| 4 1 3 2 1 3 1 2 6 4 2 5 2 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/fs.h> #include <linux/types.h> #include "ctree.h" #include "disk-io.h" #include "btrfs_inode.h" #include "export.h" #include "accessors.h" #include "super.h" #define BTRFS_FID_SIZE_NON_CONNECTABLE (offsetof(struct btrfs_fid, \ parent_objectid) / 4) #define BTRFS_FID_SIZE_CONNECTABLE (offsetof(struct btrfs_fid, \ parent_root_objectid) / 4) #define BTRFS_FID_SIZE_CONNECTABLE_ROOT (sizeof(struct btrfs_fid) / 4) static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len, struct inode *parent) { struct btrfs_fid *fid = (struct btrfs_fid *)fh; int len = *max_len; int type; if (parent && (len < BTRFS_FID_SIZE_CONNECTABLE)) { *max_len = BTRFS_FID_SIZE_CONNECTABLE; return FILEID_INVALID; } else if (len < BTRFS_FID_SIZE_NON_CONNECTABLE) { *max_len = BTRFS_FID_SIZE_NON_CONNECTABLE; return FILEID_INVALID; } len = BTRFS_FID_SIZE_NON_CONNECTABLE; type = FILEID_BTRFS_WITHOUT_PARENT; fid->objectid = btrfs_ino(BTRFS_I(inode)); fid->root_objectid = btrfs_root_id(BTRFS_I(inode)->root); fid->gen = inode->i_generation; if (parent) { u64 parent_root_id; fid->parent_objectid = btrfs_ino(BTRFS_I(parent)); fid->parent_gen = parent->i_generation; parent_root_id = btrfs_root_id(BTRFS_I(parent)->root); if (parent_root_id != fid->root_objectid) { fid->parent_root_objectid = parent_root_id; len = BTRFS_FID_SIZE_CONNECTABLE_ROOT; type = FILEID_BTRFS_WITH_PARENT_ROOT; } else { len = BTRFS_FID_SIZE_CONNECTABLE; type = FILEID_BTRFS_WITH_PARENT; } } *max_len = len; return type; } /* * Read dentry of inode with @objectid from filesystem root @root_objectid. * * @sb: the filesystem super block * @objectid: inode objectid * @root_objectid: object id of the subvolume root where to look up the inode * @generation: optional, if not zero, verify that the found inode * generation matches * * Return dentry alias for the inode, otherwise an error. In case the * generation does not match return ESTALE. */ struct dentry *btrfs_get_dentry(struct super_block *sb, u64 objectid, u64 root_objectid, u64 generation) { struct btrfs_fs_info *fs_info = btrfs_sb(sb); struct btrfs_root *root; struct btrfs_inode *inode; if (objectid < BTRFS_FIRST_FREE_OBJECTID) return ERR_PTR(-ESTALE); root = btrfs_get_fs_root(fs_info, root_objectid, true); if (IS_ERR(root)) return ERR_CAST(root); inode = btrfs_iget(objectid, root); btrfs_put_root(root); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation != 0 && generation != inode->vfs_inode.i_generation) { iput(&inode->vfs_inode); return ERR_PTR(-ESTALE); } return d_obtain_alias(&inode->vfs_inode); } static struct dentry *btrfs_fh_to_parent(struct super_block *sb, struct fid *fh, int fh_len, int fh_type) { struct btrfs_fid *fid = (struct btrfs_fid *) fh; u64 objectid, root_objectid; u32 generation; if (fh_type == FILEID_BTRFS_WITH_PARENT) { if (fh_len < BTRFS_FID_SIZE_CONNECTABLE) return NULL; root_objectid = fid->root_objectid; } else if (fh_type == FILEID_BTRFS_WITH_PARENT_ROOT) { if (fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) return NULL; root_objectid = fid->parent_root_objectid; } else return NULL; objectid = fid->parent_objectid; generation = fid->parent_gen; return btrfs_get_dentry(sb, objectid, root_objectid, generation); } static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh, int fh_len, int fh_type) { struct btrfs_fid *fid = (struct btrfs_fid *) fh; u64 objectid, root_objectid; u32 generation; if ((fh_type != FILEID_BTRFS_WITH_PARENT || fh_len < BTRFS_FID_SIZE_CONNECTABLE) && (fh_type != FILEID_BTRFS_WITH_PARENT_ROOT || fh_len < BTRFS_FID_SIZE_CONNECTABLE_ROOT) && (fh_type != FILEID_BTRFS_WITHOUT_PARENT || fh_len < BTRFS_FID_SIZE_NON_CONNECTABLE)) return NULL; objectid = fid->objectid; root_objectid = fid->root_objectid; generation = fid->gen; return btrfs_get_dentry(sb, objectid, root_objectid, generation); } struct dentry *btrfs_get_parent(struct dentry *child) { struct btrfs_inode *dir = BTRFS_I(d_inode(child)); struct btrfs_inode *inode; struct btrfs_root *root = dir->root; struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_path *path; struct extent_buffer *leaf; struct btrfs_root_ref *ref; struct btrfs_key key; struct btrfs_key found_key; int ret; path = btrfs_alloc_path(); if (!path) return ERR_PTR(-ENOMEM); if (btrfs_ino(dir) == BTRFS_FIRST_FREE_OBJECTID) { key.objectid = btrfs_root_id(root); key.type = BTRFS_ROOT_BACKREF_KEY; key.offset = (u64)-1; root = fs_info->tree_root; } else { key.objectid = btrfs_ino(dir); key.type = BTRFS_INODE_REF_KEY; key.offset = (u64)-1; } ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto fail; if (ret == 0) { /* * Key with offset of -1 found, there would have to exist an * inode with such number or a root with such id. */ ret = -EUCLEAN; goto fail; } if (path->slots[0] == 0) { ret = -ENOENT; goto fail; } path->slots[0]--; leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); if (found_key.objectid != key.objectid || found_key.type != key.type) { ret = -ENOENT; goto fail; } if (found_key.type == BTRFS_ROOT_BACKREF_KEY) { ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); key.objectid = btrfs_root_ref_dirid(leaf, ref); } else { key.objectid = found_key.offset; } btrfs_free_path(path); if (found_key.type == BTRFS_ROOT_BACKREF_KEY) { return btrfs_get_dentry(fs_info->sb, key.objectid, found_key.offset, 0); } inode = btrfs_iget(key.objectid, root); if (IS_ERR(inode)) return ERR_CAST(inode); return d_obtain_alias(&inode->vfs_inode); fail: btrfs_free_path(path); return ERR_PTR(ret); } static int btrfs_get_name(struct dentry *parent, char *name, struct dentry *child) { struct btrfs_inode *inode = BTRFS_I(d_inode(child)); struct btrfs_inode *dir = BTRFS_I(d_inode(parent)); struct btrfs_root *root = dir->root; struct btrfs_fs_info *fs_info = root->fs_info; BTRFS_PATH_AUTO_FREE(path); struct btrfs_inode_ref *iref; struct btrfs_root_ref *rref; struct extent_buffer *leaf; unsigned long name_ptr; struct btrfs_key key; int name_len; int ret; u64 ino; if (!S_ISDIR(dir->vfs_inode.i_mode)) return -EINVAL; ino = btrfs_ino(inode); path = btrfs_alloc_path(); if (!path) return -ENOMEM; if (ino == BTRFS_FIRST_FREE_OBJECTID) { key.objectid = btrfs_root_id(inode->root); key.type = BTRFS_ROOT_BACKREF_KEY; key.offset = (u64)-1; root = fs_info->tree_root; } else { key.objectid = ino; key.type = BTRFS_INODE_REF_KEY; key.offset = btrfs_ino(dir); } ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) { return ret; } else if (ret > 0) { if (ino == BTRFS_FIRST_FREE_OBJECTID) path->slots[0]--; else return -ENOENT; } leaf = path->nodes[0]; if (ino == BTRFS_FIRST_FREE_OBJECTID) { rref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref); name_ptr = (unsigned long)(rref + 1); name_len = btrfs_root_ref_name_len(leaf, rref); } else { iref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_ref); name_ptr = (unsigned long)(iref + 1); name_len = btrfs_inode_ref_name_len(leaf, iref); } read_extent_buffer(leaf, name, name_ptr, name_len); /* * have to add the null termination to make sure that reconnect_path * gets the right len for strlen */ name[name_len] = '\0'; return 0; } const struct export_operations btrfs_export_ops = { .encode_fh = btrfs_encode_fh, .fh_to_dentry = btrfs_fh_to_dentry, .fh_to_parent = btrfs_fh_to_parent, .get_parent = btrfs_get_parent, .get_name = btrfs_get_name, }; |
| 82 82 1 1 1 1 1 1 76 76 21 14 7 9 9 9 9 21 2 12 3 4 1 17 17 17 17 12 2 10 10 10 10 10 8 8 8 8 8 9 10 110 110 83 3 43 4 6 39 121 122 4 72 79 74 19 78 3 3 48 68 29 45 54 5 3 3 72 11 75 3 22 49 64 49 3 59 27 7 52 54 92 92 92 79 18 13 13 3 13 13 13 12 1 12 7 5 6 1 4 15 15 2 14 10 14 2 4 14 12 3 6 23 11 12 3 4 8 8 91 91 2 2 24 73 90 23 1 18 67 76 49 107 9 2 15 5 108 108 103 103 15 13 2 13 13 107 105 9 108 19 19 14 14 14 7 7 7 7 19 19 19 3 16 12 12 11 11 9 2 5 1 8 1 106 107 102 29 29 2 2 2 2 2 2 2 19 16 8 8 1 7 108 97 31 67 67 90 13 90 3 88 9 84 97 97 97 97 96 86 67 7 13 130 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) International Business Machines Corp., 2000-2004 * Portions Copyright (C) Tino Reichardt, 2012 */ #include <linux/fs.h> #include <linux/slab.h> #include "jfs_incore.h" #include "jfs_superblock.h" #include "jfs_dmap.h" #include "jfs_imap.h" #include "jfs_lock.h" #include "jfs_metapage.h" #include "jfs_debug.h" #include "jfs_discard.h" /* * SERIALIZATION of the Block Allocation Map. * * the working state of the block allocation map is accessed in * two directions: * * 1) allocation and free requests that start at the dmap * level and move up through the dmap control pages (i.e. * the vast majority of requests). * * 2) allocation requests that start at dmap control page * level and work down towards the dmaps. * * the serialization scheme used here is as follows. * * requests which start at the bottom are serialized against each * other through buffers and each requests holds onto its buffers * as it works it way up from a single dmap to the required level * of dmap control page. * requests that start at the top are serialized against each other * and request that start from the bottom by the multiple read/single * write inode lock of the bmap inode. requests starting at the top * take this lock in write mode while request starting at the bottom * take the lock in read mode. a single top-down request may proceed * exclusively while multiple bottoms-up requests may proceed * simultaneously (under the protection of busy buffers). * * in addition to information found in dmaps and dmap control pages, * the working state of the block allocation map also includes read/ * write information maintained in the bmap descriptor (i.e. total * free block count, allocation group level free block counts). * a single exclusive lock (BMAP_LOCK) is used to guard this information * in the face of multiple-bottoms up requests. * (lock ordering: IREAD_LOCK, BMAP_LOCK); * * accesses to the persistent state of the block allocation map (limited * to the persistent bitmaps in dmaps) is guarded by (busy) buffers. */ #define BMAP_LOCK_INIT(bmp) mutex_init(&bmp->db_bmaplock) #define BMAP_LOCK(bmp) mutex_lock(&bmp->db_bmaplock) #define BMAP_UNLOCK(bmp) mutex_unlock(&bmp->db_bmaplock) /* * forward references */ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl); static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl); static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl); static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl); static int dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level); static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results); static int dbAllocNext(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbAllocNear(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks, int l2nb, s64 * results); static int dbAllocDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbAllocDmapLev(struct bmap * bmp, struct dmap * dp, int nblocks, int l2nb, s64 * results); static int dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results); static int dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results); static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks); static int dbFindBits(u32 word, int l2nb); static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno); static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl); static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbMaxBud(u8 * cp); static int blkstol2(s64 nb); static int cntlz(u32 value); static int cnttz(u32 word); static int dbAllocDmapBU(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks); static int dbInitDmap(struct dmap * dp, s64 blkno, int nblocks); static int dbInitDmapTree(struct dmap * dp); static int dbInitTree(struct dmaptree * dtp); static int dbInitDmapCtl(struct dmapctl * dcp, int level, int i); static int dbGetL2AGSize(s64 nblocks); /* * buddy table * * table used for determining buddy sizes within characters of * dmap bitmap words. the characters themselves serve as indexes * into the table, with the table elements yielding the maximum * binary buddy of free bits within the character. */ static const s8 budtab[256] = { 3, 2, 2, 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, 1, 1, 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, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 2, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, -1 }; /* * NAME: dbMount() * * FUNCTION: initializate the block allocation map. * * memory is allocated for the in-core bmap descriptor and * the in-core descriptor is initialized from disk. * * PARAMETERS: * ipbmap - pointer to in-core inode for the block map. * * RETURN VALUES: * 0 - success * -ENOMEM - insufficient memory * -EIO - i/o error * -EINVAL - wrong bmap data */ int dbMount(struct inode *ipbmap) { struct bmap *bmp; struct dbmap_disk *dbmp_le; struct metapage *mp; int i, err; /* * allocate/initialize the in-memory bmap descriptor */ /* allocate memory for the in-memory bmap descriptor */ bmp = kmalloc(sizeof(struct bmap), GFP_KERNEL); if (bmp == NULL) return -ENOMEM; /* read the on-disk bmap descriptor. */ mp = read_metapage(ipbmap, BMAPBLKNO << JFS_SBI(ipbmap->i_sb)->l2nbperpage, PSIZE, 0); if (mp == NULL) { err = -EIO; goto err_kfree_bmp; } /* copy the on-disk bmap descriptor to its in-memory version. */ dbmp_le = (struct dbmap_disk *) mp->data; bmp->db_mapsize = le64_to_cpu(dbmp_le->dn_mapsize); bmp->db_nfree = le64_to_cpu(dbmp_le->dn_nfree); bmp->db_l2nbperpage = le32_to_cpu(dbmp_le->dn_l2nbperpage); bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag); bmp->db_maxlevel = le32_to_cpu(dbmp_le->dn_maxlevel); bmp->db_maxag = le32_to_cpu(dbmp_le->dn_maxag); bmp->db_agpref = le32_to_cpu(dbmp_le->dn_agpref); bmp->db_aglevel = le32_to_cpu(dbmp_le->dn_aglevel); bmp->db_agheight = le32_to_cpu(dbmp_le->dn_agheight); bmp->db_agwidth = le32_to_cpu(dbmp_le->dn_agwidth); bmp->db_agstart = le32_to_cpu(dbmp_le->dn_agstart); bmp->db_agl2size = le32_to_cpu(dbmp_le->dn_agl2size); if ((bmp->db_l2nbperpage > L2PSIZE - L2MINBLOCKSIZE) || (bmp->db_l2nbperpage < 0) || !bmp->db_numag || (bmp->db_numag > MAXAG) || (bmp->db_maxag >= MAXAG) || (bmp->db_maxag < 0) || (bmp->db_agpref >= MAXAG) || (bmp->db_agpref < 0) || (bmp->db_agheight < 0) || (bmp->db_agheight > (L2LPERCTL >> 1)) || (bmp->db_agwidth < 1) || (bmp->db_agwidth > (LPERCTL / MAXAG)) || (bmp->db_agwidth > (1 << (L2LPERCTL - (bmp->db_agheight << 1)))) || (bmp->db_agstart < 0) || (bmp->db_agstart > (CTLTREESIZE - 1 - bmp->db_agwidth * (MAXAG - 1))) || (bmp->db_agl2size > L2MAXL2SIZE - L2MAXAG) || (bmp->db_agl2size < 0) || ((bmp->db_mapsize - 1) >> bmp->db_agl2size) > MAXAG) { err = -EINVAL; goto err_release_metapage; } for (i = 0; i < MAXAG; i++) bmp->db_agfree[i] = le64_to_cpu(dbmp_le->dn_agfree[i]); bmp->db_agsize = le64_to_cpu(dbmp_le->dn_agsize); bmp->db_maxfreebud = dbmp_le->dn_maxfreebud; /* release the buffer. */ release_metapage(mp); /* bind the bmap inode and the bmap descriptor to each other. */ bmp->db_ipbmap = ipbmap; JFS_SBI(ipbmap->i_sb)->bmap = bmp; memset(bmp->db_active, 0, sizeof(bmp->db_active)); /* * allocate/initialize the bmap lock */ BMAP_LOCK_INIT(bmp); return (0); err_release_metapage: release_metapage(mp); err_kfree_bmp: kfree(bmp); return err; } /* * NAME: dbUnmount() * * FUNCTION: terminate the block allocation map in preparation for * file system unmount. * * the in-core bmap descriptor is written to disk and * the memory for this descriptor is freed. * * PARAMETERS: * ipbmap - pointer to in-core inode for the block map. * * RETURN VALUES: * 0 - success * -EIO - i/o error */ int dbUnmount(struct inode *ipbmap, int mounterror) { struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap; if (!(mounterror || isReadOnly(ipbmap))) dbSync(ipbmap); /* * Invalidate the page cache buffers */ truncate_inode_pages(ipbmap->i_mapping, 0); /* free the memory for the in-memory bmap. */ kfree(bmp); JFS_SBI(ipbmap->i_sb)->bmap = NULL; return (0); } /* * dbSync() */ int dbSync(struct inode *ipbmap) { struct dbmap_disk *dbmp_le; struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap; struct metapage *mp; int i; /* * write bmap global control page */ /* get the buffer for the on-disk bmap descriptor. */ mp = read_metapage(ipbmap, BMAPBLKNO << JFS_SBI(ipbmap->i_sb)->l2nbperpage, PSIZE, 0); if (mp == NULL) { jfs_err("dbSync: read_metapage failed!"); return -EIO; } /* copy the in-memory version of the bmap to the on-disk version */ dbmp_le = (struct dbmap_disk *) mp->data; dbmp_le->dn_mapsize = cpu_to_le64(bmp->db_mapsize); dbmp_le->dn_nfree = cpu_to_le64(bmp->db_nfree); dbmp_le->dn_l2nbperpage = cpu_to_le32(bmp->db_l2nbperpage); dbmp_le->dn_numag = cpu_to_le32(bmp->db_numag); dbmp_le->dn_maxlevel = cpu_to_le32(bmp->db_maxlevel); dbmp_le->dn_maxag = cpu_to_le32(bmp->db_maxag); dbmp_le->dn_agpref = cpu_to_le32(bmp->db_agpref); dbmp_le->dn_aglevel = cpu_to_le32(bmp->db_aglevel); dbmp_le->dn_agheight = cpu_to_le32(bmp->db_agheight); dbmp_le->dn_agwidth = cpu_to_le32(bmp->db_agwidth); dbmp_le->dn_agstart = cpu_to_le32(bmp->db_agstart); dbmp_le->dn_agl2size = cpu_to_le32(bmp->db_agl2size); for (i = 0; i < MAXAG; i++) dbmp_le->dn_agfree[i] = cpu_to_le64(bmp->db_agfree[i]); dbmp_le->dn_agsize = cpu_to_le64(bmp->db_agsize); dbmp_le->dn_maxfreebud = bmp->db_maxfreebud; /* write the buffer */ write_metapage(mp); /* * write out dirty pages of bmap */ filemap_write_and_wait(ipbmap->i_mapping); diWriteSpecial(ipbmap, 0); return (0); } /* * NAME: dbFree() * * FUNCTION: free the specified block range from the working block * allocation map. * * the blocks will be free from the working map one dmap * at a time. * * PARAMETERS: * ip - pointer to in-core inode; * blkno - starting block number to be freed. * nblocks - number of blocks to be freed. * * RETURN VALUES: * 0 - success * -EIO - i/o error */ int dbFree(struct inode *ip, s64 blkno, s64 nblocks) { struct metapage *mp; struct dmap *dp; int nb, rc; s64 lblkno, rem; struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap; struct bmap *bmp = JFS_SBI(ip->i_sb)->bmap; struct super_block *sb = ipbmap->i_sb; IREAD_LOCK(ipbmap, RDWRLOCK_DMAP); /* block to be freed better be within the mapsize. */ if (unlikely((blkno == 0) || (blkno + nblocks > bmp->db_mapsize))) { IREAD_UNLOCK(ipbmap); printk(KERN_ERR "blkno = %Lx, nblocks = %Lx\n", (unsigned long long) blkno, (unsigned long long) nblocks); jfs_error(ip->i_sb, "block to be freed is outside the map\n"); return -EIO; } /** * TRIM the blocks, when mounted with discard option */ if (JFS_SBI(sb)->flag & JFS_DISCARD) if (JFS_SBI(sb)->minblks_trim <= nblocks) jfs_issue_discard(ipbmap, blkno, nblocks); /* * free the blocks a dmap at a time. */ mp = NULL; for (rem = nblocks; rem > 0; rem -= nb, blkno += nb) { /* release previous dmap if any */ if (mp) { write_metapage(mp); } /* get the buffer for the current dmap. */ lblkno = BLKTODMAP(blkno, bmp->db_l2nbperpage); mp = read_metapage(ipbmap, lblkno, PSIZE, 0); if (mp == NULL) { IREAD_UNLOCK(ipbmap); return -EIO; } dp = (struct dmap *) mp->data; /* determine the number of blocks to be freed from * this dmap. */ nb = min(rem, BPERDMAP - (blkno & (BPERDMAP - 1))); /* free the blocks. */ if ((rc = dbFreeDmap(bmp, dp, blkno, nb))) { jfs_error(ip->i_sb, "error in block map\n"); release_metapage(mp); IREAD_UNLOCK(ipbmap); return (rc); } } /* write the last buffer. */ if (mp) write_metapage(mp); IREAD_UNLOCK(ipbmap); return (0); } /* * NAME: dbUpdatePMap() * * FUNCTION: update the allocation state (free or allocate) of the * specified block range in the persistent block allocation map. * * the blocks will be updated in the persistent map one * dmap at a time. * * PARAMETERS: * ipbmap - pointer to in-core inode for the block map. * free - 'true' if block range is to be freed from the persistent * map; 'false' if it is to be allocated. * blkno - starting block number of the range. * nblocks - number of contiguous blocks in the range. * tblk - transaction block; * * RETURN VALUES: * 0 - success * -EIO - i/o error */ int dbUpdatePMap(struct inode *ipbmap, int free, s64 blkno, s64 nblocks, struct tblock * tblk) { int nblks, dbitno, wbitno, rbits; int word, nbits, nwords; struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap; s64 lblkno, rem, lastlblkno; u32 mask; struct dmap *dp; struct metapage *mp; struct jfs_log *log; int lsn, difft, diffp; unsigned long flags; /* the blocks better be within the mapsize. */ if (blkno + nblocks > bmp->db_mapsize) { printk(KERN_ERR "blkno = %Lx, nblocks = %Lx\n", (unsigned long long) blkno, (unsigned long long) nblocks); jfs_error(ipbmap->i_sb, "blocks are outside the map\n"); return -EIO; } /* compute delta of transaction lsn from log syncpt */ lsn = tblk->lsn; log = (struct jfs_log *) JFS_SBI(tblk->sb)->log; logdiff(difft, lsn, log); /* * update the block state a dmap at a time. */ mp = NULL; lastlblkno = 0; for (rem = nblocks; rem > 0; rem -= nblks, blkno += nblks) { /* get the buffer for the current dmap. */ lblkno = BLKTODMAP(blkno, bmp->db_l2nbperpage); if (lblkno != lastlblkno) { if (mp) { write_metapage(mp); } mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) return -EIO; metapage_wait_for_io(mp); } dp = (struct dmap *) mp->data; /* determine the bit number and word within the dmap of * the starting block. also determine how many blocks * are to be updated within this dmap. */ dbitno = blkno & (BPERDMAP - 1); word = dbitno >> L2DBWORD; nblks = min(rem, (s64)BPERDMAP - dbitno); /* update the bits of the dmap words. the first and last * words may only have a subset of their bits updated. if * this is the case, we'll work against that word (i.e. * partial first and/or last) only in a single pass. a * single pass will also be used to update all words that * are to have all their bits updated. */ for (rbits = nblks; rbits > 0; rbits -= nbits, dbitno += nbits) { /* determine the bit number within the word and * the number of bits within the word. */ wbitno = dbitno & (DBWORD - 1); nbits = min(rbits, DBWORD - wbitno); /* check if only part of the word is to be updated. */ if (nbits < DBWORD) { /* update (free or allocate) the bits * in this word. */ mask = (ONES << (DBWORD - nbits) >> wbitno); if (free) dp->pmap[word] &= cpu_to_le32(~mask); else dp->pmap[word] |= cpu_to_le32(mask); word += 1; } else { /* one or more words are to have all * their bits updated. determine how * many words and how many bits. */ nwords = rbits >> L2DBWORD; nbits = nwords << L2DBWORD; /* update (free or allocate) the bits * in these words. */ if (free) memset(&dp->pmap[word], 0, nwords * 4); else memset(&dp->pmap[word], (int) ONES, nwords * 4); word += nwords; } } /* * update dmap lsn */ if (lblkno == lastlblkno) continue; lastlblkno = lblkno; LOGSYNC_LOCK(log, flags); if (mp->lsn != 0) { /* inherit older/smaller lsn */ logdiff(diffp, mp->lsn, log); if (difft < diffp) { mp->lsn = lsn; /* move bp after tblock in logsync list */ list_move(&mp->synclist, &tblk->synclist); } /* inherit younger/larger clsn */ logdiff(difft, tblk->clsn, log); logdiff(diffp, mp->clsn, log); if (difft > diffp) mp->clsn = tblk->clsn; } else { mp->log = log; mp->lsn = lsn; /* insert bp after tblock in logsync list */ log->count++; list_add(&mp->synclist, &tblk->synclist); mp->clsn = tblk->clsn; } LOGSYNC_UNLOCK(log, flags); } /* write the last buffer. */ if (mp) { write_metapage(mp); } return (0); } /* * NAME: dbNextAG() * * FUNCTION: find the preferred allocation group for new allocations. * * Within the allocation groups, we maintain a preferred * allocation group which consists of a group with at least * average free space. It is the preferred group that we target * new inode allocation towards. The tie-in between inode * allocation and block allocation occurs as we allocate the * first (data) block of an inode and specify the inode (block) * as the allocation hint for this block. * * We try to avoid having more than one open file growing in * an allocation group, as this will lead to fragmentation. * This differs from the old OS/2 method of trying to keep * empty ags around for large allocations. * * PARAMETERS: * ipbmap - pointer to in-core inode for the block map. * * RETURN VALUES: * the preferred allocation group number. */ int dbNextAG(struct inode *ipbmap) { s64 avgfree; int agpref; s64 hwm = 0; int i; int next_best = -1; struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap; BMAP_LOCK(bmp); /* determine the average number of free blocks within the ags. */ avgfree = (u32)bmp->db_nfree / bmp->db_numag; /* * if the current preferred ag does not have an active allocator * and has at least average freespace, return it */ agpref = bmp->db_agpref; if ((atomic_read(&bmp->db_active[agpref]) == 0) && (bmp->db_agfree[agpref] >= avgfree)) goto unlock; /* From the last preferred ag, find the next one with at least * average free space. */ for (i = 0 ; i < bmp->db_numag; i++, agpref++) { if (agpref >= bmp->db_numag) agpref = 0; if (atomic_read(&bmp->db_active[agpref])) /* open file is currently growing in this ag */ continue; if (bmp->db_agfree[agpref] >= avgfree) { /* Return this one */ bmp->db_agpref = agpref; goto unlock; } else if (bmp->db_agfree[agpref] > hwm) { /* Less than avg. freespace, but best so far */ hwm = bmp->db_agfree[agpref]; next_best = agpref; } } /* * If no inactive ag was found with average freespace, use the * next best */ if (next_best != -1) bmp->db_agpref = next_best; /* else leave db_agpref unchanged */ unlock: BMAP_UNLOCK(bmp); /* return the preferred group. */ return (bmp->db_agpref); } /* * NAME: dbAlloc() * * FUNCTION: attempt to allocate a specified number of contiguous free * blocks from the working allocation block map. * * the block allocation policy uses hints and a multi-step * approach. * * for allocation requests smaller than the number of blocks * per dmap, we first try to allocate the new blocks * immediately following the hint. if these blocks are not * available, we try to allocate blocks near the hint. if * no blocks near the hint are available, we next try to * allocate within the same dmap as contains the hint. * * if no blocks are available in the dmap or the allocation * request is larger than the dmap size, we try to allocate * within the same allocation group as contains the hint. if * this does not succeed, we finally try to allocate anywhere * within the aggregate. * * we also try to allocate anywhere within the aggregate * for allocation requests larger than the allocation group * size or requests that specify no hint value. * * PARAMETERS: * ip - pointer to in-core inode; * hint - allocation hint. * nblocks - number of contiguous blocks in the range. * results - on successful return, set to the starting block number * of the newly allocated contiguous range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error */ int dbAlloc(struct inode *ip, s64 hint, s64 nblocks, s64 * results) { int rc, agno; struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap; struct bmap *bmp; struct metapage *mp; s64 lblkno, blkno; struct dmap *dp; int l2nb; s64 mapSize; int writers; /* assert that nblocks is valid */ assert(nblocks > 0); /* get the log2 number of blocks to be allocated. * if the number of blocks is not a log2 multiple, * it will be rounded up to the next log2 multiple. */ l2nb = BLKSTOL2(nblocks); bmp = JFS_SBI(ip->i_sb)->bmap; mapSize = bmp->db_mapsize; /* the hint should be within the map */ if (hint >= mapSize) { jfs_error(ip->i_sb, "the hint is outside the map\n"); return -EIO; } /* if the number of blocks to be allocated is greater than the * allocation group size, try to allocate anywhere. */ if (l2nb > bmp->db_agl2size) { IWRITE_LOCK(ipbmap, RDWRLOCK_DMAP); rc = dbAllocAny(bmp, nblocks, l2nb, results); goto write_unlock; } /* * If no hint, let dbNextAG recommend an allocation group */ if (hint == 0) goto pref_ag; /* we would like to allocate close to the hint. adjust the * hint to the block following the hint since the allocators * will start looking for free space starting at this point. */ blkno = hint + 1; if (blkno >= bmp->db_mapsize) goto pref_ag; agno = blkno >> bmp->db_agl2size; /* check if blkno crosses over into a new allocation group. * if so, check if we should allow allocations within this * allocation group. */ if ((blkno & (bmp->db_agsize - 1)) == 0) /* check if the AG is currently being written to. * if so, call dbNextAG() to find a non-busy * AG with sufficient free space. */ if (atomic_read(&bmp->db_active[agno])) goto pref_ag; /* check if the allocation request size can be satisfied from a * single dmap. if so, try to allocate from the dmap containing * the hint using a tiered strategy. */ if (nblocks <= BPERDMAP) { IREAD_LOCK(ipbmap, RDWRLOCK_DMAP); /* get the buffer for the dmap containing the hint. */ rc = -EIO; lblkno = BLKTODMAP(blkno, bmp->db_l2nbperpage); mp = read_metapage(ipbmap, lblkno, PSIZE, 0); if (mp == NULL) goto read_unlock; dp = (struct dmap *) mp->data; /* first, try to satisfy the allocation request with the * blocks beginning at the hint. */ if ((rc = dbAllocNext(bmp, dp, blkno, (int) nblocks)) != -ENOSPC) { if (rc == 0) { *results = blkno; mark_metapage_dirty(mp); } release_metapage(mp); goto read_unlock; } writers = atomic_read(&bmp->db_active[agno]); if ((writers > 1) || ((writers == 1) && (JFS_IP(ip)->active_ag != agno))) { /* * Someone else is writing in this allocation * group. To avoid fragmenting, try another ag */ release_metapage(mp); IREAD_UNLOCK(ipbmap); goto pref_ag; } /* next, try to satisfy the allocation request with blocks * near the hint. */ if ((rc = dbAllocNear(bmp, dp, blkno, (int) nblocks, l2nb, results)) != -ENOSPC) { if (rc == 0) mark_metapage_dirty(mp); release_metapage(mp); goto read_unlock; } /* try to satisfy the allocation request with blocks within * the same dmap as the hint. */ if ((rc = dbAllocDmapLev(bmp, dp, (int) nblocks, l2nb, results)) != -ENOSPC) { if (rc == 0) mark_metapage_dirty(mp); release_metapage(mp); goto read_unlock; } release_metapage(mp); IREAD_UNLOCK(ipbmap); } /* try to satisfy the allocation request with blocks within * the same allocation group as the hint. */ IWRITE_LOCK(ipbmap, RDWRLOCK_DMAP); if ((rc = dbAllocAG(bmp, agno, nblocks, l2nb, results)) != -ENOSPC) goto write_unlock; IWRITE_UNLOCK(ipbmap); pref_ag: /* * Let dbNextAG recommend a preferred allocation group */ agno = dbNextAG(ipbmap); IWRITE_LOCK(ipbmap, RDWRLOCK_DMAP); /* Try to allocate within this allocation group. if that fails, try to * allocate anywhere in the map. */ if ((rc = dbAllocAG(bmp, agno, nblocks, l2nb, results)) == -ENOSPC) rc = dbAllocAny(bmp, nblocks, l2nb, results); write_unlock: IWRITE_UNLOCK(ipbmap); return (rc); read_unlock: IREAD_UNLOCK(ipbmap); return (rc); } /* * NAME: dbReAlloc() * * FUNCTION: attempt to extend a current allocation by a specified * number of blocks. * * this routine attempts to satisfy the allocation request * by first trying to extend the existing allocation in * place by allocating the additional blocks as the blocks * immediately following the current allocation. if these * blocks are not available, this routine will attempt to * allocate a new set of contiguous blocks large enough * to cover the existing allocation plus the additional * number of blocks required. * * PARAMETERS: * ip - pointer to in-core inode requiring allocation. * blkno - starting block of the current allocation. * nblocks - number of contiguous blocks within the current * allocation. * addnblocks - number of blocks to add to the allocation. * results - on successful return, set to the starting block number * of the existing allocation if the existing allocation * was extended in place or to a newly allocated contiguous * range if the existing allocation could not be extended * in place. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error */ int dbReAlloc(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks, s64 * results) { int rc; /* try to extend the allocation in place. */ if ((rc = dbExtend(ip, blkno, nblocks, addnblocks)) == 0) { *results = blkno; return (0); } else { if (rc != -ENOSPC) return (rc); } /* could not extend the allocation in place, so allocate a * new set of blocks for the entire request (i.e. try to get * a range of contiguous blocks large enough to cover the * existing allocation plus the additional blocks.) */ return (dbAlloc (ip, blkno + nblocks - 1, addnblocks + nblocks, results)); } /* * NAME: dbExtend() * * FUNCTION: attempt to extend a current allocation by a specified * number of blocks. * * this routine attempts to satisfy the allocation request * by first trying to extend the existing allocation in * place by allocating the additional blocks as the blocks * immediately following the current allocation. * * PARAMETERS: * ip - pointer to in-core inode requiring allocation. * blkno - starting block of the current allocation. * nblocks - number of contiguous blocks within the current * allocation. * addnblocks - number of blocks to add to the allocation. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error */ static int dbExtend(struct inode *ip, s64 blkno, s64 nblocks, s64 addnblocks) { struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb); s64 lblkno, lastblkno, extblkno; uint rel_block; struct metapage *mp; struct dmap *dp; int rc; struct inode *ipbmap = sbi->ipbmap; struct bmap *bmp; /* * We don't want a non-aligned extent to cross a page boundary */ if (((rel_block = blkno & (sbi->nbperpage - 1))) && (rel_block + nblocks + addnblocks > sbi->nbperpage)) return -ENOSPC; /* get the last block of the current allocation */ lastblkno = blkno + nblocks - 1; /* determine the block number of the block following * the existing allocation. */ extblkno = lastblkno + 1; IREAD_LOCK(ipbmap, RDWRLOCK_DMAP); /* better be within the file system */ bmp = sbi->bmap; if (lastblkno < 0 || lastblkno >= bmp->db_mapsize) { IREAD_UNLOCK(ipbmap); jfs_error(ip->i_sb, "the block is outside the filesystem\n"); return -EIO; } /* we'll attempt to extend the current allocation in place by * allocating the additional blocks as the blocks immediately * following the current allocation. we only try to extend the * current allocation in place if the number of additional blocks * can fit into a dmap, the last block of the current allocation * is not the last block of the file system, and the start of the * inplace extension is not on an allocation group boundary. */ if (addnblocks > BPERDMAP || extblkno >= bmp->db_mapsize || (extblkno & (bmp->db_agsize - 1)) == 0) { IREAD_UNLOCK(ipbmap); return -ENOSPC; } /* get the buffer for the dmap containing the first block * of the extension. */ lblkno = BLKTODMAP(extblkno, bmp->db_l2nbperpage); mp = read_metapage(ipbmap, lblkno, PSIZE, 0); if (mp == NULL) { IREAD_UNLOCK(ipbmap); return -EIO; } dp = (struct dmap *) mp->data; /* try to allocate the blocks immediately following the * current allocation. */ rc = dbAllocNext(bmp, dp, extblkno, (int) addnblocks); IREAD_UNLOCK(ipbmap); /* were we successful ? */ if (rc == 0) write_metapage(mp); else /* we were not successful */ release_metapage(mp); return (rc); } /* * NAME: dbAllocNext() * * FUNCTION: attempt to allocate the blocks of the specified block * range within a dmap. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap. * blkno - starting block number of the range. * nblocks - number of contiguous free blocks of the range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) held on entry/exit; */ static int dbAllocNext(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { int dbitno, word, rembits, nb, nwords, wbitno, nw; int l2size; s8 *leaf; u32 mask; if (dp->tree.leafidx != cpu_to_le32(LEAFIND)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmap page\n"); return -EIO; } /* pick up a pointer to the leaves of the dmap tree. */ leaf = dp->tree.stree + le32_to_cpu(dp->tree.leafidx); /* determine the bit number and word within the dmap of the * starting block. */ dbitno = blkno & (BPERDMAP - 1); word = dbitno >> L2DBWORD; /* check if the specified block range is contained within * this dmap. */ if (dbitno + nblocks > BPERDMAP) return -ENOSPC; /* check if the starting leaf indicates that anything * is free. */ if (leaf[word] == NOFREE) return -ENOSPC; /* check the dmaps words corresponding to block range to see * if the block range is free. not all bits of the first and * last words may be contained within the block range. if this * is the case, we'll work against those words (i.e. partial first * and/or last) on an individual basis (a single pass) and examine * the actual bits to determine if they are free. a single pass * will be used for all dmap words fully contained within the * specified range. within this pass, the leaves of the dmap * tree will be examined to determine if the blocks are free. a * single leaf may describe the free space of multiple dmap * words, so we may visit only a subset of the actual leaves * corresponding to the dmap words of the block range. */ for (rembits = nblocks; rembits > 0; rembits -= nb, dbitno += nb) { /* determine the bit number within the word and * the number of bits within the word. */ wbitno = dbitno & (DBWORD - 1); nb = min(rembits, DBWORD - wbitno); /* check if only part of the word is to be examined. */ if (nb < DBWORD) { /* check if the bits are free. */ mask = (ONES << (DBWORD - nb) >> wbitno); if ((mask & ~le32_to_cpu(dp->wmap[word])) != mask) return -ENOSPC; word += 1; } else { /* one or more dmap words are fully contained * within the block range. determine how many * words and how many bits. */ nwords = rembits >> L2DBWORD; nb = nwords << L2DBWORD; /* now examine the appropriate leaves to determine * if the blocks are free. */ while (nwords > 0) { /* does the leaf describe any free space ? */ if (leaf[word] < BUDMIN) return -ENOSPC; /* determine the l2 number of bits provided * by this leaf. */ l2size = min_t(int, leaf[word], NLSTOL2BSZ(nwords)); /* determine how many words were handled. */ nw = BUDSIZE(l2size, BUDMIN); nwords -= nw; word += nw; } } } /* allocate the blocks. */ return (dbAllocDmap(bmp, dp, blkno, nblocks)); } /* * NAME: dbAllocNear() * * FUNCTION: attempt to allocate a number of contiguous free blocks near * a specified block (hint) within a dmap. * * starting with the dmap leaf that covers the hint, we'll * check the next four contiguous leaves for sufficient free * space. if sufficient free space is found, we'll allocate * the desired free space. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap. * blkno - block number to allocate near. * nblocks - actual number of contiguous free blocks desired. * l2nb - log2 number of contiguous free blocks desired. * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) held on entry/exit; */ static int dbAllocNear(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks, int l2nb, s64 * results) { int word, lword, rc; s8 *leaf; if (dp->tree.leafidx != cpu_to_le32(LEAFIND)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmap page\n"); return -EIO; } leaf = dp->tree.stree + le32_to_cpu(dp->tree.leafidx); /* determine the word within the dmap that holds the hint * (i.e. blkno). also, determine the last word in the dmap * that we'll include in our examination. */ word = (blkno & (BPERDMAP - 1)) >> L2DBWORD; lword = min(word + 4, LPERDMAP); /* examine the leaves for sufficient free space. */ for (; word < lword; word++) { /* does the leaf describe sufficient free space ? */ if (leaf[word] < l2nb) continue; /* determine the block number within the file system * of the first block described by this dmap word. */ blkno = le64_to_cpu(dp->start) + (word << L2DBWORD); /* if not all bits of the dmap word are free, get the * starting bit number within the dmap word of the required * string of free bits and adjust the block number with the * value. */ if (leaf[word] < BUDMIN) blkno += dbFindBits(le32_to_cpu(dp->wmap[word]), l2nb); /* allocate the blocks. */ if ((rc = dbAllocDmap(bmp, dp, blkno, nblocks)) == 0) *results = blkno; return (rc); } return -ENOSPC; } /* * NAME: dbAllocAG() * * FUNCTION: attempt to allocate the specified number of contiguous * free blocks within the specified allocation group. * * unless the allocation group size is equal to the number * of blocks per dmap, the dmap control pages will be used to * find the required free space, if available. we start the * search at the highest dmap control page level which * distinctly describes the allocation group's free space * (i.e. the highest level at which the allocation group's * free space is not mixed in with that of any other group). * in addition, we start the search within this level at a * height of the dmapctl dmtree at which the nodes distinctly * describe the allocation group's free space. at this height, * the allocation group's free space may be represented by 1 * or two sub-trees, depending on the allocation group size. * we search the top nodes of these subtrees left to right for * sufficient free space. if sufficient free space is found, * the subtree is searched to find the leftmost leaf that * has free space. once we have made it to the leaf, we * move the search to the next lower level dmap control page * corresponding to this leaf. we continue down the dmap control * pages until we find the dmap that contains or starts the * sufficient free space and we allocate at this dmap. * * if the allocation group size is equal to the dmap size, * we'll start at the dmap corresponding to the allocation * group and attempt the allocation at this level. * * the dmap control page search is also not performed if the * allocation group is completely free and we go to the first * dmap of the allocation group to do the allocation. this is * done because the allocation group may be part (not the first * part) of a larger binary buddy system, causing the dmap * control pages to indicate no free space (NOFREE) within * the allocation group. * * PARAMETERS: * bmp - pointer to bmap descriptor * agno - allocation group number. * nblocks - actual number of contiguous free blocks desired. * l2nb - log2 number of contiguous free blocks desired. * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * note: IWRITE_LOCK(ipmap) held on entry/exit; */ static int dbAllocAG(struct bmap * bmp, int agno, s64 nblocks, int l2nb, s64 * results) { struct metapage *mp; struct dmapctl *dcp; int rc, ti, i, k, m, n, agperlev; s64 blkno, lblkno; int budmin; /* allocation request should not be for more than the * allocation group size. */ if (l2nb > bmp->db_agl2size) { jfs_error(bmp->db_ipbmap->i_sb, "allocation request is larger than the allocation group size\n"); return -EIO; } /* determine the starting block number of the allocation * group. */ blkno = (s64) agno << bmp->db_agl2size; /* check if the allocation group size is the minimum allocation * group size or if the allocation group is completely free. if * the allocation group size is the minimum size of BPERDMAP (i.e. * 1 dmap), there is no need to search the dmap control page (below) * that fully describes the allocation group since the allocation * group is already fully described by a dmap. in this case, we * just call dbAllocCtl() to search the dmap tree and allocate the * required space if available. * * if the allocation group is completely free, dbAllocCtl() is * also called to allocate the required space. this is done for * two reasons. first, it makes no sense searching the dmap control * pages for free space when we know that free space exists. second, * the dmap control pages may indicate that the allocation group * has no free space if the allocation group is part (not the first * part) of a larger binary buddy system. */ if (bmp->db_agsize == BPERDMAP || bmp->db_agfree[agno] == bmp->db_agsize) { rc = dbAllocCtl(bmp, nblocks, l2nb, blkno, results); if ((rc == -ENOSPC) && (bmp->db_agfree[agno] == bmp->db_agsize)) { printk(KERN_ERR "blkno = %Lx, blocks = %Lx\n", (unsigned long long) blkno, (unsigned long long) nblocks); jfs_error(bmp->db_ipbmap->i_sb, "dbAllocCtl failed in free AG\n"); } return (rc); } /* the buffer for the dmap control page that fully describes the * allocation group. */ lblkno = BLKTOCTL(blkno, bmp->db_l2nbperpage, bmp->db_aglevel); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) return -EIO; dcp = (struct dmapctl *) mp->data; budmin = dcp->budmin; if (dcp->leafidx != cpu_to_le32(CTLLEAFIND)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n"); release_metapage(mp); return -EIO; } /* search the subtree(s) of the dmap control page that describes * the allocation group, looking for sufficient free space. to begin, * determine how many allocation groups are represented in a dmap * control page at the control page level (i.e. L0, L1, L2) that * fully describes an allocation group. next, determine the starting * tree index of this allocation group within the control page. */ agperlev = (1 << (L2LPERCTL - (bmp->db_agheight << 1))) / bmp->db_agwidth; ti = bmp->db_agstart + bmp->db_agwidth * (agno & (agperlev - 1)); if (ti < 0 || ti >= le32_to_cpu(dcp->nleafs)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n"); release_metapage(mp); return -EIO; } /* dmap control page trees fan-out by 4 and a single allocation * group may be described by 1 or 2 subtrees within the ag level * dmap control page, depending upon the ag size. examine the ag's * subtrees for sufficient free space, starting with the leftmost * subtree. */ for (i = 0; i < bmp->db_agwidth; i++, ti++) { /* is there sufficient free space ? */ if (l2nb > dcp->stree[ti]) continue; /* sufficient free space found in a subtree. now search down * the subtree to find the leftmost leaf that describes this * free space. */ for (k = bmp->db_agheight; k > 0; k--) { for (n = 0, m = (ti << 2) + 1; n < 4; n++) { if (l2nb <= dcp->stree[m + n]) { ti = m + n; break; } } if (n == 4) { jfs_error(bmp->db_ipbmap->i_sb, "failed descending stree\n"); release_metapage(mp); return -EIO; } } /* determine the block number within the file system * that corresponds to this leaf. */ if (bmp->db_aglevel == 2) blkno = 0; else if (bmp->db_aglevel == 1) blkno &= ~(MAXL1SIZE - 1); else /* bmp->db_aglevel == 0 */ blkno &= ~(MAXL0SIZE - 1); blkno += ((s64) (ti - le32_to_cpu(dcp->leafidx))) << budmin; /* release the buffer in preparation for going down * the next level of dmap control pages. */ release_metapage(mp); /* check if we need to continue to search down the lower * level dmap control pages. we need to if the number of * blocks required is less than maximum number of blocks * described at the next lower level. */ if (l2nb < budmin) { /* search the lower level dmap control pages to get * the starting block number of the dmap that * contains or starts off the free space. */ if ((rc = dbFindCtl(bmp, l2nb, bmp->db_aglevel - 1, &blkno))) { if (rc == -ENOSPC) { jfs_error(bmp->db_ipbmap->i_sb, "control page inconsistent\n"); return -EIO; } return (rc); } } /* allocate the blocks. */ rc = dbAllocCtl(bmp, nblocks, l2nb, blkno, results); if (rc == -ENOSPC) { jfs_error(bmp->db_ipbmap->i_sb, "unable to allocate blocks\n"); rc = -EIO; } return (rc); } /* no space in the allocation group. release the buffer and * return -ENOSPC. */ release_metapage(mp); return -ENOSPC; } /* * NAME: dbAllocAny() * * FUNCTION: attempt to allocate the specified number of contiguous * free blocks anywhere in the file system. * * dbAllocAny() attempts to find the sufficient free space by * searching down the dmap control pages, starting with the * highest level (i.e. L0, L1, L2) control page. if free space * large enough to satisfy the desired free space is found, the * desired free space is allocated. * * PARAMETERS: * bmp - pointer to bmap descriptor * nblocks - actual number of contiguous free blocks desired. * l2nb - log2 number of contiguous free blocks desired. * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbAllocAny(struct bmap * bmp, s64 nblocks, int l2nb, s64 * results) { int rc; s64 blkno = 0; /* starting with the top level dmap control page, search * down the dmap control levels for sufficient free space. * if free space is found, dbFindCtl() returns the starting * block number of the dmap that contains or starts off the * range of free space. */ if ((rc = dbFindCtl(bmp, l2nb, bmp->db_maxlevel, &blkno))) return (rc); /* allocate the blocks. */ rc = dbAllocCtl(bmp, nblocks, l2nb, blkno, results); if (rc == -ENOSPC) { jfs_error(bmp->db_ipbmap->i_sb, "unable to allocate blocks\n"); return -EIO; } return (rc); } /* * NAME: dbDiscardAG() * * FUNCTION: attempt to discard (TRIM) all free blocks of specific AG * * algorithm: * 1) allocate blocks, as large as possible and save them * while holding IWRITE_LOCK on ipbmap * 2) trim all these saved block/length values * 3) mark the blocks free again * * benefit: * - we work only on one ag at some time, minimizing how long we * need to lock ipbmap * - reading / writing the fs is possible most time, even on * trimming * * downside: * - we write two times to the dmapctl and dmap pages * - but for me, this seems the best way, better ideas? * /TR 2012 * * PARAMETERS: * ip - pointer to in-core inode * agno - ag to trim * minlen - minimum value of contiguous blocks * * RETURN VALUES: * s64 - actual number of blocks trimmed */ s64 dbDiscardAG(struct inode *ip, int agno, s64 minlen) { struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap; struct bmap *bmp = JFS_SBI(ip->i_sb)->bmap; s64 nblocks, blkno; u64 trimmed = 0; int rc, l2nb; struct super_block *sb = ipbmap->i_sb; struct range2trim { u64 blkno; u64 nblocks; } *totrim, *tt; /* max blkno / nblocks pairs to trim */ int count = 0, range_cnt; u64 max_ranges; /* prevent others from writing new stuff here, while trimming */ IWRITE_LOCK(ipbmap, RDWRLOCK_DMAP); nblocks = bmp->db_agfree[agno]; max_ranges = nblocks; do_div(max_ranges, minlen); range_cnt = min_t(u64, max_ranges + 1, 32 * 1024); totrim = kmalloc_array(range_cnt, sizeof(struct range2trim), GFP_NOFS); if (totrim == NULL) { jfs_error(bmp->db_ipbmap->i_sb, "no memory for trim array\n"); IWRITE_UNLOCK(ipbmap); return 0; } tt = totrim; while (nblocks >= minlen) { l2nb = BLKSTOL2(nblocks); /* 0 = okay, -EIO = fatal, -ENOSPC -> try smaller block */ rc = dbAllocAG(bmp, agno, nblocks, l2nb, &blkno); if (rc == 0) { tt->blkno = blkno; tt->nblocks = nblocks; tt++; count++; /* the whole ag is free, trim now */ if (bmp->db_agfree[agno] == 0) break; /* give a hint for the next while */ nblocks = bmp->db_agfree[agno]; continue; } else if (rc == -ENOSPC) { /* search for next smaller log2 block */ l2nb = BLKSTOL2(nblocks) - 1; if (unlikely(l2nb < 0)) break; nblocks = 1LL << l2nb; } else { /* Trim any already allocated blocks */ jfs_error(bmp->db_ipbmap->i_sb, "-EIO\n"); break; } /* check, if our trim array is full */ if (unlikely(count >= range_cnt - 1)) break; } IWRITE_UNLOCK(ipbmap); tt->nblocks = 0; /* mark the current end */ for (tt = totrim; tt->nblocks != 0; tt++) { /* when mounted with online discard, dbFree() will * call jfs_issue_discard() itself */ if (!(JFS_SBI(sb)->flag & JFS_DISCARD)) jfs_issue_discard(ip, tt->blkno, tt->nblocks); dbFree(ip, tt->blkno, tt->nblocks); trimmed += tt->nblocks; } kfree(totrim); return trimmed; } /* * NAME: dbFindCtl() * * FUNCTION: starting at a specified dmap control page level and block * number, search down the dmap control levels for a range of * contiguous free blocks large enough to satisfy an allocation * request for the specified number of free blocks. * * if sufficient contiguous free blocks are found, this routine * returns the starting block number within a dmap page that * contains or starts a range of contiqious free blocks that * is sufficient in size. * * PARAMETERS: * bmp - pointer to bmap descriptor * level - starting dmap control page level. * l2nb - log2 number of contiguous free blocks desired. * *blkno - on entry, starting block number for conducting the search. * on successful return, the first block within a dmap page * that contains or starts a range of contiguous free blocks. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbFindCtl(struct bmap * bmp, int l2nb, int level, s64 * blkno) { int rc, leafidx, lev; s64 b, lblkno; struct dmapctl *dcp; int budmin; struct metapage *mp; /* starting at the specified dmap control page level and block * number, search down the dmap control levels for the starting * block number of a dmap page that contains or starts off * sufficient free blocks. */ for (lev = level, b = *blkno; lev >= 0; lev--) { /* get the buffer of the dmap control page for the block * number and level (i.e. L0, L1, L2). */ lblkno = BLKTOCTL(b, bmp->db_l2nbperpage, lev); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) return -EIO; dcp = (struct dmapctl *) mp->data; budmin = dcp->budmin; if (dcp->leafidx != cpu_to_le32(CTLLEAFIND)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n"); release_metapage(mp); return -EIO; } /* search the tree within the dmap control page for * sufficient free space. if sufficient free space is found, * dbFindLeaf() returns the index of the leaf at which * free space was found. */ rc = dbFindLeaf((dmtree_t *) dcp, l2nb, &leafidx, true); /* release the buffer. */ release_metapage(mp); /* space found ? */ if (rc) { if (lev != level) { jfs_error(bmp->db_ipbmap->i_sb, "dmap inconsistent\n"); return -EIO; } return -ENOSPC; } /* adjust the block number to reflect the location within * the dmap control page (i.e. the leaf) at which free * space was found. */ b += (((s64) leafidx) << budmin); /* we stop the search at this dmap control page level if * the number of blocks required is greater than or equal * to the maximum number of blocks described at the next * (lower) level. */ if (l2nb >= budmin) break; } *blkno = b; return (0); } /* * NAME: dbAllocCtl() * * FUNCTION: attempt to allocate a specified number of contiguous * blocks starting within a specific dmap. * * this routine is called by higher level routines that search * the dmap control pages above the actual dmaps for contiguous * free space. the result of successful searches by these * routines are the starting block numbers within dmaps, with * the dmaps themselves containing the desired contiguous free * space or starting a contiguous free space of desired size * that is made up of the blocks of one or more dmaps. these * calls should not fail due to insufficent resources. * * this routine is called in some cases where it is not known * whether it will fail due to insufficient resources. more * specifically, this occurs when allocating from an allocation * group whose size is equal to the number of blocks per dmap. * in this case, the dmap control pages are not examined prior * to calling this routine (to save pathlength) and the call * might fail. * * for a request size that fits within a dmap, this routine relies * upon the dmap's dmtree to find the requested contiguous free * space. for request sizes that are larger than a dmap, the * requested free space will start at the first block of the * first dmap (i.e. blkno). * * PARAMETERS: * bmp - pointer to bmap descriptor * nblocks - actual number of contiguous free blocks to allocate. * l2nb - log2 number of contiguous free blocks to allocate. * blkno - starting block number of the dmap to start the allocation * from. * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbAllocCtl(struct bmap * bmp, s64 nblocks, int l2nb, s64 blkno, s64 * results) { int rc, nb; s64 b, lblkno, n; struct metapage *mp; struct dmap *dp; /* check if the allocation request is confined to a single dmap. */ if (l2nb <= L2BPERDMAP) { /* get the buffer for the dmap. */ lblkno = BLKTODMAP(blkno, bmp->db_l2nbperpage); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) return -EIO; dp = (struct dmap *) mp->data; if (dp->tree.budmin < 0) { release_metapage(mp); return -EIO; } /* try to allocate the blocks. */ rc = dbAllocDmapLev(bmp, dp, (int) nblocks, l2nb, results); if (rc == 0) mark_metapage_dirty(mp); release_metapage(mp); return (rc); } /* allocation request involving multiple dmaps. it must start on * a dmap boundary. */ assert((blkno & (BPERDMAP - 1)) == 0); /* allocate the blocks dmap by dmap. */ for (n = nblocks, b = blkno; n > 0; n -= nb, b += nb) { /* get the buffer for the dmap. */ lblkno = BLKTODMAP(b, bmp->db_l2nbperpage); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) { rc = -EIO; goto backout; } dp = (struct dmap *) mp->data; /* the dmap better be all free. */ if (dp->tree.stree[ROOT] != L2BPERDMAP) { release_metapage(mp); jfs_error(bmp->db_ipbmap->i_sb, "the dmap is not all free\n"); rc = -EIO; goto backout; } /* determine how many blocks to allocate from this dmap. */ nb = min_t(s64, n, BPERDMAP); /* allocate the blocks from the dmap. */ if ((rc = dbAllocDmap(bmp, dp, b, nb))) { release_metapage(mp); goto backout; } /* write the buffer. */ write_metapage(mp); } /* set the results (starting block number) and return. */ *results = blkno; return (0); /* something failed in handling an allocation request involving * multiple dmaps. we'll try to clean up by backing out any * allocation that has already happened for this request. if * we fail in backing out the allocation, we'll mark the file * system to indicate that blocks have been leaked. */ backout: /* try to backout the allocations dmap by dmap. */ for (n = nblocks - n, b = blkno; n > 0; n -= BPERDMAP, b += BPERDMAP) { /* get the buffer for this dmap. */ lblkno = BLKTODMAP(b, bmp->db_l2nbperpage); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) { /* could not back out. mark the file system * to indicate that we have leaked blocks. */ jfs_error(bmp->db_ipbmap->i_sb, "I/O Error: Block Leakage\n"); continue; } dp = (struct dmap *) mp->data; /* free the blocks is this dmap. */ if (dbFreeDmap(bmp, dp, b, BPERDMAP)) { /* could not back out. mark the file system * to indicate that we have leaked blocks. */ release_metapage(mp); jfs_error(bmp->db_ipbmap->i_sb, "Block Leakage\n"); continue; } /* write the buffer. */ write_metapage(mp); } return (rc); } /* * NAME: dbAllocDmapLev() * * FUNCTION: attempt to allocate a specified number of contiguous blocks * from a specified dmap. * * this routine checks if the contiguous blocks are available. * if so, nblocks of blocks are allocated; otherwise, ENOSPC is * returned. * * PARAMETERS: * mp - pointer to bmap descriptor * dp - pointer to dmap to attempt to allocate blocks from. * l2nb - log2 number of contiguous block desired. * nblocks - actual number of contiguous block desired. * results - on successful return, set to the starting block number * of the newly allocated range. * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient disk resources * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap), e.g., from dbAlloc(), or * IWRITE_LOCK(ipbmap), e.g., dbAllocCtl(), held on entry/exit; */ static int dbAllocDmapLev(struct bmap * bmp, struct dmap * dp, int nblocks, int l2nb, s64 * results) { s64 blkno; int leafidx, rc; /* can't be more than a dmaps worth of blocks */ assert(l2nb <= L2BPERDMAP); /* search the tree within the dmap page for sufficient * free space. if sufficient free space is found, dbFindLeaf() * returns the index of the leaf at which free space was found. */ if (dbFindLeaf((dmtree_t *) &dp->tree, l2nb, &leafidx, false)) return -ENOSPC; if (leafidx < 0) return -EIO; /* determine the block number within the file system corresponding * to the leaf at which free space was found. */ blkno = le64_to_cpu(dp->start) + (leafidx << L2DBWORD); /* if not all bits of the dmap word are free, get the starting * bit number within the dmap word of the required string of free * bits and adjust the block number with this value. */ if (dp->tree.stree[leafidx + LEAFIND] < BUDMIN) blkno += dbFindBits(le32_to_cpu(dp->wmap[leafidx]), l2nb); /* allocate the blocks */ if ((rc = dbAllocDmap(bmp, dp, blkno, nblocks)) == 0) *results = blkno; return (rc); } /* * NAME: dbAllocDmap() * * FUNCTION: adjust the disk allocation map to reflect the allocation * of a specified block range within a dmap. * * this routine allocates the specified blocks from the dmap * through a call to dbAllocBits(). if the allocation of the * block range causes the maximum string of free blocks within * the dmap to change (i.e. the value of the root of the dmap's * dmtree), this routine will cause this change to be reflected * up through the appropriate levels of the dmap control pages * by a call to dbAdjCtl() for the L0 dmap control page that * covers this dmap. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap to allocate the block range from. * blkno - starting block number of the block to be allocated. * nblocks - number of blocks to be allocated. * * RETURN VALUES: * 0 - success * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbAllocDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { s8 oldroot; int rc; /* save the current value of the root (i.e. maximum free string) * of the dmap tree. */ oldroot = dp->tree.stree[ROOT]; /* allocate the specified (blocks) bits */ dbAllocBits(bmp, dp, blkno, nblocks); /* if the root has not changed, done. */ if (dp->tree.stree[ROOT] == oldroot) return (0); /* root changed. bubble the change up to the dmap control pages. * if the adjustment of the upper level control pages fails, * backout the bit allocation (thus making everything consistent). */ if ((rc = dbAdjCtl(bmp, blkno, dp->tree.stree[ROOT], 1, 0))) dbFreeBits(bmp, dp, blkno, nblocks); return (rc); } /* * NAME: dbFreeDmap() * * FUNCTION: adjust the disk allocation map to reflect the allocation * of a specified block range within a dmap. * * this routine frees the specified blocks from the dmap through * a call to dbFreeBits(). if the deallocation of the block range * causes the maximum string of free blocks within the dmap to * change (i.e. the value of the root of the dmap's dmtree), this * routine will cause this change to be reflected up through the * appropriate levels of the dmap control pages by a call to * dbAdjCtl() for the L0 dmap control page that covers this dmap. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap to free the block range from. * blkno - starting block number of the block to be freed. * nblocks - number of blocks to be freed. * * RETURN VALUES: * 0 - success * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbFreeDmap(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { s8 oldroot; int rc = 0, word; /* save the current value of the root (i.e. maximum free string) * of the dmap tree. */ oldroot = dp->tree.stree[ROOT]; /* free the specified (blocks) bits */ rc = dbFreeBits(bmp, dp, blkno, nblocks); /* if error or the root has not changed, done. */ if (rc || (dp->tree.stree[ROOT] == oldroot)) return (rc); /* root changed. bubble the change up to the dmap control pages. * if the adjustment of the upper level control pages fails, * backout the deallocation. */ if ((rc = dbAdjCtl(bmp, blkno, dp->tree.stree[ROOT], 0, 0))) { word = (blkno & (BPERDMAP - 1)) >> L2DBWORD; /* as part of backing out the deallocation, we will have * to back split the dmap tree if the deallocation caused * the freed blocks to become part of a larger binary buddy * system. */ if (dp->tree.stree[word] == NOFREE) dbBackSplit((dmtree_t *)&dp->tree, word, false); dbAllocBits(bmp, dp, blkno, nblocks); } return (rc); } /* * NAME: dbAllocBits() * * FUNCTION: allocate a specified block range from a dmap. * * this routine updates the dmap to reflect the working * state allocation of the specified block range. it directly * updates the bits of the working map and causes the adjustment * of the binary buddy system described by the dmap's dmtree * leaves to reflect the bits allocated. it also causes the * dmap's dmtree, as a whole, to reflect the allocated range. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap to allocate bits from. * blkno - starting block number of the bits to be allocated. * nblocks - number of bits to be allocated. * * RETURN VALUES: none * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { int dbitno, word, rembits, nb, nwords, wbitno, nw, agno; dmtree_t *tp = (dmtree_t *) & dp->tree; int size; s8 *leaf; /* pick up a pointer to the leaves of the dmap tree */ leaf = dp->tree.stree + LEAFIND; /* determine the bit number and word within the dmap of the * starting block. */ dbitno = blkno & (BPERDMAP - 1); word = dbitno >> L2DBWORD; /* block range better be within the dmap */ assert(dbitno + nblocks <= BPERDMAP); /* allocate the bits of the dmap's words corresponding to the block * range. not all bits of the first and last words may be contained * within the block range. if this is the case, we'll work against * those words (i.e. partial first and/or last) on an individual basis * (a single pass), allocating the bits of interest by hand and * updating the leaf corresponding to the dmap word. a single pass * will be used for all dmap words fully contained within the * specified range. within this pass, the bits of all fully contained * dmap words will be marked as free in a single shot and the leaves * will be updated. a single leaf may describe the free space of * multiple dmap words, so we may update only a subset of the actual * leaves corresponding to the dmap words of the block range. */ for (rembits = nblocks; rembits > 0; rembits -= nb, dbitno += nb) { /* determine the bit number within the word and * the number of bits within the word. */ wbitno = dbitno & (DBWORD - 1); nb = min(rembits, DBWORD - wbitno); /* check if only part of a word is to be allocated. */ if (nb < DBWORD) { /* allocate (set to 1) the appropriate bits within * this dmap word. */ dp->wmap[word] |= cpu_to_le32(ONES << (DBWORD - nb) >> wbitno); /* update the leaf for this dmap word. in addition * to setting the leaf value to the binary buddy max * of the updated dmap word, dbSplit() will split * the binary system of the leaves if need be. */ dbSplit(tp, word, BUDMIN, dbMaxBud((u8 *)&dp->wmap[word]), false); word += 1; } else { /* one or more dmap words are fully contained * within the block range. determine how many * words and allocate (set to 1) the bits of these * words. */ nwords = rembits >> L2DBWORD; memset(&dp->wmap[word], (int) ONES, nwords * 4); /* determine how many bits. */ nb = nwords << L2DBWORD; /* now update the appropriate leaves to reflect * the allocated words. */ for (; nwords > 0; nwords -= nw) { if (leaf[word] < BUDMIN) { jfs_error(bmp->db_ipbmap->i_sb, "leaf page corrupt\n"); break; } /* determine what the leaf value should be * updated to as the minimum of the l2 number * of bits being allocated and the l2 number * of bits currently described by this leaf. */ size = min_t(int, leaf[word], NLSTOL2BSZ(nwords)); /* update the leaf to reflect the allocation. * in addition to setting the leaf value to * NOFREE, dbSplit() will split the binary * system of the leaves to reflect the current * allocation (size). */ dbSplit(tp, word, size, NOFREE, false); /* get the number of dmap words handled */ nw = BUDSIZE(size, BUDMIN); word += nw; } } } /* update the free count for this dmap */ le32_add_cpu(&dp->nfree, -nblocks); BMAP_LOCK(bmp); /* if this allocation group is completely free, * update the maximum allocation group number if this allocation * group is the new max. */ agno = blkno >> bmp->db_agl2size; if (agno > bmp->db_maxag) bmp->db_maxag = agno; /* update the free count for the allocation group and map */ bmp->db_agfree[agno] -= nblocks; bmp->db_nfree -= nblocks; BMAP_UNLOCK(bmp); } /* * NAME: dbFreeBits() * * FUNCTION: free a specified block range from a dmap. * * this routine updates the dmap to reflect the working * state allocation of the specified block range. it directly * updates the bits of the working map and causes the adjustment * of the binary buddy system described by the dmap's dmtree * leaves to reflect the bits freed. it also causes the dmap's * dmtree, as a whole, to reflect the deallocated range. * * PARAMETERS: * bmp - pointer to bmap descriptor * dp - pointer to dmap to free bits from. * blkno - starting block number of the bits to be freed. * nblocks - number of bits to be freed. * * RETURN VALUES: 0 for success * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbFreeBits(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { int dbitno, word, rembits, nb, nwords, wbitno, nw, agno; dmtree_t *tp = (dmtree_t *) & dp->tree; int rc = 0; int size; /* determine the bit number and word within the dmap of the * starting block. */ dbitno = blkno & (BPERDMAP - 1); word = dbitno >> L2DBWORD; /* block range better be within the dmap. */ assert(dbitno + nblocks <= BPERDMAP); /* free the bits of the dmaps words corresponding to the block range. * not all bits of the first and last words may be contained within * the block range. if this is the case, we'll work against those * words (i.e. partial first and/or last) on an individual basis * (a single pass), freeing the bits of interest by hand and updating * the leaf corresponding to the dmap word. a single pass will be used * for all dmap words fully contained within the specified range. * within this pass, the bits of all fully contained dmap words will * be marked as free in a single shot and the leaves will be updated. a * single leaf may describe the free space of multiple dmap words, * so we may update only a subset of the actual leaves corresponding * to the dmap words of the block range. * * dbJoin() is used to update leaf values and will join the binary * buddy system of the leaves if the new leaf values indicate this * should be done. */ for (rembits = nblocks; rembits > 0; rembits -= nb, dbitno += nb) { /* determine the bit number within the word and * the number of bits within the word. */ wbitno = dbitno & (DBWORD - 1); nb = min(rembits, DBWORD - wbitno); /* check if only part of a word is to be freed. */ if (nb < DBWORD) { /* free (zero) the appropriate bits within this * dmap word. */ dp->wmap[word] &= cpu_to_le32(~(ONES << (DBWORD - nb) >> wbitno)); /* update the leaf for this dmap word. */ rc = dbJoin(tp, word, dbMaxBud((u8 *)&dp->wmap[word]), false); if (rc) return rc; word += 1; } else { /* one or more dmap words are fully contained * within the block range. determine how many * words and free (zero) the bits of these words. */ nwords = rembits >> L2DBWORD; memset(&dp->wmap[word], 0, nwords * 4); /* determine how many bits. */ nb = nwords << L2DBWORD; /* now update the appropriate leaves to reflect * the freed words. */ for (; nwords > 0; nwords -= nw) { /* determine what the leaf value should be * updated to as the minimum of the l2 number * of bits being freed and the l2 (max) number * of bits that can be described by this leaf. */ size = min(LITOL2BSZ (word, L2LPERDMAP, BUDMIN), NLSTOL2BSZ(nwords)); /* update the leaf. */ rc = dbJoin(tp, word, size, false); if (rc) return rc; /* get the number of dmap words handled. */ nw = BUDSIZE(size, BUDMIN); word += nw; } } } /* update the free count for this dmap. */ le32_add_cpu(&dp->nfree, nblocks); BMAP_LOCK(bmp); /* update the free count for the allocation group and * map. */ agno = blkno >> bmp->db_agl2size; bmp->db_nfree += nblocks; bmp->db_agfree[agno] += nblocks; /* check if this allocation group is not completely free and * if it is currently the maximum (rightmost) allocation group. * if so, establish the new maximum allocation group number by * searching left for the first allocation group with allocation. */ if ((bmp->db_agfree[agno] == bmp->db_agsize && agno == bmp->db_maxag) || (agno == bmp->db_numag - 1 && bmp->db_agfree[agno] == (bmp-> db_mapsize & (BPERDMAP - 1)))) { while (bmp->db_maxag > 0) { bmp->db_maxag -= 1; if (bmp->db_agfree[bmp->db_maxag] != bmp->db_agsize) break; } /* re-establish the allocation group preference if the * current preference is right of the maximum allocation * group. */ if (bmp->db_agpref > bmp->db_maxag) bmp->db_agpref = bmp->db_maxag; } BMAP_UNLOCK(bmp); return 0; } /* * NAME: dbAdjCtl() * * FUNCTION: adjust a dmap control page at a specified level to reflect * the change in a lower level dmap or dmap control page's * maximum string of free blocks (i.e. a change in the root * of the lower level object's dmtree) due to the allocation * or deallocation of a range of blocks with a single dmap. * * on entry, this routine is provided with the new value of * the lower level dmap or dmap control page root and the * starting block number of the block range whose allocation * or deallocation resulted in the root change. this range * is respresented by a single leaf of the current dmapctl * and the leaf will be updated with this value, possibly * causing a binary buddy system within the leaves to be * split or joined. the update may also cause the dmapctl's * dmtree to be updated. * * if the adjustment of the dmap control page, itself, causes its * root to change, this change will be bubbled up to the next dmap * control level by a recursive call to this routine, specifying * the new root value and the next dmap control page level to * be adjusted. * PARAMETERS: * bmp - pointer to bmap descriptor * blkno - the first block of a block range within a dmap. it is * the allocation or deallocation of this block range that * requires the dmap control page to be adjusted. * newval - the new value of the lower level dmap or dmap control * page root. * alloc - 'true' if adjustment is due to an allocation. * level - current level of dmap control page (i.e. L0, L1, L2) to * be adjusted. * * RETURN VALUES: * 0 - success * -EIO - i/o error * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level) { struct metapage *mp; s8 oldroot; int oldval; s64 lblkno; struct dmapctl *dcp; int rc, leafno, ti; /* get the buffer for the dmap control page for the specified * block number and control page level. */ lblkno = BLKTOCTL(blkno, bmp->db_l2nbperpage, level); mp = read_metapage(bmp->db_ipbmap, lblkno, PSIZE, 0); if (mp == NULL) return -EIO; dcp = (struct dmapctl *) mp->data; if (dcp->leafidx != cpu_to_le32(CTLLEAFIND)) { jfs_error(bmp->db_ipbmap->i_sb, "Corrupt dmapctl page\n"); release_metapage(mp); return -EIO; } /* determine the leaf number corresponding to the block and * the index within the dmap control tree. */ leafno = BLKTOCTLLEAF(blkno, dcp->budmin); ti = leafno + le32_to_cpu(dcp->leafidx); /* save the current leaf value and the current root level (i.e. * maximum l2 free string described by this dmapctl). */ oldval = dcp->stree[ti]; oldroot = dcp->stree[ROOT]; /* check if this is a control page update for an allocation. * if so, update the leaf to reflect the new leaf value using * dbSplit(); otherwise (deallocation), use dbJoin() to update * the leaf with the new value. in addition to updating the * leaf, dbSplit() will also split the binary buddy system of * the leaves, if required, and bubble new values within the * dmapctl tree, if required. similarly, dbJoin() will join * the binary buddy system of leaves and bubble new values up * the dmapctl tree as required by the new leaf value. */ if (alloc) { /* check if we are in the middle of a binary buddy * system. this happens when we are performing the * first allocation out of an allocation group that * is part (not the first part) of a larger binary * buddy system. if we are in the middle, back split * the system prior to calling dbSplit() which assumes * that it is at the front of a binary buddy system. */ if (oldval == NOFREE) { rc = dbBackSplit((dmtree_t *)dcp, leafno, true); if (rc) { release_metapage(mp); return rc; } oldval = dcp->stree[ti]; } dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval, true); } else { rc = dbJoin((dmtree_t *) dcp, leafno, newval, true); if (rc) { release_metapage(mp); return rc; } } /* check if the root of the current dmap control page changed due * to the update and if the current dmap control page is not at * the current top level (i.e. L0, L1, L2) of the map. if so (i.e. * root changed and this is not the top level), call this routine * again (recursion) for the next higher level of the mapping to * reflect the change in root for the current dmap control page. */ if (dcp->stree[ROOT] != oldroot) { /* are we below the top level of the map. if so, * bubble the root up to the next higher level. */ if (level < bmp->db_maxlevel) { /* bubble up the new root of this dmap control page to * the next level. */ if ((rc = dbAdjCtl(bmp, blkno, dcp->stree[ROOT], alloc, level + 1))) { /* something went wrong in bubbling up the new * root value, so backout the changes to the * current dmap control page. */ if (alloc) { dbJoin((dmtree_t *) dcp, leafno, oldval, true); } else { /* the dbJoin() above might have * caused a larger binary buddy system * to form and we may now be in the * middle of it. if this is the case, * back split the buddies. */ if (dcp->stree[ti] == NOFREE) dbBackSplit((dmtree_t *) dcp, leafno, true); dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, oldval, true); } /* release the buffer and return the error. */ release_metapage(mp); return (rc); } } else { /* we're at the top level of the map. update * the bmap control page to reflect the size * of the maximum free buddy system. */ assert(level == bmp->db_maxlevel); if (bmp->db_maxfreebud != oldroot) { jfs_error(bmp->db_ipbmap->i_sb, "the maximum free buddy is not the old root\n"); } bmp->db_maxfreebud = dcp->stree[ROOT]; } } /* write the buffer. */ write_metapage(mp); return (0); } /* * NAME: dbSplit() * * FUNCTION: update the leaf of a dmtree with a new value, splitting * the leaf from the binary buddy system of the dmtree's * leaves, as required. * * PARAMETERS: * tp - pointer to the tree containing the leaf. * leafno - the number of the leaf to be updated. * splitsz - the size the binary buddy system starting at the leaf * must be split to, specified as the log2 number of blocks. * newval - the new value for the leaf. * * RETURN VALUES: none * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static void dbSplit(dmtree_t *tp, int leafno, int splitsz, int newval, bool is_ctl) { int budsz; int cursz; s8 *leaf = tp->dmt_stree + le32_to_cpu(tp->dmt_leafidx); /* check if the leaf needs to be split. */ if (leaf[leafno] > tp->dmt_budmin) { /* the split occurs by cutting the buddy system in half * at the specified leaf until we reach the specified * size. pick up the starting split size (current size * - 1 in l2) and the corresponding buddy size. */ cursz = leaf[leafno] - 1; budsz = BUDSIZE(cursz, tp->dmt_budmin); /* split until we reach the specified size. */ while (cursz >= splitsz) { /* update the buddy's leaf with its new value. */ dbAdjTree(tp, leafno ^ budsz, cursz, is_ctl); /* on to the next size and buddy. */ cursz -= 1; budsz >>= 1; } } /* adjust the dmap tree to reflect the specified leaf's new * value. */ dbAdjTree(tp, leafno, newval, is_ctl); } /* * NAME: dbBackSplit() * * FUNCTION: back split the binary buddy system of dmtree leaves * that hold a specified leaf until the specified leaf * starts its own binary buddy system. * * the allocators typically perform allocations at the start * of binary buddy systems and dbSplit() is used to accomplish * any required splits. in some cases, however, allocation * may occur in the middle of a binary system and requires a * back split, with the split proceeding out from the middle of * the system (less efficient) rather than the start of the * system (more efficient). the cases in which a back split * is required are rare and are limited to the first allocation * within an allocation group which is a part (not first part) * of a larger binary buddy system and a few exception cases * in which a previous join operation must be backed out. * * PARAMETERS: * tp - pointer to the tree containing the leaf. * leafno - the number of the leaf to be updated. * * RETURN VALUES: none * * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit; */ static int dbBackSplit(dmtree_t *tp, int leafno, bool is_ctl) { int budsz, bud, w, bsz, size; int cursz; s8 *leaf = tp->dmt_stree + le32_to_cpu(tp->dmt_leafidx); /* leaf should be part (not first part) of a binary * buddy system. */ assert(leaf[leafno] == NOFREE); /* the back split is accomplished by iteratively finding the leaf * that starts the buddy system that contains the specified leaf and * splitting that system in two. this iteration continues until * the specified leaf becomes the start of a buddy system. * * determine maximum possible l2 size for the specified leaf. */ size = LITOL2BSZ(leafno, le32_to_cpu(tp->dmt_l2nleafs), tp->dmt_budmin); /* determine the number of leaves covered by this size. this * is the buddy size that we will start with as we search for * the buddy system that contains the specified leaf. */ budsz = BUDSIZE(size, tp->dmt_budmin); /* back split. */ while (leaf[leafno] == NOFREE) { /* find the leftmost buddy leaf. */ for (w = leafno, bsz = budsz;; bsz <<= 1, w = (w < bud) ? w : bud) { if (bsz >= le32_to_cpu(tp->dmt_nleafs)) { jfs_err("JFS: block map error in dbBackSplit"); return -EIO; } /* determine the buddy. */ bud = w ^ bsz; /* check if this buddy is the start of the system. */ if (leaf[bud] != NOFREE) { /* split the leaf at the start of the * system in two. */ cursz = leaf[bud] - 1; dbSplit(tp, bud, cursz, cursz, is_ctl); break; } } } if (leaf[leafno] != size) { jfs_err("JFS: wrong leaf value in dbBackSplit"); return -EIO; } return 0; } /* * NAME: dbJoin() * * FUNCTION: update the leaf of a dmtree with a new value, joining * the leaf with other leaves of the dmtree into a multi-leaf * binary buddy system, as required. * * PARAMETERS: * tp - pointer to the tree containing the leaf. * leafno - the number of the leaf to be updated. * newval - the new value for the leaf. * * RETURN VALUES: none */ static int dbJoin(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int budsz, buddy; s8 *leaf; /* can the new leaf value require a join with other leaves ? */ if (newval >= tp->dmt_budmin) { /* pickup a pointer to the leaves of the tree. */ leaf = tp->dmt_stree + le32_to_cpu(tp->dmt_leafidx); /* try to join the specified leaf into a large binary * buddy system. the join proceeds by attempting to join * the specified leafno with its buddy (leaf) at new value. * if the join occurs, we attempt to join the left leaf * of the joined buddies with its buddy at new value + 1. * we continue to join until we find a buddy that cannot be * joined (does not have a value equal to the size of the * last join) or until all leaves have been joined into a * single system. * * get the buddy size (number of words covered) of * the new value. */ budsz = BUDSIZE(newval, tp->dmt_budmin); /* try to join. */ while (budsz < le32_to_cpu(tp->dmt_nleafs)) { /* get the buddy leaf. */ buddy = leafno ^ budsz; /* if the leaf's new value is greater than its * buddy's value, we join no more. */ if (newval > leaf[buddy]) break; /* It shouldn't be less */ if (newval < leaf[buddy]) return -EIO; /* check which (leafno or buddy) is the left buddy. * the left buddy gets to claim the blocks resulting * from the join while the right gets to claim none. * the left buddy is also eligible to participate in * a join at the next higher level while the right * is not. * */ if (leafno < buddy) { /* leafno is the left buddy. */ dbAdjTree(tp, buddy, NOFREE, is_ctl); } else { /* buddy is the left buddy and becomes * leafno. */ dbAdjTree(tp, leafno, NOFREE, is_ctl); leafno = buddy; } /* on to try the next join. */ newval += 1; budsz <<= 1; } } /* update the leaf value. */ dbAdjTree(tp, leafno, newval, is_ctl); return 0; } /* * NAME: dbAdjTree() * * FUNCTION: update a leaf of a dmtree with a new value, adjusting * the dmtree, as required, to reflect the new leaf value. * the combination of any buddies must already be done before * this is called. * * PARAMETERS: * tp - pointer to the tree to be adjusted. * leafno - the number of the leaf to be updated. * newval - the new value for the leaf. * * RETURN VALUES: none */ static void dbAdjTree(dmtree_t *tp, int leafno, int newval, bool is_ctl) { int lp, pp, k; int max, size; size = is_ctl ? CTLTREESIZE : TREESIZE; /* pick up the index of the leaf for this leafno. */ lp = leafno + le32_to_cpu(tp->dmt_leafidx); if (WARN_ON_ONCE(lp >= size || lp < 0)) return; /* is the current value the same as the old value ? if so, * there is nothing to do. */ if (tp->dmt_stree[lp] == newval) return; /* set the new value. */ tp->dmt_stree[lp] = newval; /* bubble the new value up the tree as required. */ for (k = 0; k < le32_to_cpu(tp->dmt_height); k++) { if (lp == 0) break; /* get the index of the first leaf of the 4 leaf * group containing the specified leaf (leafno). */ lp = ((lp - 1) & ~0x03) + 1; /* get the index of the parent of this 4 leaf group. */ pp = (lp - 1) >> 2; /* determine the maximum of the 4 leaves. */ max = TREEMAX(&tp->dmt_stree[lp]); /* if the maximum of the 4 is the same as the * parent's value, we're done. */ if (tp->dmt_stree[pp] == max) break; /* parent gets new value. */ tp->dmt_stree[pp] = max; /* parent becomes leaf for next go-round. */ lp = pp; } } /* * NAME: dbFindLeaf() * * FUNCTION: search a dmtree_t for sufficient free blocks, returning * the index of a leaf describing the free blocks if * sufficient free blocks are found. * * the search starts at the top of the dmtree_t tree and * proceeds down the tree to the leftmost leaf with sufficient * free space. * * PARAMETERS: * tp - pointer to the tree to be searched. * l2nb - log2 number of free blocks to search for. * leafidx - return pointer to be set to the index of the leaf * describing at least l2nb free blocks if sufficient * free blocks are found. * is_ctl - determines if the tree is of type ctl * * RETURN VALUES: * 0 - success * -ENOSPC - insufficient free blocks. */ static int dbFindLeaf(dmtree_t *tp, int l2nb, int *leafidx, bool is_ctl) { int ti, n = 0, k, x = 0; int max_size, max_idx; max_size = is_ctl ? CTLTREESIZE : TREESIZE; max_idx = is_ctl ? LPERCTL : LPERDMAP; /* first check the root of the tree to see if there is * sufficient free space. */ if (l2nb > tp->dmt_stree[ROOT]) return -ENOSPC; /* sufficient free space available. now search down the tree * starting at the next level for the leftmost leaf that * describes sufficient free space. */ for (k = le32_to_cpu(tp->dmt_height), ti = 1; k > 0; k--, ti = ((ti + n) << 2) + 1) { /* search the four nodes at this level, starting from * the left. */ for (x = ti, n = 0; n < 4; n++) { /* sufficient free space found. move to the next * level (or quit if this is the last level). */ if (x + n > max_size) return -ENOSPC; if (l2nb <= tp->dmt_stree[x + n]) break; } /* better have found something since the higher * levels of the tree said it was here. */ assert(n < 4); } if (le32_to_cpu(tp->dmt_leafidx) >= max_idx) return -ENOSPC; /* set the return to the leftmost leaf describing sufficient * free space. */ *leafidx = x + n - le32_to_cpu(tp->dmt_leafidx); return (0); } /* * NAME: dbFindBits() * * FUNCTION: find a specified number of binary buddy free bits within a * dmap bitmap word value. * * this routine searches the bitmap value for (1 << l2nb) free * bits at (1 << l2nb) alignments within the value. * * PARAMETERS: * word - dmap bitmap word value. * l2nb - number of free bits specified as a log2 number. * * RETURN VALUES: * starting bit number of free bits. */ static int dbFindBits(u32 word, int l2nb) { int bitno, nb; u32 mask; /* get the number of bits. */ nb = 1 << l2nb; assert(nb <= DBWORD); /* complement the word so we can use a mask (i.e. 0s represent * free bits) and compute the mask. */ word = ~word; mask = ONES << (DBWORD - nb); /* scan the word for nb free bits at nb alignments. */ for (bitno = 0; mask != 0; bitno += nb, mask = (mask >> nb)) { if ((mask & word) == mask) break; } ASSERT(bitno < 32); /* return the bit number. */ return (bitno); } /* * NAME: dbMaxBud(u8 *cp) * * FUNCTION: determine the largest binary buddy string of free * bits within 32-bits of the map. * * PARAMETERS: * cp - pointer to the 32-bit value. * * RETURN VALUES: * largest binary buddy of free bits within a dmap word. */ static int dbMaxBud(u8 * cp) { signed char tmp1, tmp2; /* check if the wmap word is all free. if so, the * free buddy size is BUDMIN. */ if (*((uint *) cp) == 0) return (BUDMIN); /* check if the wmap word is half free. if so, the * free buddy size is BUDMIN-1. */ if (*((u16 *) cp) == 0 || *((u16 *) cp + 1) == 0) return (BUDMIN - 1); /* not all free or half free. determine the free buddy * size thru table lookup using quarters of the wmap word. */ tmp1 = max(budtab[cp[2]], budtab[cp[3]]); tmp2 = max(budtab[cp[0]], budtab[cp[1]]); return (max(tmp1, tmp2)); } /* * NAME: cnttz(uint word) * * FUNCTION: determine the number of trailing zeros within a 32-bit * value. * * PARAMETERS: * value - 32-bit value to be examined. * * RETURN VALUES: * count of trailing zeros */ static int cnttz(u32 word) { int n; for (n = 0; n < 32; n++, word >>= 1) { if (word & 0x01) break; } return (n); } /* * NAME: cntlz(u32 value) * * FUNCTION: determine the number of leading zeros within a 32-bit * value. * * PARAMETERS: * value - 32-bit value to be examined. * * RETURN VALUES: * count of leading zeros */ static int cntlz(u32 value) { int n; for (n = 0; n < 32; n++, value <<= 1) { if (value & HIGHORDER) break; } return (n); } /* * NAME: blkstol2(s64 nb) * * FUNCTION: convert a block count to its log2 value. if the block * count is not a l2 multiple, it is rounded up to the next * larger l2 multiple. * * PARAMETERS: * nb - number of blocks * * RETURN VALUES: * log2 number of blocks */ static int blkstol2(s64 nb) { int l2nb; s64 mask; /* meant to be signed */ mask = (s64) 1 << (64 - 1); /* count the leading bits. */ for (l2nb = 0; l2nb < 64; l2nb++, mask >>= 1) { /* leading bit found. */ if (nb & mask) { /* determine the l2 value. */ l2nb = (64 - 1) - l2nb; /* check if we need to round up. */ if (~mask & nb) l2nb++; return (l2nb); } } assert(0); return 0; /* fix compiler warning */ } /* * NAME: dbAllocBottomUp() * * FUNCTION: alloc the specified block range from the working block * allocation map. * * the blocks will be alloc from the working map one dmap * at a time. * * PARAMETERS: * ip - pointer to in-core inode; * blkno - starting block number to be freed. * nblocks - number of blocks to be freed. * * RETURN VALUES: * 0 - success * -EIO - i/o error */ int dbAllocBottomUp(struct inode *ip, s64 blkno, s64 nblocks) { struct metapage *mp; struct dmap *dp; int nb, rc; s64 lblkno, rem; struct inode *ipbmap = JFS_SBI(ip->i_sb)->ipbmap; struct bmap *bmp = JFS_SBI(ip->i_sb)->bmap; IREAD_LOCK(ipbmap, RDWRLOCK_DMAP); /* block to be allocated better be within the mapsize. */ ASSERT(nblocks <= bmp->db_mapsize - blkno); /* * allocate the blocks a dmap at a time. */ mp = NULL; for (rem = nblocks; rem > 0; rem -= nb, blkno += nb) { /* release previous dmap if any */ if (mp) { write_metapage(mp); } /* get the buffer for the current dmap. */ lblkno = BLKTODMAP(blkno, bmp->db_l2nbperpage); mp = read_metapage(ipbmap, lblkno, PSIZE, 0); if (mp == NULL) { IREAD_UNLOCK(ipbmap); return -EIO; } dp = (struct dmap *) mp->data; /* determine the number of blocks to be allocated from * this dmap. */ nb = min(rem, BPERDMAP - (blkno & (BPERDMAP - 1))); /* allocate the blocks. */ if ((rc = dbAllocDmapBU(bmp, dp, blkno, nb))) { release_metapage(mp); IREAD_UNLOCK(ipbmap); return (rc); } } /* write the last buffer. */ write_metapage(mp); IREAD_UNLOCK(ipbmap); return (0); } static int dbAllocDmapBU(struct bmap * bmp, struct dmap * dp, s64 blkno, int nblocks) { int rc; int dbitno, word, rembits, nb, nwords, wbitno, agno; s8 oldroot; struct dmaptree *tp = (struct dmaptree *) & dp->tree; /* save the current value of the root (i.e. maximum free string) * of the dmap tree. */ oldroot = tp->stree[ROOT]; /* determine the bit number and word within the dmap of the * starting block. */ dbitno = blkno & (BPERDMAP - 1); word = dbitno >> L2DBWORD; /* block range better be within the dmap */ assert(dbitno + nblocks <= BPERDMAP); /* allocate the bits of the dmap's words corresponding to the block * range. not all bits of the first and last words may be contained * within the block range. if this is the case, we'll work against * those words (i.e. partial first and/or last) on an individual basis * (a single pass), allocating the bits of interest by hand and * updating the leaf corresponding to the dmap word. a single pass * will be used for all dmap words fully contained within the * specified range. within this pass, the bits of all fully contained * dmap words will be marked as free in a single shot and the leaves * will be updated. a single leaf may describe the free space of * multiple dmap words, so we may update only a subset of the actual * leaves corresponding to the dmap words of the block range. */ for (rembits = nblocks; rembits > 0; rembits -= nb, dbitno += nb) { /* determine the bit number within the word and * the number of bits within the word. */ wbitno = dbitno & (DBWORD - 1); nb = min(rembits, DBWORD - wbitno); /* check if only part of a word is to be allocated. */ if (nb < DBWORD) { /* allocate (set to 1) the appropriate bits within * this dmap word. */ dp->wmap[word] |= cpu_to_le32(ONES << (DBWORD - nb) >> wbitno); word++; } else { /* one or more dmap words are fully contained * within the block range. determine how many * words and allocate (set to 1) the bits of these * words. */ nwords = rembits >> L2DBWORD; memset(&dp->wmap[word], (int) ONES, nwords * 4); /* determine how many bits */ nb = nwords << L2DBWORD; word += nwords; } } /* update the free count for this dmap */ le32_add_cpu(&dp->nfree, -nblocks); /* reconstruct summary tree */ dbInitDmapTree(dp); BMAP_LOCK(bmp); /* if this allocation group is completely free, * update the highest active allocation group number * if this allocation group is the new max. */ agno = blkno >> bmp->db_agl2size; if (agno > bmp->db_maxag) bmp->db_maxag = agno; /* update the free count for the allocation group and map */ bmp->db_agfree[agno] -= nblocks; bmp->db_nfree -= nblocks; BMAP_UNLOCK(bmp); /* if the root has not changed, done. */ if (tp->stree[ROOT] == oldroot) return (0); /* root changed. bubble the change up to the dmap control pages. * if the adjustment of the upper level control pages fails, * backout the bit allocation (thus making everything consistent). */ if ((rc = dbAdjCtl(bmp, blkno, tp->stree[ROOT], 1, 0))) dbFreeBits(bmp, dp, blkno, nblocks); return (rc); } /* * NAME: dbExtendFS() * * FUNCTION: extend bmap from blkno for nblocks; * dbExtendFS() updates bmap ready for dbAllocBottomUp(); * * L2 * | * L1---------------------------------L1 * | | * L0---------L0---------L0 L0---------L0---------L0 * | | | | | | * d0,...,dn d0,...,dn d0,...,dn d0,...,dn d0,...,dn d0,.,dm; * L2L1L0d0,...,dnL0d0,...,dnL0d0,...,dnL1L0d0,...,dnL0d0,...,dnL0d0,..dm * * <---old---><----------------------------extend-----------------------> */ int dbExtendFS(struct inode *ipbmap, s64 blkno, s64 nblocks) { struct jfs_sb_info *sbi = JFS_SBI(ipbmap->i_sb); int nbperpage = sbi->nbperpage; int i, i0 = true, j, j0 = true, k, n; s64 newsize; s64 p; struct metapage *mp, *l2mp, *l1mp = NULL, *l0mp = NULL; struct dmapctl *l2dcp, *l1dcp, *l0dcp; struct dmap *dp; s8 *l0leaf, *l1leaf, *l2leaf; struct bmap *bmp = sbi->bmap; int agno, l2agsize, oldl2agsize; s64 ag_rem; newsize = blkno + nblocks; jfs_info("dbExtendFS: blkno:%Ld nblocks:%Ld newsize:%Ld", (long long) blkno, (long long) nblocks, (long long) newsize); /* * initialize bmap control page. * * all the data in bmap control page should exclude * the mkfs hidden dmap page. */ /* update mapsize */ bmp->db_mapsize = newsize; bmp->db_maxlevel = BMAPSZTOLEV(bmp->db_mapsize); /* compute new AG size */ l2agsize = dbGetL2AGSize(newsize); oldl2agsize = bmp->db_agl2size; bmp->db_agl2size = l2agsize; bmp->db_agsize = (s64)1 << l2agsize; /* compute new number of AG */ agno = bmp->db_numag; bmp->db_numag = newsize >> l2agsize; bmp->db_numag += ((u32) newsize % (u32) bmp->db_agsize) ? 1 : 0; /* * reconfigure db_agfree[] * from old AG configuration to new AG configuration; * * coalesce contiguous k (newAGSize/oldAGSize) AGs; * i.e., (AGi, ..., AGj) where i = k*n and j = k*(n+1) - 1 to AGn; * note: new AG size = old AG size * (2**x). */ if (l2agsize == oldl2agsize) goto extend; k = 1 << (l2agsize - oldl2agsize); ag_rem = bmp->db_agfree[0]; /* save agfree[0] */ for (i = 0, n = 0; i < agno; n++) { bmp->db_agfree[n] = 0; /* init collection point */ /* coalesce contiguous k AGs; */ for (j = 0; j < k && i < agno; j++, i++) { /* merge AGi to AGn */ bmp->db_agfree[n] += bmp->db_agfree[i]; } } bmp->db_agfree[0] += ag_rem; /* restore agfree[0] */ for (; n < MAXAG; n++) bmp->db_agfree[n] = 0; /* * update highest active ag number */ bmp->db_maxag = bmp->db_maxag / k; /* * extend bmap * * update bit maps and corresponding level control pages; * global control page db_nfree, db_agfree[agno], db_maxfreebud; */ extend: /* get L2 page */ p = BMAPBLKNO + nbperpage; /* L2 page */ l2mp = read_metapage(ipbmap, p, PSIZE, 0); if (!l2mp) { jfs_error(ipbmap->i_sb, "L2 page could not be read\n"); return -EIO; } l2dcp = (struct dmapctl *) l2mp->data; /* compute start L1 */ k = blkno >> L2MAXL1SIZE; l2leaf = l2dcp->stree + CTLLEAFIND + k; p = BLKTOL1(blkno, sbi->l2nbperpage); /* L1 page */ /* * extend each L1 in L2 */ for (; k < LPERCTL; k++, p += nbperpage) { /* get L1 page */ if (j0) { /* read in L1 page: (blkno & (MAXL1SIZE - 1)) */ l1mp = read_metapage(ipbmap, p, PSIZE, 0); if (l1mp == NULL) goto errout; l1dcp = (struct dmapctl *) l1mp->data; /* compute start L0 */ j = (blkno & (MAXL1SIZE - 1)) >> L2MAXL0SIZE; l1leaf = l1dcp->stree + CTLLEAFIND + j; p = BLKTOL0(blkno, sbi->l2nbperpage); j0 = false; } else { /* assign/init L1 page */ l1mp = get_metapage(ipbmap, p, PSIZE, 0); if (l1mp == NULL) goto errout; l1dcp = (struct dmapctl *) l1mp->data; /* compute start L0 */ j = 0; l1leaf = l1dcp->stree + CTLLEAFIND; p += nbperpage; /* 1st L0 of L1.k */ } /* * extend each L0 in L1 */ for (; j < LPERCTL; j++) { /* get L0 page */ if (i0) { /* read in L0 page: (blkno & (MAXL0SIZE - 1)) */ l0mp = read_metapage(ipbmap, p, PSIZE, 0); if (l0mp == NULL) goto errout; l0dcp = (struct dmapctl *) l0mp->data; /* compute start dmap */ i = (blkno & (MAXL0SIZE - 1)) >> L2BPERDMAP; l0leaf = l0dcp->stree + CTLLEAFIND + i; p = BLKTODMAP(blkno, sbi->l2nbperpage); i0 = false; } else { /* assign/init L0 page */ l0mp = get_metapage(ipbmap, p, PSIZE, 0); if (l0mp == NULL) goto errout; l0dcp = (struct dmapctl *) l0mp->data; /* compute start dmap */ i = 0; l0leaf = l0dcp->stree + CTLLEAFIND; p += nbperpage; /* 1st dmap of L0.j */ } /* * extend each dmap in L0 */ for (; i < LPERCTL; i++) { /* * reconstruct the dmap page, and * initialize corresponding parent L0 leaf */ if ((n = blkno & (BPERDMAP - 1))) { /* read in dmap page: */ mp = read_metapage(ipbmap, p, PSIZE, 0); if (mp == NULL) goto errout; n = min(nblocks, (s64)BPERDMAP - n); } else { /* assign/init dmap page */ mp = read_metapage(ipbmap, p, PSIZE, 0); if (mp == NULL) goto errout; n = min_t(s64, nblocks, BPERDMAP); } dp = (struct dmap *) mp->data; *l0leaf = dbInitDmap(dp, blkno, n); bmp->db_nfree += n; agno = le64_to_cpu(dp->start) >> l2agsize; bmp->db_agfree[agno] += n; write_metapage(mp); l0leaf++; p += nbperpage; blkno += n; nblocks -= n; if (nblocks == 0) break; } /* for each dmap in a L0 */ /* * build current L0 page from its leaves, and * initialize corresponding parent L1 leaf */ *l1leaf = dbInitDmapCtl(l0dcp, 0, ++i); write_metapage(l0mp); l0mp = NULL; if (nblocks) l1leaf++; /* continue for next L0 */ else { /* more than 1 L0 ? */ if (j > 0) break; /* build L1 page */ else { /* summarize in global bmap page */ bmp->db_maxfreebud = *l1leaf; release_metapage(l1mp); release_metapage(l2mp); goto finalize; } } } /* for each L0 in a L1 */ /* * build current L1 page from its leaves, and * initialize corresponding parent L2 leaf */ *l2leaf = dbInitDmapCtl(l1dcp, 1, ++j); write_metapage(l1mp); l1mp = NULL; if (nblocks) l2leaf++; /* continue for next L1 */ else { /* more than 1 L1 ? */ if (k > 0) break; /* build L2 page */ else { /* summarize in global bmap page */ bmp->db_maxfreebud = *l2leaf; release_metapage(l2mp); goto finalize; } } } /* for each L1 in a L2 */ jfs_error(ipbmap->i_sb, "function has not returned as expected\n"); errout: if (l0mp) release_metapage(l0mp); if (l1mp) release_metapage(l1mp); release_metapage(l2mp); return -EIO; /* * finalize bmap control page */ finalize: return 0; } /* * dbFinalizeBmap() */ void dbFinalizeBmap(struct inode *ipbmap) { struct bmap *bmp = JFS_SBI(ipbmap->i_sb)->bmap; int actags, inactags, l2nl; s64 ag_rem, actfree, inactfree, avgfree; int i, n; /* * finalize bmap control page */ //finalize: /* * compute db_agpref: preferred ag to allocate from * (the leftmost ag with average free space in it); */ //agpref: /* get the number of active ags and inactive ags */ actags = bmp->db_maxag + 1; inactags = bmp->db_numag - actags; ag_rem = bmp->db_mapsize & (bmp->db_agsize - 1); /* ??? */ /* determine how many blocks are in the inactive allocation * groups. in doing this, we must account for the fact that * the rightmost group might be a partial group (i.e. file * system size is not a multiple of the group size). */ inactfree = (inactags && ag_rem) ? (((s64)inactags - 1) << bmp->db_agl2size) + ag_rem : ((s64)inactags << bmp->db_agl2size); /* determine how many free blocks are in the active * allocation groups plus the average number of free blocks * within the active ags. */ actfree = bmp->db_nfree - inactfree; avgfree = (u32) actfree / (u32) actags; /* if the preferred allocation group has not average free space. * re-establish the preferred group as the leftmost * group with average free space. */ if (bmp->db_agfree[bmp->db_agpref] < avgfree) { for (bmp->db_agpref = 0; bmp->db_agpref < actags; bmp->db_agpref++) { if (bmp->db_agfree[bmp->db_agpref] >= avgfree) break; } if (bmp->db_agpref >= bmp->db_numag) { jfs_error(ipbmap->i_sb, "cannot find ag with average freespace\n"); } } /* * compute db_aglevel, db_agheight, db_width, db_agstart: * an ag is covered in aglevel dmapctl summary tree, * at agheight level height (from leaf) with agwidth number of nodes * each, which starts at agstart index node of the smmary tree node * array; */ bmp->db_aglevel = BMAPSZTOLEV(bmp->db_agsize); l2nl = bmp->db_agl2size - (L2BPERDMAP + bmp->db_aglevel * L2LPERCTL); bmp->db_agheight = l2nl >> 1; bmp->db_agwidth = 1 << (l2nl - (bmp->db_agheight << 1)); for (i = 5 - bmp->db_agheight, bmp->db_agstart = 0, n = 1; i > 0; i--) { bmp->db_agstart += n; n <<= 2; } } /* * NAME: dbInitDmap()/ujfs_idmap_page() * * FUNCTION: initialize working/persistent bitmap of the dmap page * for the specified number of blocks: * * at entry, the bitmaps had been initialized as free (ZEROS); * The number of blocks will only account for the actually * existing blocks. Blocks which don't actually exist in * the aggregate will be marked as allocated (ONES); * * PARAMETERS: * dp - pointer to page of map * nblocks - number of blocks this page * * RETURNS: NONE */ static int dbInitDmap(struct dmap * dp, s64 Blkno, int nblocks) { int blkno, w, b, r, nw, nb, i; /* starting block number within the dmap */ blkno = Blkno & (BPERDMAP - 1); if (blkno == 0) { dp->nblocks = dp->nfree = cpu_to_le32(nblocks); dp->start = cpu_to_le64(Blkno); if (nblocks == BPERDMAP) { memset(&dp->wmap[0], 0, LPERDMAP * 4); memset(&dp->pmap[0], 0, LPERDMAP * 4); goto initTree; } } else { le32_add_cpu(&dp->nblocks, nblocks); le32_add_cpu(&dp->nfree, nblocks); } /* word number containing start block number */ w = blkno >> L2DBWORD; /* * free the bits corresponding to the block range (ZEROS): * note: not all bits of the first and last words may be contained * within the block range. */ for (r = nblocks; r > 0; r -= nb, blkno += nb) { /* number of bits preceding range to be freed in the word */ b = blkno & (DBWORD - 1); /* number of bits to free in the word */ nb = min(r, DBWORD - b); /* is partial word to be freed ? */ if (nb < DBWORD) { /* free (set to 0) from the bitmap word */ dp->wmap[w] &= cpu_to_le32(~(ONES << (DBWORD - nb) >> b)); dp->pmap[w] &= cpu_to_le32(~(ONES << (DBWORD - nb) >> b)); /* skip the word freed */ w++; } else { /* free (set to 0) contiguous bitmap words */ nw = r >> L2DBWORD; memset(&dp->wmap[w], 0, nw * 4); memset(&dp->pmap[w], 0, nw * 4); /* skip the words freed */ nb = nw << L2DBWORD; w += nw; } } /* * mark bits following the range to be freed (non-existing * blocks) as allocated (ONES) */ if (blkno == BPERDMAP) goto initTree; /* the first word beyond the end of existing blocks */ w = blkno >> L2DBWORD; /* does nblocks fall on a 32-bit boundary ? */ b = blkno & (DBWORD - 1); if (b) { /* mark a partial word allocated */ dp->wmap[w] = dp->pmap[w] = cpu_to_le32(ONES >> b); w++; } /* set the rest of the words in the page to allocated (ONES) */ for (i = w; i < LPERDMAP; i++) dp->pmap[i] = dp->wmap[i] = cpu_to_le32(ONES); /* * init tree */ initTree: return (dbInitDmapTree(dp)); } /* * NAME: dbInitDmapTree()/ujfs_complete_dmap() * * FUNCTION: initialize summary tree of the specified dmap: * * at entry, bitmap of the dmap has been initialized; * * PARAMETERS: * dp - dmap to complete * blkno - starting block number for this dmap * treemax - will be filled in with max free for this dmap * * RETURNS: max free string at the root of the tree */ static int dbInitDmapTree(struct dmap * dp) { struct dmaptree *tp; s8 *cp; int i; /* init fixed info of tree */ tp = &dp->tree; tp->nleafs = cpu_to_le32(LPERDMAP); tp->l2nleafs = cpu_to_le32(L2LPERDMAP); tp->leafidx = cpu_to_le32(LEAFIND); tp->height = cpu_to_le32(4); tp->budmin = BUDMIN; /* init each leaf from corresponding wmap word: * note: leaf is set to NOFREE(-1) if all blocks of corresponding * bitmap word are allocated. */ cp = tp->stree + le32_to_cpu(tp->leafidx); for (i = 0; i < LPERDMAP; i++) *cp++ = dbMaxBud((u8 *) & dp->wmap[i]); /* build the dmap's binary buddy summary tree */ return (dbInitTree(tp)); } /* * NAME: dbInitTree()/ujfs_adjtree() * * FUNCTION: initialize binary buddy summary tree of a dmap or dmapctl. * * at entry, the leaves of the tree has been initialized * from corresponding bitmap word or root of summary tree * of the child control page; * configure binary buddy system at the leaf level, then * bubble up the values of the leaf nodes up the tree. * * PARAMETERS: * cp - Pointer to the root of the tree * l2leaves- Number of leaf nodes as a power of 2 * l2min - Number of blocks that can be covered by a leaf * as a power of 2 * * RETURNS: max free string at the root of the tree */ static int dbInitTree(struct dmaptree * dtp) { int l2max, l2free, bsize, nextb, i; int child, parent, nparent; s8 *tp, *cp, *cp1; tp = dtp->stree; /* Determine the maximum free string possible for the leaves */ l2max = le32_to_cpu(dtp->l2nleafs) + dtp->budmin; /* * configure the leaf level into binary buddy system * * Try to combine buddies starting with a buddy size of 1 * (i.e. two leaves). At a buddy size of 1 two buddy leaves * can be combined if both buddies have a maximum free of l2min; * the combination will result in the left-most buddy leaf having * a maximum free of l2min+1. * After processing all buddies for a given size, process buddies * at the next higher buddy size (i.e. current size * 2) and * the next maximum free (current free + 1). * This continues until the maximum possible buddy combination * yields maximum free. */ for (l2free = dtp->budmin, bsize = 1; l2free < l2max; l2free++, bsize = nextb) { /* get next buddy size == current buddy pair size */ nextb = bsize << 1; /* scan each adjacent buddy pair at current buddy size */ for (i = 0, cp = tp + le32_to_cpu(dtp->leafidx); i < le32_to_cpu(dtp->nleafs); i += nextb, cp += nextb) { /* coalesce if both adjacent buddies are max free */ if (*cp == l2free && *(cp + bsize) == l2free) { *cp = l2free + 1; /* left take right */ *(cp + bsize) = -1; /* right give left */ } } } /* * bubble summary information of leaves up the tree. * * Starting at the leaf node level, the four nodes described by * the higher level parent node are compared for a maximum free and * this maximum becomes the value of the parent node. * when all lower level nodes are processed in this fashion then * move up to the next level (parent becomes a lower level node) and * continue the process for that level. */ for (child = le32_to_cpu(dtp->leafidx), nparent = le32_to_cpu(dtp->nleafs) >> 2; nparent > 0; nparent >>= 2, child = parent) { /* get index of 1st node of parent level */ parent = (child - 1) >> 2; /* set the value of the parent node as the maximum * of the four nodes of the current level. */ for (i = 0, cp = tp + child, cp1 = tp + parent; i < nparent; i++, cp += 4, cp1++) *cp1 = TREEMAX(cp); } return (*tp); } /* * dbInitDmapCtl() * * function: initialize dmapctl page */ static int dbInitDmapCtl(struct dmapctl * dcp, int level, int i) { /* start leaf index not covered by range */ s8 *cp; dcp->nleafs = cpu_to_le32(LPERCTL); dcp->l2nleafs = cpu_to_le32(L2LPERCTL); dcp->leafidx = cpu_to_le32(CTLLEAFIND); dcp->height = cpu_to_le32(5); dcp->budmin = L2BPERDMAP + L2LPERCTL * level; /* * initialize the leaves of current level that were not covered * by the specified input block range (i.e. the leaves have no * low level dmapctl or dmap). */ cp = &dcp->stree[CTLLEAFIND + i]; for (; i < LPERCTL; i++) *cp++ = NOFREE; /* build the dmap's binary buddy summary tree */ return (dbInitTree((struct dmaptree *) dcp)); } /* * NAME: dbGetL2AGSize()/ujfs_getagl2size() * * FUNCTION: Determine log2(allocation group size) from aggregate size * * PARAMETERS: * nblocks - Number of blocks in aggregate * * RETURNS: log2(allocation group size) in aggregate blocks */ static int dbGetL2AGSize(s64 nblocks) { s64 sz; s64 m; int l2sz; if (nblocks < BPERDMAP * MAXAG) return (L2BPERDMAP); /* round up aggregate size to power of 2 */ m = ((u64) 1 << (64 - 1)); for (l2sz = 64; l2sz >= 0; l2sz--, m >>= 1) { if (m & nblocks) break; } sz = (s64) 1 << l2sz; if (sz < nblocks) l2sz += 1; /* agsize = roundupSize/max_number_of_ag */ return (l2sz - L2MAXAG); } /* * NAME: dbMapFileSizeToMapSize() * * FUNCTION: compute number of blocks the block allocation map file * can cover from the map file size; * * RETURNS: Number of blocks which can be covered by this block map file; */ /* * maximum number of map pages at each level including control pages */ #define MAXL0PAGES (1 + LPERCTL) #define MAXL1PAGES (1 + LPERCTL * MAXL0PAGES) /* * convert number of map pages to the zero origin top dmapctl level */ #define BMAPPGTOLEV(npages) \ (((npages) <= 3 + MAXL0PAGES) ? 0 : \ ((npages) <= 2 + MAXL1PAGES) ? 1 : 2) s64 dbMapFileSizeToMapSize(struct inode * ipbmap) { struct super_block *sb = ipbmap->i_sb; s64 nblocks; s64 npages, ndmaps; int level, i; int complete, factor; nblocks = ipbmap->i_size >> JFS_SBI(sb)->l2bsize; npages = nblocks >> JFS_SBI(sb)->l2nbperpage; level = BMAPPGTOLEV(npages); /* At each level, accumulate the number of dmap pages covered by * the number of full child levels below it; * repeat for the last incomplete child level. */ ndmaps = 0; npages--; /* skip the first global control page */ /* skip higher level control pages above top level covered by map */ npages -= (2 - level); npages--; /* skip top level's control page */ for (i = level; i >= 0; i--) { factor = (i == 2) ? MAXL1PAGES : ((i == 1) ? MAXL0PAGES : 1); complete = (u32) npages / factor; ndmaps += complete * ((i == 2) ? LPERCTL * LPERCTL : ((i == 1) ? LPERCTL : 1)); /* pages in last/incomplete child */ npages = (u32) npages % factor; /* skip incomplete child's level control page */ npages--; } /* convert the number of dmaps into the number of blocks * which can be covered by the dmaps; */ nblocks = ndmaps << L2BPERDMAP; return (nblocks); } |
| 12 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM task #if !defined(_TRACE_TASK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TASK_H #include <linux/tracepoint.h> TRACE_EVENT(task_newtask, TP_PROTO(struct task_struct *task, unsigned long clone_flags), TP_ARGS(task, clone_flags), TP_STRUCT__entry( __field( pid_t, pid) __array( char, comm, TASK_COMM_LEN) __field( unsigned long, clone_flags) __field( short, oom_score_adj) ), TP_fast_assign( __entry->pid = task->pid; memcpy(__entry->comm, task->comm, TASK_COMM_LEN); __entry->clone_flags = clone_flags; __entry->oom_score_adj = task->signal->oom_score_adj; ), TP_printk("pid=%d comm=%s clone_flags=%lx oom_score_adj=%hd", __entry->pid, __entry->comm, __entry->clone_flags, __entry->oom_score_adj) ); TRACE_EVENT(task_rename, TP_PROTO(struct task_struct *task, const char *comm), TP_ARGS(task, comm), TP_STRUCT__entry( __array( char, oldcomm, TASK_COMM_LEN) __array( char, newcomm, TASK_COMM_LEN) __field( short, oom_score_adj) ), TP_fast_assign( memcpy(entry->oldcomm, task->comm, TASK_COMM_LEN); strscpy(entry->newcomm, comm, TASK_COMM_LEN); __entry->oom_score_adj = task->signal->oom_score_adj; ), TP_printk("oldcomm=%s newcomm=%s oom_score_adj=%hd", __entry->oldcomm, __entry->newcomm, __entry->oom_score_adj) ); /** * task_prctl_unknown - called on unknown prctl() option * @option: option passed * @arg2: arg2 passed * @arg3: arg3 passed * @arg4: arg4 passed * @arg5: arg5 passed * * Called on an unknown prctl() option. */ TRACE_EVENT(task_prctl_unknown, TP_PROTO(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5), TP_ARGS(option, arg2, arg3, arg4, arg5), TP_STRUCT__entry( __field( int, option) __field( unsigned long, arg2) __field( unsigned long, arg3) __field( unsigned long, arg4) __field( unsigned long, arg5) ), TP_fast_assign( __entry->option = option; __entry->arg2 = arg2; __entry->arg3 = arg3; __entry->arg4 = arg4; __entry->arg5 = arg5; ), TP_printk("option=%d arg2=%ld arg3=%ld arg4=%ld arg5=%ld", __entry->option, __entry->arg2, __entry->arg3, __entry->arg4, __entry->arg5) ); #endif /* This part must be outside protection */ #include <trace/define_trace.h> |
