * * The btree is the primary structure; most metadata exists as keys in the * various btrees. There are only a small number of btrees, they're not * sharded - we have one btree for extents, another for inodes, et cetera. * * SUPERBLOCK: * * The superblock contains the location of the journal, the list of devices in * the filesystem, and in general any metadata we need in order to decide * whether we can start a filesystem or prior to reading the journal/btree * roots. * * The superblock is extensible, and most of the contents of the superblock are * in variable length, type tagged fields; see struct bch_sb_field. * * Backup superblocks do not reside in a fixed location; also, superblocks do * not have a fixed size. To locate backup superblocks we have struct * bch_sb_layout; we store a copy of this inside every superblock, and also * before the first superblock. * * JOURNAL: * * The journal primarily records btree updates in the order they occurred; * journal replay consists of just iterating over all the keys in the open * journal entries and re-inserting them into the btrees. * * The journal also contains entry types for the btree roots, and blacklisted * journal sequence numbers (see journal_seq_blacklist.c). * * BTREE: * * bcachefs btrees are copy on write b+ trees, where nodes are big (typically * 128k-256k) and log structured. We use struct btree_node for writing the first * entry in a given node (offset 0), and struct btree_node_entry for all * subsequent writes. * * After the header, btree node entries contain a list of keys in sorted order. * Values are stored inline with the keys; since values are variable length (and * keys effectively are variable length too, due to packing) we can't do random * access without building up additional in memory tables in the btree node read * path. * * BTREE KEYS (struct bkey): * * The various btrees share a common format for the key - so as to avoid * switching in fastpath lookup/comparison code - but define their own * structures for the key values. * * The size of a key/value pair is stored as a u8 in units of u64s, so the max * size is just under 2k. The common part also contains a type tag for the * value, and a format field indicating whether the key is packed or not (and * also meant to allow adding new key fields in the future, if desired). * * bkeys, when stored within a btree node, may also be packed. In that case, the * bkey_format in that node is used to unpack it. Packed bkeys mean that we can * be generous with field sizes in the common part of the key format (64 bit * inode number, 64 bit offset, 96 bit version field, etc.) for negligible cost. */ #include <asm/types.h> #include <asm/byteorder.h> #include <linux/kernel.h> #include <linux/uuid.h> #include <uapi/linux/magic.h> #include "vstructs.h" #ifdef __KERNEL__ typedef uuid_t __uuid_t; #endif #define BITMASK(name, type, field, offset, end) \ static const __maybe_unused unsigned name##_OFFSET = offset; \ static const __maybe_unused unsigned name##_BITS = (end - offset); \ \ static inline __u64 name(const type *k) \ { \ return (k->field >> offset) & ~(~0ULL << (end - offset)); \ } \ \ static inline void SET_##name(type *k, __u64 v) \ { \ k->field &= ~(~(~0ULL << (end - offset)) << offset); \ k->field |= (v & ~(~0ULL << (end - offset))) << offset; \ } #define LE_BITMASK(_bits, name, type, field, offset, end) |