| 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 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 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 8 8 9 8 8 1 1 1 4 4 5 4 2 3 1 3 5 3 3 3 3 4 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 11217 11218 11219 11220 11221 11222 11223 11224 11225 11226 11227 11228 11229 11230 11231 11232 11233 11234 11235 11236 11237 11238 11239 11240 11241 11242 11243 11244 11245 11246 11247 11248 11249 11250 11251 11252 11253 11254 11255 11256 11257 11258 11259 11260 11261 11262 11263 11264 11265 11266 11267 11268 11269 11270 11271 11272 11273 11274 11275 11276 11277 11278 11279 11280 11281 11282 11283 11284 11285 11286 11287 11288 11289 11290 11291 11292 11293 11294 11295 11296 11297 11298 11299 11300 11301 11302 11303 11304 11305 11306 11307 11308 11309 11310 11311 11312 11313 11314 11315 11316 11317 11318 11319 11320 11321 11322 11323 11324 11325 11326 11327 11328 11329 11330 11331 11332 11333 11334 11335 11336 11337 11338 11339 11340 11341 11342 11343 11344 11345 11346 11347 11348 11349 11350 11351 11352 11353 11354 11355 11356 11357 11358 11359 11360 11361 11362 11363 11364 11365 11366 11367 11368 11369 11370 11371 11372 11373 11374 11375 11376 11377 11378 11379 11380 11381 11382 11383 11384 11385 11386 11387 11388 11389 11390 11391 11392 11393 11394 11395 11396 11397 11398 11399 11400 11401 11402 11403 11404 11405 11406 11407 11408 11409 11410 11411 11412 11413 11414 11415 11416 11417 11418 11419 11420 11421 11422 11423 11424 11425 11426 11427 11428 11429 11430 11431 11432 11433 11434 11435 11436 11437 11438 11439 11440 11441 11442 11443 11444 11445 11446 11447 11448 11449 11450 11451 11452 11453 11454 11455 11456 11457 11458 11459 11460 11461 11462 11463 11464 11465 11466 11467 11468 11469 11470 11471 11472 11473 11474 11475 11476 11477 11478 11479 11480 11481 11482 11483 11484 11485 11486 11487 11488 11489 11490 11491 11492 11493 11494 11495 11496 11497 11498 11499 11500 11501 11502 11503 11504 11505 11506 11507 11508 11509 11510 11511 11512 11513 11514 11515 11516 11517 11518 11519 11520 11521 11522 11523 11524 11525 11526 11527 11528 11529 11530 11531 11532 11533 11534 11535 11536 11537 11538 11539 11540 11541 11542 11543 11544 11545 11546 11547 11548 11549 11550 11551 11552 11553 11554 11555 11556 11557 11558 11559 11560 11561 11562 11563 11564 11565 11566 11567 11568 11569 11570 11571 11572 11573 11574 11575 11576 11577 11578 11579 11580 11581 11582 11583 11584 11585 11586 11587 11588 11589 11590 11591 11592 11593 11594 11595 11596 11597 11598 11599 11600 11601 11602 11603 11604 11605 11606 11607 11608 11609 11610 11611 11612 11613 11614 11615 11616 11617 11618 11619 11620 11621 11622 11623 11624 11625 11626 11627 11628 11629 11630 11631 11632 11633 11634 11635 11636 11637 11638 11639 11640 11641 11642 11643 11644 11645 11646 11647 11648 11649 11650 11651 11652 11653 11654 11655 11656 11657 11658 11659 11660 11661 11662 11663 11664 11665 11666 11667 11668 11669 11670 11671 11672 11673 11674 11675 11676 11677 11678 11679 11680 11681 11682 11683 11684 11685 11686 11687 11688 11689 11690 11691 11692 11693 11694 11695 11696 11697 11698 11699 11700 11701 11702 11703 11704 11705 11706 11707 11708 11709 11710 11711 11712 11713 11714 11715 11716 11717 11718 11719 11720 11721 11722 11723 11724 11725 11726 11727 11728 11729 11730 11731 11732 11733 11734 11735 11736 11737 11738 11739 11740 11741 11742 11743 11744 11745 11746 11747 11748 11749 11750 11751 11752 11753 11754 11755 11756 11757 11758 11759 11760 11761 11762 11763 11764 11765 11766 11767 11768 11769 11770 11771 11772 11773 11774 11775 11776 11777 11778 11779 11780 11781 11782 11783 11784 11785 11786 11787 11788 11789 11790 11791 11792 11793 11794 11795 11796 11797 11798 11799 11800 11801 11802 11803 11804 11805 11806 11807 11808 11809 11810 11811 11812 11813 11814 11815 11816 11817 11818 11819 11820 11821 11822 11823 11824 11825 11826 11827 11828 11829 11830 11831 11832 11833 11834 11835 11836 11837 11838 11839 11840 11841 11842 11843 11844 11845 11846 11847 11848 11849 11850 11851 11852 11853 11854 11855 11856 11857 11858 11859 11860 11861 11862 11863 11864 11865 11866 11867 11868 11869 11870 11871 11872 11873 11874 11875 11876 11877 11878 11879 11880 11881 11882 11883 11884 11885 11886 11887 11888 11889 11890 11891 11892 11893 11894 11895 11896 11897 11898 11899 11900 11901 11902 11903 11904 11905 11906 11907 11908 11909 11910 11911 11912 11913 11914 11915 11916 11917 11918 11919 11920 11921 11922 11923 11924 11925 11926 11927 11928 11929 11930 11931 11932 11933 11934 11935 11936 11937 11938 11939 11940 11941 11942 11943 11944 11945 11946 11947 11948 11949 11950 11951 11952 11953 11954 11955 11956 11957 11958 11959 11960 11961 11962 11963 11964 11965 11966 11967 11968 11969 11970 11971 11972 11973 11974 11975 11976 11977 11978 11979 11980 11981 11982 11983 11984 11985 11986 11987 11988 11989 11990 11991 11992 11993 11994 11995 11996 11997 11998 11999 12000 12001 12002 12003 12004 12005 12006 12007 12008 12009 12010 12011 12012 12013 12014 12015 12016 12017 12018 12019 12020 12021 12022 12023 12024 12025 12026 12027 12028 12029 12030 12031 12032 12033 12034 12035 12036 12037 12038 12039 12040 12041 12042 12043 12044 12045 12046 12047 12048 12049 12050 12051 12052 12053 12054 12055 12056 12057 12058 12059 12060 12061 12062 12063 12064 12065 12066 12067 12068 12069 12070 12071 12072 12073 12074 12075 12076 12077 12078 12079 12080 12081 12082 12083 12084 12085 12086 12087 12088 12089 12090 12091 12092 12093 12094 12095 12096 12097 12098 12099 12100 12101 12102 12103 12104 12105 12106 12107 12108 12109 12110 12111 12112 12113 12114 12115 12116 12117 12118 12119 12120 12121 12122 12123 12124 12125 12126 12127 12128 12129 12130 12131 12132 12133 12134 12135 12136 12137 12138 12139 12140 12141 12142 12143 12144 12145 12146 12147 12148 12149 12150 12151 12152 12153 12154 12155 12156 12157 12158 12159 12160 12161 12162 12163 12164 12165 12166 12167 12168 12169 12170 12171 12172 12173 12174 12175 12176 12177 12178 12179 12180 12181 12182 12183 12184 12185 12186 12187 12188 12189 12190 12191 12192 12193 12194 12195 12196 12197 12198 12199 12200 12201 12202 12203 12204 12205 12206 12207 12208 12209 12210 12211 12212 12213 12214 12215 12216 12217 12218 12219 12220 12221 12222 12223 12224 12225 12226 12227 12228 12229 12230 12231 12232 12233 12234 12235 12236 12237 12238 12239 12240 12241 12242 12243 12244 12245 12246 12247 12248 12249 12250 12251 12252 12253 12254 12255 12256 12257 12258 12259 12260 12261 12262 12263 12264 12265 12266 12267 12268 12269 12270 12271 12272 12273 12274 12275 12276 12277 12278 12279 12280 12281 12282 12283 12284 12285 12286 12287 12288 12289 12290 12291 12292 12293 12294 12295 12296 12297 12298 12299 12300 12301 12302 12303 12304 12305 12306 12307 12308 12309 12310 12311 12312 12313 12314 12315 12316 12317 12318 12319 12320 12321 12322 12323 12324 12325 12326 12327 12328 12329 12330 12331 12332 12333 12334 12335 12336 12337 12338 12339 12340 12341 12342 12343 12344 12345 12346 12347 12348 12349 12350 12351 12352 12353 12354 12355 12356 12357 12358 12359 12360 12361 12362 12363 12364 12365 12366 12367 12368 12369 12370 12371 12372 12373 12374 12375 12376 12377 12378 12379 12380 12381 12382 12383 12384 12385 12386 12387 12388 12389 12390 12391 12392 12393 12394 12395 12396 12397 12398 12399 12400 12401 12402 12403 12404 12405 12406 12407 12408 12409 12410 12411 12412 12413 12414 12415 12416 12417 12418 12419 12420 12421 12422 12423 12424 12425 12426 12427 12428 12429 12430 12431 12432 12433 12434 12435 12436 12437 12438 12439 12440 12441 12442 12443 12444 12445 12446 12447 12448 12449 12450 12451 12452 12453 12454 12455 12456 12457 12458 12459 12460 12461 12462 12463 12464 12465 12466 12467 12468 12469 12470 12471 12472 12473 12474 12475 12476 12477 12478 12479 12480 12481 12482 12483 12484 12485 12486 12487 12488 12489 12490 12491 12492 12493 12494 12495 12496 12497 12498 12499 12500 12501 12502 12503 12504 12505 12506 12507 12508 12509 12510 12511 12512 12513 12514 12515 12516 12517 12518 12519 12520 12521 12522 12523 12524 12525 12526 12527 12528 12529 12530 12531 12532 12533 12534 12535 12536 12537 12538 12539 12540 12541 12542 12543 12544 12545 12546 12547 12548 12549 12550 12551 12552 12553 12554 12555 12556 12557 12558 12559 12560 12561 12562 12563 12564 12565 12566 12567 12568 12569 12570 12571 12572 12573 12574 12575 12576 12577 12578 12579 12580 12581 12582 12583 12584 12585 12586 12587 12588 12589 12590 12591 12592 12593 12594 12595 12596 12597 12598 12599 12600 12601 12602 12603 12604 12605 12606 12607 12608 12609 12610 12611 12612 12613 12614 12615 12616 12617 12618 12619 12620 12621 12622 12623 12624 12625 12626 12627 12628 12629 12630 12631 12632 12633 12634 12635 12636 12637 12638 12639 12640 12641 12642 12643 12644 12645 12646 12647 12648 12649 12650 12651 12652 12653 12654 12655 12656 12657 12658 12659 12660 12661 12662 12663 12664 12665 12666 12667 12668 12669 12670 12671 12672 12673 12674 12675 12676 12677 12678 12679 12680 12681 12682 12683 12684 12685 12686 12687 12688 12689 12690 12691 12692 12693 12694 12695 12696 12697 12698 12699 12700 12701 12702 12703 12704 12705 12706 12707 12708 12709 12710 12711 12712 12713 12714 12715 12716 12717 12718 12719 12720 12721 12722 12723 12724 12725 12726 12727 12728 12729 12730 12731 12732 12733 12734 12735 12736 12737 12738 12739 12740 12741 12742 12743 12744 12745 12746 12747 12748 12749 12750 12751 12752 12753 12754 12755 12756 12757 12758 12759 12760 12761 12762 12763 12764 12765 12766 12767 12768 12769 12770 12771 12772 12773 12774 12775 12776 12777 12778 12779 12780 12781 12782 12783 12784 12785 12786 12787 12788 12789 12790 12791 12792 12793 12794 12795 12796 12797 12798 12799 12800 12801 12802 12803 12804 12805 12806 12807 12808 12809 12810 12811 12812 12813 12814 12815 12816 12817 12818 12819 12820 12821 12822 12823 12824 12825 12826 12827 12828 12829 12830 12831 12832 12833 12834 12835 12836 12837 12838 12839 12840 12841 12842 12843 12844 12845 12846 12847 12848 12849 12850 12851 12852 12853 12854 12855 12856 12857 12858 12859 12860 12861 12862 12863 12864 12865 12866 12867 12868 12869 12870 12871 12872 12873 12874 12875 12876 12877 12878 12879 12880 12881 12882 12883 12884 12885 12886 12887 12888 12889 12890 12891 12892 12893 12894 12895 12896 12897 12898 12899 12900 12901 12902 12903 12904 12905 12906 12907 12908 12909 12910 12911 12912 12913 12914 12915 12916 12917 12918 12919 12920 12921 12922 12923 12924 12925 12926 12927 12928 12929 12930 12931 12932 12933 12934 12935 12936 12937 12938 12939 12940 12941 12942 12943 12944 12945 12946 12947 12948 12949 12950 12951 12952 12953 12954 12955 12956 12957 12958 12959 12960 12961 12962 12963 12964 12965 12966 12967 12968 12969 12970 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET3 Protocol independent device support routines. * * Derived from the non IP parts of dev.c 1.0.19 * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Mark Evans, <evansmp@uhura.aston.ac.uk> * * Additional Authors: * Florian la Roche <rzsfl@rz.uni-sb.de> * Alan Cox <gw4pts@gw4pts.ampr.org> * David Hinds <dahinds@users.sourceforge.net> * Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * Adam Sulmicki <adam@cfar.umd.edu> * Pekka Riikonen <priikone@poesidon.pspt.fi> * * Changes: * D.J. Barrow : Fixed bug where dev->refcnt gets set * to 2 if register_netdev gets called * before net_dev_init & also removed a * few lines of code in the process. * Alan Cox : device private ioctl copies fields back. * Alan Cox : Transmit queue code does relevant * stunts to keep the queue safe. * Alan Cox : Fixed double lock. * Alan Cox : Fixed promisc NULL pointer trap * ???????? : Support the full private ioctl range * Alan Cox : Moved ioctl permission check into * drivers * Tim Kordas : SIOCADDMULTI/SIOCDELMULTI * Alan Cox : 100 backlog just doesn't cut it when * you start doing multicast video 8) * Alan Cox : Rewrote net_bh and list manager. * Alan Cox : Fix ETH_P_ALL echoback lengths. * Alan Cox : Took out transmit every packet pass * Saved a few bytes in the ioctl handler * Alan Cox : Network driver sets packet type before * calling netif_rx. Saves a function * call a packet. * Alan Cox : Hashed net_bh() * Richard Kooijman: Timestamp fixes. * Alan Cox : Wrong field in SIOCGIFDSTADDR * Alan Cox : Device lock protection. * Alan Cox : Fixed nasty side effect of device close * changes. * Rudi Cilibrasi : Pass the right thing to * set_mac_address() * Dave Miller : 32bit quantity for the device lock to * make it work out on a Sparc. * Bjorn Ekwall : Added KERNELD hack. * Alan Cox : Cleaned up the backlog initialise. * Craig Metz : SIOCGIFCONF fix if space for under * 1 device. * Thomas Bogendoerfer : Return ENODEV for dev_open, if there * is no device open function. * Andi Kleen : Fix error reporting for SIOCGIFCONF * Michael Chastain : Fix signed/unsigned for SIOCGIFCONF * Cyrus Durgin : Cleaned for KMOD * Adam Sulmicki : Bug Fix : Network Device Unload * A network device unload needs to purge * the backlog queue. * Paul Rusty Russell : SIOCSIFNAME * Pekka Riikonen : Netdev boot-time settings code * Andrew Morton : Make unregister_netdevice wait * indefinitely on dev->refcnt * J Hadi Salim : - Backlog queue sampling * - netif_rx() feedback */ #include <linux/uaccess.h> #include <linux/bitmap.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/isolation.h> #include <linux/sched/mm.h> #include <linux/smpboot.h> #include <linux/mutex.h> #include <linux/rwsem.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/if_ether.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/ethtool_netlink.h> #include <linux/skbuff.h> #include <linux/kthread.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/busy_poll.h> #include <linux/rtnetlink.h> #include <linux/stat.h> #include <net/dsa.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/gro.h> #include <net/netdev_queues.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <net/checksum.h> #include <net/xfrm.h> #include <net/tcx.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netpoll.h> #include <linux/rcupdate.h> #include <linux/delay.h> #include <net/iw_handler.h> #include <asm/current.h> #include <linux/audit.h> #include <linux/dmaengine.h> #include <linux/err.h> #include <linux/ctype.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/ip.h> #include <net/ip.h> #include <net/mpls.h> #include <linux/ipv6.h> #include <linux/in.h> #include <linux/jhash.h> #include <linux/random.h> #include <trace/events/napi.h> #include <trace/events/net.h> #include <trace/events/skb.h> #include <trace/events/qdisc.h> #include <trace/events/xdp.h> #include <linux/inetdevice.h> #include <linux/cpu_rmap.h> #include <linux/static_key.h> #include <linux/hashtable.h> #include <linux/vmalloc.h> #include <linux/if_macvlan.h> #include <linux/errqueue.h> #include <linux/hrtimer.h> #include <linux/netfilter_netdev.h> #include <linux/crash_dump.h> #include <linux/sctp.h> #include <net/udp_tunnel.h> #include <linux/net_namespace.h> #include <linux/indirect_call_wrapper.h> #include <net/devlink.h> #include <linux/pm_runtime.h> #include <linux/prandom.h> #include <linux/once_lite.h> #include <net/netdev_lock.h> #include <net/netdev_rx_queue.h> #include <net/page_pool/types.h> #include <net/page_pool/helpers.h> #include <net/page_pool/memory_provider.h> #include <net/rps.h> #include <linux/phy_link_topology.h> #include "dev.h" #include "devmem.h" #include "net-sysfs.h" static DEFINE_SPINLOCK(ptype_lock); struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; static int netif_rx_internal(struct sk_buff *skb); static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack); static DEFINE_MUTEX(ifalias_mutex); /* protects napi_hash addition/deletion and napi_gen_id */ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); static inline void dev_base_seq_inc(struct net *net) { unsigned int val = net->dev_base_seq + 1; WRITE_ONCE(net->dev_base_seq, val ?: 1); } static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { unsigned int hash = full_name_hash(net, name, strnlen(name, IFNAMSIZ)); return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) { return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } #ifndef CONFIG_PREEMPT_RT static DEFINE_STATIC_KEY_FALSE(use_backlog_threads_key); static int __init setup_backlog_napi_threads(char *arg) { static_branch_enable(&use_backlog_threads_key); return 0; } early_param("thread_backlog_napi", setup_backlog_napi_threads); static bool use_backlog_threads(void) { return static_branch_unlikely(&use_backlog_threads_key); } #else static bool use_backlog_threads(void) { return true; } #endif static inline void backlog_lock_irq_save(struct softnet_data *sd, unsigned long *flags) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags); else local_irq_save(*flags); } static inline void backlog_lock_irq_disable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_lock_irq(&sd->input_pkt_queue.lock); else local_irq_disable(); } static inline void backlog_unlock_irq_restore(struct softnet_data *sd, unsigned long *flags) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags); else local_irq_restore(*flags); } static inline void backlog_unlock_irq_enable(struct softnet_data *sd) { if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads()) spin_unlock_irq(&sd->input_pkt_queue.lock); else local_irq_enable(); } static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; name_node = kmalloc(sizeof(*name_node), GFP_KERNEL); if (!name_node) return NULL; INIT_HLIST_NODE(&name_node->hlist); name_node->dev = dev; name_node->name = name; return name_node; } static struct netdev_name_node * netdev_name_node_head_alloc(struct net_device *dev) { struct netdev_name_node *name_node; name_node = netdev_name_node_alloc(dev, dev->name); if (!name_node) return NULL; INIT_LIST_HEAD(&name_node->list); return name_node; } static void netdev_name_node_free(struct netdev_name_node *name_node) { kfree(name_node); } static void netdev_name_node_add(struct net *net, struct netdev_name_node *name_node) { hlist_add_head_rcu(&name_node->hlist, dev_name_hash(net, name_node->name)); } static void netdev_name_node_del(struct netdev_name_node *name_node) { hlist_del_rcu(&name_node->hlist); } static struct netdev_name_node *netdev_name_node_lookup(struct net *net, const char *name) { struct hlist_head *head = dev_name_hash(net, name); struct netdev_name_node *name_node; hlist_for_each_entry(name_node, head, hlist) if (!strcmp(name_node->name, name)) return name_node; return NULL; } static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, const char *name) { struct hlist_head *head = dev_name_hash(net, name); struct netdev_name_node *name_node; hlist_for_each_entry_rcu(name_node, head, hlist) if (!strcmp(name_node->name, name)) return name_node; return NULL; } bool netdev_name_in_use(struct net *net, const char *name) { return netdev_name_node_lookup(net, name); } EXPORT_SYMBOL(netdev_name_in_use); int netdev_name_node_alt_create(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); name_node = netdev_name_node_lookup(net, name); if (name_node) return -EEXIST; name_node = netdev_name_node_alloc(dev, name); if (!name_node) return -ENOMEM; netdev_name_node_add(net, name_node); /* The node that holds dev->name acts as a head of per-device list. */ list_add_tail_rcu(&name_node->list, &dev->name_node->list); return 0; } static void netdev_name_node_alt_free(struct rcu_head *head) { struct netdev_name_node *name_node = container_of(head, struct netdev_name_node, rcu); kfree(name_node->name); netdev_name_node_free(name_node); } static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { netdev_name_node_del(name_node); list_del(&name_node->list); call_rcu(&name_node->rcu, netdev_name_node_alt_free); } int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; /* lookup might have found our primary name or a name belonging * to another device. */ if (name_node == dev->name_node || name_node->dev != dev) return -EINVAL; __netdev_name_node_alt_destroy(name_node); return 0; } static void netdev_name_node_alt_flush(struct net_device *dev) { struct netdev_name_node *name_node, *tmp; list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) { list_del(&name_node->list); netdev_name_node_alt_free(&name_node->rcu); } } /* Device list insertion */ static void list_netdevice(struct net_device *dev) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); netdev_for_each_altname(dev, name_node) netdev_name_node_add(net, name_node); /* We reserved the ifindex, this can't fail */ WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL)); dev_base_seq_inc(net); } /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */ static void unlist_netdevice(struct net_device *dev) { struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); xa_erase(&net->dev_by_index, dev->ifindex); netdev_for_each_altname(dev, name_node) netdev_name_node_del(name_node); /* Unlink dev from the device chain */ list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); dev_base_seq_inc(dev_net(dev)); } /* * Our notifier list */ static RAW_NOTIFIER_HEAD(netdev_chain); /* * Device drivers call our routines to queue packets here. We empty the * queue in the local softnet handler. */ DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data) = { .process_queue_bh_lock = INIT_LOCAL_LOCK(process_queue_bh_lock), }; EXPORT_PER_CPU_SYMBOL(softnet_data); /* Page_pool has a lockless array/stack to alloc/recycle pages. * PP consumers must pay attention to run APIs in the appropriate context * (e.g. NAPI context). */ DEFINE_PER_CPU(struct page_pool_bh, system_page_pool) = { .bh_lock = INIT_LOCAL_LOCK(bh_lock), }; #ifdef CONFIG_LOCKDEP /* * register_netdevice() inits txq->_xmit_lock and sets lockdep class * according to dev->type */ static const unsigned short netdev_lock_type[] = { ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; static const char *const netdev_lock_name[] = { "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; static inline unsigned short netdev_lock_pos(unsigned short dev_type) { int i; for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) if (netdev_lock_type[i] == dev_type) return i; /* the last key is used by default */ return ARRAY_SIZE(netdev_lock_type) - 1; } static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { int i; i = netdev_lock_pos(dev_type); lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], netdev_lock_name[i]); } static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { int i; i = netdev_lock_pos(dev->type); lockdep_set_class_and_name(&dev->addr_list_lock, &netdev_addr_lock_key[i], netdev_lock_name[i]); } #else static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, unsigned short dev_type) { } static inline void netdev_set_addr_lockdep_class(struct net_device *dev) { } #endif /******************************************************************************* * * Protocol management and registration routines * *******************************************************************************/ /* * Add a protocol ID to the list. Now that the input handler is * smarter we can dispense with all the messy stuff that used to be * here. * * BEWARE!!! Protocol handlers, mangling input packets, * MUST BE last in hash buckets and checking protocol handlers * MUST start from promiscuous ptype_all chain in net_bh. * It is true now, do not change it. * Explanation follows: if protocol handler, mangling packet, will * be the first on list, it is not able to sense, that packet * is cloned and should be copied-on-write, so that it will * change it and subsequent readers will get broken packet. * --ANK (980803) */ static inline struct list_head *ptype_head(const struct packet_type *pt) { if (pt->type == htons(ETH_P_ALL)) { if (!pt->af_packet_net && !pt->dev) return NULL; return pt->dev ? &pt->dev->ptype_all : &pt->af_packet_net->ptype_all; } if (pt->dev) return &pt->dev->ptype_specific; return pt->af_packet_net ? &pt->af_packet_net->ptype_specific : &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; } /** * dev_add_pack - add packet handler * @pt: packet type declaration * * Add a protocol handler to the networking stack. The passed &packet_type * is linked into kernel lists and may not be freed until it has been * removed from the kernel lists. * * This call does not sleep therefore it can not * guarantee all CPU's that are in middle of receiving packets * will see the new packet type (until the next received packet). */ void dev_add_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); if (WARN_ON_ONCE(!head)) return; spin_lock(&ptype_lock); list_add_rcu(&pt->list, head); spin_unlock(&ptype_lock); } EXPORT_SYMBOL(dev_add_pack); /** * __dev_remove_pack - remove packet handler * @pt: packet type declaration * * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function * returns. * * The packet type might still be in use by receivers * and must not be freed until after all the CPU's have gone * through a quiescent state. */ void __dev_remove_pack(struct packet_type *pt) { struct list_head *head = ptype_head(pt); struct packet_type *pt1; if (!head) return; spin_lock(&ptype_lock); list_for_each_entry(pt1, head, list) { if (pt == pt1) { list_del_rcu(&pt->list); goto out; } } pr_warn("dev_remove_pack: %p not found\n", pt); out: spin_unlock(&ptype_lock); } EXPORT_SYMBOL(__dev_remove_pack); /** * dev_remove_pack - remove packet handler * @pt: packet type declaration * * Remove a protocol handler that was previously added to the kernel * protocol handlers by dev_add_pack(). The passed &packet_type is removed * from the kernel lists and can be freed or reused once this function * returns. * * This call sleeps to guarantee that no CPU is looking at the packet * type after return. */ void dev_remove_pack(struct packet_type *pt) { __dev_remove_pack(pt); synchronize_net(); } EXPORT_SYMBOL(dev_remove_pack); /******************************************************************************* * * Device Interface Subroutines * *******************************************************************************/ /** * dev_get_iflink - get 'iflink' value of a interface * @dev: targeted interface * * Indicates the ifindex the interface is linked to. * Physical interfaces have the same 'ifindex' and 'iflink' values. */ int dev_get_iflink(const struct net_device *dev) { if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink) return dev->netdev_ops->ndo_get_iflink(dev); return READ_ONCE(dev->ifindex); } EXPORT_SYMBOL(dev_get_iflink); /** * dev_fill_metadata_dst - Retrieve tunnel egress information. * @dev: targeted interface * @skb: The packet. * * For better visibility of tunnel traffic OVS needs to retrieve * egress tunnel information for a packet. Following API allows * user to get this info. */ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info; if (!dev->netdev_ops || !dev->netdev_ops->ndo_fill_metadata_dst) return -EINVAL; info = skb_tunnel_info_unclone(skb); if (!info) return -ENOMEM; if (unlikely(!(info->mode & IP_TUNNEL_INFO_TX))) return -EINVAL; return dev->netdev_ops->ndo_fill_metadata_dst(dev, skb); } EXPORT_SYMBOL_GPL(dev_fill_metadata_dst); static struct net_device_path *dev_fwd_path(struct net_device_path_stack *stack) { int k = stack->num_paths++; if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX)) return NULL; return &stack->path[k]; } int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, struct net_device_path_stack *stack) { const struct net_device *last_dev; struct net_device_path_ctx ctx = { .dev = dev, }; struct net_device_path *path; int ret = 0; memcpy(ctx.daddr, daddr, sizeof(ctx.daddr)); stack->num_paths = 0; while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) { last_dev = ctx.dev; path = dev_fwd_path(stack); if (!path) return -1; memset(path, 0, sizeof(struct net_device_path)); ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path); if (ret < 0) return -1; if (WARN_ON_ONCE(last_dev == ctx.dev)) return -1; } if (!ctx.dev) return ret; path = dev_fwd_path(stack); if (!path) return -1; path->type = DEV_PATH_ETHERNET; path->dev = ctx.dev; return ret; } EXPORT_SYMBOL_GPL(dev_fill_forward_path); /* must be called under rcu_read_lock(), as we dont take a reference */ static struct napi_struct *napi_by_id(unsigned int napi_id) { unsigned int hash = napi_id % HASH_SIZE(napi_hash); struct napi_struct *napi; hlist_for_each_entry_rcu(napi, &napi_hash[hash], napi_hash_node) if (napi->napi_id == napi_id) return napi; return NULL; } /* must be called under rcu_read_lock(), as we dont take a reference */ static struct napi_struct * netdev_napi_by_id(struct net *net, unsigned int napi_id) { struct napi_struct *napi; napi = napi_by_id(napi_id); if (!napi) return NULL; if (WARN_ON_ONCE(!napi->dev)) return NULL; if (!net_eq(net, dev_net(napi->dev))) return NULL; return napi; } /** * netdev_napi_by_id_lock() - find a device by NAPI ID and lock it * @net: the applicable net namespace * @napi_id: ID of a NAPI of a target device * * Find a NAPI instance with @napi_id. Lock its device. * The device must be in %NETREG_REGISTERED state for lookup to succeed. * netdev_unlock() must be called to release it. * * Return: pointer to NAPI, its device with lock held, NULL if not found. */ struct napi_struct * netdev_napi_by_id_lock(struct net *net, unsigned int napi_id) { struct napi_struct *napi; struct net_device *dev; rcu_read_lock(); napi = netdev_napi_by_id(net, napi_id); if (!napi || READ_ONCE(napi->dev->reg_state) != NETREG_REGISTERED) { rcu_read_unlock(); return NULL; } dev = napi->dev; dev_hold(dev); rcu_read_unlock(); dev = __netdev_put_lock(dev, net); if (!dev) return NULL; rcu_read_lock(); napi = netdev_napi_by_id(net, napi_id); if (napi && napi->dev != dev) napi = NULL; rcu_read_unlock(); if (!napi) netdev_unlock(dev); return napi; } /** * __dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. Must be called under RTNL semaphore. * If the name is found a pointer to the device is returned. * If the name is not found then %NULL is returned. The * reference counters are not incremented so the caller must be * careful with locks. */ struct net_device *__dev_get_by_name(struct net *net, const char *name) { struct netdev_name_node *node_name; node_name = netdev_name_node_lookup(net, name); return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(__dev_get_by_name); /** * dev_get_by_name_rcu - find a device by its name * @net: the applicable net namespace * @name: name to find * * Find an interface by name. * If the name is found a pointer to the device is returned. * If the name is not found then %NULL is returned. * The reference counters are not incremented so the caller must be * careful with locks. The caller must hold RCU lock. */ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { struct netdev_name_node *node_name; node_name = netdev_name_node_lookup_rcu(net, name); return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(dev_get_by_name_rcu); /* Deprecated for new users, call netdev_get_by_name() instead */ struct net_device *dev_get_by_name(struct net *net, const char *name) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_name_rcu(net, name); dev_hold(dev); rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_name); /** * netdev_get_by_name() - find a device by its name * @net: the applicable net namespace * @name: name to find * @tracker: tracking object for the acquired reference * @gfp: allocation flags for the tracker * * Find an interface by name. This can be called from any * context and does its own locking. The returned handle has * the usage count incremented and the caller must use netdev_put() to * release it when it is no longer needed. %NULL is returned if no * matching device is found. */ struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp) { struct net_device *dev; dev = dev_get_by_name(net, name); if (dev) netdev_tracker_alloc(dev, tracker, gfp); return dev; } EXPORT_SYMBOL(netdev_get_by_name); /** * __dev_get_by_index - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful * about locking. The caller must hold the RTNL semaphore. */ struct net_device *__dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); hlist_for_each_entry(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; return NULL; } EXPORT_SYMBOL(__dev_get_by_index); /** * dev_get_by_index_rcu - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. Returns %NULL if the device * is not found or a pointer to the device. The device has not * had its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) { struct net_device *dev; struct hlist_head *head = dev_index_hash(net, ifindex); hlist_for_each_entry_rcu(dev, head, index_hlist) if (dev->ifindex == ifindex) return dev; return NULL; } EXPORT_SYMBOL(dev_get_by_index_rcu); /* Deprecated for new users, call netdev_get_by_index() instead */ struct net_device *dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); dev_hold(dev); rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_index); /** * netdev_get_by_index() - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * @tracker: tracking object for the acquired reference * @gfp: allocation flags for the tracker * * Search for an interface by index. Returns NULL if the device * is not found or a pointer to the device. The device returned has * had a reference added and the pointer is safe until the user calls * netdev_put() to indicate they have finished with it. */ struct net_device *netdev_get_by_index(struct net *net, int ifindex, netdevice_tracker *tracker, gfp_t gfp) { struct net_device *dev; dev = dev_get_by_index(net, ifindex); if (dev) netdev_tracker_alloc(dev, tracker, gfp); return dev; } EXPORT_SYMBOL(netdev_get_by_index); /** * dev_get_by_napi_id - find a device by napi_id * @napi_id: ID of the NAPI struct * * Search for an interface by NAPI ID. Returns %NULL if the device * is not found or a pointer to the device. The device has not had * its reference counter increased so the caller must be careful * about locking. The caller must hold RCU lock. */ struct net_device *dev_get_by_napi_id(unsigned int napi_id) { struct napi_struct *napi; WARN_ON_ONCE(!rcu_read_lock_held()); if (!napi_id_valid(napi_id)) return NULL; napi = napi_by_id(napi_id); return napi ? napi->dev : NULL; } /* Release the held reference on the net_device, and if the net_device * is still registered try to lock the instance lock. If device is being * unregistered NULL will be returned (but the reference has been released, * either way!) * * This helper is intended for locking net_device after it has been looked up * using a lockless lookup helper. Lock prevents the instance from going away. */ struct net_device *__netdev_put_lock(struct net_device *dev, struct net *net) { netdev_lock(dev); if (dev->reg_state > NETREG_REGISTERED || dev->moving_ns || !net_eq(dev_net(dev), net)) { netdev_unlock(dev); dev_put(dev); return NULL; } dev_put(dev); return dev; } static struct net_device * __netdev_put_lock_ops_compat(struct net_device *dev, struct net *net) { netdev_lock_ops_compat(dev); if (dev->reg_state > NETREG_REGISTERED || dev->moving_ns || !net_eq(dev_net(dev), net)) { netdev_unlock_ops_compat(dev); dev_put(dev); return NULL; } dev_put(dev); return dev; } /** * netdev_get_by_index_lock() - find a device by its ifindex * @net: the applicable net namespace * @ifindex: index of device * * Search for an interface by index. If a valid device * with @ifindex is found it will be returned with netdev->lock held. * netdev_unlock() must be called to release it. * * Return: pointer to a device with lock held, NULL if not found. */ struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex) { struct net_device *dev; dev = dev_get_by_index(net, ifindex); if (!dev) return NULL; return __netdev_put_lock(dev, net); } struct net_device * netdev_get_by_index_lock_ops_compat(struct net *net, int ifindex) { struct net_device *dev; dev = dev_get_by_index(net, ifindex); if (!dev) return NULL; return __netdev_put_lock_ops_compat(dev, net); } struct net_device * netdev_xa_find_lock(struct net *net, struct net_device *dev, unsigned long *index) { if (dev) netdev_unlock(dev); do { rcu_read_lock(); dev = xa_find(&net->dev_by_index, index, ULONG_MAX, XA_PRESENT); if (!dev) { rcu_read_unlock(); return NULL; } dev_hold(dev); rcu_read_unlock(); dev = __netdev_put_lock(dev, net); if (dev) return dev; (*index)++; } while (true); } struct net_device * netdev_xa_find_lock_ops_compat(struct net *net, struct net_device *dev, unsigned long *index) { if (dev) netdev_unlock_ops_compat(dev); do { rcu_read_lock(); dev = xa_find(&net->dev_by_index, index, ULONG_MAX, XA_PRESENT); if (!dev) { rcu_read_unlock(); return NULL; } dev_hold(dev); rcu_read_unlock(); dev = __netdev_put_lock_ops_compat(dev, net); if (dev) return dev; (*index)++; } while (true); } static DEFINE_SEQLOCK(netdev_rename_lock); void netdev_copy_name(struct net_device *dev, char *name) { unsigned int seq; do { seq = read_seqbegin(&netdev_rename_lock); strscpy(name, dev->name, IFNAMSIZ); } while (read_seqretry(&netdev_rename_lock, seq)); } /** * netdev_get_name - get a netdevice name, knowing its ifindex. * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @ifindex: the ifindex of the interface to get the name from. */ int netdev_get_name(struct net *net, char *name, int ifindex) { struct net_device *dev; int ret; rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (!dev) { ret = -ENODEV; goto out; } netdev_copy_name(dev, name); ret = 0; out: rcu_read_unlock(); return ret; } static bool dev_addr_cmp(struct net_device *dev, unsigned short type, const char *ha) { return dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len); } /** * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device * is not found or a pointer to the device. * The caller must hold RCU. * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * */ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *ha) { struct net_device *dev; for_each_netdev_rcu(net, dev) if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr_rcu); /** * dev_getbyhwaddr() - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Similar to dev_getbyhwaddr_rcu(), but the owner needs to hold * rtnl_lock. * * Context: rtnl_lock() must be held. * Return: pointer to the net_device, or NULL if not found */ struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, const char *ha) { struct net_device *dev; ASSERT_RTNL(); for_each_netdev(net, dev) if (dev_addr_cmp(dev, type, ha)) return dev; return NULL; } EXPORT_SYMBOL(dev_getbyhwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) { struct net_device *dev, *ret = NULL; rcu_read_lock(); for_each_netdev_rcu(net, dev) if (dev->type == type) { dev_hold(dev); ret = dev; break; } rcu_read_unlock(); return ret; } EXPORT_SYMBOL(dev_getfirstbyhwtype); /** * netdev_get_by_flags_rcu - find any device with given flags * @net: the applicable net namespace * @tracker: tracking object for the acquired reference * @if_flags: IFF_* values * @mask: bitmask of bits in if_flags to check * * Search for any interface with the given flags. * * Context: rcu_read_lock() must be held. * Returns: NULL if a device is not found or a pointer to the device. */ struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker, unsigned short if_flags, unsigned short mask) { struct net_device *dev; for_each_netdev_rcu(net, dev) { if (((READ_ONCE(dev->flags) ^ if_flags) & mask) == 0) { netdev_hold(dev, tracker, GFP_ATOMIC); return dev; } } return NULL; } EXPORT_IPV6_MOD(netdev_get_by_flags_rcu); /** * dev_valid_name - check if name is okay for network device * @name: name string * * Network device names need to be valid file names to * allow sysfs to work. We also disallow any kind of * whitespace. */ bool dev_valid_name(const char *name) { if (*name == '\0') return false; if (strnlen(name, IFNAMSIZ) == IFNAMSIZ) return false; if (!strcmp(name, ".") || !strcmp(name, "..")) return false; while (*name) { if (*name == '/' || *name == ':' || isspace(*name)) return false; name++; } return true; } EXPORT_SYMBOL(dev_valid_name); /** * __dev_alloc_name - allocate a name for a device * @net: network namespace to allocate the device name in * @name: name format string * @res: result name string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses * the first empty slot. The caller must hold the dev_base or rtnl lock * while allocating the name and adding the device in order to avoid * duplicates. * Limited to bits_per_byte * page size devices (ie 32K on most platforms). * Returns the number of the unit assigned or a negative errno code. */ static int __dev_alloc_name(struct net *net, const char *name, char *res) { int i = 0; const char *p; const int max_netdevices = 8*PAGE_SIZE; unsigned long *inuse; struct net_device *d; char buf[IFNAMSIZ]; /* Verify the string as this thing may have come from the user. * There must be one "%d" and no other "%" characters. */ p = strchr(name, '%'); if (!p || p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; /* Use one page as a bit array of possible slots */ inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); if (!inuse) return -ENOMEM; for_each_netdev(net, d) { struct netdev_name_node *name_node; netdev_for_each_altname(d, name_node) { if (!sscanf(name_node->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, name_node->name, IFNAMSIZ)) __set_bit(i, inuse); } if (!sscanf(d->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); if (!strncmp(buf, d->name, IFNAMSIZ)) __set_bit(i, inuse); } i = find_first_zero_bit(inuse, max_netdevices); bitmap_free(inuse); if (i == max_netdevices) return -ENFILE; /* 'res' and 'name' could overlap, use 'buf' as an intermediate buffer */ strscpy(buf, name, IFNAMSIZ); snprintf(res, IFNAMSIZ, buf, i); return i; } /* Returns negative errno or allocated unit id (see __dev_alloc_name()) */ static int dev_prep_valid_name(struct net *net, struct net_device *dev, const char *want_name, char *out_name, int dup_errno) { if (!dev_valid_name(want_name)) return -EINVAL; if (strchr(want_name, '%')) return __dev_alloc_name(net, want_name, out_name); if (netdev_name_in_use(net, want_name)) return -dup_errno; if (out_name != want_name) strscpy(out_name, want_name, IFNAMSIZ); return 0; } /** * dev_alloc_name - allocate a name for a device * @dev: device * @name: name format string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses * the first empty slot. The caller must hold the dev_base or rtnl lock * while allocating the name and adding the device in order to avoid * duplicates. * Limited to bits_per_byte * page size devices (ie 32K on most platforms). * Returns the number of the unit assigned or a negative errno code. */ int dev_alloc_name(struct net_device *dev, const char *name) { return dev_prep_valid_name(dev_net(dev), dev, name, dev->name, ENFILE); } EXPORT_SYMBOL(dev_alloc_name); static int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { int ret; ret = dev_prep_valid_name(net, dev, name, dev->name, EEXIST); return ret < 0 ? ret : 0; } int netif_change_name(struct net_device *dev, const char *newname) { struct net *net = dev_net(dev); unsigned char old_assign_type; char oldname[IFNAMSIZ]; int err = 0; int ret; ASSERT_RTNL_NET(net); if (!strncmp(newname, dev->name, IFNAMSIZ)) return 0; memcpy(oldname, dev->name, IFNAMSIZ); write_seqlock_bh(&netdev_rename_lock); err = dev_get_valid_name(net, dev, newname); write_sequnlock_bh(&netdev_rename_lock); if (err < 0) return err; if (oldname[0] && !strchr(oldname, '%')) netdev_info(dev, "renamed from %s%s\n", oldname, dev->flags & IFF_UP ? " (while UP)" : ""); old_assign_type = dev->name_assign_type; WRITE_ONCE(dev->name_assign_type, NET_NAME_RENAMED); rollback: ret = device_rename(&dev->dev, dev->name); if (ret) { write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); write_sequnlock_bh(&netdev_rename_lock); WRITE_ONCE(dev->name_assign_type, old_assign_type); return ret; } netdev_adjacent_rename_links(dev, oldname); netdev_name_node_del(dev->name_node); synchronize_net(); netdev_name_node_add(net, dev->name_node); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); ret = notifier_to_errno(ret); if (ret) { /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; write_seqlock_bh(&netdev_rename_lock); memcpy(dev->name, oldname, IFNAMSIZ); write_sequnlock_bh(&netdev_rename_lock); memcpy(oldname, newname, IFNAMSIZ); WRITE_ONCE(dev->name_assign_type, old_assign_type); old_assign_type = NET_NAME_RENAMED; goto rollback; } else { netdev_err(dev, "name change rollback failed: %d\n", ret); } } return err; } int netif_set_alias(struct net_device *dev, const char *alias, size_t len) { struct dev_ifalias *new_alias = NULL; if (len >= IFALIASZ) return -EINVAL; if (len) { new_alias = kmalloc(sizeof(*new_alias) + len + 1, GFP_KERNEL); if (!new_alias) return -ENOMEM; memcpy(new_alias->ifalias, alias, len); new_alias->ifalias[len] = 0; } mutex_lock(&ifalias_mutex); new_alias = rcu_replace_pointer(dev->ifalias, new_alias, mutex_is_locked(&ifalias_mutex)); mutex_unlock(&ifalias_mutex); if (new_alias) kfree_rcu(new_alias, rcuhead); return len; } /** * dev_get_alias - get ifalias of a device * @dev: device * @name: buffer to store name of ifalias * @len: size of buffer * * get ifalias for a device. Caller must make sure dev cannot go * away, e.g. rcu read lock or own a reference count to device. */ int dev_get_alias(const struct net_device *dev, char *name, size_t len) { const struct dev_ifalias *alias; int ret = 0; rcu_read_lock(); alias = rcu_dereference(dev->ifalias); if (alias) ret = snprintf(name, len, "%s", alias->ifalias); rcu_read_unlock(); return ret; } /** * netdev_features_change - device changes features * @dev: device to cause notification * * Called to indicate a device has changed features. */ void netdev_features_change(struct net_device *dev) { call_netdevice_notifiers(NETDEV_FEAT_CHANGE, dev); } EXPORT_SYMBOL(netdev_features_change); void netif_state_change(struct net_device *dev) { netdev_ops_assert_locked_or_invisible(dev); if (dev->flags & IFF_UP) { struct netdev_notifier_change_info change_info = { .info.dev = dev, }; call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); rtmsg_ifinfo(RTM_NEWLINK, dev, 0, GFP_KERNEL, 0, NULL); } } /** * __netdev_notify_peers - notify network peers about existence of @dev, * to be called when rtnl lock is already held. * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when * a device wants to inform the rest of the network about some sort of * reconfiguration such as a failover event or virtual machine * migration. */ void __netdev_notify_peers(struct net_device *dev) { ASSERT_RTNL(); call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev); call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev); } EXPORT_SYMBOL(__netdev_notify_peers); /** * netdev_notify_peers - notify network peers about existence of @dev * @dev: network device * * Generate traffic such that interested network peers are aware of * @dev, such as by generating a gratuitous ARP. This may be used when * a device wants to inform the rest of the network about some sort of * reconfiguration such as a failover event or virtual machine * migration. */ void netdev_notify_peers(struct net_device *dev) { rtnl_lock(); __netdev_notify_peers(dev); rtnl_unlock(); } EXPORT_SYMBOL(netdev_notify_peers); static int napi_threaded_poll(void *data); static int napi_kthread_create(struct napi_struct *n) { int err = 0; /* Create and wake up the kthread once to put it in * TASK_INTERRUPTIBLE mode to avoid the blocked task * warning and work with loadavg. */ n->thread = kthread_run(napi_threaded_poll, n, "napi/%s-%d", n->dev->name, n->napi_id); if (IS_ERR(n->thread)) { err = PTR_ERR(n->thread); pr_err("kthread_run failed with err %d\n", err); n->thread = NULL; } return err; } static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int ret; ASSERT_RTNL(); dev_addr_check(dev); if (!netif_device_present(dev)) { /* may be detached because parent is runtime-suspended */ if (dev->dev.parent) pm_runtime_resume(dev->dev.parent); if (!netif_device_present(dev)) return -ENODEV; } /* Block netpoll from trying to do any rx path servicing. * If we don't do this there is a chance ndo_poll_controller * or ndo_poll may be running while we open the device */ netpoll_poll_disable(dev); ret = call_netdevice_notifiers_extack(NETDEV_PRE_UP, dev, extack); ret = notifier_to_errno(ret); if (ret) return ret; set_bit(__LINK_STATE_START, &dev->state); netdev_ops_assert_locked(dev); if (ops->ndo_validate_addr) ret = ops->ndo_validate_addr(dev); if (!ret && ops->ndo_open) ret = ops->ndo_open(dev); netpoll_poll_enable(dev); if (ret) clear_bit(__LINK_STATE_START, &dev->state); else { netif_set_up(dev, true); dev_set_rx_mode(dev); dev_activate(dev); add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; } int netif_open(struct net_device *dev, struct netlink_ext_ack *extack) { int ret; if (dev->flags & IFF_UP) return 0; ret = __dev_open(dev, extack); if (ret < 0) return ret; rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_UP, dev); return ret; } static void __dev_close_many(struct list_head *head) { struct net_device *dev; ASSERT_RTNL(); might_sleep(); list_for_each_entry(dev, head, close_list) { /* Temporarily disable netpoll until the interface is down */ netpoll_poll_disable(dev); call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); clear_bit(__LINK_STATE_START, &dev->state); /* Synchronize to scheduled poll. We cannot touch poll list, it * can be even on different cpu. So just clear netif_running(). * * dev->stop() will invoke napi_disable() on all of it's * napi_struct instances on this device. */ smp_mb__after_atomic(); /* Commit netif_running(). */ } dev_deactivate_many(head); list_for_each_entry(dev, head, close_list) { const struct net_device_ops *ops = dev->netdev_ops; /* * Call the device specific close. This cannot fail. * Only if device is UP * * We allow it to be called even after a DETACH hot-plug * event. */ netdev_ops_assert_locked(dev); if (ops->ndo_stop) ops->ndo_stop(dev); netif_set_up(dev, false); netpoll_poll_enable(dev); } } static void __dev_close(struct net_device *dev) { LIST_HEAD(single); list_add(&dev->close_list, &single); __dev_close_many(&single); list_del(&single); } void netif_close_many(struct list_head *head, bool unlink) { struct net_device *dev, *tmp; /* Remove the devices that don't need to be closed */ list_for_each_entry_safe(dev, tmp, head, close_list) if (!(dev->flags & IFF_UP)) list_del_init(&dev->close_list); __dev_close_many(head); list_for_each_entry_safe(dev, tmp, head, close_list) { rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP | IFF_RUNNING, GFP_KERNEL, 0, NULL); call_netdevice_notifiers(NETDEV_DOWN, dev); if (unlink) list_del_init(&dev->close_list); } } EXPORT_SYMBOL_NS_GPL(netif_close_many, "NETDEV_INTERNAL"); void netif_close(struct net_device *dev) { if (dev->flags & IFF_UP) { LIST_HEAD(single); list_add(&dev->close_list, &single); netif_close_many(&single, true); list_del(&single); } } EXPORT_SYMBOL(netif_close); void netif_disable_lro(struct net_device *dev) { struct net_device *lower_dev; struct list_head *iter; dev->wanted_features &= ~NETIF_F_LRO; netdev_update_features(dev); if (unlikely(dev->features & NETIF_F_LRO)) netdev_WARN(dev, "failed to disable LRO!\n"); netdev_for_each_lower_dev(dev, lower_dev, iter) { netdev_lock_ops(lower_dev); netif_disable_lro(lower_dev); netdev_unlock_ops(lower_dev); } } EXPORT_IPV6_MOD(netif_disable_lro); /** * dev_disable_gro_hw - disable HW Generic Receive Offload on a device * @dev: device * * Disable HW Generic Receive Offload (GRO_HW) on a net device. Must be * called under RTNL. This is needed if Generic XDP is installed on * the device. */ static void dev_disable_gro_hw(struct net_device *dev) { dev->wanted_features &= ~NETIF_F_GRO_HW; netdev_update_features(dev); if (unlikely(dev->features & NETIF_F_GRO_HW)) netdev_WARN(dev, "failed to disable GRO_HW!\n"); } const char *netdev_cmd_to_name(enum netdev_cmd cmd) { #define N(val) \ case NETDEV_##val: \ return "NETDEV_" __stringify(val); switch (cmd) { N(UP) N(DOWN) N(REBOOT) N(CHANGE) N(REGISTER) N(UNREGISTER) N(CHANGEMTU) N(CHANGEADDR) N(GOING_DOWN) N(CHANGENAME) N(FEAT_CHANGE) N(BONDING_FAILOVER) N(PRE_UP) N(PRE_TYPE_CHANGE) N(POST_TYPE_CHANGE) N(POST_INIT) N(PRE_UNINIT) N(RELEASE) N(NOTIFY_PEERS) N(JOIN) N(CHANGEUPPER) N(RESEND_IGMP) N(PRECHANGEMTU) N(CHANGEINFODATA) N(BONDING_INFO) N(PRECHANGEUPPER) N(CHANGELOWERSTATE) N(UDP_TUNNEL_PUSH_INFO) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE) N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA) N(XDP_FEAT_CHANGE) } #undef N return "UNKNOWN_NETDEV_EVENT"; } EXPORT_SYMBOL_GPL(netdev_cmd_to_name); static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, struct net_device *dev) { struct netdev_notifier_info info = { .dev = dev, }; return nb->notifier_call(nb, val, &info); } static int call_netdevice_register_notifiers(struct notifier_block *nb, struct net_device *dev) { int err; err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); err = notifier_to_errno(err); if (err) return err; if (!(dev->flags & IFF_UP)) return 0; call_netdevice_notifier(nb, NETDEV_UP, dev); return 0; } static void call_netdevice_unregister_notifiers(struct notifier_block *nb, struct net_device *dev) { if (dev->flags & IFF_UP) { call_netdevice_notifier(nb, NETDEV_GOING_DOWN, dev); call_netdevice_notifier(nb, NETDEV_DOWN, dev); } call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); } static int call_netdevice_register_net_notifiers(struct notifier_block *nb, struct net *net) { struct net_device *dev; int err; for_each_netdev(net, dev) { netdev_lock_ops(dev); err = call_netdevice_register_notifiers(nb, dev); netdev_unlock_ops(dev); if (err) goto rollback; } return 0; rollback: for_each_netdev_continue_reverse(net, dev) call_netdevice_unregister_notifiers(nb, dev); return err; } static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb, struct net *net) { struct net_device *dev; for_each_netdev(net, dev) call_netdevice_unregister_notifiers(nb, dev); } static int dev_boot_phase = 1; /** * register_netdevice_notifier - register a network notifier block * @nb: notifier * * Register a notifier to be called when network device events occur. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. * * When registered all registration and up events are replayed * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier(struct notifier_block *nb) { struct net *net; int err; /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); /* When RTNL is removed, we need protection for netdev_chain. */ rtnl_lock(); err = raw_notifier_chain_register(&netdev_chain, nb); if (err) goto unlock; if (dev_boot_phase) goto unlock; for_each_net(net) { __rtnl_net_lock(net); err = call_netdevice_register_net_notifiers(nb, net); __rtnl_net_unlock(net); if (err) goto rollback; } unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; rollback: for_each_net_continue_reverse(net) { __rtnl_net_lock(net); call_netdevice_unregister_net_notifiers(nb, net); __rtnl_net_unlock(net); } raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } EXPORT_SYMBOL(register_netdevice_notifier); /** * unregister_netdevice_notifier - unregister a network notifier block * @nb: notifier * * Unregister a notifier previously registered by * register_netdevice_notifier(). The notifier is unlinked into the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * * After unregistering unregister and down device events are synthesized * for all devices on the device list to the removed notifier to remove * the need for special case cleanup code. */ int unregister_netdevice_notifier(struct notifier_block *nb) { struct net *net; int err; /* Close race with setup_net() and cleanup_net() */ down_write(&pernet_ops_rwsem); rtnl_lock(); err = raw_notifier_chain_unregister(&netdev_chain, nb); if (err) goto unlock; for_each_net(net) { __rtnl_net_lock(net); call_netdevice_unregister_net_notifiers(nb, net); __rtnl_net_unlock(net); } unlock: rtnl_unlock(); up_write(&pernet_ops_rwsem); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier); static int __register_netdevice_notifier_net(struct net *net, struct notifier_block *nb, bool ignore_call_fail) { int err; err = raw_notifier_chain_register(&net->netdev_chain, nb); if (err) return err; if (dev_boot_phase) return 0; err = call_netdevice_register_net_notifiers(nb, net); if (err && !ignore_call_fail) goto chain_unregister; return 0; chain_unregister: raw_notifier_chain_unregister(&net->netdev_chain, nb); return err; } static int __unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; err = raw_notifier_chain_unregister(&net->netdev_chain, nb); if (err) return err; call_netdevice_unregister_net_notifiers(nb, net); return 0; } /** * register_netdevice_notifier_net - register a per-netns network notifier block * @net: network namespace * @nb: notifier * * Register a notifier to be called when network device events occur. * The notifier passed is linked into the kernel structures and must * not be reused until it has been unregistered. A negative errno code * is returned on a failure. * * When registered all registration and up events are replayed * to the new notifier to allow device to have a race free * view of the network device list. */ int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; rtnl_net_lock(net); err = __register_netdevice_notifier_net(net, nb, false); rtnl_net_unlock(net); return err; } EXPORT_SYMBOL(register_netdevice_notifier_net); /** * unregister_netdevice_notifier_net - unregister a per-netns * network notifier block * @net: network namespace * @nb: notifier * * Unregister a notifier previously registered by * register_netdevice_notifier_net(). The notifier is unlinked from the * kernel structures and may then be reused. A negative errno code * is returned on a failure. * * After unregistering unregister and down device events are synthesized * for all devices on the device list to the removed notifier to remove * the need for special case cleanup code. */ int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb) { int err; rtnl_net_lock(net); err = __unregister_netdevice_notifier_net(net, nb); rtnl_net_unlock(net); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_net); static void __move_netdevice_notifier_net(struct net *src_net, struct net *dst_net, struct notifier_block *nb) { __unregister_netdevice_notifier_net(src_net, nb); __register_netdevice_notifier_net(dst_net, nb, true); } static void rtnl_net_dev_lock(struct net_device *dev) { bool again; do { struct net *net; again = false; /* netns might be being dismantled. */ rcu_read_lock(); net = dev_net_rcu(dev); net_passive_inc(net); rcu_read_unlock(); rtnl_net_lock(net); #ifdef CONFIG_NET_NS /* dev might have been moved to another netns. */ if (!net_eq(net, rcu_access_pointer(dev->nd_net.net))) { rtnl_net_unlock(net); net_passive_dec(net); again = true; } #endif } while (again); } static void rtnl_net_dev_unlock(struct net_device *dev) { struct net *net = dev_net(dev); rtnl_net_unlock(net); net_passive_dec(net); } int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_net_dev_lock(dev); err = __register_netdevice_notifier_net(dev_net(dev), nb, false); if (!err) { nn->nb = nb; list_add(&nn->list, &dev->net_notifier_list); } rtnl_net_dev_unlock(dev); return err; } EXPORT_SYMBOL(register_netdevice_notifier_dev_net); int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn) { int err; rtnl_net_dev_lock(dev); list_del(&nn->list); err = __unregister_netdevice_notifier_net(dev_net(dev), nb); rtnl_net_dev_unlock(dev); return err; } EXPORT_SYMBOL(unregister_netdevice_notifier_dev_net); static void move_netdevice_notifiers_dev_net(struct net_device *dev, struct net *net) { struct netdev_net_notifier *nn; list_for_each_entry(nn, &dev->net_notifier_list, list) __move_netdevice_notifier_net(dev_net(dev), net, nn->nb); } /** * call_netdevice_notifiers_info - call all network notifier blocks * @val: value passed unmodified to notifier function * @info: notifier information data * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info) { struct net *net = dev_net(info->dev); int ret; ASSERT_RTNL(); /* Run per-netns notifier block chain first, then run the global one. * Hopefully, one day, the global one is going to be removed after * all notifier block registrators get converted to be per-netns. */ ret = raw_notifier_call_chain(&net->netdev_chain, val, info); if (ret & NOTIFY_STOP_MASK) return ret; return raw_notifier_call_chain(&netdev_chain, val, info); } /** * call_netdevice_notifiers_info_robust - call per-netns notifier blocks * for and rollback on error * @val_up: value passed unmodified to notifier function * @val_down: value passed unmodified to the notifier function when * recovering from an error on @val_up * @info: notifier information data * * Call all per-netns network notifier blocks, but not notifier blocks on * the global notifier chain. Parameters and return value are as for * raw_notifier_call_chain_robust(). */ static int call_netdevice_notifiers_info_robust(unsigned long val_up, unsigned long val_down, struct netdev_notifier_info *info) { struct net *net = dev_net(info->dev); ASSERT_RTNL(); return raw_notifier_call_chain_robust(&net->netdev_chain, val_up, val_down, info); } static int call_netdevice_notifiers_extack(unsigned long val, struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_notifier_info info = { .dev = dev, .extack = extack, }; return call_netdevice_notifiers_info(val, &info); } /** * call_netdevice_notifiers - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) { return call_netdevice_notifiers_extack(val, dev, NULL); } EXPORT_SYMBOL(call_netdevice_notifiers); /** * call_netdevice_notifiers_mtu - call all network notifier blocks * @val: value passed unmodified to notifier function * @dev: net_device pointer passed unmodified to notifier function * @arg: additional u32 argument passed to the notifier function * * Call all network notifier blocks. Parameters and return value * are as for raw_notifier_call_chain(). */ static int call_netdevice_notifiers_mtu(unsigned long val, struct net_device *dev, u32 arg) { struct netdev_notifier_info_ext info = { .info.dev = dev, .ext.mtu = arg, }; BUILD_BUG_ON(offsetof(struct netdev_notifier_info_ext, info) != 0); return call_netdevice_notifiers_info(val, &info.info); } #ifdef CONFIG_NET_INGRESS static DEFINE_STATIC_KEY_FALSE(ingress_needed_key); void net_inc_ingress_queue(void) { static_branch_inc(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_ingress_queue); void net_dec_ingress_queue(void) { static_branch_dec(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_ingress_queue); #endif #ifdef CONFIG_NET_EGRESS static DEFINE_STATIC_KEY_FALSE(egress_needed_key); void net_inc_egress_queue(void) { static_branch_inc(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_egress_queue); void net_dec_egress_queue(void) { static_branch_dec(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif #ifdef CONFIG_NET_CLS_ACT DEFINE_STATIC_KEY_FALSE(tcf_sw_enabled_key); EXPORT_SYMBOL(tcf_sw_enabled_key); #endif DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); EXPORT_SYMBOL(netstamp_needed_key); #ifdef CONFIG_JUMP_LABEL static atomic_t netstamp_needed_deferred; static atomic_t netstamp_wanted; static void netstamp_clear(struct work_struct *work) { int deferred = atomic_xchg(&netstamp_needed_deferred, 0); int wanted; wanted = atomic_add_return(deferred, &netstamp_wanted); if (wanted > 0) static_branch_enable(&netstamp_needed_key); else static_branch_disable(&netstamp_needed_key); } static DECLARE_WORK(netstamp_work, netstamp_clear); #endif void net_enable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL int wanted = atomic_read(&netstamp_wanted); while (wanted > 0) { if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted + 1)) return; } atomic_inc(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_branch_inc(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_enable_timestamp); void net_disable_timestamp(void) { #ifdef CONFIG_JUMP_LABEL int wanted = atomic_read(&netstamp_wanted); while (wanted > 1) { if (atomic_try_cmpxchg(&netstamp_wanted, &wanted, wanted - 1)) return; } atomic_dec(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else static_branch_dec(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; skb->tstamp_type = SKB_CLOCK_REALTIME; if (static_branch_unlikely(&netstamp_needed_key)) skb->tstamp = ktime_get_real(); } #define net_timestamp_check(COND, SKB) \ if (static_branch_unlikely(&netstamp_needed_key)) { \ if ((COND) && !(SKB)->tstamp) \ (SKB)->tstamp = ktime_get_real(); \ } \ bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) { return __is_skb_forwardable(dev, skb, true); } EXPORT_SYMBOL_GPL(is_skb_forwardable); static int __dev_forward_skb2(struct net_device *dev, struct sk_buff *skb, bool check_mtu) { int ret = ____dev_forward_skb(dev, skb, check_mtu); if (likely(!ret)) { skb->protocol = eth_type_trans(skb, dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } return ret; } int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb2(dev, skb, true); } EXPORT_SYMBOL_GPL(__dev_forward_skb); /** * dev_forward_skb - loopback an skb to another netif * * @dev: destination network device * @skb: buffer to forward * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped, but freed) * * dev_forward_skb can be used for injecting an skb from the * start_xmit function of one device into the receive queue * of another device. * * The receiving device may be in another namespace, so * we have to clear all information in the skb that could * impact namespace isolation. */ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb) { return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb); } static inline int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) return -ENOMEM; refcount_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } static inline void deliver_ptype_list_skb(struct sk_buff *skb, struct packet_type **pt, struct net_device *orig_dev, __be16 type, struct list_head *ptype_list) { struct packet_type *ptype, *pt_prev = *pt; list_for_each_entry_rcu(ptype, ptype_list, list) { if (ptype->type != type) continue; if (pt_prev) deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } *pt = pt_prev; } static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb) { if (!ptype->af_packet_priv || !skb->sk) return false; if (ptype->id_match) return ptype->id_match(ptype, skb->sk); else if ((struct sock *)ptype->af_packet_priv == skb->sk) return true; return false; } /** * dev_nit_active_rcu - return true if any network interface taps are in use * * The caller must hold the RCU lock * * @dev: network device to check for the presence of taps */ bool dev_nit_active_rcu(const struct net_device *dev) { /* Callers may hold either RCU or RCU BH lock */ WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); return !list_empty(&dev_net(dev)->ptype_all) || !list_empty(&dev->ptype_all); } EXPORT_SYMBOL_GPL(dev_nit_active_rcu); /* * Support routine. Sends outgoing frames to any network * taps currently in use. */ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct packet_type *ptype, *pt_prev = NULL; struct list_head *ptype_list; struct sk_buff *skb2 = NULL; rcu_read_lock(); ptype_list = &dev_net_rcu(dev)->ptype_all; again: list_for_each_entry_rcu(ptype, ptype_list, list) { if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket * they originated from - MvS (miquels@drinkel.ow.org) */ if (skb_loop_sk(ptype, skb)) continue; if (pt_prev) { deliver_skb(skb2, pt_prev, skb->dev); pt_prev = ptype; continue; } /* need to clone skb, done only once */ skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) goto out_unlock; net_timestamp_set(skb2); /* skb->nh should be correctly * set by sender, so that the second statement is * just protection against buggy protocols. */ skb_reset_mac_header(skb2); if (skb_network_header(skb2) < skb2->data || skb_network_header(skb2) > skb_tail_pointer(skb2)) { net_crit_ratelimited("protocol %04x is buggy, dev %s\n", ntohs(skb2->protocol), dev->name); skb_reset_network_header(skb2); } skb2->transport_header = skb2->network_header; skb2->pkt_type = PACKET_OUTGOING; pt_prev = ptype; } if (ptype_list != &dev->ptype_all) { ptype_list = &dev->ptype_all; goto again; } out_unlock: if (pt_prev) { if (!skb_orphan_frags_rx(skb2, GFP_ATOMIC)) pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); else kfree_skb(skb2); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(dev_queue_xmit_nit); /** * netif_setup_tc - Handle tc mappings on real_num_tx_queues change * @dev: Network device * @txq: number of queues available * * If real_num_tx_queues is changed the tc mappings may no longer be * valid. To resolve this verify the tc mapping remains valid and if * not NULL the mapping. With no priorities mapping to this * offset/count pair it will no longer be used. In the worst case TC0 * is invalid nothing can be done so disable priority mappings. If is * expected that drivers will fix this mapping if they can before * calling netif_set_real_num_tx_queues. */ static void netif_setup_tc(struct net_device *dev, unsigned int txq) { int i; struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; /* If TC0 is invalidated disable TC mapping */ if (tc->offset + tc->count > txq) { netdev_warn(dev, "Number of in use tx queues changed invalidating tc mappings. Priority traffic classification disabled!\n"); dev->num_tc = 0; return; } /* Invalidated prio to tc mappings set to TC0 */ for (i = 1; i < TC_BITMASK + 1; i++) { int q = netdev_get_prio_tc_map(dev, i); tc = &dev->tc_to_txq[q]; if (tc->offset + tc->count > txq) { netdev_warn(dev, "Number of in use tx queues changed. Priority %i to tc mapping %i is no longer valid. Setting map to 0\n", i, q); netdev_set_prio_tc_map(dev, i, 0); } } } int netdev_txq_to_tc(struct net_device *dev, unsigned int txq) { if (dev->num_tc) { struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; int i; /* walk through the TCs and see if it falls into any of them */ for (i = 0; i < TC_MAX_QUEUE; i++, tc++) { if ((txq - tc->offset) < tc->count) return i; } /* didn't find it, just return -1 to indicate no match */ return -1; } return 0; } EXPORT_SYMBOL(netdev_txq_to_tc); #ifdef CONFIG_XPS static struct static_key xps_needed __read_mostly; static struct static_key xps_rxqs_needed __read_mostly; static DEFINE_MUTEX(xps_map_mutex); #define xmap_dereference(P) \ rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) static bool remove_xps_queue(struct xps_dev_maps *dev_maps, struct xps_dev_maps *old_maps, int tci, u16 index) { struct xps_map *map = NULL; int pos; map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) return false; for (pos = map->len; pos--;) { if (map->queues[pos] != index) continue; if (map->len > 1) { map->queues[pos] = map->queues[--map->len]; break; } if (old_maps) RCU_INIT_POINTER(old_maps->attr_map[tci], NULL); RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); return false; } return true; } static bool remove_xps_queue_cpu(struct net_device *dev, struct xps_dev_maps *dev_maps, int cpu, u16 offset, u16 count) { int num_tc = dev_maps->num_tc; bool active = false; int tci; for (tci = cpu * num_tc; num_tc--; tci++) { int i, j; for (i = count, j = offset; i--; j++) { if (!remove_xps_queue(dev_maps, NULL, tci, j)) break; } active |= i < 0; } return active; } static void reset_xps_maps(struct net_device *dev, struct xps_dev_maps *dev_maps, enum xps_map_type type) { static_key_slow_dec_cpuslocked(&xps_needed); if (type == XPS_RXQS) static_key_slow_dec_cpuslocked(&xps_rxqs_needed); RCU_INIT_POINTER(dev->xps_maps[type], NULL); kfree_rcu(dev_maps, rcu); } static void clean_xps_maps(struct net_device *dev, enum xps_map_type type, u16 offset, u16 count) { struct xps_dev_maps *dev_maps; bool active = false; int i, j; dev_maps = xmap_dereference(dev->xps_maps[type]); if (!dev_maps) return; for (j = 0; j < dev_maps->nr_ids; j++) active |= remove_xps_queue_cpu(dev, dev_maps, j, offset, count); if (!active) reset_xps_maps(dev, dev_maps, type); if (type == XPS_CPUS) { for (i = offset + (count - 1); count--; i--) netdev_queue_numa_node_write( netdev_get_tx_queue(dev, i), NUMA_NO_NODE); } } static void netif_reset_xps_queues(struct net_device *dev, u16 offset, u16 count) { if (!static_key_false(&xps_needed)) return; cpus_read_lock(); mutex_lock(&xps_map_mutex); if (static_key_false(&xps_rxqs_needed)) clean_xps_maps(dev, XPS_RXQS, offset, count); clean_xps_maps(dev, XPS_CPUS, offset, count); mutex_unlock(&xps_map_mutex); cpus_read_unlock(); } static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index) { netif_reset_xps_queues(dev, index, dev->num_tx_queues - index); } static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index, u16 index, bool is_rxqs_map) { struct xps_map *new_map; int alloc_len = XPS_MIN_MAP_ALLOC; int i, pos; for (pos = 0; map && pos < map->len; pos++) { if (map->queues[pos] != index) continue; return map; } /* Need to add tx-queue to this CPU's/rx-queue's existing map */ if (map) { if (pos < map->alloc_len) return map; alloc_len = map->alloc_len * 2; } /* Need to allocate new map to store tx-queue on this CPU's/rx-queue's * map */ if (is_rxqs_map) new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL); else new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL, cpu_to_node(attr_index)); if (!new_map) return NULL; for (i = 0; i < pos; i++) new_map->queues[i] = map->queues[i]; new_map->alloc_len = alloc_len; new_map->len = pos; return new_map; } /* Copy xps maps at a given index */ static void xps_copy_dev_maps(struct xps_dev_maps *dev_maps, struct xps_dev_maps *new_dev_maps, int index, int tc, bool skip_tc) { int i, tci = index * dev_maps->num_tc; struct xps_map *map; /* copy maps belonging to foreign traffic classes */ for (i = 0; i < dev_maps->num_tc; i++, tci++) { if (i == tc && skip_tc) continue; /* fill in the new device map from the old device map */ map = xmap_dereference(dev_maps->attr_map[tci]); RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } } /* Must be called under cpus_read_lock */ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, enum xps_map_type type) { struct xps_dev_maps *dev_maps, *new_dev_maps = NULL, *old_dev_maps = NULL; const unsigned long *online_mask = NULL; bool active = false, copy = false; int i, j, tci, numa_node_id = -2; int maps_sz, num_tc = 1, tc = 0; struct xps_map *map, *new_map; unsigned int nr_ids; WARN_ON_ONCE(index >= dev->num_tx_queues); if (dev->num_tc) { /* Do not allow XPS on subordinate device directly */ num_tc = dev->num_tc; if (num_tc < 0) return -EINVAL; /* If queue belongs to subordinate dev use its map */ dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev; tc = netdev_txq_to_tc(dev, index); if (tc < 0) return -EINVAL; } mutex_lock(&xps_map_mutex); dev_maps = xmap_dereference(dev->xps_maps[type]); if (type == XPS_RXQS) { maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues); nr_ids = dev->num_rx_queues; } else { maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc); if (num_possible_cpus() > 1) online_mask = cpumask_bits(cpu_online_mask); nr_ids = nr_cpu_ids; } if (maps_sz < L1_CACHE_BYTES) maps_sz = L1_CACHE_BYTES; /* The old dev_maps could be larger or smaller than the one we're * setting up now, as dev->num_tc or nr_ids could have been updated in * between. We could try to be smart, but let's be safe instead and only * copy foreign traffic classes if the two map sizes match. */ if (dev_maps && dev_maps->num_tc == num_tc && dev_maps->nr_ids == nr_ids) copy = true; /* allocate memory for queue storage */ for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids), j < nr_ids;) { if (!new_dev_maps) { new_dev_maps = kzalloc(maps_sz, GFP_KERNEL); if (!new_dev_maps) { mutex_unlock(&xps_map_mutex); return -ENOMEM; } new_dev_maps->nr_ids = nr_ids; new_dev_maps->num_tc = num_tc; } tci = j * num_tc + tc; map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; map = expand_xps_map(map, j, index, type == XPS_RXQS); if (!map) goto error; RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map); } if (!new_dev_maps) goto out_no_new_maps; if (!dev_maps) { /* Increment static keys at most once per type */ static_key_slow_inc_cpuslocked(&xps_needed); if (type == XPS_RXQS) static_key_slow_inc_cpuslocked(&xps_rxqs_needed); } for (j = 0; j < nr_ids; j++) { bool skip_tc = false; tci = j * num_tc + tc; if (netif_attr_test_mask(j, mask, nr_ids) && netif_attr_test_online(j, online_mask, nr_ids)) { /* add tx-queue to CPU/rx-queue maps */ int pos = 0; skip_tc = true; map = xmap_dereference(new_dev_maps->attr_map[tci]); while ((pos < map->len) && (map->queues[pos] != index)) pos++; if (pos == map->len) map->queues[map->len++] = index; #ifdef CONFIG_NUMA if (type == XPS_CPUS) { if (numa_node_id == -2) numa_node_id = cpu_to_node(j); else if (numa_node_id != cpu_to_node(j)) numa_node_id = -1; } #endif } if (copy) xps_copy_dev_maps(dev_maps, new_dev_maps, j, tc, skip_tc); } rcu_assign_pointer(dev->xps_maps[type], new_dev_maps); /* Cleanup old maps */ if (!dev_maps) goto out_no_old_maps; for (j = 0; j < dev_maps->nr_ids; j++) { for (i = num_tc, tci = j * dev_maps->num_tc; i--; tci++) { map = xmap_dereference(dev_maps->attr_map[tci]); if (!map) continue; if (copy) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); if (map == new_map) continue; } RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL); kfree_rcu(map, rcu); } } old_dev_maps = dev_maps; out_no_old_maps: dev_maps = new_dev_maps; active = true; out_no_new_maps: if (type == XPS_CPUS) /* update Tx queue numa node */ netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index), (numa_node_id >= 0) ? numa_node_id : NUMA_NO_NODE); if (!dev_maps) goto out_no_maps; /* removes tx-queue from unused CPUs/rx-queues */ for (j = 0; j < dev_maps->nr_ids; j++) { tci = j * dev_maps->num_tc; for (i = 0; i < dev_maps->num_tc; i++, tci++) { if (i == tc && netif_attr_test_mask(j, mask, dev_maps->nr_ids) && netif_attr_test_online(j, online_mask, dev_maps->nr_ids)) continue; active |= remove_xps_queue(dev_maps, copy ? old_dev_maps : NULL, tci, index); } } if (old_dev_maps) kfree_rcu(old_dev_maps, rcu); /* free map if not active */ if (!active) reset_xps_maps(dev, dev_maps, type); out_no_maps: mutex_unlock(&xps_map_mutex); return 0; error: /* remove any maps that we added */ for (j = 0; j < nr_ids; j++) { for (i = num_tc, tci = j * num_tc; i--; tci++) { new_map = xmap_dereference(new_dev_maps->attr_map[tci]); map = copy ? xmap_dereference(dev_maps->attr_map[tci]) : NULL; if (new_map && new_map != map) kfree(new_map); } } mutex_unlock(&xps_map_mutex); kfree(new_dev_maps); return -ENOMEM; } EXPORT_SYMBOL_GPL(__netif_set_xps_queue); int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index) { int ret; cpus_read_lock(); ret = __netif_set_xps_queue(dev, cpumask_bits(mask), index, XPS_CPUS); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(netif_set_xps_queue); #endif static void netdev_unbind_all_sb_channels(struct net_device *dev) { struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; /* Unbind any subordinate channels */ while (txq-- != &dev->_tx[0]) { if (txq->sb_dev) netdev_unbind_sb_channel(dev, txq->sb_dev); } } void netdev_reset_tc(struct net_device *dev) { #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif netdev_unbind_all_sb_channels(dev); /* Reset TC configuration of device */ dev->num_tc = 0; memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); } EXPORT_SYMBOL(netdev_reset_tc); int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) { if (tc >= dev->num_tc) return -EINVAL; #ifdef CONFIG_XPS netif_reset_xps_queues(dev, offset, count); #endif dev->tc_to_txq[tc].count = count; dev->tc_to_txq[tc].offset = offset; return 0; } EXPORT_SYMBOL(netdev_set_tc_queue); int netdev_set_num_tc(struct net_device *dev, u8 num_tc) { if (num_tc > TC_MAX_QUEUE) return -EINVAL; #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, 0); #endif netdev_unbind_all_sb_channels(dev); dev->num_tc = num_tc; return 0; } EXPORT_SYMBOL(netdev_set_num_tc); void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev) { struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues]; #ifdef CONFIG_XPS netif_reset_xps_queues_gt(sb_dev, 0); #endif memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq)); memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map)); while (txq-- != &dev->_tx[0]) { if (txq->sb_dev == sb_dev) txq->sb_dev = NULL; } } EXPORT_SYMBOL(netdev_unbind_sb_channel); int netdev_bind_sb_channel_queue(struct net_device *dev, struct net_device *sb_dev, u8 tc, u16 count, u16 offset) { /* Make certain the sb_dev and dev are already configured */ if (sb_dev->num_tc >= 0 || tc >= dev->num_tc) return -EINVAL; /* We cannot hand out queues we don't have */ if ((offset + count) > dev->real_num_tx_queues) return -EINVAL; /* Record the mapping */ sb_dev->tc_to_txq[tc].count = count; sb_dev->tc_to_txq[tc].offset = offset; /* Provide a way for Tx queue to find the tc_to_txq map or * XPS map for itself. */ while (count--) netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev; return 0; } EXPORT_SYMBOL(netdev_bind_sb_channel_queue); int netdev_set_sb_channel(struct net_device *dev, u16 channel) { /* Do not use a multiqueue device to represent a subordinate channel */ if (netif_is_multiqueue(dev)) return -ENODEV; /* We allow channels 1 - 32767 to be used for subordinate channels. * Channel 0 is meant to be "native" mode and used only to represent * the main root device. We allow writing 0 to reset the device back * to normal mode after being used as a subordinate channel. */ if (channel > S16_MAX) return -EINVAL; dev->num_tc = -channel; return 0; } EXPORT_SYMBOL(netdev_set_sb_channel); /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater than real_num_tx_queues stale skbs on the qdisc must be flushed. */ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { bool disabling; int rc; disabling = txq < dev->real_num_tx_queues; if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED || dev->reg_state == NETREG_UNREGISTERING) { netdev_ops_assert_locked(dev); rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, txq); if (rc) return rc; if (dev->num_tc) netif_setup_tc(dev, txq); net_shaper_set_real_num_tx_queues(dev, txq); dev_qdisc_change_real_num_tx(dev, txq); dev->real_num_tx_queues = txq; if (disabling) { synchronize_net(); qdisc_reset_all_tx_gt(dev, txq); #ifdef CONFIG_XPS netif_reset_xps_queues_gt(dev, txq); #endif } } else { dev->real_num_tx_queues = txq; } return 0; } EXPORT_SYMBOL(netif_set_real_num_tx_queues); /** * netif_set_real_num_rx_queues - set actual number of RX queues used * @dev: Network device * @rxq: Actual number of RX queues * * This must be called either with the rtnl_lock held or before * registration of the net device. Returns 0 on success, or a * negative error code. If called before registration, it always * succeeds. */ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) { int rc; if (rxq < 1 || rxq > dev->num_rx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED) { netdev_ops_assert_locked(dev); rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, rxq); if (rc) return rc; } dev->real_num_rx_queues = rxq; return 0; } EXPORT_SYMBOL(netif_set_real_num_rx_queues); /** * netif_set_real_num_queues - set actual number of RX and TX queues used * @dev: Network device * @txq: Actual number of TX queues * @rxq: Actual number of RX queues * * Set the real number of both TX and RX queues. * Does nothing if the number of queues is already correct. */ int netif_set_real_num_queues(struct net_device *dev, unsigned int txq, unsigned int rxq) { unsigned int old_rxq = dev->real_num_rx_queues; int err; if (txq < 1 || txq > dev->num_tx_queues || rxq < 1 || rxq > dev->num_rx_queues) return -EINVAL; /* Start from increases, so the error path only does decreases - * decreases can't fail. */ if (rxq > dev->real_num_rx_queues) { err = netif_set_real_num_rx_queues(dev, rxq); if (err) return err; } if (txq > dev->real_num_tx_queues) { err = netif_set_real_num_tx_queues(dev, txq); if (err) goto undo_rx; } if (rxq < dev->real_num_rx_queues) WARN_ON(netif_set_real_num_rx_queues(dev, rxq)); if (txq < dev->real_num_tx_queues) WARN_ON(netif_set_real_num_tx_queues(dev, txq)); return 0; undo_rx: WARN_ON(netif_set_real_num_rx_queues(dev, old_rxq)); return err; } EXPORT_SYMBOL(netif_set_real_num_queues); /** * netif_set_tso_max_size() - set the max size of TSO frames supported * @dev: netdev to update * @size: max skb->len of a TSO frame * * Set the limit on the size of TSO super-frames the device can handle. * Unless explicitly set the stack will assume the value of * %GSO_LEGACY_MAX_SIZE. */ void netif_set_tso_max_size(struct net_device *dev, unsigned int size) { dev->tso_max_size = min(GSO_MAX_SIZE, size); if (size < READ_ONCE(dev->gso_max_size)) netif_set_gso_max_size(dev, size); if (size < READ_ONCE(dev->gso_ipv4_max_size)) netif_set_gso_ipv4_max_size(dev, size); } EXPORT_SYMBOL(netif_set_tso_max_size); /** * netif_set_tso_max_segs() - set the max number of segs supported for TSO * @dev: netdev to update * @segs: max number of TCP segments * * Set the limit on the number of TCP segments the device can generate from * a single TSO super-frame. * Unless explicitly set the stack will assume the value of %GSO_MAX_SEGS. */ void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs) { dev->tso_max_segs = segs; if (segs < READ_ONCE(dev->gso_max_segs)) netif_set_gso_max_segs(dev, segs); } EXPORT_SYMBOL(netif_set_tso_max_segs); /** * netif_inherit_tso_max() - copy all TSO limits from a lower device to an upper * @to: netdev to update * @from: netdev from which to copy the limits */ void netif_inherit_tso_max(struct net_device *to, const struct net_device *from) { netif_set_tso_max_size(to, from->tso_max_size); netif_set_tso_max_segs(to, from->tso_max_segs); } EXPORT_SYMBOL(netif_inherit_tso_max); /** * netif_get_num_default_rss_queues - default number of RSS queues * * Default value is the number of physical cores if there are only 1 or 2, or * divided by 2 if there are more. */ int netif_get_num_default_rss_queues(void) { cpumask_var_t cpus; int cpu, count = 0; if (unlikely(is_kdump_kernel() || !zalloc_cpumask_var(&cpus, GFP_KERNEL))) return 1; cpumask_copy(cpus, cpu_online_mask); for_each_cpu(cpu, cpus) { ++count; cpumask_andnot(cpus, cpus, topology_sibling_cpumask(cpu)); } free_cpumask_var(cpus); return count > 2 ? DIV_ROUND_UP(count, 2) : count; } EXPORT_SYMBOL(netif_get_num_default_rss_queues); static void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; unsigned long flags; local_irq_save(flags); sd = this_cpu_ptr(&softnet_data); q->next_sched = NULL; *sd->output_queue_tailp = q; sd->output_queue_tailp = &q->next_sched; raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } void __netif_schedule(struct Qdisc *q) { if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) __netif_reschedule(q); } EXPORT_SYMBOL(__netif_schedule); struct dev_kfree_skb_cb { enum skb_drop_reason reason; }; static struct dev_kfree_skb_cb *get_kfree_skb_cb(const struct sk_buff *skb) { return (struct dev_kfree_skb_cb *)skb->cb; } void netif_schedule_queue(struct netdev_queue *txq) { rcu_read_lock(); if (!netif_xmit_stopped(txq)) { struct Qdisc *q = rcu_dereference(txq->qdisc); __netif_schedule(q); } rcu_read_unlock(); } EXPORT_SYMBOL(netif_schedule_queue); void netif_tx_wake_queue(struct netdev_queue *dev_queue) { if (test_and_clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state)) { struct Qdisc *q; rcu_read_lock(); q = rcu_dereference(dev_queue->qdisc); __netif_schedule(q); rcu_read_unlock(); } } EXPORT_SYMBOL(netif_tx_wake_queue); void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason) { unsigned long flags; if (unlikely(!skb)) return; if (likely(refcount_read(&skb->users) == 1)) { smp_rmb(); refcount_set(&skb->users, 0); } else if (likely(!refcount_dec_and_test(&skb->users))) { return; } get_kfree_skb_cb(skb)->reason = reason; local_irq_save(flags); skb->next = __this_cpu_read(softnet_data.completion_queue); __this_cpu_write(softnet_data.completion_queue, skb); raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_restore(flags); } EXPORT_SYMBOL(dev_kfree_skb_irq_reason); void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason) { if (in_hardirq() || irqs_disabled()) dev_kfree_skb_irq_reason(skb, reason); else kfree_skb_reason(skb, reason); } EXPORT_SYMBOL(dev_kfree_skb_any_reason); /** * netif_device_detach - mark device as removed * @dev: network device * * Mark device as removed from system and therefore no longer available. */ void netif_device_detach(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_stop_all_queues(dev); } } EXPORT_SYMBOL(netif_device_detach); /** * netif_device_attach - mark device as attached * @dev: network device * * Mark device as attached from system and restart if needed. */ void netif_device_attach(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_PRESENT, &dev->state) && netif_running(dev)) { netif_tx_wake_all_queues(dev); netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_device_attach); /* * Returns a Tx hash based on the given packet descriptor a Tx queues' number * to be used as a distribution range. */ static u16 skb_tx_hash(const struct net_device *dev, const struct net_device *sb_dev, struct sk_buff *skb) { u32 hash; u16 qoffset = 0; u16 qcount = dev->real_num_tx_queues; if (dev->num_tc) { u8 tc = netdev_get_prio_tc_map(dev, skb->priority); qoffset = sb_dev->tc_to_txq[tc].offset; qcount = sb_dev->tc_to_txq[tc].count; if (unlikely(!qcount)) { net_warn_ratelimited("%s: invalid qcount, qoffset %u for tc %u\n", sb_dev->name, qoffset, tc); qoffset = 0; qcount = dev->real_num_tx_queues; } } if (skb_rx_queue_recorded(skb)) { DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; while (unlikely(hash >= qcount)) hash -= qcount; return hash + qoffset; } return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; } void skb_warn_bad_offload(const struct sk_buff *skb) { static const netdev_features_t null_features; struct net_device *dev = skb->dev; const char *name = ""; if (!net_ratelimit()) return; if (dev) { if (dev->dev.parent) name = dev_driver_string(dev->dev.parent); else name = netdev_name(dev); } skb_dump(KERN_WARNING, skb, false); WARN(1, "%s: caps=(%pNF, %pNF)\n", name, dev ? &dev->features : &null_features, skb->sk ? &skb->sk->sk_route_caps : &null_features); } /* * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. */ int skb_checksum_help(struct sk_buff *skb) { __wsum csum; int ret = 0, offset; if (skb->ip_summed == CHECKSUM_COMPLETE) goto out_set_summed; if (unlikely(skb_is_gso(skb))) { skb_warn_bad_offload(skb); return -EINVAL; } if (!skb_frags_readable(skb)) { return -EFAULT; } /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ if (skb_has_shared_frag(skb)) { ret = __skb_linearize(skb); if (ret) goto out; } offset = skb_checksum_start_offset(skb); ret = -EINVAL; if (unlikely(offset >= skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); WARN_ONCE(true, "offset (%d) >= skb_headlen() (%u)\n", offset, skb_headlen(skb)); goto out; } csum = skb_checksum(skb, offset, skb->len - offset, 0); offset += skb->csum_offset; if (unlikely(offset + sizeof(__sum16) > skb_headlen(skb))) { DO_ONCE_LITE(skb_dump, KERN_ERR, skb, false); WARN_ONCE(true, "offset+2 (%zu) > skb_headlen() (%u)\n", offset + sizeof(__sum16), skb_headlen(skb)); goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__sum16)); if (ret) goto out; *(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: return ret; } EXPORT_SYMBOL(skb_checksum_help); #ifdef CONFIG_NET_CRC32C int skb_crc32c_csum_help(struct sk_buff *skb) { u32 crc; int ret = 0, offset, start; if (skb->ip_summed != CHECKSUM_PARTIAL) goto out; if (unlikely(skb_is_gso(skb))) goto out; /* Before computing a checksum, we should make sure no frag could * be modified by an external entity : checksum could be wrong. */ if (unlikely(skb_has_shared_frag(skb))) { ret = __skb_linearize(skb); if (ret) goto out; } start = skb_checksum_start_offset(skb); offset = start + offsetof(struct sctphdr, checksum); if (WARN_ON_ONCE(offset >= skb_headlen(skb))) { ret = -EINVAL; goto out; } ret = skb_ensure_writable(skb, offset + sizeof(__le32)); if (ret) goto out; crc = ~skb_crc32c(skb, start, skb->len - start, ~0); *(__le32 *)(skb->data + offset) = cpu_to_le32(crc); skb_reset_csum_not_inet(skb); out: return ret; } EXPORT_SYMBOL(skb_crc32c_csum_help); #endif /* CONFIG_NET_CRC32C */ __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; /* Tunnel gso handlers can set protocol to ethernet. */ if (type == htons(ETH_P_TEB)) { struct ethhdr *eth; if (unlikely(!pskb_may_pull(skb, sizeof(struct ethhdr)))) return 0; eth = (struct ethhdr *)skb->data; type = eth->h_proto; } return vlan_get_protocol_and_depth(skb, type, depth); } /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG static void do_netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { netdev_err(dev, "hw csum failure\n"); skb_dump(KERN_ERR, skb, true); dump_stack(); } void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { DO_ONCE_LITE(do_netdev_rx_csum_fault, dev, skb); } EXPORT_SYMBOL(netdev_rx_csum_fault); #endif /* XXX: check that highmem exists at all on the given machine. */ static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; if (!(dev->features & NETIF_F_HIGHDMA)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct page *page = skb_frag_page(frag); if (page && PageHighMem(page)) return 1; } } #endif return 0; } /* If MPLS offload request, verify we are testing hardware MPLS features * instead of standard features for the netdev. */ #if IS_ENABLED(CONFIG_NET_MPLS_GSO) static netdev_features_t net_mpls_features(struct sk_buff *skb, netdev_features_t features, __be16 type) { if (eth_p_mpls(type)) features &= skb->dev->mpls_features; return features; } #else static netdev_features_t net_mpls_features(struct sk_buff *skb, netdev_features_t features, __be16 type) { return features; } #endif static netdev_features_t harmonize_features(struct sk_buff *skb, netdev_features_t features) { __be16 type; type = skb_network_protocol(skb, NULL); features = net_mpls_features(skb, features, type); if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, type)) { features &= ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } if (illegal_highdma(skb->dev, skb)) features &= ~NETIF_F_SG; return features; } netdev_features_t passthru_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { return features; } EXPORT_SYMBOL(passthru_features_check); static netdev_features_t dflt_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { return vlan_features_check(skb, features); } static netdev_features_t gso_features_check(const struct sk_buff *skb, struct net_device *dev, netdev_features_t features) { u16 gso_segs = skb_shinfo(skb)->gso_segs; if (gso_segs > READ_ONCE(dev->gso_max_segs)) return features & ~NETIF_F_GSO_MASK; if (unlikely(skb->len >= netif_get_gso_max_size(dev, skb))) return features & ~NETIF_F_GSO_MASK; if (!skb_shinfo(skb)->gso_type) { skb_warn_bad_offload(skb); return features & ~NETIF_F_GSO_MASK; } /* Support for GSO partial features requires software * intervention before we can actually process the packets * so we need to strip support for any partial features now * and we can pull them back in after we have partially * segmented the frame. */ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL)) features &= ~dev->gso_partial_features; /* Make sure to clear the IPv4 ID mangling feature if the * IPv4 header has the potential to be fragmented. */ if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4) { struct iphdr *iph = skb->encapsulation ? inner_ip_hdr(skb) : ip_hdr(skb); if (!(iph->frag_off & htons(IP_DF))) features &= ~NETIF_F_TSO_MANGLEID; } /* NETIF_F_IPV6_CSUM does not support IPv6 extension headers, * so neither does TSO that depends on it. */ if (features & NETIF_F_IPV6_CSUM && (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6 || (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && vlan_get_protocol(skb) == htons(ETH_P_IPV6))) && skb_transport_header_was_set(skb) && skb_network_header_len(skb) != sizeof(struct ipv6hdr) && !ipv6_has_hopopt_jumbo(skb)) features &= ~(NETIF_F_IPV6_CSUM | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4); return features; } netdev_features_t netif_skb_features(struct sk_buff *skb) { struct net_device *dev = skb->dev; netdev_features_t features = dev->features; if (skb_is_gso(skb)) features = gso_features_check(skb, dev, features); /* If encapsulation offload request, verify we are testing * hardware encapsulation features instead of standard * features for the netdev */ if (skb->encapsulation) features &= dev->hw_enc_features; if (skb_vlan_tagged(skb)) features = netdev_intersect_features(features, dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (dev->netdev_ops->ndo_features_check) features &= dev->netdev_ops->ndo_features_check(skb, dev, features); else features &= dflt_features_check(skb, dev, features); return harmonize_features(skb, features); } EXPORT_SYMBOL(netif_skb_features); static int xmit_one(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) { unsigned int len; int rc; if (dev_nit_active_rcu(dev)) dev_queue_xmit_nit(skb, dev); len = skb->len; trace_net_dev_start_xmit(skb, dev); rc = netdev_start_xmit(skb, dev, txq, more); trace_net_dev_xmit(skb, rc, dev, len); return rc; } struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *dev, struct netdev_queue *txq, int *ret) { struct sk_buff *skb = first; int rc = NETDEV_TX_OK; while (skb) { struct sk_buff *next = skb->next; skb_mark_not_on_list(skb); rc = xmit_one(skb, dev, txq, next != NULL); if (unlikely(!dev_xmit_complete(rc))) { skb->next = next; goto out; } skb = next; if (netif_tx_queue_stopped(txq) && skb) { rc = NETDEV_TX_BUSY; break; } } out: *ret = rc; return skb; } static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb, netdev_features_t features) { if (skb_vlan_tag_present(skb) && !vlan_hw_offload_capable(features, skb->vlan_proto)) skb = __vlan_hwaccel_push_inside(skb); return skb; } int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features) { if (unlikely(skb_csum_is_sctp(skb))) return !!(features & NETIF_F_SCTP_CRC) ? 0 : skb_crc32c_csum_help(skb); if (features & NETIF_F_HW_CSUM) return 0; if (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) { if (vlan_get_protocol(skb) == htons(ETH_P_IPV6) && skb_network_header_len(skb) != sizeof(struct ipv6hdr) && !ipv6_has_hopopt_jumbo(skb)) goto sw_checksum; switch (skb->csum_offset) { case offsetof(struct tcphdr, check): case offsetof(struct udphdr, check): return 0; } } sw_checksum: return skb_checksum_help(skb); } EXPORT_SYMBOL(skb_csum_hwoffload_help); static struct sk_buff *validate_xmit_unreadable_skb(struct sk_buff *skb, struct net_device *dev) { struct skb_shared_info *shinfo; struct net_iov *niov; if (likely(skb_frags_readable(skb))) goto out; if (!dev->netmem_tx) goto out_free; shinfo = skb_shinfo(skb); if (shinfo->nr_frags > 0) { niov = netmem_to_net_iov(skb_frag_netmem(&shinfo->frags[0])); if (net_is_devmem_iov(niov) && net_devmem_iov_binding(niov)->dev != dev) goto out_free; } out: return skb; out_free: kfree_skb(skb); return NULL; } static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again) { netdev_features_t features; skb = validate_xmit_unreadable_skb(skb, dev); if (unlikely(!skb)) goto out_null; features = netif_skb_features(skb); skb = validate_xmit_vlan(skb, features); if (unlikely(!skb)) goto out_null; skb = sk_validate_xmit_skb(skb, dev); if (unlikely(!skb)) goto out_null; if (netif_needs_gso(skb, features)) { struct sk_buff *segs; segs = skb_gso_segment(skb, features); if (IS_ERR(segs)) { goto out_kfree_skb; } else if (segs) { consume_skb(skb); skb = segs; } } else { if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto out_kfree_skb; /* If packet is not checksummed and device does not * support checksumming for this protocol, complete * checksumming here. */ if (skb->ip_summed == CHECKSUM_PARTIAL) { if (skb->encapsulation) skb_set_inner_transport_header(skb, skb_checksum_start_offset(skb)); else skb_set_transport_header(skb, skb_checksum_start_offset(skb)); if (skb_csum_hwoffload_help(skb, features)) goto out_kfree_skb; } } skb = validate_xmit_xfrm(skb, features, again); return skb; out_kfree_skb: kfree_skb(skb); out_null: dev_core_stats_tx_dropped_inc(dev); return NULL; } struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again) { struct sk_buff *next, *head = NULL, *tail; for (; skb != NULL; skb = next) { next = skb->next; skb_mark_not_on_list(skb); /* in case skb won't be segmented, point to itself */ skb->prev = skb; skb = validate_xmit_skb(skb, dev, again); if (!skb) continue; if (!head) head = skb; else tail->next = skb; /* If skb was segmented, skb->prev points to * the last segment. If not, it still contains skb. */ tail = skb->prev; } return head; } EXPORT_SYMBOL_GPL(validate_xmit_skb_list); static void qdisc_pkt_len_init(struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); qdisc_skb_cb(skb)->pkt_len = skb->len; /* To get more precise estimation of bytes sent on wire, * we add to pkt_len the headers size of all segments */ if (shinfo->gso_size && skb_transport_header_was_set(skb)) { u16 gso_segs = shinfo->gso_segs; unsigned int hdr_len; /* mac layer + network layer */ if (!skb->encapsulation) hdr_len = skb_transport_offset(skb); else hdr_len = skb_inner_transport_offset(skb); /* + transport layer */ if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) { const struct tcphdr *th; struct tcphdr _tcphdr; th = skb_header_pointer(skb, hdr_len, sizeof(_tcphdr), &_tcphdr); if (likely(th)) hdr_len += __tcp_hdrlen(th); } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { struct udphdr _udphdr; if (skb_header_pointer(skb, hdr_len, sizeof(_udphdr), &_udphdr)) hdr_len += sizeof(struct udphdr); } if (unlikely(shinfo->gso_type & SKB_GSO_DODGY)) { int payload = skb->len - hdr_len; /* Malicious packet. */ if (payload <= 0) return; gso_segs = DIV_ROUND_UP(payload, shinfo->gso_size); } qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } } static int dev_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *q, struct sk_buff **to_free, struct netdev_queue *txq) { int rc; rc = q->enqueue(skb, q, to_free) & NET_XMIT_MASK; if (rc == NET_XMIT_SUCCESS) trace_qdisc_enqueue(q, txq, skb); return rc; } static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) { spinlock_t *root_lock = qdisc_lock(q); struct sk_buff *to_free = NULL; bool contended; int rc; qdisc_calculate_pkt_len(skb, q); tcf_set_drop_reason(skb, SKB_DROP_REASON_QDISC_DROP); if (q->flags & TCQ_F_NOLOCK) { if (q->flags & TCQ_F_CAN_BYPASS && nolock_qdisc_is_empty(q) && qdisc_run_begin(q)) { /* Retest nolock_qdisc_is_empty() within the protection * of q->seqlock to protect from racing with requeuing. */ if (unlikely(!nolock_qdisc_is_empty(q))) { rc = dev_qdisc_enqueue(skb, q, &to_free, txq); __qdisc_run(q); qdisc_run_end(q); goto no_lock_out; } qdisc_bstats_cpu_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, NULL, true) && !nolock_qdisc_is_empty(q)) __qdisc_run(q); qdisc_run_end(q); return NET_XMIT_SUCCESS; } rc = dev_qdisc_enqueue(skb, q, &to_free, txq); qdisc_run(q); no_lock_out: if (unlikely(to_free)) kfree_skb_list_reason(to_free, tcf_get_drop_reason(to_free)); return rc; } if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) { kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP); return NET_XMIT_DROP; } /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. * This permits qdisc->running owner to get the lock more * often and dequeue packets faster. * On PREEMPT_RT it is possible to preempt the qdisc owner during xmit * and then other tasks will only enqueue packets. The packets will be * sent after the qdisc owner is scheduled again. To prevent this * scenario the task always serialize on the lock. */ contended = qdisc_is_running(q) || IS_ENABLED(CONFIG_PREEMPT_RT); if (unlikely(contended)) spin_lock(&q->busylock); spin_lock(root_lock); if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { __qdisc_drop(skb, &to_free); rc = NET_XMIT_DROP; } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && qdisc_run_begin(q)) { /* * This is a work-conserving queue; there are no old skbs * waiting to be sent out; and the qdisc is not running - * xmit the skb directly. */ qdisc_bstats_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) { if (unlikely(contended)) { spin_unlock(&q->busylock); contended = false; } __qdisc_run(q); } qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { WRITE_ONCE(q->owner, smp_processor_id()); rc = dev_qdisc_enqueue(skb, q, &to_free, txq); WRITE_ONCE(q->owner, -1); if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); contended = false; } __qdisc_run(q); qdisc_run_end(q); } } spin_unlock(root_lock); if (unlikely(to_free)) kfree_skb_list_reason(to_free, tcf_get_drop_reason(to_free)); if (unlikely(contended)) spin_unlock(&q->busylock); return rc; } #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) static void skb_update_prio(struct sk_buff *skb) { const struct netprio_map *map; const struct sock *sk; unsigned int prioidx; if (skb->priority) return; map = rcu_dereference_bh(skb->dev->priomap); if (!map) return; sk = skb_to_full_sk(skb); if (!sk) return; prioidx = sock_cgroup_prioidx(&sk->sk_cgrp_data); if (prioidx < map->priomap_len) skb->priority = map->priomap[prioidx]; } #else #define skb_update_prio(skb) #endif /** * dev_loopback_xmit - loop back @skb * @net: network namespace this loopback is happening in * @sk: sk needed to be a netfilter okfn * @skb: buffer to transmit */ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { skb_reset_mac_header(skb); __skb_pull(skb, skb_network_offset(skb)); skb->pkt_type = PACKET_LOOPBACK; if (skb->ip_summed == CHECKSUM_NONE) skb->ip_summed = CHECKSUM_UNNECESSARY; DEBUG_NET_WARN_ON_ONCE(!skb_dst(skb)); skb_dst_force(skb); netif_rx(skb); return 0; } EXPORT_SYMBOL(dev_loopback_xmit); #ifdef CONFIG_NET_EGRESS static struct netdev_queue * netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb) { int qm = skb_get_queue_mapping(skb); return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm)); } #ifndef CONFIG_PREEMPT_RT static bool netdev_xmit_txqueue_skipped(void) { return __this_cpu_read(softnet_data.xmit.skip_txqueue); } void netdev_xmit_skip_txqueue(bool skip) { __this_cpu_write(softnet_data.xmit.skip_txqueue, skip); } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); #else static bool netdev_xmit_txqueue_skipped(void) { return current->net_xmit.skip_txqueue; } void netdev_xmit_skip_txqueue(bool skip) { current->net_xmit.skip_txqueue = skip; } EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue); #endif #endif /* CONFIG_NET_EGRESS */ #ifdef CONFIG_NET_XGRESS static int tc_run(struct tcx_entry *entry, struct sk_buff *skb, enum skb_drop_reason *drop_reason) { int ret = TC_ACT_UNSPEC; #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(entry->miniq); struct tcf_result res; if (!miniq) return ret; /* Global bypass */ if (!static_branch_likely(&tcf_sw_enabled_key)) return ret; /* Block-wise bypass */ if (tcf_block_bypass_sw(miniq->block)) return ret; tc_skb_cb(skb)->mru = 0; tc_skb_cb(skb)->post_ct = false; tcf_set_drop_reason(skb, *drop_reason); mini_qdisc_bstats_cpu_update(miniq, skb); ret = tcf_classify(skb, miniq->block, miniq->filter_list, &res, false); /* Only tcf related quirks below. */ switch (ret) { case TC_ACT_SHOT: *drop_reason = tcf_get_drop_reason(skb); mini_qdisc_qstats_cpu_drop(miniq); break; case TC_ACT_OK: case TC_ACT_RECLASSIFY: skb->tc_index = TC_H_MIN(res.classid); break; } #endif /* CONFIG_NET_CLS_ACT */ return ret; } static DEFINE_STATIC_KEY_FALSE(tcx_needed_key); void tcx_inc(void) { static_branch_inc(&tcx_needed_key); } void tcx_dec(void) { static_branch_dec(&tcx_needed_key); } static __always_inline enum tcx_action_base tcx_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb, const bool needs_mac) { const struct bpf_mprog_fp *fp; const struct bpf_prog *prog; int ret = TCX_NEXT; if (needs_mac) __skb_push(skb, skb->mac_len); bpf_mprog_foreach_prog(entry, fp, prog) { bpf_compute_data_pointers(skb); ret = bpf_prog_run(prog, skb); if (ret != TCX_NEXT) break; } if (needs_mac) __skb_pull(skb, skb->mac_len); return tcx_action_code(skb, ret); } static __always_inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev, bool *another) { struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_INGRESS; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int sch_ret; if (!entry) return skb; bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } qdisc_skb_cb(skb)->pkt_len = skb->len; tcx_set_ingress(skb, true); if (static_branch_unlikely(&tcx_needed_key)) { sch_ret = tcx_run(entry, skb, true); if (sch_ret != TC_ACT_UNSPEC) goto ingress_verdict; } sch_ret = tc_run(tcx_entry(entry), skb, &drop_reason); ingress_verdict: switch (sch_ret) { case TC_ACT_REDIRECT: /* skb_mac_header check was done by BPF, so we can safely * push the L2 header back before redirecting to another * netdev. */ __skb_push(skb, skb->mac_len); if (skb_do_redirect(skb) == -EAGAIN) { __skb_pull(skb, skb->mac_len); *another = true; break; } *ret = NET_RX_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_RX_DROP; bpf_net_ctx_clear(bpf_net_ctx); return NULL; /* used by tc_run */ case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); fallthrough; case TC_ACT_CONSUMED: *ret = NET_RX_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; } bpf_net_ctx_clear(bpf_net_ctx); return skb; } static __always_inline struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress); enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_EGRESS; struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int sch_ret; if (!entry) return skb; bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); /* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was * already set by the caller. */ if (static_branch_unlikely(&tcx_needed_key)) { sch_ret = tcx_run(entry, skb, false); if (sch_ret != TC_ACT_UNSPEC) goto egress_verdict; } sch_ret = tc_run(tcx_entry(entry), skb, &drop_reason); egress_verdict: switch (sch_ret) { case TC_ACT_REDIRECT: /* No need to push/pop skb's mac_header here on egress! */ skb_do_redirect(skb); *ret = NET_XMIT_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; case TC_ACT_SHOT: kfree_skb_reason(skb, drop_reason); *ret = NET_XMIT_DROP; bpf_net_ctx_clear(bpf_net_ctx); return NULL; /* used by tc_run */ case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: consume_skb(skb); fallthrough; case TC_ACT_CONSUMED: *ret = NET_XMIT_SUCCESS; bpf_net_ctx_clear(bpf_net_ctx); return NULL; } bpf_net_ctx_clear(bpf_net_ctx); return skb; } #else static __always_inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev, bool *another) { return skb; } static __always_inline struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { return skb; } #endif /* CONFIG_NET_XGRESS */ #ifdef CONFIG_XPS static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb, struct xps_dev_maps *dev_maps, unsigned int tci) { int tc = netdev_get_prio_tc_map(dev, skb->priority); struct xps_map *map; int queue_index = -1; if (tc >= dev_maps->num_tc || tci >= dev_maps->nr_ids) return queue_index; tci *= dev_maps->num_tc; tci += tc; map = rcu_dereference(dev_maps->attr_map[tci]); if (map) { if (map->len == 1) queue_index = map->queues[0]; else queue_index = map->queues[reciprocal_scale( skb_get_hash(skb), map->len)]; if (unlikely(queue_index >= dev->real_num_tx_queues)) queue_index = -1; } return queue_index; } #endif static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev, struct sk_buff *skb) { #ifdef CONFIG_XPS struct xps_dev_maps *dev_maps; struct sock *sk = skb->sk; int queue_index = -1; if (!static_key_false(&xps_needed)) return -1; rcu_read_lock(); if (!static_key_false(&xps_rxqs_needed)) goto get_cpus_map; dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_RXQS]); if (dev_maps) { int tci = sk_rx_queue_get(sk); if (tci >= 0) queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } get_cpus_map: if (queue_index < 0) { dev_maps = rcu_dereference(sb_dev->xps_maps[XPS_CPUS]); if (dev_maps) { unsigned int tci = skb->sender_cpu - 1; queue_index = __get_xps_queue_idx(dev, skb, dev_maps, tci); } } rcu_read_unlock(); return queue_index; #else return -1; #endif } u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { return 0; } EXPORT_SYMBOL(dev_pick_tx_zero); u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); sb_dev = sb_dev ? : dev; if (queue_index < 0 || skb->ooo_okay || queue_index >= dev->real_num_tx_queues) { int new_index = get_xps_queue(dev, sb_dev, skb); if (new_index < 0) new_index = skb_tx_hash(dev, sb_dev, skb); if (queue_index != new_index && sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); queue_index = new_index; } return queue_index; } EXPORT_SYMBOL(netdev_pick_tx); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { int queue_index = 0; #ifdef CONFIG_XPS u32 sender_cpu = skb->sender_cpu - 1; if (sender_cpu >= (u32)NR_CPUS) skb->sender_cpu = raw_smp_processor_id() + 1; #endif if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) queue_index = ops->ndo_select_queue(dev, skb, sb_dev); else queue_index = netdev_pick_tx(dev, skb, sb_dev); queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); return netdev_get_tx_queue(dev, queue_index); } /** * __dev_queue_xmit() - transmit a buffer * @skb: buffer to transmit * @sb_dev: suboordinate device used for L2 forwarding offload * * Queue a buffer for transmission to a network device. The caller must * have set the device and priority and built the buffer before calling * this function. The function can be called from an interrupt. * * When calling this method, interrupts MUST be enabled. This is because * the BH enable code must have IRQs enabled so that it will not deadlock. * * Regardless of the return value, the skb is consumed, so it is currently * difficult to retry a send to this method. (You can bump the ref count * before sending to hold a reference for retry if you are careful.) * * Return: * * 0 - buffer successfully transmitted * * positive qdisc return code - NET_XMIT_DROP etc. * * negative errno - other errors */ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) { struct net_device *dev = skb->dev; struct netdev_queue *txq = NULL; struct Qdisc *q; int rc = -ENOMEM; bool again = false; skb_reset_mac_header(skb); skb_assert_len(skb); if (unlikely(skb_shinfo(skb)->tx_flags & (SKBTX_SCHED_TSTAMP | SKBTX_BPF))) __skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED); /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ rcu_read_lock_bh(); skb_update_prio(skb); qdisc_pkt_len_init(skb); tcx_set_ingress(skb, false); #ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { if (nf_hook_egress_active()) { skb = nf_hook_egress(skb, &rc, dev); if (!skb) goto out; } netdev_xmit_skip_txqueue(false); nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; nf_skip_egress(skb, false); if (netdev_xmit_txqueue_skipped()) txq = netdev_tx_queue_mapping(dev, skb); } #endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. */ if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); else skb_dst_force(skb); if (!txq) txq = netdev_core_pick_tx(dev, skb, sb_dev); q = rcu_dereference_bh(txq->qdisc); trace_net_dev_queue(skb); if (q->enqueue) { rc = __dev_xmit_skb(skb, q, dev, txq); goto out; } /* The device has no queue. Common case for software devices: * loopback, all the sorts of tunnels... * Really, it is unlikely that netif_tx_lock protection is necessary * here. (f.e. loopback and IP tunnels are clean ignoring statistics * counters.) * However, it is possible, that they rely on protection * made by us here. * Check this and shot the lock. It is not prone from deadlocks. *Either shot noqueue qdisc, it is even simpler 8) */ if (dev->flags & IFF_UP) { int cpu = smp_processor_id(); /* ok because BHs are off */ /* Other cpus might concurrently change txq->xmit_lock_owner * to -1 or to their cpu id, but not to our id. */ if (READ_ONCE(txq->xmit_lock_owner) != cpu) { if (dev_xmit_recursion()) goto recursion_alert; skb = validate_xmit_skb(skb, dev, &again); if (!skb) goto out; HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_stopped(txq)) { dev_xmit_recursion_inc(); skb = dev_hard_start_xmit(skb, dev, txq, &rc); dev_xmit_recursion_dec(); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; } } HARD_TX_UNLOCK(dev, txq); net_crit_ratelimited("Virtual device %s asks to queue packet!\n", dev->name); } else { /* Recursion is detected! It is possible, * unfortunately */ recursion_alert: net_crit_ratelimited("Dead loop on virtual device %s, fix it urgently!\n", dev->name); } } rc = -ENETDOWN; rcu_read_unlock_bh(); dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return rc; out: rcu_read_unlock_bh(); return rc; } EXPORT_SYMBOL(__dev_queue_xmit); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { struct net_device *dev = skb->dev; struct sk_buff *orig_skb = skb; struct netdev_queue *txq; int ret = NETDEV_TX_BUSY; bool again = false; if (unlikely(!netif_running(dev) || !netif_carrier_ok(dev))) goto drop; skb = validate_xmit_skb_list(skb, dev, &again); if (skb != orig_skb) goto drop; skb_set_queue_mapping(skb, queue_id); txq = skb_get_tx_queue(dev, skb); local_bh_disable(); dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); dev_xmit_recursion_dec(); local_bh_enable(); return ret; drop: dev_core_stats_tx_dropped_inc(dev); kfree_skb_list(skb); return NET_XMIT_DROP; } EXPORT_SYMBOL(__dev_direct_xmit); /************************************************************************* * Receiver routines *************************************************************************/ static DEFINE_PER_CPU(struct task_struct *, backlog_napi); int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ /* Called with irq disabled */ static inline void ____napi_schedule(struct softnet_data *sd, struct napi_struct *napi) { struct task_struct *thread; lockdep_assert_irqs_disabled(); if (test_bit(NAPI_STATE_THREADED, &napi->state)) { /* Paired with smp_mb__before_atomic() in * napi_enable()/netif_set_threaded(). * Use READ_ONCE() to guarantee a complete * read on napi->thread. Only call * wake_up_process() when it's not NULL. */ thread = READ_ONCE(napi->thread); if (thread) { if (use_backlog_threads() && thread == raw_cpu_read(backlog_napi)) goto use_local_napi; set_bit(NAPI_STATE_SCHED_THREADED, &napi->state); wake_up_process(thread); return; } } use_local_napi: DEBUG_NET_WARN_ON_ONCE(!list_empty(&napi->poll_list)); list_add_tail(&napi->poll_list, &sd->poll_list); WRITE_ONCE(napi->list_owner, smp_processor_id()); /* If not called from net_rx_action() * we have to raise NET_RX_SOFTIRQ. */ if (!sd->in_net_rx_action) raise_softirq_irqoff(NET_RX_SOFTIRQ); } #ifdef CONFIG_RPS struct static_key_false rps_needed __read_mostly; EXPORT_SYMBOL(rps_needed); struct static_key_false rfs_needed __read_mostly; EXPORT_SYMBOL(rfs_needed); static u32 rfs_slot(u32 hash, const struct rps_dev_flow_table *flow_table) { return hash_32(hash, flow_table->log); } static struct rps_dev_flow * set_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow *rflow, u16 next_cpu) { if (next_cpu < nr_cpu_ids) { u32 head; #ifdef CONFIG_RFS_ACCEL struct netdev_rx_queue *rxqueue; struct rps_dev_flow_table *flow_table; struct rps_dev_flow *old_rflow; u16 rxq_index; u32 flow_id; int rc; /* Should we steer this flow to a different hardware queue? */ if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap || !(dev->features & NETIF_F_NTUPLE)) goto out; rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu); if (rxq_index == skb_get_rx_queue(skb)) goto out; rxqueue = dev->_rx + rxq_index; flow_table = rcu_dereference(rxqueue->rps_flow_table); if (!flow_table) goto out; flow_id = rfs_slot(skb_get_hash(skb), flow_table); rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, rxq_index, flow_id); if (rc < 0) goto out; old_rflow = rflow; rflow = &flow_table->flows[flow_id]; WRITE_ONCE(rflow->filter, rc); if (old_rflow->filter == rc) WRITE_ONCE(old_rflow->filter, RPS_NO_FILTER); out: #endif head = READ_ONCE(per_cpu(softnet_data, next_cpu).input_queue_head); rps_input_queue_tail_save(&rflow->last_qtail, head); } WRITE_ONCE(rflow->cpu, next_cpu); return rflow; } /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. * rcu_read_lock must be held on entry. */ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, struct rps_dev_flow **rflowp) { const struct rps_sock_flow_table *sock_flow_table; struct netdev_rx_queue *rxqueue = dev->_rx; struct rps_dev_flow_table *flow_table; struct rps_map *map; int cpu = -1; u32 tcpu; u32 hash; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->real_num_rx_queues)) { WARN_ONCE(dev->real_num_rx_queues > 1, "%s received packet on queue %u, but number " "of RX queues is %u\n", dev->name, index, dev->real_num_rx_queues); goto done; } rxqueue += index; } /* Avoid computing hash if RFS/RPS is not active for this rxqueue */ flow_table = rcu_dereference(rxqueue->rps_flow_table); map = rcu_dereference(rxqueue->rps_map); if (!flow_table && !map) goto done; skb_reset_network_header(skb); hash = skb_get_hash(skb); if (!hash) goto done; sock_flow_table = rcu_dereference(net_hotdata.rps_sock_flow_table); if (flow_table && sock_flow_table) { struct rps_dev_flow *rflow; u32 next_cpu; u32 ident; /* First check into global flow table if there is a match. * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow(). */ ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]); if ((ident ^ hash) & ~net_hotdata.rps_cpu_mask) goto try_rps; next_cpu = ident & net_hotdata.rps_cpu_mask; /* OK, now we know there is a match, * we can look at the local (per receive queue) flow table */ rflow = &flow_table->flows[rfs_slot(hash, flow_table)]; tcpu = rflow->cpu; /* * If the desired CPU (where last recvmsg was done) is * different from current CPU (one in the rx-queue flow * table entry), switch if one of the following holds: * - Current CPU is unset (>= nr_cpu_ids). * - Current CPU is offline. * - The current CPU's queue tail has advanced beyond the * last packet that was enqueued using this table entry. * This guarantees that all previous packets for the flow * have been dequeued, thus preserving in order delivery. */ if (unlikely(tcpu != next_cpu) && (tcpu >= nr_cpu_ids || !cpu_online(tcpu) || ((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) - rflow->last_qtail)) >= 0)) { tcpu = next_cpu; rflow = set_rps_cpu(dev, skb, rflow, next_cpu); } if (tcpu < nr_cpu_ids && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; goto done; } } try_rps: if (map) { tcpu = map->cpus[reciprocal_scale(hash, map->len)]; if (cpu_online(tcpu)) { cpu = tcpu; goto done; } } done: return cpu; } #ifdef CONFIG_RFS_ACCEL /** * rps_may_expire_flow - check whether an RFS hardware filter may be removed * @dev: Device on which the filter was set * @rxq_index: RX queue index * @flow_id: Flow ID passed to ndo_rx_flow_steer() * @filter_id: Filter ID returned by ndo_rx_flow_steer() * * Drivers that implement ndo_rx_flow_steer() should periodically call * this function for each installed filter and remove the filters for * which it returns %true. */ bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id) { struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index; struct rps_dev_flow_table *flow_table; struct rps_dev_flow *rflow; bool expire = true; unsigned int cpu; rcu_read_lock(); flow_table = rcu_dereference(rxqueue->rps_flow_table); if (flow_table && flow_id < (1UL << flow_table->log)) { rflow = &flow_table->flows[flow_id]; cpu = READ_ONCE(rflow->cpu); if (READ_ONCE(rflow->filter) == filter_id && cpu < nr_cpu_ids && ((int)(READ_ONCE(per_cpu(softnet_data, cpu).input_queue_head) - READ_ONCE(rflow->last_qtail)) < (int)(10 << flow_table->log))) expire = false; } rcu_read_unlock(); return expire; } EXPORT_SYMBOL(rps_may_expire_flow); #endif /* CONFIG_RFS_ACCEL */ /* Called from hardirq (IPI) context */ static void rps_trigger_softirq(void *data) { struct softnet_data *sd = data; ____napi_schedule(sd, &sd->backlog); /* Pairs with READ_ONCE() in softnet_seq_show() */ WRITE_ONCE(sd->received_rps, sd->received_rps + 1); } #endif /* CONFIG_RPS */ /* Called from hardirq (IPI) context */ static void trigger_rx_softirq(void *data) { struct softnet_data *sd = data; __raise_softirq_irqoff(NET_RX_SOFTIRQ); smp_store_release(&sd->defer_ipi_scheduled, 0); } /* * After we queued a packet into sd->input_pkt_queue, * we need to make sure this queue is serviced soon. * * - If this is another cpu queue, link it to our rps_ipi_list, * and make sure we will process rps_ipi_list from net_rx_action(). * * - If this is our own queue, NAPI schedule our backlog. * Note that this also raises NET_RX_SOFTIRQ. */ static void napi_schedule_rps(struct softnet_data *sd) { struct softnet_data *mysd = this_cpu_ptr(&softnet_data); #ifdef CONFIG_RPS if (sd != mysd) { if (use_backlog_threads()) { __napi_schedule_irqoff(&sd->backlog); return; } sd->rps_ipi_next = mysd->rps_ipi_list; mysd->rps_ipi_list = sd; /* If not called from net_rx_action() or napi_threaded_poll() * we have to raise NET_RX_SOFTIRQ. */ if (!mysd->in_net_rx_action && !mysd->in_napi_threaded_poll) __raise_softirq_irqoff(NET_RX_SOFTIRQ); return; } #endif /* CONFIG_RPS */ __napi_schedule_irqoff(&mysd->backlog); } void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu) { unsigned long flags; if (use_backlog_threads()) { backlog_lock_irq_save(sd, &flags); if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) __napi_schedule_irqoff(&sd->backlog); backlog_unlock_irq_restore(sd, &flags); } else if (!cmpxchg(&sd->defer_ipi_scheduled, 0, 1)) { smp_call_function_single_async(cpu, &sd->defer_csd); } } #ifdef CONFIG_NET_FLOW_LIMIT int netdev_flow_limit_table_len __read_mostly = (1 << 12); #endif static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) { #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit *fl; struct softnet_data *sd; unsigned int old_flow, new_flow; if (qlen < (READ_ONCE(net_hotdata.max_backlog) >> 1)) return false; sd = this_cpu_ptr(&softnet_data); rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) { new_flow = hash_32(skb_get_hash(skb), fl->log_buckets); old_flow = fl->history[fl->history_head]; fl->history[fl->history_head] = new_flow; fl->history_head++; fl->history_head &= FLOW_LIMIT_HISTORY - 1; if (likely(fl->buckets[old_flow])) fl->buckets[old_flow]--; if (++fl->buckets[new_flow] > (FLOW_LIMIT_HISTORY >> 1)) { /* Pairs with READ_ONCE() in softnet_seq_show() */ WRITE_ONCE(fl->count, fl->count + 1); rcu_read_unlock(); return true; } } rcu_read_unlock(); #endif return false; } /* * enqueue_to_backlog is called to queue an skb to a per CPU backlog * queue (may be a remote CPU queue). */ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, unsigned int *qtail) { enum skb_drop_reason reason; struct softnet_data *sd; unsigned long flags; unsigned int qlen; int max_backlog; u32 tail; reason = SKB_DROP_REASON_DEV_READY; if (!netif_running(skb->dev)) goto bad_dev; reason = SKB_DROP_REASON_CPU_BACKLOG; sd = &per_cpu(softnet_data, cpu); qlen = skb_queue_len_lockless(&sd->input_pkt_queue); max_backlog = READ_ONCE(net_hotdata.max_backlog); if (unlikely(qlen > max_backlog)) goto cpu_backlog_drop; backlog_lock_irq_save(sd, &flags); qlen = skb_queue_len(&sd->input_pkt_queue); if (qlen <= max_backlog && !skb_flow_limit(skb, qlen)) { if (!qlen) { /* Schedule NAPI for backlog device. We can use * non atomic operation as we own the queue lock. */ if (!__test_and_set_bit(NAPI_STATE_SCHED, &sd->backlog.state)) napi_schedule_rps(sd); } __skb_queue_tail(&sd->input_pkt_queue, skb); tail = rps_input_queue_tail_incr(sd); backlog_unlock_irq_restore(sd, &flags); /* save the tail outside of the critical section */ rps_input_queue_tail_save(qtail, tail); return NET_RX_SUCCESS; } backlog_unlock_irq_restore(sd, &flags); cpu_backlog_drop: atomic_inc(&sd->dropped); bad_dev: dev_core_stats_rx_dropped_inc(skb->dev); kfree_skb_reason(skb, reason); return NET_RX_DROP; } static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct netdev_rx_queue *rxqueue; rxqueue = dev->_rx; if (skb_rx_queue_recorded(skb)) { u16 index = skb_get_rx_queue(skb); if (unlikely(index >= dev->real_num_rx_queues)) { WARN_ONCE(dev->real_num_rx_queues > 1, "%s received packet on queue %u, but number " "of RX queues is %u\n", dev->name, index, dev->real_num_rx_queues); return rxqueue; /* Return first rxqueue */ } rxqueue += index; } return rxqueue; } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { void *orig_data, *orig_data_end, *hard_start; struct netdev_rx_queue *rxqueue; bool orig_bcast, orig_host; u32 mac_len, frame_sz; __be16 orig_eth_type; struct ethhdr *eth; u32 metalen, act; int off; /* The XDP program wants to see the packet starting at the MAC * header. */ mac_len = skb->data - skb_mac_header(skb); hard_start = skb->data - skb_headroom(skb); /* SKB "head" area always have tailroom for skb_shared_info */ frame_sz = (void *)skb_end_pointer(skb) - hard_start; frame_sz += SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); rxqueue = netif_get_rxqueue(skb); xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq); xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len, skb_headlen(skb) + mac_len, 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); } orig_data_end = xdp->data_end; orig_data = xdp->data; eth = (struct ethhdr *)xdp->data; orig_host = ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr); orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest); orig_eth_type = eth->h_proto; act = bpf_prog_run_xdp(xdp_prog, xdp); /* check if bpf_xdp_adjust_head was used */ off = xdp->data - orig_data; if (off) { if (off > 0) __skb_pull(skb, off); else if (off < 0) __skb_push(skb, -off); skb->mac_header += off; skb_reset_network_header(skb); } /* check if bpf_xdp_adjust_tail was used */ off = xdp->data_end - orig_data_end; if (off != 0) { skb_set_tail_pointer(skb, xdp->data_end - xdp->data); skb->len += 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; /* check if XDP changed eth hdr such SKB needs update */ eth = (struct ethhdr *)xdp->data; if ((orig_eth_type != eth->h_proto) || (orig_host != ether_addr_equal_64bits(eth->h_dest, skb->dev->dev_addr)) || (orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) { __skb_push(skb, ETH_HLEN); skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); } /* Redirect/Tx gives L2 packet, code that will reuse skb must __skb_pull * before calling us again on redirect path. We do not call do_redirect * as we leave that up to the caller. * * Caller is responsible for managing lifetime of skb (i.e. calling * kfree_skb in response to actions it cannot handle/XDP_DROP). */ switch (act) { case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); break; case XDP_PASS: metalen = xdp->data - xdp->data_meta; if (metalen) skb_metadata_set(skb, metalen); break; } return act; } static int netif_skb_check_for_xdp(struct sk_buff **pskb, const struct bpf_prog *prog) { struct sk_buff *skb = *pskb; int err, hroom, troom; local_lock_nested_bh(&system_page_pool.bh_lock); err = skb_cow_data_for_xdp(this_cpu_read(system_page_pool.pool), pskb, prog); local_unlock_nested_bh(&system_page_pool.bh_lock); if (!err) return 0; /* In case we have to go down the path and also linearize, * then lets do the pskb_expand_head() work just once here. */ hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); troom = skb->tail + skb->data_len - skb->end; err = pskb_expand_head(skb, hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0, troom > 0 ? troom + 128 : 0, GFP_ATOMIC); if (err) return err; return skb_linearize(skb); } static u32 netif_receive_generic_xdp(struct sk_buff **pskb, struct xdp_buff *xdp, const struct bpf_prog *xdp_prog) { struct sk_buff *skb = *pskb; u32 mac_len, act = XDP_DROP; /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ if (skb_is_redirected(skb)) return XDP_PASS; /* XDP packets must have sufficient headroom of XDP_PACKET_HEADROOM * bytes. This is the guarantee that also native XDP provides, * thus we need to do it here as well. */ mac_len = skb->data - skb_mac_header(skb); __skb_push(skb, mac_len); if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { if (netif_skb_check_for_xdp(pskb, xdp_prog)) goto do_drop; } __skb_pull(*pskb, mac_len); act = bpf_prog_run_generic_xdp(*pskb, xdp, xdp_prog); switch (act) { case XDP_REDIRECT: case XDP_TX: case XDP_PASS: break; default: bpf_warn_invalid_xdp_action((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_ABORTED: trace_xdp_exception((*pskb)->dev, xdp_prog, act); fallthrough; case XDP_DROP: do_drop: kfree_skb(*pskb); break; } return act; } /* When doing generic XDP we have to bypass the qdisc layer and the * network taps in order to match in-driver-XDP behavior. This also means * that XDP packets are able to starve other packets going through a qdisc, * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX * queues, so they do not have this starvation issue. */ void generic_xdp_tx(struct sk_buff *skb, const struct bpf_prog *xdp_prog) { struct net_device *dev = skb->dev; struct netdev_queue *txq; bool free_skb = true; int cpu, rc; txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); if (!netif_xmit_frozen_or_drv_stopped(txq)) { rc = netdev_start_xmit(skb, dev, txq, 0); if (dev_xmit_complete(rc)) free_skb = false; } HARD_TX_UNLOCK(dev, txq); if (free_skb) { trace_xdp_exception(dev, xdp_prog, XDP_TX); dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); } } static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); int do_xdp_generic(const struct bpf_prog *xdp_prog, struct sk_buff **pskb) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; if (xdp_prog) { struct xdp_buff xdp; u32 act; int err; bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); act = netif_receive_generic_xdp(pskb, &xdp, xdp_prog); if (act != XDP_PASS) { switch (act) { case XDP_REDIRECT: err = xdp_do_generic_redirect((*pskb)->dev, *pskb, &xdp, xdp_prog); if (err) goto out_redir; break; case XDP_TX: generic_xdp_tx(*pskb, xdp_prog); break; } bpf_net_ctx_clear(bpf_net_ctx); return XDP_DROP; } bpf_net_ctx_clear(bpf_net_ctx); } return XDP_PASS; out_redir: bpf_net_ctx_clear(bpf_net_ctx); kfree_skb_reason(*pskb, SKB_DROP_REASON_XDP); return XDP_DROP; } EXPORT_SYMBOL_GPL(do_xdp_generic); static int netif_rx_internal(struct sk_buff *skb) { int ret; net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_rx(skb); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu; rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu < 0) cpu = smp_processor_id(); ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); } else #endif { unsigned int qtail; ret = enqueue_to_backlog(skb, smp_processor_id(), &qtail); } return ret; } /** * __netif_rx - Slightly optimized version of netif_rx * @skb: buffer to post * * This behaves as netif_rx except that it does not disable bottom halves. * As a result this function may only be invoked from the interrupt context * (either hard or soft interrupt). */ int __netif_rx(struct sk_buff *skb) { int ret; lockdep_assert_once(hardirq_count() | softirq_count()); trace_netif_rx_entry(skb); ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); return ret; } EXPORT_SYMBOL(__netif_rx); /** * netif_rx - post buffer to the network code * @skb: buffer to post * * This function receives a packet from a device driver and queues it for * the upper (protocol) levels to process via the backlog NAPI device. It * always succeeds. The buffer may be dropped during processing for * congestion control or by the protocol layers. * The network buffer is passed via the backlog NAPI device. Modern NIC * driver should use NAPI and GRO. * This function can used from interrupt and from process context. The * caller from process context must not disable interrupts before invoking * this function. * * return values: * NET_RX_SUCCESS (no congestion) * NET_RX_DROP (packet was dropped) * */ int netif_rx(struct sk_buff *skb) { bool need_bh_off = !(hardirq_count() | softirq_count()); int ret; if (need_bh_off) local_bh_disable(); trace_netif_rx_entry(skb); ret = netif_rx_internal(skb); trace_netif_rx_exit(ret); if (need_bh_off) local_bh_enable(); return ret; } EXPORT_SYMBOL(netif_rx); static __latent_entropy void net_tx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); if (sd->completion_queue) { struct sk_buff *clist; local_irq_disable(); clist = sd->completion_queue; sd->completion_queue = NULL; local_irq_enable(); while (clist) { struct sk_buff *skb = clist; clist = clist->next; WARN_ON(refcount_read(&skb->users)); if (likely(get_kfree_skb_cb(skb)->reason == SKB_CONSUMED)) trace_consume_skb(skb, net_tx_action); else trace_kfree_skb(skb, net_tx_action, get_kfree_skb_cb(skb)->reason, NULL); if (skb->fclone != SKB_FCLONE_UNAVAILABLE) __kfree_skb(skb); else __napi_kfree_skb(skb, get_kfree_skb_cb(skb)->reason); } } if (sd->output_queue) { struct Qdisc *head; local_irq_disable(); head = sd->output_queue; sd->output_queue = NULL; sd->output_queue_tailp = &sd->output_queue; local_irq_enable(); rcu_read_lock(); while (head) { struct Qdisc *q = head; spinlock_t *root_lock = NULL; head = head->next_sched; /* We need to make sure head->next_sched is read * before clearing __QDISC_STATE_SCHED */ smp_mb__before_atomic(); if (!(q->flags & TCQ_F_NOLOCK)) { root_lock = qdisc_lock(q); spin_lock(root_lock); } else if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { /* There is a synchronize_net() between * STATE_DEACTIVATED flag being set and * qdisc_reset()/some_qdisc_is_busy() in * dev_deactivate(), so we can safely bail out * early here to avoid data race between * qdisc_deactivate() and some_qdisc_is_busy() * for lockless qdisc. */ clear_bit(__QDISC_STATE_SCHED, &q->state); continue; } clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); if (root_lock) spin_unlock(root_lock); } rcu_read_unlock(); } xfrm_dev_backlog(sd); } #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_ATM_LANE) /* This hook is defined here for ATM LANE */ int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) __read_mostly; EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif /** * netdev_is_rx_handler_busy - check if receive handler is registered * @dev: device to check * * Check if a receive handler is already registered for a given device. * Return true if there one. * * The caller must hold the rtnl_mutex. */ bool netdev_is_rx_handler_busy(struct net_device *dev) { ASSERT_RTNL(); return dev && rtnl_dereference(dev->rx_handler); } EXPORT_SYMBOL_GPL(netdev_is_rx_handler_busy); /** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for * @rx_handler: receive handler to register * @rx_handler_data: data pointer that is used by rx handler * * Register a receive handler for a device. This handler will then be * called from __netif_receive_skb. A negative errno code is returned * on a failure. * * The caller must hold the rtnl_mutex. * * For a general description of rx_handler, see enum rx_handler_result. */ int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data) { if (netdev_is_rx_handler_busy(dev)) return -EBUSY; if (dev->priv_flags & IFF_NO_RX_HANDLER) return -EINVAL; /* Note: rx_handler_data must be set before rx_handler */ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); rcu_assign_pointer(dev->rx_handler, rx_handler); return 0; } EXPORT_SYMBOL_GPL(netdev_rx_handler_register); /** * netdev_rx_handler_unregister - unregister receive handler * @dev: device to unregister a handler from * * Unregister a receive handler from a device. * * The caller must hold the rtnl_mutex. */ void netdev_rx_handler_unregister(struct net_device *dev) { ASSERT_RTNL(); RCU_INIT_POINTER(dev->rx_handler, NULL); /* a reader seeing a non NULL rx_handler in a rcu_read_lock() * section has a guarantee to see a non NULL rx_handler_data * as well. */ synchronize_net(); RCU_INIT_POINTER(dev->rx_handler_data, NULL); } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); /* * Limit the use of PFMEMALLOC reserves to those protocols that implement * the special handling of PFMEMALLOC skbs. */ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) { switch (skb->protocol) { case htons(ETH_P_ARP): case htons(ETH_P_IP): case htons(ETH_P_IPV6): case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): return true; default: return false; } } static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { if (nf_hook_ingress_active(skb)) { int ingress_retval; if (*pt_prev) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } rcu_read_lock(); ingress_retval = nf_hook_ingress(skb); rcu_read_unlock(); return ingress_retval; } return 0; } static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, struct packet_type **ppt_prev) { enum skb_drop_reason drop_reason = SKB_DROP_REASON_UNHANDLED_PROTO; struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; struct sk_buff *skb = *pskb; struct net_device *orig_dev; bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; net_timestamp_check(!READ_ONCE(net_hotdata.tstamp_prequeue), skb); trace_netif_receive_skb(skb); orig_dev = skb->dev; skb_reset_network_header(skb); #if !defined(CONFIG_DEBUG_NET) /* We plan to no longer reset the transport header here. * Give some time to fuzzers and dev build to catch bugs * in network stacks. */ if (!skb_transport_header_was_set(skb)) skb_reset_transport_header(skb); #endif skb_reset_mac_len(skb); pt_prev = NULL; another_round: skb->skb_iif = skb->dev->ifindex; __this_cpu_inc(softnet_data.processed); if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret2; migrate_disable(); ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), &skb); migrate_enable(); if (ret2 != XDP_PASS) { ret = NET_RX_DROP; goto out; } } if (eth_type_vlan(skb->protocol)) { skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; } if (skb_skip_tc_classify(skb)) goto skip_classify; if (pfmemalloc) goto skip_taps; list_for_each_entry_rcu(ptype, &dev_net_rcu(skb->dev)->ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } skip_taps: #ifdef CONFIG_NET_INGRESS if (static_branch_unlikely(&ingress_needed_key)) { bool another = false; nf_skip_egress(skb, true); skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, &another); if (another) goto another_round; if (!skb) goto out; nf_skip_egress(skb, false); if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) goto out; } #endif skb_reset_redirect(skb); skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) { drop_reason = SKB_DROP_REASON_PFMEMALLOC; goto drop; } if (skb_vlan_tag_present(skb)) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } if (vlan_do_receive(&skb)) goto another_round; else if (unlikely(!skb)) goto out; } rx_handler = rcu_dereference(skb->dev->rx_handler); if (rx_handler) { if (pt_prev) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: ret = NET_RX_SUCCESS; goto out; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: deliver_exact = true; break; case RX_HANDLER_PASS: break; default: BUG(); } } if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) { check_vlan_id: if (skb_vlan_tag_get_id(skb)) { /* Vlan id is non 0 and vlan_do_receive() above couldn't * find vlan device. */ skb->pkt_type = PACKET_OTHERHOST; } else if (eth_type_vlan(skb->protocol)) { /* Outer header is 802.1P with vlan 0, inner header is * 802.1Q or 802.1AD and vlan_do_receive() above could * not find vlan dev for vlan id 0. */ __vlan_hwaccel_clear_tag(skb); skb = skb_vlan_untag(skb); if (unlikely(!skb)) goto out; if (vlan_do_receive(&skb)) /* After stripping off 802.1P header with vlan 0 * vlan dev is found for inner header. */ goto another_round; else if (unlikely(!skb)) goto out; else /* We have stripped outer 802.1P vlan 0 header. * But could not find vlan dev. * check again for vlan id to set OTHERHOST. */ goto check_vlan_id; } /* Note: we might in the future use prio bits * and set skb->priority like in vlan_do_receive() * For the time being, just ignore Priority Code Point */ __vlan_hwaccel_clear_tag(skb); } type = skb->protocol; /* deliver only exact match when indicated */ if (likely(!deliver_exact)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &ptype_base[ntohs(type) & PTYPE_HASH_MASK]); /* orig_dev and skb->dev could belong to different netns; * Even in such case we need to traverse only the list * coming from skb->dev, as the ptype owner (packet socket) * will use dev_net(skb->dev) to do namespace filtering. */ deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &dev_net_rcu(skb->dev)->ptype_specific); } deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &orig_dev->ptype_specific); if (unlikely(skb->dev != orig_dev)) { deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type, &skb->dev->ptype_specific); } if (pt_prev) { *ppt_prev = pt_prev; } else { drop: if (!deliver_exact) dev_core_stats_rx_dropped_inc(skb->dev); else dev_core_stats_rx_nohandler_inc(skb->dev); kfree_skb_reason(skb, drop_reason); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) */ ret = NET_RX_DROP; } out: /* The invariant here is that if *ppt_prev is not NULL * then skb should also be non-NULL. * * Apparently *ppt_prev assignment above holds this invariant due to * skb dereferencing near it. */ *pskb = skb; return ret; } static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; int ret; ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (pt_prev) ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb, skb->dev, pt_prev, orig_dev); return ret; } /** * netif_receive_skb_core - special purpose version of netif_receive_skb * @skb: buffer to process * * More direct receive version of netif_receive_skb(). It should * only be used by callers that have a need to skip RPS and Generic XDP. * Caller must also take care of handling if ``(page_is_)pfmemalloc``. * * This function may only be called from softirq context and interrupts * should be enabled. * * Return values (usually ignored): * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ int netif_receive_skb_core(struct sk_buff *skb) { int ret; rcu_read_lock(); ret = __netif_receive_skb_one_core(skb, false); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(netif_receive_skb_core); static inline void __netif_receive_skb_list_ptype(struct list_head *head, struct packet_type *pt_prev, struct net_device *orig_dev) { struct sk_buff *skb, *next; if (!pt_prev) return; if (list_empty(head)) return; if (pt_prev->list_func != NULL) INDIRECT_CALL_INET(pt_prev->list_func, ipv6_list_rcv, ip_list_rcv, head, pt_prev, orig_dev); else list_for_each_entry_safe(skb, next, head, list) { skb_list_del_init(skb); pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } } static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc) { /* Fast-path assumptions: * - There is no RX handler. * - Only one packet_type matches. * If either of these fails, we will end up doing some per-packet * processing in-line, then handling the 'last ptype' for the whole * sublist. This can't cause out-of-order delivery to any single ptype, * because the 'last ptype' must be constant across the sublist, and all * other ptypes are handled per-packet. */ /* Current (common) ptype of sublist */ struct packet_type *pt_curr = NULL; /* Current (common) orig_dev of sublist */ struct net_device *od_curr = NULL; struct sk_buff *skb, *next; LIST_HEAD(sublist); list_for_each_entry_safe(skb, next, head, list) { struct net_device *orig_dev = skb->dev; struct packet_type *pt_prev = NULL; skb_list_del_init(skb); __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (!pt_prev) continue; if (pt_curr != pt_prev || od_curr != orig_dev) { /* dispatch old sublist */ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); /* start new sublist */ INIT_LIST_HEAD(&sublist); pt_curr = pt_prev; od_curr = orig_dev; } list_add_tail(&skb->list, &sublist); } /* dispatch final sublist */ __netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr); } static int __netif_receive_skb(struct sk_buff *skb) { int ret; if (sk_memalloc_socks() && skb_pfmemalloc(skb)) { unsigned int noreclaim_flag; /* * PFMEMALLOC skbs are special, they should * - be delivered to SOCK_MEMALLOC sockets only * - stay away from userspace * - have bounded memory usage * * Use PF_MEMALLOC as this saves us from propagating the allocation * context down to all allocation sites. */ noreclaim_flag = memalloc_noreclaim_save(); ret = __netif_receive_skb_one_core(skb, true); memalloc_noreclaim_restore(noreclaim_flag); } else ret = __netif_receive_skb_one_core(skb, false); return ret; } static void __netif_receive_skb_list(struct list_head *head) { unsigned long noreclaim_flag = 0; struct sk_buff *skb, *next; bool pfmemalloc = false; /* Is current sublist PF_MEMALLOC? */ list_for_each_entry_safe(skb, next, head, list) { if ((sk_memalloc_socks() && skb_pfmemalloc(skb)) != pfmemalloc) { struct list_head sublist; /* Handle the previous sublist */ list_cut_before(&sublist, head, &skb->list); if (!list_empty(&sublist)) __netif_receive_skb_list_core(&sublist, pfmemalloc); pfmemalloc = !pfmemalloc; /* See comments in __netif_receive_skb */ if (pfmemalloc) noreclaim_flag = memalloc_noreclaim_save(); else memalloc_noreclaim_restore(noreclaim_flag); } } /* Handle the remaining sublist */ if (!list_empty(head)) __netif_receive_skb_list_core(head, pfmemalloc); /* Restore pflags */ if (pfmemalloc) memalloc_noreclaim_restore(noreclaim_flag); } static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) { struct bpf_prog *old = rtnl_dereference(dev->xdp_prog); struct bpf_prog *new = xdp->prog; int ret = 0; switch (xdp->command) { case XDP_SETUP_PROG: rcu_assign_pointer(dev->xdp_prog, new); if (old) bpf_prog_put(old); if (old && !new) { static_branch_dec(&generic_xdp_needed_key); } else if (new && !old) { static_branch_inc(&generic_xdp_needed_key); netif_disable_lro(dev); dev_disable_gro_hw(dev); } break; default: ret = -EINVAL; break; } return ret; } static int netif_receive_skb_internal(struct sk_buff *skb) { int ret; net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; rcu_read_lock(); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); return ret; } } #endif ret = __netif_receive_skb(skb); rcu_read_unlock(); return ret; } void netif_receive_skb_list_internal(struct list_head *head) { struct sk_buff *skb, *next; LIST_HEAD(sublist); list_for_each_entry_safe(skb, next, head, list) { net_timestamp_check(READ_ONCE(net_hotdata.tstamp_prequeue), skb); skb_list_del_init(skb); if (!skb_defer_rx_timestamp(skb)) list_add_tail(&skb->list, &sublist); } list_splice_init(&sublist, head); rcu_read_lock(); #ifdef CONFIG_RPS if (static_branch_unlikely(&rps_needed)) { list_for_each_entry_safe(skb, next, head, list) { struct rps_dev_flow voidflow, *rflow = &voidflow; int cpu = get_rps_cpu(skb->dev, skb, &rflow); if (cpu >= 0) { /* Will be handled, remove from list */ skb_list_del_init(skb); enqueue_to_backlog(skb, cpu, &rflow->last_qtail); } } } #endif __netif_receive_skb_list(head); rcu_read_unlock(); } /** * netif_receive_skb - process receive buffer from network * @skb: buffer to process * * netif_receive_skb() is the main receive data processing function. * It always succeeds. The buffer may be dropped during processing * for congestion control or by the protocol layers. * * This function may only be called from softirq context and interrupts * should be enabled. * * Return values (usually ignored): * NET_RX_SUCCESS: no congestion * NET_RX_DROP: packet was dropped */ int netif_receive_skb(struct sk_buff *skb) { int ret; trace_netif_receive_skb_entry(skb); ret = netif_receive_skb_internal(skb); trace_netif_receive_skb_exit(ret); return ret; } EXPORT_SYMBOL(netif_receive_skb); /** * netif_receive_skb_list - process many receive buffers from network * @head: list of skbs to process. * * Since return value of netif_receive_skb() is normally ignored, and * wouldn't be meaningful for a list, this function returns void. * * This function may only be called from softirq context and interrupts * should be enabled. */ void netif_receive_skb_list(struct list_head *head) { struct sk_buff *skb; if (list_empty(head)) return; if (trace_netif_receive_skb_list_entry_enabled()) { list_for_each_entry(skb, head, list) trace_netif_receive_skb_list_entry(skb); } netif_receive_skb_list_internal(head); trace_netif_receive_skb_list_exit(0); } EXPORT_SYMBOL(netif_receive_skb_list); /* Network device is going away, flush any packets still pending */ static void flush_backlog(struct work_struct *work) { struct sk_buff *skb, *tmp; struct sk_buff_head list; struct softnet_data *sd; __skb_queue_head_init(&list); local_bh_disable(); sd = this_cpu_ptr(&softnet_data); backlog_lock_irq_disable(sd); skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); __skb_queue_tail(&list, skb); rps_input_queue_head_incr(sd); } } backlog_unlock_irq_enable(sd); local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_walk_safe(&sd->process_queue, skb, tmp) { if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->process_queue); __skb_queue_tail(&list, skb); rps_input_queue_head_incr(sd); } } local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); local_bh_enable(); __skb_queue_purge_reason(&list, SKB_DROP_REASON_DEV_READY); } static bool flush_required(int cpu) { #if IS_ENABLED(CONFIG_RPS) struct softnet_data *sd = &per_cpu(softnet_data, cpu); bool do_flush; backlog_lock_irq_disable(sd); /* as insertion into process_queue happens with the rps lock held, * process_queue access may race only with dequeue */ do_flush = !skb_queue_empty(&sd->input_pkt_queue) || !skb_queue_empty_lockless(&sd->process_queue); backlog_unlock_irq_enable(sd); return do_flush; #endif /* without RPS we can't safely check input_pkt_queue: during a * concurrent remote skb_queue_splice() we can detect as empty both * input_pkt_queue and process_queue even if the latter could end-up * containing a lot of packets. */ return true; } struct flush_backlogs { cpumask_t flush_cpus; struct work_struct w[]; }; static struct flush_backlogs *flush_backlogs_alloc(void) { return kmalloc(struct_size_t(struct flush_backlogs, w, nr_cpu_ids), GFP_KERNEL); } static struct flush_backlogs *flush_backlogs_fallback; static DEFINE_MUTEX(flush_backlogs_mutex); static void flush_all_backlogs(void) { struct flush_backlogs *ptr = flush_backlogs_alloc(); unsigned int cpu; if (!ptr) { mutex_lock(&flush_backlogs_mutex); ptr = flush_backlogs_fallback; } cpumask_clear(&ptr->flush_cpus); cpus_read_lock(); for_each_online_cpu(cpu) { if (flush_required(cpu)) { INIT_WORK(&ptr->w[cpu], flush_backlog); queue_work_on(cpu, system_highpri_wq, &ptr->w[cpu]); __cpumask_set_cpu(cpu, &ptr->flush_cpus); } } /* we can have in flight packet[s] on the cpus we are not flushing, * synchronize_net() in unregister_netdevice_many() will take care of * them. */ for_each_cpu(cpu, &ptr->flush_cpus) flush_work(&ptr->w[cpu]); cpus_read_unlock(); if (ptr != flush_backlogs_fallback) kfree(ptr); else mutex_unlock(&flush_backlogs_mutex); } static void net_rps_send_ipi(struct softnet_data *remsd) { #ifdef CONFIG_RPS while (remsd) { struct softnet_data *next = remsd->rps_ipi_next; if (cpu_online(remsd->cpu)) smp_call_function_single_async(remsd->cpu, &remsd->csd); remsd = next; } #endif } /* * net_rps_action_and_irq_enable sends any pending IPI's for rps. * Note: called with local irq disabled, but exits with local irq enabled. */ static void net_rps_action_and_irq_enable(struct softnet_data *sd) { #ifdef CONFIG_RPS struct softnet_data *remsd = sd->rps_ipi_list; if (!use_backlog_threads() && remsd) { sd->rps_ipi_list = NULL; local_irq_enable(); /* Send pending IPI's to kick RPS processing on remote cpus. */ net_rps_send_ipi(remsd); } else #endif local_irq_enable(); } static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) { #ifdef CONFIG_RPS return !use_backlog_threads() && sd->rps_ipi_list; #else return false; #endif } static int process_backlog(struct napi_struct *napi, int quota) { struct softnet_data *sd = container_of(napi, struct softnet_data, backlog); bool again = true; int work = 0; /* Check if we have pending ipi, its better to send them now, * not waiting net_rx_action() end. */ if (sd_has_rps_ipi_waiting(sd)) { local_irq_disable(); net_rps_action_and_irq_enable(sd); } napi->weight = READ_ONCE(net_hotdata.dev_rx_weight); while (again) { struct sk_buff *skb; local_lock_nested_bh(&softnet_data.process_queue_bh_lock); while ((skb = __skb_dequeue(&sd->process_queue))) { local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); rcu_read_lock(); __netif_receive_skb(skb); rcu_read_unlock(); if (++work >= quota) { rps_input_queue_head_add(sd, work); return work; } local_lock_nested_bh(&softnet_data.process_queue_bh_lock); } local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); backlog_lock_irq_disable(sd); if (skb_queue_empty(&sd->input_pkt_queue)) { /* * Inline a custom version of __napi_complete(). * only current cpu owns and manipulates this napi, * and NAPI_STATE_SCHED is the only possible flag set * on backlog. * We can use a plain write instead of clear_bit(), * and we dont need an smp_mb() memory barrier. */ napi->state &= NAPIF_STATE_THREADED; again = false; } else { local_lock_nested_bh(&softnet_data.process_queue_bh_lock); skb_queue_splice_tail_init(&sd->input_pkt_queue, &sd->process_queue); local_unlock_nested_bh(&softnet_data.process_queue_bh_lock); } backlog_unlock_irq_enable(sd); } if (work) rps_input_queue_head_add(sd, work); return work; } /** * __napi_schedule - schedule for receive * @n: entry to schedule * * The entry's receive function will be scheduled to run. * Consider using __napi_schedule_irqoff() if hard irqs are masked. */ void __napi_schedule(struct napi_struct *n) { unsigned long flags; local_irq_save(flags); ____napi_schedule(this_cpu_ptr(&softnet_data), n); local_irq_restore(flags); } EXPORT_SYMBOL(__napi_schedule); /** * napi_schedule_prep - check if napi can be scheduled * @n: napi context * * Test if NAPI routine is already running, and if not mark * it as running. This is used as a condition variable to * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ bool napi_schedule_prep(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); do { if (unlikely(val & NAPIF_STATE_DISABLE)) return false; new = val | NAPIF_STATE_SCHED; /* Sets STATE_MISSED bit if STATE_SCHED was already set * This was suggested by Alexander Duyck, as compiler * emits better code than : * if (val & NAPIF_STATE_SCHED) * new |= NAPIF_STATE_MISSED; */ new |= (val & NAPIF_STATE_SCHED) / NAPIF_STATE_SCHED * NAPIF_STATE_MISSED; } while (!try_cmpxchg(&n->state, &val, new)); return !(val & NAPIF_STATE_SCHED); } EXPORT_SYMBOL(napi_schedule_prep); /** * __napi_schedule_irqoff - schedule for receive * @n: entry to schedule * * Variant of __napi_schedule() assuming hard irqs are masked. * * On PREEMPT_RT enabled kernels this maps to __napi_schedule() * because the interrupt disabled assumption might not be true * due to force-threaded interrupts and spinlock substitution. */ void __napi_schedule_irqoff(struct napi_struct *n) { if (!IS_ENABLED(CONFIG_PREEMPT_RT)) ____napi_schedule(this_cpu_ptr(&softnet_data), n); else __napi_schedule(n); } EXPORT_SYMBOL(__napi_schedule_irqoff); bool napi_complete_done(struct napi_struct *n, int work_done) { unsigned long flags, val, new, timeout = 0; bool ret = true; /* * 1) Don't let napi dequeue from the cpu poll list * just in case its running on a different cpu. * 2) If we are busy polling, do nothing here, we have * the guarantee we will be called later. */ if (unlikely(n->state & (NAPIF_STATE_NPSVC | NAPIF_STATE_IN_BUSY_POLL))) return false; if (work_done) { if (n->gro.bitmask) timeout = napi_get_gro_flush_timeout(n); n->defer_hard_irqs_count = napi_get_defer_hard_irqs(n); } if (n->defer_hard_irqs_count > 0) { n->defer_hard_irqs_count--; timeout = napi_get_gro_flush_timeout(n); if (timeout) ret = false; } /* * When the NAPI instance uses a timeout and keeps postponing * it, we need to bound somehow the time packets are kept in * the GRO layer. */ gro_flush_normal(&n->gro, !!timeout); if (unlikely(!list_empty(&n->poll_list))) { /* If n->poll_list is not empty, we need to mask irqs */ local_irq_save(flags); list_del_init(&n->poll_list); local_irq_restore(flags); } WRITE_ONCE(n->list_owner, -1); val = READ_ONCE(n->state); do { WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | NAPIF_STATE_SCHED_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); /* If STATE_MISSED was set, leave STATE_SCHED set, * because we will call napi->poll() one more time. * This C code was suggested by Alexander Duyck to help gcc. */ new |= (val & NAPIF_STATE_MISSED) / NAPIF_STATE_MISSED * NAPIF_STATE_SCHED; } while (!try_cmpxchg(&n->state, &val, new)); if (unlikely(val & NAPIF_STATE_MISSED)) { __napi_schedule(n); return false; } if (timeout) hrtimer_start(&n->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); return ret; } EXPORT_SYMBOL(napi_complete_done); static void skb_defer_free_flush(struct softnet_data *sd) { struct sk_buff *skb, *next; /* Paired with WRITE_ONCE() in skb_attempt_defer_free() */ if (!READ_ONCE(sd->defer_list)) return; spin_lock(&sd->defer_lock); skb = sd->defer_list; sd->defer_list = NULL; sd->defer_count = 0; spin_unlock(&sd->defer_lock); while (skb != NULL) { next = skb->next; napi_consume_skb(skb, 1); skb = next; } } #if defined(CONFIG_NET_RX_BUSY_POLL) static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) { if (!skip_schedule) { gro_normal_list(&napi->gro); __napi_schedule(napi); return; } /* Flush too old packets. If HZ < 1000, flush all packets */ gro_flush_normal(&napi->gro, HZ >= 1000); clear_bit(NAPI_STATE_SCHED, &napi->state); } enum { NAPI_F_PREFER_BUSY_POLL = 1, NAPI_F_END_ON_RESCHED = 2, }; static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, unsigned flags, u16 budget) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; bool skip_schedule = false; unsigned long timeout; int rc; /* Busy polling means there is a high chance device driver hard irq * could not grab NAPI_STATE_SCHED, and that NAPI_STATE_MISSED was * set in napi_schedule_prep(). * Since we are about to call napi->poll() once more, we can safely * clear NAPI_STATE_MISSED. * * Note: x86 could use a single "lock and ..." instruction * to perform these two clear_bit() */ clear_bit(NAPI_STATE_MISSED, &napi->state); clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state); local_bh_disable(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (flags & NAPI_F_PREFER_BUSY_POLL) { napi->defer_hard_irqs_count = napi_get_defer_hard_irqs(napi); timeout = napi_get_gro_flush_timeout(napi); if (napi->defer_hard_irqs_count && timeout) { hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); skip_schedule = true; } } /* All we really want here is to re-enable device interrupts. * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ rc = napi->poll(napi, budget); /* We can't gro_normal_list() here, because napi->poll() might have * rearmed the napi (napi_complete_done()) in which case it could * already be running on another CPU. */ trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); if (rc == budget) __busy_poll_stop(napi, skip_schedule); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); } static void __napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, unsigned flags, u16 budget) { unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; void *have_poll_lock = NULL; struct napi_struct *napi; WARN_ON_ONCE(!rcu_read_lock_held()); restart: napi_poll = NULL; napi = napi_by_id(napi_id); if (!napi) return; if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_disable(); for (;;) { int work = 0; local_bh_disable(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); if (!napi_poll) { unsigned long val = READ_ONCE(napi->state); /* If multiple threads are competing for this napi, * we avoid dirtying napi->state as much as we can. */ if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED | NAPIF_STATE_IN_BUSY_POLL)) { if (flags & NAPI_F_PREFER_BUSY_POLL) set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; } if (cmpxchg(&napi->state, val, val | NAPIF_STATE_IN_BUSY_POLL | NAPIF_STATE_SCHED) != val) { if (flags & NAPI_F_PREFER_BUSY_POLL) set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; } have_poll_lock = netpoll_poll_lock(napi); napi_poll = napi->poll; } work = napi_poll(napi, budget); trace_napi_poll(napi, work, budget); gro_normal_list(&napi->gro); count: if (work > 0) __NET_ADD_STATS(dev_net(napi->dev), LINUX_MIB_BUSYPOLLRXPACKETS, work); skb_defer_free_flush(this_cpu_ptr(&softnet_data)); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); if (!loop_end || loop_end(loop_end_arg, start_time)) break; if (unlikely(need_resched())) { if (flags & NAPI_F_END_ON_RESCHED) break; if (napi_poll) busy_poll_stop(napi, have_poll_lock, flags, budget); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); rcu_read_unlock(); cond_resched(); rcu_read_lock(); if (loop_end(loop_end_arg, start_time)) return; goto restart; } cpu_relax(); } if (napi_poll) busy_poll_stop(napi, have_poll_lock, flags, budget); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) preempt_enable(); } void napi_busy_loop_rcu(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned flags = NAPI_F_END_ON_RESCHED; if (prefer_busy_poll) flags |= NAPI_F_PREFER_BUSY_POLL; __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget); } void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned flags = prefer_busy_poll ? NAPI_F_PREFER_BUSY_POLL : 0; rcu_read_lock(); __napi_busy_loop(napi_id, loop_end, loop_end_arg, flags, budget); rcu_read_unlock(); } EXPORT_SYMBOL(napi_busy_loop); void napi_suspend_irqs(unsigned int napi_id) { struct napi_struct *napi; rcu_read_lock(); napi = napi_by_id(napi_id); if (napi) { unsigned long timeout = napi_get_irq_suspend_timeout(napi); if (timeout) hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); } rcu_read_unlock(); } void napi_resume_irqs(unsigned int napi_id) { struct napi_struct *napi; rcu_read_lock(); napi = napi_by_id(napi_id); if (napi) { /* If irq_suspend_timeout is set to 0 between the call to * napi_suspend_irqs and now, the original value still * determines the safety timeout as intended and napi_watchdog * will resume irq processing. */ if (napi_get_irq_suspend_timeout(napi)) { local_bh_disable(); napi_schedule(napi); local_bh_enable(); } } rcu_read_unlock(); } #endif /* CONFIG_NET_RX_BUSY_POLL */ static void __napi_hash_add_with_id(struct napi_struct *napi, unsigned int napi_id) { napi->gro.cached_napi_id = napi_id; WRITE_ONCE(napi->napi_id, napi_id); hlist_add_head_rcu(&napi->napi_hash_node, &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]); } static void napi_hash_add_with_id(struct napi_struct *napi, unsigned int napi_id) { unsigned long flags; spin_lock_irqsave(&napi_hash_lock, flags); WARN_ON_ONCE(napi_by_id(napi_id)); __napi_hash_add_with_id(napi, napi_id); spin_unlock_irqrestore(&napi_hash_lock, flags); } static void napi_hash_add(struct napi_struct *napi) { unsigned long flags; if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state)) return; spin_lock_irqsave(&napi_hash_lock, flags); /* 0..NR_CPUS range is reserved for sender_cpu use */ do { if (unlikely(!napi_id_valid(++napi_gen_id))) napi_gen_id = MIN_NAPI_ID; } while (napi_by_id(napi_gen_id)); __napi_hash_add_with_id(napi, napi_gen_id); spin_unlock_irqrestore(&napi_hash_lock, flags); } /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi */ static void napi_hash_del(struct napi_struct *napi) { unsigned long flags; spin_lock_irqsave(&napi_hash_lock, flags); hlist_del_init_rcu(&napi->napi_hash_node); spin_unlock_irqrestore(&napi_hash_lock, flags); } static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) { struct napi_struct *napi; napi = container_of(timer, struct napi_struct, timer); /* Note : we use a relaxed variant of napi_schedule_prep() not setting * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ if (!napi_disable_pending(napi) && !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) { clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); __napi_schedule_irqoff(napi); } return HRTIMER_NORESTART; } static void napi_stop_kthread(struct napi_struct *napi) { unsigned long val, new; /* Wait until the napi STATE_THREADED is unset. */ while (true) { val = READ_ONCE(napi->state); /* If napi kthread own this napi or the napi is idle, * STATE_THREADED can be unset here. */ if ((val & NAPIF_STATE_SCHED_THREADED) || !(val & NAPIF_STATE_SCHED)) { new = val & (~NAPIF_STATE_THREADED); } else { msleep(20); continue; } if (try_cmpxchg(&napi->state, &val, new)) break; } /* Once STATE_THREADED is unset, wait for SCHED_THREADED to be unset by * the kthread. */ while (true) { if (!test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) break; msleep(20); } kthread_stop(napi->thread); napi->thread = NULL; } int napi_set_threaded(struct napi_struct *napi, enum netdev_napi_threaded threaded) { if (threaded) { if (!napi->thread) { int err = napi_kthread_create(napi); if (err) return err; } } if (napi->config) napi->config->threaded = threaded; /* Setting/unsetting threaded mode on a napi might not immediately * take effect, if the current napi instance is actively being * polled. In this case, the switch between threaded mode and * softirq mode will happen in the next round of napi_schedule(). * This should not cause hiccups/stalls to the live traffic. */ if (!threaded && napi->thread) { napi_stop_kthread(napi); } else { /* Make sure kthread is created before THREADED bit is set. */ smp_mb__before_atomic(); assign_bit(NAPI_STATE_THREADED, &napi->state, threaded); } return 0; } int netif_set_threaded(struct net_device *dev, enum netdev_napi_threaded threaded) { struct napi_struct *napi; int i, err = 0; netdev_assert_locked_or_invisible(dev); if (threaded) { list_for_each_entry(napi, &dev->napi_list, dev_list) { if (!napi->thread) { err = napi_kthread_create(napi); if (err) { threaded = NETDEV_NAPI_THREADED_DISABLED; break; } } } } WRITE_ONCE(dev->threaded, threaded); /* The error should not occur as the kthreads are already created. */ list_for_each_entry(napi, &dev->napi_list, dev_list) WARN_ON_ONCE(napi_set_threaded(napi, threaded)); /* Override the config for all NAPIs even if currently not listed */ for (i = 0; i < dev->num_napi_configs; i++) dev->napi_config[i].threaded = threaded; return err; } /** * netif_threaded_enable() - enable threaded NAPIs * @dev: net_device instance * * Enable threaded mode for the NAPI instances of the device. This may be useful * for devices where multiple NAPI instances get scheduled by a single * interrupt. Threaded NAPI allows moving the NAPI processing to cores other * than the core where IRQ is mapped. * * This function should be called before @dev is registered. */ void netif_threaded_enable(struct net_device *dev) { WARN_ON_ONCE(netif_set_threaded(dev, NETDEV_NAPI_THREADED_ENABLED)); } EXPORT_SYMBOL(netif_threaded_enable); /** * netif_queue_set_napi - Associate queue with the napi * @dev: device to which NAPI and queue belong * @queue_index: Index of queue * @type: queue type as RX or TX * @napi: NAPI context, pass NULL to clear previously set NAPI * * Set queue with its corresponding napi context. This should be done after * registering the NAPI handler for the queue-vector and the queues have been * mapped to the corresponding interrupt vector. */ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, enum netdev_queue_type type, struct napi_struct *napi) { struct netdev_rx_queue *rxq; struct netdev_queue *txq; if (WARN_ON_ONCE(napi && !napi->dev)) return; netdev_ops_assert_locked_or_invisible(dev); switch (type) { case NETDEV_QUEUE_TYPE_RX: rxq = __netif_get_rx_queue(dev, queue_index); rxq->napi = napi; return; case NETDEV_QUEUE_TYPE_TX: txq = netdev_get_tx_queue(dev, queue_index); txq->napi = napi; return; default: return; } } EXPORT_SYMBOL(netif_queue_set_napi); static void netif_napi_irq_notify(struct irq_affinity_notify *notify, const cpumask_t *mask) { struct napi_struct *napi = container_of(notify, struct napi_struct, notify); #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap; int err; #endif if (napi->config && napi->dev->irq_affinity_auto) cpumask_copy(&napi->config->affinity_mask, mask); #ifdef CONFIG_RFS_ACCEL if (napi->dev->rx_cpu_rmap_auto) { err = cpu_rmap_update(rmap, napi->napi_rmap_idx, mask); if (err) netdev_warn(napi->dev, "RMAP update failed (%d)\n", err); } #endif } #ifdef CONFIG_RFS_ACCEL static void netif_napi_affinity_release(struct kref *ref) { struct napi_struct *napi = container_of(ref, struct napi_struct, notify.kref); struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap; netdev_assert_locked(napi->dev); WARN_ON(test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state)); if (!napi->dev->rx_cpu_rmap_auto) return; rmap->obj[napi->napi_rmap_idx] = NULL; napi->napi_rmap_idx = -1; cpu_rmap_put(rmap); } int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs) { if (dev->rx_cpu_rmap_auto) return 0; dev->rx_cpu_rmap = alloc_irq_cpu_rmap(num_irqs); if (!dev->rx_cpu_rmap) return -ENOMEM; dev->rx_cpu_rmap_auto = true; return 0; } EXPORT_SYMBOL(netif_enable_cpu_rmap); static void netif_del_cpu_rmap(struct net_device *dev) { struct cpu_rmap *rmap = dev->rx_cpu_rmap; if (!dev->rx_cpu_rmap_auto) return; /* Free the rmap */ cpu_rmap_put(rmap); dev->rx_cpu_rmap = NULL; dev->rx_cpu_rmap_auto = false; } #else static void netif_napi_affinity_release(struct kref *ref) { } int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs) { return 0; } EXPORT_SYMBOL(netif_enable_cpu_rmap); static void netif_del_cpu_rmap(struct net_device *dev) { } #endif void netif_set_affinity_auto(struct net_device *dev) { unsigned int i, maxqs, numa; maxqs = max(dev->num_tx_queues, dev->num_rx_queues); numa = dev_to_node(&dev->dev); for (i = 0; i < maxqs; i++) cpumask_set_cpu(cpumask_local_spread(i, numa), &dev->napi_config[i].affinity_mask); dev->irq_affinity_auto = true; } EXPORT_SYMBOL(netif_set_affinity_auto); void netif_napi_set_irq_locked(struct napi_struct *napi, int irq) { int rc; netdev_assert_locked_or_invisible(napi->dev); if (napi->irq == irq) return; /* Remove existing resources */ if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state)) irq_set_affinity_notifier(napi->irq, NULL); napi->irq = irq; if (irq < 0 || (!napi->dev->rx_cpu_rmap_auto && !napi->dev->irq_affinity_auto)) return; /* Abort for buggy drivers */ if (napi->dev->irq_affinity_auto && WARN_ON_ONCE(!napi->config)) return; #ifdef CONFIG_RFS_ACCEL if (napi->dev->rx_cpu_rmap_auto) { rc = cpu_rmap_add(napi->dev->rx_cpu_rmap, napi); if (rc < 0) return; cpu_rmap_get(napi->dev->rx_cpu_rmap); napi->napi_rmap_idx = rc; } #endif /* Use core IRQ notifier */ napi->notify.notify = netif_napi_irq_notify; napi->notify.release = netif_napi_affinity_release; rc = irq_set_affinity_notifier(irq, &napi->notify); if (rc) { netdev_warn(napi->dev, "Unable to set IRQ notifier (%d)\n", rc); goto put_rmap; } set_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state); return; put_rmap: #ifdef CONFIG_RFS_ACCEL if (napi->dev->rx_cpu_rmap_auto) { napi->dev->rx_cpu_rmap->obj[napi->napi_rmap_idx] = NULL; cpu_rmap_put(napi->dev->rx_cpu_rmap); napi->napi_rmap_idx = -1; } #endif napi->notify.notify = NULL; napi->notify.release = NULL; } EXPORT_SYMBOL(netif_napi_set_irq_locked); static void napi_restore_config(struct napi_struct *n) { n->defer_hard_irqs = n->config->defer_hard_irqs; n->gro_flush_timeout = n->config->gro_flush_timeout; n->irq_suspend_timeout = n->config->irq_suspend_timeout; if (n->dev->irq_affinity_auto && test_bit(NAPI_STATE_HAS_NOTIFIER, &n->state)) irq_set_affinity(n->irq, &n->config->affinity_mask); /* a NAPI ID might be stored in the config, if so use it. if not, use * napi_hash_add to generate one for us. */ if (n->config->napi_id) { napi_hash_add_with_id(n, n->config->napi_id); } else { napi_hash_add(n); n->config->napi_id = n->napi_id; } WARN_ON_ONCE(napi_set_threaded(n, n->config->threaded)); } static void napi_save_config(struct napi_struct *n) { n->config->defer_hard_irqs = n->defer_hard_irqs; n->config->gro_flush_timeout = n->gro_flush_timeout; n->config->irq_suspend_timeout = n->irq_suspend_timeout; napi_hash_del(n); } /* Netlink wants the NAPI list to be sorted by ID, if adding a NAPI which will * inherit an existing ID try to insert it at the right position. */ static void netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi) { unsigned int new_id, pos_id; struct list_head *higher; struct napi_struct *pos; new_id = UINT_MAX; if (napi->config && napi->config->napi_id) new_id = napi->config->napi_id; higher = &dev->napi_list; list_for_each_entry(pos, &dev->napi_list, dev_list) { if (napi_id_valid(pos->napi_id)) pos_id = pos->napi_id; else if (pos->config) pos_id = pos->config->napi_id; else pos_id = UINT_MAX; if (pos_id <= new_id) break; higher = &pos->dev_list; } list_add_rcu(&napi->dev_list, higher); /* adds after higher */ } /* Double check that napi_get_frags() allocates skbs with * skb->head being backed by slab, not a page fragment. * This is to make sure bug fixed in 3226b158e67c * ("net: avoid 32 x truesize under-estimation for tiny skbs") * does not accidentally come back. */ static void napi_get_frags_check(struct napi_struct *napi) { struct sk_buff *skb; local_bh_disable(); skb = napi_get_frags(napi); WARN_ON_ONCE(skb && skb->head_frag); napi_free_frags(napi); local_bh_enable(); } void netif_napi_add_weight_locked(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { netdev_assert_locked(dev); if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) return; INIT_LIST_HEAD(&napi->poll_list); INIT_HLIST_NODE(&napi->napi_hash_node); hrtimer_setup(&napi->timer, napi_watchdog, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); gro_init(&napi->gro); napi->skb = NULL; napi->poll = poll; if (weight > NAPI_POLL_WEIGHT) netdev_err_once(dev, "%s() called with weight %d\n", __func__, weight); napi->weight = weight; napi->dev = dev; #ifdef CONFIG_NETPOLL napi->poll_owner = -1; #endif napi->list_owner = -1; set_bit(NAPI_STATE_SCHED, &napi->state); set_bit(NAPI_STATE_NPSVC, &napi->state); netif_napi_dev_list_add(dev, napi); /* default settings from sysfs are applied to all NAPIs. any per-NAPI * configuration will be loaded in napi_enable */ napi_set_defer_hard_irqs(napi, READ_ONCE(dev->napi_defer_hard_irqs)); napi_set_gro_flush_timeout(napi, READ_ONCE(dev->gro_flush_timeout)); napi_get_frags_check(napi); /* Create kthread for this napi if dev->threaded is set. * Clear dev->threaded if kthread creation failed so that * threaded mode will not be enabled in napi_enable(). */ if (napi_get_threaded_config(dev, napi)) if (napi_kthread_create(napi)) dev->threaded = NETDEV_NAPI_THREADED_DISABLED; netif_napi_set_irq_locked(napi, -1); } EXPORT_SYMBOL(netif_napi_add_weight_locked); void napi_disable_locked(struct napi_struct *n) { unsigned long val, new; might_sleep(); netdev_assert_locked(n->dev); set_bit(NAPI_STATE_DISABLE, &n->state); val = READ_ONCE(n->state); do { while (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { usleep_range(20, 200); val = READ_ONCE(n->state); } new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); } while (!try_cmpxchg(&n->state, &val, new)); hrtimer_cancel(&n->timer); if (n->config) napi_save_config(n); else napi_hash_del(n); clear_bit(NAPI_STATE_DISABLE, &n->state); } EXPORT_SYMBOL(napi_disable_locked); /** * napi_disable() - prevent NAPI from scheduling * @n: NAPI context * * Stop NAPI from being scheduled on this context. * Waits till any outstanding processing completes. * Takes netdev_lock() for associated net_device. */ void napi_disable(struct napi_struct *n) { netdev_lock(n->dev); napi_disable_locked(n); netdev_unlock(n->dev); } EXPORT_SYMBOL(napi_disable); void napi_enable_locked(struct napi_struct *n) { unsigned long new, val = READ_ONCE(n->state); if (n->config) napi_restore_config(n); else napi_hash_add(n); do { BUG_ON(!test_bit(NAPI_STATE_SCHED, &val)); new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC); if (n->dev->threaded && n->thread) new |= NAPIF_STATE_THREADED; } while (!try_cmpxchg(&n->state, &val, new)); } EXPORT_SYMBOL(napi_enable_locked); /** * napi_enable() - enable NAPI scheduling * @n: NAPI context * * Enable scheduling of a NAPI instance. * Must be paired with napi_disable(). * Takes netdev_lock() for associated net_device. */ void napi_enable(struct napi_struct *n) { netdev_lock(n->dev); napi_enable_locked(n); netdev_unlock(n->dev); } EXPORT_SYMBOL(napi_enable); /* Must be called in process context */ void __netif_napi_del_locked(struct napi_struct *napi) { netdev_assert_locked(napi->dev); if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) return; /* Make sure NAPI is disabled (or was never enabled). */ WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state)); if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state)) irq_set_affinity_notifier(napi->irq, NULL); if (napi->config) { napi->index = -1; napi->config = NULL; } list_del_rcu(&napi->dev_list); napi_free_frags(napi); gro_cleanup(&napi->gro); if (napi->thread) { kthread_stop(napi->thread); napi->thread = NULL; } } EXPORT_SYMBOL(__netif_napi_del_locked); static int __napi_poll(struct napi_struct *n, bool *repoll) { int work, weight; weight = n->weight; /* This NAPI_STATE_SCHED test is for avoiding a race * with netpoll's poll_napi(). Only the entity which * obtains the lock and sees NAPI_STATE_SCHED set will * actually make the ->poll() call. Therefore we avoid * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; if (napi_is_scheduled(n)) { work = n->poll(n, weight); trace_napi_poll(n, work, weight); xdp_do_check_flushed(n); } if (unlikely(work > weight)) netdev_err_once(n->dev, "NAPI poll function %pS returned %d, exceeding its budget of %d.\n", n->poll, work, weight); if (likely(work < weight)) return work; /* Drivers must not modify the NAPI state if they * consume the entire weight. In such cases this code * still "owns" the NAPI instance and therefore can * move the instance around on the list at-will. */ if (unlikely(napi_disable_pending(n))) { napi_complete(n); return work; } /* The NAPI context has more processing work, but busy-polling * is preferred. Exit early. */ if (napi_prefer_busy_poll(n)) { if (napi_complete_done(n, work)) { /* If timeout is not set, we need to make sure * that the NAPI is re-scheduled. */ napi_schedule(n); } return work; } /* Flush too old packets. If HZ < 1000, flush all packets */ gro_flush_normal(&n->gro, HZ >= 1000); /* Some drivers may have called napi_schedule * prior to exhausting their budget. */ if (unlikely(!list_empty(&n->poll_list))) { pr_warn_once("%s: Budget exhausted after napi rescheduled\n", n->dev ? n->dev->name : "backlog"); return work; } *repoll = true; return work; } static int napi_poll(struct napi_struct *n, struct list_head *repoll) { bool do_repoll = false; void *have; int work; list_del_init(&n->poll_list); have = netpoll_poll_lock(n); work = __napi_poll(n, &do_repoll); if (do_repoll) { #if defined(CONFIG_DEBUG_NET) if (unlikely(!napi_is_scheduled(n))) pr_crit("repoll requested for device %s %ps but napi is not scheduled.\n", n->dev->name, n->poll); #endif list_add_tail(&n->poll_list, repoll); } netpoll_poll_unlock(have); return work; } static int napi_thread_wait(struct napi_struct *napi) { set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop()) { /* Testing SCHED_THREADED bit here to make sure the current * kthread owns this napi and could poll on this napi. * Testing SCHED bit is not enough because SCHED bit might be * set by some other busy poll thread or by napi_disable(). */ if (test_bit(NAPI_STATE_SCHED_THREADED, &napi->state)) { WARN_ON(!list_empty(&napi->poll_list)); __set_current_state(TASK_RUNNING); return 0; } schedule(); set_current_state(TASK_INTERRUPTIBLE); } __set_current_state(TASK_RUNNING); return -1; } static void napi_threaded_poll_loop(struct napi_struct *napi) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct softnet_data *sd; unsigned long last_qs = jiffies; for (;;) { bool repoll = false; void *have; local_bh_disable(); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); sd = this_cpu_ptr(&softnet_data); sd->in_napi_threaded_poll = true; have = netpoll_poll_lock(napi); __napi_poll(napi, &repoll); netpoll_poll_unlock(have); sd->in_napi_threaded_poll = false; barrier(); if (sd_has_rps_ipi_waiting(sd)) { local_irq_disable(); net_rps_action_and_irq_enable(sd); } skb_defer_free_flush(sd); bpf_net_ctx_clear(bpf_net_ctx); local_bh_enable(); if (!repoll) break; rcu_softirq_qs_periodic(last_qs); cond_resched(); } } static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; while (!napi_thread_wait(napi)) napi_threaded_poll_loop(napi); return 0; } static __latent_entropy void net_rx_action(void) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); unsigned long time_limit = jiffies + usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs)); struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; int budget = READ_ONCE(net_hotdata.netdev_budget); LIST_HEAD(list); LIST_HEAD(repoll); bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); start: sd->in_net_rx_action = true; local_irq_disable(); list_splice_init(&sd->poll_list, &list); local_irq_enable(); for (;;) { struct napi_struct *n; skb_defer_free_flush(sd); if (list_empty(&list)) { if (list_empty(&repoll)) { sd->in_net_rx_action = false; barrier(); /* We need to check if ____napi_schedule() * had refilled poll_list while * sd->in_net_rx_action was true. */ if (!list_empty(&sd->poll_list)) goto start; if (!sd_has_rps_ipi_waiting(sd)) goto end; } break; } n = list_first_entry(&list, struct napi_struct, poll_list); budget -= napi_poll(n, &repoll); /* If softirq window is exhausted then punt. * Allow this to run for 2 jiffies since which will allow * an average latency of 1.5/HZ. */ if (unlikely(budget <= 0 || time_after_eq(jiffies, time_limit))) { /* Pairs with READ_ONCE() in softnet_seq_show() */ WRITE_ONCE(sd->time_squeeze, sd->time_squeeze + 1); break; } } local_irq_disable(); list_splice_tail_init(&sd->poll_list, &list); list_splice_tail(&repoll, &list); list_splice(&list, &sd->poll_list); if (!list_empty(&sd->poll_list)) __raise_softirq_irqoff(NET_RX_SOFTIRQ); else sd->in_net_rx_action = false; net_rps_action_and_irq_enable(sd); end: bpf_net_ctx_clear(bpf_net_ctx); } struct netdev_adjacent { struct net_device *dev; netdevice_tracker dev_tracker; /* upper master flag, there can only be one master device per list */ bool master; /* lookup ignore flag */ bool ignore; /* counter for the number of times this device was added to us */ u16 ref_nr; /* private field for the users */ void *private; struct list_head list; struct rcu_head rcu; }; static struct netdev_adjacent *__netdev_find_adj(struct net_device *adj_dev, struct list_head *adj_list) { struct netdev_adjacent *adj; list_for_each_entry(adj, adj_list, list) { if (adj->dev == adj_dev) return adj; } return NULL; } static int ____netdev_has_upper_dev(struct net_device *upper_dev, struct netdev_nested_priv *priv) { struct net_device *dev = (struct net_device *)priv->data; return upper_dev == dev; } /** * netdev_has_upper_dev - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * * Find out if a device is linked to specified upper device and return true * in case it is. Note that this checks only immediate upper device, * not through a complete stack of devices. The caller must hold the RTNL lock. */ bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .data = (void *)upper_dev, }; ASSERT_RTNL(); return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, &priv); } EXPORT_SYMBOL(netdev_has_upper_dev); /** * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device * @dev: device * @upper_dev: upper device to check * * Find out if a device is linked to specified upper device and return true * in case it is. Note that this checks the entire upper device chain. * The caller must hold rcu lock. */ bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .data = (void *)upper_dev, }; return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, &priv); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); /** * netdev_has_any_upper_dev - Check if device is linked to some device * @dev: device * * Find out if a device is linked to an upper device and return true in case * it is. The caller must hold the RTNL lock. */ bool netdev_has_any_upper_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.upper); } EXPORT_SYMBOL(netdev_has_any_upper_dev); /** * netdev_master_upper_dev_get - Get master upper device * @dev: device * * Find a master upper device and return pointer to it or NULL in case * it's not there. The caller must hold the RTNL lock. */ struct net_device *netdev_master_upper_dev_get(struct net_device *dev) { struct netdev_adjacent *upper; ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper)) return NULL; upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master)) return upper->dev; return NULL; } EXPORT_SYMBOL(netdev_master_upper_dev_get); static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev) { struct netdev_adjacent *upper; ASSERT_RTNL(); if (list_empty(&dev->adj_list.upper)) return NULL; upper = list_first_entry(&dev->adj_list.upper, struct netdev_adjacent, list); if (likely(upper->master) && !upper->ignore) return upper->dev; return NULL; } /** * netdev_has_any_lower_dev - Check if device is linked to some device * @dev: device * * Find out if a device is linked to a lower device and return true in case * it is. The caller must hold the RTNL lock. */ static bool netdev_has_any_lower_dev(struct net_device *dev) { ASSERT_RTNL(); return !list_empty(&dev->adj_list.lower); } void *netdev_adjacent_get_private(struct list_head *adj_list) { struct netdev_adjacent *adj; adj = list_entry(adj_list, struct netdev_adjacent, list); return adj->private; } EXPORT_SYMBOL(netdev_adjacent_get_private); /** * netdev_upper_get_next_dev_rcu - Get the next dev from upper list * @dev: device * @iter: list_head ** of the current position * * Gets the next device from the dev's upper list, starting from iter * position. The caller must hold RCU read lock. */ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *upper; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); static struct net_device *__netdev_next_upper_dev(struct net_device *dev, struct list_head **iter, bool *ignore) { struct netdev_adjacent *upper; upper = list_entry((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; *ignore = upper->ignore; return upper->dev; } static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *upper; WARN_ON_ONCE(!rcu_read_lock_held() && !lockdep_rtnl_is_held()); upper = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&upper->list == &dev->adj_list.upper) return NULL; *iter = &upper->list; return upper->dev; } static int __netdev_walk_all_upper_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; bool ignore; now = dev; iter = &dev->adj_list.upper; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { udev = __netdev_next_upper_dev(now, &iter, &ignore); if (!udev) break; if (ignore) continue; next = udev; niter = &udev->adj_list.upper; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.upper; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { udev = netdev_next_upper_dev_rcu(now, &iter); if (!udev) break; next = udev; niter = &udev->adj_list.upper; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu); static bool __netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .flags = 0, .data = (void *)upper_dev, }; ASSERT_RTNL(); return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, &priv); } /** * netdev_lower_get_next_private - Get the next ->private from the * lower neighbour list * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold either hold the * RTNL lock or its own locking that guarantees that the neighbour lower * list will remain unchanged. */ void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = lower->list.next; return lower->private; } EXPORT_SYMBOL(netdev_lower_get_next_private); /** * netdev_lower_get_next_private_rcu - Get the next ->private from the * lower neighbour list, RCU * variant * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent->private from the dev's lower neighbour * list, starting from iter position. The caller must hold RCU read lock. */ void *netdev_lower_get_next_private_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->private; } EXPORT_SYMBOL(netdev_lower_get_next_private_rcu); /** * netdev_lower_get_next - Get the next device from the lower neighbour * list * @dev: device * @iter: list_head ** of the current position * * Gets the next netdev_adjacent from the dev's lower neighbour * list, starting from iter position. The caller must hold RTNL lock or * its own locking that guarantees that the neighbour lower * list will remain unchanged. */ void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry(*iter, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = lower->list.next; return lower->dev; } EXPORT_SYMBOL(netdev_lower_get_next); static struct net_device *netdev_next_lower_dev(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } static struct net_device *__netdev_next_lower_dev(struct net_device *dev, struct list_head **iter, bool *ignore) { struct netdev_adjacent *lower; lower = list_entry((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; *ignore = lower->ignore; return lower->dev; } int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = netdev_next_lower_dev(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); static int __netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; bool ignore; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = __netdev_next_lower_dev(now, &iter, &ignore); if (!ldev) break; if (ignore) continue; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter) { struct netdev_adjacent *lower; lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list); if (&lower->list == &dev->adj_list.lower) return NULL; *iter = &lower->list; return lower->dev; } EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { struct net_device *udev; struct list_head *iter; u8 max_depth = 0; bool ignore; for (iter = &dev->adj_list.upper, udev = __netdev_next_upper_dev(dev, &iter, &ignore); udev; udev = __netdev_next_upper_dev(dev, &iter, &ignore)) { if (ignore) continue; if (max_depth < udev->upper_level) max_depth = udev->upper_level; } return max_depth; } static u8 __netdev_lower_depth(struct net_device *dev) { struct net_device *ldev; struct list_head *iter; u8 max_depth = 0; bool ignore; for (iter = &dev->adj_list.lower, ldev = __netdev_next_lower_dev(dev, &iter, &ignore); ldev; ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) { if (ignore) continue; if (max_depth < ldev->lower_level) max_depth = ldev->lower_level; } return max_depth; } static int __netdev_update_upper_level(struct net_device *dev, struct netdev_nested_priv *__unused) { dev->upper_level = __netdev_upper_depth(dev) + 1; return 0; } #ifdef CONFIG_LOCKDEP static LIST_HEAD(net_unlink_list); static void net_unlink_todo(struct net_device *dev) { if (list_empty(&dev->unlink_list)) list_add_tail(&dev->unlink_list, &net_unlink_list); } #endif static int __netdev_update_lower_level(struct net_device *dev, struct netdev_nested_priv *priv) { dev->lower_level = __netdev_lower_depth(dev) + 1; #ifdef CONFIG_LOCKDEP if (!priv) return 0; if (priv->flags & NESTED_SYNC_IMM) dev->nested_level = dev->lower_level - 1; if (priv->flags & NESTED_SYNC_TODO) net_unlink_todo(dev); #endif return 0; } int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv) { struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; int ret, cur = 0; now = dev; iter = &dev->adj_list.lower; while (1) { if (now != dev) { ret = fn(now, priv); if (ret) return ret; } next = NULL; while (1) { ldev = netdev_next_lower_dev_rcu(now, &iter); if (!ldev) break; next = ldev; niter = &ldev->adj_list.lower; dev_stack[cur] = now; iter_stack[cur++] = iter; break; } if (!next) { if (!cur) return 0; next = dev_stack[--cur]; niter = iter_stack[cur]; } now = next; iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev_rcu); /** * netdev_lower_get_first_private_rcu - Get the first ->private from the * lower neighbour list, RCU * variant * @dev: device * * Gets the first netdev_adjacent->private from the dev's lower neighbour * list. The caller must hold RCU read lock. */ void *netdev_lower_get_first_private_rcu(struct net_device *dev) { struct netdev_adjacent *lower; lower = list_first_or_null_rcu(&dev->adj_list.lower, struct netdev_adjacent, list); if (lower) return lower->private; return NULL; } EXPORT_SYMBOL(netdev_lower_get_first_private_rcu); /** * netdev_master_upper_dev_get_rcu - Get master upper device * @dev: device * * Find a master upper device and return pointer to it or NULL in case * it's not there. The caller must hold the RCU read lock. */ struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev) { struct netdev_adjacent *upper; upper = list_first_or_null_rcu(&dev->adj_list.upper, struct netdev_adjacent, list); if (upper && likely(upper->master)) return upper->dev; return NULL; } EXPORT_SYMBOL(netdev_master_upper_dev_get_rcu); static int netdev_adjacent_sysfs_add(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", adj_dev->name); return sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), linkname); } static void netdev_adjacent_sysfs_del(struct net_device *dev, char *name, struct list_head *dev_list) { char linkname[IFNAMSIZ+7]; sprintf(linkname, dev_list == &dev->adj_list.upper ? "upper_%s" : "lower_%s", name); sysfs_remove_link(&(dev->dev.kobj), linkname); } static inline bool netdev_adjacent_is_neigh_list(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list) { return (dev_list == &dev->adj_list.upper || dev_list == &dev->adj_list.lower) && net_eq(dev_net(dev), dev_net(adj_dev)); } static int __netdev_adjacent_dev_insert(struct net_device *dev, struct net_device *adj_dev, struct list_head *dev_list, void *private, bool master) { struct netdev_adjacent *adj; int ret; adj = __netdev_find_adj(adj_dev, dev_list); if (adj) { adj->ref_nr += 1; pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d\n", dev->name, adj_dev->name, adj->ref_nr); return 0; } adj = kmalloc(sizeof(*adj), GFP_KERNEL); if (!adj) return -ENOMEM; adj->dev = adj_dev; adj->master = master; adj->ref_nr = 1; adj->private = private; adj->ignore = false; netdev_hold(adj_dev, &adj->dev_tracker, GFP_KERNEL); pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", dev->name, adj_dev->name, adj->ref_nr, adj_dev->name); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) { ret = netdev_adjacent_sysfs_add(dev, adj_dev, dev_list); if (ret) goto free_adj; } /* Ensure that master link is always the first item in list. */ if (master) { ret = sysfs_create_link(&(dev->dev.kobj), &(adj_dev->dev.kobj), "master"); if (ret) goto remove_symlinks; list_add_rcu(&adj->list, dev_list); } else { list_add_tail_rcu(&adj->list, dev_list); } return 0; remove_symlinks: if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); free_adj: netdev_put(adj_dev, &adj->dev_tracker); kfree(adj); return ret; } static void __netdev_adjacent_dev_remove(struct net_device *dev, struct net_device *adj_dev, u16 ref_nr, struct list_head *dev_list) { struct netdev_adjacent *adj; pr_debug("Remove adjacency: dev %s adj_dev %s ref_nr %d\n", dev->name, adj_dev->name, ref_nr); adj = __netdev_find_adj(adj_dev, dev_list); if (!adj) { pr_err("Adjacency does not exist for device %s from %s\n", dev->name, adj_dev->name); WARN_ON(1); return; } if (adj->ref_nr > ref_nr) { pr_debug("adjacency: %s to %s ref_nr - %d = %d\n", dev->name, adj_dev->name, ref_nr, adj->ref_nr - ref_nr); adj->ref_nr -= ref_nr; return; } if (adj->master) sysfs_remove_link(&(dev->dev.kobj), "master"); if (netdev_adjacent_is_neigh_list(dev, adj_dev, dev_list)) netdev_adjacent_sysfs_del(dev, adj_dev->name, dev_list); list_del_rcu(&adj->list); pr_debug("adjacency: dev_put for %s, because link removed from %s to %s\n", adj_dev->name, dev->name, adj_dev->name); netdev_put(adj_dev, &adj->dev_tracker); kfree_rcu(adj, rcu); } static int __netdev_adjacent_dev_link_lists(struct net_device *dev, struct net_device *upper_dev, struct list_head *up_list, struct list_head *down_list, void *private, bool master) { int ret; ret = __netdev_adjacent_dev_insert(dev, upper_dev, up_list, private, master); if (ret) return ret; ret = __netdev_adjacent_dev_insert(upper_dev, dev, down_list, private, false); if (ret) { __netdev_adjacent_dev_remove(dev, upper_dev, 1, up_list); return ret; } return 0; } static void __netdev_adjacent_dev_unlink_lists(struct net_device *dev, struct net_device *upper_dev, u16 ref_nr, struct list_head *up_list, struct list_head *down_list) { __netdev_adjacent_dev_remove(dev, upper_dev, ref_nr, up_list); __netdev_adjacent_dev_remove(upper_dev, dev, ref_nr, down_list); } static int __netdev_adjacent_dev_link_neighbour(struct net_device *dev, struct net_device *upper_dev, void *private, bool master) { return __netdev_adjacent_dev_link_lists(dev, upper_dev, &dev->adj_list.upper, &upper_dev->adj_list.lower, private, master); } static void __netdev_adjacent_dev_unlink_neighbour(struct net_device *dev, struct net_device *upper_dev) { __netdev_adjacent_dev_unlink_lists(dev, upper_dev, 1, &dev->adj_list.upper, &upper_dev->adj_list.lower); } static int __netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, bool master, void *upper_priv, void *upper_info, struct netdev_nested_priv *priv, struct netlink_ext_ack *extack) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, .extack = extack, }, .upper_dev = upper_dev, .master = master, .linking = true, .upper_info = upper_info, }; struct net_device *master_dev; int ret = 0; ASSERT_RTNL(); if (dev == upper_dev) return -EBUSY; /* To prevent loops, check if dev is not upper device to upper_dev. */ if (__netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) return -EMLINK; if (!master) { if (__netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; } else { master_dev = __netdev_master_upper_dev_get(dev); if (master_dev) return master_dev == upper_dev ? -EEXIST : -EBUSY; } ret = call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) return ret; ret = __netdev_adjacent_dev_link_neighbour(dev, upper_dev, upper_priv, master); if (ret) return ret; ret = call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); ret = notifier_to_errno(ret); if (ret) goto rollback; __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, priv); return 0; rollback: __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); return ret; } /** * netdev_upper_dev_link - Add a link to the upper device * @dev: device * @upper_dev: new upper device * @extack: netlink extended ack * * Adds a link to device which is upper to this one. The caller must hold * the RTNL lock. On a failure a negative errno code is returned. * On success the reference counts are adjusted and the function * returns zero. */ int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; return __netdev_upper_dev_link(dev, upper_dev, false, NULL, NULL, &priv, extack); } EXPORT_SYMBOL(netdev_upper_dev_link); /** * netdev_master_upper_dev_link - Add a master link to the upper device * @dev: device * @upper_dev: new upper device * @upper_priv: upper device private * @upper_info: upper info to be passed down via notifier * @extack: netlink extended ack * * Adds a link to device which is upper to this one. In this case, only * one master upper device can be linked, although other non-master devices * might be linked as well. The caller must hold the RTNL lock. * On a failure a negative errno code is returned. On success the reference * counts are adjusted and the function returns zero. */ int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; return __netdev_upper_dev_link(dev, upper_dev, true, upper_priv, upper_info, &priv, extack); } EXPORT_SYMBOL(netdev_master_upper_dev_link); static void __netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev, struct netdev_nested_priv *priv) { struct netdev_notifier_changeupper_info changeupper_info = { .info = { .dev = dev, }, .upper_dev = upper_dev, .linking = false, }; ASSERT_RTNL(); changeupper_info.master = netdev_master_upper_dev_get(dev) == upper_dev; call_netdevice_notifiers_info(NETDEV_PRECHANGEUPPER, &changeupper_info.info); __netdev_adjacent_dev_unlink_neighbour(dev, upper_dev); call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); __netdev_update_upper_level(dev, NULL); __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); __netdev_update_lower_level(upper_dev, priv); __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, priv); } /** * netdev_upper_dev_unlink - Removes a link to upper device * @dev: device * @upper_dev: new upper device * * Removes a link to device which is upper to this one. The caller must hold * the RTNL lock. */ void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_TODO, .data = NULL, }; __netdev_upper_dev_unlink(dev, upper_dev, &priv); } EXPORT_SYMBOL(netdev_upper_dev_unlink); static void __netdev_adjacent_dev_set(struct net_device *upper_dev, struct net_device *lower_dev, bool val) { struct netdev_adjacent *adj; adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower); if (adj) adj->ignore = val; adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper); if (adj) adj->ignore = val; } static void netdev_adjacent_dev_disable(struct net_device *upper_dev, struct net_device *lower_dev) { __netdev_adjacent_dev_set(upper_dev, lower_dev, true); } static void netdev_adjacent_dev_enable(struct net_device *upper_dev, struct net_device *lower_dev) { __netdev_adjacent_dev_set(upper_dev, lower_dev, false); } int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_nested_priv priv = { .flags = 0, .data = NULL, }; int err; if (!new_dev) return 0; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_disable(dev, old_dev); err = __netdev_upper_dev_link(new_dev, dev, false, NULL, NULL, &priv, extack); if (err) { if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); return err; } return 0; } EXPORT_SYMBOL(netdev_adjacent_change_prepare); void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { struct netdev_nested_priv priv = { .flags = NESTED_SYNC_IMM | NESTED_SYNC_TODO, .data = NULL, }; if (!new_dev || !old_dev) return; if (new_dev == old_dev) return; netdev_adjacent_dev_enable(dev, old_dev); __netdev_upper_dev_unlink(old_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_commit); void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev) { struct netdev_nested_priv priv = { .flags = 0, .data = NULL, }; if (!new_dev) return; if (old_dev && new_dev != old_dev) netdev_adjacent_dev_enable(dev, old_dev); __netdev_upper_dev_unlink(new_dev, dev, &priv); } EXPORT_SYMBOL(netdev_adjacent_change_abort); /** * netdev_bonding_info_change - Dispatch event about slave change * @dev: device * @bonding_info: info to dispatch * * Send NETDEV_BONDING_INFO to netdev notifiers with info. * The caller must hold the RTNL lock. */ void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info) { struct netdev_notifier_bonding_info info = { .info.dev = dev, }; memcpy(&info.bonding_info, bonding_info, sizeof(struct netdev_bonding_info)); call_netdevice_notifiers_info(NETDEV_BONDING_INFO, &info.info); } EXPORT_SYMBOL(netdev_bonding_info_change); static int netdev_offload_xstats_enable_l3(struct net_device *dev, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, }; int err; int rc; dev->offload_xstats_l3 = kzalloc(sizeof(*dev->offload_xstats_l3), GFP_KERNEL); if (!dev->offload_xstats_l3) return -ENOMEM; rc = call_netdevice_notifiers_info_robust(NETDEV_OFFLOAD_XSTATS_ENABLE, NETDEV_OFFLOAD_XSTATS_DISABLE, &info.info); err = notifier_to_errno(rc); if (err) goto free_stats; return 0; free_stats: kfree(dev->offload_xstats_l3); dev->offload_xstats_l3 = NULL; return err; } int netdev_offload_xstats_enable(struct net_device *dev, enum netdev_offload_xstats_type type, struct netlink_ext_ack *extack) { ASSERT_RTNL(); if (netdev_offload_xstats_enabled(dev, type)) return -EALREADY; switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return netdev_offload_xstats_enable_l3(dev, extack); } WARN_ON(1); return -EINVAL; } EXPORT_SYMBOL(netdev_offload_xstats_enable); static void netdev_offload_xstats_disable_l3(struct net_device *dev) { struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .type = NETDEV_OFFLOAD_XSTATS_TYPE_L3, }; call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_DISABLE, &info.info); kfree(dev->offload_xstats_l3); dev->offload_xstats_l3 = NULL; } int netdev_offload_xstats_disable(struct net_device *dev, enum netdev_offload_xstats_type type) { ASSERT_RTNL(); if (!netdev_offload_xstats_enabled(dev, type)) return -EALREADY; switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: netdev_offload_xstats_disable_l3(dev); return 0; } WARN_ON(1); return -EINVAL; } EXPORT_SYMBOL(netdev_offload_xstats_disable); static void netdev_offload_xstats_disable_all(struct net_device *dev) { netdev_offload_xstats_disable(dev, NETDEV_OFFLOAD_XSTATS_TYPE_L3); } static struct rtnl_hw_stats64 * netdev_offload_xstats_get_ptr(const struct net_device *dev, enum netdev_offload_xstats_type type) { switch (type) { case NETDEV_OFFLOAD_XSTATS_TYPE_L3: return dev->offload_xstats_l3; } WARN_ON(1); return NULL; } bool netdev_offload_xstats_enabled(const struct net_device *dev, enum netdev_offload_xstats_type type) { ASSERT_RTNL(); return netdev_offload_xstats_get_ptr(dev, type); } EXPORT_SYMBOL(netdev_offload_xstats_enabled); struct netdev_notifier_offload_xstats_ru { bool used; }; struct netdev_notifier_offload_xstats_rd { struct rtnl_hw_stats64 stats; bool used; }; static void netdev_hw_stats64_add(struct rtnl_hw_stats64 *dest, const struct rtnl_hw_stats64 *src) { dest->rx_packets += src->rx_packets; dest->tx_packets += src->tx_packets; dest->rx_bytes += src->rx_bytes; dest->tx_bytes += src->tx_bytes; dest->rx_errors += src->rx_errors; dest->tx_errors += src->tx_errors; dest->rx_dropped += src->rx_dropped; dest->tx_dropped += src->tx_dropped; dest->multicast += src->multicast; } static int netdev_offload_xstats_get_used(struct net_device *dev, enum netdev_offload_xstats_type type, bool *p_used, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_ru report_used = {}; struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = type, .report_used = &report_used, }; int rc; WARN_ON(!netdev_offload_xstats_enabled(dev, type)); rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_USED, &info.info); *p_used = report_used.used; return notifier_to_errno(rc); } static int netdev_offload_xstats_get_stats(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *p_stats, bool *p_used, struct netlink_ext_ack *extack) { struct netdev_notifier_offload_xstats_rd report_delta = {}; struct netdev_notifier_offload_xstats_info info = { .info.dev = dev, .info.extack = extack, .type = type, .report_delta = &report_delta, }; struct rtnl_hw_stats64 *stats; int rc; stats = netdev_offload_xstats_get_ptr(dev, type); if (WARN_ON(!stats)) return -EINVAL; rc = call_netdevice_notifiers_info(NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, &info.info); /* Cache whatever we got, even if there was an error, otherwise the * successful stats retrievals would get lost. */ netdev_hw_stats64_add(stats, &report_delta.stats); if (p_stats) *p_stats = *stats; *p_used = report_delta.used; return notifier_to_errno(rc); } int netdev_offload_xstats_get(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *p_stats, bool *p_used, struct netlink_ext_ack *extack) { ASSERT_RTNL(); if (p_stats) return netdev_offload_xstats_get_stats(dev, type, p_stats, p_used, extack); else return netdev_offload_xstats_get_used(dev, type, p_used, extack); } EXPORT_SYMBOL(netdev_offload_xstats_get); void netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *report_delta, const struct rtnl_hw_stats64 *stats) { report_delta->used = true; netdev_hw_stats64_add(&report_delta->stats, stats); } EXPORT_SYMBOL(netdev_offload_xstats_report_delta); void netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *report_used) { report_used->used = true; } EXPORT_SYMBOL(netdev_offload_xstats_report_used); void netdev_offload_xstats_push_delta(struct net_device *dev, enum netdev_offload_xstats_type type, const struct rtnl_hw_stats64 *p_stats) { struct rtnl_hw_stats64 *stats; ASSERT_RTNL(); stats = netdev_offload_xstats_get_ptr(dev, type); if (WARN_ON(!stats)) return; netdev_hw_stats64_add(stats, p_stats); } EXPORT_SYMBOL(netdev_offload_xstats_push_delta); /** * netdev_get_xmit_slave - Get the xmit slave of master device * @dev: device * @skb: The packet * @all_slaves: assume all the slaves are active * * The reference counters are not incremented so the caller must be * careful with locks. The caller must hold RCU lock. * %NULL is returned if no slave is found. */ struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, bool all_slaves) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_get_xmit_slave) return NULL; return ops->ndo_get_xmit_slave(dev, skb, all_slaves); } EXPORT_SYMBOL(netdev_get_xmit_slave); static struct net_device *netdev_sk_get_lower_dev(struct net_device *dev, struct sock *sk) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_sk_get_lower_dev) return NULL; return ops->ndo_sk_get_lower_dev(dev, sk); } /** * netdev_sk_get_lowest_dev - Get the lowest device in chain given device and socket * @dev: device * @sk: the socket * * %NULL is returned if no lower device is found. */ struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, struct sock *sk) { struct net_device *lower; lower = netdev_sk_get_lower_dev(dev, sk); while (lower) { dev = lower; lower = netdev_sk_get_lower_dev(dev, sk); } return dev; } EXPORT_SYMBOL(netdev_sk_get_lowest_dev); static void netdev_adjacent_add_links(struct net_device *dev) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(dev, iter->dev, &dev->adj_list.upper); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(dev, iter->dev, &dev->adj_list.lower); } } static void netdev_adjacent_del_links(struct net_device *dev) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, dev->name, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_del(dev, iter->dev->name, &dev->adj_list.upper); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, dev->name, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_del(dev, iter->dev->name, &dev->adj_list.lower); } } void netdev_adjacent_rename_links(struct net_device *dev, char *oldname) { struct netdev_adjacent *iter; struct net *net = dev_net(dev); list_for_each_entry(iter, &dev->adj_list.upper, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.lower); netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.lower); } list_for_each_entry(iter, &dev->adj_list.lower, list) { if (!net_eq(net, dev_net(iter->dev))) continue; netdev_adjacent_sysfs_del(iter->dev, oldname, &iter->dev->adj_list.upper); netdev_adjacent_sysfs_add(iter->dev, dev, &iter->dev->adj_list.upper); } } void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev) { struct netdev_adjacent *lower; if (!lower_dev) return NULL; lower = __netdev_find_adj(lower_dev, &dev->adj_list.lower); if (!lower) return NULL; return lower->private; } EXPORT_SYMBOL(netdev_lower_dev_get_private); /** * netdev_lower_state_changed - Dispatch event about lower device state change * @lower_dev: device * @lower_state_info: state to dispatch * * Send NETDEV_CHANGELOWERSTATE to netdev notifiers with info. * The caller must hold the RTNL lock. */ void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info) { struct netdev_notifier_changelowerstate_info changelowerstate_info = { .info.dev = lower_dev, }; ASSERT_RTNL(); changelowerstate_info.lower_state_info = lower_state_info; call_netdevice_notifiers_info(NETDEV_CHANGELOWERSTATE, &changelowerstate_info.info); } EXPORT_SYMBOL(netdev_lower_state_changed); static void dev_change_rx_flags(struct net_device *dev, int flags) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_change_rx_flags) ops->ndo_change_rx_flags(dev, flags); } static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags; unsigned int promiscuity, flags; kuid_t uid; kgid_t gid; ASSERT_RTNL(); promiscuity = dev->promiscuity + inc; if (promiscuity == 0) { /* * Avoid overflow. * If inc causes overflow, untouch promisc and return error. */ if (unlikely(inc > 0)) { netdev_warn(dev, "promiscuity touches roof, set promiscuity failed. promiscuity feature of device might be broken.\n"); return -EOVERFLOW; } flags = old_flags & ~IFF_PROMISC; } else { flags = old_flags | IFF_PROMISC; } WRITE_ONCE(dev->promiscuity, promiscuity); if (flags != old_flags) { WRITE_ONCE(dev->flags, flags); netdev_info(dev, "%s promiscuous mode\n", dev->flags & IFF_PROMISC ? "entered" : "left"); if (audit_enabled) { current_uid_gid(&uid, &gid); audit_log(audit_context(), GFP_ATOMIC, AUDIT_ANOM_PROMISCUOUS, "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), from_kuid(&init_user_ns, audit_get_loginuid(current)), from_kuid(&init_user_ns, uid), from_kgid(&init_user_ns, gid), audit_get_sessionid(current)); } dev_change_rx_flags(dev, IFF_PROMISC); } if (notify) { /* The ops lock is only required to ensure consistent locking * for `NETDEV_CHANGE` notifiers. This function is sometimes * called without the lock, even for devices that are ops * locked, such as in `dev_uc_sync_multiple` when using * bonding or teaming. */ netdev_ops_assert_locked(dev); __dev_notify_flags(dev, old_flags, IFF_PROMISC, 0, NULL); } return 0; } int netif_set_promiscuity(struct net_device *dev, int inc) { unsigned int old_flags = dev->flags; int err; err = __dev_set_promiscuity(dev, inc, true); if (err < 0) return err; if (dev->flags != old_flags) dev_set_rx_mode(dev); return err; } int netif_set_allmulti(struct net_device *dev, int inc, bool notify) { unsigned int old_flags = dev->flags, old_gflags = dev->gflags; unsigned int allmulti, flags; ASSERT_RTNL(); allmulti = dev->allmulti + inc; if (allmulti == 0) { /* * Avoid overflow. * If inc causes overflow, untouch allmulti and return error. */ if (unlikely(inc > 0)) { netdev_warn(dev, "allmulti touches roof, set allmulti failed. allmulti feature of device might be broken.\n"); return -EOVERFLOW; } flags = old_flags & ~IFF_ALLMULTI; } else { flags = old_flags | IFF_ALLMULTI; } WRITE_ONCE(dev->allmulti, allmulti); if (flags != old_flags) { WRITE_ONCE(dev->flags, flags); netdev_info(dev, "%s allmulticast mode\n", dev->flags & IFF_ALLMULTI ? "entered" : "left"); dev_change_rx_flags(dev, IFF_ALLMULTI); dev_set_rx_mode(dev); if (notify) __dev_notify_flags(dev, old_flags, dev->gflags ^ old_gflags, 0, NULL); } return 0; } /* * Upload unicast and multicast address lists to device and * configure RX filtering. When the device doesn't support unicast * filtering it is put in promiscuous mode while unicast addresses * are present. */ void __dev_set_rx_mode(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; /* dev_open will call this function so the list will stay sane. */ if (!(dev->flags&IFF_UP)) return; if (!netif_device_present(dev)) return; if (!(dev->priv_flags & IFF_UNICAST_FLT)) { /* Unicast addresses changes may only happen under the rtnl, * therefore calling __dev_set_promiscuity here is safe. */ if (!netdev_uc_empty(dev) && !dev->uc_promisc) { __dev_set_promiscuity(dev, 1, false); dev->uc_promisc = true; } else if (netdev_uc_empty(dev) && dev->uc_promisc) { __dev_set_promiscuity(dev, -1, false); dev->uc_promisc = false; } } if (ops->ndo_set_rx_mode) ops->ndo_set_rx_mode(dev); } void dev_set_rx_mode(struct net_device *dev) { netif_addr_lock_bh(dev); __dev_set_rx_mode(dev); netif_addr_unlock_bh(dev); } /** * netif_get_flags() - get flags reported to userspace * @dev: device * * Get the combination of flag bits exported through APIs to userspace. */ unsigned int netif_get_flags(const struct net_device *dev) { unsigned int flags; flags = (READ_ONCE(dev->flags) & ~(IFF_PROMISC | IFF_ALLMULTI | IFF_RUNNING | IFF_LOWER_UP | IFF_DORMANT)) | (READ_ONCE(dev->gflags) & (IFF_PROMISC | IFF_ALLMULTI)); if (netif_running(dev)) { if (netif_oper_up(dev)) flags |= IFF_RUNNING; if (netif_carrier_ok(dev)) flags |= IFF_LOWER_UP; if (netif_dormant(dev)) flags |= IFF_DORMANT; } return flags; } EXPORT_SYMBOL(netif_get_flags); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) { unsigned int old_flags = dev->flags; int ret; ASSERT_RTNL(); /* * Set the flags on our device. */ dev->flags = (flags & (IFF_DEBUG | IFF_NOTRAILERS | IFF_NOARP | IFF_DYNAMIC | IFF_MULTICAST | IFF_PORTSEL | IFF_AUTOMEDIA)) | (dev->flags & (IFF_UP | IFF_VOLATILE | IFF_PROMISC | IFF_ALLMULTI)); /* * Load in the correct multicast list now the flags have changed. */ if ((old_flags ^ flags) & IFF_MULTICAST) dev_change_rx_flags(dev, IFF_MULTICAST); dev_set_rx_mode(dev); /* * Have we downed the interface. We handle IFF_UP ourselves * according to user attempts to set it, rather than blindly * setting it. */ ret = 0; if ((old_flags ^ flags) & IFF_UP) { if (old_flags & IFF_UP) __dev_close(dev); else ret = __dev_open(dev, extack); } if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; old_flags = dev->flags; dev->gflags ^= IFF_PROMISC; if (__dev_set_promiscuity(dev, inc, false) >= 0) if (dev->flags != old_flags) dev_set_rx_mode(dev); } /* NOTE: order of synchronization of IFF_PROMISC and IFF_ALLMULTI * is important. Some (broken) drivers set IFF_PROMISC, when * IFF_ALLMULTI is requested not asking us and not reporting. */ if ((flags ^ dev->gflags) & IFF_ALLMULTI) { int inc = (flags & IFF_ALLMULTI) ? 1 : -1; dev->gflags ^= IFF_ALLMULTI; netif_set_allmulti(dev, inc, false); } return ret; } void __dev_notify_flags(struct net_device *dev, unsigned int old_flags, unsigned int gchanges, u32 portid, const struct nlmsghdr *nlh) { unsigned int changes = dev->flags ^ old_flags; if (gchanges) rtmsg_ifinfo(RTM_NEWLINK, dev, gchanges, GFP_ATOMIC, portid, nlh); if (changes & IFF_UP) { if (dev->flags & IFF_UP) call_netdevice_notifiers(NETDEV_UP, dev); else call_netdevice_notifiers(NETDEV_DOWN, dev); } if (dev->flags & IFF_UP && (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) { struct netdev_notifier_change_info change_info = { .info = { .dev = dev, }, .flags_changed = changes, }; call_netdevice_notifiers_info(NETDEV_CHANGE, &change_info.info); } } int netif_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack) { int ret; unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags; ret = __dev_change_flags(dev, flags, extack); if (ret < 0) return ret; changes = (old_flags ^ dev->flags) | (old_gflags ^ dev->gflags); __dev_notify_flags(dev, old_flags, changes, 0, NULL); return ret; } int __netif_set_mtu(struct net_device *dev, int new_mtu) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); /* Pairs with all the lockless reads of dev->mtu in the stack */ WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL_NS_GPL(__netif_set_mtu, "NETDEV_INTERNAL"); int dev_validate_mtu(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { /* MTU must be positive, and in range */ if (new_mtu < 0 || new_mtu < dev->min_mtu) { NL_SET_ERR_MSG(extack, "mtu less than device minimum"); return -EINVAL; } if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); return -EINVAL; } return 0; } /** * netif_set_mtu_ext() - Change maximum transfer unit * @dev: device * @new_mtu: new transfer unit * @extack: netlink extended ack * * Change the maximum transfer size of the network device. * * Return: 0 on success, -errno on failure. */ int netif_set_mtu_ext(struct net_device *dev, int new_mtu, struct netlink_ext_ack *extack) { int err, orig_mtu; netdev_ops_assert_locked(dev); if (new_mtu == dev->mtu) return 0; err = dev_validate_mtu(dev, new_mtu, extack); if (err) return err; if (!netif_device_present(dev)) return -ENODEV; err = call_netdevice_notifiers(NETDEV_PRECHANGEMTU, dev); err = notifier_to_errno(err); if (err) return err; orig_mtu = dev->mtu; err = __netif_set_mtu(dev, new_mtu); if (!err) { err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, orig_mtu); err = notifier_to_errno(err); if (err) { /* setting mtu back and notifying everyone again, * so that they have a chance to revert changes. */ __netif_set_mtu(dev, orig_mtu); call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev, new_mtu); } } return err; } int netif_set_mtu(struct net_device *dev, int new_mtu) { struct netlink_ext_ack extack; int err; memset(&extack, 0, sizeof(extack)); err = netif_set_mtu_ext(dev, new_mtu, &extack); if (err && extack._msg) net_err_ratelimited("%s: %s\n", dev->name, extack._msg); return err; } EXPORT_SYMBOL(netif_set_mtu); int netif_change_tx_queue_len(struct net_device *dev, unsigned long new_len) { unsigned int orig_len = dev->tx_queue_len; int res; if (new_len != (unsigned int)new_len) return -ERANGE; if (new_len != orig_len) { WRITE_ONCE(dev->tx_queue_len, new_len); res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev); res = notifier_to_errno(res); if (res) goto err_rollback; res = dev_qdisc_change_tx_queue_len(dev); if (res) goto err_rollback; } return 0; err_rollback: netdev_err(dev, "refused to change device tx_queue_len\n"); WRITE_ONCE(dev->tx_queue_len, orig_len); return res; } void netif_set_group(struct net_device *dev, int new_group) { dev->group = new_group; } /** * netif_pre_changeaddr_notify() - Call NETDEV_PRE_CHANGEADDR. * @dev: device * @addr: new address * @extack: netlink extended ack * * Return: 0 on success, -errno on failure. */ int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack) { struct netdev_notifier_pre_changeaddr_info info = { .info.dev = dev, .info.extack = extack, .dev_addr = addr, }; int rc; rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info); return notifier_to_errno(rc); } EXPORT_SYMBOL_NS_GPL(netif_pre_changeaddr_notify, "NETDEV_INTERNAL"); int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss, struct netlink_ext_ack *extack) { const struct net_device_ops *ops = dev->netdev_ops; int err; if (!ops->ndo_set_mac_address) return -EOPNOTSUPP; if (ss->ss_family != dev->type) return -EINVAL; if (!netif_device_present(dev)) return -ENODEV; err = netif_pre_changeaddr_notify(dev, ss->__data, extack); if (err) return err; if (memcmp(dev->dev_addr, ss->__data, dev->addr_len)) { err = ops->ndo_set_mac_address(dev, ss); if (err) return err; } dev->addr_assign_type = NET_ADDR_SET; call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); add_device_randomness(dev->dev_addr, dev->addr_len); return 0; } DECLARE_RWSEM(dev_addr_sem); /* "sa" is a true struct sockaddr with limited "sa_data" member. */ int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; down_read(&dev_addr_sem); rcu_read_lock(); dev = dev_get_by_name_rcu(net, dev_name); if (!dev) { ret = -ENODEV; goto unlock; } if (!dev->addr_len) memset(sa->sa_data, 0, size); else memcpy(sa->sa_data, dev->dev_addr, min_t(size_t, size, dev->addr_len)); sa->sa_family = dev->type; unlock: rcu_read_unlock(); up_read(&dev_addr_sem); return ret; } EXPORT_SYMBOL_NS_GPL(netif_get_mac_address, "NETDEV_INTERNAL"); int netif_change_carrier(struct net_device *dev, bool new_carrier) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_change_carrier) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; return ops->ndo_change_carrier(dev, new_carrier); } /** * dev_get_phys_port_id - Get device physical port ID * @dev: device * @ppid: port ID * * Get device physical port ID */ int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_item_id *ppid) { const struct net_device_ops *ops = dev->netdev_ops; if (!ops->ndo_get_phys_port_id) return -EOPNOTSUPP; return ops->ndo_get_phys_port_id(dev, ppid); } /** * dev_get_phys_port_name - Get device physical port name * @dev: device * @name: port name * @len: limit of bytes to copy to name * * Get device physical port name */ int dev_get_phys_port_name(struct net_device *dev, char *name, size_t len) { const struct net_device_ops *ops = dev->netdev_ops; int err; if (ops->ndo_get_phys_port_name) { err = ops->ndo_get_phys_port_name(dev, name, len); if (err != -EOPNOTSUPP) return err; } return devlink_compat_phys_port_name_get(dev, name, len); } /** * netif_get_port_parent_id() - Get the device's port parent identifier * @dev: network device * @ppid: pointer to a storage for the port's parent identifier * @recurse: allow/disallow recursion to lower devices * * Get the devices's port parent identifier. * * Return: 0 on success, -errno on failure. */ int netif_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse) { const struct net_device_ops *ops = dev->netdev_ops; struct netdev_phys_item_id first = { }; struct net_device *lower_dev; struct list_head *iter; int err; if (ops->ndo_get_port_parent_id) { err = ops->ndo_get_port_parent_id(dev, ppid); if (err != -EOPNOTSUPP) return err; } err = devlink_compat_switch_id_get(dev, ppid); if (!recurse || err != -EOPNOTSUPP) return err; netdev_for_each_lower_dev(dev, lower_dev, iter) { err = netif_get_port_parent_id(lower_dev, ppid, true); if (err) break; if (!first.id_len) first = *ppid; else if (memcmp(&first, ppid, sizeof(*ppid))) return -EOPNOTSUPP; } return err; } EXPORT_SYMBOL(netif_get_port_parent_id); /** * netdev_port_same_parent_id - Indicate if two network devices have * the same port parent identifier * @a: first network device * @b: second network device */ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) { struct netdev_phys_item_id a_id = { }; struct netdev_phys_item_id b_id = { }; if (netif_get_port_parent_id(a, &a_id, true) || netif_get_port_parent_id(b, &b_id, true)) return false; return netdev_phys_item_id_same(&a_id, &b_id); } EXPORT_SYMBOL(netdev_port_same_parent_id); int netif_change_proto_down(struct net_device *dev, bool proto_down) { if (!dev->change_proto_down) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; if (proto_down) netif_carrier_off(dev); else netif_carrier_on(dev); WRITE_ONCE(dev->proto_down, proto_down); return 0; } /** * netdev_change_proto_down_reason_locked - proto down reason * * @dev: device * @mask: proto down mask * @value: proto down value */ void netdev_change_proto_down_reason_locked(struct net_device *dev, unsigned long mask, u32 value) { u32 proto_down_reason; int b; if (!mask) { proto_down_reason = value; } else { proto_down_reason = dev->proto_down_reason; for_each_set_bit(b, &mask, 32) { if (value & (1 << b)) proto_down_reason |= BIT(b); else proto_down_reason &= ~BIT(b); } } WRITE_ONCE(dev->proto_down_reason, proto_down_reason); } struct bpf_xdp_link { struct bpf_link link; struct net_device *dev; /* protected by rtnl_lock, no refcnt held */ int flags; }; static enum bpf_xdp_mode dev_xdp_mode(struct net_device *dev, u32 flags) { if (flags & XDP_FLAGS_HW_MODE) return XDP_MODE_HW; if (flags & XDP_FLAGS_DRV_MODE) return XDP_MODE_DRV; if (flags & XDP_FLAGS_SKB_MODE) return XDP_MODE_SKB; return dev->netdev_ops->ndo_bpf ? XDP_MODE_DRV : XDP_MODE_SKB; } static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode) { switch (mode) { case XDP_MODE_SKB: return generic_xdp_install; case XDP_MODE_DRV: case XDP_MODE_HW: return dev->netdev_ops->ndo_bpf; default: return NULL; } } static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev, enum bpf_xdp_mode mode) { return dev->xdp_state[mode].link; } static struct bpf_prog *dev_xdp_prog(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_xdp_link *link = dev_xdp_link(dev, mode); if (link) return link->link.prog; return dev->xdp_state[mode].prog; } u8 dev_xdp_prog_count(struct net_device *dev) { u8 count = 0; int i; for (i = 0; i < __MAX_XDP_MODE; i++) if (dev->xdp_state[i].prog || dev->xdp_state[i].link) count++; return count; } EXPORT_SYMBOL_GPL(dev_xdp_prog_count); u8 dev_xdp_sb_prog_count(struct net_device *dev) { u8 count = 0; int i; for (i = 0; i < __MAX_XDP_MODE; i++) if (dev->xdp_state[i].prog && !dev->xdp_state[i].prog->aux->xdp_has_frags) count++; return count; } int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf) { if (!dev->netdev_ops->ndo_bpf) return -EOPNOTSUPP; if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && bpf->command == XDP_SETUP_PROG && bpf->prog && !bpf->prog->aux->xdp_has_frags) { NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using tcp-data-split"); return -EBUSY; } if (dev_get_min_mp_channel_count(dev)) { NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider"); return -EBUSY; } return dev->netdev_ops->ndo_bpf(dev, bpf); } EXPORT_SYMBOL_GPL(netif_xdp_propagate); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); return prog ? prog->aux->id : 0; } static void dev_xdp_set_link(struct net_device *dev, enum bpf_xdp_mode mode, struct bpf_xdp_link *link) { dev->xdp_state[mode].link = link; dev->xdp_state[mode].prog = NULL; } static void dev_xdp_set_prog(struct net_device *dev, enum bpf_xdp_mode mode, struct bpf_prog *prog) { dev->xdp_state[mode].link = NULL; dev->xdp_state[mode].prog = prog; } static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode, bpf_op_t bpf_op, struct netlink_ext_ack *extack, u32 flags, struct bpf_prog *prog) { struct netdev_bpf xdp; int err; netdev_ops_assert_locked(dev); if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED && prog && !prog->aux->xdp_has_frags) { NL_SET_ERR_MSG(extack, "unable to install XDP to device using tcp-data-split"); return -EBUSY; } if (dev_get_min_mp_channel_count(dev)) { NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider"); return -EBUSY; } memset(&xdp, 0, sizeof(xdp)); xdp.command = mode == XDP_MODE_HW ? XDP_SETUP_PROG_HW : XDP_SETUP_PROG; xdp.extack = extack; xdp.flags = flags; xdp.prog = prog; /* Drivers assume refcnt is already incremented (i.e, prog pointer is * "moved" into driver), so they don't increment it on their own, but * they do decrement refcnt when program is detached or replaced. * Given net_device also owns link/prog, we need to bump refcnt here * to prevent drivers from underflowing it. */ if (prog) bpf_prog_inc(prog); err = bpf_op(dev, &xdp); if (err) { if (prog) bpf_prog_put(prog); return err; } if (mode != XDP_MODE_HW) bpf_prog_change_xdp(dev_xdp_prog(dev, mode), prog); return 0; } static void dev_xdp_uninstall(struct net_device *dev) { struct bpf_xdp_link *link; struct bpf_prog *prog; enum bpf_xdp_mode mode; bpf_op_t bpf_op; ASSERT_RTNL(); for (mode = XDP_MODE_SKB; mode < __MAX_XDP_MODE; mode++) { prog = dev_xdp_prog(dev, mode); if (!prog) continue; bpf_op = dev_xdp_bpf_op(dev, mode); if (!bpf_op) continue; WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); /* auto-detach link from net device */ link = dev_xdp_link(dev, mode); if (link) link->dev = NULL; else bpf_prog_put(prog); dev_xdp_set_link(dev, mode, NULL); } } static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog, u32 flags) { unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; struct net_device *upper; struct list_head *iter; enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err; ASSERT_RTNL(); /* either link or prog attachment, never both */ if (link && (new_prog || old_prog)) return -EINVAL; /* link supports only XDP mode flags */ if (link && (flags & ~XDP_FLAGS_MODES)) { NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); return -EINVAL; } /* just one XDP mode bit should be set, zero defaults to drv/skb mode */ if (num_modes > 1) { NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); return -EINVAL; } /* avoid ambiguity if offload + drv/skb mode progs are both loaded */ if (!num_modes && dev_xdp_prog_count(dev) > 1) { NL_SET_ERR_MSG(extack, "More than one program loaded, unset mode is ambiguous"); return -EINVAL; } /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); return -EINVAL; } mode = dev_xdp_mode(dev, flags); /* can't replace attached link */ if (dev_xdp_link(dev, mode)) { NL_SET_ERR_MSG(extack, "Can't replace active BPF XDP link"); return -EBUSY; } /* don't allow if an upper device already has a program */ netdev_for_each_upper_dev_rcu(dev, upper, iter) { if (dev_xdp_prog_count(upper) > 0) { NL_SET_ERR_MSG(extack, "Cannot attach when an upper device already has a program"); return -EEXIST; } } cur_prog = dev_xdp_prog(dev, mode); /* can't replace attached prog with link */ if (link && cur_prog) { NL_SET_ERR_MSG(extack, "Can't replace active XDP program with BPF link"); return -EBUSY; } if ((flags & XDP_FLAGS_REPLACE) && cur_prog != old_prog) { NL_SET_ERR_MSG(extack, "Active program does not match expected"); return -EEXIST; } /* put effective new program into new_prog */ if (link) new_prog = link->link.prog; if (new_prog) { bool offload = mode == XDP_MODE_HW; enum bpf_xdp_mode other_mode = mode == XDP_MODE_SKB ? XDP_MODE_DRV : XDP_MODE_SKB; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && cur_prog) { NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; } if (!offload && dev_xdp_prog(dev, other_mode)) { NL_SET_ERR_MSG(extack, "Native and generic XDP can't be active at the same time"); return -EEXIST; } if (!offload && bpf_prog_is_offloaded(new_prog->aux)) { NL_SET_ERR_MSG(extack, "Using offloaded program without HW_MODE flag is not supported"); return -EINVAL; } if (bpf_prog_is_dev_bound(new_prog->aux) && !bpf_offload_dev_match(new_prog, dev)) { NL_SET_ERR_MSG(extack, "Program bound to different device"); return -EINVAL; } if (bpf_prog_is_dev_bound(new_prog->aux) && mode == XDP_MODE_SKB) { NL_SET_ERR_MSG(extack, "Can't attach device-bound programs in generic mode"); return -EINVAL; } if (new_prog->expected_attach_type == BPF_XDP_DEVMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_DEVMAP programs can not be attached to a device"); return -EINVAL; } if (new_prog->expected_attach_type == BPF_XDP_CPUMAP) { NL_SET_ERR_MSG(extack, "BPF_XDP_CPUMAP programs can not be attached to a device"); return -EINVAL; } } /* don't call drivers if the effective program didn't change */ if (new_prog != cur_prog) { bpf_op = dev_xdp_bpf_op(dev, mode); if (!bpf_op) { NL_SET_ERR_MSG(extack, "Underlying driver does not support XDP in native mode"); return -EOPNOTSUPP; } err = dev_xdp_install(dev, mode, bpf_op, extack, flags, new_prog); if (err) return err; } if (link) dev_xdp_set_link(dev, mode, link); else dev_xdp_set_prog(dev, mode, new_prog); if (cur_prog) bpf_prog_put(cur_prog); return 0; } static int dev_xdp_attach_link(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link) { return dev_xdp_attach(dev, extack, link, NULL, NULL, link->flags); } static int dev_xdp_detach_link(struct net_device *dev, struct netlink_ext_ack *extack, struct bpf_xdp_link *link) { enum bpf_xdp_mode mode; bpf_op_t bpf_op; ASSERT_RTNL(); mode = dev_xdp_mode(dev, link->flags); if (dev_xdp_link(dev, mode) != link) return -EINVAL; bpf_op = dev_xdp_bpf_op(dev, mode); WARN_ON(dev_xdp_install(dev, mode, bpf_op, NULL, 0, NULL)); dev_xdp_set_link(dev, mode, NULL); return 0; } static void bpf_xdp_link_release(struct bpf_link *link) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); rtnl_lock(); /* if racing with net_device's tear down, xdp_link->dev might be * already NULL, in which case link was already auto-detached */ if (xdp_link->dev) { netdev_lock_ops(xdp_link->dev); WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link)); netdev_unlock_ops(xdp_link->dev); xdp_link->dev = NULL; } rtnl_unlock(); } static int bpf_xdp_link_detach(struct bpf_link *link) { bpf_xdp_link_release(link); return 0; } static void bpf_xdp_link_dealloc(struct bpf_link *link) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); kfree(xdp_link); } static void bpf_xdp_link_show_fdinfo(const struct bpf_link *link, struct seq_file *seq) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); u32 ifindex = 0; rtnl_lock(); if (xdp_link->dev) ifindex = xdp_link->dev->ifindex; rtnl_unlock(); seq_printf(seq, "ifindex:\t%u\n", ifindex); } static int bpf_xdp_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); u32 ifindex = 0; rtnl_lock(); if (xdp_link->dev) ifindex = xdp_link->dev->ifindex; rtnl_unlock(); info->xdp.ifindex = ifindex; return 0; } static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog) { struct bpf_xdp_link *xdp_link = container_of(link, struct bpf_xdp_link, link); enum bpf_xdp_mode mode; bpf_op_t bpf_op; int err = 0; rtnl_lock(); /* link might have been auto-released already, so fail */ if (!xdp_link->dev) { err = -ENOLINK; goto out_unlock; } if (old_prog && link->prog != old_prog) { err = -EPERM; goto out_unlock; } old_prog = link->prog; if (old_prog->type != new_prog->type || old_prog->expected_attach_type != new_prog->expected_attach_type) { err = -EINVAL; goto out_unlock; } if (old_prog == new_prog) { /* no-op, don't disturb drivers */ bpf_prog_put(new_prog); goto out_unlock; } netdev_lock_ops(xdp_link->dev); mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags); bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode); err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL, xdp_link->flags, new_prog); netdev_unlock_ops(xdp_link->dev); if (err) goto out_unlock; old_prog = xchg(&link->prog, new_prog); bpf_prog_put(old_prog); out_unlock: rtnl_unlock(); return err; } static const struct bpf_link_ops bpf_xdp_link_lops = { .release = bpf_xdp_link_release, .dealloc = bpf_xdp_link_dealloc, .detach = bpf_xdp_link_detach, .show_fdinfo = bpf_xdp_link_show_fdinfo, .fill_link_info = bpf_xdp_link_fill_link_info, .update_prog = bpf_xdp_link_update, }; int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct net *net = current->nsproxy->net_ns; struct bpf_link_primer link_primer; struct netlink_ext_ack extack = {}; struct bpf_xdp_link *link; struct net_device *dev; int err, fd; rtnl_lock(); dev = dev_get_by_index(net, attr->link_create.target_ifindex); if (!dev) { rtnl_unlock(); return -EINVAL; } link = kzalloc(sizeof(*link), GFP_USER); if (!link) { err = -ENOMEM; goto unlock; } bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog, attr->link_create.attach_type); link->dev = dev; link->flags = attr->link_create.flags; err = bpf_link_prime(&link->link, &link_primer); if (err) { kfree(link); goto unlock; } netdev_lock_ops(dev); err = dev_xdp_attach_link(dev, &extack, link); netdev_unlock_ops(dev); rtnl_unlock(); if (err) { link->dev = NULL; bpf_link_cleanup(&link_primer); trace_bpf_xdp_link_attach_failed(extack._msg); goto out_put_dev; } fd = bpf_link_settle(&link_primer); /* link itself doesn't hold dev's refcnt to not complicate shutdown */ dev_put(dev); return fd; unlock: rtnl_unlock(); out_put_dev: dev_put(dev); return err; } /** * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device * @extack: netlink extended ack * @fd: new program fd or negative value to clear * @expected_fd: old program fd that userspace expects to replace or clear * @flags: xdp-related flags * * Set or clear a bpf program for a device */ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, int fd, int expected_fd, u32 flags) { enum bpf_xdp_mode mode = dev_xdp_mode(dev, flags); struct bpf_prog *new_prog = NULL, *old_prog = NULL; int err; ASSERT_RTNL(); if (fd >= 0) { new_prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, mode != XDP_MODE_SKB); if (IS_ERR(new_prog)) return PTR_ERR(new_prog); } if (expected_fd >= 0) { old_prog = bpf_prog_get_type_dev(expected_fd, BPF_PROG_TYPE_XDP, mode != XDP_MODE_SKB); if (IS_ERR(old_prog)) { err = PTR_ERR(old_prog); old_prog = NULL; goto err_out; } } err = dev_xdp_attach(dev, extack, NULL, new_prog, old_prog, flags); err_out: if (err && new_prog) bpf_prog_put(new_prog); if (old_prog) bpf_prog_put(old_prog); return err; } u32 dev_get_min_mp_channel_count(const struct net_device *dev) { int i; netdev_ops_assert_locked(dev); for (i = dev->real_num_rx_queues - 1; i >= 0; i--) if (dev->_rx[i].mp_params.mp_priv) /* The channel count is the idx plus 1. */ return i + 1; return 0; } /** * dev_index_reserve() - allocate an ifindex in a namespace * @net: the applicable net namespace * @ifindex: requested ifindex, pass %0 to get one allocated * * Allocate a ifindex for a new device. Caller must either use the ifindex * to store the device (via list_netdevice()) or call dev_index_release() * to give the index up. * * Return: a suitable unique value for a new device interface number or -errno. */ static int dev_index_reserve(struct net *net, u32 ifindex) { int err; if (ifindex > INT_MAX) { DEBUG_NET_WARN_ON_ONCE(1); return -EINVAL; } if (!ifindex) err = xa_alloc_cyclic(&net->dev_by_index, &ifindex, NULL, xa_limit_31b, &net->ifindex, GFP_KERNEL); else err = xa_insert(&net->dev_by_index, ifindex, NULL, GFP_KERNEL); if (err < 0) return err; return ifindex; } static void dev_index_release(struct net *net, int ifindex) { /* Expect only unused indexes, unlist_netdevice() removes the used */ WARN_ON(xa_erase(&net->dev_by_index, ifindex)); } static bool from_cleanup_net(void) { #ifdef CONFIG_NET_NS return current == READ_ONCE(cleanup_net_task); #else return false; #endif } /* Delayed registration/unregisteration */ LIST_HEAD(net_todo_list); DECLARE_WAIT_QUEUE_HEAD(netdev_unregistering_wq); atomic_t dev_unreg_count = ATOMIC_INIT(0); static void net_set_todo(struct net_device *dev) { list_add_tail(&dev->todo_list, &net_todo_list); } static netdev_features_t netdev_sync_upper_features(struct net_device *lower, struct net_device *upper, netdev_features_t features) { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; int feature_bit; for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(upper->wanted_features & feature) && (features & feature)) { netdev_dbg(lower, "Dropping feature %pNF, upper dev %s has it off.\n", &feature, upper->name); features &= ~feature; } } return features; } static void netdev_sync_lower_features(struct net_device *upper, struct net_device *lower, netdev_features_t features) { netdev_features_t upper_disables = NETIF_F_UPPER_DISABLES; netdev_features_t feature; int feature_bit; for_each_netdev_feature(upper_disables, feature_bit) { feature = __NETIF_F_BIT(feature_bit); if (!(features & feature) && (lower->features & feature)) { netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); netdev_lock_ops(lower); lower->wanted_features &= ~feature; __netdev_update_features(lower); if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); else netdev_features_change(lower); netdev_unlock_ops(lower); } } } static bool netdev_has_ip_or_hw_csum(netdev_features_t features) { netdev_features_t ip_csum_mask = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; bool ip_csum = (features & ip_csum_mask) == ip_csum_mask; bool hw_csum = features & NETIF_F_HW_CSUM; return ip_csum || hw_csum; } static netdev_features_t netdev_fix_features(struct net_device *dev, netdev_features_t features) { /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { netdev_warn(dev, "mixed HW and IP checksum settings.\n"); features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } /* TSO requires that SG is present as well. */ if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); features &= ~NETIF_F_ALL_TSO; } if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) && !(features & NETIF_F_IP_CSUM)) { netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n"); features &= ~NETIF_F_TSO; features &= ~NETIF_F_TSO_ECN; } if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) && !(features & NETIF_F_IPV6_CSUM)) { netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n"); features &= ~NETIF_F_TSO6; } /* TSO with IPv4 ID mangling requires IPv4 TSO be enabled */ if ((features & NETIF_F_TSO_MANGLEID) && !(features & NETIF_F_TSO)) features &= ~NETIF_F_TSO_MANGLEID; /* TSO ECN requires that TSO is present as well. */ if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) features &= ~NETIF_F_TSO_ECN; /* Software GSO depends on SG. */ if ((features & NETIF_F_GSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping NETIF_F_GSO since no SG feature.\n"); features &= ~NETIF_F_GSO; } /* GSO partial features require GSO partial be set */ if ((features & dev->gso_partial_features) && !(features & NETIF_F_GSO_PARTIAL)) { netdev_dbg(dev, "Dropping partially supported GSO features since no GSO partial.\n"); features &= ~dev->gso_partial_features; } if (!(features & NETIF_F_RXCSUM)) { /* NETIF_F_GRO_HW implies doing RXCSUM since every packet * successfully merged by hardware must also have the * checksum verified by hardware. If the user does not * want to enable RXCSUM, logically, we should disable GRO_HW. */ if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping NETIF_F_GRO_HW since no RXCSUM feature.\n"); features &= ~NETIF_F_GRO_HW; } } /* LRO/HW-GRO features cannot be combined with RX-FCS */ if (features & NETIF_F_RXFCS) { if (features & NETIF_F_LRO) { netdev_dbg(dev, "Dropping LRO feature since RX-FCS is requested.\n"); features &= ~NETIF_F_LRO; } if (features & NETIF_F_GRO_HW) { netdev_dbg(dev, "Dropping HW-GRO feature since RX-FCS is requested.\n"); features &= ~NETIF_F_GRO_HW; } } if ((features & NETIF_F_GRO_HW) && (features & NETIF_F_LRO)) { netdev_dbg(dev, "Dropping LRO feature since HW-GRO is requested.\n"); features &= ~NETIF_F_LRO; } if ((features & NETIF_F_HW_TLS_TX) && !netdev_has_ip_or_hw_csum(features)) { netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n"); features &= ~NETIF_F_HW_TLS_TX; } if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) { netdev_dbg(dev, "Dropping TLS RX HW offload feature since no RXCSUM feature.\n"); features &= ~NETIF_F_HW_TLS_RX; } if ((features & NETIF_F_GSO_UDP_L4) && !netdev_has_ip_or_hw_csum(features)) { netdev_dbg(dev, "Dropping USO feature since no CSUM feature.\n"); features &= ~NETIF_F_GSO_UDP_L4; } return features; } int __netdev_update_features(struct net_device *dev) { struct net_device *upper, *lower; netdev_features_t features; struct list_head *iter; int err = -1; ASSERT_RTNL(); netdev_ops_assert_locked(dev); features = netdev_get_wanted_features(dev); if (dev->netdev_ops->ndo_fix_features) features = dev->netdev_ops->ndo_fix_features(dev, features); /* driver might be less strict about feature dependencies */ features = netdev_fix_features(dev, features); /* some features can't be enabled if they're off on an upper device */ netdev_for_each_upper_dev_rcu(dev, upper, iter) features = netdev_sync_upper_features(dev, upper, features); if (dev->features == features) goto sync_lower; netdev_dbg(dev, "Features changed: %pNF -> %pNF\n", &dev->features, &features); if (dev->netdev_ops->ndo_set_features) err = dev->netdev_ops->ndo_set_features(dev, features); else err = 0; if (unlikely(err < 0)) { netdev_err(dev, "set_features() failed (%d); wanted %pNF, left %pNF\n", err, &features, &dev->features); /* return non-0 since some features might have changed and * it's better to fire a spurious notification than miss it */ return -1; } sync_lower: /* some features must be disabled on lower devices when disabled * on an upper device (think: bonding master or bridge) */ netdev_for_each_lower_dev(dev, lower, iter) netdev_sync_lower_features(dev, lower, features); if (!err) { netdev_features_t diff = features ^ dev->features; if (diff & NETIF_F_RX_UDP_TUNNEL_PORT) { /* udp_tunnel_{get,drop}_rx_info both need * NETIF_F_RX_UDP_TUNNEL_PORT enabled on the * device, or they won't do anything. * Thus we need to update dev->features * *before* calling udp_tunnel_get_rx_info, * but *after* calling udp_tunnel_drop_rx_info. */ udp_tunnel_nic_lock(dev); if (features & NETIF_F_RX_UDP_TUNNEL_PORT) { dev->features = features; udp_tunnel_get_rx_info(dev); } else { udp_tunnel_drop_rx_info(dev); } udp_tunnel_nic_unlock(dev); } if (diff & NETIF_F_HW_VLAN_CTAG_FILTER) { if (features & NETIF_F_HW_VLAN_CTAG_FILTER) { dev->features = features; err |= vlan_get_rx_ctag_filter_info(dev); } else { vlan_drop_rx_ctag_filter_info(dev); } } if (diff & NETIF_F_HW_VLAN_STAG_FILTER) { if (features & NETIF_F_HW_VLAN_STAG_FILTER) { dev->features = features; err |= vlan_get_rx_stag_filter_info(dev); } else { vlan_drop_rx_stag_filter_info(dev); } } dev->features = features; } return err < 0 ? 0 : 1; } /** * netdev_update_features - recalculate device features * @dev: the device to check * * Recalculate dev->features set and send notifications if it * has changed. Should be called after driver or hardware dependent * conditions might have changed that influence the features. */ void netdev_update_features(struct net_device *dev) { if (__netdev_update_features(dev)) netdev_features_change(dev); } EXPORT_SYMBOL(netdev_update_features); /** * netdev_change_features - recalculate device features * @dev: the device to check * * Recalculate dev->features set and send notifications even * if they have not changed. Should be called instead of * netdev_update_features() if also dev->vlan_features might * have changed to allow the changes to be propagated to stacked * VLAN devices. */ void netdev_change_features(struct net_device *dev) { __netdev_update_features(dev); netdev_features_change(dev); } EXPORT_SYMBOL(netdev_change_features); /** * netif_stacked_transfer_operstate - transfer operstate * @rootdev: the root or lower level device to transfer state from * @dev: the device to transfer operstate to * * Transfer operational state from root to device. This is normally * called when a stacking relationship exists between the root * device and the device(a leaf device). */ void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev) { if (rootdev->operstate == IF_OPER_DORMANT) netif_dormant_on(dev); else netif_dormant_off(dev); if (rootdev->operstate == IF_OPER_TESTING) netif_testing_on(dev); else netif_testing_off(dev); if (netif_carrier_ok(rootdev)) netif_carrier_on(dev); else netif_carrier_off(dev); } EXPORT_SYMBOL(netif_stacked_transfer_operstate); static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; struct netdev_rx_queue *rx; size_t sz = count * sizeof(*rx); int err = 0; BUG_ON(count < 1); rx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!rx) return -ENOMEM; dev->_rx = rx; for (i = 0; i < count; i++) { rx[i].dev = dev; /* XDP RX-queue setup */ err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0); if (err < 0) goto err_rxq_info; } return 0; err_rxq_info: /* Rollback successful reg's and free other resources */ while (i--) xdp_rxq_info_unreg(&rx[i].xdp_rxq); kvfree(dev->_rx); dev->_rx = NULL; return err; } static void netif_free_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; /* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */ if (!dev->_rx) return; for (i = 0; i < count; i++) xdp_rxq_info_unreg(&dev->_rx[i].xdp_rxq); kvfree(dev->_rx); } static void netdev_init_one_queue(struct net_device *dev, struct netdev_queue *queue, void *_unused) { /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); queue->xmit_lock_owner = -1; netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; #ifdef CONFIG_BQL dql_init(&queue->dql, HZ); #endif } static void netif_free_tx_queues(struct net_device *dev) { kvfree(dev->_tx); } static int netif_alloc_netdev_queues(struct net_device *dev) { unsigned int count = dev->num_tx_queues; struct netdev_queue *tx; size_t sz = count * sizeof(*tx); if (count < 1 || count > 0xffff) return -EINVAL; tx = kvzalloc(sz, GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!tx) return -ENOMEM; dev->_tx = tx; netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); spin_lock_init(&dev->tx_global_lock); return 0; } void netif_tx_stop_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_stop_queue(txq); } } EXPORT_SYMBOL(netif_tx_stop_all_queues); static int netdev_do_alloc_pcpu_stats(struct net_device *dev) { void __percpu *v; /* Drivers implementing ndo_get_peer_dev must support tstat * accounting, so that skb_do_redirect() can bump the dev's * RX stats upon network namespace switch. */ if (dev->netdev_ops->ndo_get_peer_dev && dev->pcpu_stat_type != NETDEV_PCPU_STAT_TSTATS) return -EOPNOTSUPP; switch (dev->pcpu_stat_type) { case NETDEV_PCPU_STAT_NONE: return 0; case NETDEV_PCPU_STAT_LSTATS: v = dev->lstats = netdev_alloc_pcpu_stats(struct pcpu_lstats); break; case NETDEV_PCPU_STAT_TSTATS: v = dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); break; case NETDEV_PCPU_STAT_DSTATS: v = dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats); break; default: return -EINVAL; } return v ? 0 : -ENOMEM; } static void netdev_do_free_pcpu_stats(struct net_device *dev) { switch (dev->pcpu_stat_type) { case NETDEV_PCPU_STAT_NONE: return; case NETDEV_PCPU_STAT_LSTATS: free_percpu(dev->lstats); break; case NETDEV_PCPU_STAT_TSTATS: free_percpu(dev->tstats); break; case NETDEV_PCPU_STAT_DSTATS: free_percpu(dev->dstats); break; } } static void netdev_free_phy_link_topology(struct net_device *dev) { struct phy_link_topology *topo = dev->link_topo; if (IS_ENABLED(CONFIG_PHYLIB) && topo) { xa_destroy(&topo->phys); kfree(topo); dev->link_topo = NULL; } } /** * register_netdevice() - register a network device * @dev: device to register * * Take a prepared network device structure and make it externally accessible. * A %NETDEV_REGISTER message is sent to the netdev notifier chain. * Callers must hold the rtnl lock - you may want register_netdev() * instead of this. */ int register_netdevice(struct net_device *dev) { int ret; struct net *net = dev_net(dev); BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE < NETDEV_FEATURE_COUNT); BUG_ON(dev_boot_phase); ASSERT_RTNL(); might_sleep(); /* When net_device's are persistent, this will be fatal. */ BUG_ON(dev->reg_state != NETREG_UNINITIALIZED); BUG_ON(!net); ret = ethtool_check_ops(dev->ethtool_ops); if (ret) return ret; /* rss ctx ID 0 is reserved for the default context, start from 1 */ xa_init_flags(&dev->ethtool->rss_ctx, XA_FLAGS_ALLOC1); mutex_init(&dev->ethtool->rss_lock); spin_lock_init(&dev->addr_list_lock); netdev_set_addr_lockdep_class(dev); ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) goto out; ret = -ENOMEM; dev->name_node = netdev_name_node_head_alloc(dev); if (!dev->name_node) goto out; /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); if (ret) { if (ret > 0) ret = -EIO; goto err_free_name; } } if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_CTAG_FILTER) && (!dev->netdev_ops->ndo_vlan_rx_add_vid || !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); ret = -EINVAL; goto err_uninit; } ret = netdev_do_alloc_pcpu_stats(dev); if (ret) goto err_uninit; ret = dev_index_reserve(net, dev->ifindex); if (ret < 0) goto err_free_pcpu; dev->ifindex = ret; /* Transfer changeable features to wanted_features and enable * software offloads (GSO and GRO). */ dev->hw_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_SOFT_FEATURES_OFF); dev->features |= NETIF_F_SOFT_FEATURES; if (dev->udp_tunnel_nic_info) { dev->features |= NETIF_F_RX_UDP_TUNNEL_PORT; dev->hw_features |= NETIF_F_RX_UDP_TUNNEL_PORT; } dev->wanted_features = dev->features & dev->hw_features; if (!(dev->flags & IFF_LOOPBACK)) dev->hw_features |= NETIF_F_NOCACHE_COPY; /* If IPv4 TCP segmentation offload is supported we should also * allow the device to enable segmenting the frame with the option * of ignoring a static IP ID value. This doesn't enable the * feature itself but allows the user to enable it later. */ if (dev->hw_features & NETIF_F_TSO) dev->hw_features |= NETIF_F_TSO_MANGLEID; if (dev->vlan_features & NETIF_F_TSO) dev->vlan_features |= NETIF_F_TSO_MANGLEID; if (dev->mpls_features & NETIF_F_TSO) dev->mpls_features |= NETIF_F_TSO_MANGLEID; if (dev->hw_enc_features & NETIF_F_TSO) dev->hw_enc_features |= NETIF_F_TSO_MANGLEID; /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. */ dev->vlan_features |= NETIF_F_HIGHDMA; /* Make NETIF_F_SG inheritable to tunnel devices. */ dev->hw_enc_features |= NETIF_F_SG | NETIF_F_GSO_PARTIAL; /* Make NETIF_F_SG inheritable to MPLS. */ dev->mpls_features |= NETIF_F_SG; ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) goto err_ifindex_release; ret = netdev_register_kobject(dev); netdev_lock(dev); WRITE_ONCE(dev->reg_state, ret ? NETREG_UNREGISTERED : NETREG_REGISTERED); netdev_unlock(dev); if (ret) goto err_uninit_notify; netdev_lock_ops(dev); __netdev_update_features(dev); netdev_unlock_ops(dev); /* * Default initial state at registry is that the * device is present. */ set_bit(__LINK_STATE_PRESENT, &dev->state); linkwatch_init_dev(dev); dev_init_scheduler(dev); netdev_hold(dev, &dev->dev_registered_tracker, GFP_KERNEL); list_netdevice(dev); add_device_randomness(dev->dev_addr, dev->addr_len); /* If the device has permanent device address, driver should * set dev_addr and also addr_assign_type should be set to * NET_ADDR_PERM (default value). */ if (dev->addr_assign_type == NET_ADDR_PERM) memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ netdev_lock_ops(dev); ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); netdev_unlock_ops(dev); ret = notifier_to_errno(ret); if (ret) { /* Expect explicit free_netdev() on failure */ dev->needs_free_netdev = false; unregister_netdevice_queue(dev, NULL); goto out; } /* * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ if (!(dev->rtnl_link_ops && dev->rtnl_link_initializing)) rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); out: return ret; err_uninit_notify: call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); err_ifindex_release: dev_index_release(net, dev->ifindex); err_free_pcpu: netdev_do_free_pcpu_stats(dev); err_uninit: if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (dev->priv_destructor) dev->priv_destructor(dev); err_free_name: netdev_name_node_free(dev->name_node); goto out; } EXPORT_SYMBOL(register_netdevice); /* Initialize the core of a dummy net device. * The setup steps dummy netdevs need which normal netdevs get by going * through register_netdevice(). */ static void init_dummy_netdev(struct net_device *dev) { /* make sure we BUG if trying to hit standard * register/unregister code path */ dev->reg_state = NETREG_DUMMY; /* a dummy interface is started by default */ set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); /* Note : We dont allocate pcpu_refcnt for dummy devices, * because users of this 'device' dont need to change * its refcount. */ } /** * register_netdev - register a network device * @dev: device to register * * Take a completed network device structure and add it to the kernel * interfaces. A %NETDEV_REGISTER message is sent to the netdev notifier * chain. 0 is returned on success. A negative errno code is returned * on a failure to set up the device, or if the name is a duplicate. * * This is a wrapper around register_netdevice that takes the rtnl semaphore * and expands the device name if you passed a format string to * alloc_netdev. */ int register_netdev(struct net_device *dev) { struct net *net = dev_net(dev); int err; if (rtnl_net_lock_killable(net)) return -EINTR; err = register_netdevice(dev); rtnl_net_unlock(net); return err; } EXPORT_SYMBOL(register_netdev); int netdev_refcnt_read(const struct net_device *dev) { #ifdef CONFIG_PCPU_DEV_REFCNT int i, refcnt = 0; for_each_possible_cpu(i) refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); return refcnt; #else return refcount_read(&dev->dev_refcnt); #endif } EXPORT_SYMBOL(netdev_refcnt_read); int netdev_unregister_timeout_secs __read_mostly = 10; #define WAIT_REFS_MIN_MSECS 1 #define WAIT_REFS_MAX_MSECS 250 /** * netdev_wait_allrefs_any - wait until all references are gone. * @list: list of net_devices to wait on * * This is called when unregistering network devices. * * Any protocol or device that holds a reference should register * for netdevice notification, and cleanup and put back the * reference if they receive an UNREGISTER event. * We can get stuck here if buggy protocols don't correctly * call dev_put. */ static struct net_device *netdev_wait_allrefs_any(struct list_head *list) { unsigned long rebroadcast_time, warning_time; struct net_device *dev; int wait = 0; rebroadcast_time = warning_time = jiffies; list_for_each_entry(dev, list, todo_list) if (netdev_refcnt_read(dev) == 1) return dev; while (true) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); /* Rebroadcast unregister notification */ list_for_each_entry(dev, list, todo_list) call_netdevice_notifiers(NETDEV_UNREGISTER, dev); __rtnl_unlock(); rcu_barrier(); rtnl_lock(); list_for_each_entry(dev, list, todo_list) if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { /* We must not have linkwatch events * pending on unregister. If this * happens, we simply run the queue * unscheduled, resulting in a noop * for this device. */ linkwatch_run_queue(); break; } __rtnl_unlock(); rebroadcast_time = jiffies; } rcu_barrier(); if (!wait) { wait = WAIT_REFS_MIN_MSECS; } else { msleep(wait); wait = min(wait << 1, WAIT_REFS_MAX_MSECS); } list_for_each_entry(dev, list, todo_list) if (netdev_refcnt_read(dev) == 1) return dev; if (time_after(jiffies, warning_time + READ_ONCE(netdev_unregister_timeout_secs) * HZ)) { list_for_each_entry(dev, list, todo_list) { pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n", dev->name, netdev_refcnt_read(dev)); ref_tracker_dir_print(&dev->refcnt_tracker, 10); } warning_time = jiffies; } } } /* The sequence is: * * rtnl_lock(); * ... * register_netdevice(x1); * register_netdevice(x2); * ... * unregister_netdevice(y1); * unregister_netdevice(y2); * ... * rtnl_unlock(); * free_netdev(y1); * free_netdev(y2); * * We are invoked by rtnl_unlock(). * This allows us to deal with problems: * 1) We can delete sysfs objects which invoke hotplug * without deadlocking with linkwatch via keventd. * 2) Since we run with the RTNL semaphore not held, we can sleep * safely in order to wait for the netdev refcnt to drop to zero. * * We must not return until all unregister events added during * the interval the lock was held have been completed. */ void netdev_run_todo(void) { struct net_device *dev, *tmp; struct list_head list; int cnt; #ifdef CONFIG_LOCKDEP struct list_head unlink_list; list_replace_init(&net_unlink_list, &unlink_list); while (!list_empty(&unlink_list)) { dev = list_first_entry(&unlink_list, struct net_device, unlink_list); list_del_init(&dev->unlink_list); dev->nested_level = dev->lower_level - 1; } #endif /* Snapshot list, allow later requests */ list_replace_init(&net_todo_list, &list); __rtnl_unlock(); /* Wait for rcu callbacks to finish before next phase */ if (!list_empty(&list)) rcu_barrier(); list_for_each_entry_safe(dev, tmp, &list, todo_list) { if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { netdev_WARN(dev, "run_todo but not unregistering\n"); list_del(&dev->todo_list); continue; } netdev_lock(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERED); netdev_unlock(dev); linkwatch_sync_dev(dev); } cnt = 0; while (!list_empty(&list)) { dev = netdev_wait_allrefs_any(&list); list_del(&dev->todo_list); /* paranoia */ BUG_ON(netdev_refcnt_read(dev) != 1); BUG_ON(!list_empty(&dev->ptype_all)); BUG_ON(!list_empty(&dev->ptype_specific)); WARN_ON(rcu_access_pointer(dev->ip_ptr)); WARN_ON(rcu_access_pointer(dev->ip6_ptr)); netdev_do_free_pcpu_stats(dev); if (dev->priv_destructor) dev->priv_destructor(dev); if (dev->needs_free_netdev) free_netdev(dev); cnt++; /* Free network device */ kobject_put(&dev->dev.kobj); } if (cnt && atomic_sub_and_test(cnt, &dev_unreg_count)) wake_up(&netdev_unregistering_wq); } /* Collate per-cpu network dstats statistics * * Read per-cpu network statistics from dev->dstats and populate the related * fields in @s. */ static void dev_fetch_dstats(struct rtnl_link_stats64 *s, const struct pcpu_dstats __percpu *dstats) { int cpu; for_each_possible_cpu(cpu) { u64 rx_packets, rx_bytes, rx_drops; u64 tx_packets, tx_bytes, tx_drops; const struct pcpu_dstats *stats; unsigned int start; stats = per_cpu_ptr(dstats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); rx_packets = u64_stats_read(&stats->rx_packets); rx_bytes = u64_stats_read(&stats->rx_bytes); rx_drops = u64_stats_read(&stats->rx_drops); tx_packets = u64_stats_read(&stats->tx_packets); tx_bytes = u64_stats_read(&stats->tx_bytes); tx_drops = u64_stats_read(&stats->tx_drops); } while (u64_stats_fetch_retry(&stats->syncp, start)); s->rx_packets += rx_packets; s->rx_bytes += rx_bytes; s->rx_dropped += rx_drops; s->tx_packets += tx_packets; s->tx_bytes += tx_bytes; s->tx_dropped += tx_drops; } } /* ndo_get_stats64 implementation for dtstats-based accounting. * * Populate @s from dev->stats and dev->dstats. This is used internally by the * core for NETDEV_PCPU_STAT_DSTAT-type stats collection. */ static void dev_get_dstats64(const struct net_device *dev, struct rtnl_link_stats64 *s) { netdev_stats_to_stats64(s, &dev->stats); dev_fetch_dstats(s, dev->dstats); } /* Convert net_device_stats to rtnl_link_stats64. rtnl_link_stats64 has * all the same fields in the same order as net_device_stats, with only * the type differing, but rtnl_link_stats64 may have additional fields * at the end for newer counters. */ void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats) { size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t); const atomic_long_t *src = (atomic_long_t *)netdev_stats; u64 *dst = (u64 *)stats64; BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64)); for (i = 0; i < n; i++) dst[i] = (unsigned long)atomic_long_read(&src[i]); /* zero out counters that only exist in rtnl_link_stats64 */ memset((char *)stats64 + n * sizeof(u64), 0, sizeof(*stats64) - n * sizeof(u64)); } EXPORT_SYMBOL(netdev_stats_to_stats64); static __cold struct net_device_core_stats __percpu *netdev_core_stats_alloc( struct net_device *dev) { struct net_device_core_stats __percpu *p; p = alloc_percpu_gfp(struct net_device_core_stats, GFP_ATOMIC | __GFP_NOWARN); if (p && cmpxchg(&dev->core_stats, NULL, p)) free_percpu(p); /* This READ_ONCE() pairs with the cmpxchg() above */ return READ_ONCE(dev->core_stats); } noinline void netdev_core_stats_inc(struct net_device *dev, u32 offset) { /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); unsigned long __percpu *field; if (unlikely(!p)) { p = netdev_core_stats_alloc(dev); if (!p) return; } field = (unsigned long __percpu *)((void __percpu *)p + offset); this_cpu_inc(*field); } EXPORT_SYMBOL_GPL(netdev_core_stats_inc); /** * dev_get_stats - get network device statistics * @dev: device to get statistics from * @storage: place to store stats * * Get network statistics from device. Return @storage. * The device driver may provide its own method by setting * dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats; * otherwise the internal statistics structure is used. */ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage) { const struct net_device_ops *ops = dev->netdev_ops; const struct net_device_core_stats __percpu *p; /* * IPv{4,6} and udp tunnels share common stat helpers and use * different stat type (NETDEV_PCPU_STAT_TSTATS vs * NETDEV_PCPU_STAT_DSTATS). Ensure the accounting is consistent. */ BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_bytes) != offsetof(struct pcpu_dstats, rx_bytes)); BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, rx_packets) != offsetof(struct pcpu_dstats, rx_packets)); BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_bytes) != offsetof(struct pcpu_dstats, tx_bytes)); BUILD_BUG_ON(offsetof(struct pcpu_sw_netstats, tx_packets) != offsetof(struct pcpu_dstats, tx_packets)); if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); ops->ndo_get_stats64(dev, storage); } else if (ops->ndo_get_stats) { netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_TSTATS) { dev_get_tstats64(dev, storage); } else if (dev->pcpu_stat_type == NETDEV_PCPU_STAT_DSTATS) { dev_get_dstats64(dev, storage); } else { netdev_stats_to_stats64(storage, &dev->stats); } /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ p = READ_ONCE(dev->core_stats); if (p) { const struct net_device_core_stats *core_stats; int i; for_each_possible_cpu(i) { core_stats = per_cpu_ptr(p, i); storage->rx_dropped += READ_ONCE(core_stats->rx_dropped); storage->tx_dropped += READ_ONCE(core_stats->tx_dropped); storage->rx_nohandler += READ_ONCE(core_stats->rx_nohandler); storage->rx_otherhost_dropped += READ_ONCE(core_stats->rx_otherhost_dropped); } } return storage; } EXPORT_SYMBOL(dev_get_stats); /** * dev_fetch_sw_netstats - get per-cpu network device statistics * @s: place to store stats * @netstats: per-cpu network stats to read from * * Read per-cpu network statistics and populate the related fields in @s. */ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats) { int cpu; for_each_possible_cpu(cpu) { u64 rx_packets, rx_bytes, tx_packets, tx_bytes; const struct pcpu_sw_netstats *stats; unsigned int start; stats = per_cpu_ptr(netstats, cpu); do { start = u64_stats_fetch_begin(&stats->syncp); rx_packets = u64_stats_read(&stats->rx_packets); rx_bytes = u64_stats_read(&stats->rx_bytes); tx_packets = u64_stats_read(&stats->tx_packets); tx_bytes = u64_stats_read(&stats->tx_bytes); } while (u64_stats_fetch_retry(&stats->syncp, start)); s->rx_packets += rx_packets; s->rx_bytes += rx_bytes; s->tx_packets += tx_packets; s->tx_bytes += tx_bytes; } } EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats); /** * dev_get_tstats64 - ndo_get_stats64 implementation * @dev: device to get statistics from * @s: place to store stats * * Populate @s from dev->stats and dev->tstats. Can be used as * ndo_get_stats64() callback. */ void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s) { netdev_stats_to_stats64(s, &dev->stats); dev_fetch_sw_netstats(s, dev->tstats); } EXPORT_SYMBOL_GPL(dev_get_tstats64); struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { struct netdev_queue *queue = dev_ingress_queue(dev); #ifdef CONFIG_NET_CLS_ACT if (queue) return queue; queue = kzalloc(sizeof(*queue), GFP_KERNEL); if (!queue) return NULL; netdev_init_one_queue(dev, queue, NULL); RCU_INIT_POINTER(queue->qdisc, &noop_qdisc); RCU_INIT_POINTER(queue->qdisc_sleeping, &noop_qdisc); rcu_assign_pointer(dev->ingress_queue, queue); #endif return queue; } static const struct ethtool_ops default_ethtool_ops; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops) { if (dev->ethtool_ops == &default_ethtool_ops) dev->ethtool_ops = ops; } EXPORT_SYMBOL_GPL(netdev_set_default_ethtool_ops); /** * netdev_sw_irq_coalesce_default_on() - enable SW IRQ coalescing by default * @dev: netdev to enable the IRQ coalescing on * * Sets a conservative default for SW IRQ coalescing. Users can use * sysfs attributes to override the default values. */ void netdev_sw_irq_coalesce_default_on(struct net_device *dev) { WARN_ON(dev->reg_state == NETREG_REGISTERED); if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { netdev_set_gro_flush_timeout(dev, 20000); netdev_set_defer_hard_irqs(dev, 1); } } EXPORT_SYMBOL_GPL(netdev_sw_irq_coalesce_default_on); /** * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @name_assign_type: origin of device name * @setup: callback to initialize device * @txqs: the number of TX subqueues to allocate * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use * and performs basic initialization. Also allocates subqueue structs * for each queue on the device. */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs) { struct net_device *dev; size_t napi_config_sz; unsigned int maxqs; BUG_ON(strlen(name) >= sizeof(dev->name)); if (txqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero queues\n"); return NULL; } if (rxqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; } maxqs = max(txqs, rxqs); dev = kvzalloc(struct_size(dev, priv, sizeof_priv), GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL); if (!dev) return NULL; dev->priv_len = sizeof_priv; ref_tracker_dir_init(&dev->refcnt_tracker, 128, "netdev"); #ifdef CONFIG_PCPU_DEV_REFCNT dev->pcpu_refcnt = alloc_percpu(int); if (!dev->pcpu_refcnt) goto free_dev; __dev_hold(dev); #else refcount_set(&dev->dev_refcnt, 1); #endif if (dev_addr_init(dev)) goto free_pcpu; dev_mc_init(dev); dev_uc_init(dev); dev_net_set(dev, &init_net); dev->gso_max_size = GSO_LEGACY_MAX_SIZE; dev->xdp_zc_max_segs = 1; dev->gso_max_segs = GSO_MAX_SEGS; dev->gro_max_size = GRO_LEGACY_MAX_SIZE; dev->gso_ipv4_max_size = GSO_LEGACY_MAX_SIZE; dev->gro_ipv4_max_size = GRO_LEGACY_MAX_SIZE; dev->tso_max_size = TSO_LEGACY_MAX_SIZE; dev->tso_max_segs = TSO_MAX_SEGS; dev->upper_level = 1; dev->lower_level = 1; #ifdef CONFIG_LOCKDEP dev->nested_level = 0; INIT_LIST_HEAD(&dev->unlink_list); #endif INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->close_list); INIT_LIST_HEAD(&dev->link_watch_list); INIT_LIST_HEAD(&dev->adj_list.upper); INIT_LIST_HEAD(&dev->adj_list.lower); INIT_LIST_HEAD(&dev->ptype_all); INIT_LIST_HEAD(&dev->ptype_specific); INIT_LIST_HEAD(&dev->net_notifier_list); #ifdef CONFIG_NET_SCHED hash_init(dev->qdisc_hash); #endif mutex_init(&dev->lock); dev->priv_flags = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; setup(dev); if (!dev->tx_queue_len) { dev->priv_flags |= IFF_NO_QUEUE; dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN; } dev->num_tx_queues = txqs; dev->real_num_tx_queues = txqs; if (netif_alloc_netdev_queues(dev)) goto free_all; dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) goto free_all; dev->ethtool = kzalloc(sizeof(*dev->ethtool), GFP_KERNEL_ACCOUNT); if (!dev->ethtool) goto free_all; dev->cfg = kzalloc(sizeof(*dev->cfg), GFP_KERNEL_ACCOUNT); if (!dev->cfg) goto free_all; dev->cfg_pending = dev->cfg; dev->num_napi_configs = maxqs; napi_config_sz = array_size(maxqs, sizeof(*dev->napi_config)); dev->napi_config = kvzalloc(napi_config_sz, GFP_KERNEL_ACCOUNT); if (!dev->napi_config) goto free_all; strscpy(dev->name, name); dev->name_assign_type = name_assign_type; dev->group = INIT_NETDEV_GROUP; if (!dev->ethtool_ops) dev->ethtool_ops = &default_ethtool_ops; nf_hook_netdev_init(dev); return dev; free_all: free_netdev(dev); return NULL; free_pcpu: #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); free_dev: #endif kvfree(dev); return NULL; } EXPORT_SYMBOL(alloc_netdev_mqs); static void netdev_napi_exit(struct net_device *dev) { if (!list_empty(&dev->napi_list)) { struct napi_struct *p, *n; netdev_lock(dev); list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) __netif_napi_del_locked(p); netdev_unlock(dev); synchronize_net(); } kvfree(dev->napi_config); } /** * free_netdev - free network device * @dev: device * * This function does the last stage of destroying an allocated device * interface. The reference to the device object is released. If this * is the last reference then it will be freed.Must be called in process * context. */ void free_netdev(struct net_device *dev) { might_sleep(); /* When called immediately after register_netdevice() failed the unwind * handling may still be dismantling the device. Handle that case by * deferring the free. */ if (dev->reg_state == NETREG_UNREGISTERING) { ASSERT_RTNL(); dev->needs_free_netdev = true; return; } WARN_ON(dev->cfg != dev->cfg_pending); kfree(dev->cfg); kfree(dev->ethtool); netif_free_tx_queues(dev); netif_free_rx_queues(dev); kfree(rcu_dereference_protected(dev->ingress_queue, 1)); /* Flush device addresses */ dev_addr_flush(dev); netdev_napi_exit(dev); netif_del_cpu_rmap(dev); ref_tracker_dir_exit(&dev->refcnt_tracker); #ifdef CONFIG_PCPU_DEV_REFCNT free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL; #endif free_percpu(dev->core_stats); dev->core_stats = NULL; free_percpu(dev->xdp_bulkq); dev->xdp_bulkq = NULL; netdev_free_phy_link_topology(dev); mutex_destroy(&dev->lock); /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED || dev->reg_state == NETREG_DUMMY) { kvfree(dev); return; } BUG_ON(dev->reg_state != NETREG_UNREGISTERED); WRITE_ONCE(dev->reg_state, NETREG_RELEASED); /* will free via device release */ put_device(&dev->dev); } EXPORT_SYMBOL(free_netdev); /** * alloc_netdev_dummy - Allocate and initialize a dummy net device. * @sizeof_priv: size of private data to allocate space for * * Return: the allocated net_device on success, NULL otherwise */ struct net_device *alloc_netdev_dummy(int sizeof_priv) { return alloc_netdev(sizeof_priv, "dummy#", NET_NAME_UNKNOWN, init_dummy_netdev); } EXPORT_SYMBOL_GPL(alloc_netdev_dummy); /** * synchronize_net - Synchronize with packet receive processing * * Wait for packets currently being received to be done. * Does not block later packets from starting. */ void synchronize_net(void) { might_sleep(); if (from_cleanup_net() || rtnl_is_locked()) synchronize_rcu_expedited(); else synchronize_rcu(); } EXPORT_SYMBOL(synchronize_net); static void netdev_rss_contexts_free(struct net_device *dev) { struct ethtool_rxfh_context *ctx; unsigned long context; mutex_lock(&dev->ethtool->rss_lock); xa_for_each(&dev->ethtool->rss_ctx, context, ctx) { xa_erase(&dev->ethtool->rss_ctx, context); dev->ethtool_ops->remove_rxfh_context(dev, ctx, context, NULL); kfree(ctx); } xa_destroy(&dev->ethtool->rss_ctx); mutex_unlock(&dev->ethtool->rss_lock); } /** * unregister_netdevice_queue - remove device from the kernel * @dev: device * @head: list * * This function shuts down a device interface and removes it * from the kernel tables. * If head not NULL, device is queued to be unregistered later. * * Callers must hold the rtnl semaphore. You may want * unregister_netdev() instead of this. */ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) { ASSERT_RTNL(); if (head) { list_move_tail(&dev->unreg_list, head); } else { LIST_HEAD(single); list_add(&dev->unreg_list, &single); unregister_netdevice_many(&single); } } EXPORT_SYMBOL(unregister_netdevice_queue); static void dev_memory_provider_uninstall(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->real_num_rx_queues; i++) { struct netdev_rx_queue *rxq = &dev->_rx[i]; struct pp_memory_provider_params *p = &rxq->mp_params; if (p->mp_ops && p->mp_ops->uninstall) p->mp_ops->uninstall(rxq->mp_params.mp_priv, rxq); } } void unregister_netdevice_many_notify(struct list_head *head, u32 portid, const struct nlmsghdr *nlh) { struct net_device *dev, *tmp; LIST_HEAD(close_head); int cnt = 0; BUG_ON(dev_boot_phase); ASSERT_RTNL(); if (list_empty(head)) return; list_for_each_entry_safe(dev, tmp, head, unreg_list) { /* Some devices call without registering * for initialization unwind. Remove those * devices and proceed with the remaining. */ if (dev->reg_state == NETREG_UNINITIALIZED) { pr_debug("unregister_netdevice: device %s/%p never was registered\n", dev->name, dev); WARN_ON(1); list_del(&dev->unreg_list); continue; } dev->dismantle = true; BUG_ON(dev->reg_state != NETREG_REGISTERED); } /* If device is running, close it first. Start with ops locked... */ list_for_each_entry(dev, head, unreg_list) { if (netdev_need_ops_lock(dev)) { list_add_tail(&dev->close_list, &close_head); netdev_lock(dev); } } netif_close_many(&close_head, true); /* ... now unlock them and go over the rest. */ list_for_each_entry(dev, head, unreg_list) { if (netdev_need_ops_lock(dev)) netdev_unlock(dev); else list_add_tail(&dev->close_list, &close_head); } netif_close_many(&close_head, true); list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ unlist_netdevice(dev); netdev_lock(dev); WRITE_ONCE(dev->reg_state, NETREG_UNREGISTERING); netdev_unlock(dev); } flush_all_backlogs(); synchronize_net(); list_for_each_entry(dev, head, unreg_list) { struct sk_buff *skb = NULL; /* Shutdown queueing discipline. */ netdev_lock_ops(dev); dev_shutdown(dev); dev_tcx_uninstall(dev); dev_xdp_uninstall(dev); dev_memory_provider_uninstall(dev); netdev_unlock_ops(dev); bpf_dev_bound_netdev_unregister(dev); netdev_offload_xstats_disable_all(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); if (!(dev->rtnl_link_ops && dev->rtnl_link_initializing)) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0, portid, nlh); /* * Flush the unicast and multicast chains */ dev_uc_flush(dev); dev_mc_flush(dev); netdev_name_node_alt_flush(dev); netdev_name_node_free(dev->name_node); netdev_rss_contexts_free(dev); call_netdevice_notifiers(NETDEV_PRE_UNINIT, dev); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); mutex_destroy(&dev->ethtool->rss_lock); net_shaper_flush_netdev(dev); if (skb) rtmsg_ifinfo_send(skb, dev, GFP_KERNEL, portid, nlh); /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); WARN_ON(netdev_has_any_lower_dev(dev)); /* Remove entries from kobject tree */ netdev_unregister_kobject(dev); #ifdef CONFIG_XPS /* Remove XPS queueing entries */ netif_reset_xps_queues_gt(dev, 0); #endif } synchronize_net(); list_for_each_entry(dev, head, unreg_list) { netdev_put(dev, &dev->dev_registered_tracker); net_set_todo(dev); cnt++; } atomic_add(cnt, &dev_unreg_count); list_del(head); } /** * unregister_netdevice_many - unregister many devices * @head: list of devices * * Note: As most callers use a stack allocated list_head, * we force a list_del() to make sure stack won't be corrupted later. */ void unregister_netdevice_many(struct list_head *head) { unregister_netdevice_many_notify(head, 0, NULL); } EXPORT_SYMBOL(unregister_netdevice_many); /** * unregister_netdev - remove device from the kernel * @dev: device * * This function shuts down a device interface and removes it * from the kernel tables. * * This is just a wrapper for unregister_netdevice that takes * the rtnl semaphore. In general you want to use this and not * unregister_netdevice. */ void unregister_netdev(struct net_device *dev) { rtnl_net_dev_lock(dev); unregister_netdevice(dev); rtnl_net_dev_unlock(dev); } EXPORT_SYMBOL(unregister_netdev); int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack) { struct netdev_name_node *name_node; struct net *net_old = dev_net(dev); char new_name[IFNAMSIZ] = {}; int err, new_nsid; ASSERT_RTNL(); /* Don't allow namespace local devices to be moved. */ err = -EINVAL; if (dev->netns_immutable) { NL_SET_ERR_MSG(extack, "The interface netns is immutable"); goto out; } /* Ensure the device has been registered */ if (dev->reg_state != NETREG_REGISTERED) { NL_SET_ERR_MSG(extack, "The interface isn't registered"); goto out; } /* Get out if there is nothing todo */ err = 0; if (net_eq(net_old, net)) goto out; /* Pick the destination device name, and ensure * we can use it in the destination network namespace. */ err = -EEXIST; if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) { NL_SET_ERR_MSG(extack, "An interface with the same name exists in the target netns"); goto out; } err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST); if (err < 0) { NL_SET_ERR_MSG_FMT(extack, "Unable to use '%s' for the new interface name in the target netns", pat); goto out; } } /* Check that none of the altnames conflicts. */ err = -EEXIST; netdev_for_each_altname(dev, name_node) { if (netdev_name_in_use(net, name_node->name)) { NL_SET_ERR_MSG_FMT(extack, "An interface with the altname %s exists in the target netns", name_node->name); goto out; } } /* Check that new_ifindex isn't used yet. */ if (new_ifindex) { err = dev_index_reserve(net, new_ifindex); if (err < 0) { NL_SET_ERR_MSG_FMT(extack, "The ifindex %d is not available in the target netns", new_ifindex); goto out; } } else { /* If there is an ifindex conflict assign a new one */ err = dev_index_reserve(net, dev->ifindex); if (err == -EBUSY) err = dev_index_reserve(net, 0); if (err < 0) { NL_SET_ERR_MSG(extack, "Unable to allocate a new ifindex in the target netns"); goto out; } new_ifindex = err; } /* * And now a mini version of register_netdevice unregister_netdevice. */ netdev_lock_ops(dev); /* If device is running close it first. */ netif_close(dev); /* And unlink it from device chain */ unlist_netdevice(dev); if (!netdev_need_ops_lock(dev)) netdev_lock(dev); dev->moving_ns = true; netdev_unlock(dev); synchronize_net(); /* Shutdown queueing discipline. */ netdev_lock_ops(dev); dev_shutdown(dev); netdev_unlock_ops(dev); /* Notify protocols, that we are about to destroy * this device. They should clean all the things. * * Note that dev->reg_state stays at NETREG_REGISTERED. * This is wanted because this way 8021q and macvlan know * the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); rtmsg_ifinfo_newnet(RTM_DELLINK, dev, ~0U, GFP_KERNEL, &new_nsid, new_ifindex); /* * Flush the unicast and multicast chains */ dev_uc_flush(dev); dev_mc_flush(dev); /* Send a netdev-removed uevent to the old namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_REMOVE); netdev_adjacent_del_links(dev); /* Move per-net netdevice notifiers that are following the netdevice */ move_netdevice_notifiers_dev_net(dev, net); /* Actually switch the network namespace */ netdev_lock(dev); dev_net_set(dev, net); netdev_unlock(dev); dev->ifindex = new_ifindex; if (new_name[0]) { /* Rename the netdev to prepared name */ write_seqlock_bh(&netdev_rename_lock); strscpy(dev->name, new_name, IFNAMSIZ); write_sequnlock_bh(&netdev_rename_lock); } /* Fixup kobjects */ dev_set_uevent_suppress(&dev->dev, 1); err = device_rename(&dev->dev, dev->name); dev_set_uevent_suppress(&dev->dev, 0); WARN_ON(err); /* Send a netdev-add uevent to the new namespace */ kobject_uevent(&dev->dev.kobj, KOBJ_ADD); netdev_adjacent_add_links(dev); /* Adapt owner in case owning user namespace of target network * namespace is different from the original one. */ err = netdev_change_owner(dev, net_old, net); WARN_ON(err); netdev_lock(dev); dev->moving_ns = false; if (!netdev_need_ops_lock(dev)) netdev_unlock(dev); /* Add the device back in the hashes */ list_netdevice(dev); /* Notify protocols, that a new device appeared. */ call_netdevice_notifiers(NETDEV_REGISTER, dev); netdev_unlock_ops(dev); /* * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U, GFP_KERNEL, 0, NULL); synchronize_net(); err = 0; out: return err; } static int dev_cpu_dead(unsigned int oldcpu) { struct sk_buff **list_skb; struct sk_buff *skb; unsigned int cpu; struct softnet_data *sd, *oldsd, *remsd = NULL; local_irq_disable(); cpu = smp_processor_id(); sd = &per_cpu(softnet_data, cpu); oldsd = &per_cpu(softnet_data, oldcpu); /* Find end of our completion_queue. */ list_skb = &sd->completion_queue; while (*list_skb) list_skb = &(*list_skb)->next; /* Append completion queue from offline CPU. */ *list_skb = oldsd->completion_queue; oldsd->completion_queue = NULL; /* Append output queue from offline CPU. */ if (oldsd->output_queue) { *sd->output_queue_tailp = oldsd->output_queue; sd->output_queue_tailp = oldsd->output_queue_tailp; oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } /* Append NAPI poll list from offline CPU, with one exception : * process_backlog() must be called by cpu owning percpu backlog. * We properly handle process_queue & input_pkt_queue later. */ while (!list_empty(&oldsd->poll_list)) { struct napi_struct *napi = list_first_entry(&oldsd->poll_list, struct napi_struct, poll_list); list_del_init(&napi->poll_list); if (napi->poll == process_backlog) napi->state &= NAPIF_STATE_THREADED; else ____napi_schedule(sd, napi); } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); if (!use_backlog_threads()) { #ifdef CONFIG_RPS remsd = oldsd->rps_ipi_list; oldsd->rps_ipi_list = NULL; #endif /* send out pending IPI's on offline CPU */ net_rps_send_ipi(remsd); } /* Process offline CPU's input_pkt_queue */ while ((skb = __skb_dequeue(&oldsd->process_queue))) { netif_rx(skb); rps_input_queue_head_incr(oldsd); } while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { netif_rx(skb); rps_input_queue_head_incr(oldsd); } return 0; } /** * netdev_increment_features - increment feature set by one * @all: current feature set * @one: new feature set * @mask: mask feature set * * Computes a new feature set after adding a device with feature set * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask) { if (mask & NETIF_F_HW_CSUM) mask |= NETIF_F_CSUM_MASK; mask |= NETIF_F_VLAN_CHALLENGED; all |= one & (NETIF_F_ONE_FOR_ALL | NETIF_F_CSUM_MASK) & mask; all &= one | ~NETIF_F_ALL_FOR_ALL; /* If one device supports hw checksumming, set for all. */ if (all & NETIF_F_HW_CSUM) all &= ~(NETIF_F_CSUM_MASK & ~NETIF_F_HW_CSUM); return all; } EXPORT_SYMBOL(netdev_increment_features); static struct hlist_head * __net_init netdev_create_hash(void) { int i; struct hlist_head *hash; hash = kmalloc_array(NETDEV_HASHENTRIES, sizeof(*hash), GFP_KERNEL); if (hash != NULL) for (i = 0; i < NETDEV_HASHENTRIES; i++) INIT_HLIST_HEAD(&hash[i]); return hash; } /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > BITS_PER_BYTE * sizeof_field(struct gro_node, bitmask)); INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) goto err_name; net->dev_index_head = netdev_create_hash(); if (net->dev_index_head == NULL) goto err_idx; xa_init_flags(&net->dev_by_index, XA_FLAGS_ALLOC1); RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain); return 0; err_idx: kfree(net->dev_name_head); err_name: return -ENOMEM; } /** * netdev_drivername - network driver for the device * @dev: network device * * Determine network driver for device. */ const char *netdev_drivername(const struct net_device *dev) { const struct device_driver *driver; const struct device *parent; const char *empty = ""; parent = dev->dev.parent; if (!parent) return empty; driver = parent->driver; if (driver && driver->name) return driver->name; return empty; } static void __netdev_printk(const char *level, const struct net_device *dev, struct va_format *vaf) { if (dev && dev->dev.parent) { dev_printk_emit(level[1] - '0', dev->dev.parent, "%s %s %s%s: %pV", dev_driver_string(dev->dev.parent), dev_name(dev->dev.parent), netdev_name(dev), netdev_reg_state(dev), vaf); } else if (dev) { printk("%s%s%s: %pV", level, netdev_name(dev), netdev_reg_state(dev), vaf); } else { printk("%s(NULL net_device): %pV", level, vaf); } } void netdev_printk(const char *level, const struct net_device *dev, const char *format, ...) { struct va_format vaf; va_list args; va_start(args, format); vaf.fmt = format; vaf.va = &args; __netdev_printk(level, dev, &vaf); va_end(args); } EXPORT_SYMBOL(netdev_printk); #define define_netdev_printk_level(func, level) \ void func(const struct net_device *dev, const char *fmt, ...) \ { \ struct va_format vaf; \ va_list args; \ \ va_start(args, fmt); \ \ vaf.fmt = fmt; \ vaf.va = &args; \ \ __netdev_printk(level, dev, &vaf); \ \ va_end(args); \ } \ EXPORT_SYMBOL(func); define_netdev_printk_level(netdev_emerg, KERN_EMERG); define_netdev_printk_level(netdev_alert, KERN_ALERT); define_netdev_printk_level(netdev_crit, KERN_CRIT); define_netdev_printk_level(netdev_err, KERN_ERR); define_netdev_printk_level(netdev_warn, KERN_WARNING); define_netdev_printk_level(netdev_notice, KERN_NOTICE); define_netdev_printk_level(netdev_info, KERN_INFO); static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); kfree(net->dev_index_head); xa_destroy(&net->dev_by_index); if (net != &init_net) WARN_ON_ONCE(!list_empty(&net->dev_base_head)); } static struct pernet_operations __net_initdata netdev_net_ops = { .init = netdev_init, .exit = netdev_exit, }; static void __net_exit default_device_exit_net(struct net *net) { struct netdev_name_node *name_node, *tmp; struct net_device *dev, *aux; /* * Push all migratable network devices back to the * initial network namespace */ ASSERT_RTNL(); for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; /* Ignore unmoveable devices (i.e. loopback) */ if (dev->netns_immutable) continue; /* Leave virtual devices for the generic cleanup */ if (dev->rtnl_link_ops && !dev->rtnl_link_ops->netns_refund) continue; /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); netdev_for_each_altname_safe(dev, name_node, tmp) if (netdev_name_in_use(&init_net, name_node->name)) __netdev_name_node_alt_destroy(name_node); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { pr_emerg("%s: failed to move %s to init_net: %d\n", __func__, dev->name, err); BUG(); } } } static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network * namespace. Do this in the reverse order of registration. * Do this across as many network namespaces as possible to * improve batching efficiency. */ struct net_device *dev; struct net *net; LIST_HEAD(dev_kill_list); rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { default_device_exit_net(net); cond_resched(); } list_for_each_entry(net, net_list, exit_list) { for_each_netdev_reverse(net, dev) { if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) dev->rtnl_link_ops->dellink(dev, &dev_kill_list); else unregister_netdevice_queue(dev, &dev_kill_list); } } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); } static struct pernet_operations __net_initdata default_device_ops = { .exit_batch = default_device_exit_batch, }; static void __init net_dev_struct_check(void) { /* TX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, priv_flags_fast); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, netdev_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, header_ops); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, _tx); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, real_num_tx_queues); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_ipv4_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_max_segs); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, gso_partial_features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, num_tc); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, mtu); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, needed_headroom); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tc_to_txq); #ifdef CONFIG_XPS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, xps_maps); #endif #ifdef CONFIG_NETFILTER_EGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, nf_hooks_egress); #endif #ifdef CONFIG_NET_XGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_tx, tcx_egress); #endif CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_tx, 160); /* TXRX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, lstats); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, state); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, flags); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, hard_header_len); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, features); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_txrx, ip6_ptr); CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_txrx, 46); /* RX read-mostly hotpath */ CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ptype_specific); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, ifindex); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, real_num_rx_queues); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, _rx); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, gro_ipv4_max_size); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, rx_handler_data); CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, nd_net); #ifdef CONFIG_NETPOLL CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, npinfo); #endif #ifdef CONFIG_NET_XGRESS CACHELINE_ASSERT_GROUP_MEMBER(struct net_device, net_device_read_rx, tcx_ingress); #endif CACHELINE_ASSERT_GROUP_SIZE(struct net_device, net_device_read_rx, 92); } /* * Initialize the DEV module. At boot time this walks the device list and * unhooks any devices that fail to initialise (normally hardware not * present) and leaves us with a valid list of present and active devices. * */ /* We allocate 256 pages for each CPU if PAGE_SHIFT is 12 */ #define SYSTEM_PERCPU_PAGE_POOL_SIZE ((1 << 20) / PAGE_SIZE) static int net_page_pool_create(int cpuid) { #if IS_ENABLED(CONFIG_PAGE_POOL) struct page_pool_params page_pool_params = { .pool_size = SYSTEM_PERCPU_PAGE_POOL_SIZE, .flags = PP_FLAG_SYSTEM_POOL, .nid = cpu_to_mem(cpuid), }; struct page_pool *pp_ptr; int err; pp_ptr = page_pool_create_percpu(&page_pool_params, cpuid); if (IS_ERR(pp_ptr)) return -ENOMEM; err = xdp_reg_page_pool(pp_ptr); if (err) { page_pool_destroy(pp_ptr); return err; } per_cpu(system_page_pool.pool, cpuid) = pp_ptr; #endif return 0; } static int backlog_napi_should_run(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); struct napi_struct *napi = &sd->backlog; return test_bit(NAPI_STATE_SCHED_THREADED, &napi->state); } static void run_backlog_napi(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); napi_threaded_poll_loop(&sd->backlog); } static void backlog_napi_setup(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); struct napi_struct *napi = &sd->backlog; napi->thread = this_cpu_read(backlog_napi); set_bit(NAPI_STATE_THREADED, &napi->state); } static struct smp_hotplug_thread backlog_threads = { .store = &backlog_napi, .thread_should_run = backlog_napi_should_run, .thread_fn = run_backlog_napi, .thread_comm = "backlog_napi/%u", .setup = backlog_napi_setup, }; /* * This is called single threaded during boot, so no need * to take the rtnl semaphore. */ static int __init net_dev_init(void) { int i, rc = -ENOMEM; BUG_ON(!dev_boot_phase); net_dev_struct_check(); if (dev_proc_init()) goto out; if (netdev_kobject_init()) goto out; for (i = 0; i < PTYPE_HASH_SIZE; i++) INIT_LIST_HEAD(&ptype_base[i]); if (register_pernet_subsys(&netdev_net_ops)) goto out; /* * Initialise the packet receive queues. */ flush_backlogs_fallback = flush_backlogs_alloc(); if (!flush_backlogs_fallback) goto out; for_each_possible_cpu(i) { struct softnet_data *sd = &per_cpu(softnet_data, i); skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); #ifdef CONFIG_XFRM_OFFLOAD skb_queue_head_init(&sd->xfrm_backlog); #endif INIT_LIST_HEAD(&sd->poll_list); sd->output_queue_tailp = &sd->output_queue; #ifdef CONFIG_RPS INIT_CSD(&sd->csd, rps_trigger_softirq, sd); sd->cpu = i; #endif INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd); spin_lock_init(&sd->defer_lock); gro_init(&sd->backlog.gro); sd->backlog.poll = process_backlog; sd->backlog.weight = weight_p; INIT_LIST_HEAD(&sd->backlog.poll_list); if (net_page_pool_create(i)) goto out; } if (use_backlog_threads()) smpboot_register_percpu_thread(&backlog_threads); dev_boot_phase = 0; /* The loopback device is special if any other network devices * is present in a network namespace the loopback device must * be present. Since we now dynamically allocate and free the * loopback device ensure this invariant is maintained by * keeping the loopback device as the first device on the * list of network devices. Ensuring the loopback devices * is the first device that appears and the last network device * that disappears. */ if (register_pernet_device(&loopback_net_ops)) goto out; if (register_pernet_device(&default_device_ops)) goto out; open_softirq(NET_TX_SOFTIRQ, net_tx_action); open_softirq(NET_RX_SOFTIRQ, net_rx_action); rc = cpuhp_setup_state_nocalls(CPUHP_NET_DEV_DEAD, "net/dev:dead", NULL, dev_cpu_dead); WARN_ON(rc < 0); rc = 0; /* avoid static key IPIs to isolated CPUs */ if (housekeeping_enabled(HK_TYPE_MISC)) net_enable_timestamp(); out: if (rc < 0) { for_each_possible_cpu(i) { struct page_pool *pp_ptr; pp_ptr = per_cpu(system_page_pool.pool, i); if (!pp_ptr) continue; xdp_unreg_page_pool(pp_ptr); page_pool_destroy(pp_ptr); per_cpu(system_page_pool.pool, i) = NULL; } } return rc; } subsys_initcall(net_dev_init); |
| 1780 1784 1780 10 5663 5665 5644 5670 5643 994 5646 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 | // SPDX-License-Identifier: GPL-2.0 #include <linux/irq_work.h> #include <linux/spinlock.h> #include <linux/task_work.h> #include <linux/resume_user_mode.h> static struct callback_head work_exited; /* all we need is ->next == NULL */ #ifdef CONFIG_IRQ_WORK static void task_work_set_notify_irq(struct irq_work *entry) { test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); } static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) = IRQ_WORK_INIT_HARD(task_work_set_notify_irq); #endif /** * task_work_add - ask the @task to execute @work->func() * @task: the task which should run the callback * @work: the callback to run * @notify: how to notify the targeted task * * Queue @work for task_work_run() below and notify the @task if @notify * is @TWA_RESUME, @TWA_SIGNAL, @TWA_SIGNAL_NO_IPI or @TWA_NMI_CURRENT. * * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted * task and run the task_work, regardless of whether the task is currently * running in the kernel or userspace. * @TWA_SIGNAL_NO_IPI works like @TWA_SIGNAL, except it doesn't send a * reschedule IPI to force the targeted task to reschedule and run task_work. * This can be advantageous if there's no strict requirement that the * task_work be run as soon as possible, just whenever the task enters the * kernel anyway. * @TWA_RESUME work is run only when the task exits the kernel and returns to * user mode, or before entering guest mode. * @TWA_NMI_CURRENT works like @TWA_RESUME, except it can only be used for the * current @task and if the current context is NMI. * * Fails if the @task is exiting/exited and thus it can't process this @work. * Otherwise @work->func() will be called when the @task goes through one of * the aforementioned transitions, or exits. * * If the targeted task is exiting, then an error is returned and the work item * is not queued. It's up to the caller to arrange for an alternative mechanism * in that case. * * Note: there is no ordering guarantee on works queued here. The task_work * list is LIFO. * * RETURNS: * 0 if succeeds or -ESRCH. */ int task_work_add(struct task_struct *task, struct callback_head *work, enum task_work_notify_mode notify) { struct callback_head *head; if (notify == TWA_NMI_CURRENT) { if (WARN_ON_ONCE(task != current)) return -EINVAL; if (!IS_ENABLED(CONFIG_IRQ_WORK)) return -EINVAL; } else { kasan_record_aux_stack(work); } head = READ_ONCE(task->task_works); do { if (unlikely(head == &work_exited)) return -ESRCH; work->next = head; } while (!try_cmpxchg(&task->task_works, &head, work)); switch (notify) { case TWA_NONE: break; case TWA_RESUME: set_notify_resume(task); break; case TWA_SIGNAL: set_notify_signal(task); break; case TWA_SIGNAL_NO_IPI: __set_notify_signal(task); break; #ifdef CONFIG_IRQ_WORK case TWA_NMI_CURRENT: irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume)); break; #endif default: WARN_ON_ONCE(1); break; } return 0; } /** * task_work_cancel_match - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @match: match function to call * @data: data to be passed in to match function * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_match(struct task_struct *task, bool (*match)(struct callback_head *, void *data), void *data) { struct callback_head **pprev = &task->task_works; struct callback_head *work; unsigned long flags; if (likely(!task_work_pending(task))) return NULL; /* * If cmpxchg() fails we continue without updating pprev. * Either we raced with task_work_add() which added the * new entry before this work, we will find it again. Or * we raced with task_work_run(), *pprev == NULL/exited. */ raw_spin_lock_irqsave(&task->pi_lock, flags); work = READ_ONCE(*pprev); while (work) { if (!match(work, data)) { pprev = &work->next; work = READ_ONCE(*pprev); } else if (try_cmpxchg(pprev, &work, work->next)) break; } raw_spin_unlock_irqrestore(&task->pi_lock, flags); return work; } static bool task_work_func_match(struct callback_head *cb, void *data) { return cb->func == data; } /** * task_work_cancel_func - cancel a pending work matching a function added by task_work_add() * @task: the task which should execute the func's work * @func: identifies the func to match with a work to remove * * Find the last queued pending work with ->func == @func and remove * it from queue. * * RETURNS: * The found work or NULL if not found. */ struct callback_head * task_work_cancel_func(struct task_struct *task, task_work_func_t func) { return task_work_cancel_match(task, task_work_func_match, func); } static bool task_work_match(struct callback_head *cb, void *data) { return cb == data; } /** * task_work_cancel - cancel a pending work added by task_work_add() * @task: the task which should execute the work * @cb: the callback to remove if queued * * Remove a callback from a task's queue if queued. * * RETURNS: * True if the callback was queued and got cancelled, false otherwise. */ bool task_work_cancel(struct task_struct *task, struct callback_head *cb) { struct callback_head *ret; ret = task_work_cancel_match(task, task_work_match, cb); return ret == cb; } /** * task_work_run - execute the works added by task_work_add() * * Flush the pending works. Should be used by the core kernel code. * Called before the task returns to the user-mode or stops, or when * it exits. In the latter case task_work_add() can no longer add the * new work after task_work_run() returns. */ void task_work_run(void) { struct task_struct *task = current; struct callback_head *work, *head, *next; for (;;) { /* * work->func() can do task_work_add(), do not set * work_exited unless the list is empty. */ work = READ_ONCE(task->task_works); do { head = NULL; if (!work) { if (task->flags & PF_EXITING) head = &work_exited; else break; } } while (!try_cmpxchg(&task->task_works, &work, head)); if (!work) break; /* * Synchronize with task_work_cancel_match(). It can not remove * the first entry == work, cmpxchg(task_works) must fail. * But it can remove another entry from the ->next list. */ raw_spin_lock_irq(&task->pi_lock); raw_spin_unlock_irq(&task->pi_lock); do { next = work->next; work->func(work); work = next; cond_resched(); } while (work); } } |
| 2861 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM ipi #if !defined(_TRACE_IPI_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_IPI_H #include <linux/tracepoint.h> TRACE_EVENT(ipi_send_cpu, TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback), TP_ARGS(cpu, callsite, callback), TP_STRUCT__entry( __field(unsigned int, cpu) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __entry->cpu = cpu; __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpu=%u callsite=%pS callback=%pS", __entry->cpu, __entry->callsite, __entry->callback) ); TRACE_EVENT(ipi_send_cpumask, TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback), TP_ARGS(cpumask, callsite, callback), TP_STRUCT__entry( __cpumask(cpumask) __field(void *, callsite) __field(void *, callback) ), TP_fast_assign( __assign_cpumask(cpumask, cpumask_bits(cpumask)); __entry->callsite = (void *)callsite; __entry->callback = callback; ), TP_printk("cpumask=%s callsite=%pS callback=%pS", __get_cpumask(cpumask), __entry->callsite, __entry->callback) ); #ifdef CONFIG_HAVE_EXTRA_IPI_TRACEPOINTS /** * ipi_raise - called when a smp cross call is made * * @mask: mask of recipient CPUs for the IPI * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string. */ TRACE_EVENT(ipi_raise, TP_PROTO(const struct cpumask *mask, const char *reason), TP_ARGS(mask, reason), TP_STRUCT__entry( __bitmask(target_cpus, nr_cpumask_bits) __field(const char *, reason) ), TP_fast_assign( __assign_bitmask(target_cpus, cpumask_bits(mask), nr_cpumask_bits); __entry->reason = reason; ), TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason) ); DECLARE_EVENT_CLASS(ipi_handler, TP_PROTO(const char *reason), TP_ARGS(reason), TP_STRUCT__entry( __field(const char *, reason) ), TP_fast_assign( __entry->reason = reason; ), TP_printk("(%s)", __entry->reason) ); /** * ipi_entry - called immediately before the IPI handler * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise * for that IPI. */ DEFINE_EVENT(ipi_handler, ipi_entry, TP_PROTO(const char *reason), TP_ARGS(reason) ); /** * ipi_exit - called immediately after the IPI handler returns * * @reason: string identifying the IPI purpose * * It is necessary for @reason to be a static string declared with * __tracepoint_string, ideally the same as used with trace_ipi_raise for * that IPI. */ DEFINE_EVENT(ipi_handler, ipi_exit, TP_PROTO(const char *reason), TP_ARGS(reason) ); #endif /* CONFIG_HAVE_EXTRA_IPI_TRACEPOINTS */ #endif /* _TRACE_IPI_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 67 37 61 9 43 5 296 10 61 313 116 105 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2009-2021 Christoph Hellwig * * NOTE: none of these tracepoints shall be considered a stable kernel ABI * as they can change at any time. * * Current conventions for printing numbers measuring specific units: * * offset: byte offset into a subcomponent of a file operation * pos: file offset, in bytes * length: length of a file operation, in bytes * ino: inode number * * Numbers describing space allocations should be formatted in hexadecimal. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM iomap #if !defined(_IOMAP_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) #define _IOMAP_TRACE_H #include <linux/tracepoint.h> struct inode; DECLARE_EVENT_CLASS(iomap_readpage_class, TP_PROTO(struct inode *inode, int nr_pages), TP_ARGS(inode, nr_pages), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(int, nr_pages) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->nr_pages = nr_pages; ), TP_printk("dev %d:%d ino 0x%llx nr_pages %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->nr_pages) ) #define DEFINE_READPAGE_EVENT(name) \ DEFINE_EVENT(iomap_readpage_class, name, \ TP_PROTO(struct inode *inode, int nr_pages), \ TP_ARGS(inode, nr_pages)) DEFINE_READPAGE_EVENT(iomap_readpage); DEFINE_READPAGE_EVENT(iomap_readahead); DECLARE_EVENT_CLASS(iomap_range_class, TP_PROTO(struct inode *inode, loff_t off, u64 len), TP_ARGS(inode, off, len), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, size) __field(loff_t, offset) __field(u64, length) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->size = i_size_read(inode); __entry->offset = off; __entry->length = len; ), TP_printk("dev %d:%d ino 0x%llx size 0x%llx offset 0x%llx length 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->offset, __entry->length) ) #define DEFINE_RANGE_EVENT(name) \ DEFINE_EVENT(iomap_range_class, name, \ TP_PROTO(struct inode *inode, loff_t off, u64 len),\ TP_ARGS(inode, off, len)) DEFINE_RANGE_EVENT(iomap_writeback_folio); DEFINE_RANGE_EVENT(iomap_release_folio); DEFINE_RANGE_EVENT(iomap_invalidate_folio); DEFINE_RANGE_EVENT(iomap_dio_invalidate_fail); DEFINE_RANGE_EVENT(iomap_dio_rw_queued); #define IOMAP_TYPE_STRINGS \ { IOMAP_HOLE, "HOLE" }, \ { IOMAP_DELALLOC, "DELALLOC" }, \ { IOMAP_MAPPED, "MAPPED" }, \ { IOMAP_UNWRITTEN, "UNWRITTEN" }, \ { IOMAP_INLINE, "INLINE" } #define IOMAP_FLAGS_STRINGS \ { IOMAP_WRITE, "WRITE" }, \ { IOMAP_ZERO, "ZERO" }, \ { IOMAP_REPORT, "REPORT" }, \ { IOMAP_FAULT, "FAULT" }, \ { IOMAP_DIRECT, "DIRECT" }, \ { IOMAP_NOWAIT, "NOWAIT" }, \ { IOMAP_OVERWRITE_ONLY, "OVERWRITE_ONLY" }, \ { IOMAP_UNSHARE, "UNSHARE" }, \ { IOMAP_DAX, "DAX" }, \ { IOMAP_ATOMIC, "ATOMIC" }, \ { IOMAP_DONTCACHE, "DONTCACHE" } #define IOMAP_F_FLAGS_STRINGS \ { IOMAP_F_NEW, "NEW" }, \ { IOMAP_F_DIRTY, "DIRTY" }, \ { IOMAP_F_SHARED, "SHARED" }, \ { IOMAP_F_MERGED, "MERGED" }, \ { IOMAP_F_BUFFER_HEAD, "BH" }, \ { IOMAP_F_XATTR, "XATTR" }, \ { IOMAP_F_BOUNDARY, "BOUNDARY" }, \ { IOMAP_F_ANON_WRITE, "ANON_WRITE" }, \ { IOMAP_F_ATOMIC_BIO, "ATOMIC_BIO" }, \ { IOMAP_F_PRIVATE, "PRIVATE" }, \ { IOMAP_F_SIZE_CHANGED, "SIZE_CHANGED" }, \ { IOMAP_F_STALE, "STALE" } #define IOMAP_DIO_STRINGS \ {IOMAP_DIO_FORCE_WAIT, "DIO_FORCE_WAIT" }, \ {IOMAP_DIO_OVERWRITE_ONLY, "DIO_OVERWRITE_ONLY" }, \ {IOMAP_DIO_PARTIAL, "DIO_PARTIAL" } DECLARE_EVENT_CLASS(iomap_class, TP_PROTO(struct inode *inode, struct iomap *iomap), TP_ARGS(inode, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d addr 0x%llx offset 0x%llx " "length 0x%llx type %s (0x%x) flags %s (0x%x)", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), __entry->addr, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), __entry->type, __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS), __entry->flags) ) #define DEFINE_IOMAP_EVENT(name) \ DEFINE_EVENT(iomap_class, name, \ TP_PROTO(struct inode *inode, struct iomap *iomap), \ TP_ARGS(inode, iomap)) DEFINE_IOMAP_EVENT(iomap_iter_dstmap); DEFINE_IOMAP_EVENT(iomap_iter_srcmap); TRACE_EVENT(iomap_add_to_ioend, TP_PROTO(struct inode *inode, u64 pos, unsigned int dirty_len, struct iomap *iomap), TP_ARGS(inode, pos, dirty_len, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(u64, pos) __field(u64, dirty_len) __field(u64, addr) __field(loff_t, offset) __field(u64, length) __field(u16, type) __field(u16, flags) __field(dev_t, bdev) ), TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; __entry->pos = pos; __entry->dirty_len = dirty_len; __entry->addr = iomap->addr; __entry->offset = iomap->offset; __entry->length = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->bdev = iomap->bdev ? iomap->bdev->bd_dev : 0; ), TP_printk("dev %d:%d ino 0x%llx bdev %d:%d pos 0x%llx dirty len 0x%llx " "addr 0x%llx offset 0x%llx length 0x%llx type %s (0x%x) flags %s (0x%x)", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, MAJOR(__entry->bdev), MINOR(__entry->bdev), __entry->pos, __entry->dirty_len, __entry->addr, __entry->offset, __entry->length, __print_symbolic(__entry->type, IOMAP_TYPE_STRINGS), __entry->type, __print_flags(__entry->flags, "|", IOMAP_F_FLAGS_STRINGS), __entry->flags) ); TRACE_EVENT(iomap_iter, TP_PROTO(struct iomap_iter *iter, const void *ops, unsigned long caller), TP_ARGS(iter, ops, caller), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, ino) __field(loff_t, pos) __field(u64, length) __field(int, status) __field(unsigned int, flags) __field(const void *, ops) __field(unsigned long, caller) ), TP_fast_assign( __entry->dev = iter->inode->i_sb->s_dev; __entry->ino = iter->inode->i_ino; __entry->pos = iter->pos; __entry->length = iomap_length(iter); __entry->status = iter->status; __entry->flags = iter->flags; __entry->ops = ops; __entry->caller = caller; ), TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx status %d flags %s (0x%x) ops %ps caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pos, __entry->length, __entry->status, __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS), __entry->flags, __entry->ops, (void *)__entry->caller) ); TRACE_EVENT(iomap_dio_rw_begin, TP_PROTO(struct kiocb *iocb, struct iov_iter *iter, unsigned int dio_flags, size_t done_before), TP_ARGS(iocb, iter, dio_flags, done_before), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, isize) __field(loff_t, pos) __field(size_t, count) __field(size_t, done_before) __field(int, ki_flags) __field(unsigned int, dio_flags) __field(bool, aio) ), TP_fast_assign( __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; __entry->ino = file_inode(iocb->ki_filp)->i_ino; __entry->isize = file_inode(iocb->ki_filp)->i_size; __entry->pos = iocb->ki_pos; __entry->count = iov_iter_count(iter); __entry->done_before = done_before; __entry->ki_flags = iocb->ki_flags; __entry->dio_flags = dio_flags; __entry->aio = !is_sync_kiocb(iocb); ), TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx length 0x%zx done_before 0x%zx flags %s dio_flags %s aio %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->isize, __entry->pos, __entry->count, __entry->done_before, __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), __print_flags(__entry->dio_flags, "|", IOMAP_DIO_STRINGS), __entry->aio) ); TRACE_EVENT(iomap_dio_complete, TP_PROTO(struct kiocb *iocb, int error, ssize_t ret), TP_ARGS(iocb, error, ret), TP_STRUCT__entry( __field(dev_t, dev) __field(ino_t, ino) __field(loff_t, isize) __field(loff_t, pos) __field(int, ki_flags) __field(bool, aio) __field(int, error) __field(ssize_t, ret) ), TP_fast_assign( __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; __entry->ino = file_inode(iocb->ki_filp)->i_ino; __entry->isize = file_inode(iocb->ki_filp)->i_size; __entry->pos = iocb->ki_pos; __entry->ki_flags = iocb->ki_flags; __entry->aio = !is_sync_kiocb(iocb); __entry->error = error; __entry->ret = ret; ), TP_printk("dev %d:%d ino 0x%lx size 0x%llx offset 0x%llx flags %s aio %d error %d ret %zd", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->isize, __entry->pos, __print_flags(__entry->ki_flags, "|", TRACE_IOCB_STRINGS), __entry->aio, __entry->error, __entry->ret) ); #endif /* _IOMAP_TRACE_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE trace #include <trace/define_trace.h> |
| 444 670 161 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 | #ifndef _LINUX_HASH_H #define _LINUX_HASH_H /* Fast hashing routine for ints, longs and pointers. (C) 2002 Nadia Yvette Chambers, IBM */ #include <asm/types.h> #include <linux/compiler.h> /* * The "GOLDEN_RATIO_PRIME" is used in ifs/btrfs/brtfs_inode.h and * fs/inode.c. It's not actually prime any more (the previous primes * were actively bad for hashing), but the name remains. */ #if BITS_PER_LONG == 32 #define GOLDEN_RATIO_PRIME GOLDEN_RATIO_32 #define hash_long(val, bits) hash_32(val, bits) #elif BITS_PER_LONG == 64 #define hash_long(val, bits) hash_64(val, bits) #define GOLDEN_RATIO_PRIME GOLDEN_RATIO_64 #else #error Wordsize not 32 or 64 #endif /* * This hash multiplies the input by a large odd number and takes the * high bits. Since multiplication propagates changes to the most * significant end only, it is essential that the high bits of the * product be used for the hash value. * * Chuck Lever verified the effectiveness of this technique: * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf * * Although a random odd number will do, it turns out that the golden * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice * properties. (See Knuth vol 3, section 6.4, exercise 9.) * * These are the negative, (1 - phi) = phi**2 = (3 - sqrt(5))/2, * which is very slightly easier to multiply by and makes no * difference to the hash distribution. */ #define GOLDEN_RATIO_32 0x61C88647 #define GOLDEN_RATIO_64 0x61C8864680B583EBull #ifdef CONFIG_HAVE_ARCH_HASH /* This header may use the GOLDEN_RATIO_xx constants */ #include <asm/hash.h> #endif /* * The _generic versions exist only so lib/test_hash.c can compare * the arch-optimized versions with the generic. * * Note that if you change these, any <asm/hash.h> that aren't updated * to match need to have their HAVE_ARCH_* define values updated so the * self-test will not false-positive. */ #ifndef HAVE_ARCH__HASH_32 #define __hash_32 __hash_32_generic #endif static inline u32 __hash_32_generic(u32 val) { return val * GOLDEN_RATIO_32; } static inline u32 hash_32(u32 val, unsigned int bits) { /* High bits are more random, so use them. */ return __hash_32(val) >> (32 - bits); } #ifndef HAVE_ARCH_HASH_64 #define hash_64 hash_64_generic #endif static __always_inline u32 hash_64_generic(u64 val, unsigned int bits) { #if BITS_PER_LONG == 64 /* 64x64-bit multiply is efficient on all 64-bit processors */ return val * GOLDEN_RATIO_64 >> (64 - bits); #else /* Hash 64 bits using only 32x32-bit multiply. */ return hash_32((u32)val ^ __hash_32(val >> 32), bits); #endif } static inline u32 hash_ptr(const void *ptr, unsigned int bits) { return hash_long((unsigned long)ptr, bits); } /* This really should be called fold32_ptr; it does no hashing to speak of. */ static inline u32 hash32_ptr(const void *ptr) { unsigned long val = (unsigned long)ptr; #if BITS_PER_LONG == 64 val ^= (val >> 32); #endif return (u32)val; } #endif /* _LINUX_HASH_H */ |
| 276 311 68 221 336 208 342 294 343 757 735 343 343 326 342 343 302 343 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/list_sort.h> #include <linux/list.h> /* * Returns a list organized in an intermediate format suited * to chaining of merge() calls: null-terminated, no reserved or * sentinel head node, "prev" links not maintained. */ __attribute__((nonnull(2,3,4))) static struct list_head *merge(void *priv, list_cmp_func_t cmp, struct list_head *a, struct list_head *b) { struct list_head *head, **tail = &head; for (;;) { /* if equal, take 'a' -- important for sort stability */ if (cmp(priv, a, b) <= 0) { *tail = a; tail = &a->next; a = a->next; if (!a) { *tail = b; break; } } else { *tail = b; tail = &b->next; b = b->next; if (!b) { *tail = a; break; } } } return head; } /* * Combine final list merge with restoration of standard doubly-linked * list structure. This approach duplicates code from merge(), but * runs faster than the tidier alternatives of either a separate final * prev-link restoration pass, or maintaining the prev links * throughout. */ __attribute__((nonnull(2,3,4,5))) static void merge_final(void *priv, list_cmp_func_t cmp, struct list_head *head, struct list_head *a, struct list_head *b) { struct list_head *tail = head; u8 count = 0; for (;;) { /* if equal, take 'a' -- important for sort stability */ if (cmp(priv, a, b) <= 0) { tail->next = a; a->prev = tail; tail = a; a = a->next; if (!a) break; } else { tail->next = b; b->prev = tail; tail = b; b = b->next; if (!b) { b = a; break; } } } /* Finish linking remainder of list b on to tail */ tail->next = b; do { /* * If the merge is highly unbalanced (e.g. the input is * already sorted), this loop may run many iterations. * Continue callbacks to the client even though no * element comparison is needed, so the client's cmp() * routine can invoke cond_resched() periodically. */ if (unlikely(!++count)) cmp(priv, b, b); b->prev = tail; tail = b; b = b->next; } while (b); /* And the final links to make a circular doubly-linked list */ tail->next = head; head->prev = tail; } /** * list_sort - sort a list * @priv: private data, opaque to list_sort(), passed to @cmp * @head: the list to sort * @cmp: the elements comparison function * * The comparison function @cmp must return > 0 if @a should sort after * @b ("@a > @b" if you want an ascending sort), and <= 0 if @a should * sort before @b *or* their original order should be preserved. It is * always called with the element that came first in the input in @a, * and list_sort is a stable sort, so it is not necessary to distinguish * the @a < @b and @a == @b cases. * * The comparison function must adhere to specific mathematical properties * to ensure correct and stable sorting: * - Antisymmetry: cmp(@a, @b) must return the opposite sign of * cmp(@b, @a). * - Transitivity: if cmp(@a, @b) <= 0 and cmp(@b, @c) <= 0, then * cmp(@a, @c) <= 0. * * This is compatible with two styles of @cmp function: * - The traditional style which returns <0 / =0 / >0, or * - Returning a boolean 0/1. * The latter offers a chance to save a few cycles in the comparison * (which is used by e.g. plug_ctx_cmp() in block/blk-mq.c). * * A good way to write a multi-word comparison is:: * * if (a->high != b->high) * return a->high > b->high; * if (a->middle != b->middle) * return a->middle > b->middle; * return a->low > b->low; * * * This mergesort is as eager as possible while always performing at least * 2:1 balanced merges. Given two pending sublists of size 2^k, they are * merged to a size-2^(k+1) list as soon as we have 2^k following elements. * * Thus, it will avoid cache thrashing as long as 3*2^k elements can * fit into the cache. Not quite as good as a fully-eager bottom-up * mergesort, but it does use 0.2*n fewer comparisons, so is faster in * the common case that everything fits into L1. * * * The merging is controlled by "count", the number of elements in the * pending lists. This is beautifully simple code, but rather subtle. * * Each time we increment "count", we set one bit (bit k) and clear * bits k-1 .. 0. Each time this happens (except the very first time * for each bit, when count increments to 2^k), we merge two lists of * size 2^k into one list of size 2^(k+1). * * This merge happens exactly when the count reaches an odd multiple of * 2^k, which is when we have 2^k elements pending in smaller lists, * so it's safe to merge away two lists of size 2^k. * * After this happens twice, we have created two lists of size 2^(k+1), * which will be merged into a list of size 2^(k+2) before we create * a third list of size 2^(k+1), so there are never more than two pending. * * The number of pending lists of size 2^k is determined by the * state of bit k of "count" plus two extra pieces of information: * * - The state of bit k-1 (when k == 0, consider bit -1 always set), and * - Whether the higher-order bits are zero or non-zero (i.e. * is count >= 2^(k+1)). * * There are six states we distinguish. "x" represents some arbitrary * bits, and "y" represents some arbitrary non-zero bits: * 0: 00x: 0 pending of size 2^k; x pending of sizes < 2^k * 1: 01x: 0 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k * 2: x10x: 0 pending of size 2^k; 2^k + x pending of sizes < 2^k * 3: x11x: 1 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k * 4: y00x: 1 pending of size 2^k; 2^k + x pending of sizes < 2^k * 5: y01x: 2 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k * (merge and loop back to state 2) * * We gain lists of size 2^k in the 2->3 and 4->5 transitions (because * bit k-1 is set while the more significant bits are non-zero) and * merge them away in the 5->2 transition. Note in particular that just * before the 5->2 transition, all lower-order bits are 11 (state 3), * so there is one list of each smaller size. * * When we reach the end of the input, we merge all the pending * lists, from smallest to largest. If you work through cases 2 to * 5 above, you can see that the number of elements we merge with a list * of size 2^k varies from 2^(k-1) (cases 3 and 5 when x == 0) to * 2^(k+1) - 1 (second merge of case 5 when x == 2^(k-1) - 1). */ __attribute__((nonnull(2,3))) void list_sort(void *priv, struct list_head *head, list_cmp_func_t cmp) { struct list_head *list = head->next, *pending = NULL; size_t count = 0; /* Count of pending */ if (list == head->prev) /* Zero or one elements */ return; /* Convert to a null-terminated singly-linked list. */ head->prev->next = NULL; /* * Data structure invariants: * - All lists are singly linked and null-terminated; prev * pointers are not maintained. * - pending is a prev-linked "list of lists" of sorted * sublists awaiting further merging. * - Each of the sorted sublists is power-of-two in size. * - Sublists are sorted by size and age, smallest & newest at front. * - There are zero to two sublists of each size. * - A pair of pending sublists are merged as soon as the number * of following pending elements equals their size (i.e. * each time count reaches an odd multiple of that size). * That ensures each later final merge will be at worst 2:1. * - Each round consists of: * - Merging the two sublists selected by the highest bit * which flips when count is incremented, and * - Adding an element from the input as a size-1 sublist. */ do { size_t bits; struct list_head **tail = &pending; /* Find the least-significant clear bit in count */ for (bits = count; bits & 1; bits >>= 1) tail = &(*tail)->prev; /* Do the indicated merge */ if (likely(bits)) { struct list_head *a = *tail, *b = a->prev; a = merge(priv, cmp, b, a); /* Install the merged result in place of the inputs */ a->prev = b->prev; *tail = a; } /* Move one element from input list to pending */ list->prev = pending; pending = list; list = list->next; pending->next = NULL; count++; } while (list); /* End of input; merge together all the pending lists. */ list = pending; pending = pending->prev; for (;;) { struct list_head *next = pending->prev; if (!next) break; list = merge(priv, cmp, pending, list); pending = next; } /* The final merge, rebuilding prev links */ merge_final(priv, cmp, head, pending, list); } EXPORT_SYMBOL(list_sort); |
| 3865 3860 3859 3860 3856 1000 3664 693 690 3872 3442 3457 447 510 509 509 510 447 3859 3872 3864 3862 3450 3446 3450 3856 3445 3859 3856 3517 1159 3873 3860 3860 3873 509 3856 3870 3445 694 1231 1488 1485 1488 1490 676 4 3858 3445 1231 690 1226 689 1226 553 554 553 554 553 554 552 553 553 553 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | // SPDX-License-Identifier: GPL-2.0 /* * 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 * * High-resolution kernel timers * * In contrast to the low-resolution timeout API, aka timer wheel, * hrtimers provide finer resolution and accuracy depending on system * configuration and capabilities. * * Started by: Thomas Gleixner and Ingo Molnar * * Credits: * Based on the original timer wheel code * * Help, testing, suggestions, bugfixes, improvements were * provided by: * * George Anzinger, Andrew Morton, Steven Rostedt, Roman Zippel * et. al. */ #include <linux/cpu.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/hrtimer.h> #include <linux/notifier.h> #include <linux/syscalls.h> #include <linux/interrupt.h> #include <linux/tick.h> #include <linux/err.h> #include <linux/debugobjects.h> #include <linux/sched/signal.h> #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> #include <linux/sched/deadline.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <trace/events/timer.h> #include "tick-internal.h" /* * Masks for selecting the soft and hard context timers from * cpu_base->active */ #define MASK_SHIFT (HRTIMER_BASE_MONOTONIC_SOFT) #define HRTIMER_ACTIVE_HARD ((1U << MASK_SHIFT) - 1) #define HRTIMER_ACTIVE_SOFT (HRTIMER_ACTIVE_HARD << MASK_SHIFT) #define HRTIMER_ACTIVE_ALL (HRTIMER_ACTIVE_SOFT | HRTIMER_ACTIVE_HARD) static void retrigger_next_event(void *arg); /* * The timer bases: * * There are more clockids than hrtimer bases. Thus, we index * into the timer bases by the hrtimer_base_type enum. When trying * to reach a base using a clockid, hrtimer_clockid_to_base() * is used to convert from clockid to the proper hrtimer_base_type. */ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), .clock_base = { { .index = HRTIMER_BASE_MONOTONIC, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, { .index = HRTIMER_BASE_MONOTONIC_SOFT, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, }, { .index = HRTIMER_BASE_REALTIME_SOFT, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, }, { .index = HRTIMER_BASE_BOOTTIME_SOFT, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, }, { .index = HRTIMER_BASE_TAI_SOFT, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, }, }, .csd = CSD_INIT(retrigger_next_event, NULL) }; static inline bool hrtimer_base_is_online(struct hrtimer_cpu_base *base) { if (!IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; else return likely(base->online); } /* * Functions and macros which are different for UP/SMP systems are kept in a * single place */ #ifdef CONFIG_SMP /* * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base() * such that hrtimer_callback_running() can unconditionally dereference * timer->base->cpu_base */ static struct hrtimer_cpu_base migration_cpu_base = { .clock_base = { { .cpu_base = &migration_cpu_base, .seq = SEQCNT_RAW_SPINLOCK_ZERO(migration_cpu_base.seq, &migration_cpu_base.lock), }, }, }; #define migration_base migration_cpu_base.clock_base[0] /* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are * locked, and the base itself is locked too. * * So __run_timers/migrate_timers can safely modify all timers which could * be found on the lists/queues. * * When the timer's base is locked, and the timer removed from list, it is * possible to set timer->base = &migration_base and drop the lock: the timer * remains locked. */ static struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->lock) { struct hrtimer_clock_base *base; for (;;) { base = READ_ONCE(timer->base); if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; /* The timer has migrated to another CPU: */ raw_spin_unlock_irqrestore(&base->cpu_base->lock, *flags); } cpu_relax(); } } /* * Check if the elected target is suitable considering its next * event and the hotplug state of the current CPU. * * If the elected target is remote and its next event is after the timer * to queue, then a remote reprogram is necessary. However there is no * guarantee the IPI handling the operation would arrive in time to meet * the high resolution deadline. In this case the local CPU becomes a * preferred target, unless it is offline. * * High and low resolution modes are handled the same way for simplicity. * * Called with cpu_base->lock of target cpu held. */ static bool hrtimer_suitable_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base, struct hrtimer_cpu_base *new_cpu_base, struct hrtimer_cpu_base *this_cpu_base) { ktime_t expires; /* * The local CPU clockevent can be reprogrammed. Also get_target_base() * guarantees it is online. */ if (new_cpu_base == this_cpu_base) return true; /* * The offline local CPU can't be the default target if the * next remote target event is after this timer. Keep the * elected new base. An IPI will we issued to reprogram * it as a last resort. */ if (!hrtimer_base_is_online(this_cpu_base)) return true; expires = ktime_sub(hrtimer_get_expires(timer), new_base->offset); return expires >= new_base->cpu_base->expires_next; } static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { if (!hrtimer_base_is_online(base)) { int cpu = cpumask_any_and(cpu_online_mask, housekeeping_cpumask(HK_TYPE_TIMER)); return &per_cpu(hrtimer_bases, cpu); } #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) if (static_branch_likely(&timers_migration_enabled) && !pinned) return &per_cpu(hrtimer_bases, get_nohz_timer_target()); #endif return base; } /* * We switch the timer base to a power-optimized selected CPU target, * if: * - NO_HZ_COMMON is enabled * - timer migration is enabled * - the timer callback is not running * - the timer is not the first expiring timer on the new target * * If one of the above requirements is not fulfilled we move the timer * to the current CPU or leave it on the previously assigned CPU if * the timer callback is currently running. */ static inline struct hrtimer_clock_base * switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, int pinned) { struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base; struct hrtimer_clock_base *new_base; int basenum = base->index; this_cpu_base = this_cpu_ptr(&hrtimer_bases); new_cpu_base = get_target_base(this_cpu_base, pinned); again: new_base = &new_cpu_base->clock_base[basenum]; if (base != new_base) { /* * We are trying to move timer to new_base. * However we can't change timer's base while it is running, * so we keep it on the same CPU. No hassle vs. reprogramming * the event source in the high resolution case. The softirq * code will take care of this when the timer function has * completed. There is no conflict as we hold the lock until * the timer is enqueued. */ if (unlikely(hrtimer_callback_running(timer))) return base; /* See the comment in lock_hrtimer_base() */ WRITE_ONCE(timer->base, &migration_base); raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); new_cpu_base = this_cpu_base; WRITE_ONCE(timer->base, base); goto again; } WRITE_ONCE(timer->base, new_base); } else { if (!hrtimer_suitable_target(timer, new_base, new_cpu_base, this_cpu_base)) { new_cpu_base = this_cpu_base; goto again; } } return new_base; } #else /* CONFIG_SMP */ static inline struct hrtimer_clock_base * lock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __acquires(&timer->base->cpu_base->lock) { struct hrtimer_clock_base *base = timer->base; raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); return base; } # define switch_hrtimer_base(t, b, p) (b) #endif /* !CONFIG_SMP */ /* * Functions for the union type storage format of ktime_t which are * too large for inlining: */ #if BITS_PER_LONG < 64 /* * Divide a ktime value by a nanosecond value */ s64 __ktime_divns(const ktime_t kt, s64 div) { int sft = 0; s64 dclc; u64 tmp; dclc = ktime_to_ns(kt); tmp = dclc < 0 ? -dclc : dclc; /* Make sure the divisor is less than 2^32: */ while (div >> 32) { sft++; div >>= 1; } tmp >>= sft; do_div(tmp, (u32) div); return dclc < 0 ? -tmp : tmp; } EXPORT_SYMBOL_GPL(__ktime_divns); #endif /* BITS_PER_LONG >= 64 */ /* * Add two ktime values and do a safety check for overflow: */ ktime_t ktime_add_safe(const ktime_t lhs, const ktime_t rhs) { ktime_t res = ktime_add_unsafe(lhs, rhs); /* * We use KTIME_SEC_MAX here, the maximum timeout which we can * return to user space in a timespec: */ if (res < 0 || res < lhs || res < rhs) res = ktime_set(KTIME_SEC_MAX, 0); return res; } EXPORT_SYMBOL_GPL(ktime_add_safe); #ifdef CONFIG_DEBUG_OBJECTS_TIMERS static const struct debug_obj_descr hrtimer_debug_descr; static void *hrtimer_debug_hint(void *addr) { return ACCESS_PRIVATE((struct hrtimer *)addr, function); } /* * fixup_init is called when: * - an active object is initialized */ static bool hrtimer_fixup_init(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_init(timer, &hrtimer_debug_descr); return true; default: return false; } } /* * fixup_activate is called when: * - an active object is activated * - an unknown non-static object is activated */ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) { switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); fallthrough; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool hrtimer_fixup_free(void *addr, enum debug_obj_state state) { struct hrtimer *timer = addr; switch (state) { case ODEBUG_STATE_ACTIVE: hrtimer_cancel(timer); debug_object_free(timer, &hrtimer_debug_descr); return true; default: return false; } } static const struct debug_obj_descr hrtimer_debug_descr = { .name = "hrtimer", .debug_hint = hrtimer_debug_hint, .fixup_init = hrtimer_fixup_init, .fixup_activate = hrtimer_fixup_activate, .fixup_free = hrtimer_fixup_free, }; static inline void debug_hrtimer_init(struct hrtimer *timer) { debug_object_init(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { debug_object_init_on_stack(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_object_activate(timer, &hrtimer_debug_descr); } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { debug_object_deactivate(timer, &hrtimer_debug_descr); } void destroy_hrtimer_on_stack(struct hrtimer *timer) { debug_object_free(timer, &hrtimer_debug_descr); } EXPORT_SYMBOL_GPL(destroy_hrtimer_on_stack); #else static inline void debug_hrtimer_init(struct hrtimer *timer) { } static inline void debug_hrtimer_init_on_stack(struct hrtimer *timer) { } static inline void debug_hrtimer_activate(struct hrtimer *timer, enum hrtimer_mode mode) { } static inline void debug_hrtimer_deactivate(struct hrtimer *timer) { } #endif static inline void debug_setup(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init(timer); trace_hrtimer_setup(timer, clockid, mode); } static inline void debug_setup_on_stack(struct hrtimer *timer, clockid_t clockid, enum hrtimer_mode mode) { debug_hrtimer_init_on_stack(timer); trace_hrtimer_setup(timer, clockid, mode); } static inline void debug_activate(struct hrtimer *timer, enum hrtimer_mode mode) { debug_hrtimer_activate(timer, mode); trace_hrtimer_start(timer, mode); } static inline void debug_deactivate(struct hrtimer *timer) { debug_hrtimer_deactivate(timer); trace_hrtimer_cancel(timer); } static struct hrtimer_clock_base * __next_base(struct hrtimer_cpu_base *cpu_base, unsigned int *active) { unsigned int idx; if (!*active) return NULL; idx = __ffs(*active); *active &= ~(1U << idx); return &cpu_base->clock_base[idx]; } #define for_each_active_base(base, cpu_base, active) \ while ((base = __next_base((cpu_base), &(active)))) static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base, const struct hrtimer *exclude, unsigned int active, ktime_t expires_next) { struct hrtimer_clock_base *base; ktime_t expires; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; struct hrtimer *timer; next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); if (timer == exclude) { /* Get to the next timer in the queue. */ next = timerqueue_iterate_next(next); if (!next) continue; timer = container_of(next, struct hrtimer, node); } expires = ktime_sub(hrtimer_get_expires(timer), base->offset); if (expires < expires_next) { expires_next = expires; /* Skip cpu_base update if a timer is being excluded. */ if (exclude) continue; if (timer->is_soft) cpu_base->softirq_next_timer = timer; else cpu_base->next_timer = timer; } } /* * clock_was_set() might have changed base->offset of any of * the clock bases so the result might be negative. Fix it up * to prevent a false positive in clockevents_program_event(). */ if (expires_next < 0) expires_next = 0; return expires_next; } /* * Recomputes cpu_base::*next_timer and returns the earliest expires_next * but does not set cpu_base::*expires_next, that is done by * hrtimer[_force]_reprogram and hrtimer_interrupt only. When updating * cpu_base::*expires_next right away, reprogramming logic would no longer * work. * * When a softirq is pending, we can ignore the HRTIMER_ACTIVE_SOFT bases, * those timers will get run whenever the softirq gets handled, at the end of * hrtimer_run_softirq(), hrtimer_update_softirq_timer() will re-add these bases. * * Therefore softirq values are those from the HRTIMER_ACTIVE_SOFT clock bases. * The !softirq values are the minima across HRTIMER_ACTIVE_ALL, unless an actual * softirq is pending, in which case they're the minima of HRTIMER_ACTIVE_HARD. * * @active_mask must be one of: * - HRTIMER_ACTIVE_ALL, * - HRTIMER_ACTIVE_SOFT, or * - HRTIMER_ACTIVE_HARD. */ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base, unsigned int active_mask) { unsigned int active; struct hrtimer *next_timer = NULL; ktime_t expires_next = KTIME_MAX; if (!cpu_base->softirq_activated && (active_mask & HRTIMER_ACTIVE_SOFT)) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; cpu_base->softirq_next_timer = NULL; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, KTIME_MAX); next_timer = cpu_base->softirq_next_timer; } if (active_mask & HRTIMER_ACTIVE_HARD) { active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; cpu_base->next_timer = next_timer; expires_next = __hrtimer_next_event_base(cpu_base, NULL, active, expires_next); } return expires_next; } static ktime_t hrtimer_update_next_event(struct hrtimer_cpu_base *cpu_base) { ktime_t expires_next, soft = KTIME_MAX; /* * If the soft interrupt has already been activated, ignore the * soft bases. They will be handled in the already raised soft * interrupt. */ if (!cpu_base->softirq_activated) { soft = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * Update the soft expiry time. clock_settime() might have * affected it. */ cpu_base->softirq_expires_next = soft; } expires_next = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_HARD); /* * If a softirq timer is expiring first, update cpu_base->next_timer * and program the hardware with the soft expiry time. */ if (expires_next > soft) { cpu_base->next_timer = cpu_base->softirq_next_timer; expires_next = soft; } return expires_next; } static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) { ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; ktime_t now = ktime_get_update_offsets_now(&base->clock_was_set_seq, offs_real, offs_boot, offs_tai); base->clock_base[HRTIMER_BASE_REALTIME_SOFT].offset = *offs_real; base->clock_base[HRTIMER_BASE_BOOTTIME_SOFT].offset = *offs_boot; base->clock_base[HRTIMER_BASE_TAI_SOFT].offset = *offs_tai; return now; } /* * Is the high resolution mode active ? */ static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? cpu_base->hres_active : 0; } static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, struct hrtimer *next_timer, ktime_t expires_next) { cpu_base->expires_next = expires_next; /* * If hres is not active, hardware does not have to be * reprogrammed yet. * * If a hang was detected in the last timer interrupt then we * leave the hang delay active in the hardware. We want the * system to make progress. That also prevents the following * scenario: * T1 expires 50ms from now * T2 expires 5s from now * * T1 is removed, so this code is called and would reprogram * the hardware to 5s from now. Any hrtimer_start after that * will not reprogram the hardware due to hang_detected being * set. So we'd effectively block all timers until the T2 event * fires. */ if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) return; tick_program_event(expires_next, 1); } /* * Reprogram the event source with checking both queues for the * next event * Called with interrupts disabled and base->lock held */ static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { ktime_t expires_next; expires_next = hrtimer_update_next_event(cpu_base); if (skip_equal && expires_next == cpu_base->expires_next) return; __hrtimer_reprogram(cpu_base, cpu_base->next_timer, expires_next); } /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer enabled ? */ static bool hrtimer_hres_enabled __read_mostly = true; unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; EXPORT_SYMBOL_GPL(hrtimer_resolution); /* * Enable / Disable high resolution mode */ static int __init setup_hrtimer_hres(char *str) { return (kstrtobool(str, &hrtimer_hres_enabled) == 0); } __setup("highres=", setup_hrtimer_hres); /* * hrtimer_high_res_enabled - query, if the highres mode is enabled */ static inline int hrtimer_is_hres_enabled(void) { return hrtimer_hres_enabled; } /* * Switch to high resolution mode */ static void hrtimer_switch_to_hres(void) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { pr_warn("Could not switch to high resolution mode on CPU %u\n", base->cpu); return; } base->hres_active = 1; hrtimer_resolution = HIGH_RES_NSEC; tick_setup_sched_timer(true); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); } #else static inline int hrtimer_is_hres_enabled(void) { return 0; } static inline void hrtimer_switch_to_hres(void) { } #endif /* CONFIG_HIGH_RES_TIMERS */ /* * Retrigger next event is called after clock was set with interrupts * disabled through an SMP function call or directly from low level * resume code. * * This is only invoked when: * - CONFIG_HIGH_RES_TIMERS is enabled. * - CONFIG_NOHZ_COMMON is enabled * * For the other cases this function is empty and because the call sites * are optimized out it vanishes as well, i.e. no need for lots of * #ifdeffery. */ static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); /* * When high resolution mode or nohz is active, then the offsets of * CLOCK_REALTIME/TAI/BOOTTIME have to be updated. Otherwise the * next tick will take care of that. * * If high resolution mode is active then the next expiring timer * must be reevaluated and the clock event device reprogrammed if * necessary. * * In the NOHZ case the update of the offset and the reevaluation * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. * * In periodic low resolution mode, the next softirq expiration * must also be updated. */ raw_spin_lock(&base->lock); hrtimer_update_base(base); if (hrtimer_hres_active(base)) hrtimer_force_reprogram(base, 0); else hrtimer_update_next_event(base); raw_spin_unlock(&base->lock); } /* * When a timer is enqueued and expires earlier than the already enqueued * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * * Called with interrupts disabled and base->cpu_base.lock held */ static void hrtimer_reprogram(struct hrtimer *timer, bool reprogram) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *base = timer->base; ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* * CLOCK_REALTIME timer might be requested with an absolute * expiry time which is less than base->offset. Set it to 0. */ if (expires < 0) expires = 0; if (timer->is_soft) { /* * soft hrtimer could be started on a remote CPU. In this * case softirq_expires_next needs to be updated on the * remote CPU. The soft hrtimer will not expire before the * first hard hrtimer on the remote CPU - * hrtimer_check_target() prevents this case. */ struct hrtimer_cpu_base *timer_cpu_base = base->cpu_base; if (timer_cpu_base->softirq_activated) return; if (!ktime_before(expires, timer_cpu_base->softirq_expires_next)) return; timer_cpu_base->softirq_next_timer = timer; timer_cpu_base->softirq_expires_next = expires; if (!ktime_before(expires, timer_cpu_base->expires_next) || !reprogram) return; } /* * If the timer is not on the current cpu, we cannot reprogram * the other cpus clock event device. */ if (base->cpu_base != cpu_base) return; if (expires >= cpu_base->expires_next) return; /* * If the hrtimer interrupt is running, then it will reevaluate the * clock bases and reprogram the clock event device. */ if (cpu_base->in_hrtirq) return; cpu_base->next_timer = timer; __hrtimer_reprogram(cpu_base, timer, expires); } static bool update_needs_ipi(struct hrtimer_cpu_base *cpu_base, unsigned int active) { struct hrtimer_clock_base *base; unsigned int seq; ktime_t expires; /* * Update the base offsets unconditionally so the following * checks whether the SMP function call is required works. * * The update is safe even when the remote CPU is in the hrtimer * interrupt or the hrtimer soft interrupt and expiring affected * bases. Either it will see the update before handling a base or * it will see it when it finishes the processing and reevaluates * the next expiring timer. */ seq = cpu_base->clock_was_set_seq; hrtimer_update_base(cpu_base); /* * If the sequence did not change over the update then the * remote CPU already handled it. */ if (seq == cpu_base->clock_was_set_seq) return false; /* * If the remote CPU is currently handling an hrtimer interrupt, it * will reevaluate the first expiring timer of all clock bases * before reprogramming. Nothing to do here. */ if (cpu_base->in_hrtirq) return false; /* * Walk the affected clock bases and check whether the first expiring * timer in a clock base is moving ahead of the first expiring timer of * @cpu_base. If so, the IPI must be invoked because per CPU clock * event devices cannot be remotely reprogrammed. */ active &= cpu_base->active_bases; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *next; next = timerqueue_getnext(&base->active); expires = ktime_sub(next->expires, base->offset); if (expires < cpu_base->expires_next) return true; /* Extra check for softirq clock bases */ if (base->clockid < HRTIMER_BASE_MONOTONIC_SOFT) continue; if (cpu_base->softirq_activated) continue; if (expires < cpu_base->softirq_expires_next) return true; } return false; } /* * Clock was set. This might affect CLOCK_REALTIME, CLOCK_TAI and * CLOCK_BOOTTIME (for late sleep time injection). * * This requires to update the offsets for these clocks * vs. CLOCK_MONOTONIC. When high resolution timers are enabled, then this * also requires to eventually reprogram the per CPU clock event devices * when the change moves an affected timer ahead of the first expiring * timer on that CPU. Obviously remote per CPU clock event devices cannot * be reprogrammed. The other reason why an IPI has to be sent is when the * system is in !HIGH_RES and NOHZ mode. The NOHZ mode updates the offsets * in the tick, which obviously might be stopped, so this has to bring out * the remote CPU which might sleep in idle to get this sorted. */ void clock_was_set(unsigned int bases) { struct hrtimer_cpu_base *cpu_base = raw_cpu_ptr(&hrtimer_bases); cpumask_var_t mask; int cpu; if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active) goto out_timerfd; if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { on_each_cpu(retrigger_next_event, NULL, 1); goto out_timerfd; } /* Avoid interrupting CPUs if possible */ cpus_read_lock(); for_each_online_cpu(cpu) { unsigned long flags; cpu_base = &per_cpu(hrtimer_bases, cpu); raw_spin_lock_irqsave(&cpu_base->lock, flags); if (update_needs_ipi(cpu_base, bases)) cpumask_set_cpu(cpu, mask); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } preempt_disable(); smp_call_function_many(mask, retrigger_next_event, NULL, 1); preempt_enable(); cpus_read_unlock(); free_cpumask_var(mask); out_timerfd: timerfd_clock_was_set(); } static void clock_was_set_work(struct work_struct *work) { clock_was_set(CLOCK_SET_WALL); } static DECLARE_WORK(hrtimer_work, clock_was_set_work); /* * Called from timekeeping code to reprogram the hrtimer interrupt device * on all cpus and to notify timerfd. */ void clock_was_set_delayed(void) { schedule_work(&hrtimer_work); } /* * Called during resume either directly from via timekeeping_resume() * or in the case of s2idle from tick_unfreeze() to ensure that the * hrtimers are up to date. */ void hrtimers_resume_local(void) { lockdep_assert_irqs_disabled(); /* Retrigger on the local CPU */ retrigger_next_event(NULL); } /* * Counterpart to lock_hrtimer_base above: */ static inline void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) __releases(&timer->base->cpu_base->lock) { raw_spin_unlock_irqrestore(&timer->base->cpu_base->lock, *flags); } /** * hrtimer_forward() - forward the timer expiry * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward * * Forward the timer expiry so it will expire in the future. * * .. note:: * This only updates the timer expiry value and does not requeue the timer. * * There is also a variant of the function hrtimer_forward_now(). * * Context: Can be safely called from the callback function of @timer. If called * from other contexts @timer must neither be enqueued nor running the * callback and the caller needs to take care of serialization. * * Return: The number of overruns are returned. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { u64 orun = 1; ktime_t delta; delta = ktime_sub(now, hrtimer_get_expires(timer)); if (delta < 0) return 0; if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED)) return 0; if (interval < hrtimer_resolution) interval = hrtimer_resolution; if (unlikely(delta >= interval)) { s64 incr = ktime_to_ns(interval); orun = ktime_divns(delta, incr); hrtimer_add_expires_ns(timer, incr * orun); if (hrtimer_get_expires_tv64(timer) > now) return orun; /* * This (and the ktime_add() below) is the * correction for exact: */ orun++; } hrtimer_add_expires(timer, interval); return orun; } EXPORT_SYMBOL_GPL(hrtimer_forward); /* * enqueue_hrtimer - internal function to (re)start a timer * * The timer is inserted in expiry order. Insertion into the * red black tree is O(log(n)). Must hold the base lock. * * Returns true when the new timer is the leftmost timer in the tree. */ static bool enqueue_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, enum hrtimer_mode mode) { debug_activate(timer, mode); WARN_ON_ONCE(!base->cpu_base->online); base->cpu_base->active_bases |= 1 << base->index; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, HRTIMER_STATE_ENQUEUED); return timerqueue_add(&base->active, &timer->node); } /* * __remove_hrtimer - internal function to remove a timer * * Caller must hold the base lock. * * High resolution timer mode reprograms the clock event device when the * timer is the one which expires next. The caller can disable this by setting * reprogram to zero. This is useful, when the context does a reprogramming * anyway (e.g. timer interrupt) */ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, u8 newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; u8 state = timer->state; /* Pairs with the lockless read in hrtimer_is_queued() */ WRITE_ONCE(timer->state, newstate); if (!(state & HRTIMER_STATE_ENQUEUED)) return; if (!timerqueue_del(&base->active, &timer->node)) cpu_base->active_bases &= ~(1 << base->index); /* * Note: If reprogram is false we do not update * cpu_base->next_timer. This happens when we remove the first * timer on a remote cpu. No harm as we never dereference * cpu_base->next_timer. So the worst thing what can happen is * an superfluous call to hrtimer_force_reprogram() on the * remote cpu later on if the same timer gets enqueued again. */ if (reprogram && timer == cpu_base->next_timer) hrtimer_force_reprogram(cpu_base, 1); } /* * remove hrtimer, called with base lock held */ static inline int remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart, bool keep_local) { u8 state = timer->state; if (state & HRTIMER_STATE_ENQUEUED) { bool reprogram; /* * Remove the timer and force reprogramming when high * resolution mode is active and the timer is on the current * CPU. If we remove a timer on another CPU, reprogramming is * skipped. The interrupt event on this CPU is fired and * reprogramming happens in the interrupt handler. This is a * rare case and less expensive than a smp call. */ debug_deactivate(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); /* * If the timer is not restarted then reprogramming is * required if the timer is local. If it is local and about * to be restarted, avoid programming it twice (on removal * and a moment later when it's requeued). */ if (!restart) state = HRTIMER_STATE_INACTIVE; else reprogram &= !keep_local; __remove_hrtimer(timer, base, state, reprogram); return 1; } return 0; } static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) { #ifdef CONFIG_TIME_LOW_RES /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution * (i.e. one jiffy) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) tim = ktime_add_safe(tim, hrtimer_resolution); #endif return tim; } static void hrtimer_update_softirq_timer(struct hrtimer_cpu_base *cpu_base, bool reprogram) { ktime_t expires; /* * Find the next SOFT expiration. */ expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_SOFT); /* * reprogramming needs to be triggered, even if the next soft * hrtimer expires at the same time than the next hard * hrtimer. cpu_base->softirq_expires_next needs to be updated! */ if (expires == KTIME_MAX) return; /* * cpu_base->*next_timer is recomputed by __hrtimer_get_next_event() * cpu_base->*expires_next is only set by hrtimer_reprogram() */ hrtimer_reprogram(cpu_base->softirq_next_timer, reprogram); } static int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode, struct hrtimer_clock_base *base) { struct hrtimer_cpu_base *this_cpu_base = this_cpu_ptr(&hrtimer_bases); struct hrtimer_clock_base *new_base; bool force_local, first; /* * If the timer is on the local cpu base and is the first expiring * timer then this might end up reprogramming the hardware twice * (on removal and on enqueue). To avoid that by prevent the * reprogram on removal, keep the timer local to the current CPU * and enforce reprogramming after it is queued no matter whether * it is the new first expiring timer again or not. */ force_local = base->cpu_base == this_cpu_base; force_local &= base->cpu_base->next_timer == timer; /* * Don't force local queuing if this enqueue happens on a unplugged * CPU after hrtimer_cpu_dying() has been invoked. */ force_local &= this_cpu_base->online; /* * Remove an active timer from the queue. In case it is not queued * on the current CPU, make sure that remove_hrtimer() updates the * remote data correctly. * * If it's on the current CPU and the first expiring timer, then * skip reprogramming, keep the timer local and enforce * reprogramming later if it was the first expiring timer. This * avoids programming the underlying clock event twice (once at * removal and once after enqueue). */ remove_hrtimer(timer, base, true, force_local); if (mode & HRTIMER_MODE_REL) tim = ktime_add_safe(tim, base->get_time()); tim = hrtimer_update_lowres(timer, tim, mode); hrtimer_set_expires_range_ns(timer, tim, delta_ns); /* Switch the timer base, if necessary: */ if (!force_local) { new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); } else { new_base = base; } first = enqueue_hrtimer(timer, new_base, mode); if (!force_local) { /* * If the current CPU base is online, then the timer is * never queued on a remote CPU if it would be the first * expiring timer there. */ if (hrtimer_base_is_online(this_cpu_base)) return first; /* * Timer was enqueued remote because the current base is * already offline. If the timer is the first to expire, * kick the remote CPU to reprogram the clock event. */ if (first) { struct hrtimer_cpu_base *new_cpu_base = new_base->cpu_base; smp_call_function_single_async(new_cpu_base->cpu, &new_cpu_base->csd); } return 0; } /* * Timer was forced to stay on the current CPU to avoid * reprogramming on removal and enqueue. Force reprogram the * hardware by evaluating the new first expiring timer. */ hrtimer_force_reprogram(new_base->cpu_base, 1); return 0; } /** * hrtimer_start_range_ns - (re)start an hrtimer * @timer: the timer to be added * @tim: expiry time * @delta_ns: "slack" range for the timer * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED); * softirq based mode is considered for debug purpose only! */ void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, u64 delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base; unsigned long flags; /* * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft * match on CONFIG_PREEMPT_RT = n. With PREEMPT_RT check the hard * expiry mode because unmarked timers are moved to softirq expiry. */ if (!IS_ENABLED(CONFIG_PREEMPT_RT)) WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); else WARN_ON_ONCE(!(mode & HRTIMER_MODE_HARD) ^ !timer->is_hard); base = lock_hrtimer_base(timer, &flags); if (__hrtimer_start_range_ns(timer, tim, delta_ns, mode, base)) hrtimer_reprogram(timer, true); unlock_hrtimer_base(timer, &flags); } EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); /** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop * * Returns: * * * 0 when the timer was not active * * 1 when the timer was active * * -1 when the timer is currently executing the callback function and * cannot be stopped */ int hrtimer_try_to_cancel(struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned long flags; int ret = -1; /* * Check lockless first. If the timer is not active (neither * enqueued nor running the callback, nothing to do here. The * base lock does not serialize against a concurrent enqueue, * so we can avoid taking it. */ if (!hrtimer_active(timer)) return 0; base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) ret = remove_hrtimer(timer, base, false, false); unlock_hrtimer_base(timer, &flags); return ret; } EXPORT_SYMBOL_GPL(hrtimer_try_to_cancel); #ifdef CONFIG_PREEMPT_RT static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { spin_lock_init(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) __acquires(&base->softirq_expiry_lock) { spin_lock(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) __releases(&base->softirq_expiry_lock) { spin_unlock(&base->softirq_expiry_lock); } /* * The counterpart to hrtimer_cancel_wait_running(). * * If there is a waiter for cpu_base->expiry_lock, then it was waiting for * the timer callback to finish. Drop expiry_lock and reacquire it. That * allows the waiter to acquire the lock and make progress. */ static void hrtimer_sync_wait_running(struct hrtimer_cpu_base *cpu_base, unsigned long flags) { if (atomic_read(&cpu_base->timer_waiters)) { raw_spin_unlock_irqrestore(&cpu_base->lock, flags); spin_unlock(&cpu_base->softirq_expiry_lock); spin_lock(&cpu_base->softirq_expiry_lock); raw_spin_lock_irq(&cpu_base->lock); } } #ifdef CONFIG_SMP static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) { return base == &migration_base; } #else static __always_inline bool is_migration_base(struct hrtimer_clock_base *base) { return false; } #endif /* * This function is called on PREEMPT_RT kernels when the fast path * deletion of a timer failed because the timer callback function was * running. * * This prevents priority inversion: if the soft irq thread is preempted * in the middle of a timer callback, then calling hrtimer_cancel() can * lead to two issues: * * - If the caller is on a remote CPU then it has to spin wait for the timer * handler to complete. This can result in unbound priority inversion. * * - If the caller originates from the task which preempted the timer * handler on the same CPU, then spin waiting for the timer handler to * complete is never going to end. */ void hrtimer_cancel_wait_running(const struct hrtimer *timer) { /* Lockless read. Prevent the compiler from reloading it below */ struct hrtimer_clock_base *base = READ_ONCE(timer->base); /* * Just relax if the timer expires in hard interrupt context or if * it is currently on the migration base. */ if (!timer->is_soft || is_migration_base(base)) { cpu_relax(); return; } /* * Mark the base as contended and grab the expiry lock, which is * held by the softirq across the timer callback. Drop the lock * immediately so the softirq can expire the next timer. In theory * the timer could already be running again, but that's more than * unlikely and just causes another wait loop. */ atomic_inc(&base->cpu_base->timer_waiters); spin_lock_bh(&base->cpu_base->softirq_expiry_lock); atomic_dec(&base->cpu_base->timer_waiters); spin_unlock_bh(&base->cpu_base->softirq_expiry_lock); } #else static inline void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) { } static inline void hrtimer_sync_wait_running(struct hrtimer_cpu_base *base, unsigned long flags) { } #endif /** * hrtimer_cancel - cancel a timer and wait for the handler to finish. * @timer: the timer to be cancelled * * Returns: * 0 when the timer was not active * 1 when the timer was active */ int hrtimer_cancel(struct hrtimer *timer) { int ret; do { ret = hrtimer_try_to_cancel(timer); if (ret < 0) hrtimer_cancel_wait_running(timer); } while (ret < 0); return ret; } EXPORT_SYMBOL_GPL(hrtimer_cancel); /** * __hrtimer_get_remaining - get remaining time for the timer * @timer: the timer to read * @adjust: adjust relative timers when CONFIG_TIME_LOW_RES=y */ ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust) { unsigned long flags; ktime_t rem; lock_hrtimer_base(timer, &flags); if (IS_ENABLED(CONFIG_TIME_LOW_RES) && adjust) rem = hrtimer_expires_remaining_adjusted(timer); else rem = hrtimer_expires_remaining(timer); unlock_hrtimer_base(timer, &flags); return rem; } EXPORT_SYMBOL_GPL(__hrtimer_get_remaining); #ifdef CONFIG_NO_HZ_COMMON /** * hrtimer_get_next_event - get the time until next expiry event * * Returns the next expiry time or KTIME_MAX if no timer is pending. */ u64 hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (!hrtimer_hres_active(cpu_base)) expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } /** * hrtimer_next_event_without - time until next expiry event w/o one timer * @exclude: timer to exclude * * Returns the next expiry time over all timers except for the @exclude one or * KTIME_MAX if none of them is pending. */ u64 hrtimer_next_event_without(const struct hrtimer *exclude) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); if (hrtimer_hres_active(cpu_base)) { unsigned int active; if (!cpu_base->softirq_activated) { active = cpu_base->active_bases & HRTIMER_ACTIVE_SOFT; expires = __hrtimer_next_event_base(cpu_base, exclude, active, KTIME_MAX); } active = cpu_base->active_bases & HRTIMER_ACTIVE_HARD; expires = __hrtimer_next_event_base(cpu_base, exclude, active, expires); } raw_spin_unlock_irqrestore(&cpu_base->lock, flags); return expires; } #endif static inline int hrtimer_clockid_to_base(clockid_t clock_id) { switch (clock_id) { case CLOCK_REALTIME: return HRTIMER_BASE_REALTIME; case CLOCK_MONOTONIC: return HRTIMER_BASE_MONOTONIC; case CLOCK_BOOTTIME: return HRTIMER_BASE_BOOTTIME; case CLOCK_TAI: return HRTIMER_BASE_TAI; default: WARN(1, "Invalid clockid %d. Using MONOTONIC\n", clock_id); return HRTIMER_BASE_MONOTONIC; } } static void __hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { bool softtimer = !!(mode & HRTIMER_MODE_SOFT); struct hrtimer_cpu_base *cpu_base; int base; /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context for latency reasons and because the callbacks * can invoke functions which might sleep on RT, e.g. spin_lock(). */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(mode & HRTIMER_MODE_HARD)) softtimer = true; memset(timer, 0, sizeof(struct hrtimer)); cpu_base = raw_cpu_ptr(&hrtimer_bases); /* * POSIX magic: Relative CLOCK_REALTIME timers are not affected by * clock modifications, so they needs to become CLOCK_MONOTONIC to * ensure POSIX compliance. */ if (clock_id == CLOCK_REALTIME && mode & HRTIMER_MODE_REL) clock_id = CLOCK_MONOTONIC; base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; base += hrtimer_clockid_to_base(clock_id); timer->is_soft = softtimer; timer->is_hard = !!(mode & HRTIMER_MODE_HARD); timer->base = &cpu_base->clock_base[base]; timerqueue_init(&timer->node); if (WARN_ON_ONCE(!function)) ACCESS_PRIVATE(timer, function) = hrtimer_dummy_timeout; else ACCESS_PRIVATE(timer, function) = function; } /** * hrtimer_setup - initialize a timer to the given clock * @timer: the timer to be initialized * @function: the callback function * @clock_id: the clock to be used * @mode: The modes which are relevant for initialization: * HRTIMER_MODE_ABS, HRTIMER_MODE_REL, HRTIMER_MODE_ABS_SOFT, * HRTIMER_MODE_REL_SOFT * * The PINNED variants of the above can be handed in, * but the PINNED bit is ignored as pinning happens * when the hrtimer is started */ void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_setup(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup); /** * hrtimer_setup_on_stack - initialize a timer on stack memory * @timer: The timer to be initialized * @function: the callback function * @clock_id: The clock to be used * @mode: The timer mode * * Similar to hrtimer_setup(), except that this one must be used if struct hrtimer is in stack * memory. */ void hrtimer_setup_on_stack(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *), clockid_t clock_id, enum hrtimer_mode mode) { debug_setup_on_stack(timer, clock_id, mode); __hrtimer_setup(timer, function, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_on_stack); /* * A timer is active, when it is enqueued into the rbtree or the * callback function is running or it's in the state of being migrated * to another cpu. * * It is important for this function to not return a false negative. */ bool hrtimer_active(const struct hrtimer *timer) { struct hrtimer_clock_base *base; unsigned int seq; do { base = READ_ONCE(timer->base); seq = raw_read_seqcount_begin(&base->seq); if (timer->state != HRTIMER_STATE_INACTIVE || base->running == timer) return true; } while (read_seqcount_retry(&base->seq, seq) || base != READ_ONCE(timer->base)); return false; } EXPORT_SYMBOL_GPL(hrtimer_active); /* * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3 * distinct sections: * * - queued: the timer is queued * - callback: the timer is being ran * - post: the timer is inactive or (re)queued * * On the read side we ensure we observe timer->state and cpu_base->running * from the same section, if anything changed while we looked at it, we retry. * This includes timer->base changing because sequence numbers alone are * insufficient for that. * * The sequence numbers are required because otherwise we could still observe * a false negative if the read side got smeared over multiple consecutive * __run_hrtimer() invocations. */ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, struct hrtimer_clock_base *base, struct hrtimer *timer, ktime_t *now, unsigned long flags) __must_hold(&cpu_base->lock) { enum hrtimer_restart (*fn)(struct hrtimer *); bool expires_in_hardirq; int restart; lockdep_assert_held(&cpu_base->lock); debug_deactivate(timer); base->running = timer; /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); fn = ACCESS_PRIVATE(timer, function); /* * Clear the 'is relative' flag for the TIME_LOW_RES case. If the * timer is restarted with a period then it becomes an absolute * timer. If its not restarted it does not matter. */ if (IS_ENABLED(CONFIG_TIME_LOW_RES)) timer->is_rel = false; /* * The timer is marked as running in the CPU base, so it is * protected against migration to a different CPU even if the lock * is dropped. */ raw_spin_unlock_irqrestore(&cpu_base->lock, flags); trace_hrtimer_expire_entry(timer, now); expires_in_hardirq = lockdep_hrtimer_enter(timer); restart = fn(timer); lockdep_hrtimer_exit(expires_in_hardirq); trace_hrtimer_expire_exit(timer); raw_spin_lock_irq(&cpu_base->lock); /* * Note: We clear the running state after enqueue_hrtimer and * we do not reprogram the event hardware. Happens either in * hrtimer_start_range_ns() or in hrtimer_interrupt() * * Note: Because we dropped the cpu_base->lock above, * hrtimer_start_range_ns() can have popped in and enqueued the timer * for us already. */ if (restart != HRTIMER_NORESTART && !(timer->state & HRTIMER_STATE_ENQUEUED)) enqueue_hrtimer(timer, base, HRTIMER_MODE_ABS); /* * Separate the ->running assignment from the ->state assignment. * * As with a regular write barrier, this ensures the read side in * hrtimer_active() cannot observe base->running.timer == NULL && * timer->state == INACTIVE. */ raw_write_seqcount_barrier(&base->seq); WARN_ON_ONCE(base->running != timer); base->running = NULL; } static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, unsigned long flags, unsigned int active_mask) { struct hrtimer_clock_base *base; unsigned int active = cpu_base->active_bases & active_mask; for_each_active_base(base, cpu_base, active) { struct timerqueue_node *node; ktime_t basenow; basenow = ktime_add(now, base->offset); while ((node = timerqueue_getnext(&base->active))) { struct hrtimer *timer; timer = container_of(node, struct hrtimer, node); /* * The immediate goal for using the softexpires is * minimizing wakeups, not running timers at the * earliest interrupt after their soft expiration. * This allows us to avoid using a Priority Search * Tree, which can answer a stabbing query for * overlapping intervals and instead use the simple * BST we already have. * We don't add extra wakeups by delaying timers that * are right-of a not yet expired timer, because that * timer will have to trigger a wakeup anyway. */ if (basenow < hrtimer_get_softexpires_tv64(timer)) break; __run_hrtimer(cpu_base, base, timer, &basenow, flags); if (active_mask == HRTIMER_ACTIVE_SOFT) hrtimer_sync_wait_running(cpu_base, flags); } } } static __latent_entropy void hrtimer_run_softirq(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; hrtimer_cpu_base_lock_expiry(cpu_base); raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_SOFT); cpu_base->softirq_activated = 0; hrtimer_update_softirq_timer(cpu_base, true); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); hrtimer_cpu_base_unlock_expiry(cpu_base); } #ifdef CONFIG_HIGH_RES_TIMERS /* * High resolution timer interrupt * Called with interrupts disabled */ void hrtimer_interrupt(struct clock_event_device *dev) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); ktime_t expires_next, now, entry_time, delta; unsigned long flags; int retries = 0; BUG_ON(!cpu_base->hres_active); cpu_base->nr_events++; dev->next_event = KTIME_MAX; raw_spin_lock_irqsave(&cpu_base->lock, flags); entry_time = now = hrtimer_update_base(cpu_base); retry: cpu_base->in_hrtirq = 1; /* * We set expires_next to KTIME_MAX here with cpu_base->lock * held to prevent that a timer is enqueued in our queue via * the migration code. This does not affect enqueueing of * timers which run their callback and need to be requeued on * this CPU. */ cpu_base->expires_next = KTIME_MAX; if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); /* Reevaluate the clock bases for the [soft] next expiry */ expires_next = hrtimer_update_next_event(cpu_base); /* * Store the new expiry value so the migration code can verify * against it. */ cpu_base->expires_next = expires_next; cpu_base->in_hrtirq = 0; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); /* Reprogramming necessary ? */ if (!tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; return; } /* * The next timer was already expired due to: * - tracing * - long lasting callbacks * - being scheduled away when running in a VM * * We need to prevent that we loop forever in the hrtimer * interrupt routine. We give it 3 attempts to avoid * overreacting on some spurious event. * * Acquire base lock for updating the offsets and retrieving * the current time. */ raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); cpu_base->nr_retries++; if (++retries < 3) goto retry; /* * Give the system a chance to do something else than looping * here. We stored the entry time, so we know exactly how long * we spent here. We schedule the next event this amount of * time away. */ cpu_base->nr_hangs++; cpu_base->hang_detected = 1; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); delta = ktime_sub(now, entry_time); if ((unsigned int)delta > cpu_base->max_hang_time) cpu_base->max_hang_time = (unsigned int) delta; /* * Limit it to a sensible value as we enforce a longer * delay. Give the CPU at least 100ms to catch up. */ if (delta > 100 * NSEC_PER_MSEC) expires_next = ktime_add_ns(now, 100 * NSEC_PER_MSEC); else expires_next = ktime_add(now, delta); tick_program_event(expires_next, 1); pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } #endif /* !CONFIG_HIGH_RES_TIMERS */ /* * Called from run_local_timers in hardirq context every jiffy */ void hrtimer_run_queues(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; ktime_t now; if (hrtimer_hres_active(cpu_base)) return; /* * This _is_ ugly: We have to check periodically, whether we * can switch to highres and / or nohz mode. The clocksource * switch happens with xtime_lock held. Notification from * there only sets the check bit in the tick_oneshot code, * otherwise we might deadlock vs. xtime_lock. */ if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) { hrtimer_switch_to_hres(); return; } raw_spin_lock_irqsave(&cpu_base->lock, flags); now = hrtimer_update_base(cpu_base); if (!ktime_before(now, cpu_base->softirq_expires_next)) { cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->softirq_activated = 1; raise_timer_softirq(HRTIMER_SOFTIRQ); } __hrtimer_run_queues(cpu_base, now, flags, HRTIMER_ACTIVE_HARD); raw_spin_unlock_irqrestore(&cpu_base->lock, flags); } /* * Sleep related functions: */ static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer) { struct hrtimer_sleeper *t = container_of(timer, struct hrtimer_sleeper, timer); struct task_struct *task = t->task; t->task = NULL; if (task) wake_up_process(task); return HRTIMER_NORESTART; } /** * hrtimer_sleeper_start_expires - Start a hrtimer sleeper timer * @sl: sleeper to be started * @mode: timer mode abs/rel * * Wrapper around hrtimer_start_expires() for hrtimer_sleeper based timers * to allow PREEMPT_RT to tweak the delivery mode (soft/hardirq context) */ void hrtimer_sleeper_start_expires(struct hrtimer_sleeper *sl, enum hrtimer_mode mode) { /* * Make the enqueue delivery mode check work on RT. If the sleeper * was initialized for hard interrupt delivery, force the mode bit. * This is a special case for hrtimer_sleepers because * __hrtimer_setup_sleeper() determines the delivery mode on RT so the * fiddling with this decision is avoided at the call sites. */ if (IS_ENABLED(CONFIG_PREEMPT_RT) && sl->timer.is_hard) mode |= HRTIMER_MODE_HARD; hrtimer_start_expires(&sl->timer, mode); } EXPORT_SYMBOL_GPL(hrtimer_sleeper_start_expires); static void __hrtimer_setup_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { /* * On PREEMPT_RT enabled kernels hrtimers which are not explicitly * marked for hard interrupt expiry mode are moved into soft * interrupt context either for latency reasons or because the * hrtimer callback takes regular spinlocks or invokes other * functions which are not suitable for hard interrupt context on * PREEMPT_RT. * * The hrtimer_sleeper callback is RT compatible in hard interrupt * context, but there is a latency concern: Untrusted userspace can * spawn many threads which arm timers for the same expiry time on * the same CPU. That causes a latency spike due to the wakeup of * a gazillion threads. * * OTOH, privileged real-time user space applications rely on the * low latency of hard interrupt wakeups. If the current task is in * a real-time scheduling class, mark the mode for hard interrupt * expiry. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) { if (rt_or_dl_task_policy(current) && !(mode & HRTIMER_MODE_SOFT)) mode |= HRTIMER_MODE_HARD; } __hrtimer_setup(&sl->timer, hrtimer_wakeup, clock_id, mode); sl->task = current; } /** * hrtimer_setup_sleeper_on_stack - initialize a sleeper in stack memory * @sl: sleeper to be initialized * @clock_id: the clock to be used * @mode: timer mode abs/rel */ void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id, enum hrtimer_mode mode) { debug_setup_on_stack(&sl->timer, clock_id, mode); __hrtimer_setup_sleeper(sl, clock_id, mode); } EXPORT_SYMBOL_GPL(hrtimer_setup_sleeper_on_stack); int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) { switch(restart->nanosleep.type) { #ifdef CONFIG_COMPAT_32BIT_TIME case TT_COMPAT: if (put_old_timespec32(ts, restart->nanosleep.compat_rmtp)) return -EFAULT; break; #endif case TT_NATIVE: if (put_timespec64(ts, restart->nanosleep.rmtp)) return -EFAULT; break; default: BUG(); } return -ERESTART_RESTARTBLOCK; } static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode) { struct restart_block *restart; do { set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); hrtimer_sleeper_start_expires(t, mode); if (likely(t->task)) schedule(); hrtimer_cancel(&t->timer); mode = HRTIMER_MODE_ABS; } while (t->task && !signal_pending(current)); __set_current_state(TASK_RUNNING); if (!t->task) return 0; restart = ¤t->restart_block; if (restart->nanosleep.type != TT_NONE) { ktime_t rem = hrtimer_expires_remaining(&t->timer); struct timespec64 rmt; if (rem <= 0) return 0; rmt = ktime_to_timespec64(rem); return nanosleep_copyout(restart, &rmt); } return -ERESTART_RESTARTBLOCK; } static long __sched hrtimer_nanosleep_restart(struct restart_block *restart) { struct hrtimer_sleeper t; int ret; hrtimer_setup_sleeper_on_stack(&t, restart->nanosleep.clockid, HRTIMER_MODE_ABS); hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); ret = do_nanosleep(&t, HRTIMER_MODE_ABS); destroy_hrtimer_on_stack(&t.timer); return ret; } long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, const clockid_t clockid) { struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; hrtimer_setup_sleeper_on_stack(&t, clockid, mode); hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; /* Absolute timers do not update the rmtp value and restart: */ if (mode == HRTIMER_MODE_ABS) { ret = -ERESTARTNOHAND; goto out; } restart = ¤t->restart_block; restart->nanosleep.clockid = t.timer.base->clockid; restart->nanosleep.expires = hrtimer_get_expires_tv64(&t.timer); set_restart_fn(restart, hrtimer_nanosleep_restart); out: destroy_hrtimer_on_stack(&t.timer); return ret; } #ifdef CONFIG_64BIT SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, struct __kernel_timespec __user *, rmtp) { struct timespec64 tu; if (get_timespec64(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE; current->restart_block.nanosleep.rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { struct timespec64 tu; if (get_old_timespec32(&tu, rqtp)) return -EFAULT; if (!timespec64_valid(&tu)) return -EINVAL; current->restart_block.fn = do_no_restart_syscall; current->restart_block.nanosleep.type = rmtp ? TT_COMPAT : TT_NONE; current->restart_block.nanosleep.compat_rmtp = rmtp; return hrtimer_nanosleep(timespec64_to_ktime(tu), HRTIMER_MODE_REL, CLOCK_MONOTONIC); } #endif /* * Functions related to boot-time initialization: */ int hrtimers_prepare_cpu(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu); int i; for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { struct hrtimer_clock_base *clock_b = &cpu_base->clock_base[i]; clock_b->cpu_base = cpu_base; seqcount_raw_spinlock_init(&clock_b->seq, &cpu_base->lock); timerqueue_init_head(&clock_b->active); } cpu_base->cpu = cpu; hrtimer_cpu_base_init_expiry_lock(cpu_base); return 0; } int hrtimers_cpu_starting(unsigned int cpu) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); /* Clear out any left over state from a CPU down operation */ cpu_base->active_bases = 0; cpu_base->hres_active = 0; cpu_base->hang_detected = 0; cpu_base->next_timer = NULL; cpu_base->softirq_next_timer = NULL; cpu_base->expires_next = KTIME_MAX; cpu_base->softirq_expires_next = KTIME_MAX; cpu_base->online = 1; return 0; } #ifdef CONFIG_HOTPLUG_CPU static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, struct hrtimer_clock_base *new_base) { struct hrtimer *timer; struct timerqueue_node *node; while ((node = timerqueue_getnext(&old_base->active))) { timer = container_of(node, struct hrtimer, node); BUG_ON(hrtimer_callback_running(timer)); debug_deactivate(timer); /* * Mark it as ENQUEUED not INACTIVE otherwise the * timer could be seen as !active and just vanish away * under us on another CPU */ __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0); timer->base = new_base; /* * Enqueue the timers on the new cpu. This does not * reprogram the event device in case the timer * expires before the earliest on this CPU, but we run * hrtimer_interrupt after we migrated everything to * sort out already expired timers and reprogram the * event device. */ enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS); } } int hrtimers_cpu_dying(unsigned int dying_cpu) { int i, ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER)); struct hrtimer_cpu_base *old_base, *new_base; old_base = this_cpu_ptr(&hrtimer_bases); new_base = &per_cpu(hrtimer_bases, ncpu); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. */ raw_spin_lock(&old_base->lock); raw_spin_lock_nested(&new_base->lock, SINGLE_DEPTH_NESTING); for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { migrate_hrtimer_list(&old_base->clock_base[i], &new_base->clock_base[i]); } /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0); raw_spin_unlock(&new_base->lock); old_base->online = 0; raw_spin_unlock(&old_base->lock); return 0; } #endif /* CONFIG_HOTPLUG_CPU */ void __init hrtimers_init(void) { hrtimers_prepare_cpu(smp_processor_id()); hrtimers_cpu_starting(smp_processor_id()); open_softirq(HRTIMER_SOFTIRQ, hrtimer_run_softirq); } |
| 381 246 246 245 19 246 3 374 2 10 374 373 374 374 372 340 371 1 2 259 368 4 2 1 294 323 202 349 188 198 335 266 336 1 175 3 1 4 158 83 3 149 1 232 2 149 2 12 21 21 2 1 150 336 9 12 5 372 221 20 345 235 345 33 131 347 18 12 149 296 369 240 136 28 92 381 403 381 90 4 404 217 216 216 2 1 215 214 8 2 213 3 213 214 214 5 8 6 8 5 8 3 186 65 135 212 69 201 201 3 3 3 192 190 60 190 12 12 1 1 8 8 12 2 6 7 7 1 46 23 23 23 73 9 51 13 11 11 13 11 3 13 3 3 3 11 13 2 12 79 20 189 189 189 21 21 1 2 18 18 15 18 94 94 1 19 22 16 33 93 2 4 2 3 7 29 54 74 85 64 20 21 16 35 65 17 3 9 9 10 18 14 43 10 17 31 34 7 58 5 66 11 10 12 94 29 66 7 7 31 5 26 18 2 4 1 3 2 293 11 1 8 2 9 1 9 9 6 9 11 2 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * */ #include <linux/buffer_head.h> #include <linux/fs.h> #include <linux/mpage.h> #include <linux/namei.h> #include <linux/nls.h> #include <linux/uio.h> #include <linux/writeback.h> #include "debug.h" #include "ntfs.h" #include "ntfs_fs.h" /* * ntfs_read_mft - Read record and parse MFT. */ static struct inode *ntfs_read_mft(struct inode *inode, const struct cpu_str *name, const struct MFT_REF *ref) { int err = 0; struct ntfs_inode *ni = ntfs_i(inode); struct super_block *sb = inode->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; mode_t mode = 0; struct ATTR_STD_INFO5 *std5 = NULL; struct ATTR_LIST_ENTRY *le; struct ATTRIB *attr; bool is_match = false; bool is_root = false; bool is_dir; unsigned long ino = inode->i_ino; u32 rp_fa = 0, asize, t32; u16 roff, rsize, names = 0, links = 0; const struct ATTR_FILE_NAME *fname = NULL; const struct INDEX_ROOT *root; struct REPARSE_DATA_BUFFER rp; // 0x18 bytes u64 t64; struct MFT_REC *rec; struct runs_tree *run; struct timespec64 ts; inode->i_op = NULL; /* Setup 'uid' and 'gid' */ inode->i_uid = sbi->options->fs_uid; inode->i_gid = sbi->options->fs_gid; err = mi_init(&ni->mi, sbi, ino); if (err) goto out; if (!sbi->mft.ni && ino == MFT_REC_MFT && !sb->s_root) { t64 = sbi->mft.lbo >> sbi->cluster_bits; t32 = bytes_to_cluster(sbi, MFT_REC_VOL * sbi->record_size); sbi->mft.ni = ni; init_rwsem(&ni->file.run_lock); if (!run_add_entry(&ni->file.run, 0, t64, t32, true)) { err = -ENOMEM; goto out; } } err = mi_read(&ni->mi, ino == MFT_REC_MFT); if (err) goto out; rec = ni->mi.mrec; if (sbi->flags & NTFS_FLAGS_LOG_REPLAYING) { ; } else if (ref->seq != rec->seq) { err = -EINVAL; ntfs_err(sb, "MFT: r=%lx, expect seq=%x instead of %x!", ino, le16_to_cpu(ref->seq), le16_to_cpu(rec->seq)); goto out; } else if (!is_rec_inuse(rec)) { err = -ESTALE; ntfs_err(sb, "Inode r=%x is not in use!", (u32)ino); goto out; } if (le32_to_cpu(rec->total) != sbi->record_size) { /* Bad inode? */ err = -EINVAL; goto out; } if (!is_rec_base(rec)) { err = -EINVAL; goto out; } /* Record should contain $I30 root. */ is_dir = rec->flags & RECORD_FLAG_DIR; /* MFT_REC_MFT is not a dir */ if (is_dir && ino == MFT_REC_MFT) { err = -EINVAL; goto out; } inode->i_generation = le16_to_cpu(rec->seq); /* Enumerate all struct Attributes MFT. */ le = NULL; attr = NULL; /* * To reduce tab pressure use goto instead of * while( (attr = ni_enum_attr_ex(ni, attr, &le, NULL) )) */ next_attr: run = NULL; err = -EINVAL; attr = ni_enum_attr_ex(ni, attr, &le, NULL); if (!attr) goto end_enum; if (le && le->vcn) { /* This is non primary attribute segment. Ignore if not MFT. */ if (ino != MFT_REC_MFT || attr->type != ATTR_DATA) goto next_attr; run = &ni->file.run; asize = le32_to_cpu(attr->size); goto attr_unpack_run; } roff = attr->non_res ? 0 : le16_to_cpu(attr->res.data_off); rsize = attr->non_res ? 0 : le32_to_cpu(attr->res.data_size); asize = le32_to_cpu(attr->size); /* * Really this check was done in 'ni_enum_attr_ex' -> ... 'mi_enum_attr'. * There not critical to check this case again */ if (attr->name_len && sizeof(short) * attr->name_len + le16_to_cpu(attr->name_off) > asize) goto out; if (attr->non_res) { t64 = le64_to_cpu(attr->nres.alloc_size); if (le64_to_cpu(attr->nres.data_size) > t64 || le64_to_cpu(attr->nres.valid_size) > t64) goto out; } switch (attr->type) { case ATTR_STD: if (attr->non_res || asize < sizeof(struct ATTR_STD_INFO) + roff || rsize < sizeof(struct ATTR_STD_INFO)) goto out; if (std5) goto next_attr; std5 = Add2Ptr(attr, roff); #ifdef STATX_BTIME nt2kernel(std5->cr_time, &ni->i_crtime); #endif nt2kernel(std5->a_time, &ts); inode_set_atime_to_ts(inode, ts); nt2kernel(std5->c_time, &ts); inode_set_ctime_to_ts(inode, ts); nt2kernel(std5->m_time, &ts); inode_set_mtime_to_ts(inode, ts); ni->std_fa = std5->fa; if (asize >= sizeof(struct ATTR_STD_INFO5) + roff && rsize >= sizeof(struct ATTR_STD_INFO5)) ni->std_security_id = std5->security_id; goto next_attr; case ATTR_LIST: if (attr->name_len || le || ino == MFT_REC_LOG) goto out; err = ntfs_load_attr_list(ni, attr); if (err) goto out; le = NULL; attr = NULL; goto next_attr; case ATTR_NAME: if (attr->non_res || asize < SIZEOF_ATTRIBUTE_FILENAME + roff || rsize < SIZEOF_ATTRIBUTE_FILENAME) goto out; names += 1; fname = Add2Ptr(attr, roff); if (fname->type == FILE_NAME_DOS) goto next_attr; links += 1; if (name && name->len == fname->name_len && !ntfs_cmp_names_cpu(name, (struct le_str *)&fname->name_len, NULL, false)) is_match = true; goto next_attr; case ATTR_DATA: if (is_dir) { /* Ignore data attribute in dir record. */ goto next_attr; } if (ino == MFT_REC_BADCLUST && !attr->non_res) goto next_attr; if (attr->name_len && ((ino != MFT_REC_BADCLUST || !attr->non_res || attr->name_len != ARRAY_SIZE(BAD_NAME) || memcmp(attr_name(attr), BAD_NAME, sizeof(BAD_NAME))) && (ino != MFT_REC_SECURE || !attr->non_res || attr->name_len != ARRAY_SIZE(SDS_NAME) || memcmp(attr_name(attr), SDS_NAME, sizeof(SDS_NAME))))) { /* File contains stream attribute. Ignore it. */ goto next_attr; } if (is_attr_sparsed(attr)) ni->std_fa |= FILE_ATTRIBUTE_SPARSE_FILE; else ni->std_fa &= ~FILE_ATTRIBUTE_SPARSE_FILE; if (is_attr_compressed(attr)) ni->std_fa |= FILE_ATTRIBUTE_COMPRESSED; else ni->std_fa &= ~FILE_ATTRIBUTE_COMPRESSED; if (is_attr_encrypted(attr)) ni->std_fa |= FILE_ATTRIBUTE_ENCRYPTED; else ni->std_fa &= ~FILE_ATTRIBUTE_ENCRYPTED; if (!attr->non_res) { ni->i_valid = inode->i_size = rsize; inode_set_bytes(inode, rsize); } mode = S_IFREG | (0777 & sbi->options->fs_fmask_inv); if (!attr->non_res) { ni->ni_flags |= NI_FLAG_RESIDENT; goto next_attr; } inode_set_bytes(inode, attr_ondisk_size(attr)); ni->i_valid = le64_to_cpu(attr->nres.valid_size); inode->i_size = le64_to_cpu(attr->nres.data_size); if (!attr->nres.alloc_size) goto next_attr; run = ino == MFT_REC_BITMAP ? &sbi->used.bitmap.run : &ni->file.run; break; case ATTR_ROOT: if (attr->non_res) goto out; root = Add2Ptr(attr, roff); if (attr->name_len != ARRAY_SIZE(I30_NAME) || memcmp(attr_name(attr), I30_NAME, sizeof(I30_NAME))) goto next_attr; if (root->type != ATTR_NAME || root->rule != NTFS_COLLATION_TYPE_FILENAME) goto out; if (!is_dir) goto next_attr; is_root = true; ni->ni_flags |= NI_FLAG_DIR; err = indx_init(&ni->dir, sbi, attr, INDEX_MUTEX_I30); if (err) goto out; mode = sb->s_root ? (S_IFDIR | (0777 & sbi->options->fs_dmask_inv)) : (S_IFDIR | 0777); goto next_attr; case ATTR_ALLOC: if (!is_root || attr->name_len != ARRAY_SIZE(I30_NAME) || memcmp(attr_name(attr), I30_NAME, sizeof(I30_NAME))) goto next_attr; inode->i_size = le64_to_cpu(attr->nres.data_size); ni->i_valid = le64_to_cpu(attr->nres.valid_size); inode_set_bytes(inode, le64_to_cpu(attr->nres.alloc_size)); run = &ni->dir.alloc_run; break; case ATTR_BITMAP: if (ino == MFT_REC_MFT) { if (!attr->non_res) goto out; #ifndef CONFIG_NTFS3_64BIT_CLUSTER /* 0x20000000 = 2^32 / 8 */ if (le64_to_cpu(attr->nres.alloc_size) >= 0x20000000) goto out; #endif run = &sbi->mft.bitmap.run; break; } else if (is_dir && attr->name_len == ARRAY_SIZE(I30_NAME) && !memcmp(attr_name(attr), I30_NAME, sizeof(I30_NAME)) && attr->non_res) { run = &ni->dir.bitmap_run; break; } goto next_attr; case ATTR_REPARSE: if (attr->name_len) goto next_attr; rp_fa = ni_parse_reparse(ni, attr, &rp); switch (rp_fa) { case REPARSE_LINK: /* * Normal symlink. * Assume one unicode symbol == one utf8. */ inode->i_size = le16_to_cpu(rp.SymbolicLinkReparseBuffer .PrintNameLength) / sizeof(u16); ni->i_valid = inode->i_size; /* Clear directory bit. */ if (ni->ni_flags & NI_FLAG_DIR) { indx_clear(&ni->dir); memset(&ni->dir, 0, sizeof(ni->dir)); ni->ni_flags &= ~NI_FLAG_DIR; } else { run_close(&ni->file.run); } mode = S_IFLNK | 0777; is_dir = false; if (attr->non_res) { run = &ni->file.run; goto attr_unpack_run; // Double break. } break; case REPARSE_COMPRESSED: break; case REPARSE_DEDUPLICATED: break; } goto next_attr; case ATTR_EA_INFO: if (!attr->name_len && resident_data_ex(attr, sizeof(struct EA_INFO))) { ni->ni_flags |= NI_FLAG_EA; /* * ntfs_get_wsl_perm updates inode->i_uid, inode->i_gid, inode->i_mode */ inode->i_mode = mode; ntfs_get_wsl_perm(inode); mode = inode->i_mode; } goto next_attr; default: goto next_attr; } attr_unpack_run: roff = le16_to_cpu(attr->nres.run_off); if (roff > asize) { err = -EINVAL; goto out; } t64 = le64_to_cpu(attr->nres.svcn); err = run_unpack_ex(run, sbi, ino, t64, le64_to_cpu(attr->nres.evcn), t64, Add2Ptr(attr, roff), asize - roff); if (err < 0) goto out; err = 0; goto next_attr; end_enum: if (!std5) goto out; if (is_bad_inode(inode)) goto out; if (!is_match && name) { err = -ENOENT; goto out; } if (std5->fa & FILE_ATTRIBUTE_READONLY) mode &= ~0222; if (!names) { err = -EINVAL; goto out; } if (names != le16_to_cpu(rec->hard_links)) { /* Correct minor error on the fly. Do not mark inode as dirty. */ ntfs_inode_warn(inode, "Correct links count -> %u.", names); rec->hard_links = cpu_to_le16(names); ni->mi.dirty = true; } set_nlink(inode, links); if (S_ISDIR(mode)) { ni->std_fa |= FILE_ATTRIBUTE_DIRECTORY; /* * Dot and dot-dot should be included in count but was not * included in enumeration. * Usually a hard links to directories are disabled. */ inode->i_op = &ntfs_dir_inode_operations; inode->i_fop = unlikely(is_legacy_ntfs(sb)) ? &ntfs_legacy_dir_operations : &ntfs_dir_operations; ni->i_valid = 0; } else if (S_ISLNK(mode)) { ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY; inode->i_op = &ntfs_link_inode_operations; inode->i_fop = NULL; inode_nohighmem(inode); } else if (S_ISREG(mode)) { ni->std_fa &= ~FILE_ATTRIBUTE_DIRECTORY; inode->i_op = &ntfs_file_inode_operations; inode->i_fop = unlikely(is_legacy_ntfs(sb)) ? &ntfs_legacy_file_operations : &ntfs_file_operations; inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr : &ntfs_aops; if (ino != MFT_REC_MFT) init_rwsem(&ni->file.run_lock); } else if (S_ISCHR(mode) || S_ISBLK(mode) || S_ISFIFO(mode) || S_ISSOCK(mode)) { inode->i_op = &ntfs_special_inode_operations; init_special_inode(inode, mode, inode->i_rdev); } else if (fname && fname->home.low == cpu_to_le32(MFT_REC_EXTEND) && fname->home.seq == cpu_to_le16(MFT_REC_EXTEND)) { /* Records in $Extend are not a files or general directories. */ inode->i_op = &ntfs_file_inode_operations; } else { err = -EINVAL; goto out; } if ((sbi->options->sys_immutable && (std5->fa & FILE_ATTRIBUTE_SYSTEM)) && !S_ISFIFO(mode) && !S_ISSOCK(mode) && !S_ISLNK(mode)) { inode->i_flags |= S_IMMUTABLE; } else { inode->i_flags &= ~S_IMMUTABLE; } inode->i_mode = mode; if (!(ni->ni_flags & NI_FLAG_EA)) { /* If no xattr then no security (stored in xattr). */ inode->i_flags |= S_NOSEC; } if (ino == MFT_REC_MFT && !sb->s_root) sbi->mft.ni = NULL; unlock_new_inode(inode); return inode; out: if (ino == MFT_REC_MFT && !sb->s_root) sbi->mft.ni = NULL; iget_failed(inode); return ERR_PTR(err); } /* * ntfs_test_inode * * Return: 1 if match. */ static int ntfs_test_inode(struct inode *inode, void *data) { struct MFT_REF *ref = data; return ino_get(ref) == inode->i_ino; } static int ntfs_set_inode(struct inode *inode, void *data) { const struct MFT_REF *ref = data; inode->i_ino = ino_get(ref); return 0; } struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref, const struct cpu_str *name) { struct inode *inode; inode = iget5_locked(sb, ino_get(ref), ntfs_test_inode, ntfs_set_inode, (void *)ref); if (unlikely(!inode)) return ERR_PTR(-ENOMEM); /* If this is a freshly allocated inode, need to read it now. */ if (inode->i_state & I_NEW) inode = ntfs_read_mft(inode, name, ref); else if (ref->seq != ntfs_i(inode)->mi.mrec->seq) { /* * Sequence number is not expected. * Looks like inode was reused but caller uses the old reference */ iput(inode); inode = ERR_PTR(-ESTALE); } if (IS_ERR(inode)) ntfs_set_state(sb->s_fs_info, NTFS_DIRTY_ERROR); return inode; } enum get_block_ctx { GET_BLOCK_GENERAL = 0, GET_BLOCK_WRITE_BEGIN = 1, GET_BLOCK_DIRECT_IO_R = 2, GET_BLOCK_DIRECT_IO_W = 3, GET_BLOCK_BMAP = 4, }; static noinline int ntfs_get_block_vbo(struct inode *inode, u64 vbo, struct buffer_head *bh, int create, enum get_block_ctx ctx) { struct super_block *sb = inode->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; struct ntfs_inode *ni = ntfs_i(inode); struct folio *folio = bh->b_folio; u8 cluster_bits = sbi->cluster_bits; u32 block_size = sb->s_blocksize; u64 bytes, lbo, valid; u32 off; int err; CLST vcn, lcn, len; bool new; /* Clear previous state. */ clear_buffer_new(bh); clear_buffer_uptodate(bh); if (is_resident(ni)) { bh->b_blocknr = RESIDENT_LCN; bh->b_size = block_size; if (!folio) { /* direct io (read) or bmap call */ err = 0; } else { ni_lock(ni); err = attr_data_read_resident(ni, folio); ni_unlock(ni); if (!err) set_buffer_uptodate(bh); } return err; } vcn = vbo >> cluster_bits; off = vbo & sbi->cluster_mask; new = false; err = attr_data_get_block(ni, vcn, 1, &lcn, &len, create ? &new : NULL, create && sbi->cluster_size > PAGE_SIZE); if (err) goto out; if (!len) return 0; bytes = ((u64)len << cluster_bits) - off; if (lcn >= sbi->used.bitmap.nbits) { /* This case includes resident/compressed/sparse. */ if (!create) { if (bh->b_size > bytes) bh->b_size = bytes; return 0; } WARN_ON(1); } if (new) set_buffer_new(bh); lbo = ((u64)lcn << cluster_bits) + off; set_buffer_mapped(bh); bh->b_bdev = sb->s_bdev; bh->b_blocknr = lbo >> sb->s_blocksize_bits; valid = ni->i_valid; if (ctx == GET_BLOCK_DIRECT_IO_W) { /* ntfs_direct_IO will update ni->i_valid. */ if (vbo >= valid) set_buffer_new(bh); } else if (create) { /* Normal write. */ if (bytes > bh->b_size) bytes = bh->b_size; if (vbo >= valid) set_buffer_new(bh); if (vbo + bytes > valid) { ni->i_valid = vbo + bytes; mark_inode_dirty(inode); } } else if (vbo >= valid) { /* Read out of valid data. */ clear_buffer_mapped(bh); } else if (vbo + bytes <= valid) { /* Normal read. */ } else if (vbo + block_size <= valid) { /* Normal short read. */ bytes = block_size; } else { /* * Read across valid size: vbo < valid && valid < vbo + block_size */ bytes = block_size; if (folio) { u32 voff = valid - vbo; bh->b_size = block_size; off = vbo & (PAGE_SIZE - 1); folio_set_bh(bh, folio, off); if (bh_read(bh, 0) < 0) { err = -EIO; goto out; } folio_zero_segment(folio, off + voff, off + block_size); } } if (bh->b_size > bytes) bh->b_size = bytes; #ifndef __LP64__ if (ctx == GET_BLOCK_DIRECT_IO_W || ctx == GET_BLOCK_DIRECT_IO_R) { static_assert(sizeof(size_t) < sizeof(loff_t)); if (bytes > 0x40000000u) bh->b_size = 0x40000000u; } #endif return 0; out: return err; } int ntfs_get_block(struct inode *inode, sector_t vbn, struct buffer_head *bh_result, int create) { return ntfs_get_block_vbo(inode, (u64)vbn << inode->i_blkbits, bh_result, create, GET_BLOCK_GENERAL); } static int ntfs_get_block_bmap(struct inode *inode, sector_t vsn, struct buffer_head *bh_result, int create) { return ntfs_get_block_vbo(inode, (u64)vsn << inode->i_sb->s_blocksize_bits, bh_result, create, GET_BLOCK_BMAP); } static sector_t ntfs_bmap(struct address_space *mapping, sector_t block) { return generic_block_bmap(mapping, block, ntfs_get_block_bmap); } static int ntfs_read_folio(struct file *file, struct folio *folio) { int err; struct address_space *mapping = folio->mapping; struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); if (is_resident(ni)) { ni_lock(ni); err = attr_data_read_resident(ni, folio); ni_unlock(ni); if (err != E_NTFS_NONRESIDENT) { folio_unlock(folio); return err; } } if (is_compressed(ni)) { ni_lock(ni); err = ni_readpage_cmpr(ni, folio); ni_unlock(ni); return err; } /* Normal + sparse files. */ return mpage_read_folio(folio, ntfs_get_block); } static void ntfs_readahead(struct readahead_control *rac) { struct address_space *mapping = rac->mapping; struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); u64 valid; loff_t pos; if (is_resident(ni)) { /* No readahead for resident. */ return; } if (is_compressed(ni)) { /* No readahead for compressed. */ return; } valid = ni->i_valid; pos = readahead_pos(rac); if (valid < i_size_read(inode) && pos <= valid && valid < pos + readahead_length(rac)) { /* Range cross 'valid'. Read it page by page. */ return; } mpage_readahead(rac, ntfs_get_block); } static int ntfs_get_block_direct_IO_R(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { return ntfs_get_block_vbo(inode, (u64)iblock << inode->i_blkbits, bh_result, create, GET_BLOCK_DIRECT_IO_R); } static int ntfs_get_block_direct_IO_W(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { return ntfs_get_block_vbo(inode, (u64)iblock << inode->i_blkbits, bh_result, create, GET_BLOCK_DIRECT_IO_W); } static ssize_t ntfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); loff_t vbo = iocb->ki_pos; loff_t end; int wr = iov_iter_rw(iter) & WRITE; size_t iter_count = iov_iter_count(iter); loff_t valid; ssize_t ret; if (is_resident(ni)) { /* Switch to buffered write. */ ret = 0; goto out; } if (is_compressed(ni)) { ret = 0; goto out; } ret = blockdev_direct_IO(iocb, inode, iter, wr ? ntfs_get_block_direct_IO_W : ntfs_get_block_direct_IO_R); if (ret > 0) end = vbo + ret; else if (wr && ret == -EIOCBQUEUED) end = vbo + iter_count; else goto out; valid = ni->i_valid; if (wr) { if (end > valid && !S_ISBLK(inode->i_mode)) { ni->i_valid = end; mark_inode_dirty(inode); } } else if (vbo < valid && valid < end) { /* Fix page. */ iov_iter_revert(iter, end - valid); iov_iter_zero(end - valid, iter); } out: return ret; } int ntfs_set_size(struct inode *inode, u64 new_size) { struct super_block *sb = inode->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; struct ntfs_inode *ni = ntfs_i(inode); int err; /* Check for maximum file size. */ if (is_sparsed(ni) || is_compressed(ni)) { if (new_size > sbi->maxbytes_sparse) { err = -EFBIG; goto out; } } else if (new_size > sbi->maxbytes) { err = -EFBIG; goto out; } ni_lock(ni); down_write(&ni->file.run_lock); err = attr_set_size(ni, ATTR_DATA, NULL, 0, &ni->file.run, new_size, &ni->i_valid, true, NULL); up_write(&ni->file.run_lock); ni_unlock(ni); mark_inode_dirty(inode); out: return err; } static int ntfs_resident_writepage(struct folio *folio, struct writeback_control *wbc, void *data) { struct address_space *mapping = data; struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); int ret; /* Avoid any operation if inode is bad. */ if (unlikely(is_bad_ni(ni))) return -EINVAL; if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) return -EIO; ni_lock(ni); ret = attr_data_write_resident(ni, folio); ni_unlock(ni); if (ret != E_NTFS_NONRESIDENT) folio_unlock(folio); mapping_set_error(mapping, ret); return ret; } static int ntfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; /* Avoid any operation if inode is bad. */ if (unlikely(is_bad_ni(ntfs_i(inode)))) return -EINVAL; if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) return -EIO; if (is_resident(ntfs_i(inode))) return write_cache_pages(mapping, wbc, ntfs_resident_writepage, mapping); return mpage_writepages(mapping, wbc, ntfs_get_block); } static int ntfs_get_block_write_begin(struct inode *inode, sector_t vbn, struct buffer_head *bh_result, int create) { return ntfs_get_block_vbo(inode, (u64)vbn << inode->i_blkbits, bh_result, create, GET_BLOCK_WRITE_BEGIN); } int ntfs_write_begin(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, u32 len, struct folio **foliop, void **fsdata) { int err; struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); /* Avoid any operation if inode is bad. */ if (unlikely(is_bad_ni(ni))) return -EINVAL; if (unlikely(ntfs3_forced_shutdown(inode->i_sb))) return -EIO; if (is_resident(ni)) { struct folio *folio = __filemap_get_folio( mapping, pos >> PAGE_SHIFT, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) { err = PTR_ERR(folio); goto out; } ni_lock(ni); err = attr_data_read_resident(ni, folio); ni_unlock(ni); if (!err) { *foliop = folio; goto out; } folio_unlock(folio); folio_put(folio); if (err != E_NTFS_NONRESIDENT) goto out; } err = block_write_begin(mapping, pos, len, foliop, ntfs_get_block_write_begin); out: return err; } /* * ntfs_write_end - Address_space_operations::write_end. */ int ntfs_write_end(const struct kiocb *iocb, struct address_space *mapping, loff_t pos, u32 len, u32 copied, struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; struct ntfs_inode *ni = ntfs_i(inode); u64 valid = ni->i_valid; bool dirty = false; int err; if (is_resident(ni)) { ni_lock(ni); err = attr_data_write_resident(ni, folio); ni_unlock(ni); if (!err) { struct buffer_head *head = folio_buffers(folio); dirty = true; /* Clear any buffers in folio. */ if (head) { struct buffer_head *bh = head; do { clear_buffer_dirty(bh); clear_buffer_mapped(bh); set_buffer_uptodate(bh); } while (head != (bh = bh->b_this_page)); } folio_mark_uptodate(folio); err = copied; } folio_unlock(folio); folio_put(folio); } else { err = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata); } if (err >= 0) { if (!(ni->std_fa & FILE_ATTRIBUTE_ARCHIVE)) { inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode)); ni->std_fa |= FILE_ATTRIBUTE_ARCHIVE; dirty = true; } if (valid != ni->i_valid) { /* ni->i_valid is changed in ntfs_get_block_vbo. */ dirty = true; } if (pos + err > inode->i_size) { i_size_write(inode, pos + err); dirty = true; } if (dirty) mark_inode_dirty(inode); } return err; } int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc) { return _ni_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); } int ntfs_sync_inode(struct inode *inode) { return _ni_write_inode(inode, 1); } /* * Helper function to read file. */ int inode_read_data(struct inode *inode, void *data, size_t bytes) { pgoff_t idx; struct address_space *mapping = inode->i_mapping; for (idx = 0; bytes; idx++) { size_t op = bytes > PAGE_SIZE ? PAGE_SIZE : bytes; struct page *page = read_mapping_page(mapping, idx, NULL); void *kaddr; if (IS_ERR(page)) return PTR_ERR(page); kaddr = kmap_atomic(page); memcpy(data, kaddr, op); kunmap_atomic(kaddr); put_page(page); bytes -= op; data = Add2Ptr(data, PAGE_SIZE); } return 0; } /* * ntfs_reparse_bytes * * Number of bytes for REPARSE_DATA_BUFFER(IO_REPARSE_TAG_SYMLINK) * for unicode string of @uni_len length. */ static inline u32 ntfs_reparse_bytes(u32 uni_len, bool is_absolute) { /* Header + unicode string + decorated unicode string. */ return sizeof(short) * (2 * uni_len + (is_absolute ? 4 : 0)) + offsetof(struct REPARSE_DATA_BUFFER, SymbolicLinkReparseBuffer.PathBuffer); } static struct REPARSE_DATA_BUFFER * ntfs_create_reparse_buffer(struct ntfs_sb_info *sbi, const char *symname, u32 size, u16 *nsize) { int i, err; struct REPARSE_DATA_BUFFER *rp; __le16 *rp_name; typeof(rp->SymbolicLinkReparseBuffer) *rs; bool is_absolute; is_absolute = (strlen(symname) > 1 && symname[1] == ':'); rp = kzalloc(ntfs_reparse_bytes(2 * size + 2, is_absolute), GFP_NOFS); if (!rp) return ERR_PTR(-ENOMEM); rs = &rp->SymbolicLinkReparseBuffer; rp_name = rs->PathBuffer; /* Convert link name to UTF-16. */ err = ntfs_nls_to_utf16(sbi, symname, size, (struct cpu_str *)(rp_name - 1), 2 * size, UTF16_LITTLE_ENDIAN); if (err < 0) goto out; /* err = the length of unicode name of symlink. */ *nsize = ntfs_reparse_bytes(err, is_absolute); if (*nsize > sbi->reparse.max_size) { err = -EFBIG; goto out; } /* Translate Linux '/' into Windows '\'. */ for (i = 0; i < err; i++) { if (rp_name[i] == cpu_to_le16('/')) rp_name[i] = cpu_to_le16('\\'); } rp->ReparseTag = IO_REPARSE_TAG_SYMLINK; rp->ReparseDataLength = cpu_to_le16(*nsize - offsetof(struct REPARSE_DATA_BUFFER, SymbolicLinkReparseBuffer)); /* PrintName + SubstituteName. */ rs->SubstituteNameOffset = cpu_to_le16(sizeof(short) * err); rs->SubstituteNameLength = cpu_to_le16(sizeof(short) * err + (is_absolute ? 8 : 0)); rs->PrintNameLength = rs->SubstituteNameOffset; /* * TODO: Use relative path if possible to allow Windows to * parse this path. * 0-absolute path 1- relative path (SYMLINK_FLAG_RELATIVE). */ rs->Flags = cpu_to_le32(is_absolute ? 0 : SYMLINK_FLAG_RELATIVE); memmove(rp_name + err + (is_absolute ? 4 : 0), rp_name, sizeof(short) * err); if (is_absolute) { /* Decorate SubstituteName. */ rp_name += err; rp_name[0] = cpu_to_le16('\\'); rp_name[1] = cpu_to_le16('?'); rp_name[2] = cpu_to_le16('?'); rp_name[3] = cpu_to_le16('\\'); } return rp; out: kfree(rp); return ERR_PTR(err); } /* * ntfs_create_inode * * Helper function for: * - ntfs_create * - ntfs_mknod * - ntfs_symlink * - ntfs_mkdir * - ntfs_atomic_open * * NOTE: if fnd != NULL (ntfs_atomic_open) then @dir is locked */ 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 err; struct super_block *sb = dir->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; const struct qstr *name = &dentry->d_name; CLST ino = 0; struct ntfs_inode *dir_ni = ntfs_i(dir); struct ntfs_inode *ni = NULL; struct inode *inode = NULL; struct ATTRIB *attr; struct ATTR_STD_INFO5 *std5; struct ATTR_FILE_NAME *fname; struct MFT_REC *rec; u32 asize, dsize, sd_size; enum FILE_ATTRIBUTE fa; __le32 security_id = SECURITY_ID_INVALID; CLST vcn; const void *sd; u16 t16, nsize = 0, aid = 0; struct INDEX_ROOT *root, *dir_root; struct NTFS_DE *e, *new_de = NULL; struct REPARSE_DATA_BUFFER *rp = NULL; bool rp_inserted = false; /* New file will be resident or non resident. */ const bool new_file_resident = 1; if (!fnd) ni_lock_dir(dir_ni); dir_root = indx_get_root(&dir_ni->dir, dir_ni, NULL, NULL); if (!dir_root) { err = -EINVAL; goto out1; } if (S_ISDIR(mode)) { /* Use parent's directory attributes. */ fa = dir_ni->std_fa | FILE_ATTRIBUTE_DIRECTORY | FILE_ATTRIBUTE_ARCHIVE; /* * By default child directory inherits parent attributes. * Root directory is hidden + system. * Make an exception for children in root. */ if (dir->i_ino == MFT_REC_ROOT) fa &= ~(FILE_ATTRIBUTE_HIDDEN | FILE_ATTRIBUTE_SYSTEM); } else if (S_ISLNK(mode)) { /* It is good idea that link should be the same type (file/dir) as target */ fa = FILE_ATTRIBUTE_REPARSE_POINT; /* * Linux: there are dir/file/symlink and so on. * NTFS: symlinks are "dir + reparse" or "file + reparse" * It is good idea to create: * dir + reparse if 'symname' points to directory * or * file + reparse if 'symname' points to file * Unfortunately kern_path hangs if symname contains 'dir'. */ /* * struct path path; * * if (!kern_path(symname, LOOKUP_FOLLOW, &path)){ * struct inode *target = d_inode(path.dentry); * * if (S_ISDIR(target->i_mode)) * fa |= FILE_ATTRIBUTE_DIRECTORY; * // if ( target->i_sb == sb ){ * // use relative path? * // } * path_put(&path); * } */ } else if (S_ISREG(mode)) { if (sbi->options->sparse) { /* Sparsed regular file, cause option 'sparse'. */ fa = FILE_ATTRIBUTE_SPARSE_FILE | FILE_ATTRIBUTE_ARCHIVE; } else if (dir_ni->std_fa & FILE_ATTRIBUTE_COMPRESSED) { /* Compressed regular file, if parent is compressed. */ fa = FILE_ATTRIBUTE_COMPRESSED | FILE_ATTRIBUTE_ARCHIVE; } else { /* Regular file, default attributes. */ fa = FILE_ATTRIBUTE_ARCHIVE; } } else { fa = FILE_ATTRIBUTE_ARCHIVE; } /* If option "hide_dot_files" then set hidden attribute for dot files. */ if (sbi->options->hide_dot_files && name->name[0] == '.') fa |= FILE_ATTRIBUTE_HIDDEN; if (!(mode & 0222)) fa |= FILE_ATTRIBUTE_READONLY; /* Allocate PATH_MAX bytes. */ new_de = __getname(); if (!new_de) { err = -ENOMEM; goto out1; } /* Avoid any operation if inode is bad. */ if (unlikely(is_bad_ni(dir_ni))) { err = -EINVAL; goto out2; } if (unlikely(ntfs3_forced_shutdown(sb))) { err = -EIO; goto out2; } /* Mark rw ntfs as dirty. it will be cleared at umount. */ ntfs_set_state(sbi, NTFS_DIRTY_DIRTY); /* Step 1: allocate and fill new mft record. */ err = ntfs_look_free_mft(sbi, &ino, false, NULL, NULL); if (err) goto out2; ni = ntfs_new_inode(sbi, ino, S_ISDIR(mode) ? RECORD_FLAG_DIR : 0); if (IS_ERR(ni)) { err = PTR_ERR(ni); ni = NULL; goto out3; } inode = &ni->vfs_inode; inode_init_owner(idmap, inode, dir, mode); mode = inode->i_mode; ni->i_crtime = current_time(inode); rec = ni->mi.mrec; rec->hard_links = cpu_to_le16(1); attr = Add2Ptr(rec, le16_to_cpu(rec->attr_off)); /* Get default security id. */ sd = s_default_security; sd_size = sizeof(s_default_security); if (is_ntfs3(sbi)) { security_id = dir_ni->std_security_id; if (le32_to_cpu(security_id) < SECURITY_ID_FIRST) { security_id = sbi->security.def_security_id; if (security_id == SECURITY_ID_INVALID && !ntfs_insert_security(sbi, sd, sd_size, &security_id, NULL)) sbi->security.def_security_id = security_id; } } /* Insert standard info. */ std5 = Add2Ptr(attr, SIZEOF_RESIDENT); if (security_id == SECURITY_ID_INVALID) { dsize = sizeof(struct ATTR_STD_INFO); } else { dsize = sizeof(struct ATTR_STD_INFO5); std5->security_id = security_id; ni->std_security_id = security_id; } asize = SIZEOF_RESIDENT + dsize; attr->type = ATTR_STD; attr->size = cpu_to_le32(asize); attr->id = cpu_to_le16(aid++); attr->res.data_off = SIZEOF_RESIDENT_LE; attr->res.data_size = cpu_to_le32(dsize); std5->cr_time = std5->m_time = std5->c_time = std5->a_time = kernel2nt(&ni->i_crtime); std5->fa = ni->std_fa = fa; attr = Add2Ptr(attr, asize); /* Insert file name. */ err = fill_name_de(sbi, new_de, name, uni); if (err) goto out4; mi_get_ref(&ni->mi, &new_de->ref); fname = (struct ATTR_FILE_NAME *)(new_de + 1); if (sbi->options->windows_names && !valid_windows_name(sbi, (struct le_str *)&fname->name_len)) { err = -EINVAL; goto out4; } mi_get_ref(&dir_ni->mi, &fname->home); fname->dup.cr_time = fname->dup.m_time = fname->dup.c_time = fname->dup.a_time = std5->cr_time; fname->dup.alloc_size = fname->dup.data_size = 0; fname->dup.fa = std5->fa; fname->dup.extend_data = S_ISLNK(mode) ? IO_REPARSE_TAG_SYMLINK : 0; dsize = le16_to_cpu(new_de->key_size); asize = ALIGN(SIZEOF_RESIDENT + dsize, 8); attr->type = ATTR_NAME; attr->size = cpu_to_le32(asize); attr->res.data_off = SIZEOF_RESIDENT_LE; attr->res.flags = RESIDENT_FLAG_INDEXED; attr->id = cpu_to_le16(aid++); attr->res.data_size = cpu_to_le32(dsize); memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), fname, dsize); attr = Add2Ptr(attr, asize); if (security_id == SECURITY_ID_INVALID) { /* Insert security attribute. */ asize = SIZEOF_RESIDENT + ALIGN(sd_size, 8); attr->type = ATTR_SECURE; attr->size = cpu_to_le32(asize); attr->id = cpu_to_le16(aid++); attr->res.data_off = SIZEOF_RESIDENT_LE; attr->res.data_size = cpu_to_le32(sd_size); memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), sd, sd_size); attr = Add2Ptr(attr, asize); } attr->id = cpu_to_le16(aid++); if (fa & FILE_ATTRIBUTE_DIRECTORY) { /* * Regular directory or symlink to directory. * Create root attribute. */ dsize = sizeof(struct INDEX_ROOT) + sizeof(struct NTFS_DE); asize = sizeof(I30_NAME) + SIZEOF_RESIDENT + dsize; attr->type = ATTR_ROOT; attr->size = cpu_to_le32(asize); attr->name_len = ARRAY_SIZE(I30_NAME); attr->name_off = SIZEOF_RESIDENT_LE; attr->res.data_off = cpu_to_le16(sizeof(I30_NAME) + SIZEOF_RESIDENT); attr->res.data_size = cpu_to_le32(dsize); memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), I30_NAME, sizeof(I30_NAME)); root = Add2Ptr(attr, sizeof(I30_NAME) + SIZEOF_RESIDENT); memcpy(root, dir_root, offsetof(struct INDEX_ROOT, ihdr)); root->ihdr.de_off = cpu_to_le32(sizeof(struct INDEX_HDR)); root->ihdr.used = cpu_to_le32(sizeof(struct INDEX_HDR) + sizeof(struct NTFS_DE)); root->ihdr.total = root->ihdr.used; e = Add2Ptr(root, sizeof(struct INDEX_ROOT)); e->size = cpu_to_le16(sizeof(struct NTFS_DE)); e->flags = NTFS_IE_LAST; } else if (S_ISLNK(mode)) { /* * Symlink to file. * Create empty resident data attribute. */ asize = SIZEOF_RESIDENT; /* Insert empty ATTR_DATA */ attr->type = ATTR_DATA; attr->size = cpu_to_le32(SIZEOF_RESIDENT); attr->name_off = SIZEOF_RESIDENT_LE; attr->res.data_off = SIZEOF_RESIDENT_LE; } else if (!new_file_resident && S_ISREG(mode)) { /* * Regular file. Create empty non resident data attribute. */ attr->type = ATTR_DATA; attr->non_res = 1; attr->nres.evcn = cpu_to_le64(-1ll); if (fa & FILE_ATTRIBUTE_SPARSE_FILE) { attr->size = cpu_to_le32(SIZEOF_NONRESIDENT_EX + 8); attr->name_off = SIZEOF_NONRESIDENT_EX_LE; attr->flags = ATTR_FLAG_SPARSED; asize = SIZEOF_NONRESIDENT_EX + 8; } else if (fa & FILE_ATTRIBUTE_COMPRESSED) { attr->size = cpu_to_le32(SIZEOF_NONRESIDENT_EX + 8); attr->name_off = SIZEOF_NONRESIDENT_EX_LE; attr->flags = ATTR_FLAG_COMPRESSED; attr->nres.c_unit = NTFS_LZNT_CUNIT; asize = SIZEOF_NONRESIDENT_EX + 8; } else { attr->size = cpu_to_le32(SIZEOF_NONRESIDENT + 8); attr->name_off = SIZEOF_NONRESIDENT_LE; asize = SIZEOF_NONRESIDENT + 8; } attr->nres.run_off = attr->name_off; } else { /* * Node. Create empty resident data attribute. */ attr->type = ATTR_DATA; attr->size = cpu_to_le32(SIZEOF_RESIDENT); attr->name_off = SIZEOF_RESIDENT_LE; if (fa & FILE_ATTRIBUTE_SPARSE_FILE) attr->flags = ATTR_FLAG_SPARSED; else if (fa & FILE_ATTRIBUTE_COMPRESSED) attr->flags = ATTR_FLAG_COMPRESSED; attr->res.data_off = SIZEOF_RESIDENT_LE; asize = SIZEOF_RESIDENT; ni->ni_flags |= NI_FLAG_RESIDENT; } if (S_ISDIR(mode)) { ni->ni_flags |= NI_FLAG_DIR; err = indx_init(&ni->dir, sbi, attr, INDEX_MUTEX_I30); if (err) goto out4; } else if (S_ISLNK(mode)) { rp = ntfs_create_reparse_buffer(sbi, symname, size, &nsize); if (IS_ERR(rp)) { err = PTR_ERR(rp); rp = NULL; goto out4; } /* * Insert ATTR_REPARSE. */ attr = Add2Ptr(attr, asize); attr->type = ATTR_REPARSE; attr->id = cpu_to_le16(aid++); /* Resident or non resident? */ asize = ALIGN(SIZEOF_RESIDENT + nsize, 8); t16 = PtrOffset(rec, attr); /* * Below function 'ntfs_save_wsl_perm' requires 0x78 bytes. * It is good idea to keep extended attributes resident. */ if (asize + t16 + 0x78 + 8 > sbi->record_size) { CLST alen; CLST clst = bytes_to_cluster(sbi, nsize); /* Bytes per runs. */ t16 = sbi->record_size - t16 - SIZEOF_NONRESIDENT; attr->non_res = 1; attr->nres.evcn = cpu_to_le64(clst - 1); attr->name_off = SIZEOF_NONRESIDENT_LE; attr->nres.run_off = attr->name_off; attr->nres.data_size = cpu_to_le64(nsize); attr->nres.valid_size = attr->nres.data_size; attr->nres.alloc_size = cpu_to_le64(ntfs_up_cluster(sbi, nsize)); err = attr_allocate_clusters(sbi, &ni->file.run, 0, 0, clst, NULL, ALLOCATE_DEF, &alen, 0, NULL, NULL); if (err) goto out5; err = run_pack(&ni->file.run, 0, clst, Add2Ptr(attr, SIZEOF_NONRESIDENT), t16, &vcn); if (err < 0) goto out5; if (vcn != clst) { err = -EINVAL; goto out5; } asize = SIZEOF_NONRESIDENT + ALIGN(err, 8); /* Write non resident data. */ err = ntfs_sb_write_run(sbi, &ni->file.run, 0, rp, nsize, 0); if (err) goto out5; } else { attr->res.data_off = SIZEOF_RESIDENT_LE; attr->res.data_size = cpu_to_le32(nsize); memcpy(Add2Ptr(attr, SIZEOF_RESIDENT), rp, nsize); } /* Size of symlink equals the length of input string. */ inode->i_size = size; attr->size = cpu_to_le32(asize); err = ntfs_insert_reparse(sbi, IO_REPARSE_TAG_SYMLINK, &new_de->ref); if (err) goto out5; rp_inserted = true; } attr = Add2Ptr(attr, asize); attr->type = ATTR_END; rec->used = cpu_to_le32(PtrOffset(rec, attr) + 8); rec->next_attr_id = cpu_to_le16(aid); inode->i_generation = le16_to_cpu(rec->seq); if (S_ISDIR(mode)) { inode->i_op = &ntfs_dir_inode_operations; inode->i_fop = unlikely(is_legacy_ntfs(sb)) ? &ntfs_legacy_dir_operations : &ntfs_dir_operations; } else if (S_ISLNK(mode)) { inode->i_op = &ntfs_link_inode_operations; inode->i_fop = NULL; inode->i_mapping->a_ops = &ntfs_aops; inode->i_size = size; inode_nohighmem(inode); } else if (S_ISREG(mode)) { inode->i_op = &ntfs_file_inode_operations; inode->i_fop = unlikely(is_legacy_ntfs(sb)) ? &ntfs_legacy_file_operations : &ntfs_file_operations; inode->i_mapping->a_ops = is_compressed(ni) ? &ntfs_aops_cmpr : &ntfs_aops; init_rwsem(&ni->file.run_lock); } else { inode->i_op = &ntfs_special_inode_operations; init_special_inode(inode, mode, dev); } #ifdef CONFIG_NTFS3_FS_POSIX_ACL if (!S_ISLNK(mode) && (sb->s_flags & SB_POSIXACL)) { err = ntfs_init_acl(idmap, inode, dir); if (err) goto out5; } else #endif { inode->i_flags |= S_NOSEC; } if (!S_ISLNK(mode)) { /* * ntfs_init_acl and ntfs_save_wsl_perm update extended attribute. * The packed size of extended attribute is stored in direntry too. * 'fname' here points to inside new_de. */ err = ntfs_save_wsl_perm(inode, &fname->dup.extend_data); if (err) goto out6; /* * update ea_size in file_name attribute too. * Use ni_find_attr cause layout of MFT record may be changed * in ntfs_init_acl and ntfs_save_wsl_perm. */ attr = ni_find_attr(ni, NULL, NULL, ATTR_NAME, NULL, 0, NULL, NULL); if (attr) { struct ATTR_FILE_NAME *fn; fn = resident_data_ex(attr, SIZEOF_ATTRIBUTE_FILENAME); if (fn) fn->dup.extend_data = fname->dup.extend_data; } } /* We do not need to update parent directory later */ ni->ni_flags &= ~NI_FLAG_UPDATE_PARENT; /* Step 2: Add new name in index. */ err = indx_insert_entry(&dir_ni->dir, dir_ni, new_de, sbi, fnd, 0); if (err) goto out6; /* * Call 'd_instantiate' after inode->i_op is set * but before finish_open. */ d_instantiate(dentry, inode); /* Set original time. inode times (i_ctime) may be changed in ntfs_init_acl. */ inode_set_atime_to_ts(inode, ni->i_crtime); inode_set_ctime_to_ts(inode, ni->i_crtime); inode_set_mtime_to_ts(inode, ni->i_crtime); inode_set_mtime_to_ts(dir, ni->i_crtime); inode_set_ctime_to_ts(dir, ni->i_crtime); mark_inode_dirty(dir); mark_inode_dirty(inode); /* Normal exit. */ goto out2; out6: attr = ni_find_attr(ni, NULL, NULL, ATTR_EA, NULL, 0, NULL, NULL); if (attr && attr->non_res) { /* Delete ATTR_EA, if non-resident. */ struct runs_tree run; run_init(&run); attr_set_size(ni, ATTR_EA, NULL, 0, &run, 0, NULL, false, NULL); run_close(&run); } if (rp_inserted) ntfs_remove_reparse(sbi, IO_REPARSE_TAG_SYMLINK, &new_de->ref); out5: if (!S_ISDIR(mode)) run_deallocate(sbi, &ni->file.run, false); out4: clear_rec_inuse(rec); clear_nlink(inode); ni->mi.dirty = false; discard_new_inode(inode); out3: ntfs_mark_rec_free(sbi, ino, false); out2: __putname(new_de); kfree(rp); out1: if (!fnd) ni_unlock(dir_ni); if (!err) unlock_new_inode(inode); return err; } int ntfs_link_inode(struct inode *inode, struct dentry *dentry) { int err; struct ntfs_inode *ni = ntfs_i(inode); struct ntfs_sb_info *sbi = inode->i_sb->s_fs_info; struct NTFS_DE *de; /* Allocate PATH_MAX bytes. */ de = __getname(); if (!de) return -ENOMEM; /* Mark rw ntfs as dirty. It will be cleared at umount. */ ntfs_set_state(sbi, NTFS_DIRTY_DIRTY); /* Construct 'de'. */ err = fill_name_de(sbi, de, &dentry->d_name, NULL); if (err) goto out; err = ni_add_name(ntfs_i(d_inode(dentry->d_parent)), ni, de); out: __putname(de); return err; } /* * ntfs_unlink_inode * * inode_operations::unlink * inode_operations::rmdir */ int ntfs_unlink_inode(struct inode *dir, const struct dentry *dentry) { int err; struct ntfs_sb_info *sbi = dir->i_sb->s_fs_info; struct inode *inode = d_inode(dentry); struct ntfs_inode *ni = ntfs_i(inode); struct ntfs_inode *dir_ni = ntfs_i(dir); struct NTFS_DE *de, *de2 = NULL; int undo_remove; if (ntfs_is_meta_file(sbi, ni->mi.rno)) return -EINVAL; /* Allocate PATH_MAX bytes. */ de = __getname(); if (!de) return -ENOMEM; ni_lock(ni); if (S_ISDIR(inode->i_mode) && !dir_is_empty(inode)) { err = -ENOTEMPTY; goto out; } err = fill_name_de(sbi, de, &dentry->d_name, NULL); if (err < 0) goto out; undo_remove = 0; err = ni_remove_name(dir_ni, ni, de, &de2, &undo_remove); if (!err) { drop_nlink(inode); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); inode_set_ctime_to_ts(inode, inode_get_ctime(dir)); if (inode->i_nlink) mark_inode_dirty(inode); } else if (!ni_remove_name_undo(dir_ni, ni, de, de2, undo_remove)) { _ntfs_bad_inode(inode); } else { if (ni_is_dirty(dir)) mark_inode_dirty(dir); if (ni_is_dirty(inode)) mark_inode_dirty(inode); } out: ni_unlock(ni); __putname(de); return err; } void ntfs_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); clear_inode(inode); ni_clear(ntfs_i(inode)); } /* * ntfs_translate_junction * * Translate a Windows junction target to the Linux equivalent. * On junctions, targets are always absolute (they include the drive * letter). We have no way of knowing if the target is for the current * mounted device or not so we just assume it is. */ static int ntfs_translate_junction(const struct super_block *sb, const struct dentry *link_de, char *target, int target_len, int target_max) { int tl_len, err = target_len; char *link_path_buffer = NULL, *link_path; char *translated = NULL; char *target_start; int copy_len; link_path_buffer = kmalloc(PATH_MAX, GFP_NOFS); if (!link_path_buffer) { err = -ENOMEM; goto out; } /* Get link path, relative to mount point */ link_path = dentry_path_raw(link_de, link_path_buffer, PATH_MAX); if (IS_ERR(link_path)) { ntfs_err(sb, "Error getting link path"); err = -EINVAL; goto out; } translated = kmalloc(PATH_MAX, GFP_NOFS); if (!translated) { err = -ENOMEM; goto out; } /* Make translated path a relative path to mount point */ strcpy(translated, "./"); ++link_path; /* Skip leading / */ for (tl_len = sizeof("./") - 1; *link_path; ++link_path) { if (*link_path == '/') { if (PATH_MAX - tl_len < sizeof("../")) { ntfs_err(sb, "Link path %s has too many components", link_path); err = -EINVAL; goto out; } strcpy(translated + tl_len, "../"); tl_len += sizeof("../") - 1; } } /* Skip drive letter */ target_start = target; while (*target_start && *target_start != ':') ++target_start; if (!*target_start) { ntfs_err(sb, "Link target (%s) missing drive separator", target); err = -EINVAL; goto out; } /* Skip drive separator and leading /, if exists */ target_start += 1 + (target_start[1] == '/'); copy_len = target_len - (target_start - target); if (PATH_MAX - tl_len <= copy_len) { ntfs_err(sb, "Link target %s too large for buffer (%d <= %d)", target_start, PATH_MAX - tl_len, copy_len); err = -EINVAL; goto out; } /* translated path has a trailing / and target_start does not */ strcpy(translated + tl_len, target_start); tl_len += copy_len; if (target_max <= tl_len) { ntfs_err(sb, "Target path %s too large for buffer (%d <= %d)", translated, target_max, tl_len); err = -EINVAL; goto out; } strcpy(target, translated); err = tl_len; out: kfree(link_path_buffer); kfree(translated); return err; } static noinline int ntfs_readlink_hlp(const struct dentry *link_de, struct inode *inode, char *buffer, int buflen) { int i, err = -EINVAL; struct ntfs_inode *ni = ntfs_i(inode); struct super_block *sb = inode->i_sb; struct ntfs_sb_info *sbi = sb->s_fs_info; u64 size; u16 ulen = 0; void *to_free = NULL; struct REPARSE_DATA_BUFFER *rp; const __le16 *uname; struct ATTRIB *attr; /* Reparse data present. Try to parse it. */ static_assert(!offsetof(struct REPARSE_DATA_BUFFER, ReparseTag)); static_assert(sizeof(u32) == sizeof(rp->ReparseTag)); *buffer = 0; attr = ni_find_attr(ni, NULL, NULL, ATTR_REPARSE, NULL, 0, NULL, NULL); if (!attr) goto out; if (!attr->non_res) { rp = resident_data_ex(attr, sizeof(struct REPARSE_DATA_BUFFER)); if (!rp) goto out; size = le32_to_cpu(attr->res.data_size); } else { size = le64_to_cpu(attr->nres.data_size); rp = NULL; } if (size > sbi->reparse.max_size || size <= sizeof(u32)) goto out; if (!rp) { rp = kmalloc(size, GFP_NOFS); if (!rp) { err = -ENOMEM; goto out; } to_free = rp; /* Read into temporal buffer. */ err = ntfs_read_run_nb(sbi, &ni->file.run, 0, rp, size, NULL); if (err) goto out; } /* Microsoft Tag. */ switch (rp->ReparseTag) { case IO_REPARSE_TAG_MOUNT_POINT: /* Mount points and junctions. */ /* Can we use 'Rp->MountPointReparseBuffer.PrintNameLength'? */ if (size <= offsetof(struct REPARSE_DATA_BUFFER, MountPointReparseBuffer.PathBuffer)) goto out; uname = Add2Ptr(rp, offsetof(struct REPARSE_DATA_BUFFER, MountPointReparseBuffer.PathBuffer) + le16_to_cpu(rp->MountPointReparseBuffer .PrintNameOffset)); ulen = le16_to_cpu(rp->MountPointReparseBuffer.PrintNameLength); break; case IO_REPARSE_TAG_SYMLINK: /* FolderSymbolicLink */ /* Can we use 'Rp->SymbolicLinkReparseBuffer.PrintNameLength'? */ if (size <= offsetof(struct REPARSE_DATA_BUFFER, SymbolicLinkReparseBuffer.PathBuffer)) goto out; uname = Add2Ptr( rp, offsetof(struct REPARSE_DATA_BUFFER, SymbolicLinkReparseBuffer.PathBuffer) + le16_to_cpu(rp->SymbolicLinkReparseBuffer .PrintNameOffset)); ulen = le16_to_cpu( rp->SymbolicLinkReparseBuffer.PrintNameLength); break; case IO_REPARSE_TAG_CLOUD: case IO_REPARSE_TAG_CLOUD_1: case IO_REPARSE_TAG_CLOUD_2: case IO_REPARSE_TAG_CLOUD_3: case IO_REPARSE_TAG_CLOUD_4: case IO_REPARSE_TAG_CLOUD_5: case IO_REPARSE_TAG_CLOUD_6: case IO_REPARSE_TAG_CLOUD_7: case IO_REPARSE_TAG_CLOUD_8: case IO_REPARSE_TAG_CLOUD_9: case IO_REPARSE_TAG_CLOUD_A: case IO_REPARSE_TAG_CLOUD_B: case IO_REPARSE_TAG_CLOUD_C: case IO_REPARSE_TAG_CLOUD_D: case IO_REPARSE_TAG_CLOUD_E: case IO_REPARSE_TAG_CLOUD_F: err = sizeof("OneDrive") - 1; if (err > buflen) err = buflen; memcpy(buffer, "OneDrive", err); goto out; default: if (IsReparseTagMicrosoft(rp->ReparseTag)) { /* Unknown Microsoft Tag. */ goto out; } if (!IsReparseTagNameSurrogate(rp->ReparseTag) || size <= sizeof(struct REPARSE_POINT)) { goto out; } /* Users tag. */ uname = Add2Ptr(rp, sizeof(struct REPARSE_POINT)); ulen = le16_to_cpu(rp->ReparseDataLength) - sizeof(struct REPARSE_POINT); } /* Convert nlen from bytes to UNICODE chars. */ ulen >>= 1; /* Check that name is available. */ if (!ulen || uname + ulen > (__le16 *)Add2Ptr(rp, size)) goto out; /* If name is already zero terminated then truncate it now. */ if (!uname[ulen - 1]) ulen -= 1; err = ntfs_utf16_to_nls(sbi, uname, ulen, buffer, buflen); if (err < 0) goto out; /* Translate Windows '\' into Linux '/'. */ for (i = 0; i < err; i++) { if (buffer[i] == '\\') buffer[i] = '/'; } /* Always set last zero. */ buffer[err] = 0; /* If this is a junction, translate the link target. */ if (rp->ReparseTag == IO_REPARSE_TAG_MOUNT_POINT) err = ntfs_translate_junction(sb, link_de, buffer, err, buflen); out: kfree(to_free); return err; } static const char *ntfs_get_link(struct dentry *de, struct inode *inode, struct delayed_call *done) { int err; char *ret; if (!de) return ERR_PTR(-ECHILD); ret = kmalloc(PAGE_SIZE, GFP_NOFS); if (!ret) return ERR_PTR(-ENOMEM); err = ntfs_readlink_hlp(de, inode, ret, PAGE_SIZE); if (err < 0) { kfree(ret); return ERR_PTR(err); } set_delayed_call(done, kfree_link, ret); return ret; } // clang-format off const struct inode_operations ntfs_link_inode_operations = { .get_link = ntfs_get_link, .setattr = ntfs_setattr, .listxattr = ntfs_listxattr, }; const struct address_space_operations ntfs_aops = { .read_folio = ntfs_read_folio, .readahead = ntfs_readahead, .writepages = ntfs_writepages, .write_begin = ntfs_write_begin, .write_end = ntfs_write_end, .direct_IO = ntfs_direct_IO, .bmap = ntfs_bmap, .dirty_folio = block_dirty_folio, .migrate_folio = buffer_migrate_folio, .invalidate_folio = block_invalidate_folio, }; const struct address_space_operations ntfs_aops_cmpr = { .read_folio = ntfs_read_folio, .readahead = ntfs_readahead, .dirty_folio = block_dirty_folio, .direct_IO = ntfs_direct_IO, }; // clang-format on |
| 7 7 1 1 2 1 1 6 1 2 2 1 6 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 | // SPDX-License-Identifier: GPL-2.0-only /* * Optimized MPEG FS - inode and super operations. * Copyright (C) 2006 Bob Copeland <me@bobcopeland.com> */ #include <linux/module.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/vfs.h> #include <linux/cred.h> #include <linux/buffer_head.h> #include <linux/vmalloc.h> #include <linux/writeback.h> #include <linux/seq_file.h> #include <linux/crc-itu-t.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include "omfs.h" MODULE_AUTHOR("Bob Copeland <me@bobcopeland.com>"); MODULE_DESCRIPTION("OMFS (ReplayTV/Karma) Filesystem for Linux"); MODULE_LICENSE("GPL"); struct buffer_head *omfs_bread(struct super_block *sb, sector_t block) { struct omfs_sb_info *sbi = OMFS_SB(sb); if (block >= sbi->s_num_blocks) return NULL; return sb_bread(sb, clus_to_blk(sbi, block)); } struct inode *omfs_new_inode(struct inode *dir, umode_t mode) { struct inode *inode; u64 new_block; int err; int len; struct omfs_sb_info *sbi = OMFS_SB(dir->i_sb); inode = new_inode(dir->i_sb); if (!inode) return ERR_PTR(-ENOMEM); err = omfs_allocate_range(dir->i_sb, sbi->s_mirrors, sbi->s_mirrors, &new_block, &len); if (err) goto fail; inode->i_ino = new_block; inode_init_owner(&nop_mnt_idmap, inode, NULL, mode); inode->i_mapping->a_ops = &omfs_aops; simple_inode_init_ts(inode); switch (mode & S_IFMT) { case S_IFDIR: inode->i_op = &omfs_dir_inops; inode->i_fop = &omfs_dir_operations; inode->i_size = sbi->s_sys_blocksize; inc_nlink(inode); break; case S_IFREG: inode->i_op = &omfs_file_inops; inode->i_fop = &omfs_file_operations; inode->i_size = 0; break; } insert_inode_hash(inode); mark_inode_dirty(inode); return inode; fail: make_bad_inode(inode); iput(inode); return ERR_PTR(err); } /* * Update the header checksums for a dirty inode based on its contents. * Caller is expected to hold the buffer head underlying oi and mark it * dirty. */ static void omfs_update_checksums(struct omfs_inode *oi) { int xor, i, ofs = 0, count; u16 crc = 0; unsigned char *ptr = (unsigned char *) oi; count = be32_to_cpu(oi->i_head.h_body_size); ofs = sizeof(struct omfs_header); crc = crc_itu_t(crc, ptr + ofs, count); oi->i_head.h_crc = cpu_to_be16(crc); xor = ptr[0]; for (i = 1; i < OMFS_XOR_COUNT; i++) xor ^= ptr[i]; oi->i_head.h_check_xor = xor; } static int __omfs_write_inode(struct inode *inode, int wait) { struct omfs_inode *oi; struct omfs_sb_info *sbi = OMFS_SB(inode->i_sb); struct buffer_head *bh, *bh2; u64 ctime; int i; int ret = -EIO; int sync_failed = 0; /* get current inode since we may have written sibling ptrs etc. */ bh = omfs_bread(inode->i_sb, inode->i_ino); if (!bh) goto out; oi = (struct omfs_inode *) bh->b_data; oi->i_head.h_self = cpu_to_be64(inode->i_ino); if (S_ISDIR(inode->i_mode)) oi->i_type = OMFS_DIR; else if (S_ISREG(inode->i_mode)) oi->i_type = OMFS_FILE; else { printk(KERN_WARNING "omfs: unknown file type: %d\n", inode->i_mode); goto out_brelse; } oi->i_head.h_body_size = cpu_to_be32(sbi->s_sys_blocksize - sizeof(struct omfs_header)); oi->i_head.h_version = 1; oi->i_head.h_type = OMFS_INODE_NORMAL; oi->i_head.h_magic = OMFS_IMAGIC; oi->i_size = cpu_to_be64(inode->i_size); ctime = inode_get_ctime_sec(inode) * 1000LL + ((inode_get_ctime_nsec(inode) + 999)/1000); oi->i_ctime = cpu_to_be64(ctime); omfs_update_checksums(oi); mark_buffer_dirty(bh); if (wait) { sync_dirty_buffer(bh); if (buffer_req(bh) && !buffer_uptodate(bh)) sync_failed = 1; } /* if mirroring writes, copy to next fsblock */ for (i = 1; i < sbi->s_mirrors; i++) { bh2 = omfs_bread(inode->i_sb, inode->i_ino + i); if (!bh2) goto out_brelse; memcpy(bh2->b_data, bh->b_data, bh->b_size); mark_buffer_dirty(bh2); if (wait) { sync_dirty_buffer(bh2); if (buffer_req(bh2) && !buffer_uptodate(bh2)) sync_failed = 1; } brelse(bh2); } ret = (sync_failed) ? -EIO : 0; out_brelse: brelse(bh); out: return ret; } static int omfs_write_inode(struct inode *inode, struct writeback_control *wbc) { return __omfs_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); } int omfs_sync_inode(struct inode *inode) { return __omfs_write_inode(inode, 1); } /* * called when an entry is deleted, need to clear the bits in the * bitmaps. */ static void omfs_evict_inode(struct inode *inode) { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); if (inode->i_nlink) return; if (S_ISREG(inode->i_mode)) { inode->i_size = 0; omfs_shrink_inode(inode); } omfs_clear_range(inode->i_sb, inode->i_ino, 2); } struct inode *omfs_iget(struct super_block *sb, ino_t ino) { struct omfs_sb_info *sbi = OMFS_SB(sb); struct omfs_inode *oi; struct buffer_head *bh; u64 ctime; unsigned long nsecs; struct inode *inode; inode = iget_locked(sb, ino); if (!inode) return ERR_PTR(-ENOMEM); if (!(inode->i_state & I_NEW)) return inode; bh = omfs_bread(inode->i_sb, ino); if (!bh) goto iget_failed; oi = (struct omfs_inode *)bh->b_data; /* check self */ if (ino != be64_to_cpu(oi->i_head.h_self)) goto fail_bh; inode->i_uid = sbi->s_uid; inode->i_gid = sbi->s_gid; ctime = be64_to_cpu(oi->i_ctime); nsecs = do_div(ctime, 1000) * 1000L; inode_set_atime(inode, ctime, nsecs); inode_set_mtime(inode, ctime, nsecs); inode_set_ctime(inode, ctime, nsecs); inode->i_mapping->a_ops = &omfs_aops; switch (oi->i_type) { case OMFS_DIR: inode->i_mode = S_IFDIR | (S_IRWXUGO & ~sbi->s_dmask); inode->i_op = &omfs_dir_inops; inode->i_fop = &omfs_dir_operations; inode->i_size = sbi->s_sys_blocksize; inc_nlink(inode); break; case OMFS_FILE: inode->i_mode = S_IFREG | (S_IRWXUGO & ~sbi->s_fmask); inode->i_fop = &omfs_file_operations; inode->i_size = be64_to_cpu(oi->i_size); break; } brelse(bh); unlock_new_inode(inode); return inode; fail_bh: brelse(bh); iget_failed: iget_failed(inode); return ERR_PTR(-EIO); } static void omfs_put_super(struct super_block *sb) { struct omfs_sb_info *sbi = OMFS_SB(sb); kfree(sbi->s_imap); kfree(sbi); sb->s_fs_info = NULL; } static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *s = dentry->d_sb; struct omfs_sb_info *sbi = OMFS_SB(s); u64 id = huge_encode_dev(s->s_bdev->bd_dev); buf->f_type = OMFS_MAGIC; buf->f_bsize = sbi->s_blocksize; buf->f_blocks = sbi->s_num_blocks; buf->f_files = sbi->s_num_blocks; buf->f_namelen = OMFS_NAMELEN; buf->f_fsid = u64_to_fsid(id); buf->f_bfree = buf->f_bavail = buf->f_ffree = omfs_count_free(s); return 0; } /* * Display the mount options in /proc/mounts. */ static int omfs_show_options(struct seq_file *m, struct dentry *root) { struct omfs_sb_info *sbi = OMFS_SB(root->d_sb); umode_t cur_umask = current_umask(); if (!uid_eq(sbi->s_uid, current_uid())) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, sbi->s_uid)); if (!gid_eq(sbi->s_gid, current_gid())) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, sbi->s_gid)); if (sbi->s_dmask == sbi->s_fmask) { if (sbi->s_fmask != cur_umask) seq_printf(m, ",umask=%o", sbi->s_fmask); } else { if (sbi->s_dmask != cur_umask) seq_printf(m, ",dmask=%o", sbi->s_dmask); if (sbi->s_fmask != cur_umask) seq_printf(m, ",fmask=%o", sbi->s_fmask); } return 0; } static const struct super_operations omfs_sops = { .write_inode = omfs_write_inode, .evict_inode = omfs_evict_inode, .put_super = omfs_put_super, .statfs = omfs_statfs, .show_options = omfs_show_options, }; /* * For Rio Karma, there is an on-disk free bitmap whose location is * stored in the root block. For ReplayTV, there is no such free bitmap * so we have to walk the tree. Both inodes and file data are allocated * from the same map. This array can be big (300k) so we allocate * in units of the blocksize. */ static int omfs_get_imap(struct super_block *sb) { unsigned int bitmap_size, array_size; int count; struct omfs_sb_info *sbi = OMFS_SB(sb); struct buffer_head *bh; unsigned long **ptr; sector_t block; bitmap_size = DIV_ROUND_UP(sbi->s_num_blocks, 8); array_size = DIV_ROUND_UP(bitmap_size, sb->s_blocksize); if (sbi->s_bitmap_ino == ~0ULL) goto out; sbi->s_imap_size = array_size; sbi->s_imap = kcalloc(array_size, sizeof(unsigned long *), GFP_KERNEL); if (!sbi->s_imap) goto nomem; block = clus_to_blk(sbi, sbi->s_bitmap_ino); if (block >= sbi->s_num_blocks) goto nomem; ptr = sbi->s_imap; for (count = bitmap_size; count > 0; count -= sb->s_blocksize) { bh = sb_bread(sb, block++); if (!bh) goto nomem_free; *ptr = kmemdup(bh->b_data, sb->s_blocksize, GFP_KERNEL); if (!*ptr) { brelse(bh); goto nomem_free; } if (count < sb->s_blocksize) memset((void *)*ptr + count, 0xff, sb->s_blocksize - count); brelse(bh); ptr++; } out: return 0; nomem_free: for (count = 0; count < array_size; count++) kfree(sbi->s_imap[count]); kfree(sbi->s_imap); nomem: sbi->s_imap = NULL; sbi->s_imap_size = 0; return -ENOMEM; } struct omfs_mount_options { kuid_t s_uid; kgid_t s_gid; int s_dmask; int s_fmask; }; enum { Opt_uid, Opt_gid, Opt_umask, Opt_dmask, Opt_fmask, }; static const struct fs_parameter_spec omfs_param_spec[] = { 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), {} }; static int omfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct omfs_mount_options *opts = fc->fs_private; int token; struct fs_parse_result result; /* All options are ignored on remount */ if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) return 0; token = fs_parse(fc, omfs_param_spec, param, &result); if (token < 0) return token; switch (token) { case Opt_uid: opts->s_uid = result.uid; break; case Opt_gid: opts->s_gid = result.gid; break; case Opt_umask: opts->s_fmask = opts->s_dmask = result.uint_32; break; case Opt_dmask: opts->s_dmask = result.uint_32; break; case Opt_fmask: opts->s_fmask = result.uint_32; break; default: return -EINVAL; } return 0; } static void omfs_set_options(struct omfs_sb_info *sbi, struct omfs_mount_options *opts) { sbi->s_uid = opts->s_uid; sbi->s_gid = opts->s_gid; sbi->s_dmask = opts->s_dmask; sbi->s_fmask = opts->s_fmask; } static int omfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct buffer_head *bh, *bh2; struct omfs_super_block *omfs_sb; struct omfs_root_block *omfs_rb; struct omfs_sb_info *sbi; struct inode *root; struct omfs_mount_options *parsed_opts = fc->fs_private; int ret = -EINVAL; int silent = fc->sb_flags & SB_SILENT; sbi = kzalloc(sizeof(struct omfs_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; sb->s_fs_info = sbi; omfs_set_options(sbi, parsed_opts); sb->s_maxbytes = 0xffffffff; sb->s_time_gran = NSEC_PER_MSEC; sb->s_time_min = 0; sb->s_time_max = U64_MAX / MSEC_PER_SEC; sb_set_blocksize(sb, 0x200); bh = sb_bread(sb, 0); if (!bh) goto end; omfs_sb = (struct omfs_super_block *)bh->b_data; if (omfs_sb->s_magic != cpu_to_be32(OMFS_MAGIC)) { if (!silent) printk(KERN_ERR "omfs: Invalid superblock (%x)\n", omfs_sb->s_magic); goto out_brelse_bh; } sb->s_magic = OMFS_MAGIC; sbi->s_num_blocks = be64_to_cpu(omfs_sb->s_num_blocks); sbi->s_blocksize = be32_to_cpu(omfs_sb->s_blocksize); sbi->s_mirrors = be32_to_cpu(omfs_sb->s_mirrors); sbi->s_root_ino = be64_to_cpu(omfs_sb->s_root_block); sbi->s_sys_blocksize = be32_to_cpu(omfs_sb->s_sys_blocksize); mutex_init(&sbi->s_bitmap_lock); if (sbi->s_num_blocks > OMFS_MAX_BLOCKS) { printk(KERN_ERR "omfs: sysblock number (%llx) is out of range\n", (unsigned long long)sbi->s_num_blocks); goto out_brelse_bh; } if (sbi->s_sys_blocksize > PAGE_SIZE) { printk(KERN_ERR "omfs: sysblock size (%d) is out of range\n", sbi->s_sys_blocksize); goto out_brelse_bh; } if (sbi->s_blocksize < sbi->s_sys_blocksize || sbi->s_blocksize > OMFS_MAX_BLOCK_SIZE) { printk(KERN_ERR "omfs: block size (%d) is out of range\n", sbi->s_blocksize); goto out_brelse_bh; } /* * Use sys_blocksize as the fs block since it is smaller than a * page while the fs blocksize can be larger. */ sb_set_blocksize(sb, sbi->s_sys_blocksize); /* * ...and the difference goes into a shift. sys_blocksize is always * a power of two factor of blocksize. */ sbi->s_block_shift = get_bitmask_order(sbi->s_blocksize) - get_bitmask_order(sbi->s_sys_blocksize); bh2 = omfs_bread(sb, be64_to_cpu(omfs_sb->s_root_block)); if (!bh2) goto out_brelse_bh; omfs_rb = (struct omfs_root_block *)bh2->b_data; sbi->s_bitmap_ino = be64_to_cpu(omfs_rb->r_bitmap); sbi->s_clustersize = be32_to_cpu(omfs_rb->r_clustersize); if (sbi->s_num_blocks != be64_to_cpu(omfs_rb->r_num_blocks)) { printk(KERN_ERR "omfs: block count discrepancy between " "super and root blocks (%llx, %llx)\n", (unsigned long long)sbi->s_num_blocks, (unsigned long long)be64_to_cpu(omfs_rb->r_num_blocks)); goto out_brelse_bh2; } if (sbi->s_bitmap_ino != ~0ULL && sbi->s_bitmap_ino > sbi->s_num_blocks) { printk(KERN_ERR "omfs: free space bitmap location is corrupt " "(%llx, total blocks %llx)\n", (unsigned long long) sbi->s_bitmap_ino, (unsigned long long) sbi->s_num_blocks); goto out_brelse_bh2; } if (sbi->s_clustersize < 1 || sbi->s_clustersize > OMFS_MAX_CLUSTER_SIZE) { printk(KERN_ERR "omfs: cluster size out of range (%d)", sbi->s_clustersize); goto out_brelse_bh2; } ret = omfs_get_imap(sb); if (ret) goto out_brelse_bh2; sb->s_op = &omfs_sops; root = omfs_iget(sb, be64_to_cpu(omfs_rb->r_root_dir)); if (IS_ERR(root)) { ret = PTR_ERR(root); goto out_brelse_bh2; } sb->s_root = d_make_root(root); if (!sb->s_root) { ret = -ENOMEM; goto out_brelse_bh2; } printk(KERN_DEBUG "omfs: Mounted volume %s\n", omfs_rb->r_name); ret = 0; out_brelse_bh2: brelse(bh2); out_brelse_bh: brelse(bh); end: if (ret) kfree(sbi); return ret; } static int omfs_get_tree(struct fs_context *fc) { return get_tree_bdev(fc, omfs_fill_super); } static void omfs_free_fc(struct fs_context *fc); static const struct fs_context_operations omfs_context_ops = { .parse_param = omfs_parse_param, .get_tree = omfs_get_tree, .free = omfs_free_fc, }; static int omfs_init_fs_context(struct fs_context *fc) { struct omfs_mount_options *opts; opts = kzalloc(sizeof(*opts), GFP_KERNEL); if (!opts) return -ENOMEM; /* Set mount options defaults */ opts->s_uid = current_uid(); opts->s_gid = current_gid(); opts->s_dmask = opts->s_fmask = current_umask(); fc->fs_private = opts; fc->ops = &omfs_context_ops; return 0; } static void omfs_free_fc(struct fs_context *fc) { kfree(fc->fs_private); } static struct file_system_type omfs_fs_type = { .owner = THIS_MODULE, .name = "omfs", .kill_sb = kill_block_super, .fs_flags = FS_REQUIRES_DEV, .init_fs_context = omfs_init_fs_context, .parameters = omfs_param_spec, }; MODULE_ALIAS_FS("omfs"); static int __init init_omfs_fs(void) { return register_filesystem(&omfs_fs_type); } static void __exit exit_omfs_fs(void) { unregister_filesystem(&omfs_fs_type); } module_init(init_omfs_fs); module_exit(exit_omfs_fs); |
| 21 13 8 17 3 18 4 15 50 11 41 2413 2405 8 39 6 39 33 4 3 1 4 1 3 4 6 6 2 1 1 1 1 1 1 5 2 3 5 3 3 3 2 4 1 1 1 1 1 2 1 1 1 1 1 2 1 1 220 109 1 2 2 2 1 1 1 21 1 29 1 64 2 4 6 7 2 2 3 8 24 24 1 5 8 7 1 226 18 215 7 221 216 56 56 56 56 56 56 50 5 1 60 2 56 56 55 2 27 21 7 20 14 21 17 6 9 36 26 9 16 3 13 16 1000 985 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/file.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/rw_hint.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #include "internal.h" #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned int arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(file_mnt_idmap(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT) && !(filp->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); filp->f_iocb_flags = iocb_flags(filp); spin_unlock(&filp->f_lock); out: return error; } /* * Allocate an file->f_owner struct if it doesn't exist, handling racing * allocations correctly. */ int file_f_owner_allocate(struct file *file) { struct fown_struct *f_owner; f_owner = file_f_owner(file); if (f_owner) return 0; f_owner = kzalloc(sizeof(struct fown_struct), GFP_KERNEL); if (!f_owner) return -ENOMEM; rwlock_init(&f_owner->lock); f_owner->file = file; /* If someone else raced us, drop our allocation. */ if (unlikely(cmpxchg(&file->f_owner, NULL, f_owner))) kfree(f_owner); return 0; } EXPORT_SYMBOL(file_f_owner_allocate); void file_f_owner_release(struct file *file) { struct fown_struct *f_owner; f_owner = file_f_owner(file); if (f_owner) { put_pid(f_owner->pid); kfree(f_owner); } } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { struct fown_struct *f_owner; f_owner = file_f_owner(filp); if (WARN_ON_ONCE(!f_owner)) return; write_lock_irq(&f_owner->lock); if (force || !f_owner->pid) { put_pid(f_owner->pid); f_owner->pid = get_pid(pid); f_owner->pid_type = type; if (pid) { const struct cred *cred = current_cred(); security_file_set_fowner(filp); f_owner->uid = cred->uid; f_owner->euid = cred->euid; } } write_unlock_irq(&f_owner->lock); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, int who, int force) { enum pid_type type; struct pid *pid = NULL; int ret = 0; might_sleep(); type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } ret = file_f_owner_allocate(filp); if (ret) return ret; rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { __f_setown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; struct fown_struct *f_owner; f_owner = file_f_owner(filp); if (!f_owner) return pid; read_lock_irq(&f_owner->lock); rcu_read_lock(); if (pid_task(f_owner->pid, f_owner->pid_type)) { pid = pid_vnr(f_owner->pid); if (f_owner->pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&f_owner->lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } ret = file_f_owner_allocate(filp); if (ret) return ret; rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; struct fown_struct *f_owner; enum pid_type pid_type = PIDTYPE_PID; f_owner = file_f_owner(filp); if (f_owner) { read_lock_irq(&f_owner->lock); rcu_read_lock(); if (pid_task(f_owner->pid, f_owner->pid_type)) owner.pid = pid_vnr(f_owner->pid); rcu_read_unlock(); pid_type = f_owner->pid_type; } switch (pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } if (f_owner) read_unlock_irq(&f_owner->lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); struct fown_struct *f_owner; uid_t __user *dst = (void __user *)arg; uid_t src[2] = {0, 0}; int err; f_owner = file_f_owner(filp); if (f_owner) { read_lock_irq(&f_owner->lock); src[0] = from_kuid(user_ns, f_owner->uid); src[1] = from_kuid(user_ns, f_owner->euid); read_unlock_irq(&f_owner->lock); } err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(u64 hint) { BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET); BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE); BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT); BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM); BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG); BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME); switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_get_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint = READ_ONCE(inode->i_write_hint); if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; } static long fcntl_set_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint; if (!inode_owner_or_capable(file_mnt_idmap(file), inode)) return -EPERM; if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; if (!rw_hint_valid(hint)) return -EINVAL; WRITE_ONCE(inode->i_write_hint, hint); /* * file->f_mapping->host may differ from inode. As an example, * blkdev_open() modifies file->f_mapping. */ if (file->f_mapping->host != inode) WRITE_ONCE(file->f_mapping->host->i_write_hint, hint); return 0; } /* Is the file descriptor a dup of the file? */ static long f_dupfd_query(int fd, struct file *filp) { CLASS(fd_raw, f)(fd); if (fd_empty(f)) return -EBADF; /* * We can do the 'fdput()' immediately, as the only thing that * matters is the pointer value which isn't changed by the fdput. * * Technically we didn't need a ref at all, and 'fdget()' was * overkill, but given our lockless file pointer lookup, the * alternatives are complicated. */ return fd_file(f) == filp; } /* Let the caller figure out whether a given file was just created. */ static long f_created_query(const struct file *filp) { return !!(filp->f_mode & FMODE_CREATED); } static int f_owner_sig(struct file *filp, int signum, bool setsig) { int ret = 0; struct fown_struct *f_owner; might_sleep(); if (setsig) { if (!valid_signal(signum)) return -EINVAL; ret = file_f_owner_allocate(filp); if (ret) return ret; } f_owner = file_f_owner(filp); if (setsig) f_owner->signum = signum; else if (f_owner) ret = f_owner->signum; return ret; } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; int argi = (int)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_CREATED_QUERY: err = f_created_query(filp); break; case F_DUPFD: err = f_dupfd(argi, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(argi, filp, O_CLOEXEC); break; case F_DUPFD_QUERY: err = f_dupfd_query(argi, filp); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, argi & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, argi); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: fallthrough; #endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, argi, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = f_owner_sig(filp, 0, false); break; case F_SETSIG: err = f_owner_sig(filp, argi, true); break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, argi); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, argi); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, argi); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, argi); break; case F_GET_RW_HINT: err = fcntl_get_rw_hint(filp, cmd, arg); break; case F_SET_RW_HINT: err = fcntl_set_rw_hint(filp, cmd, arg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_CREATED_QUERY: case F_DUPFD: case F_DUPFD_CLOEXEC: case F_DUPFD_QUERY: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { CLASS(fd_raw, f)(fd); long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, fd_file(f)); return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; CLASS(fd_raw, f)(fd); struct flock64 flock; long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (err) return err; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(fd_file(f), cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, fd_file(f), cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { CLASS(fd_raw, f)(fd); struct flock flock; long err; if (fd_empty(f)) return -EBADF; if (unlikely(fd_file(f)->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) return -EBADF; } err = security_file_fcntl(fd_file(f), cmd, arg); if (err) return err; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(fd_file(f), convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, fd_file(f), convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, fd_file(f)); break; } return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct file *file) { struct fown_struct *fown; struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; fown = file_f_owner(file); if (!fown) return 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __ro_after_init; /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; kfree_rcu(fa, fa_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = file_f_owner(fa->fa_file); if (!fown) goto next; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } next: read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } module_init(fcntl_init) |
| 38 80 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_BITOPS_LE_H_ #define _ASM_GENERIC_BITOPS_LE_H_ #include <asm/types.h> #include <asm/byteorder.h> #if defined(__LITTLE_ENDIAN) #define BITOP_LE_SWIZZLE 0 #elif defined(__BIG_ENDIAN) #define BITOP_LE_SWIZZLE ((BITS_PER_LONG-1) & ~0x7) #endif static inline int test_bit_le(int nr, const void *addr) { return test_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void set_bit_le(int nr, void *addr) { set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void clear_bit_le(int nr, void *addr) { clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void __set_bit_le(int nr, void *addr) { __set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline void __clear_bit_le(int nr, void *addr) { __clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int test_and_set_bit_le(int nr, void *addr) { return test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int test_and_clear_bit_le(int nr, void *addr) { return test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int __test_and_set_bit_le(int nr, void *addr) { return __test_and_set_bit(nr ^ BITOP_LE_SWIZZLE, addr); } static inline int __test_and_clear_bit_le(int nr, void *addr) { return __test_and_clear_bit(nr ^ BITOP_LE_SWIZZLE, addr); } #endif /* _ASM_GENERIC_BITOPS_LE_H_ */ |
| 102 407 96 270 210 1 87 363 296 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 1991, 1992 Linus Torvalds * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs */ #ifndef _ASM_X86_STACKTRACE_H #define _ASM_X86_STACKTRACE_H #include <linux/uaccess.h> #include <linux/ptrace.h> #include <asm/cpu_entry_area.h> #include <asm/switch_to.h> enum stack_type { STACK_TYPE_UNKNOWN, STACK_TYPE_TASK, STACK_TYPE_IRQ, STACK_TYPE_SOFTIRQ, STACK_TYPE_ENTRY, STACK_TYPE_EXCEPTION, STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, }; struct stack_info { enum stack_type type; unsigned long *begin, *end, *next_sp; }; bool in_task_stack(unsigned long *stack, struct task_struct *task, struct stack_info *info); bool in_entry_stack(unsigned long *stack, struct stack_info *info); int get_stack_info(unsigned long *stack, struct task_struct *task, struct stack_info *info, unsigned long *visit_mask); bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task, struct stack_info *info); static __always_inline bool get_stack_guard_info(unsigned long *stack, struct stack_info *info) { /* make sure it's not in the stack proper */ if (get_stack_info_noinstr(stack, current, info)) return false; /* but if it is in the page below it, we hit a guard */ return get_stack_info_noinstr((void *)stack + PAGE_SIZE, current, info); } const char *stack_type_name(enum stack_type type); static inline bool on_stack(struct stack_info *info, void *addr, size_t len) { void *begin = info->begin; void *end = info->end; return (info->type != STACK_TYPE_UNKNOWN && addr >= begin && addr < end && addr + len > begin && addr + len <= end); } #ifdef CONFIG_X86_32 #define STACKSLOTS_PER_LINE 8 #else #define STACKSLOTS_PER_LINE 4 #endif #ifdef CONFIG_FRAME_POINTER static inline unsigned long * get_frame_pointer(struct task_struct *task, struct pt_regs *regs) { if (regs) return (unsigned long *)regs->bp; if (task == current) return __builtin_frame_address(0); return &((struct inactive_task_frame *)task->thread.sp)->bp; } #else static inline unsigned long * get_frame_pointer(struct task_struct *task, struct pt_regs *regs) { return NULL; } #endif /* CONFIG_FRAME_POINTER */ static inline unsigned long * get_stack_pointer(struct task_struct *task, struct pt_regs *regs) { if (regs) return (unsigned long *)regs->sp; if (task == current) return __builtin_frame_address(0); return (unsigned long *)task->thread.sp; } /* The form of the top of the frame on the stack */ struct stack_frame { struct stack_frame *next_frame; unsigned long return_address; }; struct stack_frame_ia32 { u32 next_frame; u32 return_address; }; void show_opcodes(struct pt_regs *regs, const char *loglvl); void show_ip(struct pt_regs *regs, const char *loglvl); #endif /* _ASM_X86_STACKTRACE_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_FPU_XCR_H #define _ASM_X86_FPU_XCR_H #define XCR_XFEATURE_ENABLED_MASK 0x00000000 #define XCR_XFEATURE_IN_USE_MASK 0x00000001 static __always_inline u64 xgetbv(u32 index) { u32 eax, edx; asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index)); return eax + ((u64)edx << 32); } static inline void xsetbv(u32 index, u64 value) { u32 eax = value; u32 edx = value >> 32; asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); } /* * Return a mask of xfeatures which are currently being tracked * by the processor as being in the initial configuration. * * Callers should check X86_FEATURE_XGETBV1. */ static __always_inline u64 xfeatures_in_use(void) { return xgetbv(XCR_XFEATURE_IN_USE_MASK); } #endif /* _ASM_X86_FPU_XCR_H */ |
| 8115 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Sleepable Read-Copy Update mechanism for mutual exclusion * * Copyright (C) IBM Corporation, 2006 * Copyright (C) Fujitsu, 2012 * * Author: Paul McKenney <paulmck@linux.ibm.com> * Lai Jiangshan <laijs@cn.fujitsu.com> * * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU/ *.txt * */ #ifndef _LINUX_SRCU_H #define _LINUX_SRCU_H #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/rcu_segcblist.h> struct srcu_struct; #ifdef CONFIG_DEBUG_LOCK_ALLOC int __init_srcu_struct(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); #define init_srcu_struct(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ __init_srcu_struct((ssp), #ssp, &__srcu_key); \ }) #define __SRCU_DEP_MAP_INIT(srcu_name) .dep_map = { .name = #srcu_name }, #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ int init_srcu_struct(struct srcu_struct *ssp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /* Values for SRCU Tree srcu_data ->srcu_reader_flavor, but also used by rcutorture. */ #define SRCU_READ_FLAVOR_NORMAL 0x1 // srcu_read_lock(). #define SRCU_READ_FLAVOR_NMI 0x2 // srcu_read_lock_nmisafe(). // 0x4 // SRCU-lite is no longer with us. #define SRCU_READ_FLAVOR_FAST 0x8 // srcu_read_lock_fast(). #define SRCU_READ_FLAVOR_ALL (SRCU_READ_FLAVOR_NORMAL | SRCU_READ_FLAVOR_NMI | \ SRCU_READ_FLAVOR_FAST) // All of the above. #define SRCU_READ_FLAVOR_SLOWGP SRCU_READ_FLAVOR_FAST // Flavors requiring synchronize_rcu() // instead of smp_mb(). void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); #ifdef CONFIG_TINY_SRCU #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) #include <linux/srcutree.h> #else #error "Unknown SRCU implementation specified to kernel configuration" #endif void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); void cleanup_srcu_struct(struct srcu_struct *ssp); void synchronize_srcu(struct srcu_struct *ssp); #define SRCU_GET_STATE_COMPLETED 0x1 /** * get_completed_synchronize_srcu - Return a pre-completed polled state cookie * * Returns a value that poll_state_synchronize_srcu() will always treat * as a cookie whose grace period has already completed. */ static inline unsigned long get_completed_synchronize_srcu(void) { return SRCU_GET_STATE_COMPLETED; } unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); // Maximum number of unsigned long values corresponding to // not-yet-completed SRCU grace periods. #define NUM_ACTIVE_SRCU_POLL_OLDSTATE 2 /** * same_state_synchronize_srcu - Are two old-state values identical? * @oldstate1: First old-state value. * @oldstate2: Second old-state value. * * The two old-state values must have been obtained from either * get_state_synchronize_srcu(), start_poll_synchronize_srcu(), or * get_completed_synchronize_srcu(). Returns @true if the two values are * identical and @false otherwise. This allows structures whose lifetimes * are tracked by old-state values to push these values to a list header, * allowing those structures to be slightly smaller. */ static inline bool same_state_synchronize_srcu(unsigned long oldstate1, unsigned long oldstate2) { return oldstate1 == oldstate2; } #ifdef CONFIG_NEED_SRCU_NMI_SAFE int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); #else static inline int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) { return __srcu_read_lock(ssp); } static inline void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) { __srcu_read_unlock(ssp, idx); } #endif /* CONFIG_NEED_SRCU_NMI_SAFE */ void srcu_init(void); #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * srcu_read_lock_held - might we be in SRCU read-side critical section? * @ssp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an SRCU read-side critical section unless it can * prove otherwise. * * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * * Note that SRCU is based on its own statemachine and it doesn't * relies on normal RCU, it can be called from the CPU which * is in the idle loop from an RCU point of view or offline. */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { if (!debug_lockdep_rcu_enabled()) return 1; return lock_is_held(&ssp->dep_map); } /* * Annotations provide deadlock detection for SRCU. * * Similar to other lockdep annotations, except there is an additional * srcu_lock_sync(), which is basically an empty *write*-side critical section, * see lock_sync() for more information. */ /* Annotates a srcu_read_lock() */ static inline void srcu_lock_acquire(struct lockdep_map *map) { lock_map_acquire_read(map); } /* Annotates a srcu_read_lock() */ static inline void srcu_lock_release(struct lockdep_map *map) { lock_map_release(map); } /* Annotates a synchronize_srcu() */ static inline void srcu_lock_sync(struct lockdep_map *map) { lock_map_sync(map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { return 1; } #define srcu_lock_acquire(m) do { } while (0) #define srcu_lock_release(m) do { } while (0) #define srcu_lock_sync(m) do { } while (0) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * @c: condition to check for update-side use * * If PROVE_RCU is enabled, invoking this outside of an RCU read-side * critical section will result in an RCU-lockdep splat, unless @c evaluates * to 1. The @c argument will normally be a logical expression containing * lockdep_is_held() calls. */ #define srcu_dereference_check(p, ssp, c) \ __rcu_dereference_check((p), __UNIQUE_ID(rcu), \ (c) || srcu_read_lock_held(ssp), __rcu) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * * Makes rcu_dereference_check() do the dirty work. If PROVE_RCU * is enabled, invoking this outside of an RCU read-side critical * section will result in an RCU-lockdep splat. */ #define srcu_dereference(p, ssp) srcu_dereference_check((p), (ssp), 0) /** * srcu_dereference_notrace - no tracing and no lockdep calls from here * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. */ #define srcu_dereference_notrace(p, ssp) srcu_dereference_check((p), (ssp), 1) /** * srcu_read_lock - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section. Note that SRCU read-side * critical sections may be nested. However, it is illegal to * call anything that waits on an SRCU grace period for the same * srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * * The return value from srcu_read_lock() is guaranteed to be * non-negative. This value must be passed unaltered to the matching * srcu_read_unlock(). Note that srcu_read_lock() and the matching * srcu_read_unlock() must occur in the same context, for example, it is * illegal to invoke srcu_read_unlock() in an irq handler if the matching * srcu_read_lock() was invoked in process context. Or, for that matter to * invoke srcu_read_unlock() from one task and the matching srcu_read_lock() * from another. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); srcu_lock_acquire(&ssp->dep_map); return retval; } /** * srcu_read_lock_fast - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but for a light-weight * smp_mb()-free reader. See srcu_read_lock() for more information. * * If srcu_read_lock_fast() is ever used on an srcu_struct structure, * then none of the other flavors may be used, whether before, during, * or after. Note that grace-period auto-expediting is disabled for _fast * srcu_struct structures because auto-expedited grace periods invoke * synchronize_rcu_expedited(), IPIs and all. * * Note that srcu_read_lock_fast() can be invoked only from those contexts * where RCU is watching, that is, from contexts where it would be legal * to invoke rcu_read_lock(). Otherwise, lockdep will complain. */ static inline struct srcu_ctr __percpu *srcu_read_lock_fast(struct srcu_struct *ssp) __acquires(ssp) { struct srcu_ctr __percpu *retval; srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_FAST); retval = __srcu_read_lock_fast(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /** * srcu_down_read_fast - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter a semaphore-like SRCU read-side critical section, but for * a light-weight smp_mb()-free reader. See srcu_read_lock_fast() and * srcu_down_read() for more information. * * The same srcu_struct may be used concurrently by srcu_down_read_fast() * and srcu_read_lock_fast(). */ static inline struct srcu_ctr __percpu *srcu_down_read_fast(struct srcu_struct *ssp) __acquires(ssp) { WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi()); srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_FAST); return __srcu_read_lock_fast(ssp); } /** * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section, but in an NMI-safe manner. * See srcu_read_lock() for more information. * * If srcu_read_lock_nmisafe() is ever used on an srcu_struct structure, * then none of the other flavors may be used, whether before, during, * or after. */ static inline int srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); retval = __srcu_read_lock_nmisafe(ssp); rcu_try_lock_acquire(&ssp->dep_map); return retval; } /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); retval = __srcu_read_lock(ssp); return retval; } /** * srcu_down_read - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter a semaphore-like SRCU read-side critical section. Note that * SRCU read-side critical sections may be nested. However, it is * illegal to call anything that waits on an SRCU grace period for the * same srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). But if you want lockdep to help you * keep this stuff straight, you should instead use srcu_read_lock(). * * The semaphore-like nature of srcu_down_read() means that the matching * srcu_up_read() can be invoked from some other context, for example, * from some other task or from an irq handler. However, neither * srcu_down_read() nor srcu_up_read() may be invoked from an NMI handler. * * Calls to srcu_down_read() may be nested, similar to the manner in * which calls to down_read() may be nested. The same srcu_struct may be * used concurrently by srcu_down_read() and srcu_read_lock(). */ static inline int srcu_down_read(struct srcu_struct *ssp) __acquires(ssp) { WARN_ON_ONCE(in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); return __srcu_read_lock(ssp); } /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section. */ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock(ssp, idx); } /** * srcu_read_unlock_fast - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @scp: return value from corresponding srcu_read_lock_fast(). * * Exit a light-weight SRCU read-side critical section. */ static inline void srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp) __releases(ssp) { srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST); srcu_lock_release(&ssp->dep_map); __srcu_read_unlock_fast(ssp, scp); } /** * srcu_up_read_fast - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @scp: return value from corresponding srcu_read_lock_fast(). * * Exit an SRCU read-side critical section, but not necessarily from * the same context as the maching srcu_down_read_fast(). */ static inline void srcu_up_read_fast(struct srcu_struct *ssp, struct srcu_ctr __percpu *scp) __releases(ssp) { WARN_ON_ONCE(IS_ENABLED(CONFIG_PROVE_RCU) && in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_FAST); __srcu_read_unlock_fast(ssp, scp); } /** * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock_nmisafe(). * * Exit an SRCU read-side critical section, but in an NMI-safe manner. */ static inline void srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NMI); rcu_lock_release(&ssp->dep_map); __srcu_read_unlock_nmisafe(ssp, idx); } /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } /** * srcu_up_read - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section, but not necessarily from * the same context as the maching srcu_down_read(). */ static inline void srcu_up_read(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); WARN_ON_ONCE(in_nmi()); srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_NORMAL); __srcu_read_unlock(ssp, idx); } /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * * Converts the preceding srcu_read_unlock into a two-way memory barrier. * * Call this after srcu_read_unlock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_unlock will appear to happen after * the preceding srcu_read_unlock. */ static inline void smp_mb__after_srcu_read_unlock(void) { /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } /** * smp_mb__after_srcu_read_lock - ensure full ordering after srcu_read_lock * * Converts the preceding srcu_read_lock into a two-way memory barrier. * * Call this after srcu_read_lock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_lock will appear to happen after * the preceding srcu_read_lock. */ static inline void smp_mb__after_srcu_read_lock(void) { /* __srcu_read_lock has smp_mb() internally so nothing to do here. */ } DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, _T->idx = srcu_read_lock(_T->lock), srcu_read_unlock(_T->lock, _T->idx), int idx) DEFINE_LOCK_GUARD_1(srcu_fast, struct srcu_struct, _T->scp = srcu_read_lock_fast(_T->lock), srcu_read_unlock_fast(_T->lock, _T->scp), struct srcu_ctr __percpu *scp) #endif |
| 103 108 5 117 2 106 43 143 108 36 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_BTREE_CACHE_H #define _BCACHEFS_BTREE_CACHE_H #include "bcachefs.h" #include "btree_types.h" #include "bkey_methods.h" extern const char * const bch2_btree_node_flags[]; struct btree_iter; void bch2_recalc_btree_reserve(struct bch_fs *); void bch2_btree_node_to_freelist(struct bch_fs *, struct btree *); void __bch2_btree_node_hash_remove(struct btree_cache *, struct btree *); void bch2_btree_node_hash_remove(struct btree_cache *, struct btree *); int __bch2_btree_node_hash_insert(struct btree_cache *, struct btree *); int bch2_btree_node_hash_insert(struct btree_cache *, struct btree *, unsigned, enum btree_id); void bch2_node_pin(struct bch_fs *, struct btree *); void bch2_btree_cache_unpin(struct bch_fs *); void bch2_btree_node_update_key_early(struct btree_trans *, enum btree_id, unsigned, struct bkey_s_c, struct bkey_i *); void bch2_btree_cache_cannibalize_unlock(struct btree_trans *); int bch2_btree_cache_cannibalize_lock(struct btree_trans *, struct closure *); void __btree_node_data_free(struct btree *); struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *); struct btree *bch2_btree_node_mem_alloc(struct btree_trans *, bool); struct btree *bch2_btree_node_get(struct btree_trans *, struct btree_path *, const struct bkey_i *, unsigned, enum six_lock_type, unsigned long); struct btree *bch2_btree_node_get_noiter(struct btree_trans *, const struct bkey_i *, enum btree_id, unsigned, bool); int bch2_btree_node_prefetch(struct btree_trans *, struct btree_path *, const struct bkey_i *, enum btree_id, unsigned); void bch2_btree_node_evict(struct btree_trans *, const struct bkey_i *); void bch2_fs_btree_cache_exit(struct bch_fs *); int bch2_fs_btree_cache_init(struct bch_fs *); void bch2_fs_btree_cache_init_early(struct btree_cache *); static inline u64 btree_ptr_hash_val(const struct bkey_i *k) { switch (k->k.type) { case KEY_TYPE_btree_ptr: return *((u64 *) bkey_i_to_btree_ptr_c(k)->v.start); case KEY_TYPE_btree_ptr_v2: /* * The cast/deref is only necessary to avoid sparse endianness * warnings: */ return *((u64 *) &bkey_i_to_btree_ptr_v2_c(k)->v.seq); default: return 0; } } static inline struct btree *btree_node_mem_ptr(const struct bkey_i *k) { return k->k.type == KEY_TYPE_btree_ptr_v2 ? (void *)(unsigned long)bkey_i_to_btree_ptr_v2_c(k)->v.mem_ptr : NULL; } /* is btree node in hash table? */ static inline bool btree_node_hashed(struct btree *b) { return b->hash_val != 0; } #define for_each_cached_btree(_b, _c, _tbl, _iter, _pos) \ for ((_tbl) = rht_dereference_rcu((_c)->btree_cache.table.tbl, \ &(_c)->btree_cache.table), \ _iter = 0; _iter < (_tbl)->size; _iter++) \ rht_for_each_entry_rcu((_b), (_pos), _tbl, _iter, hash) static inline size_t btree_buf_bytes(const struct btree *b) { return 1UL << b->byte_order; } static inline size_t btree_buf_max_u64s(const struct btree *b) { return (btree_buf_bytes(b) - sizeof(struct btree_node)) / sizeof(u64); } static inline size_t btree_max_u64s(const struct bch_fs *c) { return (c->opts.btree_node_size - sizeof(struct btree_node)) / sizeof(u64); } static inline size_t btree_sectors(const struct bch_fs *c) { return c->opts.btree_node_size >> SECTOR_SHIFT; } static inline unsigned btree_blocks(const struct bch_fs *c) { return btree_sectors(c) >> c->block_bits; } #define BTREE_SPLIT_THRESHOLD(c) (btree_max_u64s(c) * 2 / 3) #define BTREE_FOREGROUND_MERGE_THRESHOLD(c) (btree_max_u64s(c) * 1 / 3) #define BTREE_FOREGROUND_MERGE_HYSTERESIS(c) \ (BTREE_FOREGROUND_MERGE_THRESHOLD(c) + \ (BTREE_FOREGROUND_MERGE_THRESHOLD(c) >> 2)) static inline unsigned btree_id_nr_alive(struct bch_fs *c) { return BTREE_ID_NR + c->btree_roots_extra.nr; } static inline struct btree_root *bch2_btree_id_root(struct bch_fs *c, unsigned id) { if (likely(id < BTREE_ID_NR)) { return &c->btree_roots_known[id]; } else { unsigned idx = id - BTREE_ID_NR; /* This can happen when we're called from btree_node_scan */ if (idx >= c->btree_roots_extra.nr) return NULL; return &c->btree_roots_extra.data[idx]; } } static inline struct btree *btree_node_root(struct bch_fs *c, struct btree *b) { struct btree_root *r = bch2_btree_id_root(c, b->c.btree_id); return r ? r->b : NULL; } const char *bch2_btree_id_str(enum btree_id); /* avoid */ void bch2_btree_id_to_text(struct printbuf *, enum btree_id); void bch2_btree_id_level_to_text(struct printbuf *, enum btree_id, unsigned); void __bch2_btree_pos_to_text(struct printbuf *, struct bch_fs *, enum btree_id, unsigned, struct bkey_s_c); void bch2_btree_pos_to_text(struct printbuf *, struct bch_fs *, const struct btree *); void bch2_btree_node_to_text(struct printbuf *, struct bch_fs *, const struct btree *); void bch2_btree_cache_to_text(struct printbuf *, const struct btree_cache *); #endif /* _BCACHEFS_BTREE_CACHE_H */ |
| 3388 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | /* * Performance events: * * Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra * * Data type definitions, declarations, prototypes. * * Started by: Thomas Gleixner and Ingo Molnar * * For licencing details see kernel-base/COPYING */ #ifndef _LINUX_PERF_EVENT_H #define _LINUX_PERF_EVENT_H #include <uapi/linux/perf_event.h> #include <uapi/linux/bpf_perf_event.h> /* * Kernel-internal data types and definitions: */ #ifdef CONFIG_PERF_EVENTS # include <asm/perf_event.h> # include <asm/local64.h> #endif #ifdef CONFIG_HAVE_HW_BREAKPOINT # include <linux/rhashtable-types.h> # include <asm/hw_breakpoint.h> #endif #include <linux/list.h> #include <linux/mutex.h> #include <linux/rculist.h> #include <linux/rcupdate.h> #include <linux/spinlock.h> #include <linux/hrtimer.h> #include <linux/fs.h> #include <linux/pid_namespace.h> #include <linux/workqueue.h> #include <linux/ftrace.h> #include <linux/cpu.h> #include <linux/irq_work.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/atomic.h> #include <linux/sysfs.h> #include <linux/perf_regs.h> #include <linux/cgroup.h> #include <linux/refcount.h> #include <linux/security.h> #include <linux/static_call.h> #include <linux/lockdep.h> #include <asm/local.h> struct perf_callchain_entry { u64 nr; u64 ip[]; /* /proc/sys/kernel/perf_event_max_stack */ }; struct perf_callchain_entry_ctx { struct perf_callchain_entry *entry; u32 max_stack; u32 nr; short contexts; bool contexts_maxed; }; typedef unsigned long (*perf_copy_f)(void *dst, const void *src, unsigned long off, unsigned long len); struct perf_raw_frag { union { struct perf_raw_frag *next; unsigned long pad; }; perf_copy_f copy; void *data; u32 size; } __packed; struct perf_raw_record { struct perf_raw_frag frag; u32 size; }; static __always_inline bool perf_raw_frag_last(const struct perf_raw_frag *frag) { return frag->pad < sizeof(u64); } /* * branch stack layout: * nr: number of taken branches stored in entries[] * hw_idx: The low level index of raw branch records * for the most recent branch. * -1ULL means invalid/unknown. * * Note that nr can vary from sample to sample * branches (to, from) are stored from most recent * to least recent, i.e., entries[0] contains the most * recent branch. * The entries[] is an abstraction of raw branch records, * which may not be stored in age order in HW, e.g. Intel LBR. * The hw_idx is to expose the low level index of raw * branch record for the most recent branch aka entries[0]. * The hw_idx index is between -1 (unknown) and max depth, * which can be retrieved in /sys/devices/cpu/caps/branches. * For the architectures whose raw branch records are * already stored in age order, the hw_idx should be 0. */ struct perf_branch_stack { u64 nr; u64 hw_idx; struct perf_branch_entry entries[]; }; struct task_struct; /* * extra PMU register associated with an event */ struct hw_perf_event_extra { u64 config; /* register value */ unsigned int reg; /* register address or index */ int alloc; /* extra register already allocated */ int idx; /* index in shared_regs->regs[] */ }; /** * hw_perf_event::flag values * * PERF_EVENT_FLAG_ARCH bits are reserved for architecture-specific * usage. */ #define PERF_EVENT_FLAG_ARCH 0x0fffffff #define PERF_EVENT_FLAG_USER_READ_CNT 0x80000000 static_assert((PERF_EVENT_FLAG_USER_READ_CNT & PERF_EVENT_FLAG_ARCH) == 0); /** * struct hw_perf_event - performance event hardware details: */ struct hw_perf_event { #ifdef CONFIG_PERF_EVENTS union { struct { /* hardware */ u64 config; u64 config1; u64 last_tag; u64 dyn_constraint; unsigned long config_base; unsigned long event_base; int event_base_rdpmc; int idx; int last_cpu; int flags; struct hw_perf_event_extra extra_reg; struct hw_perf_event_extra branch_reg; }; struct { /* aux / Intel-PT */ u64 aux_config; /* * For AUX area events, aux_paused cannot be a state * flag because it can be updated asynchronously to * state. */ unsigned int aux_paused; }; struct { /* software */ struct hrtimer hrtimer; }; struct { /* tracepoint */ /* for tp_event->class */ struct list_head tp_list; }; struct { /* amd_power */ u64 pwr_acc; u64 ptsc; }; #ifdef CONFIG_HAVE_HW_BREAKPOINT struct { /* breakpoint */ /* * Crufty hack to avoid the chicken and egg * problem hw_breakpoint has with context * creation and event initalization. */ struct arch_hw_breakpoint info; struct rhlist_head bp_list; }; #endif struct { /* amd_iommu */ u8 iommu_bank; u8 iommu_cntr; u16 padding; u64 conf; u64 conf1; }; }; /* * If the event is a per task event, this will point to the task in * question. See the comment in perf_event_alloc(). */ struct task_struct *target; /* * PMU would store hardware filter configuration * here. */ void *addr_filters; /* Last sync'ed generation of filters */ unsigned long addr_filters_gen; /* * hw_perf_event::state flags; used to track the PERF_EF_* state. */ /* the counter is stopped */ #define PERF_HES_STOPPED 0x01 /* event->count up-to-date */ #define PERF_HES_UPTODATE 0x02 #define PERF_HES_ARCH 0x04 int state; /* * The last observed hardware counter value, updated with a * local64_cmpxchg() such that pmu::read() can be called nested. */ local64_t prev_count; /* * The period to start the next sample with. */ u64 sample_period; union { struct { /* Sampling */ /* * The period we started this sample with. */ u64 last_period; /* * However much is left of the current period; * note that this is a full 64bit value and * allows for generation of periods longer * than hardware might allow. */ local64_t period_left; }; struct { /* Topdown events counting for context switch */ u64 saved_metric; u64 saved_slots; }; }; /* * State for throttling the event, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 interrupts_seq; u64 interrupts; /* * State for freq target events, see __perf_event_overflow() and * perf_adjust_freq_unthr_context(). */ u64 freq_time_stamp; u64 freq_count_stamp; #endif /* CONFIG_PERF_EVENTS */ }; struct perf_event; struct perf_event_pmu_context; /* * Common implementation detail of pmu::{start,commit,cancel}_txn */ /* txn to add/schedule event on PMU */ #define PERF_PMU_TXN_ADD 0x1 /* txn to read event group from PMU */ #define PERF_PMU_TXN_READ 0x2 /** * pmu::capabilities flags */ #define PERF_PMU_CAP_NO_INTERRUPT 0x0001 #define PERF_PMU_CAP_NO_NMI 0x0002 #define PERF_PMU_CAP_AUX_NO_SG 0x0004 #define PERF_PMU_CAP_EXTENDED_REGS 0x0008 #define PERF_PMU_CAP_EXCLUSIVE 0x0010 #define PERF_PMU_CAP_ITRACE 0x0020 #define PERF_PMU_CAP_NO_EXCLUDE 0x0040 #define PERF_PMU_CAP_AUX_OUTPUT 0x0080 #define PERF_PMU_CAP_EXTENDED_HW_TYPE 0x0100 #define PERF_PMU_CAP_AUX_PAUSE 0x0200 #define PERF_PMU_CAP_AUX_PREFER_LARGE 0x0400 /** * pmu::scope */ enum perf_pmu_scope { PERF_PMU_SCOPE_NONE = 0, PERF_PMU_SCOPE_CORE, PERF_PMU_SCOPE_DIE, PERF_PMU_SCOPE_CLUSTER, PERF_PMU_SCOPE_PKG, PERF_PMU_SCOPE_SYS_WIDE, PERF_PMU_MAX_SCOPE, }; struct perf_output_handle; #define PMU_NULL_DEV ((void *)(~0UL)) /** * struct pmu - generic performance monitoring unit */ struct pmu { struct list_head entry; spinlock_t events_lock; struct list_head events; struct module *module; struct device *dev; struct device *parent; const struct attribute_group **attr_groups; const struct attribute_group **attr_update; const char *name; int type; /* * various common per-pmu feature flags */ int capabilities; /* * PMU scope */ unsigned int scope; struct perf_cpu_pmu_context * __percpu *cpu_pmu_context; atomic_t exclusive_cnt; /* < 0: cpu; > 0: tsk */ int task_ctx_nr; int hrtimer_interval_ms; /* number of address filters this PMU can do */ unsigned int nr_addr_filters; /* * Fully disable/enable this PMU, can be used to protect from the PMI * as well as for lazy/batch writing of the MSRs. */ void (*pmu_enable) (struct pmu *pmu); /* optional */ void (*pmu_disable) (struct pmu *pmu); /* optional */ /* * Try and initialize the event for this PMU. * * Returns: * -ENOENT -- @event is not for this PMU * * -ENODEV -- @event is for this PMU but PMU not present * -EBUSY -- @event is for this PMU but PMU temporarily unavailable * -EINVAL -- @event is for this PMU but @event is not valid * -EOPNOTSUPP -- @event is for this PMU, @event is valid, but not supported * -EACCES -- @event is for this PMU, @event is valid, but no privileges * * 0 -- @event is for this PMU and valid * * Other error return values are allowed. */ int (*event_init) (struct perf_event *event); /* * Notification that the event was mapped or unmapped. Called * in the context of the mapping task. */ void (*event_mapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ void (*event_unmapped) (struct perf_event *event, struct mm_struct *mm); /* optional */ /* * Flags for ->add()/->del()/ ->start()/->stop(). There are * matching hw_perf_event::state flags. */ /* start the counter when adding */ #define PERF_EF_START 0x01 /* reload the counter when starting */ #define PERF_EF_RELOAD 0x02 /* update the counter when stopping */ #define PERF_EF_UPDATE 0x04 /* AUX area event, pause tracing */ #define PERF_EF_PAUSE 0x08 /* AUX area event, resume tracing */ #define PERF_EF_RESUME 0x10 /* * Adds/Removes a counter to/from the PMU, can be done inside a * transaction, see the ->*_txn() methods. * * The add/del callbacks will reserve all hardware resources required * to service the event, this includes any counter constraint * scheduling etc. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on. * * ->add() called without PERF_EF_START should result in the same state * as ->add() followed by ->stop(). * * ->del() must always PERF_EF_UPDATE stop an event. If it calls * ->stop() that must deal with already being stopped without * PERF_EF_UPDATE. */ int (*add) (struct perf_event *event, int flags); void (*del) (struct perf_event *event, int flags); /* * Starts/Stops a counter present on the PMU. * * The PMI handler should stop the counter when perf_event_overflow() * returns !0. ->start() will be used to continue. * * Also used to change the sample period. * * Called with IRQs disabled and the PMU disabled on the CPU the event * is on -- will be called from NMI context with the PMU generates * NMIs. * * ->stop() with PERF_EF_UPDATE will read the counter and update * period/count values like ->read() would. * * ->start() with PERF_EF_RELOAD will reprogram the counter * value, must be preceded by a ->stop() with PERF_EF_UPDATE. * * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with * PERF_EF_RESUME. * * ->start() with PERF_EF_RESUME will start as simply as possible but * only if the counter is not otherwise stopped. Will not overlap * another ->start() with PERF_EF_RESUME nor ->stop() with * PERF_EF_PAUSE. * * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other * ->stop()/->start() invocations, just not itself. */ void (*start) (struct perf_event *event, int flags); void (*stop) (struct perf_event *event, int flags); /* * Updates the counter value of the event. * * For sampling capable PMUs this will also update the software period * hw_perf_event::period_left field. */ void (*read) (struct perf_event *event); /* * Group events scheduling is treated as a transaction, add * group events as a whole and perform one schedulability test. * If the test fails, roll back the whole group * * Start the transaction, after this ->add() doesn't need to * do schedulability tests. * * Optional. */ void (*start_txn) (struct pmu *pmu, unsigned int txn_flags); /* * If ->start_txn() disabled the ->add() schedulability test * then ->commit_txn() is required to perform one. On success * the transaction is closed. On error the transaction is kept * open until ->cancel_txn() is called. * * Optional. */ int (*commit_txn) (struct pmu *pmu); /* * Will cancel the transaction, assumes ->del() is called * for each successful ->add() during the transaction. * * Optional. */ void (*cancel_txn) (struct pmu *pmu); /* * Will return the value for perf_event_mmap_page::index for this event, * if no implementation is provided it will default to 0 (see * perf_event_idx_default). */ int (*event_idx) (struct perf_event *event); /*optional */ /* * context-switches callback */ void (*sched_task) (struct perf_event_pmu_context *pmu_ctx, struct task_struct *task, bool sched_in); /* * Kmem cache of PMU specific data */ struct kmem_cache *task_ctx_cache; /* * Set up pmu-private data structures for an AUX area */ void *(*setup_aux) (struct perf_event *event, void **pages, int nr_pages, bool overwrite); /* optional */ /* * Free pmu-private AUX data structures */ void (*free_aux) (void *aux); /* optional */ /* * Take a snapshot of the AUX buffer without touching the event * state, so that preempting ->start()/->stop() callbacks does * not interfere with their logic. Called in PMI context. * * Returns the size of AUX data copied to the output handle. * * Optional. */ long (*snapshot_aux) (struct perf_event *event, struct perf_output_handle *handle, unsigned long size); /* * Validate address range filters: make sure the HW supports the * requested configuration and number of filters; return 0 if the * supplied filters are valid, -errno otherwise. * * Runs in the context of the ioctl()ing process and is not serialized * with the rest of the PMU callbacks. */ int (*addr_filters_validate) (struct list_head *filters); /* optional */ /* * Synchronize address range filter configuration: * translate hw-agnostic filters into hardware configuration in * event::hw::addr_filters. * * Runs as a part of filter sync sequence that is done in ->start() * callback by calling perf_event_addr_filters_sync(). * * May (and should) traverse event::addr_filters::list, for which its * caller provides necessary serialization. */ void (*addr_filters_sync) (struct perf_event *event); /* optional */ /* * Check if event can be used for aux_output purposes for * events of this PMU. * * Runs from perf_event_open(). Should return 0 for "no match" * or non-zero for "match". */ int (*aux_output_match) (struct perf_event *event); /* optional */ /* * Skip programming this PMU on the given CPU. Typically needed for * big.LITTLE things. */ bool (*filter) (struct pmu *pmu, int cpu); /* optional */ /* * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ }; enum perf_addr_filter_action_t { PERF_ADDR_FILTER_ACTION_STOP = 0, PERF_ADDR_FILTER_ACTION_START, PERF_ADDR_FILTER_ACTION_FILTER, }; /** * struct perf_addr_filter - address range filter definition * @entry: event's filter list linkage * @path: object file's path for file-based filters * @offset: filter range offset * @size: filter range size (size==0 means single address trigger) * @action: filter/start/stop * * This is a hardware-agnostic filter configuration as specified by the user. */ struct perf_addr_filter { struct list_head entry; struct path path; unsigned long offset; unsigned long size; enum perf_addr_filter_action_t action; }; /** * struct perf_addr_filters_head - container for address range filters * @list: list of filters for this event * @lock: spinlock that serializes accesses to the @list and event's * (and its children's) filter generations. * @nr_file_filters: number of file-based filters * * A child event will use parent's @list (and therefore @lock), so they are * bundled together; see perf_event_addr_filters(). */ struct perf_addr_filters_head { struct list_head list; raw_spinlock_t lock; unsigned int nr_file_filters; }; struct perf_addr_filter_range { unsigned long start; unsigned long size; }; /* * The normal states are: * * ACTIVE --. * ^ | * | | * sched_{in,out}() | * | | * v | * ,---> INACTIVE --+ <-. * | | | * | {dis,en}able() * sched_in() | | * | OFF <--' --+ * | | * `---> ERROR ------' * * That is: * * sched_in: INACTIVE -> {ACTIVE,ERROR} * sched_out: ACTIVE -> INACTIVE * disable: {ACTIVE,INACTIVE} -> OFF * enable: {OFF,ERROR} -> INACTIVE * * Where {OFF,ERROR} are disabled states. * * Then we have the {EXIT,REVOKED,DEAD} states which are various shades of * defunct events: * * - EXIT means task that the even was assigned to died, but child events * still live, and further children can still be created. But the event * itself will never be active again. It can only transition to * {REVOKED,DEAD}; * * - REVOKED means the PMU the event was associated with is gone; all * functionality is stopped but the event is still alive. Can only * transition to DEAD; * * - DEAD event really is DYING tearing down state and freeing bits. * */ enum perf_event_state { PERF_EVENT_STATE_DEAD = -5, PERF_EVENT_STATE_REVOKED = -4, /* pmu gone, must not touch */ PERF_EVENT_STATE_EXIT = -3, /* task died, still inherit */ PERF_EVENT_STATE_ERROR = -2, /* scheduling error, can enable */ PERF_EVENT_STATE_OFF = -1, PERF_EVENT_STATE_INACTIVE = 0, PERF_EVENT_STATE_ACTIVE = 1, }; struct file; struct perf_sample_data; typedef void (*perf_overflow_handler_t)(struct perf_event *, struct perf_sample_data *, struct pt_regs *regs); /* * Event capabilities. For event_caps and groups caps. * * PERF_EV_CAP_SOFTWARE: Is a software event. * PERF_EV_CAP_READ_ACTIVE_PKG: A CPU event (or cgroup event) that can be read * from any CPU in the package where it is active. * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and * cannot be a group leader. If an event with this flag is detached from the * group it is scheduled out and moved into an unrecoverable ERROR state. * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the * PMU scope where it is active. */ #define PERF_EV_CAP_SOFTWARE BIT(0) #define PERF_EV_CAP_READ_ACTIVE_PKG BIT(1) #define PERF_EV_CAP_SIBLING BIT(2) #define PERF_EV_CAP_READ_SCOPE BIT(3) #define SWEVENT_HLIST_BITS 8 #define SWEVENT_HLIST_SIZE (1 << SWEVENT_HLIST_BITS) struct swevent_hlist { struct hlist_head heads[SWEVENT_HLIST_SIZE]; struct rcu_head rcu_head; }; #define PERF_ATTACH_CONTEXT 0x0001 #define PERF_ATTACH_GROUP 0x0002 #define PERF_ATTACH_TASK 0x0004 #define PERF_ATTACH_TASK_DATA 0x0008 #define PERF_ATTACH_GLOBAL_DATA 0x0010 #define PERF_ATTACH_SCHED_CB 0x0020 #define PERF_ATTACH_CHILD 0x0040 #define PERF_ATTACH_EXCLUSIVE 0x0080 #define PERF_ATTACH_CALLCHAIN 0x0100 #define PERF_ATTACH_ITRACE 0x0200 struct bpf_prog; struct perf_cgroup; struct perf_buffer; struct pmu_event_list { raw_spinlock_t lock; struct list_head list; }; /* * event->sibling_list is modified whole holding both ctx->lock and ctx->mutex * as such iteration must hold either lock. However, since ctx->lock is an IRQ * safe lock, and is only held by the CPU doing the modification, having IRQs * disabled is sufficient since it will hold-off the IPIs. */ #ifdef CONFIG_PROVE_LOCKING # define lockdep_assert_event_ctx(event) \ WARN_ON_ONCE(__lockdep_enabled && \ (this_cpu_read(hardirqs_enabled) && \ lockdep_is_held(&(event)->ctx->mutex) != LOCK_STATE_HELD)) #else # define lockdep_assert_event_ctx(event) #endif #define for_each_sibling_event(sibling, event) \ lockdep_assert_event_ctx(event); \ if ((event)->group_leader == (event)) \ list_for_each_entry((sibling), &(event)->sibling_list, sibling_list) /** * struct perf_event - performance event kernel representation: */ struct perf_event { #ifdef CONFIG_PERF_EVENTS /* * entry onto perf_event_context::event_list; * modifications require ctx->lock * RCU safe iterations. */ struct list_head event_entry; /* * Locked for modification by both ctx->mutex and ctx->lock; holding * either sufficies for read. */ struct list_head sibling_list; struct list_head active_list; /* * Node on the pinned or flexible tree located at the event context; */ struct rb_node group_node; u64 group_index; /* * We need storage to track the entries in perf_pmu_migrate_context; we * cannot use the event_entry because of RCU and we want to keep the * group in tact which avoids us using the other two entries. */ struct list_head migrate_entry; struct hlist_node hlist_entry; struct list_head active_entry; int nr_siblings; /* Not serialized. Only written during event initialization. */ int event_caps; /* The cumulative AND of all event_caps for events in this group. */ int group_caps; unsigned int group_generation; struct perf_event *group_leader; /* * event->pmu will always point to pmu in which this event belongs. * Whereas event->pmu_ctx->pmu may point to other pmu when group of * different pmu events is created. */ struct pmu *pmu; void *pmu_private; enum perf_event_state state; unsigned int attach_state; local64_t count; atomic64_t child_count; /* * These are the total time in nanoseconds that the event * has been enabled (i.e. eligible to run, and the task has * been scheduled in, if this is a per-task event) * and running (scheduled onto the CPU), respectively. */ u64 total_time_enabled; u64 total_time_running; u64 tstamp; struct perf_event_attr attr; u16 header_size; u16 id_header_size; u16 read_size; struct hw_perf_event hw; struct perf_event_context *ctx; /* * event->pmu_ctx points to perf_event_pmu_context in which the event * is added. This pmu_ctx can be of other pmu for sw event when that * sw event is part of a group which also contains non-sw events. */ struct perf_event_pmu_context *pmu_ctx; atomic_long_t refcount; /* * These accumulate total time (in nanoseconds) that children * events have been enabled and running, respectively. */ atomic64_t child_total_time_enabled; atomic64_t child_total_time_running; /* * Protect attach/detach and child_list: */ struct mutex child_mutex; struct list_head child_list; struct perf_event *parent; int oncpu; int cpu; struct list_head owner_entry; struct task_struct *owner; /* mmap bits */ struct mutex mmap_mutex; atomic_t mmap_count; struct perf_buffer *rb; struct list_head rb_entry; unsigned long rcu_batches; int rcu_pending; /* poll related */ wait_queue_head_t waitq; struct fasync_struct *fasync; /* delayed work for NMIs and such */ unsigned int pending_wakeup; unsigned int pending_kill; unsigned int pending_disable; unsigned long pending_addr; /* SIGTRAP */ struct irq_work pending_irq; struct irq_work pending_disable_irq; struct callback_head pending_task; unsigned int pending_work; atomic_t event_limit; /* address range filters */ struct perf_addr_filters_head addr_filters; /* vma address array for file-based filders */ struct perf_addr_filter_range *addr_filter_ranges; unsigned long addr_filters_gen; /* for aux_output events */ struct perf_event *aux_event; void (*destroy)(struct perf_event *); struct rcu_head rcu_head; struct pid_namespace *ns; u64 id; atomic64_t lost_samples; u64 (*clock)(void); perf_overflow_handler_t overflow_handler; void *overflow_handler_context; struct bpf_prog *prog; u64 bpf_cookie; #ifdef CONFIG_EVENT_TRACING struct trace_event_call *tp_event; struct event_filter *filter; # ifdef CONFIG_FUNCTION_TRACER struct ftrace_ops ftrace_ops; # endif #endif #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; /* cgroup event is attach to */ #endif #ifdef CONFIG_SECURITY void *security; #endif struct list_head sb_list; struct list_head pmu_list; /* * Certain events gets forwarded to another pmu internally by over- * writing kernel copy of event->attr.type without user being aware * of it. event->orig_type contains original 'type' requested by * user. */ u32 orig_type; #endif /* CONFIG_PERF_EVENTS */ }; /* * ,-----------------------[1:n]------------------------. * V V * perf_event_context <-[1:n]-> perf_event_pmu_context <-[1:n]- perf_event * | | * `--[n:1]-> pmu <-[1:n]--' * * * struct perf_event_pmu_context lifetime is refcount based and RCU freed * (similar to perf_event_context). Locking is as if it were a member of * perf_event_context; specifically: * * modification, both: ctx->mutex && ctx->lock * reading, either: ctx->mutex || ctx->lock * * There is one exception to this; namely put_pmu_ctx() isn't always called * with ctx->mutex held; this means that as long as we can guarantee the epc * has events the above rules hold. * * Specificially, sys_perf_event_open()'s group_leader case depends on * ctx->mutex pinning the configuration. Since we hold a reference on * group_leader (through the filedesc) it can't go away, therefore it's * associated pmu_ctx must exist and cannot change due to ctx->mutex. * * perf_event holds a refcount on perf_event_context * perf_event holds a refcount on perf_event_pmu_context */ struct perf_event_pmu_context { struct pmu *pmu; struct perf_event_context *ctx; struct list_head pmu_ctx_entry; struct list_head pinned_active; struct list_head flexible_active; /* Used to identify the per-cpu perf_event_pmu_context */ unsigned int embedded : 1; unsigned int nr_events; unsigned int nr_cgroups; unsigned int nr_freq; atomic_t refcount; /* event <-> epc */ struct rcu_head rcu_head; /* * Set when one or more (plausibly active) event can't be scheduled * due to pmu overcommit or pmu constraints, except tolerant to * events not necessary to be active due to scheduling constraints, * such as cgroups. */ int rotate_necessary; }; static inline bool perf_pmu_ctx_is_active(struct perf_event_pmu_context *epc) { return !list_empty(&epc->flexible_active) || !list_empty(&epc->pinned_active); } struct perf_event_groups { struct rb_root tree; u64 index; }; /** * struct perf_event_context - event context structure * * Used as a container for task events and CPU events as well: */ struct perf_event_context { /* * Protect the states of the events in the list, * nr_active, and the list: */ raw_spinlock_t lock; /* * Protect the list of events. Locking either mutex or lock * is sufficient to ensure the list doesn't change; to change * the list you need to lock both the mutex and the spinlock. */ struct mutex mutex; struct list_head pmu_ctx_list; struct perf_event_groups pinned_groups; struct perf_event_groups flexible_groups; struct list_head event_list; int nr_events; int nr_user; int is_active; int nr_stat; int nr_freq; int rotate_disable; refcount_t refcount; /* event <-> ctx */ struct task_struct *task; /* * Context clock, runs when context enabled. */ u64 time; u64 timestamp; u64 timeoffset; /* * These fields let us detect when two contexts have both * been cloned (inherited) from a common ancestor. */ struct perf_event_context *parent_ctx; u64 parent_gen; u64 generation; int pin_count; #ifdef CONFIG_CGROUP_PERF int nr_cgroups; /* cgroup evts */ #endif struct rcu_head rcu_head; /* * The count of events for which using the switch-out fast path * should be avoided. * * Sum (event->pending_work + events with * (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ))) * * The SIGTRAP is targeted at ctx->task, as such it won't do changing * that until the signal is delivered. */ local_t nr_no_switch_fast; }; /** * struct perf_ctx_data - PMU specific data for a task * @rcu_head: To avoid the race on free PMU specific data * @refcount: To track users * @global: To track system-wide users * @ctx_cache: Kmem cache of PMU specific data * @data: PMU specific data * * Currently, the struct is only used in Intel LBR call stack mode to * save/restore the call stack of a task on context switches. * * The rcu_head is used to prevent the race on free the data. * The data only be allocated when Intel LBR call stack mode is enabled. * The data will be freed when the mode is disabled. * The content of the data will only be accessed in context switch, which * should be protected by rcu_read_lock(). * * Because of the alignment requirement of Intel Arch LBR, the Kmem cache * is used to allocate the PMU specific data. The ctx_cache is to track * the Kmem cache. * * Careful: Struct perf_ctx_data is added as a pointer in struct task_struct. * When system-wide Intel LBR call stack mode is enabled, a buffer with * constant size will be allocated for each task. * Also, system memory consumption can further grow when the size of * struct perf_ctx_data enlarges. */ struct perf_ctx_data { struct rcu_head rcu_head; refcount_t refcount; int global; struct kmem_cache *ctx_cache; void *data; }; struct perf_cpu_pmu_context { struct perf_event_pmu_context epc; struct perf_event_pmu_context *task_epc; struct list_head sched_cb_entry; int sched_cb_usage; int active_oncpu; int exclusive; int pmu_disable_count; raw_spinlock_t hrtimer_lock; struct hrtimer hrtimer; ktime_t hrtimer_interval; unsigned int hrtimer_active; }; /** * struct perf_event_cpu_context - per cpu event context structure */ struct perf_cpu_context { struct perf_event_context ctx; struct perf_event_context *task_ctx; int online; #ifdef CONFIG_CGROUP_PERF struct perf_cgroup *cgrp; #endif /* * Per-CPU storage for iterators used in visit_groups_merge. The default * storage is of size 2 to hold the CPU and any CPU event iterators. */ int heap_size; struct perf_event **heap; struct perf_event *heap_default[2]; }; struct perf_output_handle { struct perf_event *event; struct perf_buffer *rb; unsigned long wakeup; unsigned long size; union { u64 flags; /* perf_output*() */ u64 aux_flags; /* perf_aux_output*() */ struct { u64 skip_read : 1; }; }; union { void *addr; unsigned long head; }; int page; }; struct bpf_perf_event_data_kern { bpf_user_pt_regs_t *regs; struct perf_sample_data *data; struct perf_event *event; }; #ifdef CONFIG_CGROUP_PERF /* * perf_cgroup_info keeps track of time_enabled for a cgroup. * This is a per-cpu dynamically allocated data structure. */ struct perf_cgroup_info { u64 time; u64 timestamp; u64 timeoffset; int active; }; struct perf_cgroup { struct cgroup_subsys_state css; struct perf_cgroup_info __percpu *info; }; /* * Must ensure cgroup is pinned (css_get) before calling * this function. In other words, we cannot call this function * if there is no cgroup event for the current CPU context. */ static inline struct perf_cgroup * perf_cgroup_from_task(struct task_struct *task, struct perf_event_context *ctx) { return container_of(task_css_check(task, perf_event_cgrp_id, ctx ? lockdep_is_held(&ctx->lock) : true), struct perf_cgroup, css); } #endif /* CONFIG_CGROUP_PERF */ #ifdef CONFIG_PERF_EVENTS extern struct perf_event_context *perf_cpu_task_ctx(void); extern void *perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event); extern void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size); extern int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size); extern void *perf_get_aux(struct perf_output_handle *handle); extern void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags); extern void perf_event_itrace_started(struct perf_event *event); extern int perf_pmu_register(struct pmu *pmu, const char *name, int type); extern int perf_pmu_unregister(struct pmu *pmu); extern void __perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task); extern void __perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next); extern int perf_event_init_task(struct task_struct *child, u64 clone_flags); extern void perf_event_exit_task(struct task_struct *child); extern void perf_event_free_task(struct task_struct *task); extern void perf_event_delayed_put(struct task_struct *task); extern struct file *perf_event_get(unsigned int fd); extern const struct perf_event *perf_get_event(struct file *file); extern const struct perf_event_attr *perf_event_attrs(struct perf_event *event); extern void perf_event_print_debug(void); extern void perf_pmu_disable(struct pmu *pmu); extern void perf_pmu_enable(struct pmu *pmu); extern void perf_sched_cb_dec(struct pmu *pmu); extern void perf_sched_cb_inc(struct pmu *pmu); extern int perf_event_task_disable(void); extern int perf_event_task_enable(void); extern void perf_pmu_resched(struct pmu *pmu); extern int perf_event_refresh(struct perf_event *event, int refresh); extern void perf_event_update_userpage(struct perf_event *event); extern int perf_event_release_kernel(struct perf_event *event); extern struct perf_event * perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu, struct task_struct *task, perf_overflow_handler_t callback, void *context); extern void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu); extern int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running); extern u64 perf_event_read_value(struct perf_event *event, u64 *enabled, u64 *running); extern struct perf_callchain_entry *perf_callchain(struct perf_event *event, struct pt_regs *regs); static inline bool branch_sample_no_flags(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_FLAGS; } static inline bool branch_sample_no_cycles(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_NO_CYCLES; } static inline bool branch_sample_type(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_TYPE_SAVE; } static inline bool branch_sample_hw_index(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX; } static inline bool branch_sample_priv(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_PRIV_SAVE; } static inline bool branch_sample_counters(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS; } static inline bool branch_sample_call_stack(const struct perf_event *event) { return event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK; } struct perf_sample_data { /* * Fields set by perf_sample_data_init() unconditionally, * group so as to minimize the cachelines touched. */ u64 sample_flags; u64 period; u64 dyn_size; /* * Fields commonly set by __perf_event_header__init_id(), * group so as to minimize the cachelines touched. */ u64 type; struct { u32 pid; u32 tid; } tid_entry; u64 time; u64 id; struct { u32 cpu; u32 reserved; } cpu_entry; /* * The other fields, optionally {set,used} by * perf_{prepare,output}_sample(). */ u64 ip; struct perf_callchain_entry *callchain; struct perf_raw_record *raw; struct perf_branch_stack *br_stack; u64 *br_stack_cntr; union perf_sample_weight weight; union perf_mem_data_src data_src; u64 txn; struct perf_regs regs_user; struct perf_regs regs_intr; u64 stack_user_size; u64 stream_id; u64 cgroup; u64 addr; u64 phys_addr; u64 data_page_size; u64 code_page_size; u64 aux_size; } ____cacheline_aligned; /* default value for data source */ #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA) |\ PERF_MEM_S(LVLNUM, NA)) static inline void perf_sample_data_init(struct perf_sample_data *data, u64 addr, u64 period) { /* remaining struct members initialized in perf_prepare_sample() */ data->sample_flags = PERF_SAMPLE_PERIOD; data->period = period; data->dyn_size = 0; if (addr) { data->addr = addr; data->sample_flags |= PERF_SAMPLE_ADDR; } } static inline void perf_sample_save_callchain(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs) { int size = 1; if (!(event->attr.sample_type & PERF_SAMPLE_CALLCHAIN)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) return; data->callchain = perf_callchain(event, regs); size += data->callchain->nr; data->dyn_size += size * sizeof(u64); data->sample_flags |= PERF_SAMPLE_CALLCHAIN; } static inline void perf_sample_save_raw_data(struct perf_sample_data *data, struct perf_event *event, struct perf_raw_record *raw) { struct perf_raw_frag *frag = &raw->frag; u32 sum = 0; int size; if (!(event->attr.sample_type & PERF_SAMPLE_RAW)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_RAW)) return; do { sum += frag->size; if (perf_raw_frag_last(frag)) break; frag = frag->next; } while (1); size = round_up(sum + sizeof(u32), sizeof(u64)); raw->size = size - sizeof(u32); frag->pad = raw->size - sum; data->raw = raw; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_RAW; } static inline bool has_branch_stack(struct perf_event *event) { return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK; } static inline void perf_sample_save_brstack(struct perf_sample_data *data, struct perf_event *event, struct perf_branch_stack *brs, u64 *brs_cntr) { int size = sizeof(u64); /* nr */ if (!has_branch_stack(event)) return; if (WARN_ON_ONCE(data->sample_flags & PERF_SAMPLE_BRANCH_STACK)) return; if (branch_sample_hw_index(event)) size += sizeof(u64); brs->nr = min_t(u16, event->attr.sample_max_stack, brs->nr); size += brs->nr * sizeof(struct perf_branch_entry); /* * The extension space for counters is appended after the * struct perf_branch_stack. It is used to store the occurrences * of events of each branch. */ if (brs_cntr) size += brs->nr * sizeof(u64); data->br_stack = brs; data->br_stack_cntr = brs_cntr; data->dyn_size += size; data->sample_flags |= PERF_SAMPLE_BRANCH_STACK; } static inline u32 perf_sample_data_size(struct perf_sample_data *data, struct perf_event *event) { u32 size = sizeof(struct perf_event_header); size += event->header_size + event->id_header_size; size += data->dyn_size; return size; } /* * Clear all bitfields in the perf_branch_entry. * The to and from fields are not cleared because they are * systematically modified by caller. */ static inline void perf_clear_branch_entry_bitfields(struct perf_branch_entry *br) { br->mispred = 0; br->predicted = 0; br->in_tx = 0; br->abort = 0; br->cycles = 0; br->type = 0; br->spec = PERF_BR_SPEC_NA; br->reserved = 0; } extern void perf_output_sample(struct perf_output_handle *handle, struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_prepare_sample(struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern void perf_prepare_header(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event, struct pt_regs *regs); extern int perf_event_overflow(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_forward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern void perf_event_output_backward(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); extern int perf_event_output(struct perf_event *event, struct perf_sample_data *data, struct pt_regs *regs); static inline bool is_default_overflow_handler(struct perf_event *event) { perf_overflow_handler_t overflow_handler = event->overflow_handler; if (likely(overflow_handler == perf_event_output_forward)) return true; if (unlikely(overflow_handler == perf_event_output_backward)) return true; return false; } extern void perf_event_header__init_id(struct perf_event_header *header, struct perf_sample_data *data, struct perf_event *event); extern void perf_event__output_id_sample(struct perf_event *event, struct perf_output_handle *handle, struct perf_sample_data *sample); extern void perf_log_lost_samples(struct perf_event *event, u64 lost); static inline bool event_has_any_exclude_flag(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; return attr->exclude_idle || attr->exclude_user || attr->exclude_kernel || attr->exclude_hv || attr->exclude_guest || attr->exclude_host; } static inline bool is_sampling_event(struct perf_event *event) { return event->attr.sample_period != 0; } /* * Return 1 for a software event, 0 for a hardware event */ static inline int is_software_event(struct perf_event *event) { return event->event_caps & PERF_EV_CAP_SOFTWARE; } /* * Return 1 for event in sw context, 0 for event in hw context */ static inline int in_software_context(struct perf_event *event) { return event->pmu_ctx->pmu->task_ctx_nr == perf_sw_context; } static inline int is_exclusive_pmu(struct pmu *pmu) { return pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE; } extern struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX]; extern void ___perf_sw_event(u32, u64, struct pt_regs *, u64); extern void __perf_sw_event(u32, u64, struct pt_regs *, u64); #ifndef perf_arch_fetch_caller_regs static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { } #endif /* * When generating a perf sample in-line, instead of from an interrupt / * exception, we lack a pt_regs. This is typically used from software events * like: SW_CONTEXT_SWITCHES, SW_MIGRATIONS and the tie-in with tracepoints. * * We typically don't need a full set, but (for x86) do require: * - ip for PERF_SAMPLE_IP * - cs for user_mode() tests * - sp for PERF_SAMPLE_CALLCHAIN * - eflags for MISC bits and CALLCHAIN (see: perf_hw_regs()) * * NOTE: assumes @regs is otherwise already 0 filled; this is important for * things like PERF_SAMPLE_REGS_INTR. */ static inline void perf_fetch_caller_regs(struct pt_regs *regs) { perf_arch_fetch_caller_regs(regs, CALLER_ADDR0); } static __always_inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { if (static_key_false(&perf_swevent_enabled[event_id])) __perf_sw_event(event_id, nr, regs, addr); } DECLARE_PER_CPU(struct pt_regs, __perf_regs[4]); /* * 'Special' version for the scheduler, it hard assumes no recursion, * which is guaranteed by us not actually scheduling inside other swevents * because those disable preemption. */ static __always_inline void __perf_sw_event_sched(u32 event_id, u64 nr, u64 addr) { struct pt_regs *regs = this_cpu_ptr(&__perf_regs[0]); perf_fetch_caller_regs(regs); ___perf_sw_event(event_id, nr, regs, addr); } extern struct static_key_false perf_sched_events; static __always_inline bool __perf_sw_enabled(int swevt) { return static_key_false(&perf_swevent_enabled[swevt]); } static inline void perf_event_task_migrate(struct task_struct *task) { if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS)) task->sched_migrated = 1; } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_in(prev, task); if (__perf_sw_enabled(PERF_COUNT_SW_CPU_MIGRATIONS) && task->sched_migrated) { __perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); task->sched_migrated = 0; } } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { if (__perf_sw_enabled(PERF_COUNT_SW_CONTEXT_SWITCHES)) __perf_sw_event_sched(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 0); #ifdef CONFIG_CGROUP_PERF if (__perf_sw_enabled(PERF_COUNT_SW_CGROUP_SWITCHES) && perf_cgroup_from_task(prev, NULL) != perf_cgroup_from_task(next, NULL)) __perf_sw_event_sched(PERF_COUNT_SW_CGROUP_SWITCHES, 1, 0); #endif if (static_branch_unlikely(&perf_sched_events)) __perf_event_task_sched_out(prev, next); } extern void perf_event_mmap(struct vm_area_struct *vma); extern void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym); extern void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags); #define PERF_GUEST_ACTIVE 0x01 #define PERF_GUEST_USER 0x02 struct perf_guest_info_callbacks { unsigned int (*state)(void); unsigned long (*get_ip)(void); unsigned int (*handle_intel_pt_intr)(void); }; #ifdef CONFIG_GUEST_PERF_EVENTS extern struct perf_guest_info_callbacks __rcu *perf_guest_cbs; DECLARE_STATIC_CALL(__perf_guest_state, *perf_guest_cbs->state); DECLARE_STATIC_CALL(__perf_guest_get_ip, *perf_guest_cbs->get_ip); DECLARE_STATIC_CALL(__perf_guest_handle_intel_pt_intr, *perf_guest_cbs->handle_intel_pt_intr); static inline unsigned int perf_guest_state(void) { return static_call(__perf_guest_state)(); } static inline unsigned long perf_guest_get_ip(void) { return static_call(__perf_guest_get_ip)(); } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return static_call(__perf_guest_handle_intel_pt_intr)(); } extern void perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); extern void perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *cbs); #else /* !CONFIG_GUEST_PERF_EVENTS: */ static inline unsigned int perf_guest_state(void) { return 0; } static inline unsigned long perf_guest_get_ip(void) { return 0; } static inline unsigned int perf_guest_handle_intel_pt_intr(void) { return 0; } #endif /* !CONFIG_GUEST_PERF_EVENTS */ extern void perf_event_exec(void); extern void perf_event_comm(struct task_struct *tsk, bool exec); extern void perf_event_namespaces(struct task_struct *tsk); extern void perf_event_fork(struct task_struct *tsk); extern void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len); /* Callchains */ DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry); extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); extern void put_callchain_entry(int rctx); extern int sysctl_perf_event_max_stack; extern int sysctl_perf_event_max_contexts_per_stack; static inline int perf_callchain_store_context(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->contexts < sysctl_perf_event_max_contexts_per_stack) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->contexts; return 0; } else { ctx->contexts_maxed = true; return -1; /* no more room, stop walking the stack */ } } static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64 ip) { if (ctx->nr < ctx->max_stack && !ctx->contexts_maxed) { struct perf_callchain_entry *entry = ctx->entry; entry->ip[entry->nr++] = ip; ++ctx->nr; return 0; } else { return -1; /* no more room, stop walking the stack */ } } extern int sysctl_perf_event_paranoid; extern int sysctl_perf_event_sample_rate; extern void perf_sample_event_took(u64 sample_len_ns); /* Access to perf_event_open(2) syscall. */ #define PERF_SECURITY_OPEN 0 /* Finer grained perf_event_open(2) access control. */ #define PERF_SECURITY_CPU 1 #define PERF_SECURITY_KERNEL 2 #define PERF_SECURITY_TRACEPOINT 3 static inline int perf_is_paranoid(void) { return sysctl_perf_event_paranoid > -1; } extern int perf_allow_kernel(void); static inline int perf_allow_cpu(void) { if (sysctl_perf_event_paranoid > 0 && !perfmon_capable()) return -EACCES; return security_perf_event_open(PERF_SECURITY_CPU); } static inline int perf_allow_tracepoint(void) { if (sysctl_perf_event_paranoid > -1 && !perfmon_capable()) return -EPERM; return security_perf_event_open(PERF_SECURITY_TRACEPOINT); } extern int perf_exclude_event(struct perf_event *event, struct pt_regs *regs); extern void perf_event_init(void); extern void perf_tp_event(u16 event_type, u64 count, void *record, int entry_size, struct pt_regs *regs, struct hlist_head *head, int rctx, struct task_struct *task); extern void perf_bp_event(struct perf_event *event, void *data); extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs); extern unsigned long perf_instruction_pointer(struct perf_event *event, struct pt_regs *regs); #ifndef perf_arch_misc_flags # define perf_arch_misc_flags(regs) \ (user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL) # define perf_arch_instruction_pointer(regs) instruction_pointer(regs) #endif #ifndef perf_arch_bpf_user_pt_regs # define perf_arch_bpf_user_pt_regs(regs) regs #endif #ifndef perf_arch_guest_misc_flags static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs) { unsigned long guest_state = perf_guest_state(); if (!(guest_state & PERF_GUEST_ACTIVE)) return 0; if (guest_state & PERF_GUEST_USER) return PERF_RECORD_MISC_GUEST_USER; else return PERF_RECORD_MISC_GUEST_KERNEL; } # define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs) #endif static inline bool needs_branch_stack(struct perf_event *event) { return event->attr.branch_sample_type != 0; } static inline bool has_aux(struct perf_event *event) { return event->pmu && event->pmu->setup_aux; } static inline bool has_aux_action(struct perf_event *event) { return event->attr.aux_sample_size || event->attr.aux_pause || event->attr.aux_resume; } static inline bool is_write_backward(struct perf_event *event) { return !!event->attr.write_backward; } static inline bool has_addr_filter(struct perf_event *event) { return event->pmu->nr_addr_filters; } /* * An inherited event uses parent's filters */ static inline struct perf_addr_filters_head * perf_event_addr_filters(struct perf_event *event) { struct perf_addr_filters_head *ifh = &event->addr_filters; if (event->parent) ifh = &event->parent->addr_filters; return ifh; } static inline struct fasync_struct **perf_event_fasync(struct perf_event *event) { /* Only the parent has fasync state */ if (event->parent) event = event->parent; return &event->fasync; } extern void perf_event_addr_filters_sync(struct perf_event *event); extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_forward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern int perf_output_begin_backward(struct perf_output_handle *handle, struct perf_sample_data *data, struct perf_event *event, unsigned int size); extern void perf_output_end(struct perf_output_handle *handle); extern unsigned int perf_output_copy(struct perf_output_handle *handle, const void *buf, unsigned int len); extern unsigned int perf_output_skip(struct perf_output_handle *handle, unsigned int len); extern long perf_output_copy_aux(struct perf_output_handle *aux_handle, struct perf_output_handle *handle, unsigned long from, unsigned long to); extern int perf_swevent_get_recursion_context(void); extern void perf_swevent_put_recursion_context(int rctx); extern u64 perf_swevent_set_period(struct perf_event *event); extern void perf_event_enable(struct perf_event *event); extern void perf_event_disable(struct perf_event *event); extern void perf_event_disable_local(struct perf_event *event); extern void perf_event_disable_inatomic(struct perf_event *event); extern void perf_event_task_tick(void); extern int perf_event_account_interrupt(struct perf_event *event); extern int perf_event_period(struct perf_event *event, u64 value); extern u64 perf_event_pause(struct perf_event *event, bool reset); #else /* !CONFIG_PERF_EVENTS: */ static inline void * perf_aux_output_begin(struct perf_output_handle *handle, struct perf_event *event) { return NULL; } static inline void perf_aux_output_end(struct perf_output_handle *handle, unsigned long size) { } static inline int perf_aux_output_skip(struct perf_output_handle *handle, unsigned long size) { return -EINVAL; } static inline void * perf_get_aux(struct perf_output_handle *handle) { return NULL; } static inline void perf_event_task_migrate(struct task_struct *task) { } static inline void perf_event_task_sched_in(struct task_struct *prev, struct task_struct *task) { } static inline void perf_event_task_sched_out(struct task_struct *prev, struct task_struct *next) { } static inline int perf_event_init_task(struct task_struct *child, u64 clone_flags) { return 0; } static inline void perf_event_exit_task(struct task_struct *child) { } static inline void perf_event_free_task(struct task_struct *task) { } static inline void perf_event_delayed_put(struct task_struct *task) { } static inline struct file *perf_event_get(unsigned int fd) { return ERR_PTR(-EINVAL); } static inline const struct perf_event *perf_get_event(struct file *file) { return ERR_PTR(-EINVAL); } static inline const struct perf_event_attr *perf_event_attrs(struct perf_event *event) { return ERR_PTR(-EINVAL); } static inline int perf_event_read_local(struct perf_event *event, u64 *value, u64 *enabled, u64 *running) { return -EINVAL; } static inline void perf_event_print_debug(void) { } static inline int perf_event_task_disable(void) { return -EINVAL; } static inline int perf_event_task_enable(void) { return -EINVAL; } static inline int perf_event_refresh(struct perf_event *event, int refresh) { return -EINVAL; } static inline void perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr) { } static inline void perf_bp_event(struct perf_event *event, void *data) { } static inline void perf_event_mmap(struct vm_area_struct *vma) { } typedef int (perf_ksymbol_get_name_f)(char *name, int name_len, void *data); static inline void perf_event_ksymbol(u16 ksym_type, u64 addr, u32 len, bool unregister, const char *sym) { } static inline void perf_event_bpf_event(struct bpf_prog *prog, enum perf_bpf_event_type type, u16 flags) { } static inline void perf_event_exec(void) { } static inline void perf_event_comm(struct task_struct *tsk, bool exec) { } static inline void perf_event_namespaces(struct task_struct *tsk) { } static inline void perf_event_fork(struct task_struct *tsk) { } static inline void perf_event_text_poke(const void *addr, const void *old_bytes, size_t old_len, const void *new_bytes, size_t new_len) { } static inline void perf_event_init(void) { } static inline int perf_swevent_get_recursion_context(void) { return -1; } static inline void perf_swevent_put_recursion_context(int rctx) { } static inline u64 perf_swevent_set_period(struct perf_event *event) { return 0; } static inline void perf_event_enable(struct perf_event *event) { } static inline void perf_event_disable(struct perf_event *event) { } static inline int __perf_event_disable(void *info) { return -1; } static inline void perf_event_task_tick(void) { } static inline int perf_event_release_kernel(struct perf_event *event) { return 0; } static inline int perf_event_period(struct perf_event *event, u64 value) { return -EINVAL; } static inline u64 perf_event_pause(struct perf_event *event, bool reset) { return 0; } static inline int perf_exclude_event(struct perf_event *event, struct pt_regs *regs) { return 0; } #endif /* !CONFIG_PERF_EVENTS */ #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern void perf_restore_debug_store(void); #else static inline void perf_restore_debug_store(void) { } #endif #define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x)) struct perf_pmu_events_attr { struct device_attribute attr; u64 id; const char *event_str; }; struct perf_pmu_events_ht_attr { struct device_attribute attr; u64 id; const char *event_str_ht; const char *event_str_noht; }; struct perf_pmu_events_hybrid_attr { struct device_attribute attr; u64 id; const char *event_str; u64 pmu_type; }; struct perf_pmu_format_hybrid_attr { struct device_attribute attr; u64 pmu_type; }; ssize_t perf_event_sysfs_show(struct device *dev, struct device_attribute *attr, char *page); #define PMU_EVENT_ATTR(_name, _var, _id, _show) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, \ }; #define PMU_EVENT_ATTR_STRING(_name, _var, _str) \ static struct perf_pmu_events_attr _var = { \ .attr = __ATTR(_name, 0444, perf_event_sysfs_show, NULL), \ .id = 0, \ .event_str = _str, \ }; #define PMU_EVENT_ATTR_ID(_name, _show, _id) \ (&((struct perf_pmu_events_attr[]) { \ { .attr = __ATTR(_name, 0444, _show, NULL), \ .id = _id, } \ })[0].attr.attr) #define PMU_FORMAT_ATTR_SHOW(_name, _format) \ static ssize_t \ _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *page) \ { \ BUILD_BUG_ON(sizeof(_format) >= PAGE_SIZE); \ return sprintf(page, _format "\n"); \ } \ #define PMU_FORMAT_ATTR(_name, _format) \ PMU_FORMAT_ATTR_SHOW(_name, _format) \ \ static struct device_attribute format_attr_##_name = __ATTR_RO(_name) /* Performance counter hotplug functions */ #ifdef CONFIG_PERF_EVENTS extern int perf_event_init_cpu(unsigned int cpu); extern int perf_event_exit_cpu(unsigned int cpu); #else # define perf_event_init_cpu NULL # define perf_event_exit_cpu NULL #endif extern void arch_perf_update_userpage(struct perf_event *event, struct perf_event_mmap_page *userpg, u64 now); /* * Snapshot branch stack on software events. * * Branch stack can be very useful in understanding software events. For * example, when a long function, e.g. sys_perf_event_open, returns an * errno, it is not obvious why the function failed. Branch stack could * provide very helpful information in this type of scenarios. * * On software event, it is necessary to stop the hardware branch recorder * fast. Otherwise, the hardware register/buffer will be flushed with * entries of the triggering event. Therefore, static call is used to * stop the hardware recorder. */ /* * cnt is the number of entries allocated for entries. * Return number of entries copied to . */ typedef int (perf_snapshot_branch_stack_t)(struct perf_branch_entry *entries, unsigned int cnt); DECLARE_STATIC_CALL(perf_snapshot_branch_stack, perf_snapshot_branch_stack_t); #ifndef PERF_NEEDS_LOPWR_CB static inline void perf_lopwr_cb(bool mode) { } #endif #endif /* _LINUX_PERF_EVENT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 | /* SPDX-License-Identifier: GPL-2.0 */ /* * * Definitions for mount interface. This describes the in the kernel build * linkedlist with mounted filesystems. * * Author: Marco van Wieringen <mvw@planets.elm.net> * */ #ifndef _LINUX_MOUNT_H #define _LINUX_MOUNT_H #include <linux/types.h> #include <asm/barrier.h> struct super_block; struct dentry; struct user_namespace; struct mnt_idmap; struct file_system_type; struct fs_context; struct file; struct path; enum mount_flags { MNT_NOSUID = 0x01, MNT_NODEV = 0x02, MNT_NOEXEC = 0x04, MNT_NOATIME = 0x08, MNT_NODIRATIME = 0x10, MNT_RELATIME = 0x20, MNT_READONLY = 0x40, /* does the user want this to be r/o? */ MNT_NOSYMFOLLOW = 0x80, MNT_SHRINKABLE = 0x100, MNT_WRITE_HOLD = 0x200, MNT_INTERNAL = 0x4000, MNT_LOCK_ATIME = 0x040000, MNT_LOCK_NOEXEC = 0x080000, MNT_LOCK_NOSUID = 0x100000, MNT_LOCK_NODEV = 0x200000, MNT_LOCK_READONLY = 0x400000, MNT_LOCKED = 0x800000, MNT_DOOMED = 0x1000000, MNT_SYNC_UMOUNT = 0x2000000, MNT_UMOUNT = 0x8000000, MNT_USER_SETTABLE_MASK = MNT_NOSUID | MNT_NODEV | MNT_NOEXEC | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME | MNT_READONLY | MNT_NOSYMFOLLOW, MNT_ATIME_MASK = MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME, MNT_INTERNAL_FLAGS = MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_LOCKED }; struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; struct mnt_idmap *mnt_idmap; } __randomize_layout; static inline struct mnt_idmap *mnt_idmap(const struct vfsmount *mnt) { /* Pairs with smp_store_release() in do_idmap_mount(). */ return READ_ONCE(mnt->mnt_idmap); } extern int mnt_want_write(struct vfsmount *mnt); extern int mnt_want_write_file(struct file *file); extern void mnt_drop_write(struct vfsmount *mnt); extern void mnt_drop_write_file(struct file *file); extern void mntput(struct vfsmount *mnt); extern struct vfsmount *mntget(struct vfsmount *mnt); extern void mnt_make_shortterm(struct vfsmount *mnt); extern struct vfsmount *mnt_clone_internal(const struct path *path); extern bool __mnt_is_readonly(struct vfsmount *mnt); extern bool mnt_may_suid(struct vfsmount *mnt); extern struct vfsmount *clone_private_mount(const struct path *path); int mnt_get_write_access(struct vfsmount *mnt); void mnt_put_write_access(struct vfsmount *mnt); extern struct vfsmount *fc_mount(struct fs_context *fc); extern struct vfsmount *fc_mount_longterm(struct fs_context *fc); extern struct vfsmount *vfs_create_mount(struct fs_context *fc); extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data); extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); extern bool path_is_mountpoint(const struct path *path); extern bool our_mnt(struct vfsmount *mnt); extern struct vfsmount *kern_mount(struct file_system_type *); extern void kern_unmount(struct vfsmount *mnt); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); int do_mount(const char *, const char __user *, const char *, unsigned long, void *); extern struct path *collect_paths(const struct path *, struct path *, unsigned); extern void drop_collected_paths(struct path *, struct path *); extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); extern int cifs_root_data(char **dev, char **opts); #endif /* _LINUX_MOUNT_H */ |
| 68 69 69 341 342 73 73 46 23 23 45 12 12 40 10 30 18 11 16 150 15 15 15 17 17 2 1 14 15 15 15 15 15 15 39 33 21 9 23 25 26 5 23 23 23 23 23 23 23 42 42 42 42 41 2 2 2 15 15 1 15 9 11 4 9 1 1 2 32 30 17 32 32 11 11 11 6 8 8 8 32 32 32 32 67 11 11 1 56 139 91 70 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2007 Oracle. All rights reserved. */ #include <linux/bio.h> #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/sched/mm.h> #include <crypto/hash.h> #include "messages.h" #include "ctree.h" #include "disk-io.h" #include "transaction.h" #include "bio.h" #include "compression.h" #include "fs.h" #include "accessors.h" #include "file-item.h" #define __MAX_CSUM_ITEMS(r, size) ((unsigned long)(((BTRFS_LEAF_DATA_SIZE(r) - \ sizeof(struct btrfs_item) * 2) / \ size) - 1)) #define MAX_CSUM_ITEMS(r, size) (min_t(u32, __MAX_CSUM_ITEMS(r, size), \ PAGE_SIZE)) /* * Set inode's size according to filesystem options. * * @inode: inode we want to update the disk_i_size for * @new_i_size: i_size we want to set to, 0 if we use i_size * * With NO_HOLES set this simply sets the disk_is_size to whatever i_size_read() * returns as it is perfectly fine with a file that has holes without hole file * extent items. * * However without NO_HOLES we need to only return the area that is contiguous * from the 0 offset of the file. Otherwise we could end up adjust i_size up * to an extent that has a gap in between. * * Finally new_i_size should only be set in the case of truncate where we're not * ready to use i_size_read() as the limiter yet. */ void btrfs_inode_safe_disk_i_size_write(struct btrfs_inode *inode, u64 new_i_size) { u64 start, end, i_size; bool found; spin_lock(&inode->lock); i_size = new_i_size ?: i_size_read(&inode->vfs_inode); if (!inode->file_extent_tree) { inode->disk_i_size = i_size; goto out_unlock; } found = btrfs_find_contiguous_extent_bit(inode->file_extent_tree, 0, &start, &end, EXTENT_DIRTY); if (found && start == 0) i_size = min(i_size, end + 1); else i_size = 0; inode->disk_i_size = i_size; out_unlock: spin_unlock(&inode->lock); } /* * Mark range within a file as having a new extent inserted. * * @inode: inode being modified * @start: start file offset of the file extent we've inserted * @len: logical length of the file extent item * * Call when we are inserting a new file extent where there was none before. * Does not need to call this in the case where we're replacing an existing file * extent, however if not sure it's fine to call this multiple times. * * The start and len must match the file extent item, so thus must be sectorsize * aligned. */ int btrfs_inode_set_file_extent_range(struct btrfs_inode *inode, u64 start, u64 len) { if (!inode->file_extent_tree) return 0; if (len == 0) return 0; ASSERT(IS_ALIGNED(start + len, inode->root->fs_info->sectorsize)); return btrfs_set_extent_bit(inode->file_extent_tree, start, start + len - 1, EXTENT_DIRTY, NULL); } /* * Mark an inode range as not having a backing extent. * * @inode: inode being modified * @start: start file offset of the file extent we've inserted * @len: logical length of the file extent item * * Called when we drop a file extent, for example when we truncate. Doesn't * need to be called for cases where we're replacing a file extent, like when * we've COWed a file extent. * * The start and len must match the file extent item, so thus must be sectorsize * aligned. */ int btrfs_inode_clear_file_extent_range(struct btrfs_inode *inode, u64 start, u64 len) { if (!inode->file_extent_tree) return 0; if (len == 0) return 0; ASSERT(IS_ALIGNED(start + len, inode->root->fs_info->sectorsize) || len == (u64)-1); return btrfs_clear_extent_bit(inode->file_extent_tree, start, start + len - 1, EXTENT_DIRTY, NULL); } static size_t bytes_to_csum_size(const struct btrfs_fs_info *fs_info, u32 bytes) { ASSERT(IS_ALIGNED(bytes, fs_info->sectorsize)); return (bytes >> fs_info->sectorsize_bits) * fs_info->csum_size; } static size_t csum_size_to_bytes(const struct btrfs_fs_info *fs_info, u32 csum_size) { ASSERT(IS_ALIGNED(csum_size, fs_info->csum_size)); return (csum_size / fs_info->csum_size) << fs_info->sectorsize_bits; } static inline u32 max_ordered_sum_bytes(const struct btrfs_fs_info *fs_info) { u32 max_csum_size = round_down(PAGE_SIZE - sizeof(struct btrfs_ordered_sum), fs_info->csum_size); return csum_size_to_bytes(fs_info, max_csum_size); } /* * Calculate the total size needed to allocate for an ordered sum structure * spanning @bytes in the file. */ static int btrfs_ordered_sum_size(const struct btrfs_fs_info *fs_info, unsigned long bytes) { return sizeof(struct btrfs_ordered_sum) + bytes_to_csum_size(fs_info, bytes); } int btrfs_insert_hole_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 objectid, u64 pos, u64 num_bytes) { int ret = 0; struct btrfs_file_extent_item *item; struct btrfs_key file_key; BTRFS_PATH_AUTO_FREE(path); struct extent_buffer *leaf; path = btrfs_alloc_path(); if (!path) return -ENOMEM; file_key.objectid = objectid; file_key.type = BTRFS_EXTENT_DATA_KEY; file_key.offset = pos; ret = btrfs_insert_empty_item(trans, root, path, &file_key, sizeof(*item)); if (ret < 0) return ret; leaf = path->nodes[0]; item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item); btrfs_set_file_extent_disk_bytenr(leaf, item, 0); btrfs_set_file_extent_disk_num_bytes(leaf, item, 0); btrfs_set_file_extent_offset(leaf, item, 0); btrfs_set_file_extent_num_bytes(leaf, item, num_bytes); btrfs_set_file_extent_ram_bytes(leaf, item, num_bytes); btrfs_set_file_extent_generation(leaf, item, trans->transid); btrfs_set_file_extent_type(leaf, item, BTRFS_FILE_EXTENT_REG); btrfs_set_file_extent_compression(leaf, item, 0); btrfs_set_file_extent_encryption(leaf, item, 0); btrfs_set_file_extent_other_encoding(leaf, item, 0); return ret; } static struct btrfs_csum_item * btrfs_lookup_csum(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 bytenr, int cow) { struct btrfs_fs_info *fs_info = root->fs_info; int ret; struct btrfs_key file_key; struct btrfs_key found_key; struct btrfs_csum_item *item; struct extent_buffer *leaf; u64 csum_offset = 0; const u32 csum_size = fs_info->csum_size; int csums_in_item; file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; file_key.type = BTRFS_EXTENT_CSUM_KEY; file_key.offset = bytenr; ret = btrfs_search_slot(trans, root, &file_key, path, 0, cow); if (ret < 0) goto fail; leaf = path->nodes[0]; if (ret > 0) { ret = 1; if (path->slots[0] == 0) goto fail; path->slots[0]--; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); if (found_key.type != BTRFS_EXTENT_CSUM_KEY) goto fail; csum_offset = (bytenr - found_key.offset) >> fs_info->sectorsize_bits; csums_in_item = btrfs_item_size(leaf, path->slots[0]); csums_in_item /= csum_size; if (csum_offset == csums_in_item) { ret = -EFBIG; goto fail; } else if (csum_offset > csums_in_item) { goto fail; } } item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item); item = (struct btrfs_csum_item *)((unsigned char *)item + csum_offset * csum_size); return item; fail: if (ret > 0) ret = -ENOENT; return ERR_PTR(ret); } int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, u64 objectid, u64 offset, int mod) { struct btrfs_key file_key; int ins_len = mod < 0 ? -1 : 0; int cow = mod != 0; file_key.objectid = objectid; file_key.type = BTRFS_EXTENT_DATA_KEY; file_key.offset = offset; return btrfs_search_slot(trans, root, &file_key, path, ins_len, cow); } /* * Find checksums for logical bytenr range [disk_bytenr, disk_bytenr + len) and * store the result to @dst. * * Return >0 for the number of sectors we found. * Return 0 for the range [disk_bytenr, disk_bytenr + sectorsize) has no csum * for it. Caller may want to try next sector until one range is hit. * Return <0 for fatal error. */ static int search_csum_tree(struct btrfs_fs_info *fs_info, struct btrfs_path *path, u64 disk_bytenr, u64 len, u8 *dst) { struct btrfs_root *csum_root; struct btrfs_csum_item *item = NULL; struct btrfs_key key; const u32 sectorsize = fs_info->sectorsize; const u32 csum_size = fs_info->csum_size; u32 itemsize; int ret; u64 csum_start; u64 csum_len; ASSERT(IS_ALIGNED(disk_bytenr, sectorsize) && IS_ALIGNED(len, sectorsize)); /* Check if the current csum item covers disk_bytenr */ if (path->nodes[0]) { item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_csum_item); btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); itemsize = btrfs_item_size(path->nodes[0], path->slots[0]); csum_start = key.offset; csum_len = (itemsize / csum_size) * sectorsize; if (in_range(disk_bytenr, csum_start, csum_len)) goto found; } /* Current item doesn't contain the desired range, search again */ btrfs_release_path(path); csum_root = btrfs_csum_root(fs_info, disk_bytenr); item = btrfs_lookup_csum(NULL, csum_root, path, disk_bytenr, 0); if (IS_ERR(item)) { ret = PTR_ERR(item); goto out; } btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); itemsize = btrfs_item_size(path->nodes[0], path->slots[0]); csum_start = key.offset; csum_len = (itemsize / csum_size) * sectorsize; ASSERT(in_range(disk_bytenr, csum_start, csum_len)); found: ret = (min(csum_start + csum_len, disk_bytenr + len) - disk_bytenr) >> fs_info->sectorsize_bits; read_extent_buffer(path->nodes[0], dst, (unsigned long)item, ret * csum_size); out: if (ret == -ENOENT || ret == -EFBIG) ret = 0; return ret; } /* * Lookup the checksum for the read bio in csum tree. * * Return: BLK_STS_RESOURCE if allocating memory fails, BLK_STS_OK otherwise. */ int btrfs_lookup_bio_sums(struct btrfs_bio *bbio) { struct btrfs_inode *inode = bbio->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; struct bio *bio = &bbio->bio; BTRFS_PATH_AUTO_FREE(path); const u32 sectorsize = fs_info->sectorsize; const u32 csum_size = fs_info->csum_size; u32 orig_len = bio->bi_iter.bi_size; u64 orig_disk_bytenr = bio->bi_iter.bi_sector << SECTOR_SHIFT; const unsigned int nblocks = orig_len >> fs_info->sectorsize_bits; int ret = 0; u32 bio_offset = 0; if ((inode->flags & BTRFS_INODE_NODATASUM) || test_bit(BTRFS_FS_STATE_NO_DATA_CSUMS, &fs_info->fs_state)) return 0; /* * This function is only called for read bio. * * This means two things: * - All our csums should only be in csum tree * No ordered extents csums, as ordered extents are only for write * path. * - No need to bother any other info from bvec * Since we're looking up csums, the only important info is the * disk_bytenr and the length, which can be extracted from bi_iter * directly. */ ASSERT(bio_op(bio) == REQ_OP_READ); path = btrfs_alloc_path(); if (!path) return -ENOMEM; if (nblocks * csum_size > BTRFS_BIO_INLINE_CSUM_SIZE) { bbio->csum = kmalloc_array(nblocks, csum_size, GFP_NOFS); if (!bbio->csum) return -ENOMEM; } else { bbio->csum = bbio->csum_inline; } /* * If requested number of sectors is larger than one leaf can contain, * kick the readahead for csum tree. */ if (nblocks > fs_info->csums_per_leaf) path->reada = READA_FORWARD; /* * the free space stuff is only read when it hasn't been * updated in the current transaction. So, we can safely * read from the commit root and sidestep a nasty deadlock * between reading the free space cache and updating the csum tree. */ if (btrfs_is_free_space_inode(inode)) { path->search_commit_root = 1; path->skip_locking = 1; } while (bio_offset < orig_len) { int count; u64 cur_disk_bytenr = orig_disk_bytenr + bio_offset; u8 *csum_dst = bbio->csum + (bio_offset >> fs_info->sectorsize_bits) * csum_size; count = search_csum_tree(fs_info, path, cur_disk_bytenr, orig_len - bio_offset, csum_dst); if (count < 0) { ret = count; if (bbio->csum != bbio->csum_inline) kfree(bbio->csum); bbio->csum = NULL; break; } /* * We didn't find a csum for this range. We need to make sure * we complain loudly about this, because we are not NODATASUM. * * However for the DATA_RELOC inode we could potentially be * relocating data extents for a NODATASUM inode, so the inode * itself won't be marked with NODATASUM, but the extent we're * copying is in fact NODATASUM. If we don't find a csum we * assume this is the case. */ if (count == 0) { memset(csum_dst, 0, csum_size); count = 1; if (btrfs_is_data_reloc_root(inode->root)) { u64 file_offset = bbio->file_offset + bio_offset; btrfs_set_extent_bit(&inode->io_tree, file_offset, file_offset + sectorsize - 1, EXTENT_NODATASUM, NULL); } else { btrfs_warn_rl(fs_info, "csum hole found for disk bytenr range [%llu, %llu)", cur_disk_bytenr, cur_disk_bytenr + sectorsize); } } bio_offset += count * sectorsize; } return ret; } /* * Search for checksums for a given logical range. * * @root: The root where to look for checksums. * @start: Logical address of target checksum range. * @end: End offset (inclusive) of the target checksum range. * @list: List for adding each checksum that was found. * Can be NULL in case the caller only wants to check if * there any checksums for the range. * @nowait: Indicate if the search must be non-blocking or not. * * Return < 0 on error, 0 if no checksums were found, or 1 if checksums were * found. */ int btrfs_lookup_csums_list(struct btrfs_root *root, u64 start, u64 end, struct list_head *list, bool nowait) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key key; struct btrfs_path *path; struct extent_buffer *leaf; struct btrfs_ordered_sum *sums; struct btrfs_csum_item *item; int ret; bool found_csums = false; ASSERT(IS_ALIGNED(start, fs_info->sectorsize) && IS_ALIGNED(end + 1, fs_info->sectorsize)); path = btrfs_alloc_path(); if (!path) return -ENOMEM; path->nowait = nowait; key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; key.type = BTRFS_EXTENT_CSUM_KEY; key.offset = start; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto out; if (ret > 0 && path->slots[0] > 0) { leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1); /* * There are two cases we can hit here for the previous csum * item: * * |<- search range ->| * |<- csum item ->| * * Or * |<- search range ->| * |<- csum item ->| * * Check if the previous csum item covers the leading part of * the search range. If so we have to start from previous csum * item. */ if (key.objectid == BTRFS_EXTENT_CSUM_OBJECTID && key.type == BTRFS_EXTENT_CSUM_KEY) { if (bytes_to_csum_size(fs_info, start - key.offset) < btrfs_item_size(leaf, path->slots[0] - 1)) path->slots[0]--; } } while (start <= end) { u64 csum_end; leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) goto out; if (ret > 0) break; leaf = path->nodes[0]; } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || key.type != BTRFS_EXTENT_CSUM_KEY || key.offset > end) break; if (key.offset > start) start = key.offset; csum_end = key.offset + csum_size_to_bytes(fs_info, btrfs_item_size(leaf, path->slots[0])); if (csum_end <= start) { path->slots[0]++; continue; } found_csums = true; if (!list) goto out; csum_end = min(csum_end, end + 1); item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_csum_item); while (start < csum_end) { unsigned long offset; size_t size; size = min_t(size_t, csum_end - start, max_ordered_sum_bytes(fs_info)); sums = kzalloc(btrfs_ordered_sum_size(fs_info, size), GFP_NOFS); if (!sums) { ret = -ENOMEM; goto out; } sums->logical = start; sums->len = size; offset = bytes_to_csum_size(fs_info, start - key.offset); read_extent_buffer(path->nodes[0], sums->sums, ((unsigned long)item) + offset, bytes_to_csum_size(fs_info, size)); start += size; list_add_tail(&sums->list, list); } path->slots[0]++; } out: btrfs_free_path(path); if (ret < 0) { if (list) { struct btrfs_ordered_sum *tmp_sums; list_for_each_entry_safe(sums, tmp_sums, list, list) kfree(sums); } return ret; } return found_csums ? 1 : 0; } /* * Do the same work as btrfs_lookup_csums_list(), the difference is in how * we return the result. * * This version will set the corresponding bits in @csum_bitmap to represent * that there is a csum found. * Each bit represents a sector. Thus caller should ensure @csum_buf passed * in is large enough to contain all csums. */ int btrfs_lookup_csums_bitmap(struct btrfs_root *root, struct btrfs_path *path, u64 start, u64 end, u8 *csum_buf, unsigned long *csum_bitmap) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key key; struct extent_buffer *leaf; struct btrfs_csum_item *item; const u64 orig_start = start; bool free_path = false; int ret; ASSERT(IS_ALIGNED(start, fs_info->sectorsize) && IS_ALIGNED(end + 1, fs_info->sectorsize)); if (!path) { path = btrfs_alloc_path(); if (!path) return -ENOMEM; free_path = true; } /* Check if we can reuse the previous path. */ if (path->nodes[0]) { btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]); if (key.objectid == BTRFS_EXTENT_CSUM_OBJECTID && key.type == BTRFS_EXTENT_CSUM_KEY && key.offset <= start) goto search_forward; btrfs_release_path(path); } key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; key.type = BTRFS_EXTENT_CSUM_KEY; key.offset = start; ret = btrfs_search_slot(NULL, root, &key, path, 0, 0); if (ret < 0) goto fail; if (ret > 0 && path->slots[0] > 0) { leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1); /* * There are two cases we can hit here for the previous csum * item: * * |<- search range ->| * |<- csum item ->| * * Or * |<- search range ->| * |<- csum item ->| * * Check if the previous csum item covers the leading part of * the search range. If so we have to start from previous csum * item. */ if (key.objectid == BTRFS_EXTENT_CSUM_OBJECTID && key.type == BTRFS_EXTENT_CSUM_KEY) { if (bytes_to_csum_size(fs_info, start - key.offset) < btrfs_item_size(leaf, path->slots[0] - 1)) path->slots[0]--; } } search_forward: while (start <= end) { u64 csum_end; leaf = path->nodes[0]; if (path->slots[0] >= btrfs_header_nritems(leaf)) { ret = btrfs_next_leaf(root, path); if (ret < 0) goto fail; if (ret > 0) break; leaf = path->nodes[0]; } btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || key.type != BTRFS_EXTENT_CSUM_KEY || key.offset > end) break; if (key.offset > start) start = key.offset; csum_end = key.offset + csum_size_to_bytes(fs_info, btrfs_item_size(leaf, path->slots[0])); if (csum_end <= start) { path->slots[0]++; continue; } csum_end = min(csum_end, end + 1); item = btrfs_item_ptr(path->nodes[0], path->slots[0], struct btrfs_csum_item); while (start < csum_end) { unsigned long offset; size_t size; u8 *csum_dest = csum_buf + bytes_to_csum_size(fs_info, start - orig_start); size = min_t(size_t, csum_end - start, end + 1 - start); offset = bytes_to_csum_size(fs_info, start - key.offset); read_extent_buffer(path->nodes[0], csum_dest, ((unsigned long)item) + offset, bytes_to_csum_size(fs_info, size)); bitmap_set(csum_bitmap, (start - orig_start) >> fs_info->sectorsize_bits, size >> fs_info->sectorsize_bits); start += size; } path->slots[0]++; } ret = 0; fail: if (free_path) btrfs_free_path(path); return ret; } /* * Calculate checksums of the data contained inside a bio. */ int btrfs_csum_one_bio(struct btrfs_bio *bbio) { struct btrfs_ordered_extent *ordered = bbio->ordered; struct btrfs_inode *inode = bbio->inode; struct btrfs_fs_info *fs_info = inode->root->fs_info; SHASH_DESC_ON_STACK(shash, fs_info->csum_shash); struct bio *bio = &bbio->bio; struct btrfs_ordered_sum *sums; char *data; struct bvec_iter iter; struct bio_vec bvec; int index; unsigned int blockcount; int i; unsigned nofs_flag; nofs_flag = memalloc_nofs_save(); sums = kvzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size), GFP_KERNEL); memalloc_nofs_restore(nofs_flag); if (!sums) return -ENOMEM; sums->len = bio->bi_iter.bi_size; INIT_LIST_HEAD(&sums->list); sums->logical = bio->bi_iter.bi_sector << SECTOR_SHIFT; index = 0; shash->tfm = fs_info->csum_shash; bio_for_each_segment(bvec, bio, iter) { blockcount = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len + fs_info->sectorsize - 1); for (i = 0; i < blockcount; i++) { data = bvec_kmap_local(&bvec); crypto_shash_digest(shash, data + (i * fs_info->sectorsize), fs_info->sectorsize, sums->sums + index); kunmap_local(data); index += fs_info->csum_size; } } bbio->sums = sums; btrfs_add_ordered_sum(ordered, sums); return 0; } /* * Nodatasum I/O on zoned file systems still requires an btrfs_ordered_sum to * record the updated logical address on Zone Append completion. * Allocate just the structure with an empty sums array here for that case. */ int btrfs_alloc_dummy_sum(struct btrfs_bio *bbio) { bbio->sums = kmalloc(sizeof(*bbio->sums), GFP_NOFS); if (!bbio->sums) return -ENOMEM; bbio->sums->len = bbio->bio.bi_iter.bi_size; bbio->sums->logical = bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT; btrfs_add_ordered_sum(bbio->ordered, bbio->sums); return 0; } /* * Remove one checksum overlapping a range. * * This expects the key to describe the csum pointed to by the path, and it * expects the csum to overlap the range [bytenr, len] * * The csum should not be entirely contained in the range and the range should * not be entirely contained in the csum. * * This calls btrfs_truncate_item with the correct args based on the overlap, * and fixes up the key as required. */ static noinline void truncate_one_csum(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_key *key, u64 bytenr, u64 len) { struct btrfs_fs_info *fs_info = trans->fs_info; struct extent_buffer *leaf; const u32 csum_size = fs_info->csum_size; u64 csum_end; u64 end_byte = bytenr + len; u32 blocksize_bits = fs_info->sectorsize_bits; leaf = path->nodes[0]; csum_end = btrfs_item_size(leaf, path->slots[0]) / csum_size; csum_end <<= blocksize_bits; csum_end += key->offset; if (key->offset < bytenr && csum_end <= end_byte) { /* * [ bytenr - len ] * [ ] * [csum ] * A simple truncate off the end of the item */ u32 new_size = (bytenr - key->offset) >> blocksize_bits; new_size *= csum_size; btrfs_truncate_item(trans, path, new_size, 1); } else if (key->offset >= bytenr && csum_end > end_byte && end_byte > key->offset) { /* * [ bytenr - len ] * [ ] * [csum ] * we need to truncate from the beginning of the csum */ u32 new_size = (csum_end - end_byte) >> blocksize_bits; new_size *= csum_size; btrfs_truncate_item(trans, path, new_size, 0); key->offset = end_byte; btrfs_set_item_key_safe(trans, path, key); } else { BUG(); } } /* * Delete the csum items from the csum tree for a given range of bytes. */ int btrfs_del_csums(struct btrfs_trans_handle *trans, struct btrfs_root *root, u64 bytenr, u64 len) { struct btrfs_fs_info *fs_info = trans->fs_info; BTRFS_PATH_AUTO_FREE(path); struct btrfs_key key; u64 end_byte = bytenr + len; u64 csum_end; struct extent_buffer *leaf; int ret = 0; const u32 csum_size = fs_info->csum_size; u32 blocksize_bits = fs_info->sectorsize_bits; ASSERT(btrfs_root_id(root) == BTRFS_CSUM_TREE_OBJECTID || btrfs_root_id(root) == BTRFS_TREE_LOG_OBJECTID); path = btrfs_alloc_path(); if (!path) return -ENOMEM; while (1) { key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; key.type = BTRFS_EXTENT_CSUM_KEY; key.offset = end_byte - 1; ret = btrfs_search_slot(trans, root, &key, path, -1, 1); if (ret > 0) { ret = 0; if (path->slots[0] == 0) break; path->slots[0]--; } else if (ret < 0) { break; } leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &key, path->slots[0]); if (key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || key.type != BTRFS_EXTENT_CSUM_KEY) { break; } if (key.offset >= end_byte) break; csum_end = btrfs_item_size(leaf, path->slots[0]) / csum_size; csum_end <<= blocksize_bits; csum_end += key.offset; /* this csum ends before we start, we're done */ if (csum_end <= bytenr) break; /* delete the entire item, it is inside our range */ if (key.offset >= bytenr && csum_end <= end_byte) { int del_nr = 1; /* * Check how many csum items preceding this one in this * leaf correspond to our range and then delete them all * at once. */ if (key.offset > bytenr && path->slots[0] > 0) { int slot = path->slots[0] - 1; while (slot >= 0) { struct btrfs_key pk; btrfs_item_key_to_cpu(leaf, &pk, slot); if (pk.offset < bytenr || pk.type != BTRFS_EXTENT_CSUM_KEY || pk.objectid != BTRFS_EXTENT_CSUM_OBJECTID) break; path->slots[0] = slot; del_nr++; key.offset = pk.offset; slot--; } } ret = btrfs_del_items(trans, root, path, path->slots[0], del_nr); if (ret) break; if (key.offset == bytenr) break; } else if (key.offset < bytenr && csum_end > end_byte) { unsigned long offset; unsigned long shift_len; unsigned long item_offset; /* * [ bytenr - len ] * [csum ] * * Our bytes are in the middle of the csum, * we need to split this item and insert a new one. * * But we can't drop the path because the * csum could change, get removed, extended etc. * * The trick here is the max size of a csum item leaves * enough room in the tree block for a single * item header. So, we split the item in place, * adding a new header pointing to the existing * bytes. Then we loop around again and we have * a nicely formed csum item that we can neatly * truncate. */ offset = (bytenr - key.offset) >> blocksize_bits; offset *= csum_size; shift_len = (len >> blocksize_bits) * csum_size; item_offset = btrfs_item_ptr_offset(leaf, path->slots[0]); memzero_extent_buffer(leaf, item_offset + offset, shift_len); key.offset = bytenr; /* * btrfs_split_item returns -EAGAIN when the * item changed size or key */ ret = btrfs_split_item(trans, root, path, &key, offset); if (ret && ret != -EAGAIN) { btrfs_abort_transaction(trans, ret); break; } ret = 0; key.offset = end_byte - 1; } else { truncate_one_csum(trans, path, &key, bytenr, len); if (key.offset < bytenr) break; } btrfs_release_path(path); } return ret; } static int find_next_csum_offset(struct btrfs_root *root, struct btrfs_path *path, u64 *next_offset) { const u32 nritems = btrfs_header_nritems(path->nodes[0]); struct btrfs_key found_key; int slot = path->slots[0] + 1; int ret; if (nritems == 0 || slot >= nritems) { ret = btrfs_next_leaf(root, path); if (ret < 0) { return ret; } else if (ret > 0) { *next_offset = (u64)-1; return 0; } slot = path->slots[0]; } btrfs_item_key_to_cpu(path->nodes[0], &found_key, slot); if (found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || found_key.type != BTRFS_EXTENT_CSUM_KEY) *next_offset = (u64)-1; else *next_offset = found_key.offset; return 0; } int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_ordered_sum *sums) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_key file_key; struct btrfs_key found_key; BTRFS_PATH_AUTO_FREE(path); struct btrfs_csum_item *item; struct btrfs_csum_item *item_end; struct extent_buffer *leaf = NULL; u64 next_offset; u64 total_bytes = 0; u64 csum_offset; u64 bytenr; u32 ins_size; int index = 0; int found_next; int ret; const u32 csum_size = fs_info->csum_size; path = btrfs_alloc_path(); if (!path) return -ENOMEM; again: next_offset = (u64)-1; found_next = 0; bytenr = sums->logical + total_bytes; file_key.objectid = BTRFS_EXTENT_CSUM_OBJECTID; file_key.type = BTRFS_EXTENT_CSUM_KEY; file_key.offset = bytenr; item = btrfs_lookup_csum(trans, root, path, bytenr, 1); if (!IS_ERR(item)) { ret = 0; leaf = path->nodes[0]; item_end = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item); item_end = (struct btrfs_csum_item *)((char *)item_end + btrfs_item_size(leaf, path->slots[0])); goto found; } ret = PTR_ERR(item); if (ret != -EFBIG && ret != -ENOENT) goto out; if (ret == -EFBIG) { u32 item_size; /* we found one, but it isn't big enough yet */ leaf = path->nodes[0]; item_size = btrfs_item_size(leaf, path->slots[0]); if ((item_size / csum_size) >= MAX_CSUM_ITEMS(fs_info, csum_size)) { /* already at max size, make a new one */ goto insert; } } else { /* We didn't find a csum item, insert one. */ ret = find_next_csum_offset(root, path, &next_offset); if (ret < 0) goto out; found_next = 1; goto insert; } /* * At this point, we know the tree has a checksum item that ends at an * offset matching the start of the checksum range we want to insert. * We try to extend that item as much as possible and then add as many * checksums to it as they fit. * * First check if the leaf has enough free space for at least one * checksum. If it has go directly to the item extension code, otherwise * release the path and do a search for insertion before the extension. */ if (btrfs_leaf_free_space(leaf) >= csum_size) { btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); csum_offset = (bytenr - found_key.offset) >> fs_info->sectorsize_bits; goto extend_csum; } btrfs_release_path(path); path->search_for_extension = 1; ret = btrfs_search_slot(trans, root, &file_key, path, csum_size, 1); path->search_for_extension = 0; if (ret < 0) goto out; if (ret > 0) { if (path->slots[0] == 0) goto insert; path->slots[0]--; } leaf = path->nodes[0]; btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]); csum_offset = (bytenr - found_key.offset) >> fs_info->sectorsize_bits; if (found_key.type != BTRFS_EXTENT_CSUM_KEY || found_key.objectid != BTRFS_EXTENT_CSUM_OBJECTID || csum_offset >= MAX_CSUM_ITEMS(fs_info, csum_size)) { goto insert; } extend_csum: if (csum_offset == btrfs_item_size(leaf, path->slots[0]) / csum_size) { int extend_nr; u64 tmp; u32 diff; tmp = sums->len - total_bytes; tmp >>= fs_info->sectorsize_bits; WARN_ON(tmp < 1); extend_nr = max_t(int, 1, tmp); /* * A log tree can already have checksum items with a subset of * the checksums we are trying to log. This can happen after * doing a sequence of partial writes into prealloc extents and * fsyncs in between, with a full fsync logging a larger subrange * of an extent for which a previous fast fsync logged a smaller * subrange. And this happens in particular due to merging file * extent items when we complete an ordered extent for a range * covered by a prealloc extent - this is done at * btrfs_mark_extent_written(). * * So if we try to extend the previous checksum item, which has * a range that ends at the start of the range we want to insert, * make sure we don't extend beyond the start offset of the next * checksum item. If we are at the last item in the leaf, then * forget the optimization of extending and add a new checksum * item - it is not worth the complexity of releasing the path, * getting the first key for the next leaf, repeat the btree * search, etc, because log trees are temporary anyway and it * would only save a few bytes of leaf space. */ if (btrfs_root_id(root) == BTRFS_TREE_LOG_OBJECTID) { if (path->slots[0] + 1 >= btrfs_header_nritems(path->nodes[0])) { ret = find_next_csum_offset(root, path, &next_offset); if (ret < 0) goto out; found_next = 1; goto insert; } ret = find_next_csum_offset(root, path, &next_offset); if (ret < 0) goto out; tmp = (next_offset - bytenr) >> fs_info->sectorsize_bits; if (tmp <= INT_MAX) extend_nr = min_t(int, extend_nr, tmp); } diff = (csum_offset + extend_nr) * csum_size; diff = min(diff, MAX_CSUM_ITEMS(fs_info, csum_size) * csum_size); diff = diff - btrfs_item_size(leaf, path->slots[0]); diff = min_t(u32, btrfs_leaf_free_space(leaf), diff); diff /= csum_size; diff *= csum_size; btrfs_extend_item(trans, path, diff); ret = 0; goto csum; } insert: btrfs_release_path(path); csum_offset = 0; if (found_next) { u64 tmp; tmp = sums->len - total_bytes; tmp >>= fs_info->sectorsize_bits; tmp = min(tmp, (next_offset - file_key.offset) >> fs_info->sectorsize_bits); tmp = max_t(u64, 1, tmp); tmp = min_t(u64, tmp, MAX_CSUM_ITEMS(fs_info, csum_size)); ins_size = csum_size * tmp; } else { ins_size = csum_size; } ret = btrfs_insert_empty_item(trans, root, path, &file_key, ins_size); if (ret < 0) goto out; leaf = path->nodes[0]; csum: item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_csum_item); item_end = (struct btrfs_csum_item *)((unsigned char *)item + btrfs_item_size(leaf, path->slots[0])); item = (struct btrfs_csum_item *)((unsigned char *)item + csum_offset * csum_size); found: ins_size = (u32)(sums->len - total_bytes) >> fs_info->sectorsize_bits; ins_size *= csum_size; ins_size = min_t(u32, (unsigned long)item_end - (unsigned long)item, ins_size); write_extent_buffer(leaf, sums->sums + index, (unsigned long)item, ins_size); index += ins_size; ins_size /= csum_size; total_bytes += ins_size * fs_info->sectorsize; if (total_bytes < sums->len) { btrfs_release_path(path); cond_resched(); goto again; } out: return ret; } void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode, const struct btrfs_path *path, const struct btrfs_file_extent_item *fi, struct extent_map *em) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_root *root = inode->root; struct extent_buffer *leaf = path->nodes[0]; const int slot = path->slots[0]; struct btrfs_key key; u64 extent_start; u8 type = btrfs_file_extent_type(leaf, fi); int compress_type = btrfs_file_extent_compression(leaf, fi); btrfs_item_key_to_cpu(leaf, &key, slot); extent_start = key.offset; em->ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi); em->generation = btrfs_file_extent_generation(leaf, fi); if (type == BTRFS_FILE_EXTENT_REG || type == BTRFS_FILE_EXTENT_PREALLOC) { const u64 disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi); em->start = extent_start; em->len = btrfs_file_extent_end(path) - extent_start; if (disk_bytenr == 0) { em->disk_bytenr = EXTENT_MAP_HOLE; em->disk_num_bytes = 0; em->offset = 0; return; } em->disk_bytenr = disk_bytenr; em->disk_num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi); em->offset = btrfs_file_extent_offset(leaf, fi); if (compress_type != BTRFS_COMPRESS_NONE) { btrfs_extent_map_set_compression(em, compress_type); } else { /* * Older kernels can create regular non-hole data * extents with ram_bytes smaller than disk_num_bytes. * Not a big deal, just always use disk_num_bytes * for ram_bytes. */ em->ram_bytes = em->disk_num_bytes; if (type == BTRFS_FILE_EXTENT_PREALLOC) em->flags |= EXTENT_FLAG_PREALLOC; } } else if (type == BTRFS_FILE_EXTENT_INLINE) { /* Tree-checker has ensured this. */ ASSERT(extent_start == 0); em->disk_bytenr = EXTENT_MAP_INLINE; em->start = 0; em->len = fs_info->sectorsize; em->offset = 0; btrfs_extent_map_set_compression(em, compress_type); } else { btrfs_err(fs_info, "unknown file extent item type %d, inode %llu, offset %llu, " "root %llu", type, btrfs_ino(inode), extent_start, btrfs_root_id(root)); } } /* * Returns the end offset (non inclusive) of the file extent item the given path * points to. If it points to an inline extent, the returned offset is rounded * up to the sector size. */ u64 btrfs_file_extent_end(const struct btrfs_path *path) { const struct extent_buffer *leaf = path->nodes[0]; const int slot = path->slots[0]; struct btrfs_file_extent_item *fi; struct btrfs_key key; u64 end; btrfs_item_key_to_cpu(leaf, &key, slot); ASSERT(key.type == BTRFS_EXTENT_DATA_KEY); fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item); if (btrfs_file_extent_type(leaf, fi) == BTRFS_FILE_EXTENT_INLINE) end = leaf->fs_info->sectorsize; else end = key.offset + btrfs_file_extent_num_bytes(leaf, fi); return end; } |
| 7 7 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CPUSET_H #define _LINUX_CPUSET_H /* * cpuset interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/sched/topology.h> #include <linux/sched/task.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/mm.h> #include <linux/mmu_context.h> #include <linux/jump_label.h> #ifdef CONFIG_CPUSETS /* * Static branch rewrites can happen in an arbitrary order for a given * key. In code paths where we need to loop with read_mems_allowed_begin() and * read_mems_allowed_retry() to get a consistent view of mems_allowed, we need * to ensure that begin() always gets rewritten before retry() in the * disabled -> enabled transition. If not, then if local irqs are disabled * around the loop, we can deadlock since retry() would always be * comparing the latest value of the mems_allowed seqcount against 0 as * begin() still would see cpusets_enabled() as false. The enabled -> disabled * transition should happen in reverse order for the same reasons (want to stop * looking at real value of mems_allowed.sequence in retry() first). */ extern struct static_key_false cpusets_pre_enable_key; extern struct static_key_false cpusets_enabled_key; extern struct static_key_false cpusets_insane_config_key; static inline bool cpusets_enabled(void) { return static_branch_unlikely(&cpusets_enabled_key); } static inline void cpuset_inc(void) { static_branch_inc_cpuslocked(&cpusets_pre_enable_key); static_branch_inc_cpuslocked(&cpusets_enabled_key); } static inline void cpuset_dec(void) { static_branch_dec_cpuslocked(&cpusets_enabled_key); static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } /* * This will get enabled whenever a cpuset configuration is considered * unsupportable in general. E.g. movable only node which cannot satisfy * any non movable allocations (see update_nodemask). Page allocator * needs to make additional checks for those configurations and this * check is meant to guard those checks without any overhead for sane * configurations. */ static inline bool cpusets_insane_config(void) { return static_branch_unlikely(&cpusets_insane_config_key); } extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_force_rebuild(void); extern void cpuset_update_active_cpus(void); extern void inc_dl_tasks_cs(struct task_struct *task); extern void dec_dl_tasks_cs(struct task_struct *task); extern void cpuset_lock(void); extern void cpuset_unlock(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); extern bool cpuset_cpus_allowed_fallback(struct task_struct *p); extern bool cpuset_cpu_is_isolated(int cpu); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask); extern bool cpuset_current_node_allowed(int node, gfp_t gfp_mask); static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return cpuset_current_node_allowed(zone_to_nid(z), gfp_mask); } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { if (cpusets_enabled()) return __cpuset_zone_allowed(z, gfp_mask); return true; } extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2); #ifdef CONFIG_CPUSETS_V1 #define cpuset_memory_pressure_bump() \ do { \ if (cpuset_memory_pressure_enabled) \ __cpuset_memory_pressure_bump(); \ } while (0) extern int cpuset_memory_pressure_enabled; extern void __cpuset_memory_pressure_bump(void); #else static inline void cpuset_memory_pressure_bump(void) { } #endif extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk); extern int cpuset_mem_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { return task_spread_page(current); } extern bool current_cpuset_is_being_rebound(void); extern void dl_rebuild_rd_accounting(void); extern void rebuild_sched_domains(void); extern void cpuset_print_current_mems_allowed(void); extern void cpuset_reset_sched_domains(void); /* * read_mems_allowed_begin is required when making decisions involving * mems_allowed such as during page allocation. mems_allowed can be updated in * parallel and depending on the new value an operation can fail potentially * causing process failure. A retry loop with read_mems_allowed_begin and * read_mems_allowed_retry prevents these artificial failures. */ static inline unsigned int read_mems_allowed_begin(void) { if (!static_branch_unlikely(&cpusets_pre_enable_key)) return 0; return read_seqcount_begin(¤t->mems_allowed_seq); } /* * If this returns true, the operation that took place after * read_mems_allowed_begin may have failed artificially due to a concurrent * update of mems_allowed. It is up to the caller to retry the operation if * appropriate. */ static inline bool read_mems_allowed_retry(unsigned int seq) { if (!static_branch_unlikely(&cpusets_enabled_key)) return false; return read_seqcount_retry(¤t->mems_allowed_seq, seq); } static inline void set_mems_allowed(nodemask_t nodemask) { unsigned long flags; task_lock(current); local_irq_save(flags); write_seqcount_begin(¤t->mems_allowed_seq); current->mems_allowed = nodemask; write_seqcount_end(¤t->mems_allowed_seq); local_irq_restore(flags); task_unlock(current); } extern bool cpuset_node_allowed(struct cgroup *cgroup, int nid); #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } static inline bool cpusets_insane_config(void) { return false; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} static inline void cpuset_force_rebuild(void) { } static inline void cpuset_update_active_cpus(void) { partition_sched_domains(1, NULL, NULL); } static inline void inc_dl_tasks_cs(struct task_struct *task) { } static inline void dec_dl_tasks_cs(struct task_struct *task) { } static inline void cpuset_lock(void) { } static inline void cpuset_unlock(void) { } static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { cpumask_copy(mask, task_cpu_possible_mask(p)); } static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p) { return false; } static inline bool cpuset_cpu_is_isolated(int cpu) { return false; } static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; } #define cpuset_current_mems_allowed (node_states[N_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return 1; } static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask) { return true; } static inline int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return 1; } static inline void cpuset_memory_pressure_bump(void) {} static inline void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { } static inline int cpuset_mem_spread_node(void) { return 0; } static inline int cpuset_do_page_mem_spread(void) { return 0; } static inline bool current_cpuset_is_being_rebound(void) { return false; } static inline void dl_rebuild_rd_accounting(void) { } static inline void rebuild_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_reset_sched_domains(void) { partition_sched_domains(1, NULL, NULL); } static inline void cpuset_print_current_mems_allowed(void) { } static inline void set_mems_allowed(nodemask_t nodemask) { } static inline unsigned int read_mems_allowed_begin(void) { return 0; } static inline bool read_mems_allowed_retry(unsigned int seq) { return false; } static inline bool cpuset_node_allowed(struct cgroup *cgroup, int nid) { return true; } #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright 2002-2005, Instant802 Networks, Inc. * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH * Copyright (C) 2018-2025 Intel Corporation */ #include <linux/module.h> #include <linux/init.h> #include <linux/etherdevice.h> #include <linux/netdevice.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/timer.h> #include <linux/rtnetlink.h> #include <net/mac80211.h> #include "ieee80211_i.h" #include "driver-ops.h" #include "rate.h" #include "sta_info.h" #include "debugfs_sta.h" #include "mesh.h" #include "wme.h" /** * DOC: STA information lifetime rules * * STA info structures (&struct sta_info) are managed in a hash table * for faster lookup and a list for iteration. They are managed using * RCU, i.e. access to the list and hash table is protected by RCU. * * Upon allocating a STA info structure with sta_info_alloc(), the caller * owns that structure. It must then insert it into the hash table using * either sta_info_insert() or sta_info_insert_rcu(); only in the latter * case (which acquires an rcu read section but must not be called from * within one) will the pointer still be valid after the call. Note that * the caller may not do much with the STA info before inserting it; in * particular, it may not start any mesh peer link management or add * encryption keys. * * When the insertion fails (sta_info_insert()) returns non-zero), the * structure will have been freed by sta_info_insert()! * * Station entries are added by mac80211 when you establish a link with a * peer. This means different things for the different type of interfaces * we support. For a regular station this mean we add the AP sta when we * receive an association response from the AP. For IBSS this occurs when * get to know about a peer on the same IBSS. For WDS we add the sta for * the peer immediately upon device open. When using AP mode we add stations * for each respective station upon request from userspace through nl80211. * * In order to remove a STA info structure, various sta_info_destroy_*() * calls are available. * * There is no concept of ownership on a STA entry; each structure is * owned by the global hash table/list until it is removed. All users of * the structure need to be RCU protected so that the structure won't be * freed before they are done using it. */ struct sta_link_alloc { struct link_sta_info info; struct ieee80211_link_sta sta; struct rcu_head rcu_head; }; static const struct rhashtable_params sta_rht_params = { .nelem_hint = 3, /* start small */ .automatic_shrinking = true, .head_offset = offsetof(struct sta_info, hash_node), .key_offset = offsetof(struct sta_info, addr), .key_len = ETH_ALEN, .max_size = CONFIG_MAC80211_STA_HASH_MAX_SIZE, }; static const struct rhashtable_params link_sta_rht_params = { .nelem_hint = 3, /* start small */ .automatic_shrinking = true, .head_offset = offsetof(struct link_sta_info, link_hash_node), .key_offset = offsetof(struct link_sta_info, addr), .key_len = ETH_ALEN, .max_size = CONFIG_MAC80211_STA_HASH_MAX_SIZE, }; static int sta_info_hash_del(struct ieee80211_local *local, struct sta_info *sta) { return rhltable_remove(&local->sta_hash, &sta->hash_node, sta_rht_params); } static int link_sta_info_hash_add(struct ieee80211_local *local, struct link_sta_info *link_sta) { lockdep_assert_wiphy(local->hw.wiphy); return rhltable_insert(&local->link_sta_hash, &link_sta->link_hash_node, link_sta_rht_params); } static int link_sta_info_hash_del(struct ieee80211_local *local, struct link_sta_info *link_sta) { lockdep_assert_wiphy(local->hw.wiphy); return rhltable_remove(&local->link_sta_hash, &link_sta->link_hash_node, link_sta_rht_params); } void ieee80211_purge_sta_txqs(struct sta_info *sta) { struct ieee80211_local *local = sta->sdata->local; int i; for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { struct txq_info *txqi; if (!sta->sta.txq[i]) continue; txqi = to_txq_info(sta->sta.txq[i]); ieee80211_txq_purge(local, txqi); } } static void __cleanup_single_sta(struct sta_info *sta) { int ac, i; struct tid_ampdu_tx *tid_tx; struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct ps_data *ps; if (test_sta_flag(sta, WLAN_STA_PS_STA) || test_sta_flag(sta, WLAN_STA_PS_DRIVER) || test_sta_flag(sta, WLAN_STA_PS_DELIVER)) { if (sta->sdata->vif.type == NL80211_IFTYPE_AP || sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) ps = &sdata->bss->ps; else if (ieee80211_vif_is_mesh(&sdata->vif)) ps = &sdata->u.mesh.ps; else return; clear_sta_flag(sta, WLAN_STA_PS_STA); clear_sta_flag(sta, WLAN_STA_PS_DRIVER); clear_sta_flag(sta, WLAN_STA_PS_DELIVER); atomic_dec(&ps->num_sta_ps); } ieee80211_purge_sta_txqs(sta); for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { local->total_ps_buffered -= skb_queue_len(&sta->ps_tx_buf[ac]); ieee80211_purge_tx_queue(&local->hw, &sta->ps_tx_buf[ac]); ieee80211_purge_tx_queue(&local->hw, &sta->tx_filtered[ac]); } if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_sta_cleanup(sta); cancel_work_sync(&sta->drv_deliver_wk); /* * Destroy aggregation state here. It would be nice to wait for the * driver to finish aggregation stop and then clean up, but for now * drivers have to handle aggregation stop being requested, followed * directly by station destruction. */ for (i = 0; i < IEEE80211_NUM_TIDS; i++) { kfree(sta->ampdu_mlme.tid_start_tx[i]); tid_tx = rcu_dereference_raw(sta->ampdu_mlme.tid_tx[i]); if (!tid_tx) continue; ieee80211_purge_tx_queue(&local->hw, &tid_tx->pending); kfree(tid_tx); } } static void cleanup_single_sta(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; __cleanup_single_sta(sta); sta_info_free(local, sta); } struct rhlist_head *sta_info_hash_lookup(struct ieee80211_local *local, const u8 *addr) { return rhltable_lookup(&local->sta_hash, addr, sta_rht_params); } /* protected by RCU */ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata, const u8 *addr) { struct ieee80211_local *local = sdata->local; struct rhlist_head *tmp; struct sta_info *sta; rcu_read_lock(); for_each_sta_info(local, addr, sta, tmp) { if (sta->sdata == sdata) { rcu_read_unlock(); /* this is safe as the caller must already hold * another rcu read section or the mutex */ return sta; } } rcu_read_unlock(); return NULL; } /* * Get sta info either from the specified interface * or from one of its vlans */ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr) { struct ieee80211_local *local = sdata->local; struct rhlist_head *tmp; struct sta_info *sta; rcu_read_lock(); for_each_sta_info(local, addr, sta, tmp) { if (sta->sdata == sdata || (sta->sdata->bss && sta->sdata->bss == sdata->bss)) { rcu_read_unlock(); /* this is safe as the caller must already hold * another rcu read section or the mutex */ return sta; } } rcu_read_unlock(); return NULL; } struct rhlist_head *link_sta_info_hash_lookup(struct ieee80211_local *local, const u8 *addr) { return rhltable_lookup(&local->link_sta_hash, addr, link_sta_rht_params); } struct link_sta_info * link_sta_info_get_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr) { struct ieee80211_local *local = sdata->local; struct rhlist_head *tmp; struct link_sta_info *link_sta; rcu_read_lock(); for_each_link_sta_info(local, addr, link_sta, tmp) { struct sta_info *sta = link_sta->sta; if (sta->sdata == sdata || (sta->sdata->bss && sta->sdata->bss == sdata->bss)) { rcu_read_unlock(); /* this is safe as the caller must already hold * another rcu read section or the mutex */ return link_sta; } } rcu_read_unlock(); return NULL; } struct ieee80211_sta * ieee80211_find_sta_by_link_addrs(struct ieee80211_hw *hw, const u8 *addr, const u8 *localaddr, unsigned int *link_id) { struct ieee80211_local *local = hw_to_local(hw); struct link_sta_info *link_sta; struct rhlist_head *tmp; for_each_link_sta_info(local, addr, link_sta, tmp) { struct sta_info *sta = link_sta->sta; struct ieee80211_link_data *link; u8 _link_id = link_sta->link_id; if (!localaddr) { if (link_id) *link_id = _link_id; return &sta->sta; } link = rcu_dereference(sta->sdata->link[_link_id]); if (!link) continue; if (memcmp(link->conf->addr, localaddr, ETH_ALEN)) continue; if (link_id) *link_id = _link_id; return &sta->sta; } return NULL; } EXPORT_SYMBOL_GPL(ieee80211_find_sta_by_link_addrs); struct sta_info *sta_info_get_by_addrs(struct ieee80211_local *local, const u8 *sta_addr, const u8 *vif_addr) { struct rhlist_head *tmp; struct sta_info *sta; for_each_sta_info(local, sta_addr, sta, tmp) { if (ether_addr_equal(vif_addr, sta->sdata->vif.addr)) return sta; } return NULL; } struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata, int idx) { struct ieee80211_local *local = sdata->local; struct sta_info *sta; int i = 0; list_for_each_entry_rcu(sta, &local->sta_list, list, lockdep_is_held(&local->hw.wiphy->mtx)) { if (sdata != sta->sdata) continue; if (i < idx) { ++i; continue; } return sta; } return NULL; } static void sta_info_free_link(struct link_sta_info *link_sta) { free_percpu(link_sta->pcpu_rx_stats); } static void sta_accumulate_removed_link_stats(struct sta_info *sta, int link_id) { struct link_sta_info *link_sta = wiphy_dereference(sta->local->hw.wiphy, sta->link[link_id]); struct ieee80211_link_data *link; int ac, tid; u32 thr; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { sta->rem_link_stats.tx_packets += link_sta->tx_stats.packets[ac]; sta->rem_link_stats.tx_bytes += link_sta->tx_stats.bytes[ac]; } sta->rem_link_stats.rx_packets += link_sta->rx_stats.packets; sta->rem_link_stats.rx_bytes += link_sta->rx_stats.bytes; sta->rem_link_stats.tx_retries += link_sta->status_stats.retry_count; sta->rem_link_stats.tx_failed += link_sta->status_stats.retry_failed; sta->rem_link_stats.rx_dropped_misc += link_sta->rx_stats.dropped; thr = sta_get_expected_throughput(sta); if (thr != 0) sta->rem_link_stats.expected_throughput += thr; for (tid = 0; tid < IEEE80211_NUM_TIDS; tid++) { sta->rem_link_stats.pertid_stats.rx_msdu += link_sta->rx_stats.msdu[tid]; sta->rem_link_stats.pertid_stats.tx_msdu += link_sta->tx_stats.msdu[tid]; sta->rem_link_stats.pertid_stats.tx_msdu_retries += link_sta->status_stats.msdu_retries[tid]; sta->rem_link_stats.pertid_stats.tx_msdu_failed += link_sta->status_stats.msdu_failed[tid]; } if (sta->sdata->vif.type == NL80211_IFTYPE_STATION) { link = wiphy_dereference(sta->sdata->local->hw.wiphy, sta->sdata->link[link_id]); if (link) sta->rem_link_stats.beacon_loss_count += link->u.mgd.beacon_loss_count; } } static void sta_remove_link(struct sta_info *sta, unsigned int link_id, bool unhash) { struct sta_link_alloc *alloc = NULL; struct link_sta_info *link_sta; lockdep_assert_wiphy(sta->local->hw.wiphy); link_sta = rcu_access_pointer(sta->link[link_id]); if (WARN_ON(!link_sta)) return; if (unhash) link_sta_info_hash_del(sta->local, link_sta); if (test_sta_flag(sta, WLAN_STA_INSERTED)) ieee80211_link_sta_debugfs_remove(link_sta); if (link_sta != &sta->deflink) alloc = container_of(link_sta, typeof(*alloc), info); sta->sta.valid_links &= ~BIT(link_id); /* store removed link info for accumulated stats consistency */ sta_accumulate_removed_link_stats(sta, link_id); RCU_INIT_POINTER(sta->link[link_id], NULL); RCU_INIT_POINTER(sta->sta.link[link_id], NULL); if (alloc) { sta_info_free_link(&alloc->info); kfree_rcu(alloc, rcu_head); } ieee80211_sta_recalc_aggregates(&sta->sta); } /** * sta_info_free - free STA * * @local: pointer to the global information * @sta: STA info to free * * This function must undo everything done by sta_info_alloc() * that may happen before sta_info_insert(). It may only be * called when sta_info_insert() has not been attempted (and * if that fails, the station is freed anyway.) */ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta) { int i; for (i = 0; i < ARRAY_SIZE(sta->link); i++) { struct link_sta_info *link_sta; link_sta = rcu_access_pointer(sta->link[i]); if (!link_sta) continue; sta_remove_link(sta, i, false); } /* * If we had used sta_info_pre_move_state() then we might not * have gone through the state transitions down again, so do * it here now (and warn if it's inserted). * * This will clear state such as fast TX/RX that may have been * allocated during state transitions. */ while (sta->sta_state > IEEE80211_STA_NONE) { int ret; WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED)); ret = sta_info_move_state(sta, sta->sta_state - 1); if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret)) break; } if (sta->rate_ctrl) rate_control_free_sta(sta); sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr); kfree(to_txq_info(sta->sta.txq[0])); kfree(rcu_dereference_raw(sta->sta.rates)); #ifdef CONFIG_MAC80211_MESH kfree(sta->mesh); #endif sta_info_free_link(&sta->deflink); kfree(sta); } static int sta_info_hash_add(struct ieee80211_local *local, struct sta_info *sta) { return rhltable_insert(&local->sta_hash, &sta->hash_node, sta_rht_params); } static void sta_deliver_ps_frames(struct work_struct *wk) { struct sta_info *sta; sta = container_of(wk, struct sta_info, drv_deliver_wk); if (sta->dead) return; local_bh_disable(); if (!test_sta_flag(sta, WLAN_STA_PS_STA)) ieee80211_sta_ps_deliver_wakeup(sta); else if (test_and_clear_sta_flag(sta, WLAN_STA_PSPOLL)) ieee80211_sta_ps_deliver_poll_response(sta); else if (test_and_clear_sta_flag(sta, WLAN_STA_UAPSD)) ieee80211_sta_ps_deliver_uapsd(sta); local_bh_enable(); } static int sta_prepare_rate_control(struct ieee80211_local *local, struct sta_info *sta, gfp_t gfp) { if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL)) return 0; sta->rate_ctrl = local->rate_ctrl; sta->rate_ctrl_priv = rate_control_alloc_sta(sta->rate_ctrl, sta, gfp); if (!sta->rate_ctrl_priv) return -ENOMEM; return 0; } static int sta_info_alloc_link(struct ieee80211_local *local, struct link_sta_info *link_info, gfp_t gfp) { struct ieee80211_hw *hw = &local->hw; int i; if (ieee80211_hw_check(hw, USES_RSS)) { link_info->pcpu_rx_stats = alloc_percpu_gfp(struct ieee80211_sta_rx_stats, gfp); if (!link_info->pcpu_rx_stats) return -ENOMEM; } link_info->rx_stats.last_rx = jiffies; u64_stats_init(&link_info->rx_stats.syncp); ewma_signal_init(&link_info->rx_stats_avg.signal); ewma_avg_signal_init(&link_info->status_stats.avg_ack_signal); for (i = 0; i < ARRAY_SIZE(link_info->rx_stats_avg.chain_signal); i++) ewma_signal_init(&link_info->rx_stats_avg.chain_signal[i]); link_info->rx_omi_bw_rx = IEEE80211_STA_RX_BW_MAX; link_info->rx_omi_bw_tx = IEEE80211_STA_RX_BW_MAX; link_info->rx_omi_bw_staging = IEEE80211_STA_RX_BW_MAX; /* * Cause (a) warning(s) if IEEE80211_STA_RX_BW_MAX != 320 * or if new values are added to the enum. */ switch (link_info->cur_max_bandwidth) { case IEEE80211_STA_RX_BW_20: case IEEE80211_STA_RX_BW_40: case IEEE80211_STA_RX_BW_80: case IEEE80211_STA_RX_BW_160: case IEEE80211_STA_RX_BW_MAX: /* intentionally nothing */ break; } return 0; } static void sta_info_add_link(struct sta_info *sta, unsigned int link_id, struct link_sta_info *link_info, struct ieee80211_link_sta *link_sta) { link_info->sta = sta; link_info->link_id = link_id; link_info->pub = link_sta; link_info->pub->sta = &sta->sta; link_sta->link_id = link_id; rcu_assign_pointer(sta->link[link_id], link_info); rcu_assign_pointer(sta->sta.link[link_id], link_sta); link_sta->smps_mode = IEEE80211_SMPS_OFF; link_sta->agg.max_rc_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_BA; } static struct sta_info * __sta_info_alloc(struct ieee80211_sub_if_data *sdata, const u8 *addr, int link_id, const u8 *link_addr, gfp_t gfp) { struct ieee80211_local *local = sdata->local; struct ieee80211_hw *hw = &local->hw; struct sta_info *sta; void *txq_data; int size; int i; sta = kzalloc(sizeof(*sta) + hw->sta_data_size, gfp); if (!sta) return NULL; sta->local = local; sta->sdata = sdata; if (sta_info_alloc_link(local, &sta->deflink, gfp)) goto free; if (link_id >= 0) { sta_info_add_link(sta, link_id, &sta->deflink, &sta->sta.deflink); sta->sta.valid_links = BIT(link_id); } else { sta_info_add_link(sta, 0, &sta->deflink, &sta->sta.deflink); } sta->sta.cur = &sta->sta.deflink.agg; spin_lock_init(&sta->lock); spin_lock_init(&sta->ps_lock); INIT_WORK(&sta->drv_deliver_wk, sta_deliver_ps_frames); wiphy_work_init(&sta->ampdu_mlme.work, ieee80211_ba_session_work); #ifdef CONFIG_MAC80211_MESH if (ieee80211_vif_is_mesh(&sdata->vif)) { sta->mesh = kzalloc(sizeof(*sta->mesh), gfp); if (!sta->mesh) goto free; sta->mesh->plink_sta = sta; spin_lock_init(&sta->mesh->plink_lock); if (!sdata->u.mesh.user_mpm) timer_setup(&sta->mesh->plink_timer, mesh_plink_timer, 0); sta->mesh->nonpeer_pm = NL80211_MESH_POWER_ACTIVE; } #endif memcpy(sta->addr, addr, ETH_ALEN); memcpy(sta->sta.addr, addr, ETH_ALEN); memcpy(sta->deflink.addr, link_addr, ETH_ALEN); memcpy(sta->sta.deflink.addr, link_addr, ETH_ALEN); sta->sta.max_rx_aggregation_subframes = local->hw.max_rx_aggregation_subframes; /* TODO link specific alloc and assignments for MLO Link STA */ /* Extended Key ID needs to install keys for keyid 0 and 1 Rx-only. * The Tx path starts to use a key as soon as the key slot ptk_idx * references to is not NULL. To not use the initial Rx-only key * prematurely for Tx initialize ptk_idx to an impossible PTK keyid * which always will refer to a NULL key. */ BUILD_BUG_ON(ARRAY_SIZE(sta->ptk) <= INVALID_PTK_KEYIDX); sta->ptk_idx = INVALID_PTK_KEYIDX; ieee80211_init_frag_cache(&sta->frags); sta->sta_state = IEEE80211_STA_NONE; if (sdata->vif.type == NL80211_IFTYPE_MESH_POINT) sta->amsdu_mesh_control = -1; /* Mark TID as unreserved */ sta->reserved_tid = IEEE80211_TID_UNRESERVED; sta->last_connected = ktime_get_seconds(); size = sizeof(struct txq_info) + ALIGN(hw->txq_data_size, sizeof(void *)); txq_data = kcalloc(ARRAY_SIZE(sta->sta.txq), size, gfp); if (!txq_data) goto free; for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { struct txq_info *txq = txq_data + i * size; /* might not do anything for the (bufferable) MMPDU TXQ */ ieee80211_txq_init(sdata, sta, txq, i); } if (sta_prepare_rate_control(local, sta, gfp)) goto free_txq; sta->airtime_weight = IEEE80211_DEFAULT_AIRTIME_WEIGHT; for (i = 0; i < IEEE80211_NUM_ACS; i++) { skb_queue_head_init(&sta->ps_tx_buf[i]); skb_queue_head_init(&sta->tx_filtered[i]); sta->airtime[i].deficit = sta->airtime_weight; atomic_set(&sta->airtime[i].aql_tx_pending, 0); sta->airtime[i].aql_limit_low = local->aql_txq_limit_low[i]; sta->airtime[i].aql_limit_high = local->aql_txq_limit_high[i]; } for (i = 0; i < IEEE80211_NUM_TIDS; i++) sta->last_seq_ctrl[i] = cpu_to_le16(USHRT_MAX); for (i = 0; i < NUM_NL80211_BANDS; i++) { u32 mandatory = 0; int r; if (!hw->wiphy->bands[i]) continue; switch (i) { case NL80211_BAND_2GHZ: case NL80211_BAND_LC: /* * We use both here, even if we cannot really know for * sure the station will support both, but the only use * for this is when we don't know anything yet and send * management frames, and then we'll pick the lowest * possible rate anyway. * If we don't include _G here, we cannot find a rate * in P2P, and thus trigger the WARN_ONCE() in rate.c */ mandatory = IEEE80211_RATE_MANDATORY_B | IEEE80211_RATE_MANDATORY_G; break; case NL80211_BAND_5GHZ: case NL80211_BAND_6GHZ: mandatory = IEEE80211_RATE_MANDATORY_A; break; case NL80211_BAND_60GHZ: WARN_ON(1); mandatory = 0; break; } for (r = 0; r < hw->wiphy->bands[i]->n_bitrates; r++) { struct ieee80211_rate *rate; rate = &hw->wiphy->bands[i]->bitrates[r]; if (!(rate->flags & mandatory)) continue; sta->sta.deflink.supp_rates[i] |= BIT(r); } } sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); return sta; free_txq: kfree(to_txq_info(sta->sta.txq[0])); free: sta_info_free_link(&sta->deflink); #ifdef CONFIG_MAC80211_MESH kfree(sta->mesh); #endif kfree(sta); return NULL; } struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, const u8 *addr, gfp_t gfp) { return __sta_info_alloc(sdata, addr, -1, addr, gfp); } struct sta_info *sta_info_alloc_with_link(struct ieee80211_sub_if_data *sdata, const u8 *mld_addr, unsigned int link_id, const u8 *link_addr, gfp_t gfp) { return __sta_info_alloc(sdata, mld_addr, link_id, link_addr, gfp); } static int sta_info_insert_check(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; lockdep_assert_wiphy(sdata->local->hw.wiphy); /* * Can't be a WARN_ON because it can be triggered through a race: * something inserts a STA (on one CPU) without holding the RTNL * and another CPU turns off the net device. */ if (unlikely(!ieee80211_sdata_running(sdata))) return -ENETDOWN; if (WARN_ON(ether_addr_equal(sta->sta.addr, sdata->vif.addr) || !is_valid_ether_addr(sta->sta.addr))) return -EINVAL; /* The RCU read lock is required by rhashtable due to * asynchronous resize/rehash. We also require the mutex * for correctness. */ rcu_read_lock(); if (ieee80211_hw_check(&sdata->local->hw, NEEDS_UNIQUE_STA_ADDR) && ieee80211_find_sta_by_ifaddr(&sdata->local->hw, sta->addr, NULL)) { rcu_read_unlock(); return -ENOTUNIQ; } rcu_read_unlock(); return 0; } static int sta_info_insert_drv_state(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, struct sta_info *sta) { enum ieee80211_sta_state state; int err = 0; for (state = IEEE80211_STA_NOTEXIST; state < sta->sta_state; state++) { err = drv_sta_state(local, sdata, sta, state, state + 1); if (err) break; } if (!err) { /* * Drivers using legacy sta_add/sta_remove callbacks only * get uploaded set to true after sta_add is called. */ if (!local->ops->sta_add) sta->uploaded = true; return 0; } if (sdata->vif.type == NL80211_IFTYPE_ADHOC) { sdata_info(sdata, "failed to move IBSS STA %pM to state %d (%d) - keeping it anyway\n", sta->sta.addr, state + 1, err); err = 0; } /* unwind on error */ for (; state > IEEE80211_STA_NOTEXIST; state--) WARN_ON(drv_sta_state(local, sdata, sta, state, state - 1)); return err; } static void ieee80211_recalc_p2p_go_ps_allowed(struct ieee80211_sub_if_data *sdata) { struct ieee80211_local *local = sdata->local; bool allow_p2p_go_ps = sdata->vif.p2p; struct sta_info *sta; rcu_read_lock(); list_for_each_entry_rcu(sta, &local->sta_list, list) { if (sdata != sta->sdata || !test_sta_flag(sta, WLAN_STA_ASSOC)) continue; if (!sta->sta.support_p2p_ps) { allow_p2p_go_ps = false; break; } } rcu_read_unlock(); if (allow_p2p_go_ps != sdata->vif.bss_conf.allow_p2p_go_ps) { sdata->vif.bss_conf.allow_p2p_go_ps = allow_p2p_go_ps; ieee80211_link_info_change_notify(sdata, &sdata->deflink, BSS_CHANGED_P2P_PS); } } static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) { struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; struct station_info *sinfo = NULL; int err = 0; lockdep_assert_wiphy(local->hw.wiphy); /* check if STA exists already */ if (sta_info_get_bss(sdata, sta->sta.addr)) { err = -EEXIST; goto out_cleanup; } sinfo = kzalloc(sizeof(struct station_info), GFP_KERNEL); if (!sinfo) { err = -ENOMEM; goto out_cleanup; } local->num_sta++; local->sta_generation++; smp_mb(); /* simplify things and don't accept BA sessions yet */ set_sta_flag(sta, WLAN_STA_BLOCK_BA); /* make the station visible */ err = sta_info_hash_add(local, sta); if (err) goto out_drop_sta; if (sta->sta.valid_links) { err = link_sta_info_hash_add(local, &sta->deflink); if (err) { sta_info_hash_del(local, sta); goto out_drop_sta; } } list_add_tail_rcu(&sta->list, &local->sta_list); /* update channel context before notifying the driver about state * change, this enables driver using the updated channel context right away. */ if (sta->sta_state >= IEEE80211_STA_ASSOC) { ieee80211_recalc_min_chandef(sta->sdata, -1); if (!sta->sta.support_p2p_ps) ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); } /* notify driver */ err = sta_info_insert_drv_state(local, sdata, sta); if (err) goto out_remove; set_sta_flag(sta, WLAN_STA_INSERTED); /* accept BA sessions now */ clear_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_sta_debugfs_add(sta); rate_control_add_sta_debugfs(sta); if (sta->sta.valid_links) { int i; for (i = 0; i < ARRAY_SIZE(sta->link); i++) { struct link_sta_info *link_sta; link_sta = rcu_dereference_protected(sta->link[i], lockdep_is_held(&local->hw.wiphy->mtx)); if (!link_sta) continue; ieee80211_link_sta_debugfs_add(link_sta); if (sdata->vif.active_links & BIT(i)) ieee80211_link_sta_debugfs_drv_add(link_sta); } } else { ieee80211_link_sta_debugfs_add(&sta->deflink); ieee80211_link_sta_debugfs_drv_add(&sta->deflink); } sinfo->generation = local->sta_generation; cfg80211_new_sta(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); kfree(sinfo); sta_dbg(sdata, "Inserted STA %pM\n", sta->sta.addr); /* move reference to rcu-protected */ rcu_read_lock(); if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_accept_plinks_update(sdata); ieee80211_check_fast_xmit(sta); return 0; out_remove: if (sta->sta.valid_links) link_sta_info_hash_del(local, &sta->deflink); sta_info_hash_del(local, sta); list_del_rcu(&sta->list); out_drop_sta: local->num_sta--; synchronize_net(); out_cleanup: cleanup_single_sta(sta); kfree(sinfo); rcu_read_lock(); return err; } int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU) { struct ieee80211_local *local = sta->local; int err; might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); err = sta_info_insert_check(sta); if (err) { sta_info_free(local, sta); rcu_read_lock(); return err; } return sta_info_insert_finish(sta); } int sta_info_insert(struct sta_info *sta) { int err = sta_info_insert_rcu(sta); rcu_read_unlock(); return err; } static inline void __bss_tim_set(u8 *tim, u16 id) { /* * This format has been mandated by the IEEE specifications, * so this line may not be changed to use the __set_bit() format. */ tim[id / 8] |= (1 << (id % 8)); } static inline void __bss_tim_clear(u8 *tim, u16 id) { /* * This format has been mandated by the IEEE specifications, * so this line may not be changed to use the __clear_bit() format. */ tim[id / 8] &= ~(1 << (id % 8)); } static inline bool __bss_tim_get(u8 *tim, u16 id) { /* * This format has been mandated by the IEEE specifications, * so this line may not be changed to use the test_bit() format. */ return tim[id / 8] & (1 << (id % 8)); } static unsigned long ieee80211_tids_for_ac(int ac) { /* If we ever support TIDs > 7, this obviously needs to be adjusted */ switch (ac) { case IEEE80211_AC_VO: return BIT(6) | BIT(7); case IEEE80211_AC_VI: return BIT(4) | BIT(5); case IEEE80211_AC_BE: return BIT(0) | BIT(3); case IEEE80211_AC_BK: return BIT(1) | BIT(2); default: WARN_ON(1); return 0; } } static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending) { struct ieee80211_local *local = sta->local; struct ps_data *ps; bool indicate_tim = false; u8 ignore_for_tim = sta->sta.uapsd_queues; int ac; u16 id = sta->sta.aid; if (sta->sdata->vif.type == NL80211_IFTYPE_AP || sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) { if (WARN_ON_ONCE(!sta->sdata->bss)) return; ps = &sta->sdata->bss->ps; #ifdef CONFIG_MAC80211_MESH } else if (ieee80211_vif_is_mesh(&sta->sdata->vif)) { ps = &sta->sdata->u.mesh.ps; #endif } else { return; } /* No need to do anything if the driver does all */ if (ieee80211_hw_check(&local->hw, AP_LINK_PS) && !local->ops->set_tim) return; if (sta->dead) goto done; /* * If all ACs are delivery-enabled then we should build * the TIM bit for all ACs anyway; if only some are then * we ignore those and build the TIM bit using only the * non-enabled ones. */ if (ignore_for_tim == BIT(IEEE80211_NUM_ACS) - 1) ignore_for_tim = 0; if (ignore_pending) ignore_for_tim = BIT(IEEE80211_NUM_ACS) - 1; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { unsigned long tids; if (ignore_for_tim & ieee80211_ac_to_qos_mask[ac]) continue; indicate_tim |= !skb_queue_empty(&sta->tx_filtered[ac]) || !skb_queue_empty(&sta->ps_tx_buf[ac]); if (indicate_tim) break; tids = ieee80211_tids_for_ac(ac); indicate_tim |= sta->driver_buffered_tids & tids; indicate_tim |= sta->txq_buffered_tids & tids; } done: spin_lock_bh(&local->tim_lock); if (indicate_tim == __bss_tim_get(ps->tim, id)) goto out_unlock; if (indicate_tim) __bss_tim_set(ps->tim, id); else __bss_tim_clear(ps->tim, id); if (local->ops->set_tim && !WARN_ON(sta->dead)) { local->tim_in_locked_section = true; drv_set_tim(local, &sta->sta, indicate_tim); local->tim_in_locked_section = false; } out_unlock: spin_unlock_bh(&local->tim_lock); } void sta_info_recalc_tim(struct sta_info *sta) { __sta_info_recalc_tim(sta, false); } static bool sta_info_buffer_expired(struct sta_info *sta, struct sk_buff *skb) { struct ieee80211_tx_info *info; int timeout; if (!skb) return false; info = IEEE80211_SKB_CB(skb); /* Timeout: (2 * listen_interval * beacon_int * 1024 / 1000000) sec */ timeout = (sta->listen_interval * sta->sdata->vif.bss_conf.beacon_int * 32 / 15625) * HZ; if (timeout < STA_TX_BUFFER_EXPIRE) timeout = STA_TX_BUFFER_EXPIRE; return time_after(jiffies, info->control.jiffies + timeout); } static bool sta_info_cleanup_expire_buffered_ac(struct ieee80211_local *local, struct sta_info *sta, int ac) { unsigned long flags; struct sk_buff *skb; /* * First check for frames that should expire on the filtered * queue. Frames here were rejected by the driver and are on * a separate queue to avoid reordering with normal PS-buffered * frames. They also aren't accounted for right now in the * total_ps_buffered counter. */ for (;;) { spin_lock_irqsave(&sta->tx_filtered[ac].lock, flags); skb = skb_peek(&sta->tx_filtered[ac]); if (sta_info_buffer_expired(sta, skb)) skb = __skb_dequeue(&sta->tx_filtered[ac]); else skb = NULL; spin_unlock_irqrestore(&sta->tx_filtered[ac].lock, flags); /* * Frames are queued in order, so if this one * hasn't expired yet we can stop testing. If * we actually reached the end of the queue we * also need to stop, of course. */ if (!skb) break; ieee80211_free_txskb(&local->hw, skb); } /* * Now also check the normal PS-buffered queue, this will * only find something if the filtered queue was emptied * since the filtered frames are all before the normal PS * buffered frames. */ for (;;) { spin_lock_irqsave(&sta->ps_tx_buf[ac].lock, flags); skb = skb_peek(&sta->ps_tx_buf[ac]); if (sta_info_buffer_expired(sta, skb)) skb = __skb_dequeue(&sta->ps_tx_buf[ac]); else skb = NULL; spin_unlock_irqrestore(&sta->ps_tx_buf[ac].lock, flags); /* * frames are queued in order, so if this one * hasn't expired yet (or we reached the end of * the queue) we can stop testing */ if (!skb) break; local->total_ps_buffered--; ps_dbg(sta->sdata, "Buffered frame expired (STA %pM)\n", sta->sta.addr); ieee80211_free_txskb(&local->hw, skb); } /* * Finally, recalculate the TIM bit for this station -- it might * now be clear because the station was too slow to retrieve its * frames. */ sta_info_recalc_tim(sta); /* * Return whether there are any frames still buffered, this is * used to check whether the cleanup timer still needs to run, * if there are no frames we don't need to rearm the timer. */ return !(skb_queue_empty(&sta->ps_tx_buf[ac]) && skb_queue_empty(&sta->tx_filtered[ac])); } static bool sta_info_cleanup_expire_buffered(struct ieee80211_local *local, struct sta_info *sta) { bool have_buffered = false; int ac; /* This is only necessary for stations on BSS/MBSS interfaces */ if (!sta->sdata->bss && !ieee80211_vif_is_mesh(&sta->sdata->vif)) return false; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) have_buffered |= sta_info_cleanup_expire_buffered_ac(local, sta, ac); return have_buffered; } static int __must_check __sta_info_destroy_part1(struct sta_info *sta) { struct ieee80211_local *local; struct ieee80211_sub_if_data *sdata; int ret, i; might_sleep(); if (!sta) return -ENOENT; local = sta->local; sdata = sta->sdata; lockdep_assert_wiphy(local->hw.wiphy); /* * Before removing the station from the driver and * rate control, it might still start new aggregation * sessions -- block that to make sure the tear-down * will be sufficient. */ set_sta_flag(sta, WLAN_STA_BLOCK_BA); ieee80211_sta_tear_down_BA_sessions(sta, AGG_STOP_DESTROY_STA); /* * Before removing the station from the driver there might be pending * rx frames on RSS queues sent prior to the disassociation - wait for * all such frames to be processed. */ drv_sync_rx_queues(local, sta); for (i = 0; i < ARRAY_SIZE(sta->link); i++) { struct link_sta_info *link_sta; if (!(sta->sta.valid_links & BIT(i))) continue; link_sta = rcu_dereference_protected(sta->link[i], lockdep_is_held(&local->hw.wiphy->mtx)); link_sta_info_hash_del(local, link_sta); } ret = sta_info_hash_del(local, sta); if (WARN_ON(ret)) return ret; /* * for TDLS peers, make sure to return to the base channel before * removal. */ if (test_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL)) { drv_tdls_cancel_channel_switch(local, sdata, &sta->sta); clear_sta_flag(sta, WLAN_STA_TDLS_OFF_CHANNEL); } list_del_rcu(&sta->list); sta->removed = true; if (sta->uploaded) drv_sta_pre_rcu_remove(local, sta->sdata, sta); if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN && rcu_access_pointer(sdata->u.vlan.sta) == sta) RCU_INIT_POINTER(sdata->u.vlan.sta, NULL); return 0; } static int _sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state, bool recalc) { struct ieee80211_local *local = sta->local; might_sleep(); if (sta->sta_state == new_state) return 0; /* check allowed transitions first */ switch (new_state) { case IEEE80211_STA_NONE: if (sta->sta_state != IEEE80211_STA_AUTH) return -EINVAL; break; case IEEE80211_STA_AUTH: if (sta->sta_state != IEEE80211_STA_NONE && sta->sta_state != IEEE80211_STA_ASSOC) return -EINVAL; break; case IEEE80211_STA_ASSOC: if (sta->sta_state != IEEE80211_STA_AUTH && sta->sta_state != IEEE80211_STA_AUTHORIZED) return -EINVAL; break; case IEEE80211_STA_AUTHORIZED: if (sta->sta_state != IEEE80211_STA_ASSOC) return -EINVAL; break; default: WARN(1, "invalid state %d", new_state); return -EINVAL; } sta_dbg(sta->sdata, "moving STA %pM to state %d\n", sta->sta.addr, new_state); /* notify the driver before the actual changes so it can * fail the transition if the state is increasing. * The driver is required not to fail when the transition * is decreasing the state, so first, do all the preparation * work and only then, notify the driver. */ if (new_state > sta->sta_state && test_sta_flag(sta, WLAN_STA_INSERTED)) { int err = drv_sta_state(sta->local, sta->sdata, sta, sta->sta_state, new_state); if (err) return err; } /* reflect the change in all state variables */ switch (new_state) { case IEEE80211_STA_NONE: if (sta->sta_state == IEEE80211_STA_AUTH) clear_bit(WLAN_STA_AUTH, &sta->_flags); break; case IEEE80211_STA_AUTH: if (sta->sta_state == IEEE80211_STA_NONE) { set_bit(WLAN_STA_AUTH, &sta->_flags); } else if (sta->sta_state == IEEE80211_STA_ASSOC) { clear_bit(WLAN_STA_ASSOC, &sta->_flags); if (recalc) { ieee80211_recalc_min_chandef(sta->sdata, -1); if (!sta->sta.support_p2p_ps) ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); } } break; case IEEE80211_STA_ASSOC: if (sta->sta_state == IEEE80211_STA_AUTH) { set_bit(WLAN_STA_ASSOC, &sta->_flags); sta->assoc_at = ktime_get_boottime_ns(); if (recalc) { ieee80211_recalc_min_chandef(sta->sdata, -1); if (!sta->sta.support_p2p_ps) ieee80211_recalc_p2p_go_ps_allowed(sta->sdata); } } else if (sta->sta_state == IEEE80211_STA_AUTHORIZED) { ieee80211_vif_dec_num_mcast(sta->sdata); clear_bit(WLAN_STA_AUTHORIZED, &sta->_flags); /* * If we have encryption offload, flush (station) queues * (after ensuring concurrent TX completed) so we won't * transmit anything later unencrypted if/when keys are * also removed, which might otherwise happen depending * on how the hardware offload works. */ if (local->ops->set_key) { synchronize_net(); if (local->ops->flush_sta) drv_flush_sta(local, sta->sdata, sta); else ieee80211_flush_queues(local, sta->sdata, false); } ieee80211_clear_fast_xmit(sta); ieee80211_clear_fast_rx(sta); } break; case IEEE80211_STA_AUTHORIZED: if (sta->sta_state == IEEE80211_STA_ASSOC) { ieee80211_vif_inc_num_mcast(sta->sdata); set_bit(WLAN_STA_AUTHORIZED, &sta->_flags); ieee80211_check_fast_xmit(sta); ieee80211_check_fast_rx(sta); } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN || sta->sdata->vif.type == NL80211_IFTYPE_AP) cfg80211_send_layer2_update(sta->sdata->dev, sta->sta.addr); break; default: break; } if (new_state < sta->sta_state && test_sta_flag(sta, WLAN_STA_INSERTED)) { int err = drv_sta_state(sta->local, sta->sdata, sta, sta->sta_state, new_state); WARN_ONCE(err, "Driver is not allowed to fail if the sta_state is transitioning down the list: %d\n", err); } sta->sta_state = new_state; return 0; } int sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state) { return _sta_info_move_state(sta, new_state, true); } static void __sta_info_destroy_part2(struct sta_info *sta, bool recalc) { struct ieee80211_local *local = sta->local; struct ieee80211_sub_if_data *sdata = sta->sdata; struct station_info *sinfo; int ret; /* * NOTE: This assumes at least synchronize_net() was done * after _part1 and before _part2! */ /* * There's a potential race in _part1 where we set WLAN_STA_BLOCK_BA * but someone might have just gotten past a check, and not yet into * queuing the work/creating the data/etc. * * Do another round of destruction so that the worker is certainly * canceled before we later free the station. * * Since this is after synchronize_rcu()/synchronize_net() we're now * certain that nobody can actually hold a reference to the STA and * be calling e.g. ieee80211_start_tx_ba_session(). */ ieee80211_sta_tear_down_BA_sessions(sta, AGG_STOP_DESTROY_STA); might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); if (sta->sta_state == IEEE80211_STA_AUTHORIZED) { ret = _sta_info_move_state(sta, IEEE80211_STA_ASSOC, recalc); WARN_ON_ONCE(ret); } /* now keys can no longer be reached */ ieee80211_free_sta_keys(local, sta); /* disable TIM bit - last chance to tell driver */ __sta_info_recalc_tim(sta, true); sta->dead = true; local->num_sta--; local->sta_generation++; while (sta->sta_state > IEEE80211_STA_NONE) { ret = _sta_info_move_state(sta, sta->sta_state - 1, recalc); if (ret) { WARN_ON_ONCE(1); break; } } if (sta->uploaded) { ret = drv_sta_state(local, sdata, sta, IEEE80211_STA_NONE, IEEE80211_STA_NOTEXIST); WARN_ON_ONCE(ret != 0); } sta_dbg(sdata, "Removed STA %pM\n", sta->sta.addr); sinfo = kzalloc(sizeof(*sinfo), GFP_KERNEL); if (sinfo) sta_set_sinfo(sta, sinfo, true); cfg80211_del_sta_sinfo(sdata->dev, sta->sta.addr, sinfo, GFP_KERNEL); kfree(sinfo); ieee80211_sta_debugfs_remove(sta); ieee80211_destroy_frag_cache(&sta->frags); cleanup_single_sta(sta); } int __must_check __sta_info_destroy(struct sta_info *sta) { int err = __sta_info_destroy_part1(sta); if (err) return err; synchronize_net(); __sta_info_destroy_part2(sta, true); return 0; } int sta_info_destroy_addr(struct ieee80211_sub_if_data *sdata, const u8 *addr) { struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); sta = sta_info_get(sdata, addr); return __sta_info_destroy(sta); } int sta_info_destroy_addr_bss(struct ieee80211_sub_if_data *sdata, const u8 *addr) { struct sta_info *sta; lockdep_assert_wiphy(sdata->local->hw.wiphy); sta = sta_info_get_bss(sdata, addr); return __sta_info_destroy(sta); } static void sta_info_cleanup(struct timer_list *t) { struct ieee80211_local *local = timer_container_of(local, t, sta_cleanup); struct sta_info *sta; bool timer_needed = false; rcu_read_lock(); list_for_each_entry_rcu(sta, &local->sta_list, list) if (sta_info_cleanup_expire_buffered(local, sta)) timer_needed = true; rcu_read_unlock(); if (local->quiescing) return; if (!timer_needed) return; mod_timer(&local->sta_cleanup, round_jiffies(jiffies + STA_INFO_CLEANUP_INTERVAL)); } int sta_info_init(struct ieee80211_local *local) { int err; err = rhltable_init(&local->sta_hash, &sta_rht_params); if (err) return err; err = rhltable_init(&local->link_sta_hash, &link_sta_rht_params); if (err) { rhltable_destroy(&local->sta_hash); return err; } spin_lock_init(&local->tim_lock); INIT_LIST_HEAD(&local->sta_list); timer_setup(&local->sta_cleanup, sta_info_cleanup, 0); return 0; } void sta_info_stop(struct ieee80211_local *local) { timer_delete_sync(&local->sta_cleanup); rhltable_destroy(&local->sta_hash); rhltable_destroy(&local->link_sta_hash); } int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans, int link_id, struct sta_info *do_not_flush_sta) { struct ieee80211_local *local = sdata->local; struct sta_info *sta, *tmp; LIST_HEAD(free_list); int ret = 0; might_sleep(); lockdep_assert_wiphy(local->hw.wiphy); WARN_ON(vlans && sdata->vif.type != NL80211_IFTYPE_AP); WARN_ON(vlans && !sdata->bss); list_for_each_entry_safe(sta, tmp, &local->sta_list, list) { if (sdata != sta->sdata && (!vlans || sdata->bss != sta->sdata->bss)) continue; if (sta == do_not_flush_sta) continue; if (link_id >= 0 && sta->sta.valid_links && !(sta->sta.valid_links & BIT(link_id))) continue; if (!WARN_ON(__sta_info_destroy_part1(sta))) list_add(&sta->free_list, &free_list); ret++; } if (!list_empty(&free_list)) { bool support_p2p_ps = true; synchronize_net(); list_for_each_entry_safe(sta, tmp, &free_list, free_list) { if (!sta->sta.support_p2p_ps) support_p2p_ps = false; __sta_info_destroy_part2(sta, false); } ieee80211_recalc_min_chandef(sdata, -1); if (!support_p2p_ps) ieee80211_recalc_p2p_go_ps_allowed(sdata); } return ret; } void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata, unsigned long exp_time) { struct ieee80211_local *local = sdata->local; struct sta_info *sta, *tmp; lockdep_assert_wiphy(local->hw.wiphy); list_for_each_entry_safe(sta, tmp, &local->sta_list, list) { unsigned long last_active = ieee80211_sta_last_active(sta, -1); if (sdata != sta->sdata) continue; if (time_is_before_jiffies(last_active + exp_time)) { sta_dbg(sta->sdata, "expiring inactive STA %pM\n", sta->sta.addr); if (ieee80211_vif_is_mesh(&sdata->vif) && test_sta_flag(sta, WLAN_STA_PS_STA)) atomic_dec(&sdata->u.mesh.ps.num_sta_ps); WARN_ON(__sta_info_destroy(sta)); } } } struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw, const u8 *addr, const u8 *localaddr) { struct ieee80211_local *local = hw_to_local(hw); struct rhlist_head *tmp; struct sta_info *sta; /* * Just return a random station if localaddr is NULL * ... first in list. */ for_each_sta_info(local, addr, sta, tmp) { if (localaddr && !ether_addr_equal(sta->sdata->vif.addr, localaddr)) continue; if (!sta->uploaded) return NULL; return &sta->sta; } return NULL; } EXPORT_SYMBOL_GPL(ieee80211_find_sta_by_ifaddr); struct ieee80211_sta *ieee80211_find_sta(struct ieee80211_vif *vif, const u8 *addr) { struct sta_info *sta; if (!vif) return NULL; sta = sta_info_get_bss(vif_to_sdata(vif), addr); if (!sta) return NULL; if (!sta->uploaded) return NULL; return &sta->sta; } EXPORT_SYMBOL(ieee80211_find_sta); /* powersave support code */ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct sk_buff_head pending; int filtered = 0, buffered = 0, ac, i; unsigned long flags; struct ps_data *ps; if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap); if (sdata->vif.type == NL80211_IFTYPE_AP) ps = &sdata->bss->ps; else if (ieee80211_vif_is_mesh(&sdata->vif)) ps = &sdata->u.mesh.ps; else return; clear_sta_flag(sta, WLAN_STA_SP); BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1); sta->driver_buffered_tids = 0; sta->txq_buffered_tids = 0; if (!ieee80211_hw_check(&local->hw, AP_LINK_PS)) drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta); for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) { if (!sta->sta.txq[i] || !txq_has_queue(sta->sta.txq[i])) continue; schedule_and_wake_txq(local, to_txq_info(sta->sta.txq[i])); } skb_queue_head_init(&pending); /* sync with ieee80211_tx_h_unicast_ps_buf */ spin_lock_bh(&sta->ps_lock); /* Send all buffered frames to the station */ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { int count = skb_queue_len(&pending), tmp; spin_lock_irqsave(&sta->tx_filtered[ac].lock, flags); skb_queue_splice_tail_init(&sta->tx_filtered[ac], &pending); spin_unlock_irqrestore(&sta->tx_filtered[ac].lock, flags); tmp = skb_queue_len(&pending); filtered += tmp - count; count = tmp; spin_lock_irqsave(&sta->ps_tx_buf[ac].lock, flags); skb_queue_splice_tail_init(&sta->ps_tx_buf[ac], &pending); spin_unlock_irqrestore(&sta->ps_tx_buf[ac].lock, flags); tmp = skb_queue_len(&pending); buffered += tmp - count; } ieee80211_add_pending_skbs(local, &pending); /* now we're no longer in the deliver code */ clear_sta_flag(sta, WLAN_STA_PS_DELIVER); /* The station might have polled and then woken up before we responded, * so clear these flags now to avoid them sticking around. */ clear_sta_flag(sta, WLAN_STA_PSPOLL); clear_sta_flag(sta, WLAN_STA_UAPSD); spin_unlock_bh(&sta->ps_lock); atomic_dec(&ps->num_sta_ps); local->total_ps_buffered -= buffered; sta_info_recalc_tim(sta); ps_dbg(sdata, "STA %pM aid %d sending %d filtered/%d PS frames since STA woke up\n", sta->sta.addr, sta->sta.aid, filtered, buffered); ieee80211_check_fast_xmit(sta); } static void ieee80211_send_null_response(struct sta_info *sta, int tid, enum ieee80211_frame_release_type reason, bool call_driver, bool more_data) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct ieee80211_qos_hdr *nullfunc; struct sk_buff *skb; int size = sizeof(*nullfunc); __le16 fc; bool qos = sta->sta.wme; struct ieee80211_tx_info *info; struct ieee80211_chanctx_conf *chanctx_conf; 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) return; 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; skb->priority = tid; skb_set_queue_mapping(skb, ieee802_1d_to_ac[tid]); if (qos) { nullfunc->qos_ctrl = cpu_to_le16(tid); if (reason == IEEE80211_FRAME_RELEASE_UAPSD) { nullfunc->qos_ctrl |= cpu_to_le16(IEEE80211_QOS_CTL_EOSP); if (more_data) nullfunc->frame_control |= cpu_to_le16(IEEE80211_FCTL_MOREDATA); } } info = IEEE80211_SKB_CB(skb); /* * Tell TX path to send this frame even though the * STA may still remain is PS mode after this frame * exchange. Also set EOSP to indicate this packet * ends the poll/service period. */ info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER | IEEE80211_TX_STATUS_EOSP | IEEE80211_TX_CTL_REQ_TX_STATUS; info->control.flags |= IEEE80211_TX_CTRL_PS_RESPONSE; if (call_driver) drv_allow_buffered_frames(local, sta, BIT(tid), 1, reason, false); skb->dev = sdata->dev; rcu_read_lock(); chanctx_conf = rcu_dereference(sdata->vif.bss_conf.chanctx_conf); if (WARN_ON(!chanctx_conf)) { rcu_read_unlock(); kfree_skb(skb); return; } info->band = chanctx_conf->def.chan->band; ieee80211_xmit(sdata, sta, skb); rcu_read_unlock(); } static int find_highest_prio_tid(unsigned long tids) { /* lower 3 TIDs aren't ordered perfectly */ if (tids & 0xF8) return fls(tids) - 1; /* TID 0 is BE just like TID 3 */ if (tids & BIT(0)) return 0; return fls(tids) - 1; } /* Indicates if the MORE_DATA bit should be set in the last * frame obtained by ieee80211_sta_ps_get_frames. * Note that driver_release_tids is relevant only if * reason = IEEE80211_FRAME_RELEASE_PSPOLL */ static bool ieee80211_sta_ps_more_data(struct sta_info *sta, u8 ignored_acs, enum ieee80211_frame_release_type reason, unsigned long driver_release_tids) { int ac; /* If the driver has data on more than one TID then * certainly there's more data if we release just a * single frame now (from a single TID). This will * only happen for PS-Poll. */ if (reason == IEEE80211_FRAME_RELEASE_PSPOLL && hweight16(driver_release_tids) > 1) return true; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { if (ignored_acs & ieee80211_ac_to_qos_mask[ac]) continue; if (!skb_queue_empty(&sta->tx_filtered[ac]) || !skb_queue_empty(&sta->ps_tx_buf[ac])) return true; } return false; } static void ieee80211_sta_ps_get_frames(struct sta_info *sta, int n_frames, u8 ignored_acs, enum ieee80211_frame_release_type reason, struct sk_buff_head *frames, unsigned long *driver_release_tids) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; int ac; /* Get response frame(s) and more data bit for the last one. */ for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { unsigned long tids; if (ignored_acs & ieee80211_ac_to_qos_mask[ac]) continue; tids = ieee80211_tids_for_ac(ac); /* if we already have frames from software, then we can't also * release from hardware queues */ if (skb_queue_empty(frames)) { *driver_release_tids |= sta->driver_buffered_tids & tids; *driver_release_tids |= sta->txq_buffered_tids & tids; } if (!*driver_release_tids) { struct sk_buff *skb; while (n_frames > 0) { skb = skb_dequeue(&sta->tx_filtered[ac]); if (!skb) { skb = skb_dequeue( &sta->ps_tx_buf[ac]); if (skb) local->total_ps_buffered--; } if (!skb) break; n_frames--; __skb_queue_tail(frames, skb); } } /* If we have more frames buffered on this AC, then abort the * loop since we can't send more data from other ACs before * the buffered frames from this. */ if (!skb_queue_empty(&sta->tx_filtered[ac]) || !skb_queue_empty(&sta->ps_tx_buf[ac])) break; } } static void ieee80211_sta_ps_deliver_response(struct sta_info *sta, int n_frames, u8 ignored_acs, enum ieee80211_frame_release_type reason) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; unsigned long driver_release_tids = 0; struct sk_buff_head frames; bool more_data; /* Service or PS-Poll period starts */ set_sta_flag(sta, WLAN_STA_SP); __skb_queue_head_init(&frames); ieee80211_sta_ps_get_frames(sta, n_frames, ignored_acs, reason, &frames, &driver_release_tids); more_data = ieee80211_sta_ps_more_data(sta, ignored_acs, reason, driver_release_tids); if (driver_release_tids && reason == IEEE80211_FRAME_RELEASE_PSPOLL) driver_release_tids = BIT(find_highest_prio_tid(driver_release_tids)); if (skb_queue_empty(&frames) && !driver_release_tids) { int tid, ac; /* * For PS-Poll, this can only happen due to a race condition * when we set the TIM bit and the station notices it, but * before it can poll for the frame we expire it. * * For uAPSD, this is said in the standard (11.2.1.5 h): * At each unscheduled SP for a non-AP STA, the AP shall * attempt to transmit at least one MSDU or MMPDU, but no * more than the value specified in the Max SP Length field * in the QoS Capability element from delivery-enabled ACs, * that are destined for the non-AP STA. * * Since we have no other MSDU/MMPDU, transmit a QoS null frame. */ /* This will evaluate to 1, 3, 5 or 7. */ for (ac = IEEE80211_AC_VO; ac < IEEE80211_NUM_ACS; ac++) if (!(ignored_acs & ieee80211_ac_to_qos_mask[ac])) break; tid = 7 - 2 * ac; ieee80211_send_null_response(sta, tid, reason, true, false); } else if (!driver_release_tids) { struct sk_buff_head pending; struct sk_buff *skb; int num = 0; u16 tids = 0; bool need_null = false; skb_queue_head_init(&pending); while ((skb = __skb_dequeue(&frames))) { struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (void *) skb->data; u8 *qoshdr = NULL; num++; /* * Tell TX path to send this frame even though the * STA may still remain is PS mode after this frame * exchange. */ info->flags |= IEEE80211_TX_CTL_NO_PS_BUFFER; info->control.flags |= IEEE80211_TX_CTRL_PS_RESPONSE; /* * Use MoreData flag to indicate whether there are * more buffered frames for this STA */ if (more_data || !skb_queue_empty(&frames)) hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_MOREDATA); else hdr->frame_control &= cpu_to_le16(~IEEE80211_FCTL_MOREDATA); if (ieee80211_is_data_qos(hdr->frame_control) || ieee80211_is_qos_nullfunc(hdr->frame_control)) qoshdr = ieee80211_get_qos_ctl(hdr); tids |= BIT(skb->priority); __skb_queue_tail(&pending, skb); /* end service period after last frame or add one */ if (!skb_queue_empty(&frames)) continue; if (reason != IEEE80211_FRAME_RELEASE_UAPSD) { /* for PS-Poll, there's only one frame */ info->flags |= IEEE80211_TX_STATUS_EOSP | IEEE80211_TX_CTL_REQ_TX_STATUS; break; } /* For uAPSD, things are a bit more complicated. If the * last frame has a QoS header (i.e. is a QoS-data or * QoS-nulldata frame) then just set the EOSP bit there * and be done. * If the frame doesn't have a QoS header (which means * it should be a bufferable MMPDU) then we can't set * the EOSP bit in the QoS header; add a QoS-nulldata * frame to the list to send it after the MMPDU. * * Note that this code is only in the mac80211-release * code path, we assume that the driver will not buffer * anything but QoS-data frames, or if it does, will * create the QoS-nulldata frame by itself if needed. * * Cf. 802.11-2012 10.2.1.10 (c). */ if (qoshdr) { *qoshdr |= IEEE80211_QOS_CTL_EOSP; info->flags |= IEEE80211_TX_STATUS_EOSP | IEEE80211_TX_CTL_REQ_TX_STATUS; } else { /* The standard isn't completely clear on this * as it says the more-data bit should be set * if there are more BUs. The QoS-Null frame * we're about to send isn't buffered yet, we * only create it below, but let's pretend it * was buffered just in case some clients only * expect more-data=0 when eosp=1. */ hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_MOREDATA); need_null = true; num++; } break; } drv_allow_buffered_frames(local, sta, tids, num, reason, more_data); ieee80211_add_pending_skbs(local, &pending); if (need_null) ieee80211_send_null_response( sta, find_highest_prio_tid(tids), reason, false, false); sta_info_recalc_tim(sta); } else { int tid; /* * We need to release a frame that is buffered somewhere in the * driver ... it'll have to handle that. * Note that the driver also has to check the number of frames * on the TIDs we're releasing from - if there are more than * n_frames it has to set the more-data bit (if we didn't ask * it to set it anyway due to other buffered frames); if there * are fewer than n_frames it has to make sure to adjust that * to allow the service period to end properly. */ drv_release_buffered_frames(local, sta, driver_release_tids, n_frames, reason, more_data); /* * Note that we don't recalculate the TIM bit here as it would * most likely have no effect at all unless the driver told us * that the TID(s) became empty before returning here from the * release function. * Either way, however, when the driver tells us that the TID(s) * became empty or we find that a txq became empty, we'll do the * TIM recalculation. */ for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) { if (!sta->sta.txq[tid] || !(driver_release_tids & BIT(tid)) || txq_has_queue(sta->sta.txq[tid])) continue; sta_info_recalc_tim(sta); break; } } } void ieee80211_sta_ps_deliver_poll_response(struct sta_info *sta) { u8 ignore_for_response = sta->sta.uapsd_queues; /* * If all ACs are delivery-enabled then we should reply * from any of them, if only some are enabled we reply * only from the non-enabled ones. */ if (ignore_for_response == BIT(IEEE80211_NUM_ACS) - 1) ignore_for_response = 0; ieee80211_sta_ps_deliver_response(sta, 1, ignore_for_response, IEEE80211_FRAME_RELEASE_PSPOLL); } void ieee80211_sta_ps_deliver_uapsd(struct sta_info *sta) { int n_frames = sta->sta.max_sp; u8 delivery_enabled = sta->sta.uapsd_queues; /* * If we ever grow support for TSPEC this might happen if * the TSPEC update from hostapd comes in between a trigger * frame setting WLAN_STA_UAPSD in the RX path and this * actually getting called. */ if (!delivery_enabled) return; switch (sta->sta.max_sp) { case 1: n_frames = 2; break; case 2: n_frames = 4; break; case 3: n_frames = 6; break; case 0: /* XXX: what is a good value? */ n_frames = 128; break; } ieee80211_sta_ps_deliver_response(sta, n_frames, ~delivery_enabled, IEEE80211_FRAME_RELEASE_UAPSD); } void ieee80211_sta_block_awake(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta, bool block) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); trace_api_sta_block_awake(sta->local, pubsta, block); if (block) { set_sta_flag(sta, WLAN_STA_PS_DRIVER); ieee80211_clear_fast_xmit(sta); return; } if (!test_sta_flag(sta, WLAN_STA_PS_DRIVER)) return; if (!test_sta_flag(sta, WLAN_STA_PS_STA)) { set_sta_flag(sta, WLAN_STA_PS_DELIVER); clear_sta_flag(sta, WLAN_STA_PS_DRIVER); ieee80211_queue_work(hw, &sta->drv_deliver_wk); } else if (test_sta_flag(sta, WLAN_STA_PSPOLL) || test_sta_flag(sta, WLAN_STA_UAPSD)) { /* must be asleep in this case */ clear_sta_flag(sta, WLAN_STA_PS_DRIVER); ieee80211_queue_work(hw, &sta->drv_deliver_wk); } else { clear_sta_flag(sta, WLAN_STA_PS_DRIVER); ieee80211_check_fast_xmit(sta); } } EXPORT_SYMBOL(ieee80211_sta_block_awake); void ieee80211_sta_eosp(struct ieee80211_sta *pubsta) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_local *local = sta->local; trace_api_eosp(local, pubsta); clear_sta_flag(sta, WLAN_STA_SP); } EXPORT_SYMBOL(ieee80211_sta_eosp); void ieee80211_send_eosp_nullfunc(struct ieee80211_sta *pubsta, int tid) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); enum ieee80211_frame_release_type reason; bool more_data; trace_api_send_eosp_nullfunc(sta->local, pubsta, tid); reason = IEEE80211_FRAME_RELEASE_UAPSD; more_data = ieee80211_sta_ps_more_data(sta, ~sta->sta.uapsd_queues, reason, 0); ieee80211_send_null_response(sta, tid, reason, false, more_data); } EXPORT_SYMBOL(ieee80211_send_eosp_nullfunc); void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, u8 tid, bool buffered) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); if (WARN_ON(tid >= IEEE80211_NUM_TIDS)) return; trace_api_sta_set_buffered(sta->local, pubsta, tid, buffered); if (buffered) set_bit(tid, &sta->driver_buffered_tids); else clear_bit(tid, &sta->driver_buffered_tids); sta_info_recalc_tim(sta); } EXPORT_SYMBOL(ieee80211_sta_set_buffered); void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, u32 tx_airtime, u32 rx_airtime) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); struct ieee80211_local *local = sta->sdata->local; u8 ac = ieee80211_ac_from_tid(tid); u32 airtime = 0; if (sta->local->airtime_flags & AIRTIME_USE_TX) airtime += tx_airtime; if (sta->local->airtime_flags & AIRTIME_USE_RX) airtime += rx_airtime; spin_lock_bh(&local->active_txq_lock[ac]); sta->airtime[ac].tx_airtime += tx_airtime; sta->airtime[ac].rx_airtime += rx_airtime; if (ieee80211_sta_keep_active(sta, ac)) sta->airtime[ac].deficit -= airtime; spin_unlock_bh(&local->active_txq_lock[ac]); } EXPORT_SYMBOL(ieee80211_sta_register_airtime); void __ieee80211_sta_recalc_aggregates(struct sta_info *sta, u16 active_links) { bool first = true; int link_id; if (!sta->sta.valid_links || !sta->sta.mlo) { sta->sta.cur = &sta->sta.deflink.agg; return; } rcu_read_lock(); for (link_id = 0; link_id < ARRAY_SIZE((sta)->link); link_id++) { struct ieee80211_link_sta *link_sta; int i; if (!(active_links & BIT(link_id))) continue; link_sta = rcu_dereference(sta->sta.link[link_id]); if (!link_sta) continue; if (first) { sta->cur = sta->sta.deflink.agg; first = false; continue; } sta->cur.max_amsdu_len = min(sta->cur.max_amsdu_len, link_sta->agg.max_amsdu_len); sta->cur.max_rc_amsdu_len = min(sta->cur.max_rc_amsdu_len, link_sta->agg.max_rc_amsdu_len); for (i = 0; i < ARRAY_SIZE(sta->cur.max_tid_amsdu_len); i++) sta->cur.max_tid_amsdu_len[i] = min(sta->cur.max_tid_amsdu_len[i], link_sta->agg.max_tid_amsdu_len[i]); } rcu_read_unlock(); sta->sta.cur = &sta->cur; } void ieee80211_sta_recalc_aggregates(struct ieee80211_sta *pubsta) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); __ieee80211_sta_recalc_aggregates(sta, sta->sdata->vif.active_links); } EXPORT_SYMBOL(ieee80211_sta_recalc_aggregates); void ieee80211_sta_update_pending_airtime(struct ieee80211_local *local, struct sta_info *sta, u8 ac, u16 tx_airtime, bool tx_completed) { int tx_pending; if (!wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) return; if (!tx_completed) { if (sta) atomic_add(tx_airtime, &sta->airtime[ac].aql_tx_pending); atomic_add(tx_airtime, &local->aql_total_pending_airtime); atomic_add(tx_airtime, &local->aql_ac_pending_airtime[ac]); return; } if (sta) { tx_pending = atomic_sub_return(tx_airtime, &sta->airtime[ac].aql_tx_pending); if (tx_pending < 0) atomic_cmpxchg(&sta->airtime[ac].aql_tx_pending, tx_pending, 0); } atomic_sub(tx_airtime, &local->aql_total_pending_airtime); tx_pending = atomic_sub_return(tx_airtime, &local->aql_ac_pending_airtime[ac]); if (WARN_ONCE(tx_pending < 0, "Device %s AC %d pending airtime underflow: %u, %u", wiphy_name(local->hw.wiphy), ac, tx_pending, tx_airtime)) { atomic_cmpxchg(&local->aql_ac_pending_airtime[ac], tx_pending, 0); atomic_sub(tx_pending, &local->aql_total_pending_airtime); } } static struct ieee80211_sta_rx_stats * sta_get_last_rx_stats(struct sta_info *sta, int link_id) { struct ieee80211_sta_rx_stats *stats; struct link_sta_info *link_sta_info; int cpu; if (link_id < 0) link_sta_info = &sta->deflink; else link_sta_info = wiphy_dereference(sta->local->hw.wiphy, sta->link[link_id]); stats = &link_sta_info->rx_stats; if (!link_sta_info->pcpu_rx_stats) return stats; for_each_possible_cpu(cpu) { struct ieee80211_sta_rx_stats *cpustats; cpustats = per_cpu_ptr(link_sta_info->pcpu_rx_stats, cpu); if (time_after(cpustats->last_rx, stats->last_rx)) stats = cpustats; } return stats; } static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate, struct rate_info *rinfo) { rinfo->bw = STA_STATS_GET(BW, rate); switch (STA_STATS_GET(TYPE, rate)) { case STA_STATS_RATE_TYPE_VHT: rinfo->flags = RATE_INFO_FLAGS_VHT_MCS; rinfo->mcs = STA_STATS_GET(VHT_MCS, rate); rinfo->nss = STA_STATS_GET(VHT_NSS, rate); if (STA_STATS_GET(SGI, rate)) rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; break; case STA_STATS_RATE_TYPE_HT: rinfo->flags = RATE_INFO_FLAGS_MCS; rinfo->mcs = STA_STATS_GET(HT_MCS, rate); if (STA_STATS_GET(SGI, rate)) rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI; break; case STA_STATS_RATE_TYPE_LEGACY: { struct ieee80211_supported_band *sband; u16 brate; unsigned int shift; int band = STA_STATS_GET(LEGACY_BAND, rate); int rate_idx = STA_STATS_GET(LEGACY_IDX, rate); sband = local->hw.wiphy->bands[band]; if (WARN_ON_ONCE(!sband->bitrates)) break; brate = sband->bitrates[rate_idx].bitrate; if (rinfo->bw == RATE_INFO_BW_5) shift = 2; else if (rinfo->bw == RATE_INFO_BW_10) shift = 1; else shift = 0; rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift); break; } case STA_STATS_RATE_TYPE_HE: rinfo->flags = RATE_INFO_FLAGS_HE_MCS; rinfo->mcs = STA_STATS_GET(HE_MCS, rate); rinfo->nss = STA_STATS_GET(HE_NSS, rate); rinfo->he_gi = STA_STATS_GET(HE_GI, rate); rinfo->he_ru_alloc = STA_STATS_GET(HE_RU, rate); rinfo->he_dcm = STA_STATS_GET(HE_DCM, rate); break; case STA_STATS_RATE_TYPE_EHT: rinfo->flags = RATE_INFO_FLAGS_EHT_MCS; rinfo->mcs = STA_STATS_GET(EHT_MCS, rate); rinfo->nss = STA_STATS_GET(EHT_NSS, rate); rinfo->eht_gi = STA_STATS_GET(EHT_GI, rate); rinfo->eht_ru_alloc = STA_STATS_GET(EHT_RU, rate); break; } } static int sta_set_rate_info_rx(struct sta_info *sta, struct rate_info *rinfo, int link_id) { u32 rate = READ_ONCE(sta_get_last_rx_stats(sta, link_id)->last_rate); if (rate == STA_STATS_RATE_INVALID) return -EINVAL; sta_stats_decode_rate(sta->local, rate, rinfo); return 0; } static inline u64 sta_get_tidstats_msdu(struct ieee80211_sta_rx_stats *rxstats, int tid) { unsigned int start; u64 value; do { start = u64_stats_fetch_begin(&rxstats->syncp); value = rxstats->msdu[tid]; } while (u64_stats_fetch_retry(&rxstats->syncp, start)); return value; } static void sta_set_tidstats(struct sta_info *sta, struct cfg80211_tid_stats *tidstats, int tid, int link_id) { struct ieee80211_local *local = sta->local; struct link_sta_info *link_sta_info; int cpu; if (link_id < 0) link_sta_info = &sta->deflink; else link_sta_info = wiphy_dereference(sta->local->hw.wiphy, sta->link[link_id]); if (!(tidstats->filled & BIT(NL80211_TID_STATS_RX_MSDU))) { tidstats->rx_msdu += sta_get_tidstats_msdu(&link_sta_info->rx_stats, tid); if (link_sta_info->pcpu_rx_stats) { for_each_possible_cpu(cpu) { struct ieee80211_sta_rx_stats *cpurxs; cpurxs = per_cpu_ptr(link_sta_info->pcpu_rx_stats, cpu); tidstats->rx_msdu += sta_get_tidstats_msdu(cpurxs, tid); } } tidstats->filled |= BIT(NL80211_TID_STATS_RX_MSDU); } if (!(tidstats->filled & BIT(NL80211_TID_STATS_TX_MSDU))) { tidstats->filled |= BIT(NL80211_TID_STATS_TX_MSDU); tidstats->tx_msdu = link_sta_info->tx_stats.msdu[tid]; } if (!(tidstats->filled & BIT(NL80211_TID_STATS_TX_MSDU_RETRIES)) && ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { tidstats->filled |= BIT(NL80211_TID_STATS_TX_MSDU_RETRIES); tidstats->tx_msdu_retries = link_sta_info->status_stats.msdu_retries[tid]; } if (!(tidstats->filled & BIT(NL80211_TID_STATS_TX_MSDU_FAILED)) && ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { tidstats->filled |= BIT(NL80211_TID_STATS_TX_MSDU_FAILED); tidstats->tx_msdu_failed = link_sta_info->status_stats.msdu_failed[tid]; } if (link_id < 0 && tid < IEEE80211_NUM_TIDS) { spin_lock_bh(&local->fq.lock); rcu_read_lock(); tidstats->filled |= BIT(NL80211_TID_STATS_TXQ_STATS); ieee80211_fill_txq_stats(&tidstats->txq_stats, to_txq_info(sta->sta.txq[tid])); rcu_read_unlock(); spin_unlock_bh(&local->fq.lock); } } static inline u64 sta_get_stats_bytes(struct ieee80211_sta_rx_stats *rxstats) { unsigned int start; u64 value; do { start = u64_stats_fetch_begin(&rxstats->syncp); value = rxstats->bytes; } while (u64_stats_fetch_retry(&rxstats->syncp, start)); return value; } #ifdef CONFIG_MAC80211_MESH static void sta_set_mesh_sinfo(struct sta_info *sta, struct station_info *sinfo) { struct ieee80211_local *local = sta->sdata->local; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_LLID) | BIT_ULL(NL80211_STA_INFO_PLID) | BIT_ULL(NL80211_STA_INFO_PLINK_STATE) | BIT_ULL(NL80211_STA_INFO_LOCAL_PM) | BIT_ULL(NL80211_STA_INFO_PEER_PM) | BIT_ULL(NL80211_STA_INFO_NONPEER_PM) | BIT_ULL(NL80211_STA_INFO_CONNECTED_TO_GATE) | BIT_ULL(NL80211_STA_INFO_CONNECTED_TO_AS); sinfo->llid = sta->mesh->llid; sinfo->plid = sta->mesh->plid; sinfo->plink_state = sta->mesh->plink_state; if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) { sinfo->filled |= BIT_ULL(NL80211_STA_INFO_T_OFFSET); sinfo->t_offset = sta->mesh->t_offset; } sinfo->local_pm = sta->mesh->local_pm; sinfo->peer_pm = sta->mesh->peer_pm; sinfo->nonpeer_pm = sta->mesh->nonpeer_pm; sinfo->connected_to_gate = sta->mesh->connected_to_gate; sinfo->connected_to_as = sta->mesh->connected_to_as; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_LINK_METRIC); sinfo->airtime_link_metric = airtime_link_metric_get(local, sta); } #endif void sta_set_accumulated_removed_links_sinfo(struct sta_info *sta, struct station_info *sinfo) { /* Accumulating the removed link statistics. */ sinfo->tx_packets = sta->rem_link_stats.tx_packets; sinfo->rx_packets = sta->rem_link_stats.rx_packets; sinfo->tx_bytes = sta->rem_link_stats.tx_bytes; sinfo->rx_bytes = sta->rem_link_stats.rx_bytes; sinfo->tx_retries = sta->rem_link_stats.tx_retries; sinfo->tx_failed = sta->rem_link_stats.tx_failed; sinfo->rx_dropped_misc = sta->rem_link_stats.rx_dropped_misc; sinfo->beacon_loss_count = sta->rem_link_stats.beacon_loss_count; sinfo->expected_throughput = sta->rem_link_stats.expected_throughput; if (sinfo->pertid) { sinfo->pertid->rx_msdu = sta->rem_link_stats.pertid_stats.rx_msdu; sinfo->pertid->tx_msdu = sta->rem_link_stats.pertid_stats.tx_msdu; sinfo->pertid->tx_msdu_retries = sta->rem_link_stats.pertid_stats.tx_msdu_retries; sinfo->pertid->tx_msdu_failed = sta->rem_link_stats.pertid_stats.tx_msdu_failed; } } static void sta_set_link_sinfo(struct sta_info *sta, struct link_station_info *link_sinfo, struct ieee80211_link_data *link, bool tidstats) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_sta_rx_stats *last_rxstats; int i, ac, cpu, link_id = link->link_id; struct link_sta_info *link_sta_info; u32 thr = 0; last_rxstats = sta_get_last_rx_stats(sta, link_id); link_sta_info = wiphy_dereference(sta->local->hw.wiphy, sta->link[link_id]); /* do before driver, so beacon filtering drivers have a * chance to e.g. just add the number of filtered beacons * (or just modify the value entirely, of course) */ if (sdata->vif.type == NL80211_IFTYPE_STATION) link_sinfo->rx_beacon = link->u.mgd.count_beacon_signal; ether_addr_copy(link_sinfo->addr, link_sta_info->addr); drv_link_sta_statistics(sta->local, sdata, link_sta_info->pub, link_sinfo); link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME) | BIT_ULL(NL80211_STA_INFO_BSS_PARAM) | BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC); if (sdata->vif.type == NL80211_IFTYPE_STATION) { link_sinfo->beacon_loss_count = link->u.mgd.beacon_loss_count; link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_LOSS); } link_sinfo->inactive_time = jiffies_to_msecs(jiffies - ieee80211_sta_last_active(sta, link_id)); if (!(link_sinfo->filled & (BIT_ULL(NL80211_STA_INFO_TX_BYTES64) | BIT_ULL(NL80211_STA_INFO_TX_BYTES)))) { link_sinfo->tx_bytes = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) link_sinfo->tx_bytes += link_sta_info->tx_stats.bytes[ac]; link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64); } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_PACKETS))) { link_sinfo->tx_packets = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) link_sinfo->tx_packets += link_sta_info->tx_stats.packets[ac]; link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS); } if (!(link_sinfo->filled & (BIT_ULL(NL80211_STA_INFO_RX_BYTES64) | BIT_ULL(NL80211_STA_INFO_RX_BYTES)))) { link_sinfo->rx_bytes += sta_get_stats_bytes(&link_sta_info->rx_stats); if (link_sta_info->pcpu_rx_stats) { for_each_possible_cpu(cpu) { struct ieee80211_sta_rx_stats *cpurxs; cpurxs = per_cpu_ptr(link_sta_info->pcpu_rx_stats, cpu); link_sinfo->rx_bytes += sta_get_stats_bytes(cpurxs); } } link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64); } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_PACKETS))) { link_sinfo->rx_packets = link_sta_info->rx_stats.packets; if (link_sta_info->pcpu_rx_stats) { for_each_possible_cpu(cpu) { struct ieee80211_sta_rx_stats *cpurxs; cpurxs = per_cpu_ptr(link_sta_info->pcpu_rx_stats, cpu); link_sinfo->rx_packets += cpurxs->packets; } } link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS); } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_RETRIES))) { link_sinfo->tx_retries = link_sta_info->status_stats.retry_count; link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES); } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED))) { link_sinfo->tx_failed = link_sta_info->status_stats.retry_failed; link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED); } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_DURATION))) { for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) link_sinfo->rx_duration += sta->airtime[ac].rx_airtime; link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_DURATION); } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_DURATION))) { for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) link_sinfo->tx_duration += sta->airtime[ac].tx_airtime; link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_DURATION); } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT))) { link_sinfo->airtime_weight = sta->airtime_weight; link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT); } link_sinfo->rx_dropped_misc = link_sta_info->rx_stats.dropped; if (link_sta_info->pcpu_rx_stats) { for_each_possible_cpu(cpu) { struct ieee80211_sta_rx_stats *cpurxs; cpurxs = per_cpu_ptr(link_sta_info->pcpu_rx_stats, cpu); link_sinfo->rx_dropped_misc += cpurxs->dropped; } } if (sdata->vif.type == NL80211_IFTYPE_STATION && !(sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)) { link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_RX) | BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG); link_sinfo->rx_beacon_signal_avg = ieee80211_ave_rssi(&sdata->vif, -1); } if (ieee80211_hw_check(&sta->local->hw, SIGNAL_DBM) || ieee80211_hw_check(&sta->local->hw, SIGNAL_UNSPEC)) { if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_SIGNAL))) { link_sinfo->signal = (s8)last_rxstats->last_signal; link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL); } if (!link_sta_info->pcpu_rx_stats && !(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG))) { link_sinfo->signal_avg = -ewma_signal_read(&link_sta_info->rx_stats_avg.signal); link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG); } } /* for the average - if pcpu_rx_stats isn't set - rxstats must point to * the sta->rx_stats struct, so the check here is fine with and without * pcpu statistics */ if (last_rxstats->chains && !(link_sinfo->filled & (BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL) | BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) { link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL); if (!link_sta_info->pcpu_rx_stats) link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG); link_sinfo->chains = last_rxstats->chains; for (i = 0; i < ARRAY_SIZE(link_sinfo->chain_signal); i++) { link_sinfo->chain_signal[i] = last_rxstats->chain_signal_last[i]; link_sinfo->chain_signal_avg[i] = -ewma_signal_read( &link_sta_info->rx_stats_avg.chain_signal[i]); } } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE)) && ieee80211_rate_valid(&link_sta_info->tx_stats.last_rate)) { sta_set_rate_info_tx(sta, &link_sta_info->tx_stats.last_rate, &link_sinfo->txrate); link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE); } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE))) { if (sta_set_rate_info_rx(sta, &link_sinfo->rxrate, link_id) == 0) link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE); } if (tidstats && !cfg80211_link_sinfo_alloc_tid_stats(link_sinfo, GFP_KERNEL)) { for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) sta_set_tidstats(sta, &link_sinfo->pertid[i], i, link_id); } link_sinfo->bss_param.flags = 0; if (sdata->vif.bss_conf.use_cts_prot) link_sinfo->bss_param.flags |= BSS_PARAM_FLAGS_CTS_PROT; if (sdata->vif.bss_conf.use_short_preamble) link_sinfo->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_PREAMBLE; if (sdata->vif.bss_conf.use_short_slot) link_sinfo->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_SLOT_TIME; link_sinfo->bss_param.dtim_period = link->conf->dtim_period; link_sinfo->bss_param.beacon_interval = link->conf->beacon_int; thr = sta_get_expected_throughput(sta); if (thr != 0) { link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_EXPECTED_THROUGHPUT); link_sinfo->expected_throughput = thr; } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL)) && link_sta_info->status_stats.ack_signal_filled) { link_sinfo->ack_signal = link_sta_info->status_stats.last_ack_signal; link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL); } if (!(link_sinfo->filled & BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG)) && link_sta_info->status_stats.ack_signal_filled) { link_sinfo->avg_ack_signal = -(s8)ewma_avg_signal_read( &link_sta_info->status_stats.avg_ack_signal); link_sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG); } } void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, bool tidstats) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; u32 thr = 0; int i, ac, cpu, link_id; struct ieee80211_sta_rx_stats *last_rxstats; last_rxstats = sta_get_last_rx_stats(sta, -1); sinfo->generation = sdata->local->sta_generation; /* do before driver, so beacon filtering drivers have a * chance to e.g. just add the number of filtered beacons * (or just modify the value entirely, of course) */ if (sdata->vif.type == NL80211_IFTYPE_STATION) sinfo->rx_beacon = sdata->deflink.u.mgd.count_beacon_signal; drv_sta_statistics(local, sdata, &sta->sta, sinfo); sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME) | BIT_ULL(NL80211_STA_INFO_STA_FLAGS) | BIT_ULL(NL80211_STA_INFO_BSS_PARAM) | BIT_ULL(NL80211_STA_INFO_CONNECTED_TIME) | BIT_ULL(NL80211_STA_INFO_ASSOC_AT_BOOTTIME) | BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC); if (sdata->vif.type == NL80211_IFTYPE_STATION) { sinfo->beacon_loss_count = sdata->deflink.u.mgd.beacon_loss_count; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_LOSS); } sinfo->connected_time = ktime_get_seconds() - sta->last_connected; sinfo->assoc_at = sta->assoc_at; sinfo->inactive_time = jiffies_to_msecs(jiffies - ieee80211_sta_last_active(sta, -1)); if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_TX_BYTES64) | BIT_ULL(NL80211_STA_INFO_TX_BYTES)))) { sinfo->tx_bytes = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) sinfo->tx_bytes += sta->deflink.tx_stats.bytes[ac]; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64); } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_PACKETS))) { sinfo->tx_packets = 0; for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) sinfo->tx_packets += sta->deflink.tx_stats.packets[ac]; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS); } if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_RX_BYTES64) | BIT_ULL(NL80211_STA_INFO_RX_BYTES)))) { sinfo->rx_bytes += sta_get_stats_bytes(&sta->deflink.rx_stats); if (sta->deflink.pcpu_rx_stats) { for_each_possible_cpu(cpu) { struct ieee80211_sta_rx_stats *cpurxs; cpurxs = per_cpu_ptr(sta->deflink.pcpu_rx_stats, cpu); sinfo->rx_bytes += sta_get_stats_bytes(cpurxs); } } sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64); } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_PACKETS))) { sinfo->rx_packets = sta->deflink.rx_stats.packets; if (sta->deflink.pcpu_rx_stats) { for_each_possible_cpu(cpu) { struct ieee80211_sta_rx_stats *cpurxs; cpurxs = per_cpu_ptr(sta->deflink.pcpu_rx_stats, cpu); sinfo->rx_packets += cpurxs->packets; } } sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS); } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_RETRIES))) { sinfo->tx_retries = sta->deflink.status_stats.retry_count; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES); } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED))) { sinfo->tx_failed = sta->deflink.status_stats.retry_failed; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED); } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_DURATION))) { for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) sinfo->rx_duration += sta->airtime[ac].rx_airtime; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_DURATION); } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_DURATION))) { for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) sinfo->tx_duration += sta->airtime[ac].tx_airtime; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_DURATION); } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT))) { sinfo->airtime_weight = sta->airtime_weight; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT); } sinfo->rx_dropped_misc = sta->deflink.rx_stats.dropped; if (sta->deflink.pcpu_rx_stats) { for_each_possible_cpu(cpu) { struct ieee80211_sta_rx_stats *cpurxs; cpurxs = per_cpu_ptr(sta->deflink.pcpu_rx_stats, cpu); sinfo->rx_dropped_misc += cpurxs->dropped; } } if (sdata->vif.type == NL80211_IFTYPE_STATION && !(sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)) { sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_RX) | BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG); sinfo->rx_beacon_signal_avg = ieee80211_ave_rssi(&sdata->vif, -1); } if (ieee80211_hw_check(&sta->local->hw, SIGNAL_DBM) || ieee80211_hw_check(&sta->local->hw, SIGNAL_UNSPEC)) { if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_SIGNAL))) { sinfo->signal = (s8)last_rxstats->last_signal; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL); } if (!sta->deflink.pcpu_rx_stats && !(sinfo->filled & BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG))) { sinfo->signal_avg = -ewma_signal_read(&sta->deflink.rx_stats_avg.signal); sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG); } } /* for the average - if pcpu_rx_stats isn't set - rxstats must point to * the sta->rx_stats struct, so the check here is fine with and without * pcpu statistics */ if (last_rxstats->chains && !(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL) | BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) { sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL); if (!sta->deflink.pcpu_rx_stats) sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG); sinfo->chains = last_rxstats->chains; for (i = 0; i < ARRAY_SIZE(sinfo->chain_signal); i++) { sinfo->chain_signal[i] = last_rxstats->chain_signal_last[i]; sinfo->chain_signal_avg[i] = -ewma_signal_read(&sta->deflink.rx_stats_avg.chain_signal[i]); } } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE)) && !sta->sta.valid_links && ieee80211_rate_valid(&sta->deflink.tx_stats.last_rate)) { sta_set_rate_info_tx(sta, &sta->deflink.tx_stats.last_rate, &sinfo->txrate); sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE); } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE)) && !sta->sta.valid_links) { if (sta_set_rate_info_rx(sta, &sinfo->rxrate, -1) == 0) sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE); } if (tidstats && !cfg80211_sinfo_alloc_tid_stats(sinfo, GFP_KERNEL)) { for (i = 0; i < IEEE80211_NUM_TIDS + 1; i++) sta_set_tidstats(sta, &sinfo->pertid[i], i, -1); } #ifdef CONFIG_MAC80211_MESH if (ieee80211_vif_is_mesh(&sdata->vif)) sta_set_mesh_sinfo(sta, sinfo); #endif sinfo->bss_param.flags = 0; if (sdata->vif.bss_conf.use_cts_prot) sinfo->bss_param.flags |= BSS_PARAM_FLAGS_CTS_PROT; if (sdata->vif.bss_conf.use_short_preamble) sinfo->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_PREAMBLE; if (sdata->vif.bss_conf.use_short_slot) sinfo->bss_param.flags |= BSS_PARAM_FLAGS_SHORT_SLOT_TIME; sinfo->bss_param.dtim_period = sdata->vif.bss_conf.dtim_period; sinfo->bss_param.beacon_interval = sdata->vif.bss_conf.beacon_int; sinfo->sta_flags.set = 0; sinfo->sta_flags.mask = BIT(NL80211_STA_FLAG_AUTHORIZED) | BIT(NL80211_STA_FLAG_SHORT_PREAMBLE) | BIT(NL80211_STA_FLAG_WME) | BIT(NL80211_STA_FLAG_MFP) | BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_ASSOCIATED) | BIT(NL80211_STA_FLAG_TDLS_PEER); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHORIZED); if (test_sta_flag(sta, WLAN_STA_SHORT_PREAMBLE)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_SHORT_PREAMBLE); if (sta->sta.wme) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_WME); if (test_sta_flag(sta, WLAN_STA_MFP)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_MFP); if (test_sta_flag(sta, WLAN_STA_AUTH)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_AUTHENTICATED); if (test_sta_flag(sta, WLAN_STA_ASSOC)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_ASSOCIATED); if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) sinfo->sta_flags.set |= BIT(NL80211_STA_FLAG_TDLS_PEER); thr = sta_get_expected_throughput(sta); if (thr != 0) { sinfo->filled |= BIT_ULL(NL80211_STA_INFO_EXPECTED_THROUGHPUT); sinfo->expected_throughput = thr; } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL)) && sta->deflink.status_stats.ack_signal_filled) { sinfo->ack_signal = sta->deflink.status_stats.last_ack_signal; sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL); } if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG)) && sta->deflink.status_stats.ack_signal_filled) { sinfo->avg_ack_signal = -(s8)ewma_avg_signal_read( &sta->deflink.status_stats.avg_ack_signal); sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG); } if (sta->sta.valid_links) { struct ieee80211_link_data *link; struct link_sta_info *link_sta; ether_addr_copy(sinfo->mld_addr, sta->addr); for_each_valid_link(sinfo, link_id) { link_sta = wiphy_dereference(sta->local->hw.wiphy, sta->link[link_id]); link = wiphy_dereference(sdata->local->hw.wiphy, sdata->link[link_id]); if (!link_sta || !sinfo->links[link_id] || !link) continue; sinfo->valid_links = sta->sta.valid_links; sta_set_link_sinfo(sta, sinfo->links[link_id], link, tidstats); } } } u32 sta_get_expected_throughput(struct sta_info *sta) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; struct rate_control_ref *ref = NULL; u32 thr = 0; if (test_sta_flag(sta, WLAN_STA_RATE_CONTROL)) ref = local->rate_ctrl; /* check if the driver has a SW RC implementation */ if (ref && ref->ops->get_expected_throughput) thr = ref->ops->get_expected_throughput(sta->rate_ctrl_priv); else thr = drv_get_expected_throughput(local, sta); return thr; } unsigned long ieee80211_sta_last_active(struct sta_info *sta, int link_id) { struct ieee80211_sta_rx_stats *stats; struct link_sta_info *link_sta_info; stats = sta_get_last_rx_stats(sta, link_id); if (link_id < 0) link_sta_info = &sta->deflink; else link_sta_info = wiphy_dereference(sta->local->hw.wiphy, sta->link[link_id]); if (!link_sta_info->status_stats.last_ack || time_after(stats->last_rx, link_sta_info->status_stats.last_ack)) return stats->last_rx; return link_sta_info->status_stats.last_ack; } int ieee80211_sta_allocate_link(struct sta_info *sta, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct sta_link_alloc *alloc; int ret; lockdep_assert_wiphy(sdata->local->hw.wiphy); WARN_ON(!test_sta_flag(sta, WLAN_STA_INSERTED)); /* must represent an MLD from the start */ if (WARN_ON(!sta->sta.valid_links)) return -EINVAL; if (WARN_ON(sta->sta.valid_links & BIT(link_id) || sta->link[link_id])) return -EBUSY; alloc = kzalloc(sizeof(*alloc), GFP_KERNEL); if (!alloc) return -ENOMEM; ret = sta_info_alloc_link(sdata->local, &alloc->info, GFP_KERNEL); if (ret) { kfree(alloc); return ret; } sta_info_add_link(sta, link_id, &alloc->info, &alloc->sta); ieee80211_link_sta_debugfs_add(&alloc->info); return 0; } void ieee80211_sta_free_link(struct sta_info *sta, unsigned int link_id) { lockdep_assert_wiphy(sta->sdata->local->hw.wiphy); WARN_ON(!test_sta_flag(sta, WLAN_STA_INSERTED)); sta_remove_link(sta, link_id, false); } int ieee80211_sta_activate_link(struct sta_info *sta, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct link_sta_info *link_sta; u16 old_links = sta->sta.valid_links; u16 new_links = old_links | BIT(link_id); int ret; link_sta = rcu_dereference_protected(sta->link[link_id], lockdep_is_held(&sdata->local->hw.wiphy->mtx)); if (WARN_ON(old_links == new_links || !link_sta)) return -EINVAL; rcu_read_lock(); if (link_sta_info_hash_lookup(sdata->local, link_sta->addr)) { rcu_read_unlock(); return -EALREADY; } /* we only modify under the mutex so this is fine */ rcu_read_unlock(); sta->sta.valid_links = new_links; if (WARN_ON(!test_sta_flag(sta, WLAN_STA_INSERTED))) goto hash; ieee80211_recalc_min_chandef(sdata, link_id); /* Ensure the values are updated for the driver, * redone by sta_remove_link on failure. */ ieee80211_sta_recalc_aggregates(&sta->sta); ret = drv_change_sta_links(sdata->local, sdata, &sta->sta, old_links, new_links); if (ret) { sta->sta.valid_links = old_links; sta_remove_link(sta, link_id, false); return ret; } hash: ret = link_sta_info_hash_add(sdata->local, link_sta); WARN_ON(ret); return 0; } void ieee80211_sta_remove_link(struct sta_info *sta, unsigned int link_id) { struct ieee80211_sub_if_data *sdata = sta->sdata; u16 old_links = sta->sta.valid_links; lockdep_assert_wiphy(sdata->local->hw.wiphy); sta->sta.valid_links &= ~BIT(link_id); if (!WARN_ON(!test_sta_flag(sta, WLAN_STA_INSERTED))) drv_change_sta_links(sdata->local, sdata, &sta->sta, old_links, sta->sta.valid_links); sta_remove_link(sta, link_id, true); } void ieee80211_sta_set_max_amsdu_subframes(struct sta_info *sta, const u8 *ext_capab, unsigned int ext_capab_len) { u8 val; sta->sta.max_amsdu_subframes = 0; if (ext_capab_len < 8) return; /* The sender might not have sent the last bit, consider it to be 0 */ val = u8_get_bits(ext_capab[7], WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB); /* we did get all the bits, take the MSB as well */ if (ext_capab_len >= 9) val |= u8_get_bits(ext_capab[8], WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB) << 1; if (val) sta->sta.max_amsdu_subframes = 4 << (4 - val); } #ifdef CONFIG_LOCKDEP bool lockdep_sta_mutex_held(struct ieee80211_sta *pubsta) { struct sta_info *sta = container_of(pubsta, struct sta_info, sta); return lockdep_is_held(&sta->local->hw.wiphy->mtx); } EXPORT_SYMBOL(lockdep_sta_mutex_held); #endif |
| 108 80 63 102 10 28 57 57 28 56 28 57 50 80 79 80 80 80 80 94 94 30 94 94 30 30 94 93 94 94 23 94 4 94 94 80 80 80 80 80 80 88 7 7 413 412 411 412 410 8 57 57 57 63 63 63 24 63 62 8 57 8 57 63 412 317 403 411 144 124 97 44 24 44 69 6 23 69 88 88 34 69 20 53 88 69 88 30 69 69 29 44 69 17 57 69 28 37 8 8 88 87 55 54 94 94 94 94 94 94 94 94 23 94 23 94 57 47 94 94 47 57 57 57 57 57 57 57 56 57 57 57 57 94 94 94 94 2 2 55 63 47 57 57 188 188 277 75 187 187 188 181 188 187 187 188 188 188 188 188 188 188 188 475 477 476 476 34 1 188 187 188 188 188 188 188 187 188 188 188 187 187 187 184 184 175 169 177 177 176 188 188 188 5 187 187 188 188 187 186 187 187 102 103 103 102 94 94 94 94 27 27 23 94 92 94 92 4 93 101 102 103 103 103 101 101 44 44 4 44 14 14 13 41 41 41 41 34 16 22 5 14 24 34 41 5 397 313 272 399 312 273 399 399 397 411 412 33 33 33 33 33 33 296 296 296 296 295 296 296 478 479 403 424 424 475 477 402 424 4 424 21 21 21 415 404 402 21 21 402 21 21 404 404 403 415 415 76 403 404 404 404 402 403 403 16 402 404 404 404 401 488 488 488 397 507 317 71 500 467 358 449 2 149 388 374 189 74 277 277 278 277 75 75 75 75 74 75 296 296 295 296 293 277 277 277 277 277 261 261 260 261 261 411 408 411 411 1 1 1 318 78 261 261 260 260 261 261 319 320 497 494 493 310 309 309 4 4 4 4 4 361 362 361 87 87 86 420 420 293 310 311 311 311 310 416 281 281 280 281 282 282 279 282 282 87 87 87 87 87 87 280 276 201 280 280 281 21 16 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/bitops.h> #include <linux/slab.h> #include <linux/bio.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/page-flags.h> #include <linux/sched/mm.h> #include <linux/spinlock.h> #include <linux/blkdev.h> #include <linux/swap.h> #include <linux/writeback.h> #include <linux/pagevec.h> #include <linux/prefetch.h> #include <linux/fsverity.h> #include "extent_io.h" #include "extent-io-tree.h" #include "extent_map.h" #include "ctree.h" #include "btrfs_inode.h" #include "bio.h" #include "locking.h" #include "backref.h" #include "disk-io.h" #include "subpage.h" #include "zoned.h" #include "block-group.h" #include "compression.h" #include "fs.h" #include "accessors.h" #include "file-item.h" #include "file.h" #include "dev-replace.h" #include "super.h" #include "transaction.h" static struct kmem_cache *extent_buffer_cache; #ifdef CONFIG_BTRFS_DEBUG static inline void btrfs_leak_debug_add_eb(struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = eb->fs_info; unsigned long flags; spin_lock_irqsave(&fs_info->eb_leak_lock, flags); list_add(&eb->leak_list, &fs_info->allocated_ebs); spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags); } static inline void btrfs_leak_debug_del_eb(struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = eb->fs_info; unsigned long flags; spin_lock_irqsave(&fs_info->eb_leak_lock, flags); list_del(&eb->leak_list); spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags); } void btrfs_extent_buffer_leak_debug_check(struct btrfs_fs_info *fs_info) { struct extent_buffer *eb; unsigned long flags; /* * If we didn't get into open_ctree our allocated_ebs will not be * initialized, so just skip this. */ if (!fs_info->allocated_ebs.next) return; WARN_ON(!list_empty(&fs_info->allocated_ebs)); spin_lock_irqsave(&fs_info->eb_leak_lock, flags); while (!list_empty(&fs_info->allocated_ebs)) { eb = list_first_entry(&fs_info->allocated_ebs, struct extent_buffer, leak_list); btrfs_err(fs_info, "buffer leak start %llu len %u refs %d bflags %lu owner %llu", eb->start, eb->len, refcount_read(&eb->refs), eb->bflags, btrfs_header_owner(eb)); list_del(&eb->leak_list); WARN_ON_ONCE(1); kmem_cache_free(extent_buffer_cache, eb); } spin_unlock_irqrestore(&fs_info->eb_leak_lock, flags); } #else #define btrfs_leak_debug_add_eb(eb) do {} while (0) #define btrfs_leak_debug_del_eb(eb) do {} while (0) #endif /* * Structure to record info about the bio being assembled, and other info like * how many bytes are there before stripe/ordered extent boundary. */ struct btrfs_bio_ctrl { struct btrfs_bio *bbio; /* Last byte contained in bbio + 1 . */ loff_t next_file_offset; enum btrfs_compression_type compress_type; u32 len_to_oe_boundary; blk_opf_t opf; btrfs_bio_end_io_t end_io_func; struct writeback_control *wbc; /* * The sectors of the page which are going to be submitted by * extent_writepage_io(). * This is to avoid touching ranges covered by compression/inline. */ unsigned long submit_bitmap; struct readahead_control *ractl; /* * The start offset of the last used extent map by a read operation. * * This is for proper compressed read merge. * U64_MAX means we are starting the read and have made no progress yet. * * The current btrfs_bio_is_contig() only uses disk_bytenr as * the condition to check if the read can be merged with previous * bio, which is not correct. E.g. two file extents pointing to the * same extent but with different offset. * * So here we need to do extra checks to only merge reads that are * covered by the same extent map. * Just extent_map::start will be enough, as they are unique * inside the same inode. */ u64 last_em_start; }; static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) { struct btrfs_bio *bbio = bio_ctrl->bbio; if (!bbio) return; /* Caller should ensure the bio has at least some range added */ ASSERT(bbio->bio.bi_iter.bi_size); if (btrfs_op(&bbio->bio) == BTRFS_MAP_READ && bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) btrfs_submit_compressed_read(bbio); else btrfs_submit_bbio(bbio, 0); /* The bbio is owned by the end_io handler now */ bio_ctrl->bbio = NULL; } /* * Submit or fail the current bio in the bio_ctrl structure. */ static void submit_write_bio(struct btrfs_bio_ctrl *bio_ctrl, int ret) { struct btrfs_bio *bbio = bio_ctrl->bbio; if (!bbio) return; if (ret) { ASSERT(ret < 0); btrfs_bio_end_io(bbio, errno_to_blk_status(ret)); /* The bio is owned by the end_io handler now */ bio_ctrl->bbio = NULL; } else { submit_one_bio(bio_ctrl); } } int __init extent_buffer_init_cachep(void) { extent_buffer_cache = kmem_cache_create("btrfs_extent_buffer", sizeof(struct extent_buffer), 0, 0, NULL); if (!extent_buffer_cache) return -ENOMEM; return 0; } void __cold extent_buffer_free_cachep(void) { /* * Make sure all delayed rcu free are flushed before we * destroy caches. */ rcu_barrier(); kmem_cache_destroy(extent_buffer_cache); } static void process_one_folio(struct btrfs_fs_info *fs_info, struct folio *folio, const struct folio *locked_folio, unsigned long page_ops, u64 start, u64 end) { u32 len; ASSERT(end + 1 - start != 0 && end + 1 - start < U32_MAX); len = end + 1 - start; if (page_ops & PAGE_SET_ORDERED) btrfs_folio_clamp_set_ordered(fs_info, folio, start, len); if (page_ops & PAGE_START_WRITEBACK) { btrfs_folio_clamp_clear_dirty(fs_info, folio, start, len); btrfs_folio_clamp_set_writeback(fs_info, folio, start, len); } if (page_ops & PAGE_END_WRITEBACK) btrfs_folio_clamp_clear_writeback(fs_info, folio, start, len); if (folio != locked_folio && (page_ops & PAGE_UNLOCK)) btrfs_folio_end_lock(fs_info, folio, start, len); } static void __process_folios_contig(struct address_space *mapping, const struct folio *locked_folio, u64 start, u64 end, unsigned long page_ops) { struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); pgoff_t index = start >> PAGE_SHIFT; pgoff_t end_index = end >> PAGE_SHIFT; struct folio_batch fbatch; int i; folio_batch_init(&fbatch); while (index <= end_index) { int found_folios; found_folios = filemap_get_folios_contig(mapping, &index, end_index, &fbatch); for (i = 0; i < found_folios; i++) { struct folio *folio = fbatch.folios[i]; process_one_folio(fs_info, folio, locked_folio, page_ops, start, end); } folio_batch_release(&fbatch); cond_resched(); } } static noinline void unlock_delalloc_folio(const struct inode *inode, struct folio *locked_folio, u64 start, u64 end) { ASSERT(locked_folio); __process_folios_contig(inode->i_mapping, locked_folio, start, end, PAGE_UNLOCK); } static noinline int lock_delalloc_folios(struct inode *inode, struct folio *locked_folio, u64 start, u64 end) { struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct address_space *mapping = inode->i_mapping; pgoff_t index = start >> PAGE_SHIFT; pgoff_t end_index = end >> PAGE_SHIFT; u64 processed_end = start; struct folio_batch fbatch; folio_batch_init(&fbatch); while (index <= end_index) { unsigned int found_folios, i; found_folios = filemap_get_folios_contig(mapping, &index, end_index, &fbatch); if (found_folios == 0) goto out; for (i = 0; i < found_folios; i++) { struct folio *folio = fbatch.folios[i]; u64 range_start; u32 range_len; if (folio == locked_folio) continue; folio_lock(folio); if (!folio_test_dirty(folio) || folio->mapping != mapping) { folio_unlock(folio); goto out; } range_start = max_t(u64, folio_pos(folio), start); range_len = min_t(u64, folio_end(folio), end + 1) - range_start; btrfs_folio_set_lock(fs_info, folio, range_start, range_len); processed_end = range_start + range_len - 1; } folio_batch_release(&fbatch); cond_resched(); } return 0; out: folio_batch_release(&fbatch); if (processed_end > start) unlock_delalloc_folio(inode, locked_folio, start, processed_end); return -EAGAIN; } /* * Find and lock a contiguous range of bytes in the file marked as delalloc, no * more than @max_bytes. * * @start: The original start bytenr to search. * Will store the extent range start bytenr. * @end: The original end bytenr of the search range * Will store the extent range end bytenr. * * Return true if we find a delalloc range which starts inside the original * range, and @start/@end will store the delalloc range start/end. * * Return false if we can't find any delalloc range which starts inside the * original range, and @start/@end will be the non-delalloc range start/end. */ EXPORT_FOR_TESTS noinline_for_stack bool find_lock_delalloc_range(struct inode *inode, struct folio *locked_folio, u64 *start, u64 *end) { struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree; const u64 orig_start = *start; const u64 orig_end = *end; /* The sanity tests may not set a valid fs_info. */ u64 max_bytes = fs_info ? fs_info->max_extent_size : BTRFS_MAX_EXTENT_SIZE; u64 delalloc_start; u64 delalloc_end; bool found; struct extent_state *cached_state = NULL; int ret; int loops = 0; /* Caller should pass a valid @end to indicate the search range end */ ASSERT(orig_end > orig_start); /* The range should at least cover part of the folio */ ASSERT(!(orig_start >= folio_end(locked_folio) || orig_end <= folio_pos(locked_folio))); again: /* step one, find a bunch of delalloc bytes starting at start */ delalloc_start = *start; delalloc_end = 0; found = btrfs_find_delalloc_range(tree, &delalloc_start, &delalloc_end, max_bytes, &cached_state); if (!found || delalloc_end <= *start || delalloc_start > orig_end) { *start = delalloc_start; /* @delalloc_end can be -1, never go beyond @orig_end */ *end = min(delalloc_end, orig_end); btrfs_free_extent_state(cached_state); return false; } /* * start comes from the offset of locked_folio. We have to lock * folios in order, so we can't process delalloc bytes before * locked_folio */ if (delalloc_start < *start) delalloc_start = *start; /* * make sure to limit the number of folios we try to lock down */ if (delalloc_end + 1 - delalloc_start > max_bytes) delalloc_end = delalloc_start + max_bytes - 1; /* step two, lock all the folioss after the folios that has start */ ret = lock_delalloc_folios(inode, locked_folio, delalloc_start, delalloc_end); ASSERT(!ret || ret == -EAGAIN); if (ret == -EAGAIN) { /* some of the folios are gone, lets avoid looping by * shortening the size of the delalloc range we're searching */ btrfs_free_extent_state(cached_state); cached_state = NULL; if (!loops) { max_bytes = PAGE_SIZE; loops = 1; goto again; } else { found = false; goto out_failed; } } /* step three, lock the state bits for the whole range */ btrfs_lock_extent(tree, delalloc_start, delalloc_end, &cached_state); /* then test to make sure it is all still delalloc */ ret = btrfs_test_range_bit(tree, delalloc_start, delalloc_end, EXTENT_DELALLOC, cached_state); btrfs_unlock_extent(tree, delalloc_start, delalloc_end, &cached_state); if (!ret) { unlock_delalloc_folio(inode, locked_folio, delalloc_start, delalloc_end); cond_resched(); goto again; } *start = delalloc_start; *end = delalloc_end; out_failed: return found; } void extent_clear_unlock_delalloc(struct btrfs_inode *inode, u64 start, u64 end, const struct folio *locked_folio, struct extent_state **cached, u32 clear_bits, unsigned long page_ops) { btrfs_clear_extent_bit(&inode->io_tree, start, end, clear_bits, cached); __process_folios_contig(inode->vfs_inode.i_mapping, locked_folio, start, end, page_ops); } static bool btrfs_verify_folio(struct folio *folio, u64 start, u32 len) { struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); if (!fsverity_active(folio->mapping->host) || btrfs_folio_test_uptodate(fs_info, folio, start, len) || start >= i_size_read(folio->mapping->host)) return true; return fsverity_verify_folio(folio); } static void end_folio_read(struct folio *folio, bool uptodate, u64 start, u32 len) { struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); ASSERT(folio_pos(folio) <= start && start + len <= folio_end(folio)); if (uptodate && btrfs_verify_folio(folio, start, len)) btrfs_folio_set_uptodate(fs_info, folio, start, len); else btrfs_folio_clear_uptodate(fs_info, folio, start, len); if (!btrfs_is_subpage(fs_info, folio)) folio_unlock(folio); else btrfs_folio_end_lock(fs_info, folio, start, len); } /* * After a write IO is done, we need to: * * - clear the uptodate bits on error * - clear the writeback bits in the extent tree for the range * - filio_end_writeback() if there is no more pending io for the folio * * Scheduling is not allowed, so the extent state tree is expected * to have one and only one object corresponding to this IO. */ static void end_bbio_data_write(struct btrfs_bio *bbio) { struct btrfs_fs_info *fs_info = bbio->fs_info; struct bio *bio = &bbio->bio; int error = blk_status_to_errno(bio->bi_status); struct folio_iter fi; const u32 sectorsize = fs_info->sectorsize; ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_folio_all(fi, bio) { struct folio *folio = fi.folio; u64 start = folio_pos(folio) + fi.offset; u32 len = fi.length; /* Our read/write should always be sector aligned. */ if (!IS_ALIGNED(fi.offset, sectorsize)) btrfs_err(fs_info, "partial page write in btrfs with offset %zu and length %zu", fi.offset, fi.length); else if (!IS_ALIGNED(fi.length, sectorsize)) btrfs_info(fs_info, "incomplete page write with offset %zu and length %zu", fi.offset, fi.length); btrfs_finish_ordered_extent(bbio->ordered, folio, start, len, !error); if (error) mapping_set_error(folio->mapping, error); btrfs_folio_clear_writeback(fs_info, folio, start, len); } bio_put(bio); } static void begin_folio_read(struct btrfs_fs_info *fs_info, struct folio *folio) { ASSERT(folio_test_locked(folio)); if (!btrfs_is_subpage(fs_info, folio)) return; ASSERT(folio_test_private(folio)); btrfs_folio_set_lock(fs_info, folio, folio_pos(folio), folio_size(folio)); } /* * After a data read IO is done, we need to: * * - clear the uptodate bits on error * - set the uptodate bits if things worked * - set the folio up to date if all extents in the tree are uptodate * - clear the lock bit in the extent tree * - unlock the folio if there are no other extents locked for it * * Scheduling is not allowed, so the extent state tree is expected * to have one and only one object corresponding to this IO. */ static void end_bbio_data_read(struct btrfs_bio *bbio) { struct btrfs_fs_info *fs_info = bbio->fs_info; struct bio *bio = &bbio->bio; struct folio_iter fi; ASSERT(!bio_flagged(bio, BIO_CLONED)); bio_for_each_folio_all(fi, &bbio->bio) { bool uptodate = !bio->bi_status; struct folio *folio = fi.folio; struct inode *inode = folio->mapping->host; u64 start = folio_pos(folio) + fi.offset; btrfs_debug(fs_info, "%s: bi_sector=%llu, err=%d, mirror=%u", __func__, bio->bi_iter.bi_sector, bio->bi_status, bbio->mirror_num); if (likely(uptodate)) { u64 end = start + fi.length - 1; loff_t i_size = i_size_read(inode); /* * Zero out the remaining part if this range straddles * i_size. * * Here we should only zero the range inside the folio, * not touch anything else. * * NOTE: i_size is exclusive while end is inclusive and * folio_contains() takes PAGE_SIZE units. */ if (folio_contains(folio, i_size >> PAGE_SHIFT) && i_size <= end) { u32 zero_start = max(offset_in_folio(folio, i_size), offset_in_folio(folio, start)); u32 zero_len = offset_in_folio(folio, end) + 1 - zero_start; folio_zero_range(folio, zero_start, zero_len); } } /* Update page status and unlock. */ end_folio_read(folio, uptodate, start, fi.length); } bio_put(bio); } /* * Populate every free slot in a provided array with folios using GFP_NOFS. * * @nr_folios: number of folios to allocate * @folio_array: the array to fill with folios; any existing non-NULL entries in * the array will be skipped * * Return: 0 if all folios were able to be allocated; * -ENOMEM otherwise, the partially allocated folios would be freed and * the array slots zeroed */ int btrfs_alloc_folio_array(unsigned int nr_folios, struct folio **folio_array) { for (int i = 0; i < nr_folios; i++) { if (folio_array[i]) continue; folio_array[i] = folio_alloc(GFP_NOFS, 0); if (!folio_array[i]) goto error; } return 0; error: for (int i = 0; i < nr_folios; i++) { if (folio_array[i]) folio_put(folio_array[i]); } return -ENOMEM; } /* * Populate every free slot in a provided array with pages, using GFP_NOFS. * * @nr_pages: number of pages to allocate * @page_array: the array to fill with pages; any existing non-null entries in * the array will be skipped * @nofail: whether using __GFP_NOFAIL flag * * Return: 0 if all pages were able to be allocated; * -ENOMEM otherwise, the partially allocated pages would be freed and * the array slots zeroed */ int btrfs_alloc_page_array(unsigned int nr_pages, struct page **page_array, bool nofail) { const gfp_t gfp = nofail ? (GFP_NOFS | __GFP_NOFAIL) : GFP_NOFS; unsigned int allocated; for (allocated = 0; allocated < nr_pages;) { unsigned int last = allocated; allocated = alloc_pages_bulk(gfp, nr_pages, page_array); if (unlikely(allocated == last)) { /* No progress, fail and do cleanup. */ for (int i = 0; i < allocated; i++) { __free_page(page_array[i]); page_array[i] = NULL; } return -ENOMEM; } } return 0; } /* * Populate needed folios for the extent buffer. * * For now, the folios populated are always in order 0 (aka, single page). */ static int alloc_eb_folio_array(struct extent_buffer *eb, bool nofail) { struct page *page_array[INLINE_EXTENT_BUFFER_PAGES] = { 0 }; int num_pages = num_extent_pages(eb); int ret; ret = btrfs_alloc_page_array(num_pages, page_array, nofail); if (ret < 0) return ret; for (int i = 0; i < num_pages; i++) eb->folios[i] = page_folio(page_array[i]); eb->folio_size = PAGE_SIZE; eb->folio_shift = PAGE_SHIFT; return 0; } static bool btrfs_bio_is_contig(struct btrfs_bio_ctrl *bio_ctrl, u64 disk_bytenr, loff_t file_offset) { struct bio *bio = &bio_ctrl->bbio->bio; const sector_t sector = disk_bytenr >> SECTOR_SHIFT; if (bio_ctrl->compress_type != BTRFS_COMPRESS_NONE) { /* * For compression, all IO should have its logical bytenr set * to the starting bytenr of the compressed extent. */ return bio->bi_iter.bi_sector == sector; } /* * To merge into a bio both the disk sector and the logical offset in * the file need to be contiguous. */ return bio_ctrl->next_file_offset == file_offset && bio_end_sector(bio) == sector; } static void alloc_new_bio(struct btrfs_inode *inode, struct btrfs_bio_ctrl *bio_ctrl, u64 disk_bytenr, u64 file_offset) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct btrfs_bio *bbio; bbio = btrfs_bio_alloc(BIO_MAX_VECS, bio_ctrl->opf, fs_info, bio_ctrl->end_io_func, NULL); bbio->bio.bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT; bbio->bio.bi_write_hint = inode->vfs_inode.i_write_hint; bbio->inode = inode; bbio->file_offset = file_offset; bio_ctrl->bbio = bbio; bio_ctrl->len_to_oe_boundary = U32_MAX; bio_ctrl->next_file_offset = file_offset; /* Limit data write bios to the ordered boundary. */ if (bio_ctrl->wbc) { struct btrfs_ordered_extent *ordered; ordered = btrfs_lookup_ordered_extent(inode, file_offset); if (ordered) { bio_ctrl->len_to_oe_boundary = min_t(u32, U32_MAX, ordered->file_offset + ordered->disk_num_bytes - file_offset); bbio->ordered = ordered; } /* * Pick the last added device to support cgroup writeback. For * multi-device file systems this means blk-cgroup policies have * to always be set on the last added/replaced device. * This is a bit odd but has been like that for a long time. */ bio_set_dev(&bbio->bio, fs_info->fs_devices->latest_dev->bdev); wbc_init_bio(bio_ctrl->wbc, &bbio->bio); } } /* * @disk_bytenr: logical bytenr where the write will be * @page: page to add to the bio * @size: portion of page that we want to write to * @pg_offset: offset of the new bio or to check whether we are adding * a contiguous page to the previous one * * The will either add the page into the existing @bio_ctrl->bbio, or allocate a * new one in @bio_ctrl->bbio. * The mirror number for this IO should already be initizlied in * @bio_ctrl->mirror_num. */ static void submit_extent_folio(struct btrfs_bio_ctrl *bio_ctrl, u64 disk_bytenr, struct folio *folio, size_t size, unsigned long pg_offset) { struct btrfs_inode *inode = folio_to_inode(folio); loff_t file_offset = folio_pos(folio) + pg_offset; ASSERT(pg_offset + size <= folio_size(folio)); ASSERT(bio_ctrl->end_io_func); if (bio_ctrl->bbio && !btrfs_bio_is_contig(bio_ctrl, disk_bytenr, file_offset)) submit_one_bio(bio_ctrl); do { u32 len = size; /* Allocate new bio if needed */ if (!bio_ctrl->bbio) alloc_new_bio(inode, bio_ctrl, disk_bytenr, file_offset); /* Cap to the current ordered extent boundary if there is one. */ if (len > bio_ctrl->len_to_oe_boundary) { ASSERT(bio_ctrl->compress_type == BTRFS_COMPRESS_NONE); ASSERT(is_data_inode(inode)); len = bio_ctrl->len_to_oe_boundary; } if (!bio_add_folio(&bio_ctrl->bbio->bio, folio, len, pg_offset)) { /* bio full: move on to a new one */ submit_one_bio(bio_ctrl); continue; } bio_ctrl->next_file_offset += len; if (bio_ctrl->wbc) wbc_account_cgroup_owner(bio_ctrl->wbc, folio, len); size -= len; pg_offset += len; disk_bytenr += len; file_offset += len; /* * len_to_oe_boundary defaults to U32_MAX, which isn't folio or * sector aligned. alloc_new_bio() then sets it to the end of * our ordered extent for writes into zoned devices. * * When len_to_oe_boundary is tracking an ordered extent, we * trust the ordered extent code to align things properly, and * the check above to cap our write to the ordered extent * boundary is correct. * * When len_to_oe_boundary is U32_MAX, the cap above would * result in a 4095 byte IO for the last folio right before * we hit the bio limit of UINT_MAX. bio_add_folio() has all * the checks required to make sure we don't overflow the bio, * and we should just ignore len_to_oe_boundary completely * unless we're using it to track an ordered extent. * * It's pretty hard to make a bio sized U32_MAX, but it can * happen when the page cache is able to feed us contiguous * folios for large extents. */ if (bio_ctrl->len_to_oe_boundary != U32_MAX) bio_ctrl->len_to_oe_boundary -= len; /* Ordered extent boundary: move on to a new bio. */ if (bio_ctrl->len_to_oe_boundary == 0) submit_one_bio(bio_ctrl); } while (size); } static int attach_extent_buffer_folio(struct extent_buffer *eb, struct folio *folio, struct btrfs_folio_state *prealloc) { struct btrfs_fs_info *fs_info = eb->fs_info; int ret = 0; /* * If the page is mapped to btree inode, we should hold the private * lock to prevent race. * For cloned or dummy extent buffers, their pages are not mapped and * will not race with any other ebs. */ if (folio->mapping) lockdep_assert_held(&folio->mapping->i_private_lock); if (!btrfs_meta_is_subpage(fs_info)) { if (!folio_test_private(folio)) folio_attach_private(folio, eb); else WARN_ON(folio_get_private(folio) != eb); return 0; } /* Already mapped, just free prealloc */ if (folio_test_private(folio)) { btrfs_free_folio_state(prealloc); return 0; } if (prealloc) /* Has preallocated memory for subpage */ folio_attach_private(folio, prealloc); else /* Do new allocation to attach subpage */ ret = btrfs_attach_folio_state(fs_info, folio, BTRFS_SUBPAGE_METADATA); return ret; } int set_folio_extent_mapped(struct folio *folio) { struct btrfs_fs_info *fs_info; ASSERT(folio->mapping); if (folio_test_private(folio)) return 0; fs_info = folio_to_fs_info(folio); if (btrfs_is_subpage(fs_info, folio)) return btrfs_attach_folio_state(fs_info, folio, BTRFS_SUBPAGE_DATA); folio_attach_private(folio, (void *)EXTENT_FOLIO_PRIVATE); return 0; } void clear_folio_extent_mapped(struct folio *folio) { struct btrfs_fs_info *fs_info; ASSERT(folio->mapping); if (!folio_test_private(folio)) return; fs_info = folio_to_fs_info(folio); if (btrfs_is_subpage(fs_info, folio)) return btrfs_detach_folio_state(fs_info, folio, BTRFS_SUBPAGE_DATA); folio_detach_private(folio); } static struct extent_map *get_extent_map(struct btrfs_inode *inode, struct folio *folio, u64 start, u64 len, struct extent_map **em_cached) { struct extent_map *em; ASSERT(em_cached); if (*em_cached) { em = *em_cached; if (btrfs_extent_map_in_tree(em) && start >= em->start && start < btrfs_extent_map_end(em)) { refcount_inc(&em->refs); return em; } btrfs_free_extent_map(em); *em_cached = NULL; } em = btrfs_get_extent(inode, folio, start, len); if (!IS_ERR(em)) { BUG_ON(*em_cached); refcount_inc(&em->refs); *em_cached = em; } return em; } static void btrfs_readahead_expand(struct readahead_control *ractl, const struct extent_map *em) { const u64 ra_pos = readahead_pos(ractl); const u64 ra_end = ra_pos + readahead_length(ractl); const u64 em_end = em->start + em->ram_bytes; /* No expansion for holes and inline extents. */ if (em->disk_bytenr > EXTENT_MAP_LAST_BYTE) return; ASSERT(em_end >= ra_pos, "extent_map %llu %llu ends before current readahead position %llu", em->start, em->len, ra_pos); if (em_end > ra_end) readahead_expand(ractl, ra_pos, em_end - ra_pos); } /* * basic readpage implementation. Locked extent state structs are inserted * into the tree that are removed when the IO is done (by the end_io * handlers) * XXX JDM: This needs looking at to ensure proper page locking * return 0 on success, otherwise return error */ static int btrfs_do_readpage(struct folio *folio, struct extent_map **em_cached, struct btrfs_bio_ctrl *bio_ctrl) { struct inode *inode = folio->mapping->host; struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); u64 start = folio_pos(folio); const u64 end = start + folio_size(folio) - 1; u64 extent_offset; u64 last_byte = i_size_read(inode); struct extent_map *em; int ret = 0; const size_t blocksize = fs_info->sectorsize; ret = set_folio_extent_mapped(folio); if (ret < 0) { folio_unlock(folio); return ret; } if (folio_contains(folio, last_byte >> PAGE_SHIFT)) { size_t zero_offset = offset_in_folio(folio, last_byte); if (zero_offset) folio_zero_range(folio, zero_offset, folio_size(folio) - zero_offset); } bio_ctrl->end_io_func = end_bbio_data_read; begin_folio_read(fs_info, folio); for (u64 cur = start; cur <= end; cur += blocksize) { enum btrfs_compression_type compress_type = BTRFS_COMPRESS_NONE; unsigned long pg_offset = offset_in_folio(folio, cur); bool force_bio_submit = false; u64 disk_bytenr; u64 block_start; ASSERT(IS_ALIGNED(cur, fs_info->sectorsize)); if (cur >= last_byte) { folio_zero_range(folio, pg_offset, end - cur + 1); end_folio_read(folio, true, cur, end - cur + 1); break; } if (btrfs_folio_test_uptodate(fs_info, folio, cur, blocksize)) { end_folio_read(folio, true, cur, blocksize); continue; } em = get_extent_map(BTRFS_I(inode), folio, cur, end - cur + 1, em_cached); if (IS_ERR(em)) { end_folio_read(folio, false, cur, end + 1 - cur); return PTR_ERR(em); } extent_offset = cur - em->start; BUG_ON(btrfs_extent_map_end(em) <= cur); BUG_ON(end < cur); compress_type = btrfs_extent_map_compression(em); /* * Only expand readahead for extents which are already creating * the pages anyway in add_ra_bio_pages, which is compressed * extents in the non subpage case. */ if (bio_ctrl->ractl && !btrfs_is_subpage(fs_info, folio) && compress_type != BTRFS_COMPRESS_NONE) btrfs_readahead_expand(bio_ctrl->ractl, em); if (compress_type != BTRFS_COMPRESS_NONE) disk_bytenr = em->disk_bytenr; else disk_bytenr = btrfs_extent_map_block_start(em) + extent_offset; if (em->flags & EXTENT_FLAG_PREALLOC) block_start = EXTENT_MAP_HOLE; else block_start = btrfs_extent_map_block_start(em); /* * If we have a file range that points to a compressed extent * and it's followed by a consecutive file range that points * to the same compressed extent (possibly with a different * offset and/or length, so it either points to the whole extent * or only part of it), we must make sure we do not submit a * single bio to populate the folios for the 2 ranges because * this makes the compressed extent read zero out the folios * belonging to the 2nd range. Imagine the following scenario: * * File layout * [0 - 8K] [8K - 24K] * | | * | | * points to extent X, points to extent X, * offset 4K, length of 8K offset 0, length 16K * * [extent X, compressed length = 4K uncompressed length = 16K] * * If the bio to read the compressed extent covers both ranges, * it will decompress extent X into the folios belonging to the * first range and then it will stop, zeroing out the remaining * folios that belong to the other range that points to extent X. * So here we make sure we submit 2 bios, one for the first * range and another one for the third range. Both will target * the same physical extent from disk, but we can't currently * make the compressed bio endio callback populate the folios * for both ranges because each compressed bio is tightly * coupled with a single extent map, and each range can have * an extent map with a different offset value relative to the * uncompressed data of our extent and different lengths. This * is a corner case so we prioritize correctness over * non-optimal behavior (submitting 2 bios for the same extent). */ if (compress_type != BTRFS_COMPRESS_NONE && bio_ctrl->last_em_start != U64_MAX && bio_ctrl->last_em_start != em->start) force_bio_submit = true; bio_ctrl->last_em_start = em->start; btrfs_free_extent_map(em); em = NULL; /* we've found a hole, just zero and go on */ if (block_start == EXTENT_MAP_HOLE) { folio_zero_range(folio, pg_offset, blocksize); end_folio_read(folio, true, cur, blocksize); continue; } /* the get_extent function already copied into the folio */ if (block_start == EXTENT_MAP_INLINE) { end_folio_read(folio, true, cur, blocksize); continue; } if (bio_ctrl->compress_type != compress_type) { submit_one_bio(bio_ctrl); bio_ctrl->compress_type = compress_type; } if (force_bio_submit) submit_one_bio(bio_ctrl); submit_extent_folio(bio_ctrl, disk_bytenr, folio, blocksize, pg_offset); } return 0; } /* * Check if we can skip waiting the @ordered extent covering the block at @fileoff. * * @fileoff: Both input and output. * Input as the file offset where the check should start at. * Output as where the next check should start at, * if the function returns true. * * Return true if we can skip to @fileoff. The caller needs to check the new * @fileoff value to make sure it covers the full range, before skipping the * full OE. * * Return false if we must wait for the ordered extent. */ static bool can_skip_one_ordered_range(struct btrfs_inode *inode, struct btrfs_ordered_extent *ordered, u64 *fileoff) { const struct btrfs_fs_info *fs_info = inode->root->fs_info; struct folio *folio; const u32 blocksize = fs_info->sectorsize; u64 cur = *fileoff; bool ret; folio = filemap_get_folio(inode->vfs_inode.i_mapping, cur >> PAGE_SHIFT); /* * We should have locked the folio(s) for range [start, end], thus * there must be a folio and it must be locked. */ ASSERT(!IS_ERR(folio)); ASSERT(folio_test_locked(folio)); /* * There are several cases for the folio and OE combination: * * 1) Folio has no private flag * The OE has all its IO done but not yet finished, and folio got * invalidated. * * Have we have to wait for the OE to finish, as it may contain the * to-be-inserted data checksum. * Without the data checksum inserted into the csum tree, read will * just fail with missing csum. */ if (!folio_test_private(folio)) { ret = false; goto out; } /* * 2) The first block is DIRTY. * * This means the OE is created by some other folios whose file pos is * before this one. And since we are holding the folio lock, the writeback * of this folio cannot start. * * We must skip the whole OE, because it will never start until we * finished our folio read and unlocked the folio. */ if (btrfs_folio_test_dirty(fs_info, folio, cur, blocksize)) { u64 range_len = min(folio_end(folio), ordered->file_offset + ordered->num_bytes) - cur; ret = true; /* * At least inside the folio, all the remaining blocks should * also be dirty. */ ASSERT(btrfs_folio_test_dirty(fs_info, folio, cur, range_len)); *fileoff = ordered->file_offset + ordered->num_bytes; goto out; } /* * 3) The first block is uptodate. * * At least the first block can be skipped, but we are still not fully * sure. E.g. if the OE has some other folios in the range that cannot * be skipped. * So we return true and update @next_ret to the OE/folio boundary. */ if (btrfs_folio_test_uptodate(fs_info, folio, cur, blocksize)) { u64 range_len = min(folio_end(folio), ordered->file_offset + ordered->num_bytes) - cur; /* * The whole range to the OE end or folio boundary should also * be uptodate. */ ASSERT(btrfs_folio_test_uptodate(fs_info, folio, cur, range_len)); ret = true; *fileoff = cur + range_len; goto out; } /* * 4) The first block is not uptodate. * * This means the folio is invalidated after the writeback was finished, * but by some other operations (e.g. block aligned buffered write) the * folio is inserted into filemap. * Very much the same as case 1). */ ret = false; out: folio_put(folio); return ret; } static bool can_skip_ordered_extent(struct btrfs_inode *inode, struct btrfs_ordered_extent *ordered, u64 start, u64 end) { const u64 range_end = min(end, ordered->file_offset + ordered->num_bytes - 1); u64 cur = max(start, ordered->file_offset); while (cur < range_end) { bool can_skip; can_skip = can_skip_one_ordered_range(inode, ordered, &cur); if (!can_skip) return false; } return true; } /* * Locking helper to make sure we get a stable view of extent maps for the * involved range. * * This is for folio read paths (read and readahead), thus the involved range * should have all the folios locked. */ static void lock_extents_for_read(struct btrfs_inode *inode, u64 start, u64 end, struct extent_state **cached_state) { u64 cur_pos; /* Caller must provide a valid @cached_state. */ ASSERT(cached_state); /* The range must at least be page aligned, as all read paths are folio based. */ ASSERT(IS_ALIGNED(start, PAGE_SIZE)); ASSERT(IS_ALIGNED(end + 1, PAGE_SIZE)); again: btrfs_lock_extent(&inode->io_tree, start, end, cached_state); cur_pos = start; while (cur_pos < end) { struct btrfs_ordered_extent *ordered; ordered = btrfs_lookup_ordered_range(inode, cur_pos, end - cur_pos + 1); /* * No ordered extents in the range, and we hold the extent lock, * no one can modify the extent maps in the range, we're safe to return. */ if (!ordered) break; /* Check if we can skip waiting for the whole OE. */ if (can_skip_ordered_extent(inode, ordered, start, end)) { cur_pos = min(ordered->file_offset + ordered->num_bytes, end + 1); btrfs_put_ordered_extent(ordered); continue; } /* Now wait for the OE to finish. */ btrfs_unlock_extent(&inode->io_tree, start, end, cached_state); btrfs_start_ordered_extent_nowriteback(ordered, start, end + 1 - start); btrfs_put_ordered_extent(ordered); /* We have unlocked the whole range, restart from the beginning. */ goto again; } } int btrfs_read_folio(struct file *file, struct folio *folio) { struct btrfs_inode *inode = folio_to_inode(folio); const u64 start = folio_pos(folio); const u64 end = start + folio_size(folio) - 1; struct extent_state *cached_state = NULL; struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ, .last_em_start = U64_MAX, }; struct extent_map *em_cached = NULL; int ret; lock_extents_for_read(inode, start, end, &cached_state); ret = btrfs_do_readpage(folio, &em_cached, &bio_ctrl); btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state); btrfs_free_extent_map(em_cached); /* * If btrfs_do_readpage() failed we will want to submit the assembled * bio to do the cleanup. */ submit_one_bio(&bio_ctrl); return ret; } static void set_delalloc_bitmap(struct folio *folio, unsigned long *delalloc_bitmap, u64 start, u32 len) { struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); const u64 folio_start = folio_pos(folio); unsigned int start_bit; unsigned int nbits; ASSERT(start >= folio_start && start + len <= folio_start + folio_size(folio)); start_bit = (start - folio_start) >> fs_info->sectorsize_bits; nbits = len >> fs_info->sectorsize_bits; ASSERT(bitmap_test_range_all_zero(delalloc_bitmap, start_bit, nbits)); bitmap_set(delalloc_bitmap, start_bit, nbits); } static bool find_next_delalloc_bitmap(struct folio *folio, unsigned long *delalloc_bitmap, u64 start, u64 *found_start, u32 *found_len) { struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); const u64 folio_start = folio_pos(folio); const unsigned int bitmap_size = btrfs_blocks_per_folio(fs_info, folio); unsigned int start_bit; unsigned int first_zero; unsigned int first_set; ASSERT(start >= folio_start && start < folio_start + folio_size(folio)); start_bit = (start - folio_start) >> fs_info->sectorsize_bits; first_set = find_next_bit(delalloc_bitmap, bitmap_size, start_bit); if (first_set >= bitmap_size) return false; *found_start = folio_start + (first_set << fs_info->sectorsize_bits); first_zero = find_next_zero_bit(delalloc_bitmap, bitmap_size, first_set); *found_len = (first_zero - first_set) << fs_info->sectorsize_bits; return true; } /* * Do all of the delayed allocation setup. * * Return >0 if all the dirty blocks are submitted async (compression) or inlined. * The @folio should no longer be touched (treat it as already unlocked). * * Return 0 if there is still dirty block that needs to be submitted through * extent_writepage_io(). * bio_ctrl->submit_bitmap will indicate which blocks of the folio should be * submitted, and @folio is still kept locked. * * Return <0 if there is any error hit. * Any allocated ordered extent range covering this folio will be marked * finished (IOERR), and @folio is still kept locked. */ static noinline_for_stack int writepage_delalloc(struct btrfs_inode *inode, struct folio *folio, struct btrfs_bio_ctrl *bio_ctrl) { struct btrfs_fs_info *fs_info = inode_to_fs_info(&inode->vfs_inode); struct writeback_control *wbc = bio_ctrl->wbc; const bool is_subpage = btrfs_is_subpage(fs_info, folio); const u64 page_start = folio_pos(folio); const u64 page_end = page_start + folio_size(folio) - 1; const unsigned int blocks_per_folio = btrfs_blocks_per_folio(fs_info, folio); unsigned long delalloc_bitmap = 0; /* * Save the last found delalloc end. As the delalloc end can go beyond * page boundary, thus we cannot rely on subpage bitmap to locate the * last delalloc end. */ u64 last_delalloc_end = 0; /* * The range end (exclusive) of the last successfully finished delalloc * range. * Any range covered by ordered extent must either be manually marked * finished (error handling), or has IO submitted (and finish the * ordered extent normally). * * This records the end of ordered extent cleanup if we hit an error. */ u64 last_finished_delalloc_end = page_start; u64 delalloc_start = page_start; u64 delalloc_end = page_end; u64 delalloc_to_write = 0; int ret = 0; int bit; /* Save the dirty bitmap as our submission bitmap will be a subset of it. */ if (btrfs_is_subpage(fs_info, folio)) { ASSERT(blocks_per_folio > 1); btrfs_get_subpage_dirty_bitmap(fs_info, folio, &bio_ctrl->submit_bitmap); } else { bio_ctrl->submit_bitmap = 1; } for_each_set_bit(bit, &bio_ctrl->submit_bitmap, blocks_per_folio) { u64 start = page_start + (bit << fs_info->sectorsize_bits); btrfs_folio_set_lock(fs_info, folio, start, fs_info->sectorsize); } /* Lock all (subpage) delalloc ranges inside the folio first. */ while (delalloc_start < page_end) { delalloc_end = page_end; if (!find_lock_delalloc_range(&inode->vfs_inode, folio, &delalloc_start, &delalloc_end)) { delalloc_start = delalloc_end + 1; continue; } set_delalloc_bitmap(folio, &delalloc_bitmap, delalloc_start, min(delalloc_end, page_end) + 1 - delalloc_start); last_delalloc_end = delalloc_end; delalloc_start = delalloc_end + 1; } delalloc_start = page_start; if (!last_delalloc_end) goto out; /* Run the delalloc ranges for the above locked ranges. */ while (delalloc_start < page_end) { u64 found_start; u32 found_len; bool found; if (!is_subpage) { /* * For non-subpage case, the found delalloc range must * cover this folio and there must be only one locked * delalloc range. */ found_start = page_start; found_len = last_delalloc_end + 1 - found_start; found = true; } else { found = find_next_delalloc_bitmap(folio, &delalloc_bitmap, delalloc_start, &found_start, &found_len); } if (!found) break; /* * The subpage range covers the last sector, the delalloc range may * end beyond the folio boundary, use the saved delalloc_end * instead. */ if (found_start + found_len >= page_end) found_len = last_delalloc_end + 1 - found_start; if (ret >= 0) { /* * Some delalloc range may be created by previous folios. * Thus we still need to clean up this range during error * handling. */ last_finished_delalloc_end = found_start; /* No errors hit so far, run the current delalloc range. */ ret = btrfs_run_delalloc_range(inode, folio, found_start, found_start + found_len - 1, wbc); if (ret >= 0) last_finished_delalloc_end = found_start + found_len; if (unlikely(ret < 0)) btrfs_err_rl(fs_info, "failed to run delalloc range, root=%lld ino=%llu folio=%llu submit_bitmap=%*pbl start=%llu len=%u: %d", btrfs_root_id(inode->root), btrfs_ino(inode), folio_pos(folio), blocks_per_folio, &bio_ctrl->submit_bitmap, found_start, found_len, ret); } else { /* * We've hit an error during previous delalloc range, * have to cleanup the remaining locked ranges. */ btrfs_unlock_extent(&inode->io_tree, found_start, found_start + found_len - 1, NULL); unlock_delalloc_folio(&inode->vfs_inode, folio, found_start, found_start + found_len - 1); } /* * We have some ranges that's going to be submitted asynchronously * (compression or inline). These range have their own control * on when to unlock the pages. We should not touch them * anymore, so clear the range from the submission bitmap. */ if (ret > 0) { unsigned int start_bit = (found_start - page_start) >> fs_info->sectorsize_bits; unsigned int end_bit = (min(page_end + 1, found_start + found_len) - page_start) >> fs_info->sectorsize_bits; bitmap_clear(&bio_ctrl->submit_bitmap, start_bit, end_bit - start_bit); } /* * Above btrfs_run_delalloc_range() may have unlocked the folio, * thus for the last range, we cannot touch the folio anymore. */ if (found_start + found_len >= last_delalloc_end + 1) break; delalloc_start = found_start + found_len; } /* * It's possible we had some ordered extents created before we hit * an error, cleanup non-async successfully created delalloc ranges. */ if (unlikely(ret < 0)) { unsigned int bitmap_size = min( (last_finished_delalloc_end - page_start) >> fs_info->sectorsize_bits, blocks_per_folio); for_each_set_bit(bit, &bio_ctrl->submit_bitmap, bitmap_size) btrfs_mark_ordered_io_finished(inode, folio, page_start + (bit << fs_info->sectorsize_bits), fs_info->sectorsize, false); return ret; } out: if (last_delalloc_end) delalloc_end = last_delalloc_end; else delalloc_end = page_end; /* * delalloc_end is already one less than the total length, so * we don't subtract one from PAGE_SIZE. */ delalloc_to_write += DIV_ROUND_UP(delalloc_end + 1 - page_start, PAGE_SIZE); /* * If all ranges are submitted asynchronously, we just need to account * for them here. */ if (bitmap_empty(&bio_ctrl->submit_bitmap, blocks_per_folio)) { wbc->nr_to_write -= delalloc_to_write; return 1; } if (wbc->nr_to_write < delalloc_to_write) { int thresh = 8192; if (delalloc_to_write < thresh * 2) thresh = delalloc_to_write; wbc->nr_to_write = min_t(u64, delalloc_to_write, thresh); } return 0; } /* * Return 0 if we have submitted or queued the sector for submission. * Return <0 for critical errors, and the sector will have its dirty flag cleared. * * Caller should make sure filepos < i_size and handle filepos >= i_size case. */ static int submit_one_sector(struct btrfs_inode *inode, struct folio *folio, u64 filepos, struct btrfs_bio_ctrl *bio_ctrl, loff_t i_size) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_map *em; u64 block_start; u64 disk_bytenr; u64 extent_offset; u64 em_end; const u32 sectorsize = fs_info->sectorsize; ASSERT(IS_ALIGNED(filepos, sectorsize)); /* @filepos >= i_size case should be handled by the caller. */ ASSERT(filepos < i_size); em = btrfs_get_extent(inode, NULL, filepos, sectorsize); if (IS_ERR(em)) { /* * When submission failed, we should still clear the folio dirty. * Or the folio will be written back again but without any * ordered extent. */ btrfs_folio_clear_dirty(fs_info, folio, filepos, sectorsize); btrfs_folio_set_writeback(fs_info, folio, filepos, sectorsize); btrfs_folio_clear_writeback(fs_info, folio, filepos, sectorsize); return PTR_ERR(em); } extent_offset = filepos - em->start; em_end = btrfs_extent_map_end(em); ASSERT(filepos <= em_end); ASSERT(IS_ALIGNED(em->start, sectorsize)); ASSERT(IS_ALIGNED(em->len, sectorsize)); block_start = btrfs_extent_map_block_start(em); disk_bytenr = btrfs_extent_map_block_start(em) + extent_offset; ASSERT(!btrfs_extent_map_is_compressed(em)); ASSERT(block_start != EXTENT_MAP_HOLE); ASSERT(block_start != EXTENT_MAP_INLINE); btrfs_free_extent_map(em); em = NULL; /* * Although the PageDirty bit is cleared before entering this * function, subpage dirty bit is not cleared. * So clear subpage dirty bit here so next time we won't submit * a folio for a range already written to disk. */ btrfs_folio_clear_dirty(fs_info, folio, filepos, sectorsize); btrfs_folio_set_writeback(fs_info, folio, filepos, sectorsize); /* * Above call should set the whole folio with writeback flag, even * just for a single subpage sector. * As long as the folio is properly locked and the range is correct, * we should always get the folio with writeback flag. */ ASSERT(folio_test_writeback(folio)); submit_extent_folio(bio_ctrl, disk_bytenr, folio, sectorsize, filepos - folio_pos(folio)); return 0; } /* * Helper for extent_writepage(). This calls the writepage start hooks, * and does the loop to map the page into extents and bios. * * We return 1 if the IO is started and the page is unlocked, * 0 if all went well (page still locked) * < 0 if there were errors (page still locked) */ static noinline_for_stack int extent_writepage_io(struct btrfs_inode *inode, struct folio *folio, u64 start, u32 len, struct btrfs_bio_ctrl *bio_ctrl, loff_t i_size) { struct btrfs_fs_info *fs_info = inode->root->fs_info; unsigned long range_bitmap = 0; bool submitted_io = false; bool error = false; const u64 folio_start = folio_pos(folio); const unsigned int blocks_per_folio = btrfs_blocks_per_folio(fs_info, folio); u64 cur; int bit; int ret = 0; ASSERT(start >= folio_start && start + len <= folio_start + folio_size(folio)); ret = btrfs_writepage_cow_fixup(folio); if (ret == -EAGAIN) { /* Fixup worker will requeue */ folio_redirty_for_writepage(bio_ctrl->wbc, folio); folio_unlock(folio); return 1; } if (ret < 0) { btrfs_folio_clear_dirty(fs_info, folio, start, len); btrfs_folio_set_writeback(fs_info, folio, start, len); btrfs_folio_clear_writeback(fs_info, folio, start, len); return ret; } for (cur = start; cur < start + len; cur += fs_info->sectorsize) set_bit((cur - folio_start) >> fs_info->sectorsize_bits, &range_bitmap); bitmap_and(&bio_ctrl->submit_bitmap, &bio_ctrl->submit_bitmap, &range_bitmap, blocks_per_folio); bio_ctrl->end_io_func = end_bbio_data_write; for_each_set_bit(bit, &bio_ctrl->submit_bitmap, blocks_per_folio) { cur = folio_pos(folio) + (bit << fs_info->sectorsize_bits); if (cur >= i_size) { btrfs_mark_ordered_io_finished(inode, folio, cur, start + len - cur, true); /* * This range is beyond i_size, thus we don't need to * bother writing back. * But we still need to clear the dirty subpage bit, or * the next time the folio gets dirtied, we will try to * writeback the sectors with subpage dirty bits, * causing writeback without ordered extent. */ btrfs_folio_clear_dirty(fs_info, folio, cur, start + len - cur); break; } ret = submit_one_sector(inode, folio, cur, bio_ctrl, i_size); if (unlikely(ret < 0)) { /* * bio_ctrl may contain a bio crossing several folios. * Submit it immediately so that the bio has a chance * to finish normally, other than marked as error. */ submit_one_bio(bio_ctrl); /* * Failed to grab the extent map which should be very rare. * Since there is no bio submitted to finish the ordered * extent, we have to manually finish this sector. */ btrfs_mark_ordered_io_finished(inode, folio, cur, fs_info->sectorsize, false); error = true; continue; } submitted_io = true; } /* * If we didn't submitted any sector (>= i_size), folio dirty get * cleared but PAGECACHE_TAG_DIRTY is not cleared (only cleared * by folio_start_writeback() if the folio is not dirty). * * Here we set writeback and clear for the range. If the full folio * is no longer dirty then we clear the PAGECACHE_TAG_DIRTY tag. * * If we hit any error, the corresponding sector will have its dirty * flag cleared and writeback finished, thus no need to handle the error case. */ if (!submitted_io && !error) { btrfs_folio_set_writeback(fs_info, folio, start, len); btrfs_folio_clear_writeback(fs_info, folio, start, len); } return ret; } /* * the writepage semantics are similar to regular writepage. extent * records are inserted to lock ranges in the tree, and as dirty areas * are found, they are marked writeback. Then the lock bits are removed * and the end_io handler clears the writeback ranges * * Return 0 if everything goes well. * Return <0 for error. */ static int extent_writepage(struct folio *folio, struct btrfs_bio_ctrl *bio_ctrl) { struct btrfs_inode *inode = BTRFS_I(folio->mapping->host); struct btrfs_fs_info *fs_info = inode->root->fs_info; int ret; size_t pg_offset; loff_t i_size = i_size_read(&inode->vfs_inode); const pgoff_t end_index = i_size >> PAGE_SHIFT; const unsigned int blocks_per_folio = btrfs_blocks_per_folio(fs_info, folio); trace_extent_writepage(folio, &inode->vfs_inode, bio_ctrl->wbc); WARN_ON(!folio_test_locked(folio)); pg_offset = offset_in_folio(folio, i_size); if (folio->index > end_index || (folio->index == end_index && !pg_offset)) { folio_invalidate(folio, 0, folio_size(folio)); folio_unlock(folio); return 0; } if (folio_contains(folio, end_index)) folio_zero_range(folio, pg_offset, folio_size(folio) - pg_offset); /* * Default to unlock the whole folio. * The proper bitmap can only be initialized until writepage_delalloc(). */ bio_ctrl->submit_bitmap = (unsigned long)-1; /* * If the page is dirty but without private set, it's marked dirty * without informing the fs. * Nowadays that is a bug, since the introduction of * pin_user_pages*(). * * So here we check if the page has private set to rule out such * case. * But we also have a long history of relying on the COW fixup, * so here we only enable this check for experimental builds until * we're sure it's safe. */ if (IS_ENABLED(CONFIG_BTRFS_EXPERIMENTAL) && unlikely(!folio_test_private(folio))) { WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG)); btrfs_err_rl(fs_info, "root %lld ino %llu folio %llu is marked dirty without notifying the fs", btrfs_root_id(inode->root), btrfs_ino(inode), folio_pos(folio)); ret = -EUCLEAN; goto done; } ret = set_folio_extent_mapped(folio); if (ret < 0) goto done; ret = writepage_delalloc(inode, folio, bio_ctrl); if (ret == 1) return 0; if (ret) goto done; ret = extent_writepage_io(inode, folio, folio_pos(folio), folio_size(folio), bio_ctrl, i_size); if (ret == 1) return 0; if (ret < 0) btrfs_err_rl(fs_info, "failed to submit blocks, root=%lld inode=%llu folio=%llu submit_bitmap=%*pbl: %d", btrfs_root_id(inode->root), btrfs_ino(inode), folio_pos(folio), blocks_per_folio, &bio_ctrl->submit_bitmap, ret); bio_ctrl->wbc->nr_to_write--; done: if (ret < 0) mapping_set_error(folio->mapping, ret); /* * Only unlock ranges that are submitted. As there can be some async * submitted ranges inside the folio. */ btrfs_folio_end_lock_bitmap(fs_info, folio, bio_ctrl->submit_bitmap); ASSERT(ret <= 0); return ret; } /* * Lock extent buffer status and pages for writeback. * * Return %false if the extent buffer doesn't need to be submitted (e.g. the * extent buffer is not dirty) * Return %true is the extent buffer is submitted to bio. */ static noinline_for_stack bool lock_extent_buffer_for_io(struct extent_buffer *eb, struct writeback_control *wbc) { struct btrfs_fs_info *fs_info = eb->fs_info; bool ret = false; btrfs_tree_lock(eb); while (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags)) { btrfs_tree_unlock(eb); if (wbc->sync_mode != WB_SYNC_ALL) return false; wait_on_extent_buffer_writeback(eb); btrfs_tree_lock(eb); } /* * We need to do this to prevent races in people who check if the eb is * under IO since we can end up having no IO bits set for a short period * of time. */ spin_lock(&eb->refs_lock); if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { XA_STATE(xas, &fs_info->buffer_tree, eb->start >> fs_info->nodesize_bits); unsigned long flags; set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); spin_unlock(&eb->refs_lock); xas_lock_irqsave(&xas, flags); xas_load(&xas); xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); xas_unlock_irqrestore(&xas, flags); btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN); percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, -eb->len, fs_info->dirty_metadata_batch); ret = true; } else { spin_unlock(&eb->refs_lock); } btrfs_tree_unlock(eb); return ret; } static void set_btree_ioerr(struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = eb->fs_info; set_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags); /* * A read may stumble upon this buffer later, make sure that it gets an * error and knows there was an error. */ clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); /* * We need to set the mapping with the io error as well because a write * error will flip the file system readonly, and then syncfs() will * return a 0 because we are readonly if we don't modify the err seq for * the superblock. */ mapping_set_error(eb->fs_info->btree_inode->i_mapping, -EIO); /* * If writeback for a btree extent that doesn't belong to a log tree * failed, increment the counter transaction->eb_write_errors. * We do this because while the transaction is running and before it's * committing (when we call filemap_fdata[write|wait]_range against * the btree inode), we might have * btree_inode->i_mapping->a_ops->writepages() called by the VM - if it * returns an error or an error happens during writeback, when we're * committing the transaction we wouldn't know about it, since the pages * can be no longer dirty nor marked anymore for writeback (if a * subsequent modification to the extent buffer didn't happen before the * transaction commit), which makes filemap_fdata[write|wait]_range not * able to find the pages which contain errors at transaction * commit time. So if this happens we must abort the transaction, * otherwise we commit a super block with btree roots that point to * btree nodes/leafs whose content on disk is invalid - either garbage * or the content of some node/leaf from a past generation that got * cowed or deleted and is no longer valid. * * Note: setting AS_EIO/AS_ENOSPC in the btree inode's i_mapping would * not be enough - we need to distinguish between log tree extents vs * non-log tree extents, and the next filemap_fdatawait_range() call * will catch and clear such errors in the mapping - and that call might * be from a log sync and not from a transaction commit. Also, checking * for the eb flag EXTENT_BUFFER_WRITE_ERR at transaction commit time is * not done and would not be reliable - the eb might have been released * from memory and reading it back again means that flag would not be * set (since it's a runtime flag, not persisted on disk). * * Using the flags below in the btree inode also makes us achieve the * goal of AS_EIO/AS_ENOSPC when writepages() returns success, started * writeback for all dirty pages and before filemap_fdatawait_range() * is called, the writeback for all dirty pages had already finished * with errors - because we were not using AS_EIO/AS_ENOSPC, * filemap_fdatawait_range() would return success, as it could not know * that writeback errors happened (the pages were no longer tagged for * writeback). */ switch (eb->log_index) { case -1: set_bit(BTRFS_FS_BTREE_ERR, &fs_info->flags); break; case 0: set_bit(BTRFS_FS_LOG1_ERR, &fs_info->flags); break; case 1: set_bit(BTRFS_FS_LOG2_ERR, &fs_info->flags); break; default: BUG(); /* unexpected, logic error */ } } static void buffer_tree_set_mark(const struct extent_buffer *eb, xa_mark_t mark) { struct btrfs_fs_info *fs_info = eb->fs_info; XA_STATE(xas, &fs_info->buffer_tree, eb->start >> fs_info->nodesize_bits); unsigned long flags; xas_lock_irqsave(&xas, flags); xas_load(&xas); xas_set_mark(&xas, mark); xas_unlock_irqrestore(&xas, flags); } static void buffer_tree_clear_mark(const struct extent_buffer *eb, xa_mark_t mark) { struct btrfs_fs_info *fs_info = eb->fs_info; XA_STATE(xas, &fs_info->buffer_tree, eb->start >> fs_info->nodesize_bits); unsigned long flags; xas_lock_irqsave(&xas, flags); xas_load(&xas); xas_clear_mark(&xas, mark); xas_unlock_irqrestore(&xas, flags); } static void buffer_tree_tag_for_writeback(struct btrfs_fs_info *fs_info, unsigned long start, unsigned long end) { XA_STATE(xas, &fs_info->buffer_tree, start); unsigned int tagged = 0; void *eb; xas_lock_irq(&xas); xas_for_each_marked(&xas, eb, end, PAGECACHE_TAG_DIRTY) { xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); if (++tagged % XA_CHECK_SCHED) continue; xas_pause(&xas); xas_unlock_irq(&xas); cond_resched(); xas_lock_irq(&xas); } xas_unlock_irq(&xas); } struct eb_batch { unsigned int nr; unsigned int cur; struct extent_buffer *ebs[PAGEVEC_SIZE]; }; static inline bool eb_batch_add(struct eb_batch *batch, struct extent_buffer *eb) { batch->ebs[batch->nr++] = eb; return (batch->nr < PAGEVEC_SIZE); } static inline void eb_batch_init(struct eb_batch *batch) { batch->nr = 0; batch->cur = 0; } static inline struct extent_buffer *eb_batch_next(struct eb_batch *batch) { if (batch->cur >= batch->nr) return NULL; return batch->ebs[batch->cur++]; } static inline void eb_batch_release(struct eb_batch *batch) { for (unsigned int i = 0; i < batch->nr; i++) free_extent_buffer(batch->ebs[i]); eb_batch_init(batch); } static inline struct extent_buffer *find_get_eb(struct xa_state *xas, unsigned long max, xa_mark_t mark) { struct extent_buffer *eb; retry: eb = xas_find_marked(xas, max, mark); if (xas_retry(xas, eb)) goto retry; if (!eb) return NULL; if (!refcount_inc_not_zero(&eb->refs)) { xas_reset(xas); goto retry; } if (unlikely(eb != xas_reload(xas))) { free_extent_buffer(eb); xas_reset(xas); goto retry; } return eb; } static unsigned int buffer_tree_get_ebs_tag(struct btrfs_fs_info *fs_info, unsigned long *start, unsigned long end, xa_mark_t tag, struct eb_batch *batch) { XA_STATE(xas, &fs_info->buffer_tree, *start); struct extent_buffer *eb; rcu_read_lock(); while ((eb = find_get_eb(&xas, end, tag)) != NULL) { if (!eb_batch_add(batch, eb)) { *start = ((eb->start + eb->len) >> fs_info->nodesize_bits); goto out; } } if (end == ULONG_MAX) *start = ULONG_MAX; else *start = end + 1; out: rcu_read_unlock(); return batch->nr; } /* * The endio specific version which won't touch any unsafe spinlock in endio * context. */ static struct extent_buffer *find_extent_buffer_nolock( struct btrfs_fs_info *fs_info, u64 start) { struct extent_buffer *eb; unsigned long index = (start >> fs_info->nodesize_bits); rcu_read_lock(); eb = xa_load(&fs_info->buffer_tree, index); if (eb && !refcount_inc_not_zero(&eb->refs)) eb = NULL; rcu_read_unlock(); return eb; } static void end_bbio_meta_write(struct btrfs_bio *bbio) { struct extent_buffer *eb = bbio->private; struct folio_iter fi; if (bbio->bio.bi_status != BLK_STS_OK) set_btree_ioerr(eb); bio_for_each_folio_all(fi, &bbio->bio) { btrfs_meta_folio_clear_writeback(fi.folio, eb); } buffer_tree_clear_mark(eb, PAGECACHE_TAG_WRITEBACK); clear_and_wake_up_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags); bio_put(&bbio->bio); } static void prepare_eb_write(struct extent_buffer *eb) { u32 nritems; unsigned long start; unsigned long end; clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags); /* Set btree blocks beyond nritems with 0 to avoid stale content */ nritems = btrfs_header_nritems(eb); if (btrfs_header_level(eb) > 0) { end = btrfs_node_key_ptr_offset(eb, nritems); memzero_extent_buffer(eb, end, eb->len - end); } else { /* * Leaf: * header 0 1 2 .. N ... data_N .. data_2 data_1 data_0 */ start = btrfs_item_nr_offset(eb, nritems); end = btrfs_item_nr_offset(eb, 0); if (nritems == 0) end += BTRFS_LEAF_DATA_SIZE(eb->fs_info); else end += btrfs_item_offset(eb, nritems - 1); memzero_extent_buffer(eb, start, end - start); } } static noinline_for_stack void write_one_eb(struct extent_buffer *eb, struct writeback_control *wbc) { struct btrfs_fs_info *fs_info = eb->fs_info; struct btrfs_bio *bbio; prepare_eb_write(eb); bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES, REQ_OP_WRITE | REQ_META | wbc_to_write_flags(wbc), eb->fs_info, end_bbio_meta_write, eb); bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT; bio_set_dev(&bbio->bio, fs_info->fs_devices->latest_dev->bdev); wbc_init_bio(wbc, &bbio->bio); bbio->inode = BTRFS_I(eb->fs_info->btree_inode); bbio->file_offset = eb->start; for (int i = 0; i < num_extent_folios(eb); i++) { struct folio *folio = eb->folios[i]; u64 range_start = max_t(u64, eb->start, folio_pos(folio)); u32 range_len = min_t(u64, folio_end(folio), eb->start + eb->len) - range_start; folio_lock(folio); btrfs_meta_folio_clear_dirty(folio, eb); btrfs_meta_folio_set_writeback(folio, eb); if (!folio_test_dirty(folio)) wbc->nr_to_write -= folio_nr_pages(folio); bio_add_folio_nofail(&bbio->bio, folio, range_len, offset_in_folio(folio, range_start)); wbc_account_cgroup_owner(wbc, folio, range_len); folio_unlock(folio); } btrfs_submit_bbio(bbio, 0); } /* * Wait for all eb writeback in the given range to finish. * * @fs_info: The fs_info for this file system. * @start: The offset of the range to start waiting on writeback. * @end: The end of the range, inclusive. This is meant to be used in * conjuction with wait_marked_extents, so this will usually be * the_next_eb->start - 1. */ void btrfs_btree_wait_writeback_range(struct btrfs_fs_info *fs_info, u64 start, u64 end) { struct eb_batch batch; unsigned long start_index = (start >> fs_info->nodesize_bits); unsigned long end_index = (end >> fs_info->nodesize_bits); eb_batch_init(&batch); while (start_index <= end_index) { struct extent_buffer *eb; unsigned int nr_ebs; nr_ebs = buffer_tree_get_ebs_tag(fs_info, &start_index, end_index, PAGECACHE_TAG_WRITEBACK, &batch); if (!nr_ebs) break; while ((eb = eb_batch_next(&batch)) != NULL) wait_on_extent_buffer_writeback(eb); eb_batch_release(&batch); cond_resched(); } } int btree_write_cache_pages(struct address_space *mapping, struct writeback_control *wbc) { struct btrfs_eb_write_context ctx = { .wbc = wbc }; struct btrfs_fs_info *fs_info = inode_to_fs_info(mapping->host); int ret = 0; int done = 0; int nr_to_write_done = 0; struct eb_batch batch; unsigned int nr_ebs; unsigned long index; unsigned long end; int scanned = 0; xa_mark_t tag; eb_batch_init(&batch); if (wbc->range_cyclic) { index = ((mapping->writeback_index << PAGE_SHIFT) >> fs_info->nodesize_bits); end = -1; /* * Start from the beginning does not need to cycle over the * range, mark it as scanned. */ scanned = (index == 0); } else { index = (wbc->range_start >> fs_info->nodesize_bits); end = (wbc->range_end >> fs_info->nodesize_bits); scanned = 1; } if (wbc->sync_mode == WB_SYNC_ALL) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; btrfs_zoned_meta_io_lock(fs_info); retry: if (wbc->sync_mode == WB_SYNC_ALL) buffer_tree_tag_for_writeback(fs_info, index, end); while (!done && !nr_to_write_done && (index <= end) && (nr_ebs = buffer_tree_get_ebs_tag(fs_info, &index, end, tag, &batch))) { struct extent_buffer *eb; while ((eb = eb_batch_next(&batch)) != NULL) { ctx.eb = eb; ret = btrfs_check_meta_write_pointer(eb->fs_info, &ctx); if (ret) { if (ret == -EBUSY) ret = 0; if (ret) { done = 1; break; } continue; } if (!lock_extent_buffer_for_io(eb, wbc)) continue; /* Implies write in zoned mode. */ if (ctx.zoned_bg) { /* Mark the last eb in the block group. */ btrfs_schedule_zone_finish_bg(ctx.zoned_bg, eb); ctx.zoned_bg->meta_write_pointer += eb->len; } write_one_eb(eb, wbc); } nr_to_write_done = (wbc->nr_to_write <= 0); eb_batch_release(&batch); cond_resched(); } if (!scanned && !done) { /* * We hit the last page and there is more work to be done: wrap * back to the start of the file */ scanned = 1; index = 0; goto retry; } /* * If something went wrong, don't allow any metadata write bio to be * submitted. * * This would prevent use-after-free if we had dirty pages not * cleaned up, which can still happen by fuzzed images. * * - Bad extent tree * Allowing existing tree block to be allocated for other trees. * * - Log tree operations * Exiting tree blocks get allocated to log tree, bumps its * generation, then get cleaned in tree re-balance. * Such tree block will not be written back, since it's clean, * thus no WRITTEN flag set. * And after log writes back, this tree block is not traced by * any dirty extent_io_tree. * * - Offending tree block gets re-dirtied from its original owner * Since it has bumped generation, no WRITTEN flag, it can be * reused without COWing. This tree block will not be traced * by btrfs_transaction::dirty_pages. * * Now such dirty tree block will not be cleaned by any dirty * extent io tree. Thus we don't want to submit such wild eb * if the fs already has error. * * We can get ret > 0 from submit_extent_folio() indicating how many ebs * were submitted. Reset it to 0 to avoid false alerts for the caller. */ if (ret > 0) ret = 0; if (!ret && BTRFS_FS_ERROR(fs_info)) ret = -EROFS; if (ctx.zoned_bg) btrfs_put_block_group(ctx.zoned_bg); btrfs_zoned_meta_io_unlock(fs_info); return ret; } /* * Walk the list of dirty pages of the given address space and write all of them. * * @mapping: address space structure to write * @wbc: subtract the number of written pages from *@wbc->nr_to_write * @bio_ctrl: holds context for the write, namely the bio * * If a page is already under I/O, write_cache_pages() skips it, even * if it's dirty. This is desirable behaviour for memory-cleaning writeback, * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() * and msync() need to guarantee that all the data which was dirty at the time * the call was made get new I/O started against them. If wbc->sync_mode is * WB_SYNC_ALL then we were called for data integrity and we must wait for * existing IO to complete. */ static int extent_write_cache_pages(struct address_space *mapping, struct btrfs_bio_ctrl *bio_ctrl) { struct writeback_control *wbc = bio_ctrl->wbc; struct inode *inode = mapping->host; int ret = 0; int done = 0; int nr_to_write_done = 0; struct folio_batch fbatch; unsigned int nr_folios; pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; int range_whole = 0; int scanned = 0; xa_mark_t tag; /* * We have to hold onto the inode so that ordered extents can do their * work when the IO finishes. The alternative to this is failing to add * an ordered extent if the igrab() fails there and that is a huge pain * to deal with, so instead just hold onto the inode throughout the * writepages operation. If it fails here we are freeing up the inode * anyway and we'd rather not waste our time writing out stuff that is * going to be truncated anyway. */ if (!igrab(inode)) return 0; folio_batch_init(&fbatch); if (wbc->range_cyclic) { index = mapping->writeback_index; /* Start from prev offset */ end = -1; /* * Start from the beginning does not need to cycle over the * range, mark it as scanned. */ scanned = (index == 0); } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; scanned = 1; } /* * We do the tagged writepage as long as the snapshot flush bit is set * and we are the first one who do the filemap_flush() on this inode. * * The nr_to_write == LONG_MAX is needed to make sure other flushers do * not race in and drop the bit. */ if (range_whole && wbc->nr_to_write == LONG_MAX && test_and_clear_bit(BTRFS_INODE_SNAPSHOT_FLUSH, &BTRFS_I(inode)->runtime_flags)) wbc->tagged_writepages = 1; if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, index, end); done_index = index; while (!done && !nr_to_write_done && (index <= end) && (nr_folios = filemap_get_folios_tag(mapping, &index, end, tag, &fbatch))) { unsigned i; for (i = 0; i < nr_folios; i++) { struct folio *folio = fbatch.folios[i]; done_index = folio_next_index(folio); /* * At this point we hold neither the i_pages lock nor * the folio lock: the folio may be truncated or * invalidated (changing folio->mapping to NULL). */ if (!folio_trylock(folio)) { submit_write_bio(bio_ctrl, 0); folio_lock(folio); } if (unlikely(folio->mapping != mapping)) { folio_unlock(folio); continue; } if (!folio_test_dirty(folio)) { /* Someone wrote it for us. */ folio_unlock(folio); continue; } /* * For subpage case, compression can lead to mixed * writeback and dirty flags, e.g: * 0 32K 64K 96K 128K * | |//////||/////| |//| * * In above case, [32K, 96K) is asynchronously submitted * for compression, and [124K, 128K) needs to be written back. * * If we didn't wait wrtiteback for page 64K, [128K, 128K) * won't be submitted as the page still has writeback flag * and will be skipped in the next check. * * This mixed writeback and dirty case is only possible for * subpage case. * * TODO: Remove this check after migrating compression to * regular submission. */ if (wbc->sync_mode != WB_SYNC_NONE || btrfs_is_subpage(inode_to_fs_info(inode), folio)) { if (folio_test_writeback(folio)) submit_write_bio(bio_ctrl, 0); folio_wait_writeback(folio); } if (folio_test_writeback(folio) || !folio_clear_dirty_for_io(folio)) { folio_unlock(folio); continue; } ret = extent_writepage(folio, bio_ctrl); if (ret < 0) { done = 1; break; } /* * The filesystem may choose to bump up nr_to_write. * We have to make sure to honor the new nr_to_write * at any time. */ nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE && wbc->nr_to_write <= 0); } folio_batch_release(&fbatch); cond_resched(); } if (!scanned && !done) { /* * We hit the last page and there is more work to be done: wrap * back to the start of the file */ scanned = 1; index = 0; /* * If we're looping we could run into a page that is locked by a * writer and that writer could be waiting on writeback for a * page in our current bio, and thus deadlock, so flush the * write bio here. */ submit_write_bio(bio_ctrl, 0); goto retry; } if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole)) mapping->writeback_index = done_index; btrfs_add_delayed_iput(BTRFS_I(inode)); return ret; } /* * Submit the pages in the range to bio for call sites which delalloc range has * already been ran (aka, ordered extent inserted) and all pages are still * locked. */ void extent_write_locked_range(struct inode *inode, const struct folio *locked_folio, u64 start, u64 end, struct writeback_control *wbc, bool pages_dirty) { bool found_error = false; int ret = 0; struct address_space *mapping = inode->i_mapping; struct btrfs_fs_info *fs_info = inode_to_fs_info(inode); const u32 sectorsize = fs_info->sectorsize; loff_t i_size = i_size_read(inode); u64 cur = start; struct btrfs_bio_ctrl bio_ctrl = { .wbc = wbc, .opf = REQ_OP_WRITE | wbc_to_write_flags(wbc), }; if (wbc->no_cgroup_owner) bio_ctrl.opf |= REQ_BTRFS_CGROUP_PUNT; ASSERT(IS_ALIGNED(start, sectorsize) && IS_ALIGNED(end + 1, sectorsize)); while (cur <= end) { u64 cur_end; u32 cur_len; struct folio *folio; folio = filemap_get_folio(mapping, cur >> PAGE_SHIFT); /* * This shouldn't happen, the pages are pinned and locked, this * code is just in case, but shouldn't actually be run. */ if (IS_ERR(folio)) { cur_end = min(round_down(cur, PAGE_SIZE) + PAGE_SIZE - 1, end); cur_len = cur_end + 1 - cur; btrfs_mark_ordered_io_finished(BTRFS_I(inode), NULL, cur, cur_len, false); mapping_set_error(mapping, PTR_ERR(folio)); cur = cur_end; continue; } cur_end = min_t(u64, folio_end(folio) - 1, end); cur_len = cur_end + 1 - cur; ASSERT(folio_test_locked(folio)); if (pages_dirty && folio != locked_folio) ASSERT(folio_test_dirty(folio)); /* * Set the submission bitmap to submit all sectors. * extent_writepage_io() will do the truncation correctly. */ bio_ctrl.submit_bitmap = (unsigned long)-1; ret = extent_writepage_io(BTRFS_I(inode), folio, cur, cur_len, &bio_ctrl, i_size); if (ret == 1) goto next_page; if (ret) mapping_set_error(mapping, ret); btrfs_folio_end_lock(fs_info, folio, cur, cur_len); if (ret < 0) found_error = true; next_page: folio_put(folio); cur = cur_end + 1; } submit_write_bio(&bio_ctrl, found_error ? ret : 0); } int btrfs_writepages(struct address_space *mapping, struct writeback_control *wbc) { struct inode *inode = mapping->host; int ret = 0; struct btrfs_bio_ctrl bio_ctrl = { .wbc = wbc, .opf = REQ_OP_WRITE | wbc_to_write_flags(wbc), }; /* * Allow only a single thread to do the reloc work in zoned mode to * protect the write pointer updates. */ btrfs_zoned_data_reloc_lock(BTRFS_I(inode)); ret = extent_write_cache_pages(mapping, &bio_ctrl); submit_write_bio(&bio_ctrl, ret); btrfs_zoned_data_reloc_unlock(BTRFS_I(inode)); return ret; } void btrfs_readahead(struct readahead_control *rac) { struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD, .ractl = rac, .last_em_start = U64_MAX, }; struct folio *folio; struct btrfs_inode *inode = BTRFS_I(rac->mapping->host); const u64 start = readahead_pos(rac); const u64 end = start + readahead_length(rac) - 1; struct extent_state *cached_state = NULL; struct extent_map *em_cached = NULL; lock_extents_for_read(inode, start, end, &cached_state); while ((folio = readahead_folio(rac)) != NULL) btrfs_do_readpage(folio, &em_cached, &bio_ctrl); btrfs_unlock_extent(&inode->io_tree, start, end, &cached_state); if (em_cached) btrfs_free_extent_map(em_cached); submit_one_bio(&bio_ctrl); } /* * basic invalidate_folio code, this waits on any locked or writeback * ranges corresponding to the folio, and then deletes any extent state * records from the tree */ int extent_invalidate_folio(struct extent_io_tree *tree, struct folio *folio, size_t offset) { struct extent_state *cached_state = NULL; u64 start = folio_pos(folio); u64 end = start + folio_size(folio) - 1; size_t blocksize = folio_to_fs_info(folio)->sectorsize; /* This function is only called for the btree inode */ ASSERT(tree->owner == IO_TREE_BTREE_INODE_IO); start += ALIGN(offset, blocksize); if (start > end) return 0; btrfs_lock_extent(tree, start, end, &cached_state); folio_wait_writeback(folio); /* * Currently for btree io tree, only EXTENT_LOCKED is utilized, * so here we only need to unlock the extent range to free any * existing extent state. */ btrfs_unlock_extent(tree, start, end, &cached_state); return 0; } /* * A helper for struct address_space_operations::release_folio, this tests for * areas of the folio that are locked or under IO and drops the related state * bits if it is safe to drop the folio. */ static bool try_release_extent_state(struct extent_io_tree *tree, struct folio *folio) { struct extent_state *cached_state = NULL; u64 start = folio_pos(folio); u64 end = start + folio_size(folio) - 1; u32 range_bits; u32 clear_bits; bool ret = false; int ret2; btrfs_get_range_bits(tree, start, end, &range_bits, &cached_state); /* * We can release the folio if it's locked only for ordered extent * completion, since that doesn't require using the folio. */ if ((range_bits & EXTENT_LOCKED) && !(range_bits & EXTENT_FINISHING_ORDERED)) goto out; clear_bits = ~(EXTENT_LOCKED | EXTENT_NODATASUM | EXTENT_DELALLOC_NEW | EXTENT_CTLBITS | EXTENT_QGROUP_RESERVED | EXTENT_FINISHING_ORDERED); /* * At this point we can safely clear everything except the locked, * nodatasum, delalloc new and finishing ordered bits. The delalloc new * bit will be cleared by ordered extent completion. */ ret2 = btrfs_clear_extent_bit(tree, start, end, clear_bits, &cached_state); /* * If clear_extent_bit failed for enomem reasons, we can't allow the * release to continue. */ if (ret2 == 0) ret = true; out: btrfs_free_extent_state(cached_state); return ret; } /* * a helper for release_folio. As long as there are no locked extents * in the range corresponding to the page, both state records and extent * map records are removed */ bool try_release_extent_mapping(struct folio *folio, gfp_t mask) { u64 start = folio_pos(folio); u64 end = start + folio_size(folio) - 1; struct btrfs_inode *inode = folio_to_inode(folio); struct extent_io_tree *io_tree = &inode->io_tree; while (start <= end) { const u64 cur_gen = btrfs_get_fs_generation(inode->root->fs_info); const u64 len = end - start + 1; struct extent_map_tree *extent_tree = &inode->extent_tree; struct extent_map *em; write_lock(&extent_tree->lock); em = btrfs_lookup_extent_mapping(extent_tree, start, len); if (!em) { write_unlock(&extent_tree->lock); break; } if ((em->flags & EXTENT_FLAG_PINNED) || em->start != start) { write_unlock(&extent_tree->lock); btrfs_free_extent_map(em); break; } if (btrfs_test_range_bit_exists(io_tree, em->start, btrfs_extent_map_end(em) - 1, EXTENT_LOCKED)) goto next; /* * If it's not in the list of modified extents, used by a fast * fsync, we can remove it. If it's being logged we can safely * remove it since fsync took an extra reference on the em. */ if (list_empty(&em->list) || (em->flags & EXTENT_FLAG_LOGGING)) goto remove_em; /* * If it's in the list of modified extents, remove it only if * its generation is older then the current one, in which case * we don't need it for a fast fsync. Otherwise don't remove it, * we could be racing with an ongoing fast fsync that could miss * the new extent. */ if (em->generation >= cur_gen) goto next; remove_em: /* * We only remove extent maps that are not in the list of * modified extents or that are in the list but with a * generation lower then the current generation, so there is no * need to set the full fsync flag on the inode (it hurts the * fsync performance for workloads with a data size that exceeds * or is close to the system's memory). */ btrfs_remove_extent_mapping(inode, em); /* Once for the inode's extent map tree. */ btrfs_free_extent_map(em); next: start = btrfs_extent_map_end(em); write_unlock(&extent_tree->lock); /* Once for us, for the lookup_extent_mapping() reference. */ btrfs_free_extent_map(em); if (need_resched()) { /* * If we need to resched but we can't block just exit * and leave any remaining extent maps. */ if (!gfpflags_allow_blocking(mask)) break; cond_resched(); } } return try_release_extent_state(io_tree, folio); } static int extent_buffer_under_io(const struct extent_buffer *eb) { return (test_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags) || test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); } static bool folio_range_has_eb(struct folio *folio) { struct btrfs_folio_state *bfs; lockdep_assert_held(&folio->mapping->i_private_lock); if (folio_test_private(folio)) { bfs = folio_get_private(folio); if (atomic_read(&bfs->eb_refs)) return true; } return false; } static void detach_extent_buffer_folio(const struct extent_buffer *eb, struct folio *folio) { struct btrfs_fs_info *fs_info = eb->fs_info; struct address_space *mapping = folio->mapping; const bool mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags); /* * For mapped eb, we're going to change the folio private, which should * be done under the i_private_lock. */ if (mapped) spin_lock(&mapping->i_private_lock); if (!folio_test_private(folio)) { if (mapped) spin_unlock(&mapping->i_private_lock); return; } if (!btrfs_meta_is_subpage(fs_info)) { /* * We do this since we'll remove the pages after we've removed * the eb from the xarray, so we could race and have this page * now attached to the new eb. So only clear folio if it's * still connected to this eb. */ if (folio_test_private(folio) && folio_get_private(folio) == eb) { BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)); BUG_ON(folio_test_dirty(folio)); BUG_ON(folio_test_writeback(folio)); /* We need to make sure we haven't be attached to a new eb. */ folio_detach_private(folio); } if (mapped) spin_unlock(&mapping->i_private_lock); return; } /* * For subpage, we can have dummy eb with folio private attached. In * this case, we can directly detach the private as such folio is only * attached to one dummy eb, no sharing. */ if (!mapped) { btrfs_detach_folio_state(fs_info, folio, BTRFS_SUBPAGE_METADATA); return; } btrfs_folio_dec_eb_refs(fs_info, folio); /* * We can only detach the folio private if there are no other ebs in the * page range and no unfinished IO. */ if (!folio_range_has_eb(folio)) btrfs_detach_folio_state(fs_info, folio, BTRFS_SUBPAGE_METADATA); spin_unlock(&mapping->i_private_lock); } /* Release all folios attached to the extent buffer */ static void btrfs_release_extent_buffer_folios(const struct extent_buffer *eb) { ASSERT(!extent_buffer_under_io(eb)); for (int i = 0; i < INLINE_EXTENT_BUFFER_PAGES; i++) { struct folio *folio = eb->folios[i]; if (!folio) continue; detach_extent_buffer_folio(eb, folio); } } /* * Helper for releasing the extent buffer. */ static inline void btrfs_release_extent_buffer(struct extent_buffer *eb) { btrfs_release_extent_buffer_folios(eb); btrfs_leak_debug_del_eb(eb); kmem_cache_free(extent_buffer_cache, eb); } static struct extent_buffer *__alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start) { struct extent_buffer *eb = NULL; eb = kmem_cache_zalloc(extent_buffer_cache, GFP_NOFS|__GFP_NOFAIL); eb->start = start; eb->len = fs_info->nodesize; eb->fs_info = fs_info; init_rwsem(&eb->lock); btrfs_leak_debug_add_eb(eb); spin_lock_init(&eb->refs_lock); refcount_set(&eb->refs, 1); ASSERT(eb->len <= BTRFS_MAX_METADATA_BLOCKSIZE); return eb; } /* * For use in eb allocation error cleanup paths, as btrfs_release_extent_buffer() * does not call folio_put(), and we need to set the folios to NULL so that * btrfs_release_extent_buffer() will not detach them a second time. */ static void cleanup_extent_buffer_folios(struct extent_buffer *eb) { const int num_folios = num_extent_folios(eb); /* We canont use num_extent_folios() as loop bound as eb->folios changes. */ for (int i = 0; i < num_folios; i++) { ASSERT(eb->folios[i]); detach_extent_buffer_folio(eb, eb->folios[i]); folio_put(eb->folios[i]); eb->folios[i] = NULL; } } struct extent_buffer *btrfs_clone_extent_buffer(const struct extent_buffer *src) { struct extent_buffer *new; int num_folios; int ret; new = __alloc_extent_buffer(src->fs_info, src->start); if (new == NULL) return NULL; /* * Set UNMAPPED before calling btrfs_release_extent_buffer(), as * btrfs_release_extent_buffer() have different behavior for * UNMAPPED subpage extent buffer. */ set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags); ret = alloc_eb_folio_array(new, false); if (ret) goto release_eb; ASSERT(num_extent_folios(src) == num_extent_folios(new), "%d != %d", num_extent_folios(src), num_extent_folios(new)); /* Explicitly use the cached num_extent value from now on. */ num_folios = num_extent_folios(src); for (int i = 0; i < num_folios; i++) { struct folio *folio = new->folios[i]; ret = attach_extent_buffer_folio(new, folio, NULL); if (ret < 0) goto cleanup_folios; WARN_ON(folio_test_dirty(folio)); } for (int i = 0; i < num_folios; i++) folio_put(new->folios[i]); copy_extent_buffer_full(new, src); set_extent_buffer_uptodate(new); return new; cleanup_folios: cleanup_extent_buffer_folios(new); release_eb: btrfs_release_extent_buffer(new); return NULL; } struct extent_buffer *alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info, u64 start) { struct extent_buffer *eb; int ret; eb = __alloc_extent_buffer(fs_info, start); if (!eb) return NULL; ret = alloc_eb_folio_array(eb, false); if (ret) goto release_eb; for (int i = 0; i < num_extent_folios(eb); i++) { ret = attach_extent_buffer_folio(eb, eb->folios[i], NULL); if (ret < 0) goto cleanup_folios; } for (int i = 0; i < num_extent_folios(eb); i++) folio_put(eb->folios[i]); set_extent_buffer_uptodate(eb); btrfs_set_header_nritems(eb, 0); set_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags); return eb; cleanup_folios: cleanup_extent_buffer_folios(eb); release_eb: btrfs_release_extent_buffer(eb); return NULL; } static void check_buffer_tree_ref(struct extent_buffer *eb) { int refs; /* * The TREE_REF bit is first set when the extent_buffer is added to the * xarray. It is also reset, if unset, when a new reference is created * by find_extent_buffer. * * It is only cleared in two cases: freeing the last non-tree * reference to the extent_buffer when its STALE bit is set or * calling release_folio when the tree reference is the only reference. * * In both cases, care is taken to ensure that the extent_buffer's * pages are not under io. However, release_folio can be concurrently * called with creating new references, which is prone to race * conditions between the calls to check_buffer_tree_ref in those * codepaths and clearing TREE_REF in try_release_extent_buffer. * * The actual lifetime of the extent_buffer in the xarray is adequately * protected by the refcount, but the TREE_REF bit and its corresponding * reference are not. To protect against this class of races, we call * check_buffer_tree_ref() from the code paths which trigger io. Note that * once io is initiated, TREE_REF can no longer be cleared, so that is * the moment at which any such race is best fixed. */ refs = refcount_read(&eb->refs); if (refs >= 2 && test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) return; spin_lock(&eb->refs_lock); if (!test_and_set_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) refcount_inc(&eb->refs); spin_unlock(&eb->refs_lock); } static void mark_extent_buffer_accessed(struct extent_buffer *eb) { check_buffer_tree_ref(eb); for (int i = 0; i < num_extent_folios(eb); i++) folio_mark_accessed(eb->folios[i]); } struct extent_buffer *find_extent_buffer(struct btrfs_fs_info *fs_info, u64 start) { struct extent_buffer *eb; eb = find_extent_buffer_nolock(fs_info, start); if (!eb) return NULL; /* * Lock our eb's refs_lock to avoid races with free_extent_buffer(). * When we get our eb it might be flagged with EXTENT_BUFFER_STALE and * another task running free_extent_buffer() might have seen that flag * set, eb->refs == 2, that the buffer isn't under IO (dirty and * writeback flags not set) and it's still in the tree (flag * EXTENT_BUFFER_TREE_REF set), therefore being in the process of * decrementing the extent buffer's reference count twice. So here we * could race and increment the eb's reference count, clear its stale * flag, mark it as dirty and drop our reference before the other task * finishes executing free_extent_buffer, which would later result in * an attempt to free an extent buffer that is dirty. */ if (test_bit(EXTENT_BUFFER_STALE, &eb->bflags)) { spin_lock(&eb->refs_lock); spin_unlock(&eb->refs_lock); } mark_extent_buffer_accessed(eb); return eb; } struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info, u64 start) { #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS struct extent_buffer *eb, *exists = NULL; int ret; eb = find_extent_buffer(fs_info, start); if (eb) return eb; eb = alloc_dummy_extent_buffer(fs_info, start); if (!eb) return ERR_PTR(-ENOMEM); eb->fs_info = fs_info; again: xa_lock_irq(&fs_info->buffer_tree); exists = __xa_cmpxchg(&fs_info->buffer_tree, start >> fs_info->nodesize_bits, NULL, eb, GFP_NOFS); if (xa_is_err(exists)) { ret = xa_err(exists); xa_unlock_irq(&fs_info->buffer_tree); btrfs_release_extent_buffer(eb); return ERR_PTR(ret); } if (exists) { if (!refcount_inc_not_zero(&exists->refs)) { /* The extent buffer is being freed, retry. */ xa_unlock_irq(&fs_info->buffer_tree); goto again; } xa_unlock_irq(&fs_info->buffer_tree); btrfs_release_extent_buffer(eb); return exists; } xa_unlock_irq(&fs_info->buffer_tree); check_buffer_tree_ref(eb); return eb; #else /* Stub to avoid linker error when compiled with optimizations turned off. */ return NULL; #endif } static struct extent_buffer *grab_extent_buffer(struct btrfs_fs_info *fs_info, struct folio *folio) { struct extent_buffer *exists; lockdep_assert_held(&folio->mapping->i_private_lock); /* * For subpage case, we completely rely on xarray to ensure we don't try * to insert two ebs for the same bytenr. So here we always return NULL * and just continue. */ if (btrfs_meta_is_subpage(fs_info)) return NULL; /* Page not yet attached to an extent buffer */ if (!folio_test_private(folio)) return NULL; /* * We could have already allocated an eb for this folio and attached one * so lets see if we can get a ref on the existing eb, and if we can we * know it's good and we can just return that one, else we know we can * just overwrite folio private. */ exists = folio_get_private(folio); if (refcount_inc_not_zero(&exists->refs)) return exists; WARN_ON(folio_test_dirty(folio)); folio_detach_private(folio); return NULL; } /* * Validate alignment constraints of eb at logical address @start. */ static bool check_eb_alignment(struct btrfs_fs_info *fs_info, u64 start) { if (!IS_ALIGNED(start, fs_info->sectorsize)) { btrfs_err(fs_info, "bad tree block start %llu", start); return true; } if (fs_info->nodesize < PAGE_SIZE && !IS_ALIGNED(start, fs_info->nodesize)) { btrfs_err(fs_info, "tree block is not nodesize aligned, start %llu nodesize %u", start, fs_info->nodesize); return true; } if (fs_info->nodesize >= PAGE_SIZE && !PAGE_ALIGNED(start)) { btrfs_err(fs_info, "tree block is not page aligned, start %llu nodesize %u", start, fs_info->nodesize); return true; } if (!IS_ALIGNED(start, fs_info->nodesize) && !test_and_set_bit(BTRFS_FS_UNALIGNED_TREE_BLOCK, &fs_info->flags)) { btrfs_warn(fs_info, "tree block not nodesize aligned, start %llu nodesize %u, can be resolved by a full metadata balance", start, fs_info->nodesize); } return false; } /* * Return 0 if eb->folios[i] is attached to btree inode successfully. * Return >0 if there is already another extent buffer for the range, * and @found_eb_ret would be updated. * Return -EAGAIN if the filemap has an existing folio but with different size * than @eb. * The caller needs to free the existing folios and retry using the same order. */ static int attach_eb_folio_to_filemap(struct extent_buffer *eb, int i, struct btrfs_folio_state *prealloc, struct extent_buffer **found_eb_ret) { struct btrfs_fs_info *fs_info = eb->fs_info; struct address_space *mapping = fs_info->btree_inode->i_mapping; const pgoff_t index = eb->start >> PAGE_SHIFT; struct folio *existing_folio; int ret; ASSERT(found_eb_ret); /* Caller should ensure the folio exists. */ ASSERT(eb->folios[i]); retry: existing_folio = NULL; ret = filemap_add_folio(mapping, eb->folios[i], index + i, GFP_NOFS | __GFP_NOFAIL); if (!ret) goto finish; existing_folio = filemap_lock_folio(mapping, index + i); /* The page cache only exists for a very short time, just retry. */ if (IS_ERR(existing_folio)) goto retry; /* For now, we should only have single-page folios for btree inode. */ ASSERT(folio_nr_pages(existing_folio) == 1); if (folio_size(existing_folio) != eb->folio_size) { folio_unlock(existing_folio); folio_put(existing_folio); return -EAGAIN; } finish: spin_lock(&mapping->i_private_lock); if (existing_folio && btrfs_meta_is_subpage(fs_info)) { /* We're going to reuse the existing page, can drop our folio now. */ __free_page(folio_page(eb->folios[i], 0)); eb->folios[i] = existing_folio; } else if (existing_folio) { struct extent_buffer *existing_eb; existing_eb = grab_extent_buffer(fs_info, existing_folio); if (existing_eb) { /* The extent buffer still exists, we can use it directly. */ *found_eb_ret = existing_eb; spin_unlock(&mapping->i_private_lock); folio_unlock(existing_folio); folio_put(existing_folio); return 1; } /* The extent buffer no longer exists, we can reuse the folio. */ __free_page(folio_page(eb->folios[i], 0)); eb->folios[i] = existing_folio; } eb->folio_size = folio_size(eb->folios[i]); eb->folio_shift = folio_shift(eb->folios[i]); /* Should not fail, as we have preallocated the memory. */ ret = attach_extent_buffer_folio(eb, eb->folios[i], prealloc); ASSERT(!ret); /* * To inform we have an extra eb under allocation, so that * detach_extent_buffer_page() won't release the folio private when the * eb hasn't been inserted into the xarray yet. * * The ref will be decreased when the eb releases the page, in * detach_extent_buffer_page(). Thus needs no special handling in the * error path. */ btrfs_folio_inc_eb_refs(fs_info, eb->folios[i]); spin_unlock(&mapping->i_private_lock); return 0; } struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start, u64 owner_root, int level) { int attached = 0; struct extent_buffer *eb; struct extent_buffer *existing_eb = NULL; struct btrfs_folio_state *prealloc = NULL; u64 lockdep_owner = owner_root; bool page_contig = true; int uptodate = 1; int ret; if (check_eb_alignment(fs_info, start)) return ERR_PTR(-EINVAL); #if BITS_PER_LONG == 32 if (start >= MAX_LFS_FILESIZE) { btrfs_err_rl(fs_info, "extent buffer %llu is beyond 32bit page cache limit", start); btrfs_err_32bit_limit(fs_info); return ERR_PTR(-EOVERFLOW); } if (start >= BTRFS_32BIT_EARLY_WARN_THRESHOLD) btrfs_warn_32bit_limit(fs_info); #endif eb = find_extent_buffer(fs_info, start); if (eb) return eb; eb = __alloc_extent_buffer(fs_info, start); if (!eb) return ERR_PTR(-ENOMEM); /* * The reloc trees are just snapshots, so we need them to appear to be * just like any other fs tree WRT lockdep. */ if (lockdep_owner == BTRFS_TREE_RELOC_OBJECTID) lockdep_owner = BTRFS_FS_TREE_OBJECTID; btrfs_set_buffer_lockdep_class(lockdep_owner, eb, level); /* * Preallocate folio private for subpage case, so that we won't * allocate memory with i_private_lock nor page lock hold. * * The memory will be freed by attach_extent_buffer_page() or freed * manually if we exit earlier. */ if (btrfs_meta_is_subpage(fs_info)) { prealloc = btrfs_alloc_folio_state(fs_info, PAGE_SIZE, BTRFS_SUBPAGE_METADATA); if (IS_ERR(prealloc)) { ret = PTR_ERR(prealloc); goto out; } } reallocate: /* Allocate all pages first. */ ret = alloc_eb_folio_array(eb, true); if (ret < 0) { btrfs_free_folio_state(prealloc); goto out; } /* Attach all pages to the filemap. */ for (int i = 0; i < num_extent_folios(eb); i++) { struct folio *folio; ret = attach_eb_folio_to_filemap(eb, i, prealloc, &existing_eb); if (ret > 0) { ASSERT(existing_eb); goto out; } /* * TODO: Special handling for a corner case where the order of * folios mismatch between the new eb and filemap. * * This happens when: * * - the new eb is using higher order folio * * - the filemap is still using 0-order folios for the range * This can happen at the previous eb allocation, and we don't * have higher order folio for the call. * * - the existing eb has already been freed * * In this case, we have to free the existing folios first, and * re-allocate using the same order. * Thankfully this is not going to happen yet, as we're still * using 0-order folios. */ if (unlikely(ret == -EAGAIN)) { DEBUG_WARN("folio order mismatch between new eb and filemap"); goto reallocate; } attached++; /* * Only after attach_eb_folio_to_filemap(), eb->folios[] is * reliable, as we may choose to reuse the existing page cache * and free the allocated page. */ folio = eb->folios[i]; WARN_ON(btrfs_meta_folio_test_dirty(folio, eb)); /* * Check if the current page is physically contiguous with previous eb * page. * At this stage, either we allocated a large folio, thus @i * would only be 0, or we fall back to per-page allocation. */ if (i && folio_page(eb->folios[i - 1], 0) + 1 != folio_page(folio, 0)) page_contig = false; if (!btrfs_meta_folio_test_uptodate(folio, eb)) uptodate = 0; /* * We can't unlock the pages just yet since the extent buffer * hasn't been properly inserted into the xarray, this opens a * race with btree_release_folio() which can free a page while we * are still filling in all pages for the buffer and we could crash. */ } if (uptodate) set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); /* All pages are physically contiguous, can skip cross page handling. */ if (page_contig) eb->addr = folio_address(eb->folios[0]) + offset_in_page(eb->start); again: xa_lock_irq(&fs_info->buffer_tree); existing_eb = __xa_cmpxchg(&fs_info->buffer_tree, start >> fs_info->nodesize_bits, NULL, eb, GFP_NOFS); if (xa_is_err(existing_eb)) { ret = xa_err(existing_eb); xa_unlock_irq(&fs_info->buffer_tree); goto out; } if (existing_eb) { if (!refcount_inc_not_zero(&existing_eb->refs)) { xa_unlock_irq(&fs_info->buffer_tree); goto again; } xa_unlock_irq(&fs_info->buffer_tree); goto out; } xa_unlock_irq(&fs_info->buffer_tree); /* add one reference for the tree */ check_buffer_tree_ref(eb); /* * Now it's safe to unlock the pages because any calls to * btree_release_folio will correctly detect that a page belongs to a * live buffer and won't free them prematurely. */ for (int i = 0; i < num_extent_folios(eb); i++) { folio_unlock(eb->folios[i]); /* * A folio that has been added to an address_space mapping * should not continue holding the refcount from its original * allocation indefinitely. */ folio_put(eb->folios[i]); } return eb; out: WARN_ON(!refcount_dec_and_test(&eb->refs)); /* * Any attached folios need to be detached before we unlock them. This * is because when we're inserting our new folios into the mapping, and * then attaching our eb to that folio. If we fail to insert our folio * we'll lookup the folio for that index, and grab that EB. We do not * want that to grab this eb, as we're getting ready to free it. So we * have to detach it first and then unlock it. * * Note: the bounds is num_extent_pages() as we need to go through all slots. */ for (int i = 0; i < num_extent_pages(eb); i++) { struct folio *folio = eb->folios[i]; if (i < attached) { ASSERT(folio); detach_extent_buffer_folio(eb, folio); folio_unlock(folio); } else if (!folio) { continue; } folio_put(folio); eb->folios[i] = NULL; } btrfs_release_extent_buffer(eb); if (ret < 0) return ERR_PTR(ret); ASSERT(existing_eb); return existing_eb; } static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head) { struct extent_buffer *eb = container_of(head, struct extent_buffer, rcu_head); kmem_cache_free(extent_buffer_cache, eb); } static int release_extent_buffer(struct extent_buffer *eb) __releases(&eb->refs_lock) { lockdep_assert_held(&eb->refs_lock); if (refcount_dec_and_test(&eb->refs)) { struct btrfs_fs_info *fs_info = eb->fs_info; spin_unlock(&eb->refs_lock); /* * We're erasing, theoretically there will be no allocations, so * just use GFP_ATOMIC. * * We use cmpxchg instead of erase because we do not know if * this eb is actually in the tree or not, we could be cleaning * up an eb that we allocated but never inserted into the tree. * Thus use cmpxchg to remove it from the tree if it is there, * or leave the other entry if this isn't in the tree. * * The documentation says that putting a NULL value is the same * as erase as long as XA_FLAGS_ALLOC is not set, which it isn't * in this case. */ xa_cmpxchg_irq(&fs_info->buffer_tree, eb->start >> fs_info->nodesize_bits, eb, NULL, GFP_ATOMIC); btrfs_leak_debug_del_eb(eb); /* Should be safe to release folios at this point. */ btrfs_release_extent_buffer_folios(eb); #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))) { kmem_cache_free(extent_buffer_cache, eb); return 1; } #endif call_rcu(&eb->rcu_head, btrfs_release_extent_buffer_rcu); return 1; } spin_unlock(&eb->refs_lock); return 0; } void free_extent_buffer(struct extent_buffer *eb) { int refs; if (!eb) return; refs = refcount_read(&eb->refs); while (1) { if (test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags)) { if (refs == 1) break; } else if (refs <= 3) { break; } /* Optimization to avoid locking eb->refs_lock. */ if (atomic_try_cmpxchg(&eb->refs.refs, &refs, refs - 1)) return; } spin_lock(&eb->refs_lock); if (refcount_read(&eb->refs) == 2 && test_bit(EXTENT_BUFFER_STALE, &eb->bflags) && !extent_buffer_under_io(eb) && test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) refcount_dec(&eb->refs); /* * I know this is terrible, but it's temporary until we stop tracking * the uptodate bits and such for the extent buffers. */ release_extent_buffer(eb); } void free_extent_buffer_stale(struct extent_buffer *eb) { if (!eb) return; spin_lock(&eb->refs_lock); set_bit(EXTENT_BUFFER_STALE, &eb->bflags); if (refcount_read(&eb->refs) == 2 && !extent_buffer_under_io(eb) && test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) refcount_dec(&eb->refs); release_extent_buffer(eb); } static void btree_clear_folio_dirty_tag(struct folio *folio) { ASSERT(!folio_test_dirty(folio)); ASSERT(folio_test_locked(folio)); xa_lock_irq(&folio->mapping->i_pages); if (!folio_test_dirty(folio)) __xa_clear_mark(&folio->mapping->i_pages, folio->index, PAGECACHE_TAG_DIRTY); xa_unlock_irq(&folio->mapping->i_pages); } void btrfs_clear_buffer_dirty(struct btrfs_trans_handle *trans, struct extent_buffer *eb) { struct btrfs_fs_info *fs_info = eb->fs_info; btrfs_assert_tree_write_locked(eb); if (trans && btrfs_header_generation(eb) != trans->transid) return; /* * Instead of clearing the dirty flag off of the buffer, mark it as * EXTENT_BUFFER_ZONED_ZEROOUT. This allows us to preserve * write-ordering in zoned mode, without the need to later re-dirty * the extent_buffer. * * The actual zeroout of the buffer will happen later in * btree_csum_one_bio. */ if (btrfs_is_zoned(fs_info) && test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) { set_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags); return; } if (!test_and_clear_bit(EXTENT_BUFFER_DIRTY, &eb->bflags)) return; buffer_tree_clear_mark(eb, PAGECACHE_TAG_DIRTY); percpu_counter_add_batch(&fs_info->dirty_metadata_bytes, -eb->len, fs_info->dirty_metadata_batch); for (int i = 0; i < num_extent_folios(eb); i++) { struct folio *folio = eb->folios[i]; bool last; if (!folio_test_dirty(folio)) continue; folio_lock(folio); last = btrfs_meta_folio_clear_and_test_dirty(folio, eb); if (last) btree_clear_folio_dirty_tag(folio); folio_unlock(folio); } WARN_ON(refcount_read(&eb->refs) == 0); } void set_extent_buffer_dirty(struct extent_buffer *eb) { bool was_dirty; check_buffer_tree_ref(eb); was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags); WARN_ON(refcount_read(&eb->refs) == 0); WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)); WARN_ON(test_bit(EXTENT_BUFFER_ZONED_ZEROOUT, &eb->bflags)); if (!was_dirty) { bool subpage = btrfs_meta_is_subpage(eb->fs_info); /* * For subpage case, we can have other extent buffers in the * same page, and in clear_extent_buffer_dirty() we * have to clear page dirty without subpage lock held. * This can cause race where our page gets dirty cleared after * we just set it. * * Thankfully, clear_extent_buffer_dirty() has locked * its page for other reasons, we can use page lock to prevent * the above race. */ if (subpage) folio_lock(eb->folios[0]); for (int i = 0; i < num_extent_folios(eb); i++) btrfs_meta_folio_set_dirty(eb->folios[i], eb); buffer_tree_set_mark(eb, PAGECACHE_TAG_DIRTY); if (subpage) folio_unlock(eb->folios[0]); percpu_counter_add_batch(&eb->fs_info->dirty_metadata_bytes, eb->len, eb->fs_info->dirty_metadata_batch); } #ifdef CONFIG_BTRFS_DEBUG for (int i = 0; i < num_extent_folios(eb); i++) ASSERT(folio_test_dirty(eb->folios[i])); #endif } void clear_extent_buffer_uptodate(struct extent_buffer *eb) { clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); for (int i = 0; i < num_extent_folios(eb); i++) { struct folio *folio = eb->folios[i]; if (!folio) continue; btrfs_meta_folio_clear_uptodate(folio, eb); } } void set_extent_buffer_uptodate(struct extent_buffer *eb) { set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags); for (int i = 0; i < num_extent_folios(eb); i++) btrfs_meta_folio_set_uptodate(eb->folios[i], eb); } static void clear_extent_buffer_reading(struct extent_buffer *eb) { clear_and_wake_up_bit(EXTENT_BUFFER_READING, &eb->bflags); } static void end_bbio_meta_read(struct btrfs_bio *bbio) { struct extent_buffer *eb = bbio->private; bool uptodate = !bbio->bio.bi_status; /* * If the extent buffer is marked UPTODATE before the read operation * completes, other calls to read_extent_buffer_pages() will return * early without waiting for the read to finish, causing data races. */ WARN_ON(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)); eb->read_mirror = bbio->mirror_num; if (uptodate && btrfs_validate_extent_buffer(eb, &bbio->parent_check) < 0) uptodate = false; if (uptodate) set_extent_buffer_uptodate(eb); else clear_extent_buffer_uptodate(eb); clear_extent_buffer_reading(eb); free_extent_buffer(eb); bio_put(&bbio->bio); } int read_extent_buffer_pages_nowait(struct extent_buffer *eb, int mirror_num, const struct btrfs_tree_parent_check *check) { struct btrfs_bio *bbio; if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return 0; /* * We could have had EXTENT_BUFFER_UPTODATE cleared by the write * operation, which could potentially still be in flight. In this case * we simply want to return an error. */ if (unlikely(test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags))) return -EIO; /* Someone else is already reading the buffer, just wait for it. */ if (test_and_set_bit(EXTENT_BUFFER_READING, &eb->bflags)) return 0; /* * Between the initial test_bit(EXTENT_BUFFER_UPTODATE) and the above * test_and_set_bit(EXTENT_BUFFER_READING), someone else could have * started and finished reading the same eb. In this case, UPTODATE * will now be set, and we shouldn't read it in again. */ if (unlikely(test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))) { clear_extent_buffer_reading(eb); return 0; } eb->read_mirror = 0; check_buffer_tree_ref(eb); refcount_inc(&eb->refs); bbio = btrfs_bio_alloc(INLINE_EXTENT_BUFFER_PAGES, REQ_OP_READ | REQ_META, eb->fs_info, end_bbio_meta_read, eb); bbio->bio.bi_iter.bi_sector = eb->start >> SECTOR_SHIFT; bbio->inode = BTRFS_I(eb->fs_info->btree_inode); bbio->file_offset = eb->start; memcpy(&bbio->parent_check, check, sizeof(*check)); for (int i = 0; i < num_extent_folios(eb); i++) { struct folio *folio = eb->folios[i]; u64 range_start = max_t(u64, eb->start, folio_pos(folio)); u32 range_len = min_t(u64, folio_end(folio), eb->start + eb->len) - range_start; bio_add_folio_nofail(&bbio->bio, folio, range_len, offset_in_folio(folio, range_start)); } btrfs_submit_bbio(bbio, mirror_num); return 0; } int read_extent_buffer_pages(struct extent_buffer *eb, int mirror_num, const struct btrfs_tree_parent_check *check) { int ret; ret = read_extent_buffer_pages_nowait(eb, mirror_num, check); if (ret < 0) return ret; wait_on_bit_io(&eb->bflags, EXTENT_BUFFER_READING, TASK_UNINTERRUPTIBLE); if (!test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags)) return -EIO; return 0; } static bool report_eb_range(const struct extent_buffer *eb, unsigned long start, unsigned long len) { btrfs_warn(eb->fs_info, "access to eb bytenr %llu len %u out of range start %lu len %lu", eb->start, eb->len, start, len); DEBUG_WARN(); return true; } /* * Check if the [start, start + len) range is valid before reading/writing * the eb. * NOTE: @start and @len are offset inside the eb, not logical address. * * Caller should not touch the dst/src memory if this function returns error. */ static inline int check_eb_range(const struct extent_buffer *eb, unsigned long start, unsigned long len) { unsigned long offset; /* start, start + len should not go beyond eb->len nor overflow */ if (unlikely(check_add_overflow(start, len, &offset) || offset > eb->len)) return report_eb_range(eb, start, len); return false; } void read_extent_buffer(const struct extent_buffer *eb, void *dstv, unsigned long start, unsigned long len) { const int unit_size = eb->folio_size; size_t cur; size_t offset; char *dst = (char *)dstv; unsigned long i = get_eb_folio_index(eb, start); if (check_eb_range(eb, start, len)) { /* * Invalid range hit, reset the memory, so callers won't get * some random garbage for their uninitialized memory. */ memset(dstv, 0, len); return; } if (eb->addr) { memcpy(dstv, eb->addr + start, len); return; } offset = get_eb_offset_in_folio(eb, start); while (len > 0) { char *kaddr; cur = min(len, unit_size - offset); kaddr = folio_address(eb->folios[i]); memcpy(dst, kaddr + offset, cur); dst += cur; len -= cur; offset = 0; i++; } } int read_extent_buffer_to_user_nofault(const struct extent_buffer *eb, void __user *dstv, unsigned long start, unsigned long len) { const int unit_size = eb->folio_size; size_t cur; size_t offset; char __user *dst = (char __user *)dstv; unsigned long i = get_eb_folio_index(eb, start); int ret = 0; WARN_ON(start > eb->len); WARN_ON(start + len > eb->start + eb->len); if (eb->addr) { if (copy_to_user_nofault(dstv, eb->addr + start, len)) ret = -EFAULT; return ret; } offset = get_eb_offset_in_folio(eb, start); while (len > 0) { char *kaddr; cur = min(len, unit_size - offset); kaddr = folio_address(eb->folios[i]); if (copy_to_user_nofault(dst, kaddr + offset, cur)) { ret = -EFAULT; break; } dst += cur; len -= cur; offset = 0; i++; } return ret; } int memcmp_extent_buffer(const struct extent_buffer *eb, const void *ptrv, unsigned long start, unsigned long len) { const int unit_size = eb->folio_size; size_t cur; size_t offset; char *kaddr; char *ptr = (char *)ptrv; unsigned long i = get_eb_folio_index(eb, start); int ret = 0; if (check_eb_range(eb, start, len)) return -EINVAL; if (eb->addr) return memcmp(ptrv, eb->addr + start, len); offset = get_eb_offset_in_folio(eb, start); while (len > 0) { cur = min(len, unit_size - offset); kaddr = folio_address(eb->folios[i]); ret = memcmp(ptr, kaddr + offset, cur); if (ret) break; ptr += cur; len -= cur; offset = 0; i++; } return ret; } /* * Check that the extent buffer is uptodate. * * For regular sector size == PAGE_SIZE case, check if @page is uptodate. * For subpage case, check if the range covered by the eb has EXTENT_UPTODATE. */ static void assert_eb_folio_uptodate(const struct extent_buffer *eb, int i) { struct btrfs_fs_info *fs_info = eb->fs_info; struct folio *folio = eb->folios[i]; ASSERT(folio); /* * If we are using the commit root we could potentially clear a page * Uptodate while we're using the extent buffer that we've previously * looked up. We don't want to complain in this case, as the page was * valid before, we just didn't write it out. Instead we want to catch * the case where we didn't actually read the block properly, which * would have !PageUptodate and !EXTENT_BUFFER_WRITE_ERR. */ if (test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) return; if (btrfs_meta_is_subpage(fs_info)) { folio = eb->folios[0]; ASSERT(i == 0); if (WARN_ON(!btrfs_subpage_test_uptodate(fs_info, folio, eb->start, eb->len))) btrfs_subpage_dump_bitmap(fs_info, folio, eb->start, eb->len); } else { WARN_ON(!folio_test_uptodate(folio)); } } static void __write_extent_buffer(const struct extent_buffer *eb, const void *srcv, unsigned long start, unsigned long len, bool use_memmove) { const int unit_size = eb->folio_size; size_t cur; size_t offset; char *kaddr; const char *src = (const char *)srcv; unsigned long i = get_eb_folio_index(eb, start); /* For unmapped (dummy) ebs, no need to check their uptodate status. */ const bool check_uptodate = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags); if (check_eb_range(eb, start, len)) return; if (eb->addr) { if (use_memmove) memmove(eb->addr + start, srcv, len); else memcpy(eb->addr + start, srcv, len); return; } offset = get_eb_offset_in_folio(eb, start); while (len > 0) { if (check_uptodate) assert_eb_folio_uptodate(eb, i); cur = min(len, unit_size - offset); kaddr = folio_address(eb->folios[i]); if (use_memmove) memmove(kaddr + offset, src, cur); else memcpy(kaddr + offset, src, cur); src += cur; len -= cur; offset = 0; i++; } } void write_extent_buffer(const struct extent_buffer *eb, const void *srcv, unsigned long start, unsigned long len) { return __write_extent_buffer(eb, srcv, start, len, false); } static void memset_extent_buffer(const struct extent_buffer *eb, int c, unsigned long start, unsigned long len) { const int unit_size = eb->folio_size; unsigned long cur = start; if (eb->addr) { memset(eb->addr + start, c, len); return; } while (cur < start + len) { unsigned long index = get_eb_folio_index(eb, cur); unsigned int offset = get_eb_offset_in_folio(eb, cur); unsigned int cur_len = min(start + len - cur, unit_size - offset); assert_eb_folio_uptodate(eb, index); memset(folio_address(eb->folios[index]) + offset, c, cur_len); cur += cur_len; } } void memzero_extent_buffer(const struct extent_buffer *eb, unsigned long start, unsigned long len) { if (check_eb_range(eb, start, len)) return; return memset_extent_buffer(eb, 0, start, len); } void copy_extent_buffer_full(const struct extent_buffer *dst, const struct extent_buffer *src) { const int unit_size = src->folio_size; unsigned long cur = 0; ASSERT(dst->len == src->len); while (cur < src->len) { unsigned long index = get_eb_folio_index(src, cur); unsigned long offset = get_eb_offset_in_folio(src, cur); unsigned long cur_len = min(src->len, unit_size - offset); void *addr = folio_address(src->folios[index]) + offset; write_extent_buffer(dst, addr, cur, cur_len); cur += cur_len; } } void copy_extent_buffer(const struct extent_buffer *dst, const struct extent_buffer *src, unsigned long dst_offset, unsigned long src_offset, unsigned long len) { const int unit_size = dst->folio_size; u64 dst_len = dst->len; size_t cur; size_t offset; char *kaddr; unsigned long i = get_eb_folio_index(dst, dst_offset); if (check_eb_range(dst, dst_offset, len) || check_eb_range(src, src_offset, len)) return; WARN_ON(src->len != dst_len); offset = get_eb_offset_in_folio(dst, dst_offset); while (len > 0) { assert_eb_folio_uptodate(dst, i); cur = min(len, (unsigned long)(unit_size - offset)); kaddr = folio_address(dst->folios[i]); read_extent_buffer(src, kaddr + offset, src_offset, cur); src_offset += cur; len -= cur; offset = 0; i++; } } /* * Calculate the folio and offset of the byte containing the given bit number. * * @eb: the extent buffer * @start: offset of the bitmap item in the extent buffer * @nr: bit number * @folio_index: return index of the folio in the extent buffer that contains * the given bit number * @folio_offset: return offset into the folio given by folio_index * * This helper hides the ugliness of finding the byte in an extent buffer which * contains a given bit. */ static inline void eb_bitmap_offset(const struct extent_buffer *eb, unsigned long start, unsigned long nr, unsigned long *folio_index, size_t *folio_offset) { size_t byte_offset = BIT_BYTE(nr); size_t offset; /* * The byte we want is the offset of the extent buffer + the offset of * the bitmap item in the extent buffer + the offset of the byte in the * bitmap item. */ offset = start + offset_in_eb_folio(eb, eb->start) + byte_offset; *folio_index = offset >> eb->folio_shift; *folio_offset = offset_in_eb_folio(eb, offset); } /* * Determine whether a bit in a bitmap item is set. * * @eb: the extent buffer * @start: offset of the bitmap item in the extent buffer * @nr: bit number to test */ bool extent_buffer_test_bit(const struct extent_buffer *eb, unsigned long start, unsigned long nr) { unsigned long i; size_t offset; u8 *kaddr; eb_bitmap_offset(eb, start, nr, &i, &offset); assert_eb_folio_uptodate(eb, i); kaddr = folio_address(eb->folios[i]); return 1U & (kaddr[offset] >> (nr & (BITS_PER_BYTE - 1))); } static u8 *extent_buffer_get_byte(const struct extent_buffer *eb, unsigned long bytenr) { unsigned long index = get_eb_folio_index(eb, bytenr); if (check_eb_range(eb, bytenr, 1)) return NULL; return folio_address(eb->folios[index]) + get_eb_offset_in_folio(eb, bytenr); } /* * Set an area of a bitmap to 1. * * @eb: the extent buffer * @start: offset of the bitmap item in the extent buffer * @pos: bit number of the first bit * @len: number of bits to set */ void extent_buffer_bitmap_set(const struct extent_buffer *eb, unsigned long start, unsigned long pos, unsigned long len) { unsigned int first_byte = start + BIT_BYTE(pos); unsigned int last_byte = start + BIT_BYTE(pos + len - 1); const bool same_byte = (first_byte == last_byte); u8 mask = BITMAP_FIRST_BYTE_MASK(pos); u8 *kaddr; if (same_byte) mask &= BITMAP_LAST_BYTE_MASK(pos + len); /* Handle the first byte. */ kaddr = extent_buffer_get_byte(eb, first_byte); *kaddr |= mask; if (same_byte) return; /* Handle the byte aligned part. */ ASSERT(first_byte + 1 <= last_byte); memset_extent_buffer(eb, 0xff, first_byte + 1, last_byte - first_byte - 1); /* Handle the last byte. */ kaddr = extent_buffer_get_byte(eb, last_byte); *kaddr |= BITMAP_LAST_BYTE_MASK(pos + len); } /* * Clear an area of a bitmap. * * @eb: the extent buffer * @start: offset of the bitmap item in the extent buffer * @pos: bit number of the first bit * @len: number of bits to clear */ void extent_buffer_bitmap_clear(const struct extent_buffer *eb, unsigned long start, unsigned long pos, unsigned long len) { unsigned int first_byte = start + BIT_BYTE(pos); unsigned int last_byte = start + BIT_BYTE(pos + len - 1); const bool same_byte = (first_byte == last_byte); u8 mask = BITMAP_FIRST_BYTE_MASK(pos); u8 *kaddr; if (same_byte) mask &= BITMAP_LAST_BYTE_MASK(pos + len); /* Handle the first byte. */ kaddr = extent_buffer_get_byte(eb, first_byte); *kaddr &= ~mask; if (same_byte) return; /* Handle the byte aligned part. */ ASSERT(first_byte + 1 <= last_byte); memset_extent_buffer(eb, 0, first_byte + 1, last_byte - first_byte - 1); /* Handle the last byte. */ kaddr = extent_buffer_get_byte(eb, last_byte); *kaddr &= ~BITMAP_LAST_BYTE_MASK(pos + len); } static inline bool areas_overlap(unsigned long src, unsigned long dst, unsigned long len) { unsigned long distance = (src > dst) ? src - dst : dst - src; return distance < len; } void memcpy_extent_buffer(const struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_offset, unsigned long len) { const int unit_size = dst->folio_size; unsigned long cur_off = 0; if (check_eb_range(dst, dst_offset, len) || check_eb_range(dst, src_offset, len)) return; if (dst->addr) { const bool use_memmove = areas_overlap(src_offset, dst_offset, len); if (use_memmove) memmove(dst->addr + dst_offset, dst->addr + src_offset, len); else memcpy(dst->addr + dst_offset, dst->addr + src_offset, len); return; } while (cur_off < len) { unsigned long cur_src = cur_off + src_offset; unsigned long folio_index = get_eb_folio_index(dst, cur_src); unsigned long folio_off = get_eb_offset_in_folio(dst, cur_src); unsigned long cur_len = min(src_offset + len - cur_src, unit_size - folio_off); void *src_addr = folio_address(dst->folios[folio_index]) + folio_off; const bool use_memmove = areas_overlap(src_offset + cur_off, dst_offset + cur_off, cur_len); __write_extent_buffer(dst, src_addr, dst_offset + cur_off, cur_len, use_memmove); cur_off += cur_len; } } void memmove_extent_buffer(const struct extent_buffer *dst, unsigned long dst_offset, unsigned long src_offset, unsigned long len) { unsigned long dst_end = dst_offset + len - 1; unsigned long src_end = src_offset + len - 1; if (check_eb_range(dst, dst_offset, len) || check_eb_range(dst, src_offset, len)) return; if (dst_offset < src_offset) { memcpy_extent_buffer(dst, dst_offset, src_offset, len); return; } if (dst->addr) { memmove(dst->addr + dst_offset, dst->addr + src_offset, len); return; } while (len > 0) { unsigned long src_i; size_t cur; size_t dst_off_in_folio; size_t src_off_in_folio; void *src_addr; bool use_memmove; src_i = get_eb_folio_index(dst, src_end); dst_off_in_folio = get_eb_offset_in_folio(dst, dst_end); src_off_in_folio = get_eb_offset_in_folio(dst, src_end); cur = min_t(unsigned long, len, src_off_in_folio + 1); cur = min(cur, dst_off_in_folio + 1); src_addr = folio_address(dst->folios[src_i]) + src_off_in_folio - cur + 1; use_memmove = areas_overlap(src_end - cur + 1, dst_end - cur + 1, cur); __write_extent_buffer(dst, src_addr, dst_end - cur + 1, cur, use_memmove); dst_end -= cur; src_end -= cur; len -= cur; } } static int try_release_subpage_extent_buffer(struct folio *folio) { struct btrfs_fs_info *fs_info = folio_to_fs_info(folio); struct extent_buffer *eb; unsigned long start = (folio_pos(folio) >> fs_info->nodesize_bits); unsigned long index = start; unsigned long end = index + (PAGE_SIZE >> fs_info->nodesize_bits) - 1; int ret; rcu_read_lock(); xa_for_each_range(&fs_info->buffer_tree, index, eb, start, end) { /* * The same as try_release_extent_buffer(), to ensure the eb * won't disappear out from under us. */ spin_lock(&eb->refs_lock); rcu_read_unlock(); if (refcount_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { spin_unlock(&eb->refs_lock); rcu_read_lock(); continue; } /* * If tree ref isn't set then we know the ref on this eb is a * real ref, so just return, this eb will likely be freed soon * anyway. */ if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) { spin_unlock(&eb->refs_lock); break; } /* * Here we don't care about the return value, we will always * check the folio private at the end. And * release_extent_buffer() will release the refs_lock. */ release_extent_buffer(eb); rcu_read_lock(); } rcu_read_unlock(); /* * Finally to check if we have cleared folio private, as if we have * released all ebs in the page, the folio private should be cleared now. */ spin_lock(&folio->mapping->i_private_lock); if (!folio_test_private(folio)) ret = 1; else ret = 0; spin_unlock(&folio->mapping->i_private_lock); return ret; } int try_release_extent_buffer(struct folio *folio) { struct extent_buffer *eb; if (btrfs_meta_is_subpage(folio_to_fs_info(folio))) return try_release_subpage_extent_buffer(folio); /* * We need to make sure nobody is changing folio private, as we rely on * folio private as the pointer to extent buffer. */ spin_lock(&folio->mapping->i_private_lock); if (!folio_test_private(folio)) { spin_unlock(&folio->mapping->i_private_lock); return 1; } eb = folio_get_private(folio); BUG_ON(!eb); /* * This is a little awful but should be ok, we need to make sure that * the eb doesn't disappear out from under us while we're looking at * this page. */ spin_lock(&eb->refs_lock); if (refcount_read(&eb->refs) != 1 || extent_buffer_under_io(eb)) { spin_unlock(&eb->refs_lock); spin_unlock(&folio->mapping->i_private_lock); return 0; } spin_unlock(&folio->mapping->i_private_lock); /* * If tree ref isn't set then we know the ref on this eb is a real ref, * so just return, this page will likely be freed soon anyway. */ if (!test_and_clear_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags)) { spin_unlock(&eb->refs_lock); return 0; } return release_extent_buffer(eb); } /* * Attempt to readahead a child block. * * @fs_info: the fs_info * @bytenr: bytenr to read * @owner_root: objectid of the root that owns this eb * @gen: generation for the uptodate check, can be 0 * @level: level for the eb * * Attempt to readahead a tree block at @bytenr. If @gen is 0 then we do a * normal uptodate check of the eb, without checking the generation. If we have * to read the block we will not block on anything. */ void btrfs_readahead_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr, u64 owner_root, u64 gen, int level) { struct btrfs_tree_parent_check check = { .level = level, .transid = gen }; struct extent_buffer *eb; int ret; eb = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level); if (IS_ERR(eb)) return; if (btrfs_buffer_uptodate(eb, gen, 1)) { free_extent_buffer(eb); return; } ret = read_extent_buffer_pages_nowait(eb, 0, &check); if (ret < 0) free_extent_buffer_stale(eb); else free_extent_buffer(eb); } /* * Readahead a node's child block. * * @node: parent node we're reading from * @slot: slot in the parent node for the child we want to read * * A helper for btrfs_readahead_tree_block, we simply read the bytenr pointed at * the slot in the node provided. */ void btrfs_readahead_node_child(struct extent_buffer *node, int slot) { btrfs_readahead_tree_block(node->fs_info, btrfs_node_blockptr(node, slot), btrfs_header_owner(node), btrfs_node_ptr_generation(node, slot), btrfs_header_level(node) - 1); } |
| 1725 3703 1548 1494 3872 3457 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM timer #if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_TIMER_H #include <linux/tracepoint.h> #include <linux/hrtimer.h> #include <linux/timer.h> DECLARE_EVENT_CLASS(timer_class, TP_PROTO(struct timer_list *timer), TP_ARGS(timer), TP_STRUCT__entry( __field( void *, timer ) ), TP_fast_assign( __entry->timer = timer; ), TP_printk("timer=%p", __entry->timer) ); /** * timer_init - called when the timer is initialized * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_init, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); #define decode_timer_flags(flags) \ __print_flags(flags, "|", \ { TIMER_MIGRATING, "M" }, \ { TIMER_DEFERRABLE, "D" }, \ { TIMER_PINNED, "P" }, \ { TIMER_IRQSAFE, "I" }) /** * timer_start - called when the timer is started * @timer: pointer to struct timer_list * @bucket_expiry: the bucket expiry time */ TRACE_EVENT(timer_start, TP_PROTO(struct timer_list *timer, unsigned long bucket_expiry), TP_ARGS(timer, bucket_expiry), TP_STRUCT__entry( __field( void *, timer ) __field( void *, function ) __field( unsigned long, expires ) __field( unsigned long, bucket_expiry ) __field( unsigned long, now ) __field( unsigned int, flags ) ), TP_fast_assign( __entry->timer = timer; __entry->function = timer->function; __entry->expires = timer->expires; __entry->bucket_expiry = bucket_expiry; __entry->now = jiffies; __entry->flags = timer->flags; ), TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] bucket_expiry=%lu cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->bucket_expiry, __entry->flags & TIMER_CPUMASK, __entry->flags >> TIMER_ARRAYSHIFT, decode_timer_flags(__entry->flags & TIMER_TRACE_FLAGMASK)) ); /** * timer_expire_entry - called immediately before the timer callback * @timer: pointer to struct timer_list * @baseclk: value of timer_base::clk when timer expires * * Allows to determine the timer latency. */ TRACE_EVENT(timer_expire_entry, TP_PROTO(struct timer_list *timer, unsigned long baseclk), TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; __entry->baseclk = baseclk; ), TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", __entry->timer, __entry->function, __entry->now, __entry->baseclk) ); /** * timer_expire_exit - called immediately after the timer callback returns * @timer: pointer to struct timer_list * * When used in combination with the timer_expire_entry tracepoint we can * determine the runtime of the timer callback function. * * NOTE: Do NOT dereference timer in TP_fast_assign. The pointer might * be invalid. We solely track the pointer. */ DEFINE_EVENT(timer_class, timer_expire_exit, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); /** * timer_cancel - called when the timer is canceled * @timer: pointer to struct timer_list */ DEFINE_EVENT(timer_class, timer_cancel, TP_PROTO(struct timer_list *timer), TP_ARGS(timer) ); TRACE_EVENT(timer_base_idle, TP_PROTO(bool is_idle, unsigned int cpu), TP_ARGS(is_idle, cpu), TP_STRUCT__entry( __field( bool, is_idle ) __field( unsigned int, cpu ) ), TP_fast_assign( __entry->is_idle = is_idle; __entry->cpu = cpu; ), TP_printk("is_idle=%d cpu=%d", __entry->is_idle, __entry->cpu) ); #define decode_clockid(type) \ __print_symbolic(type, \ { CLOCK_REALTIME, "CLOCK_REALTIME" }, \ { CLOCK_MONOTONIC, "CLOCK_MONOTONIC" }, \ { CLOCK_BOOTTIME, "CLOCK_BOOTTIME" }, \ { CLOCK_TAI, "CLOCK_TAI" }) #define decode_hrtimer_mode(mode) \ __print_symbolic(mode, \ { HRTIMER_MODE_ABS, "ABS" }, \ { HRTIMER_MODE_REL, "REL" }, \ { HRTIMER_MODE_ABS_PINNED, "ABS|PINNED" }, \ { HRTIMER_MODE_REL_PINNED, "REL|PINNED" }, \ { HRTIMER_MODE_ABS_SOFT, "ABS|SOFT" }, \ { HRTIMER_MODE_REL_SOFT, "REL|SOFT" }, \ { HRTIMER_MODE_ABS_PINNED_SOFT, "ABS|PINNED|SOFT" }, \ { HRTIMER_MODE_REL_PINNED_SOFT, "REL|PINNED|SOFT" }, \ { HRTIMER_MODE_ABS_HARD, "ABS|HARD" }, \ { HRTIMER_MODE_REL_HARD, "REL|HARD" }, \ { HRTIMER_MODE_ABS_PINNED_HARD, "ABS|PINNED|HARD" }, \ { HRTIMER_MODE_REL_PINNED_HARD, "REL|PINNED|HARD" }) /** * hrtimer_setup - called when the hrtimer is initialized * @hrtimer: pointer to struct hrtimer * @clockid: the hrtimers clock * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_setup, TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid, enum hrtimer_mode mode), TP_ARGS(hrtimer, clockid, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( clockid_t, clockid ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->clockid = clockid; __entry->mode = mode; ), TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer, decode_clockid(__entry->clockid), decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_start - called when the hrtimer is started * @hrtimer: pointer to struct hrtimer * @mode: the hrtimers mode */ TRACE_EVENT(hrtimer_start, TP_PROTO(struct hrtimer *hrtimer, enum hrtimer_mode mode), TP_ARGS(hrtimer, mode), TP_STRUCT__entry( __field( void *, hrtimer ) __field( void *, function ) __field( s64, expires ) __field( s64, softexpires ) __field( enum hrtimer_mode, mode ) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->function = ACCESS_PRIVATE(hrtimer, function); __entry->expires = hrtimer_get_expires(hrtimer); __entry->softexpires = hrtimer_get_softexpires(hrtimer); __entry->mode = mode; ), TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, decode_hrtimer_mode(__entry->mode)) ); /** * hrtimer_expire_entry - called immediately before the hrtimer callback * @hrtimer: pointer to struct hrtimer * @now: pointer to variable which contains current time of the * timers base. * * Allows to determine the timer latency. */ TRACE_EVENT(hrtimer_expire_entry, TP_PROTO(struct hrtimer *hrtimer, ktime_t *now), TP_ARGS(hrtimer, now), TP_STRUCT__entry( __field( void *, hrtimer ) __field( s64, now ) __field( void *, function) ), TP_fast_assign( __entry->hrtimer = hrtimer; __entry->now = *now; __entry->function = ACCESS_PRIVATE(hrtimer, function); ), TP_printk("hrtimer=%p function=%ps now=%llu", __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); DECLARE_EVENT_CLASS(hrtimer_class, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer), TP_STRUCT__entry( __field( void *, hrtimer ) ), TP_fast_assign( __entry->hrtimer = hrtimer; ), TP_printk("hrtimer=%p", __entry->hrtimer) ); /** * hrtimer_expire_exit - called immediately after the hrtimer callback returns * @hrtimer: pointer to struct hrtimer * * When used in combination with the hrtimer_expire_entry tracepoint we can * determine the runtime of the callback function. */ DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * hrtimer_cancel - called when the hrtimer is canceled * @hrtimer: pointer to struct hrtimer */ DEFINE_EVENT(hrtimer_class, hrtimer_cancel, TP_PROTO(struct hrtimer *hrtimer), TP_ARGS(hrtimer) ); /** * itimer_state - called when itimer is started or canceled * @which: name of the interval timer * @value: the itimers value, itimer is canceled if value->it_value is * zero, otherwise it is started * @expires: the itimers expiry time */ TRACE_EVENT(itimer_state, TP_PROTO(int which, const struct itimerspec64 *const value, unsigned long long expires), TP_ARGS(which, value, expires), TP_STRUCT__entry( __field( int, which ) __field( unsigned long long, expires ) __field( long, value_sec ) __field( long, value_nsec ) __field( long, interval_sec ) __field( long, interval_nsec ) ), TP_fast_assign( __entry->which = which; __entry->expires = expires; __entry->value_sec = value->it_value.tv_sec; __entry->value_nsec = value->it_value.tv_nsec; __entry->interval_sec = value->it_interval.tv_sec; __entry->interval_nsec = value->it_interval.tv_nsec; ), TP_printk("which=%d expires=%llu it_value=%ld.%06ld it_interval=%ld.%06ld", __entry->which, __entry->expires, __entry->value_sec, __entry->value_nsec / NSEC_PER_USEC, __entry->interval_sec, __entry->interval_nsec / NSEC_PER_USEC) ); /** * itimer_expire - called when itimer expires * @which: type of the interval timer * @pid: pid of the process which owns the timer * @now: current time, used to calculate the latency of itimer */ TRACE_EVENT(itimer_expire, TP_PROTO(int which, struct pid *pid, unsigned long long now), TP_ARGS(which, pid, now), TP_STRUCT__entry( __field( int , which ) __field( pid_t, pid ) __field( unsigned long long, now ) ), TP_fast_assign( __entry->which = which; __entry->now = now; __entry->pid = pid_nr(pid); ), TP_printk("which=%d pid=%d now=%llu", __entry->which, (int) __entry->pid, __entry->now) ); #ifdef CONFIG_NO_HZ_COMMON #define TICK_DEP_NAMES \ tick_dep_mask_name(NONE) \ tick_dep_name(POSIX_TIMER) \ tick_dep_name(PERF_EVENTS) \ tick_dep_name(SCHED) \ tick_dep_name(CLOCK_UNSTABLE) \ tick_dep_name(RCU) \ tick_dep_name_end(RCU_EXP) #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end /* The MASK will convert to their bits and they need to be processed too */ #define tick_dep_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); #define tick_dep_name_end(sdep) TRACE_DEFINE_ENUM(TICK_DEP_BIT_##sdep); \ TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); /* NONE only has a mask defined for it */ #define tick_dep_mask_name(sdep) TRACE_DEFINE_ENUM(TICK_DEP_MASK_##sdep); TICK_DEP_NAMES #undef tick_dep_name #undef tick_dep_mask_name #undef tick_dep_name_end #define tick_dep_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_mask_name(sdep) { TICK_DEP_MASK_##sdep, #sdep }, #define tick_dep_name_end(sdep) { TICK_DEP_MASK_##sdep, #sdep } #define show_tick_dep_name(val) \ __print_symbolic(val, TICK_DEP_NAMES) TRACE_EVENT(tick_stop, TP_PROTO(int success, int dependency), TP_ARGS(success, dependency), TP_STRUCT__entry( __field( int , success ) __field( int , dependency ) ), TP_fast_assign( __entry->success = success; __entry->dependency = dependency; ), TP_printk("success=%d dependency=%s", __entry->success, \ show_tick_dep_name(__entry->dependency)) ); #endif #endif /* _TRACE_TIMER_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 73 72 170 170 3 39 35 3 137 120 18 1 1 170 169 33 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | // SPDX-License-Identifier: GPL-2.0 /* * f2fs compress support * * Copyright (c) 2019 Chao Yu <chao@kernel.org> */ #include <linux/fs.h> #include <linux/f2fs_fs.h> #include <linux/moduleparam.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/lzo.h> #include <linux/lz4.h> #include <linux/zstd.h> #include <linux/pagevec.h> #include "f2fs.h" #include "node.h" #include "segment.h" #include <trace/events/f2fs.h> static struct kmem_cache *cic_entry_slab; static struct kmem_cache *dic_entry_slab; static void *page_array_alloc(struct f2fs_sb_info *sbi, int nr) { unsigned int size = sizeof(struct page *) * nr; if (likely(size <= sbi->page_array_slab_size)) return f2fs_kmem_cache_alloc(sbi->page_array_slab, GFP_F2FS_ZERO, false, sbi); return f2fs_kzalloc(sbi, size, GFP_NOFS); } static void page_array_free(struct f2fs_sb_info *sbi, void *pages, int nr) { unsigned int size = sizeof(struct page *) * nr; if (!pages) return; if (likely(size <= sbi->page_array_slab_size)) kmem_cache_free(sbi->page_array_slab, pages); else kfree(pages); } struct f2fs_compress_ops { int (*init_compress_ctx)(struct compress_ctx *cc); void (*destroy_compress_ctx)(struct compress_ctx *cc); int (*compress_pages)(struct compress_ctx *cc); int (*init_decompress_ctx)(struct decompress_io_ctx *dic); void (*destroy_decompress_ctx)(struct decompress_io_ctx *dic); int (*decompress_pages)(struct decompress_io_ctx *dic); bool (*is_level_valid)(int level); }; static unsigned int offset_in_cluster(struct compress_ctx *cc, pgoff_t index) { return index & (cc->cluster_size - 1); } static pgoff_t cluster_idx(struct compress_ctx *cc, pgoff_t index) { return index >> cc->log_cluster_size; } static pgoff_t start_idx_of_cluster(struct compress_ctx *cc) { return cc->cluster_idx << cc->log_cluster_size; } bool f2fs_is_compressed_page(struct folio *folio) { if (!folio->private) return false; if (folio_test_f2fs_nonpointer(folio)) return false; f2fs_bug_on(F2FS_F_SB(folio), *((u32 *)folio->private) != F2FS_COMPRESSED_PAGE_MAGIC); return true; } static void f2fs_set_compressed_page(struct page *page, struct inode *inode, pgoff_t index, void *data) { struct folio *folio = page_folio(page); folio_attach_private(folio, (void *)data); /* i_crypto_info and iv index */ folio->index = index; folio->mapping = inode->i_mapping; } static void f2fs_drop_rpages(struct compress_ctx *cc, int len, bool unlock) { int i; for (i = 0; i < len; i++) { if (!cc->rpages[i]) continue; if (unlock) unlock_page(cc->rpages[i]); else put_page(cc->rpages[i]); } } static void f2fs_put_rpages(struct compress_ctx *cc) { f2fs_drop_rpages(cc, cc->cluster_size, false); } static void f2fs_unlock_rpages(struct compress_ctx *cc, int len) { f2fs_drop_rpages(cc, len, true); } static void f2fs_put_rpages_wbc(struct compress_ctx *cc, struct writeback_control *wbc, bool redirty, int unlock) { unsigned int i; for (i = 0; i < cc->cluster_size; i++) { if (!cc->rpages[i]) continue; if (redirty) redirty_page_for_writepage(wbc, cc->rpages[i]); f2fs_put_page(cc->rpages[i], unlock); } } struct folio *f2fs_compress_control_folio(struct folio *folio) { struct compress_io_ctx *ctx = folio->private; return page_folio(ctx->rpages[0]); } int f2fs_init_compress_ctx(struct compress_ctx *cc) { if (cc->rpages) return 0; cc->rpages = page_array_alloc(F2FS_I_SB(cc->inode), cc->cluster_size); return cc->rpages ? 0 : -ENOMEM; } void f2fs_destroy_compress_ctx(struct compress_ctx *cc, bool reuse) { page_array_free(F2FS_I_SB(cc->inode), cc->rpages, cc->cluster_size); cc->rpages = NULL; cc->nr_rpages = 0; cc->nr_cpages = 0; cc->valid_nr_cpages = 0; if (!reuse) cc->cluster_idx = NULL_CLUSTER; } void f2fs_compress_ctx_add_page(struct compress_ctx *cc, struct folio *folio) { unsigned int cluster_ofs; if (!f2fs_cluster_can_merge_page(cc, folio->index)) f2fs_bug_on(F2FS_I_SB(cc->inode), 1); cluster_ofs = offset_in_cluster(cc, folio->index); cc->rpages[cluster_ofs] = folio_page(folio, 0); cc->nr_rpages++; cc->cluster_idx = cluster_idx(cc, folio->index); } #ifdef CONFIG_F2FS_FS_LZO static int lzo_init_compress_ctx(struct compress_ctx *cc) { cc->private = f2fs_vmalloc(F2FS_I_SB(cc->inode), LZO1X_MEM_COMPRESS); if (!cc->private) return -ENOMEM; cc->clen = lzo1x_worst_compress(PAGE_SIZE << cc->log_cluster_size); return 0; } static void lzo_destroy_compress_ctx(struct compress_ctx *cc) { vfree(cc->private); cc->private = NULL; } static int lzo_compress_pages(struct compress_ctx *cc) { int ret; ret = lzo1x_1_compress(cc->rbuf, cc->rlen, cc->cbuf->cdata, &cc->clen, cc->private); if (ret != LZO_E_OK) { f2fs_err_ratelimited(F2FS_I_SB(cc->inode), "lzo compress failed, ret:%d", ret); return -EIO; } return 0; } static int lzo_decompress_pages(struct decompress_io_ctx *dic) { int ret; ret = lzo1x_decompress_safe(dic->cbuf->cdata, dic->clen, dic->rbuf, &dic->rlen); if (ret != LZO_E_OK) { f2fs_err_ratelimited(dic->sbi, "lzo decompress failed, ret:%d", ret); return -EIO; } if (dic->rlen != PAGE_SIZE << dic->log_cluster_size) { f2fs_err_ratelimited(dic->sbi, "lzo invalid rlen:%zu, expected:%lu", dic->rlen, PAGE_SIZE << dic->log_cluster_size); return -EIO; } return 0; } static const struct f2fs_compress_ops f2fs_lzo_ops = { .init_compress_ctx = lzo_init_compress_ctx, .destroy_compress_ctx = lzo_destroy_compress_ctx, .compress_pages = lzo_compress_pages, .decompress_pages = lzo_decompress_pages, }; #endif #ifdef CONFIG_F2FS_FS_LZ4 static int lz4_init_compress_ctx(struct compress_ctx *cc) { unsigned int size = LZ4_MEM_COMPRESS; #ifdef CONFIG_F2FS_FS_LZ4HC if (F2FS_I(cc->inode)->i_compress_level) size = LZ4HC_MEM_COMPRESS; #endif cc->private = f2fs_vmalloc(F2FS_I_SB(cc->inode), size); if (!cc->private) return -ENOMEM; /* * we do not change cc->clen to LZ4_compressBound(inputsize) to * adapt worst compress case, because lz4 compressor can handle * output budget properly. */ cc->clen = cc->rlen - PAGE_SIZE - COMPRESS_HEADER_SIZE; return 0; } static void lz4_destroy_compress_ctx(struct compress_ctx *cc) { vfree(cc->private); cc->private = NULL; } static int lz4_compress_pages(struct compress_ctx *cc) { int len = -EINVAL; unsigned char level = F2FS_I(cc->inode)->i_compress_level; if (!level) len = LZ4_compress_default(cc->rbuf, cc->cbuf->cdata, cc->rlen, cc->clen, cc->private); #ifdef CONFIG_F2FS_FS_LZ4HC else len = LZ4_compress_HC(cc->rbuf, cc->cbuf->cdata, cc->rlen, cc->clen, level, cc->private); #endif if (len < 0) return len; if (!len) return -EAGAIN; cc->clen = len; return 0; } static int lz4_decompress_pages(struct decompress_io_ctx *dic) { int ret; ret = LZ4_decompress_safe(dic->cbuf->cdata, dic->rbuf, dic->clen, dic->rlen); if (ret < 0) { f2fs_err_ratelimited(dic->sbi, "lz4 decompress failed, ret:%d", ret); return -EIO; } if (ret != PAGE_SIZE << dic->log_cluster_size) { f2fs_err_ratelimited(dic->sbi, "lz4 invalid ret:%d, expected:%lu", ret, PAGE_SIZE << dic->log_cluster_size); return -EIO; } return 0; } static bool lz4_is_level_valid(int lvl) { #ifdef CONFIG_F2FS_FS_LZ4HC return !lvl || (lvl >= LZ4HC_MIN_CLEVEL && lvl <= LZ4HC_MAX_CLEVEL); #else return lvl == 0; #endif } static const struct f2fs_compress_ops f2fs_lz4_ops = { .init_compress_ctx = lz4_init_compress_ctx, .destroy_compress_ctx = lz4_destroy_compress_ctx, .compress_pages = lz4_compress_pages, .decompress_pages = lz4_decompress_pages, .is_level_valid = lz4_is_level_valid, }; #endif #ifdef CONFIG_F2FS_FS_ZSTD static int zstd_init_compress_ctx(struct compress_ctx *cc) { zstd_parameters params; zstd_cstream *stream; void *workspace; unsigned int workspace_size; unsigned char level = F2FS_I(cc->inode)->i_compress_level; /* Need to remain this for backward compatibility */ if (!level) level = F2FS_ZSTD_DEFAULT_CLEVEL; params = zstd_get_params(level, cc->rlen); workspace_size = zstd_cstream_workspace_bound(¶ms.cParams); workspace = f2fs_vmalloc(F2FS_I_SB(cc->inode), workspace_size); if (!workspace) return -ENOMEM; stream = zstd_init_cstream(¶ms, 0, workspace, workspace_size); if (!stream) { f2fs_err_ratelimited(F2FS_I_SB(cc->inode), "%s zstd_init_cstream failed", __func__); vfree(workspace); return -EIO; } cc->private = workspace; cc->private2 = stream; cc->clen = cc->rlen - PAGE_SIZE - COMPRESS_HEADER_SIZE; return 0; } static void zstd_destroy_compress_ctx(struct compress_ctx *cc) { vfree(cc->private); cc->private = NULL; cc->private2 = NULL; } static int zstd_compress_pages(struct compress_ctx *cc) { zstd_cstream *stream = cc->private2; zstd_in_buffer inbuf; zstd_out_buffer outbuf; int src_size = cc->rlen; int dst_size = src_size - PAGE_SIZE - COMPRESS_HEADER_SIZE; int ret; inbuf.pos = 0; inbuf.src = cc->rbuf; inbuf.size = src_size; outbuf.pos = 0; outbuf.dst = cc->cbuf->cdata; outbuf.size = dst_size; ret = zstd_compress_stream(stream, &outbuf, &inbuf); if (zstd_is_error(ret)) { f2fs_err_ratelimited(F2FS_I_SB(cc->inode), "%s zstd_compress_stream failed, ret: %d", __func__, zstd_get_error_code(ret)); return -EIO; } ret = zstd_end_stream(stream, &outbuf); if (zstd_is_error(ret)) { f2fs_err_ratelimited(F2FS_I_SB(cc->inode), "%s zstd_end_stream returned %d", __func__, zstd_get_error_code(ret)); return -EIO; } /* * there is compressed data remained in intermediate buffer due to * no more space in cbuf.cdata */ if (ret) return -EAGAIN; cc->clen = outbuf.pos; return 0; } static int zstd_init_decompress_ctx(struct decompress_io_ctx *dic) { zstd_dstream *stream; void *workspace; unsigned int workspace_size; unsigned int max_window_size = MAX_COMPRESS_WINDOW_SIZE(dic->log_cluster_size); workspace_size = zstd_dstream_workspace_bound(max_window_size); workspace = f2fs_vmalloc(dic->sbi, workspace_size); if (!workspace) return -ENOMEM; stream = zstd_init_dstream(max_window_size, workspace, workspace_size); if (!stream) { f2fs_err_ratelimited(dic->sbi, "%s zstd_init_dstream failed", __func__); vfree(workspace); return -EIO; } dic->private = workspace; dic->private2 = stream; return 0; } static void zstd_destroy_decompress_ctx(struct decompress_io_ctx *dic) { vfree(dic->private); dic->private = NULL; dic->private2 = NULL; } static int zstd_decompress_pages(struct decompress_io_ctx *dic) { zstd_dstream *stream = dic->private2; zstd_in_buffer inbuf; zstd_out_buffer outbuf; int ret; inbuf.pos = 0; inbuf.src = dic->cbuf->cdata; inbuf.size = dic->clen; outbuf.pos = 0; outbuf.dst = dic->rbuf; outbuf.size = dic->rlen; ret = zstd_decompress_stream(stream, &outbuf, &inbuf); if (zstd_is_error(ret)) { f2fs_err_ratelimited(dic->sbi, "%s zstd_decompress_stream failed, ret: %d", __func__, zstd_get_error_code(ret)); return -EIO; } if (dic->rlen != outbuf.pos) { f2fs_err_ratelimited(dic->sbi, "%s ZSTD invalid rlen:%zu, expected:%lu", __func__, dic->rlen, PAGE_SIZE << dic->log_cluster_size); return -EIO; } return 0; } static bool zstd_is_level_valid(int lvl) { return lvl >= zstd_min_clevel() && lvl <= zstd_max_clevel(); } static const struct f2fs_compress_ops f2fs_zstd_ops = { .init_compress_ctx = zstd_init_compress_ctx, .destroy_compress_ctx = zstd_destroy_compress_ctx, .compress_pages = zstd_compress_pages, .init_decompress_ctx = zstd_init_decompress_ctx, .destroy_decompress_ctx = zstd_destroy_decompress_ctx, .decompress_pages = zstd_decompress_pages, .is_level_valid = zstd_is_level_valid, }; #endif #ifdef CONFIG_F2FS_FS_LZO #ifdef CONFIG_F2FS_FS_LZORLE static int lzorle_compress_pages(struct compress_ctx *cc) { int ret; ret = lzorle1x_1_compress(cc->rbuf, cc->rlen, cc->cbuf->cdata, &cc->clen, cc->private); if (ret != LZO_E_OK) { f2fs_err_ratelimited(F2FS_I_SB(cc->inode), "lzo-rle compress failed, ret:%d", ret); return -EIO; } return 0; } static const struct f2fs_compress_ops f2fs_lzorle_ops = { .init_compress_ctx = lzo_init_compress_ctx, .destroy_compress_ctx = lzo_destroy_compress_ctx, .compress_pages = lzorle_compress_pages, .decompress_pages = lzo_decompress_pages, }; #endif #endif static const struct f2fs_compress_ops *f2fs_cops[COMPRESS_MAX] = { #ifdef CONFIG_F2FS_FS_LZO &f2fs_lzo_ops, #else NULL, #endif #ifdef CONFIG_F2FS_FS_LZ4 &f2fs_lz4_ops, #else NULL, #endif #ifdef CONFIG_F2FS_FS_ZSTD &f2fs_zstd_ops, #else NULL, #endif #if defined(CONFIG_F2FS_FS_LZO) && defined(CONFIG_F2FS_FS_LZORLE) &f2fs_lzorle_ops, #else NULL, #endif }; bool f2fs_is_compress_backend_ready(struct inode *inode) { if (!f2fs_compressed_file(inode)) return true; return f2fs_cops[F2FS_I(inode)->i_compress_algorithm]; } bool f2fs_is_compress_level_valid(int alg, int lvl) { const struct f2fs_compress_ops *cops = f2fs_cops[alg]; if (cops->is_level_valid) return cops->is_level_valid(lvl); return lvl == 0; } static mempool_t *compress_page_pool; static int num_compress_pages = 512; module_param(num_compress_pages, uint, 0444); MODULE_PARM_DESC(num_compress_pages, "Number of intermediate compress pages to preallocate"); int __init f2fs_init_compress_mempool(void) { compress_page_pool = mempool_create_page_pool(num_compress_pages, 0); return compress_page_pool ? 0 : -ENOMEM; } void f2fs_destroy_compress_mempool(void) { mempool_destroy(compress_page_pool); } static struct page *f2fs_compress_alloc_page(void) { struct page *page; page = mempool_alloc(compress_page_pool, GFP_NOFS); lock_page(page); return page; } static void f2fs_compress_free_page(struct page *page) { struct folio *folio; if (!page) return; folio = page_folio(page); folio_detach_private(folio); folio->mapping = NULL; folio_unlock(folio); mempool_free(page, compress_page_pool); } #define MAX_VMAP_RETRIES 3 static void *f2fs_vmap(struct page **pages, unsigned int count) { int i; void *buf = NULL; for (i = 0; i < MAX_VMAP_RETRIES; i++) { buf = vm_map_ram(pages, count, -1); if (buf) break; vm_unmap_aliases(); } return buf; } static int f2fs_compress_pages(struct compress_ctx *cc) { struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode); struct f2fs_inode_info *fi = F2FS_I(cc->inode); const struct f2fs_compress_ops *cops = f2fs_cops[fi->i_compress_algorithm]; unsigned int max_len, new_nr_cpages; u32 chksum = 0; int i, ret; trace_f2fs_compress_pages_start(cc->inode, cc->cluster_idx, cc->cluster_size, fi->i_compress_algorithm); if (cops->init_compress_ctx) { ret = cops->init_compress_ctx(cc); if (ret) goto out; } max_len = COMPRESS_HEADER_SIZE + cc->clen; cc->nr_cpages = DIV_ROUND_UP(max_len, PAGE_SIZE); cc->valid_nr_cpages = cc->nr_cpages; cc->cpages = page_array_alloc(sbi, cc->nr_cpages); if (!cc->cpages) { ret = -ENOMEM; goto destroy_compress_ctx; } for (i = 0; i < cc->nr_cpages; i++) cc->cpages[i] = f2fs_compress_alloc_page(); cc->rbuf = f2fs_vmap(cc->rpages, cc->cluster_size); if (!cc->rbuf) { ret = -ENOMEM; goto out_free_cpages; } cc->cbuf = f2fs_vmap(cc->cpages, cc->nr_cpages); if (!cc->cbuf) { ret = -ENOMEM; goto out_vunmap_rbuf; } ret = cops->compress_pages(cc); if (ret) goto out_vunmap_cbuf; max_len = PAGE_SIZE * (cc->cluster_size - 1) - COMPRESS_HEADER_SIZE; if (cc->clen > max_len) { ret = -EAGAIN; goto out_vunmap_cbuf; } cc->cbuf->clen = cpu_to_le32(cc->clen); if (fi->i_compress_flag & BIT(COMPRESS_CHKSUM)) chksum = f2fs_crc32(cc->cbuf->cdata, cc->clen); cc->cbuf->chksum = cpu_to_le32(chksum); for (i = 0; i < COMPRESS_DATA_RESERVED_SIZE; i++) cc->cbuf->reserved[i] = cpu_to_le32(0); new_nr_cpages = DIV_ROUND_UP(cc->clen + COMPRESS_HEADER_SIZE, PAGE_SIZE); /* zero out any unused part of the last page */ memset(&cc->cbuf->cdata[cc->clen], 0, (new_nr_cpages * PAGE_SIZE) - (cc->clen + COMPRESS_HEADER_SIZE)); vm_unmap_ram(cc->cbuf, cc->nr_cpages); vm_unmap_ram(cc->rbuf, cc->cluster_size); for (i = new_nr_cpages; i < cc->nr_cpages; i++) { f2fs_compress_free_page(cc->cpages[i]); cc->cpages[i] = NULL; } if (cops->destroy_compress_ctx) cops->destroy_compress_ctx(cc); cc->valid_nr_cpages = new_nr_cpages; trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx, cc->clen, ret); return 0; out_vunmap_cbuf: vm_unmap_ram(cc->cbuf, cc->nr_cpages); out_vunmap_rbuf: vm_unmap_ram(cc->rbuf, cc->cluster_size); out_free_cpages: for (i = 0; i < cc->nr_cpages; i++) { if (cc->cpages[i]) f2fs_compress_free_page(cc->cpages[i]); } page_array_free(sbi, cc->cpages, cc->nr_cpages); cc->cpages = NULL; destroy_compress_ctx: if (cops->destroy_compress_ctx) cops->destroy_compress_ctx(cc); out: trace_f2fs_compress_pages_end(cc->inode, cc->cluster_idx, cc->clen, ret); return ret; } static int f2fs_prepare_decomp_mem(struct decompress_io_ctx *dic, bool pre_alloc); static void f2fs_release_decomp_mem(struct decompress_io_ctx *dic, bool bypass_destroy_callback, bool pre_alloc); void f2fs_decompress_cluster(struct decompress_io_ctx *dic, bool in_task) { struct f2fs_sb_info *sbi = dic->sbi; struct f2fs_inode_info *fi = F2FS_I(dic->inode); const struct f2fs_compress_ops *cops = f2fs_cops[fi->i_compress_algorithm]; bool bypass_callback = false; int ret; trace_f2fs_decompress_pages_start(dic->inode, dic->cluster_idx, dic->cluster_size, fi->i_compress_algorithm); if (dic->failed) { ret = -EIO; goto out_end_io; } ret = f2fs_prepare_decomp_mem(dic, false); if (ret) { bypass_callback = true; goto out_release; } dic->clen = le32_to_cpu(dic->cbuf->clen); dic->rlen = PAGE_SIZE << dic->log_cluster_size; if (dic->clen > PAGE_SIZE * dic->nr_cpages - COMPRESS_HEADER_SIZE) { ret = -EFSCORRUPTED; /* Avoid f2fs_commit_super in irq context */ if (!in_task) f2fs_handle_error_async(sbi, ERROR_FAIL_DECOMPRESSION); else f2fs_handle_error(sbi, ERROR_FAIL_DECOMPRESSION); goto out_release; } ret = cops->decompress_pages(dic); if (!ret && (fi->i_compress_flag & BIT(COMPRESS_CHKSUM))) { u32 provided = le32_to_cpu(dic->cbuf->chksum); u32 calculated = f2fs_crc32(dic->cbuf->cdata, dic->clen); if (provided != calculated) { if (!is_inode_flag_set(dic->inode, FI_COMPRESS_CORRUPT)) { set_inode_flag(dic->inode, FI_COMPRESS_CORRUPT); f2fs_info_ratelimited(sbi, "checksum invalid, nid = %lu, %x vs %x", dic->inode->i_ino, provided, calculated); } set_sbi_flag(sbi, SBI_NEED_FSCK); } } out_release: f2fs_release_decomp_mem(dic, bypass_callback, false); out_end_io: trace_f2fs_decompress_pages_end(dic->inode, dic->cluster_idx, dic->clen, ret); f2fs_decompress_end_io(dic, ret, in_task); } static void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct folio *folio, nid_t ino, block_t blkaddr); /* * This is called when a page of a compressed cluster has been read from disk * (or failed to be read from disk). It checks whether this page was the last * page being waited on in the cluster, and if so, it decompresses the cluster * (or in the case of a failure, cleans up without actually decompressing). */ void f2fs_end_read_compressed_page(struct folio *folio, bool failed, block_t blkaddr, bool in_task) { struct decompress_io_ctx *dic = folio->private; struct f2fs_sb_info *sbi = dic->sbi; dec_page_count(sbi, F2FS_RD_DATA); if (failed) WRITE_ONCE(dic->failed, true); else if (blkaddr && in_task) f2fs_cache_compressed_page(sbi, folio, dic->inode->i_ino, blkaddr); if (atomic_dec_and_test(&dic->remaining_pages)) f2fs_decompress_cluster(dic, in_task); } static bool is_page_in_cluster(struct compress_ctx *cc, pgoff_t index) { if (cc->cluster_idx == NULL_CLUSTER) return true; return cc->cluster_idx == cluster_idx(cc, index); } bool f2fs_cluster_is_empty(struct compress_ctx *cc) { return cc->nr_rpages == 0; } static bool f2fs_cluster_is_full(struct compress_ctx *cc) { return cc->cluster_size == cc->nr_rpages; } bool f2fs_cluster_can_merge_page(struct compress_ctx *cc, pgoff_t index) { if (f2fs_cluster_is_empty(cc)) return true; return is_page_in_cluster(cc, index); } bool f2fs_all_cluster_page_ready(struct compress_ctx *cc, struct page **pages, int index, int nr_pages, bool uptodate) { unsigned long pgidx = page_folio(pages[index])->index; int i = uptodate ? 0 : 1; /* * when uptodate set to true, try to check all pages in cluster is * uptodate or not. */ if (uptodate && (pgidx % cc->cluster_size)) return false; if (nr_pages - index < cc->cluster_size) return false; for (; i < cc->cluster_size; i++) { struct folio *folio = page_folio(pages[index + i]); if (folio->index != pgidx + i) return false; if (uptodate && !folio_test_uptodate(folio)) return false; } return true; } static bool cluster_has_invalid_data(struct compress_ctx *cc) { loff_t i_size = i_size_read(cc->inode); unsigned nr_pages = DIV_ROUND_UP(i_size, PAGE_SIZE); int i; for (i = 0; i < cc->cluster_size; i++) { struct page *page = cc->rpages[i]; f2fs_bug_on(F2FS_I_SB(cc->inode), !page); /* beyond EOF */ if (page_folio(page)->index >= nr_pages) return true; } return false; } bool f2fs_sanity_check_cluster(struct dnode_of_data *dn) { #ifdef CONFIG_F2FS_CHECK_FS struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode); unsigned int cluster_size = F2FS_I(dn->inode)->i_cluster_size; int cluster_end = 0; unsigned int count; int i; char *reason = ""; if (dn->data_blkaddr != COMPRESS_ADDR) return false; /* [..., COMPR_ADDR, ...] */ if (dn->ofs_in_node % cluster_size) { reason = "[*|C|*|*]"; goto out; } for (i = 1, count = 1; i < cluster_size; i++, count++) { block_t blkaddr = data_blkaddr(dn->inode, dn->node_folio, dn->ofs_in_node + i); /* [COMPR_ADDR, ..., COMPR_ADDR] */ if (blkaddr == COMPRESS_ADDR) { reason = "[C|*|C|*]"; goto out; } if (!__is_valid_data_blkaddr(blkaddr)) { if (!cluster_end) cluster_end = i; continue; } /* [COMPR_ADDR, NULL_ADDR or NEW_ADDR, valid_blkaddr] */ if (cluster_end) { reason = "[C|N|N|V]"; goto out; } } f2fs_bug_on(F2FS_I_SB(dn->inode), count != cluster_size && !is_inode_flag_set(dn->inode, FI_COMPRESS_RELEASED)); return false; out: f2fs_warn(sbi, "access invalid cluster, ino:%lu, nid:%u, ofs_in_node:%u, reason:%s", dn->inode->i_ino, dn->nid, dn->ofs_in_node, reason); set_sbi_flag(sbi, SBI_NEED_FSCK); return true; #else return false; #endif } static int __f2fs_get_cluster_blocks(struct inode *inode, struct dnode_of_data *dn) { unsigned int cluster_size = F2FS_I(inode)->i_cluster_size; int count, i; for (i = 0, count = 0; i < cluster_size; i++) { block_t blkaddr = data_blkaddr(dn->inode, dn->node_folio, dn->ofs_in_node + i); if (__is_valid_data_blkaddr(blkaddr)) count++; } return count; } static int __f2fs_cluster_blocks(struct inode *inode, unsigned int cluster_idx, enum cluster_check_type type) { struct dnode_of_data dn; unsigned int start_idx = cluster_idx << F2FS_I(inode)->i_log_cluster_size; int ret; set_new_dnode(&dn, inode, NULL, NULL, 0); ret = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE); if (ret) { if (ret == -ENOENT) ret = 0; goto fail; } if (f2fs_sanity_check_cluster(&dn)) { ret = -EFSCORRUPTED; goto fail; } if (dn.data_blkaddr == COMPRESS_ADDR) { if (type == CLUSTER_COMPR_BLKS) ret = 1 + __f2fs_get_cluster_blocks(inode, &dn); else if (type == CLUSTER_IS_COMPR) ret = 1; } else if (type == CLUSTER_RAW_BLKS) { ret = __f2fs_get_cluster_blocks(inode, &dn); } fail: f2fs_put_dnode(&dn); return ret; } /* return # of compressed blocks in compressed cluster */ static int f2fs_compressed_blocks(struct compress_ctx *cc) { return __f2fs_cluster_blocks(cc->inode, cc->cluster_idx, CLUSTER_COMPR_BLKS); } /* return # of raw blocks in non-compressed cluster */ static int f2fs_decompressed_blocks(struct inode *inode, unsigned int cluster_idx) { return __f2fs_cluster_blocks(inode, cluster_idx, CLUSTER_RAW_BLKS); } /* return whether cluster is compressed one or not */ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index) { return __f2fs_cluster_blocks(inode, index >> F2FS_I(inode)->i_log_cluster_size, CLUSTER_IS_COMPR); } /* return whether cluster contains non raw blocks or not */ bool f2fs_is_sparse_cluster(struct inode *inode, pgoff_t index) { unsigned int cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size; return f2fs_decompressed_blocks(inode, cluster_idx) != F2FS_I(inode)->i_cluster_size; } static bool cluster_may_compress(struct compress_ctx *cc) { if (!f2fs_need_compress_data(cc->inode)) return false; if (f2fs_is_atomic_file(cc->inode)) return false; if (!f2fs_cluster_is_full(cc)) return false; if (unlikely(f2fs_cp_error(F2FS_I_SB(cc->inode)))) return false; return !cluster_has_invalid_data(cc); } static void set_cluster_writeback(struct compress_ctx *cc) { int i; for (i = 0; i < cc->cluster_size; i++) { if (cc->rpages[i]) set_page_writeback(cc->rpages[i]); } } static void cancel_cluster_writeback(struct compress_ctx *cc, struct compress_io_ctx *cic, int submitted) { int i; /* Wait for submitted IOs. */ if (submitted > 1) { f2fs_submit_merged_write(F2FS_I_SB(cc->inode), DATA); while (atomic_read(&cic->pending_pages) != (cc->valid_nr_cpages - submitted + 1)) f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); } /* Cancel writeback and stay locked. */ for (i = 0; i < cc->cluster_size; i++) { if (i < submitted) { inode_inc_dirty_pages(cc->inode); lock_page(cc->rpages[i]); } clear_page_private_gcing(cc->rpages[i]); if (folio_test_writeback(page_folio(cc->rpages[i]))) end_page_writeback(cc->rpages[i]); } } static void set_cluster_dirty(struct compress_ctx *cc) { int i; for (i = 0; i < cc->cluster_size; i++) if (cc->rpages[i]) { set_page_dirty(cc->rpages[i]); set_page_private_gcing(cc->rpages[i]); } } static int prepare_compress_overwrite(struct compress_ctx *cc, struct page **pagep, pgoff_t index, void **fsdata) { struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode); struct address_space *mapping = cc->inode->i_mapping; struct folio *folio; sector_t last_block_in_bio; fgf_t fgp_flag = FGP_LOCK | FGP_WRITE | FGP_CREAT; pgoff_t start_idx = start_idx_of_cluster(cc); int i, ret; retry: ret = f2fs_is_compressed_cluster(cc->inode, start_idx); if (ret <= 0) return ret; ret = f2fs_init_compress_ctx(cc); if (ret) return ret; /* keep folio reference to avoid page reclaim */ for (i = 0; i < cc->cluster_size; i++) { folio = f2fs_filemap_get_folio(mapping, start_idx + i, fgp_flag, GFP_NOFS); if (IS_ERR(folio)) { ret = PTR_ERR(folio); goto unlock_pages; } if (folio_test_uptodate(folio)) f2fs_folio_put(folio, true); else f2fs_compress_ctx_add_page(cc, folio); } if (!f2fs_cluster_is_empty(cc)) { struct bio *bio = NULL; ret = f2fs_read_multi_pages(cc, &bio, cc->cluster_size, &last_block_in_bio, NULL, true); f2fs_put_rpages(cc); f2fs_destroy_compress_ctx(cc, true); if (ret) goto out; if (bio) f2fs_submit_read_bio(sbi, bio, DATA); ret = f2fs_init_compress_ctx(cc); if (ret) goto out; } for (i = 0; i < cc->cluster_size; i++) { f2fs_bug_on(sbi, cc->rpages[i]); folio = filemap_lock_folio(mapping, start_idx + i); if (IS_ERR(folio)) { /* folio could be truncated */ goto release_and_retry; } f2fs_folio_wait_writeback(folio, DATA, true, true); f2fs_compress_ctx_add_page(cc, folio); if (!folio_test_uptodate(folio)) { f2fs_handle_page_eio(sbi, folio, DATA); release_and_retry: f2fs_put_rpages(cc); f2fs_unlock_rpages(cc, i + 1); f2fs_destroy_compress_ctx(cc, true); goto retry; } } if (likely(!ret)) { *fsdata = cc->rpages; *pagep = cc->rpages[offset_in_cluster(cc, index)]; return cc->cluster_size; } unlock_pages: f2fs_put_rpages(cc); f2fs_unlock_rpages(cc, i); f2fs_destroy_compress_ctx(cc, true); out: return ret; } int f2fs_prepare_compress_overwrite(struct inode *inode, struct page **pagep, pgoff_t index, void **fsdata) { struct compress_ctx cc = { .inode = inode, .log_cluster_size = F2FS_I(inode)->i_log_cluster_size, .cluster_size = F2FS_I(inode)->i_cluster_size, .cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size, .rpages = NULL, .nr_rpages = 0, }; return prepare_compress_overwrite(&cc, pagep, index, fsdata); } bool f2fs_compress_write_end(struct inode *inode, void *fsdata, pgoff_t index, unsigned copied) { struct compress_ctx cc = { .inode = inode, .log_cluster_size = F2FS_I(inode)->i_log_cluster_size, .cluster_size = F2FS_I(inode)->i_cluster_size, .rpages = fsdata, }; struct folio *folio = page_folio(cc.rpages[0]); bool first_index = (index == folio->index); if (copied) set_cluster_dirty(&cc); f2fs_put_rpages_wbc(&cc, NULL, false, 1); f2fs_destroy_compress_ctx(&cc, false); return first_index; } int f2fs_truncate_partial_cluster(struct inode *inode, u64 from, bool lock) { void *fsdata = NULL; struct page *pagep; int log_cluster_size = F2FS_I(inode)->i_log_cluster_size; pgoff_t start_idx = from >> (PAGE_SHIFT + log_cluster_size) << log_cluster_size; int err; err = f2fs_is_compressed_cluster(inode, start_idx); if (err < 0) return err; /* truncate normal cluster */ if (!err) return f2fs_do_truncate_blocks(inode, from, lock); /* truncate compressed cluster */ err = f2fs_prepare_compress_overwrite(inode, &pagep, start_idx, &fsdata); /* should not be a normal cluster */ f2fs_bug_on(F2FS_I_SB(inode), err == 0); if (err <= 0) return err; if (err > 0) { struct page **rpages = fsdata; int cluster_size = F2FS_I(inode)->i_cluster_size; int i; for (i = cluster_size - 1; i >= 0; i--) { struct folio *folio = page_folio(rpages[i]); loff_t start = folio->index << PAGE_SHIFT; if (from <= start) { folio_zero_segment(folio, 0, folio_size(folio)); } else { folio_zero_segment(folio, from - start, folio_size(folio)); break; } } f2fs_compress_write_end(inode, fsdata, start_idx, true); } return 0; } static int f2fs_write_compressed_pages(struct compress_ctx *cc, int *submitted, struct writeback_control *wbc, enum iostat_type io_type) { struct inode *inode = cc->inode; struct f2fs_sb_info *sbi = F2FS_I_SB(inode); struct f2fs_inode_info *fi = F2FS_I(inode); struct f2fs_io_info fio = { .sbi = sbi, .ino = cc->inode->i_ino, .type = DATA, .op = REQ_OP_WRITE, .op_flags = wbc_to_write_flags(wbc), .old_blkaddr = NEW_ADDR, .page = NULL, .encrypted_page = NULL, .compressed_page = NULL, .io_type = io_type, .io_wbc = wbc, .encrypted = fscrypt_inode_uses_fs_layer_crypto(cc->inode) ? 1 : 0, }; struct folio *folio; struct dnode_of_data dn; struct node_info ni; struct compress_io_ctx *cic; pgoff_t start_idx = start_idx_of_cluster(cc); unsigned int last_index = cc->cluster_size - 1; loff_t psize; int i, err; bool quota_inode = IS_NOQUOTA(inode); /* we should bypass data pages to proceed the kworker jobs */ if (unlikely(f2fs_cp_error(sbi))) { mapping_set_error(inode->i_mapping, -EIO); goto out_free; } if (quota_inode) { /* * We need to wait for node_write to avoid block allocation during * checkpoint. This can only happen to quota writes which can cause * the below discard race condition. */ f2fs_down_read(&sbi->node_write); } else if (!f2fs_trylock_op(sbi)) { goto out_free; } set_new_dnode(&dn, cc->inode, NULL, NULL, 0); err = f2fs_get_dnode_of_data(&dn, start_idx, LOOKUP_NODE); if (err) goto out_unlock_op; for (i = 0; i < cc->cluster_size; i++) { if (data_blkaddr(dn.inode, dn.node_folio, dn.ofs_in_node + i) == NULL_ADDR) goto out_put_dnode; } folio = page_folio(cc->rpages[last_index]); psize = folio_pos(folio) + folio_size(folio); err = f2fs_get_node_info(fio.sbi, dn.nid, &ni, false); if (err) goto out_put_dnode; fio.version = ni.version; cic = f2fs_kmem_cache_alloc(cic_entry_slab, GFP_F2FS_ZERO, false, sbi); if (!cic) goto out_put_dnode; cic->magic = F2FS_COMPRESSED_PAGE_MAGIC; cic->inode = inode; atomic_set(&cic->pending_pages, cc->valid_nr_cpages); cic->rpages = page_array_alloc(sbi, cc->cluster_size); if (!cic->rpages) goto out_put_cic; cic->nr_rpages = cc->cluster_size; for (i = 0; i < cc->valid_nr_cpages; i++) { f2fs_set_compressed_page(cc->cpages[i], inode, page_folio(cc->rpages[i + 1])->index, cic); fio.compressed_page = cc->cpages[i]; fio.old_blkaddr = data_blkaddr(dn.inode, dn.node_folio, dn.ofs_in_node + i + 1); /* wait for GCed page writeback via META_MAPPING */ f2fs_wait_on_block_writeback(inode, fio.old_blkaddr); if (fio.encrypted) { fio.page = cc->rpages[i + 1]; err = f2fs_encrypt_one_page(&fio); if (err) goto out_destroy_crypt; cc->cpages[i] = fio.encrypted_page; } } set_cluster_writeback(cc); for (i = 0; i < cc->cluster_size; i++) cic->rpages[i] = cc->rpages[i]; for (i = 0; i < cc->cluster_size; i++, dn.ofs_in_node++) { block_t blkaddr; blkaddr = f2fs_data_blkaddr(&dn); fio.page = cc->rpages[i]; fio.old_blkaddr = blkaddr; /* cluster header */ if (i == 0) { if (blkaddr == COMPRESS_ADDR) fio.compr_blocks++; if (__is_valid_data_blkaddr(blkaddr)) f2fs_invalidate_blocks(sbi, blkaddr, 1); f2fs_update_data_blkaddr(&dn, COMPRESS_ADDR); goto unlock_continue; } if (fio.compr_blocks && __is_valid_data_blkaddr(blkaddr)) fio.compr_blocks++; if (i > cc->valid_nr_cpages) { if (__is_valid_data_blkaddr(blkaddr)) { f2fs_invalidate_blocks(sbi, blkaddr, 1); f2fs_update_data_blkaddr(&dn, NEW_ADDR); } goto unlock_continue; } f2fs_bug_on(fio.sbi, blkaddr == NULL_ADDR); if (fio.encrypted) fio.encrypted_page = cc->cpages[i - 1]; else fio.compressed_page = cc->cpages[i - 1]; cc->cpages[i - 1] = NULL; fio.submitted = 0; f2fs_outplace_write_data(&dn, &fio); if (unlikely(!fio.submitted)) { cancel_cluster_writeback(cc, cic, i); /* To call fscrypt_finalize_bounce_page */ i = cc->valid_nr_cpages; *submitted = 0; goto out_destroy_crypt; } (*submitted)++; unlock_continue: inode_dec_dirty_pages(cc->inode); folio_unlock(fio.folio); } if (fio.compr_blocks) f2fs_i_compr_blocks_update(inode, fio.compr_blocks - 1, false); f2fs_i_compr_blocks_update(inode, cc->valid_nr_cpages, true); add_compr_block_stat(inode, cc->valid_nr_cpages); set_inode_flag(cc->inode, FI_APPEND_WRITE); f2fs_put_dnode(&dn); if (quota_inode) f2fs_up_read(&sbi->node_write); else f2fs_unlock_op(sbi); spin_lock(&fi->i_size_lock); if (fi->last_disk_size < psize) fi->last_disk_size = psize; spin_unlock(&fi->i_size_lock); f2fs_put_rpages(cc); page_array_free(sbi, cc->cpages, cc->nr_cpages); cc->cpages = NULL; f2fs_destroy_compress_ctx(cc, false); return 0; out_destroy_crypt: page_array_free(sbi, cic->rpages, cc->cluster_size); for (--i; i >= 0; i--) { if (!cc->cpages[i]) continue; fscrypt_finalize_bounce_page(&cc->cpages[i]); } out_put_cic: kmem_cache_free(cic_entry_slab, cic); out_put_dnode: f2fs_put_dnode(&dn); out_unlock_op: if (quota_inode) f2fs_up_read(&sbi->node_write); else f2fs_unlock_op(sbi); out_free: for (i = 0; i < cc->valid_nr_cpages; i++) { f2fs_compress_free_page(cc->cpages[i]); cc->cpages[i] = NULL; } page_array_free(sbi, cc->cpages, cc->nr_cpages); cc->cpages = NULL; return -EAGAIN; } void f2fs_compress_write_end_io(struct bio *bio, struct folio *folio) { struct page *page = &folio->page; struct f2fs_sb_info *sbi = bio->bi_private; struct compress_io_ctx *cic = folio->private; enum count_type type = WB_DATA_TYPE(folio, f2fs_is_compressed_page(folio)); int i; if (unlikely(bio->bi_status != BLK_STS_OK)) mapping_set_error(cic->inode->i_mapping, -EIO); f2fs_compress_free_page(page); dec_page_count(sbi, type); if (atomic_dec_return(&cic->pending_pages)) return; for (i = 0; i < cic->nr_rpages; i++) { WARN_ON(!cic->rpages[i]); clear_page_private_gcing(cic->rpages[i]); end_page_writeback(cic->rpages[i]); } page_array_free(sbi, cic->rpages, cic->nr_rpages); kmem_cache_free(cic_entry_slab, cic); } static int f2fs_write_raw_pages(struct compress_ctx *cc, int *submitted_p, struct writeback_control *wbc, enum iostat_type io_type) { struct address_space *mapping = cc->inode->i_mapping; struct f2fs_sb_info *sbi = F2FS_M_SB(mapping); int submitted, compr_blocks, i; int ret = 0; compr_blocks = f2fs_compressed_blocks(cc); for (i = 0; i < cc->cluster_size; i++) { if (!cc->rpages[i]) continue; redirty_page_for_writepage(wbc, cc->rpages[i]); unlock_page(cc->rpages[i]); } if (compr_blocks < 0) return compr_blocks; /* overwrite compressed cluster w/ normal cluster */ if (compr_blocks > 0) f2fs_lock_op(sbi); for (i = 0; i < cc->cluster_size; i++) { struct folio *folio; if (!cc->rpages[i]) continue; folio = page_folio(cc->rpages[i]); retry_write: folio_lock(folio); if (folio->mapping != mapping) { continue_unlock: folio_unlock(folio); continue; } if (!folio_test_dirty(folio)) goto continue_unlock; if (folio_test_writeback(folio)) { if (wbc->sync_mode == WB_SYNC_NONE) goto continue_unlock; f2fs_folio_wait_writeback(folio, DATA, true, true); } if (!folio_clear_dirty_for_io(folio)) goto continue_unlock; submitted = 0; ret = f2fs_write_single_data_page(folio, &submitted, NULL, NULL, wbc, io_type, compr_blocks, false); if (ret) { if (ret == 1) { ret = 0; } else if (ret == -EAGAIN) { ret = 0; /* * for quota file, just redirty left pages to * avoid deadlock caused by cluster update race * from foreground operation. */ if (IS_NOQUOTA(cc->inode)) goto out; f2fs_io_schedule_timeout(DEFAULT_IO_TIMEOUT); goto retry_write; } goto out; } *submitted_p += submitted; } out: if (compr_blocks > 0) f2fs_unlock_op(sbi); f2fs_balance_fs(sbi, true); return ret; } int f2fs_write_multi_pages(struct compress_ctx *cc, int *submitted, struct writeback_control *wbc, enum iostat_type io_type) { int err; *submitted = 0; if (cluster_may_compress(cc)) { err = f2fs_compress_pages(cc); if (err == -EAGAIN) { add_compr_block_stat(cc->inode, cc->cluster_size); goto write; } else if (err) { f2fs_put_rpages_wbc(cc, wbc, true, 1); goto destroy_out; } err = f2fs_write_compressed_pages(cc, submitted, wbc, io_type); if (!err) return 0; f2fs_bug_on(F2FS_I_SB(cc->inode), err != -EAGAIN); } write: f2fs_bug_on(F2FS_I_SB(cc->inode), *submitted); err = f2fs_write_raw_pages(cc, submitted, wbc, io_type); f2fs_put_rpages_wbc(cc, wbc, false, 0); destroy_out: f2fs_destroy_compress_ctx(cc, false); return err; } static inline bool allow_memalloc_for_decomp(struct f2fs_sb_info *sbi, bool pre_alloc) { return pre_alloc ^ f2fs_low_mem_mode(sbi); } static int f2fs_prepare_decomp_mem(struct decompress_io_ctx *dic, bool pre_alloc) { const struct f2fs_compress_ops *cops = f2fs_cops[dic->compress_algorithm]; int i; if (!allow_memalloc_for_decomp(dic->sbi, pre_alloc)) return 0; dic->tpages = page_array_alloc(dic->sbi, dic->cluster_size); if (!dic->tpages) return -ENOMEM; for (i = 0; i < dic->cluster_size; i++) { if (dic->rpages[i]) { dic->tpages[i] = dic->rpages[i]; continue; } dic->tpages[i] = f2fs_compress_alloc_page(); } dic->rbuf = f2fs_vmap(dic->tpages, dic->cluster_size); if (!dic->rbuf) return -ENOMEM; dic->cbuf = f2fs_vmap(dic->cpages, dic->nr_cpages); if (!dic->cbuf) return -ENOMEM; if (cops->init_decompress_ctx) return cops->init_decompress_ctx(dic); return 0; } static void f2fs_release_decomp_mem(struct decompress_io_ctx *dic, bool bypass_destroy_callback, bool pre_alloc) { const struct f2fs_compress_ops *cops = f2fs_cops[dic->compress_algorithm]; if (!allow_memalloc_for_decomp(dic->sbi, pre_alloc)) return; if (!bypass_destroy_callback && cops->destroy_decompress_ctx) cops->destroy_decompress_ctx(dic); if (dic->cbuf) vm_unmap_ram(dic->cbuf, dic->nr_cpages); if (dic->rbuf) vm_unmap_ram(dic->rbuf, dic->cluster_size); } static void f2fs_free_dic(struct decompress_io_ctx *dic, bool bypass_destroy_callback); struct decompress_io_ctx *f2fs_alloc_dic(struct compress_ctx *cc) { struct decompress_io_ctx *dic; pgoff_t start_idx = start_idx_of_cluster(cc); struct f2fs_sb_info *sbi = F2FS_I_SB(cc->inode); int i, ret; dic = f2fs_kmem_cache_alloc(dic_entry_slab, GFP_F2FS_ZERO, false, sbi); if (!dic) return ERR_PTR(-ENOMEM); dic->rpages = page_array_alloc(sbi, cc->cluster_size); if (!dic->rpages) { kmem_cache_free(dic_entry_slab, dic); return ERR_PTR(-ENOMEM); } dic->magic = F2FS_COMPRESSED_PAGE_MAGIC; dic->inode = cc->inode; dic->sbi = sbi; dic->compress_algorithm = F2FS_I(cc->inode)->i_compress_algorithm; atomic_set(&dic->remaining_pages, cc->nr_cpages); dic->cluster_idx = cc->cluster_idx; dic->cluster_size = cc->cluster_size; dic->log_cluster_size = cc->log_cluster_size; dic->nr_cpages = cc->nr_cpages; refcount_set(&dic->refcnt, 1); dic->failed = false; dic->need_verity = f2fs_need_verity(cc->inode, start_idx); for (i = 0; i < dic->cluster_size; i++) dic->rpages[i] = cc->rpages[i]; dic->nr_rpages = cc->cluster_size; dic->cpages = page_array_alloc(sbi, dic->nr_cpages); if (!dic->cpages) { ret = -ENOMEM; goto out_free; } for (i = 0; i < dic->nr_cpages; i++) { struct page *page; page = f2fs_compress_alloc_page(); f2fs_set_compressed_page(page, cc->inode, start_idx + i + 1, dic); dic->cpages[i] = page; } ret = f2fs_prepare_decomp_mem(dic, true); if (ret) goto out_free; return dic; out_free: f2fs_free_dic(dic, true); return ERR_PTR(ret); } static void f2fs_free_dic(struct decompress_io_ctx *dic, bool bypass_destroy_callback) { int i; /* use sbi in dic to avoid UFA of dic->inode*/ struct f2fs_sb_info *sbi = dic->sbi; f2fs_release_decomp_mem(dic, bypass_destroy_callback, true); if (dic->tpages) { for (i = 0; i < dic->cluster_size; i++) { if (dic->rpages[i]) continue; if (!dic->tpages[i]) continue; f2fs_compress_free_page(dic->tpages[i]); } page_array_free(sbi, dic->tpages, dic->cluster_size); } if (dic->cpages) { for (i = 0; i < dic->nr_cpages; i++) { if (!dic->cpages[i]) continue; f2fs_compress_free_page(dic->cpages[i]); } page_array_free(sbi, dic->cpages, dic->nr_cpages); } page_array_free(sbi, dic->rpages, dic->nr_rpages); kmem_cache_free(dic_entry_slab, dic); } static void f2fs_late_free_dic(struct work_struct *work) { struct decompress_io_ctx *dic = container_of(work, struct decompress_io_ctx, free_work); f2fs_free_dic(dic, false); } static void f2fs_put_dic(struct decompress_io_ctx *dic, bool in_task) { if (refcount_dec_and_test(&dic->refcnt)) { if (in_task) { f2fs_free_dic(dic, false); } else { INIT_WORK(&dic->free_work, f2fs_late_free_dic); queue_work(dic->sbi->post_read_wq, &dic->free_work); } } } static void f2fs_verify_cluster(struct work_struct *work) { struct decompress_io_ctx *dic = container_of(work, struct decompress_io_ctx, verity_work); int i; /* Verify, update, and unlock the decompressed pages. */ for (i = 0; i < dic->cluster_size; i++) { struct page *rpage = dic->rpages[i]; if (!rpage) continue; if (fsverity_verify_page(rpage)) SetPageUptodate(rpage); else ClearPageUptodate(rpage); unlock_page(rpage); } f2fs_put_dic(dic, true); } /* * This is called when a compressed cluster has been decompressed * (or failed to be read and/or decompressed). */ void f2fs_decompress_end_io(struct decompress_io_ctx *dic, bool failed, bool in_task) { int i; if (!failed && dic->need_verity) { /* * Note that to avoid deadlocks, the verity work can't be done * on the decompression workqueue. This is because verifying * the data pages can involve reading metadata pages from the * file, and these metadata pages may be compressed. */ INIT_WORK(&dic->verity_work, f2fs_verify_cluster); fsverity_enqueue_verify_work(&dic->verity_work); return; } /* Update and unlock the cluster's pagecache pages. */ for (i = 0; i < dic->cluster_size; i++) { struct page *rpage = dic->rpages[i]; if (!rpage) continue; if (failed) ClearPageUptodate(rpage); else SetPageUptodate(rpage); unlock_page(rpage); } /* * Release the reference to the decompress_io_ctx that was being held * for I/O completion. */ f2fs_put_dic(dic, in_task); } /* * Put a reference to a compressed folio's decompress_io_ctx. * * This is called when the folio is no longer needed and can be freed. */ void f2fs_put_folio_dic(struct folio *folio, bool in_task) { struct decompress_io_ctx *dic = folio->private; f2fs_put_dic(dic, in_task); } /* * check whether cluster blocks are contiguous, and add extent cache entry * only if cluster blocks are logically and physically contiguous. */ unsigned int f2fs_cluster_blocks_are_contiguous(struct dnode_of_data *dn, unsigned int ofs_in_node) { bool compressed = data_blkaddr(dn->inode, dn->node_folio, ofs_in_node) == COMPRESS_ADDR; int i = compressed ? 1 : 0; block_t first_blkaddr = data_blkaddr(dn->inode, dn->node_folio, ofs_in_node + i); for (i += 1; i < F2FS_I(dn->inode)->i_cluster_size; i++) { block_t blkaddr = data_blkaddr(dn->inode, dn->node_folio, ofs_in_node + i); if (!__is_valid_data_blkaddr(blkaddr)) break; if (first_blkaddr + i - (compressed ? 1 : 0) != blkaddr) return 0; } return compressed ? i - 1 : i; } const struct address_space_operations f2fs_compress_aops = { .release_folio = f2fs_release_folio, .invalidate_folio = f2fs_invalidate_folio, .migrate_folio = filemap_migrate_folio, }; struct address_space *COMPRESS_MAPPING(struct f2fs_sb_info *sbi) { return sbi->compress_inode->i_mapping; } void f2fs_invalidate_compress_pages_range(struct f2fs_sb_info *sbi, block_t blkaddr, unsigned int len) { if (!sbi->compress_inode) return; invalidate_mapping_pages(COMPRESS_MAPPING(sbi), blkaddr, blkaddr + len - 1); } static void f2fs_cache_compressed_page(struct f2fs_sb_info *sbi, struct folio *folio, nid_t ino, block_t blkaddr) { struct folio *cfolio; int ret; if (!test_opt(sbi, COMPRESS_CACHE)) return; if (!f2fs_is_valid_blkaddr(sbi, blkaddr, DATA_GENERIC_ENHANCE_READ)) return; if (!f2fs_available_free_memory(sbi, COMPRESS_PAGE)) return; cfolio = filemap_get_folio(COMPRESS_MAPPING(sbi), blkaddr); if (!IS_ERR(cfolio)) { f2fs_folio_put(cfolio, false); return; } cfolio = filemap_alloc_folio(__GFP_NOWARN | __GFP_IO, 0); if (!cfolio) return; ret = filemap_add_folio(COMPRESS_MAPPING(sbi), cfolio, blkaddr, GFP_NOFS); if (ret) { f2fs_folio_put(cfolio, false); return; } folio_set_f2fs_data(cfolio, ino); memcpy(folio_address(cfolio), folio_address(folio), PAGE_SIZE); folio_mark_uptodate(cfolio); f2fs_folio_put(cfolio, true); } bool f2fs_load_compressed_folio(struct f2fs_sb_info *sbi, struct folio *folio, block_t blkaddr) { struct folio *cfolio; bool hitted = false; if (!test_opt(sbi, COMPRESS_CACHE)) return false; cfolio = f2fs_filemap_get_folio(COMPRESS_MAPPING(sbi), blkaddr, FGP_LOCK | FGP_NOWAIT, GFP_NOFS); if (!IS_ERR(cfolio)) { if (folio_test_uptodate(cfolio)) { atomic_inc(&sbi->compress_page_hit); memcpy(folio_address(folio), folio_address(cfolio), folio_size(folio)); hitted = true; } f2fs_folio_put(cfolio, true); } return hitted; } void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi, nid_t ino) { struct address_space *mapping = COMPRESS_MAPPING(sbi); struct folio_batch fbatch; pgoff_t index = 0; pgoff_t end = MAX_BLKADDR(sbi); if (!mapping->nrpages) return; folio_batch_init(&fbatch); do { unsigned int nr, i; nr = filemap_get_folios(mapping, &index, end - 1, &fbatch); if (!nr) break; for (i = 0; i < nr; i++) { struct folio *folio = fbatch.folios[i]; folio_lock(folio); if (folio->mapping != mapping) { folio_unlock(folio); continue; } if (ino != folio_get_f2fs_data(folio)) { folio_unlock(folio); continue; } generic_error_remove_folio(mapping, folio); folio_unlock(folio); } folio_batch_release(&fbatch); cond_resched(); } while (index < end); } int f2fs_init_compress_inode(struct f2fs_sb_info *sbi) { struct inode *inode; if (!test_opt(sbi, COMPRESS_CACHE)) return 0; inode = f2fs_iget(sbi->sb, F2FS_COMPRESS_INO(sbi)); if (IS_ERR(inode)) return PTR_ERR(inode); sbi->compress_inode = inode; sbi->compress_percent = COMPRESS_PERCENT; sbi->compress_watermark = COMPRESS_WATERMARK; atomic_set(&sbi->compress_page_hit, 0); return 0; } void f2fs_destroy_compress_inode(struct f2fs_sb_info *sbi) { if (!sbi->compress_inode) return; iput(sbi->compress_inode); sbi->compress_inode = NULL; } int f2fs_init_page_array_cache(struct f2fs_sb_info *sbi) { dev_t dev = sbi->sb->s_bdev->bd_dev; char slab_name[35]; if (!f2fs_sb_has_compression(sbi)) return 0; sprintf(slab_name, "f2fs_page_array_entry-%u:%u", MAJOR(dev), MINOR(dev)); sbi->page_array_slab_size = sizeof(struct page *) << F2FS_OPTION(sbi).compress_log_size; sbi->page_array_slab = f2fs_kmem_cache_create(slab_name, sbi->page_array_slab_size); return sbi->page_array_slab ? 0 : -ENOMEM; } void f2fs_destroy_page_array_cache(struct f2fs_sb_info *sbi) { kmem_cache_destroy(sbi->page_array_slab); } int __init f2fs_init_compress_cache(void) { cic_entry_slab = f2fs_kmem_cache_create("f2fs_cic_entry", sizeof(struct compress_io_ctx)); if (!cic_entry_slab) return -ENOMEM; dic_entry_slab = f2fs_kmem_cache_create("f2fs_dic_entry", sizeof(struct decompress_io_ctx)); if (!dic_entry_slab) goto free_cic; return 0; free_cic: kmem_cache_destroy(cic_entry_slab); return -ENOMEM; } void f2fs_destroy_compress_cache(void) { kmem_cache_destroy(dic_entry_slab); kmem_cache_destroy(cic_entry_slab); } |
| 70 70 70 70 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 | // SPDX-License-Identifier: GPL-2.0-or-later /* * The ChaCha stream cipher (RFC7539) * * Copyright (C) 2015 Martin Willi */ #include <crypto/algapi.h> // for crypto_xor_cpy #include <crypto/chacha.h> #include <linux/export.h> #include <linux/kernel.h> #include <linux/module.h> void chacha_crypt_generic(struct chacha_state *state, u8 *dst, const u8 *src, unsigned int bytes, int nrounds) { /* aligned to potentially speed up crypto_xor() */ u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long)); while (bytes >= CHACHA_BLOCK_SIZE) { chacha_block_generic(state, stream, nrounds); crypto_xor_cpy(dst, src, stream, CHACHA_BLOCK_SIZE); bytes -= CHACHA_BLOCK_SIZE; dst += CHACHA_BLOCK_SIZE; src += CHACHA_BLOCK_SIZE; } if (bytes) { chacha_block_generic(state, stream, nrounds); crypto_xor_cpy(dst, src, stream, bytes); } } EXPORT_SYMBOL(chacha_crypt_generic); MODULE_DESCRIPTION("ChaCha stream cipher (RFC7539)"); MODULE_LICENSE("GPL"); |
| 1 1 1 2 2 2 2 1 1 1 1 1 1 1 1 2 2 2 1 2 2 2 2 2 2 1 1 2 2 2 2 2 2 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Core registration and callback routines for MTD * drivers and users. * * Copyright © 1999-2010 David Woodhouse <dwmw2@infradead.org> * Copyright © 2006 Red Hat UK Limited */ #include <linux/module.h> #include <linux/kernel.h> #include <linux/ptrace.h> #include <linux/seq_file.h> #include <linux/string.h> #include <linux/timer.h> #include <linux/major.h> #include <linux/fs.h> #include <linux/err.h> #include <linux/ioctl.h> #include <linux/init.h> #include <linux/of.h> #include <linux/proc_fs.h> #include <linux/idr.h> #include <linux/backing-dev.h> #include <linux/gfp.h> #include <linux/random.h> #include <linux/slab.h> #include <linux/reboot.h> #include <linux/leds.h> #include <linux/debugfs.h> #include <linux/nvmem-provider.h> #include <linux/root_dev.h> #include <linux/error-injection.h> #include <linux/mtd/mtd.h> #include <linux/mtd/partitions.h> #include "mtdcore.h" struct backing_dev_info *mtd_bdi; #ifdef CONFIG_PM_SLEEP static int mtd_cls_suspend(struct device *dev) { struct mtd_info *mtd = dev_get_drvdata(dev); return mtd ? mtd_suspend(mtd) : 0; } static int mtd_cls_resume(struct device *dev) { struct mtd_info *mtd = dev_get_drvdata(dev); if (mtd) mtd_resume(mtd); return 0; } static SIMPLE_DEV_PM_OPS(mtd_cls_pm_ops, mtd_cls_suspend, mtd_cls_resume); #define MTD_CLS_PM_OPS (&mtd_cls_pm_ops) #else #define MTD_CLS_PM_OPS NULL #endif static struct class mtd_class = { .name = "mtd", .pm = MTD_CLS_PM_OPS, }; static DEFINE_IDR(mtd_idr); /* These are exported solely for the purpose of mtd_blkdevs.c. You should not use them for _anything_ else */ DEFINE_MUTEX(mtd_table_mutex); EXPORT_SYMBOL_GPL(mtd_table_mutex); struct mtd_info *__mtd_next_device(int i) { return idr_get_next(&mtd_idr, &i); } EXPORT_SYMBOL_GPL(__mtd_next_device); static LIST_HEAD(mtd_notifiers); #define MTD_DEVT(index) MKDEV(MTD_CHAR_MAJOR, (index)*2) /* REVISIT once MTD uses the driver model better, whoever allocates * the mtd_info will probably want to use the release() hook... */ static void mtd_release(struct device *dev) { struct mtd_info *mtd = dev_get_drvdata(dev); dev_t index = MTD_DEVT(mtd->index); idr_remove(&mtd_idr, mtd->index); of_node_put(mtd_get_of_node(mtd)); if (mtd_is_partition(mtd)) release_mtd_partition(mtd); /* remove /dev/mtdXro node */ device_destroy(&mtd_class, index + 1); } static void mtd_device_release(struct kref *kref) { struct mtd_info *mtd = container_of(kref, struct mtd_info, refcnt); bool is_partition = mtd_is_partition(mtd); debugfs_remove_recursive(mtd->dbg.dfs_dir); /* Try to remove the NVMEM provider */ nvmem_unregister(mtd->nvmem); device_unregister(&mtd->dev); /* * Clear dev so mtd can be safely re-registered later if desired. * Should not be done for partition, * as it was already destroyed in device_unregister(). */ if (!is_partition) memset(&mtd->dev, 0, sizeof(mtd->dev)); module_put(THIS_MODULE); } #define MTD_DEVICE_ATTR_RO(name) \ static DEVICE_ATTR(name, 0444, mtd_##name##_show, NULL) #define MTD_DEVICE_ATTR_RW(name) \ static DEVICE_ATTR(name, 0644, mtd_##name##_show, mtd_##name##_store) static ssize_t mtd_type_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); char *type; switch (mtd->type) { case MTD_ABSENT: type = "absent"; break; case MTD_RAM: type = "ram"; break; case MTD_ROM: type = "rom"; break; case MTD_NORFLASH: type = "nor"; break; case MTD_NANDFLASH: type = "nand"; break; case MTD_DATAFLASH: type = "dataflash"; break; case MTD_UBIVOLUME: type = "ubi"; break; case MTD_MLCNANDFLASH: type = "mlc-nand"; break; default: type = "unknown"; } return sysfs_emit(buf, "%s\n", type); } MTD_DEVICE_ATTR_RO(type); static ssize_t mtd_flags_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "0x%lx\n", (unsigned long)mtd->flags); } MTD_DEVICE_ATTR_RO(flags); static ssize_t mtd_size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", (unsigned long long)mtd->size); } MTD_DEVICE_ATTR_RO(size); static ssize_t mtd_erasesize_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "%lu\n", (unsigned long)mtd->erasesize); } MTD_DEVICE_ATTR_RO(erasesize); static ssize_t mtd_writesize_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "%lu\n", (unsigned long)mtd->writesize); } MTD_DEVICE_ATTR_RO(writesize); static ssize_t mtd_subpagesize_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); unsigned int subpagesize = mtd->writesize >> mtd->subpage_sft; return sysfs_emit(buf, "%u\n", subpagesize); } MTD_DEVICE_ATTR_RO(subpagesize); static ssize_t mtd_oobsize_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "%lu\n", (unsigned long)mtd->oobsize); } MTD_DEVICE_ATTR_RO(oobsize); static ssize_t mtd_oobavail_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "%u\n", mtd->oobavail); } MTD_DEVICE_ATTR_RO(oobavail); static ssize_t mtd_numeraseregions_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "%u\n", mtd->numeraseregions); } MTD_DEVICE_ATTR_RO(numeraseregions); static ssize_t mtd_name_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "%s\n", mtd->name); } MTD_DEVICE_ATTR_RO(name); static ssize_t mtd_ecc_strength_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "%u\n", mtd->ecc_strength); } MTD_DEVICE_ATTR_RO(ecc_strength); static ssize_t mtd_bitflip_threshold_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "%u\n", mtd->bitflip_threshold); } static ssize_t mtd_bitflip_threshold_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct mtd_info *mtd = dev_get_drvdata(dev); unsigned int bitflip_threshold; int retval; retval = kstrtouint(buf, 0, &bitflip_threshold); if (retval) return retval; mtd->bitflip_threshold = bitflip_threshold; return count; } MTD_DEVICE_ATTR_RW(bitflip_threshold); static ssize_t mtd_ecc_step_size_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); return sysfs_emit(buf, "%u\n", mtd->ecc_step_size); } MTD_DEVICE_ATTR_RO(ecc_step_size); static ssize_t mtd_corrected_bits_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); struct mtd_ecc_stats *ecc_stats = &mtd->ecc_stats; return sysfs_emit(buf, "%u\n", ecc_stats->corrected); } MTD_DEVICE_ATTR_RO(corrected_bits); /* ecc stats corrected */ static ssize_t mtd_ecc_failures_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); struct mtd_ecc_stats *ecc_stats = &mtd->ecc_stats; return sysfs_emit(buf, "%u\n", ecc_stats->failed); } MTD_DEVICE_ATTR_RO(ecc_failures); /* ecc stats errors */ static ssize_t mtd_bad_blocks_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); struct mtd_ecc_stats *ecc_stats = &mtd->ecc_stats; return sysfs_emit(buf, "%u\n", ecc_stats->badblocks); } MTD_DEVICE_ATTR_RO(bad_blocks); static ssize_t mtd_bbt_blocks_show(struct device *dev, struct device_attribute *attr, char *buf) { struct mtd_info *mtd = dev_get_drvdata(dev); struct mtd_ecc_stats *ecc_stats = &mtd->ecc_stats; return sysfs_emit(buf, "%u\n", ecc_stats->bbtblocks); } MTD_DEVICE_ATTR_RO(bbt_blocks); static struct attribute *mtd_attrs[] = { &dev_attr_type.attr, &dev_attr_flags.attr, &dev_attr_size.attr, &dev_attr_erasesize.attr, &dev_attr_writesize.attr, &dev_attr_subpagesize.attr, &dev_attr_oobsize.attr, &dev_attr_oobavail.attr, &dev_attr_numeraseregions.attr, &dev_attr_name.attr, &dev_attr_ecc_strength.attr, &dev_attr_ecc_step_size.attr, &dev_attr_corrected_bits.attr, &dev_attr_ecc_failures.attr, &dev_attr_bad_blocks.attr, &dev_attr_bbt_blocks.attr, &dev_attr_bitflip_threshold.attr, NULL, }; ATTRIBUTE_GROUPS(mtd); static const struct device_type mtd_devtype = { .name = "mtd", .groups = mtd_groups, .release = mtd_release, }; static bool mtd_expert_analysis_mode; #ifdef CONFIG_DEBUG_FS bool mtd_check_expert_analysis_mode(void) { const char *mtd_expert_analysis_warning = "Bad block checks have been entirely disabled.\n" "This is only reserved for post-mortem forensics and debug purposes.\n" "Never enable this mode if you do not know what you are doing!\n"; return WARN_ONCE(mtd_expert_analysis_mode, mtd_expert_analysis_warning); } EXPORT_SYMBOL_GPL(mtd_check_expert_analysis_mode); #endif static struct dentry *dfs_dir_mtd; static void mtd_debugfs_populate(struct mtd_info *mtd) { struct device *dev = &mtd->dev; if (IS_ERR_OR_NULL(dfs_dir_mtd)) return; mtd->dbg.dfs_dir = debugfs_create_dir(dev_name(dev), dfs_dir_mtd); } #ifndef CONFIG_MMU unsigned mtd_mmap_capabilities(struct mtd_info *mtd) { switch (mtd->type) { case MTD_RAM: return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC | NOMMU_MAP_READ | NOMMU_MAP_WRITE; case MTD_ROM: return NOMMU_MAP_COPY | NOMMU_MAP_DIRECT | NOMMU_MAP_EXEC | NOMMU_MAP_READ; default: return NOMMU_MAP_COPY; } } EXPORT_SYMBOL_GPL(mtd_mmap_capabilities); #endif static int mtd_reboot_notifier(struct notifier_block *n, unsigned long state, void *cmd) { struct mtd_info *mtd; mtd = container_of(n, struct mtd_info, reboot_notifier); mtd->_reboot(mtd); return NOTIFY_DONE; } /** * mtd_wunit_to_pairing_info - get pairing information of a wunit * @mtd: pointer to new MTD device info structure * @wunit: write unit we are interested in * @info: returned pairing information * * Retrieve pairing information associated to the wunit. * This is mainly useful when dealing with MLC/TLC NANDs where pages can be * paired together, and where programming a page may influence the page it is * paired with. * The notion of page is replaced by the term wunit (write-unit) to stay * consistent with the ->writesize field. * * The @wunit argument can be extracted from an absolute offset using * mtd_offset_to_wunit(). @info is filled with the pairing information attached * to @wunit. * * From the pairing info the MTD user can find all the wunits paired with * @wunit using the following loop: * * for (i = 0; i < mtd_pairing_groups(mtd); i++) { * info.pair = i; * mtd_pairing_info_to_wunit(mtd, &info); * ... * } */ int mtd_wunit_to_pairing_info(struct mtd_info *mtd, int wunit, struct mtd_pairing_info *info) { struct mtd_info *master = mtd_get_master(mtd); int npairs = mtd_wunit_per_eb(master) / mtd_pairing_groups(master); if (wunit < 0 || wunit >= npairs) return -EINVAL; if (master->pairing && master->pairing->get_info) return master->pairing->get_info(master, wunit, info); info->group = 0; info->pair = wunit; return 0; } EXPORT_SYMBOL_GPL(mtd_wunit_to_pairing_info); /** * mtd_pairing_info_to_wunit - get wunit from pairing information * @mtd: pointer to new MTD device info structure * @info: pairing information struct * * Returns a positive number representing the wunit associated to the info * struct, or a negative error code. * * This is the reverse of mtd_wunit_to_pairing_info(), and can help one to * iterate over all wunits of a given pair (see mtd_wunit_to_pairing_info() * doc). * * It can also be used to only program the first page of each pair (i.e. * page attached to group 0), which allows one to use an MLC NAND in * software-emulated SLC mode: * * info.group = 0; * npairs = mtd_wunit_per_eb(mtd) / mtd_pairing_groups(mtd); * for (info.pair = 0; info.pair < npairs; info.pair++) { * wunit = mtd_pairing_info_to_wunit(mtd, &info); * mtd_write(mtd, mtd_wunit_to_offset(mtd, blkoffs, wunit), * mtd->writesize, &retlen, buf + (i * mtd->writesize)); * } */ int mtd_pairing_info_to_wunit(struct mtd_info *mtd, const struct mtd_pairing_info *info) { struct mtd_info *master = mtd_get_master(mtd); int ngroups = mtd_pairing_groups(master); int npairs = mtd_wunit_per_eb(master) / ngroups; if (!info || info->pair < 0 || info->pair >= npairs || info->group < 0 || info->group >= ngroups) return -EINVAL; if (master->pairing && master->pairing->get_wunit) return mtd->pairing->get_wunit(master, info); return info->pair; } EXPORT_SYMBOL_GPL(mtd_pairing_info_to_wunit); /** * mtd_pairing_groups - get the number of pairing groups * @mtd: pointer to new MTD device info structure * * Returns the number of pairing groups. * * This number is usually equal to the number of bits exposed by a single * cell, and can be used in conjunction with mtd_pairing_info_to_wunit() * to iterate over all pages of a given pair. */ int mtd_pairing_groups(struct mtd_info *mtd) { struct mtd_info *master = mtd_get_master(mtd); if (!master->pairing || !master->pairing->ngroups) return 1; return master->pairing->ngroups; } EXPORT_SYMBOL_GPL(mtd_pairing_groups); static int mtd_nvmem_reg_read(void *priv, unsigned int offset, void *val, size_t bytes) { struct mtd_info *mtd = priv; size_t retlen; int err; err = mtd_read(mtd, offset, bytes, &retlen, val); if (err && err != -EUCLEAN) return err; return retlen == bytes ? 0 : -EIO; } static int mtd_nvmem_add(struct mtd_info *mtd) { struct device_node *node = mtd_get_of_node(mtd); struct nvmem_config config = {}; config.id = NVMEM_DEVID_NONE; config.dev = &mtd->dev; config.name = dev_name(&mtd->dev); config.owner = THIS_MODULE; config.add_legacy_fixed_of_cells = of_device_is_compatible(node, "nvmem-cells"); config.reg_read = mtd_nvmem_reg_read; config.size = mtd->size; config.word_size = 1; config.stride = 1; config.read_only = true; config.root_only = true; config.ignore_wp = true; config.priv = mtd; mtd->nvmem = nvmem_register(&config); if (IS_ERR(mtd->nvmem)) { /* Just ignore if there is no NVMEM support in the kernel */ if (PTR_ERR(mtd->nvmem) == -EOPNOTSUPP) mtd->nvmem = NULL; else return dev_err_probe(&mtd->dev, PTR_ERR(mtd->nvmem), "Failed to register NVMEM device\n"); } return 0; } static void mtd_check_of_node(struct mtd_info *mtd) { struct device_node *partitions, *parent_dn, *mtd_dn = NULL; const char *pname, *prefix = "partition-"; int plen, mtd_name_len, offset, prefix_len; /* Check if MTD already has a device node */ if (mtd_get_of_node(mtd)) return; if (!mtd_is_partition(mtd)) return; parent_dn = of_node_get(mtd_get_of_node(mtd->parent)); if (!parent_dn) return; if (mtd_is_partition(mtd->parent)) partitions = of_node_get(parent_dn); else partitions = of_get_child_by_name(parent_dn, "partitions"); if (!partitions) goto exit_parent; prefix_len = strlen(prefix); mtd_name_len = strlen(mtd->name); /* Search if a partition is defined with the same name */ for_each_child_of_node(partitions, mtd_dn) { /* Skip partition with no/wrong prefix */ if (!of_node_name_prefix(mtd_dn, prefix)) continue; /* Label have priority. Check that first */ if (!of_property_read_string(mtd_dn, "label", &pname)) { offset = 0; } else { pname = mtd_dn->name; offset = prefix_len; } plen = strlen(pname) - offset; if (plen == mtd_name_len && !strncmp(mtd->name, pname + offset, plen)) { mtd_set_of_node(mtd, mtd_dn); of_node_put(mtd_dn); break; } } of_node_put(partitions); exit_parent: of_node_put(parent_dn); } /** * add_mtd_device - register an MTD device * @mtd: pointer to new MTD device info structure * * Add a device to the list of MTD devices present in the system, and * notify each currently active MTD 'user' of its arrival. Returns * zero on success or non-zero on failure. */ int add_mtd_device(struct mtd_info *mtd) { struct device_node *np = mtd_get_of_node(mtd); struct mtd_info *master = mtd_get_master(mtd); struct mtd_notifier *not; int i, error, ofidx; /* * May occur, for instance, on buggy drivers which call * mtd_device_parse_register() multiple times on the same master MTD, * especially with CONFIG_MTD_PARTITIONED_MASTER=y. */ if (WARN_ONCE(mtd->dev.type, "MTD already registered\n")) return -EEXIST; BUG_ON(mtd->writesize == 0); /* * MTD drivers should implement ->_{write,read}() or * ->_{write,read}_oob(), but not both. */ if (WARN_ON((mtd->_write && mtd->_write_oob) || (mtd->_read && mtd->_read_oob))) return -EINVAL; if (WARN_ON((!mtd->erasesize || !master->_erase) && !(mtd->flags & MTD_NO_ERASE))) return -EINVAL; /* * MTD_SLC_ON_MLC_EMULATION can only be set on partitions, when the * master is an MLC NAND and has a proper pairing scheme defined. * We also reject masters that implement ->_writev() for now, because * NAND controller drivers don't implement this hook, and adding the * SLC -> MLC address/length conversion to this path is useless if we * don't have a user. */ if (mtd->flags & MTD_SLC_ON_MLC_EMULATION && (!mtd_is_partition(mtd) || master->type != MTD_MLCNANDFLASH || !master->pairing || master->_writev)) return -EINVAL; mutex_lock(&mtd_table_mutex); ofidx = -1; if (np) ofidx = of_alias_get_id(np, "mtd"); if (ofidx >= 0) i = idr_alloc(&mtd_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL); else i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL); if (i < 0) { error = i; goto fail_locked; } mtd->index = i; kref_init(&mtd->refcnt); /* default value if not set by driver */ if (mtd->bitflip_threshold == 0) mtd->bitflip_threshold = mtd->ecc_strength; if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) { int ngroups = mtd_pairing_groups(master); mtd->erasesize /= ngroups; mtd->size = (u64)mtd_div_by_eb(mtd->size, master) * mtd->erasesize; } if (is_power_of_2(mtd->erasesize)) mtd->erasesize_shift = ffs(mtd->erasesize) - 1; else mtd->erasesize_shift = 0; if (is_power_of_2(mtd->writesize)) mtd->writesize_shift = ffs(mtd->writesize) - 1; else mtd->writesize_shift = 0; mtd->erasesize_mask = (1 << mtd->erasesize_shift) - 1; mtd->writesize_mask = (1 << mtd->writesize_shift) - 1; /* Some chips always power up locked. Unlock them now */ if ((mtd->flags & MTD_WRITEABLE) && (mtd->flags & MTD_POWERUP_LOCK)) { error = mtd_unlock(mtd, 0, mtd->size); if (error && error != -EOPNOTSUPP) printk(KERN_WARNING "%s: unlock failed, writes may not work\n", mtd->name); /* Ignore unlock failures? */ error = 0; } /* Caller should have set dev.parent to match the * physical device, if appropriate. */ mtd->dev.type = &mtd_devtype; mtd->dev.class = &mtd_class; mtd->dev.devt = MTD_DEVT(i); error = dev_set_name(&mtd->dev, "mtd%d", i); if (error) goto fail_devname; dev_set_drvdata(&mtd->dev, mtd); mtd_check_of_node(mtd); of_node_get(mtd_get_of_node(mtd)); error = device_register(&mtd->dev); if (error) { put_device(&mtd->dev); goto fail_added; } /* Add the nvmem provider */ error = mtd_nvmem_add(mtd); if (error) goto fail_nvmem_add; mtd_debugfs_populate(mtd); device_create(&mtd_class, mtd->dev.parent, MTD_DEVT(i) + 1, NULL, "mtd%dro", i); pr_debug("mtd: Giving out device %d to %s\n", i, mtd->name); /* No need to get a refcount on the module containing the notifier, since we hold the mtd_table_mutex */ list_for_each_entry(not, &mtd_notifiers, list) not->add(mtd); mutex_unlock(&mtd_table_mutex); if (of_property_read_bool(mtd_get_of_node(mtd), "linux,rootfs")) { if (IS_BUILTIN(CONFIG_MTD)) { pr_info("mtd: setting mtd%d (%s) as root device\n", mtd->index, mtd->name); ROOT_DEV = MKDEV(MTD_BLOCK_MAJOR, mtd->index); } else { pr_warn("mtd: can't set mtd%d (%s) as root device - mtd must be builtin\n", mtd->index, mtd->name); } } /* We _know_ we aren't being removed, because our caller is still holding us here. So none of this try_ nonsense, and no bitching about it either. :) */ __module_get(THIS_MODULE); return 0; fail_nvmem_add: device_unregister(&mtd->dev); fail_added: of_node_put(mtd_get_of_node(mtd)); fail_devname: idr_remove(&mtd_idr, i); fail_locked: mutex_unlock(&mtd_table_mutex); return error; } /** * del_mtd_device - unregister an MTD device * @mtd: pointer to MTD device info structure * * Remove a device from the list of MTD devices present in the system, * and notify each currently active MTD 'user' of its departure. * Returns zero on success or 1 on failure, which currently will happen * if the requested device does not appear to be present in the list. */ int del_mtd_device(struct mtd_info *mtd) { int ret; struct mtd_notifier *not; mutex_lock(&mtd_table_mutex); if (idr_find(&mtd_idr, mtd->index) != mtd) { ret = -ENODEV; goto out_error; } /* No need to get a refcount on the module containing the notifier, since we hold the mtd_table_mutex */ list_for_each_entry(not, &mtd_notifiers, list) not->remove(mtd); kref_put(&mtd->refcnt, mtd_device_release); ret = 0; out_error: mutex_unlock(&mtd_table_mutex); return ret; } /* * Set a few defaults based on the parent devices, if not provided by the * driver */ static void mtd_set_dev_defaults(struct mtd_info *mtd) { if (mtd->dev.parent) { if (!mtd->owner && mtd->dev.parent->driver) mtd->owner = mtd->dev.parent->driver->owner; if (!mtd->name) mtd->name = dev_name(mtd->dev.parent); } else { pr_debug("mtd device won't show a device symlink in sysfs\n"); } INIT_LIST_HEAD(&mtd->partitions); mutex_init(&mtd->master.partitions_lock); mutex_init(&mtd->master.chrdev_lock); } static ssize_t mtd_otp_size(struct mtd_info *mtd, bool is_user) { struct otp_info *info; ssize_t size = 0; unsigned int i; size_t retlen; int ret; info = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!info) return -ENOMEM; if (is_user) ret = mtd_get_user_prot_info(mtd, PAGE_SIZE, &retlen, info); else ret = mtd_get_fact_prot_info(mtd, PAGE_SIZE, &retlen, info); if (ret) goto err; for (i = 0; i < retlen / sizeof(*info); i++) size += info[i].length; kfree(info); return size; err: kfree(info); /* ENODATA means there is no OTP region. */ return ret == -ENODATA ? 0 : ret; } static struct nvmem_device *mtd_otp_nvmem_register(struct mtd_info *mtd, const char *compatible, int size, nvmem_reg_read_t reg_read) { struct nvmem_device *nvmem = NULL; struct nvmem_config config = {}; struct device_node *np; /* DT binding is optional */ np = of_get_compatible_child(mtd->dev.of_node, compatible); /* OTP nvmem will be registered on the physical device */ config.dev = mtd->dev.parent; config.name = compatible; config.id = NVMEM_DEVID_AUTO; config.owner = THIS_MODULE; config.add_legacy_fixed_of_cells = !mtd_type_is_nand(mtd); config.type = NVMEM_TYPE_OTP; config.root_only = true; config.ignore_wp = true; config.reg_read = reg_read; config.size = size; config.of_node = np; config.priv = mtd; nvmem = nvmem_register(&config); /* Just ignore if there is no NVMEM support in the kernel */ if (IS_ERR(nvmem) && PTR_ERR(nvmem) == -EOPNOTSUPP) nvmem = NULL; of_node_put(np); return nvmem; } static int mtd_nvmem_user_otp_reg_read(void *priv, unsigned int offset, void *val, size_t bytes) { struct mtd_info *mtd = priv; size_t retlen; int ret; ret = mtd_read_user_prot_reg(mtd, offset, bytes, &retlen, val); if (ret) return ret; return retlen == bytes ? 0 : -EIO; } static int mtd_nvmem_fact_otp_reg_read(void *priv, unsigned int offset, void *val, size_t bytes) { struct mtd_info *mtd = priv; size_t retlen; int ret; ret = mtd_read_fact_prot_reg(mtd, offset, bytes, &retlen, val); if (ret) return ret; return retlen == bytes ? 0 : -EIO; } static int mtd_otp_nvmem_add(struct mtd_info *mtd) { struct device *dev = mtd->dev.parent; struct nvmem_device *nvmem; ssize_t size; int err; if (mtd->_get_user_prot_info && mtd->_read_user_prot_reg) { size = mtd_otp_size(mtd, true); if (size < 0) { err = size; goto err; } if (size > 0) { nvmem = mtd_otp_nvmem_register(mtd, "user-otp", size, mtd_nvmem_user_otp_reg_read); if (IS_ERR(nvmem)) { err = PTR_ERR(nvmem); goto err; } mtd->otp_user_nvmem = nvmem; } } if (mtd->_get_fact_prot_info && mtd->_read_fact_prot_reg) { size = mtd_otp_size(mtd, false); if (size < 0) { err = size; goto err; } if (size > 0) { /* * The factory OTP contains thing such as a unique serial * number and is small, so let's read it out and put it * into the entropy pool. */ void *otp; otp = kmalloc(size, GFP_KERNEL); if (!otp) { err = -ENOMEM; goto err; } err = mtd_nvmem_fact_otp_reg_read(mtd, 0, otp, size); if (err < 0) { kfree(otp); goto err; } add_device_randomness(otp, err); kfree(otp); nvmem = mtd_otp_nvmem_register(mtd, "factory-otp", size, mtd_nvmem_fact_otp_reg_read); if (IS_ERR(nvmem)) { err = PTR_ERR(nvmem); goto err; } mtd->otp_factory_nvmem = nvmem; } } return 0; err: nvmem_unregister(mtd->otp_user_nvmem); /* Don't report error if OTP is not supported. */ if (err == -EOPNOTSUPP) return 0; return dev_err_probe(dev, err, "Failed to register OTP NVMEM device\n"); } /** * mtd_device_parse_register - parse partitions and register an MTD device. * * @mtd: the MTD device to register * @types: the list of MTD partition probes to try, see * 'parse_mtd_partitions()' for more information * @parser_data: MTD partition parser-specific data * @parts: fallback partition information to register, if parsing fails; * only valid if %nr_parts > %0 * @nr_parts: the number of partitions in parts, if zero then the full * MTD device is registered if no partition info is found * * This function aggregates MTD partitions parsing (done by * 'parse_mtd_partitions()') and MTD device and partitions registering. It * basically follows the most common pattern found in many MTD drivers: * * * If the MTD_PARTITIONED_MASTER option is set, then the device as a whole is * registered first. * * Then It tries to probe partitions on MTD device @mtd using parsers * specified in @types (if @types is %NULL, then the default list of parsers * is used, see 'parse_mtd_partitions()' for more information). If none are * found this functions tries to fallback to information specified in * @parts/@nr_parts. * * If no partitions were found this function just registers the MTD device * @mtd and exits. * * Returns zero in case of success and a negative error code in case of failure. */ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types, struct mtd_part_parser_data *parser_data, const struct mtd_partition *parts, int nr_parts) { int ret, err; mtd_set_dev_defaults(mtd); ret = mtd_otp_nvmem_add(mtd); if (ret) goto out; if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) { ret = add_mtd_device(mtd); if (ret) goto out; } /* Prefer parsed partitions over driver-provided fallback */ ret = parse_mtd_partitions(mtd, types, parser_data); if (ret == -EPROBE_DEFER) goto out; if (ret > 0) ret = 0; else if (nr_parts) ret = add_mtd_partitions(mtd, parts, nr_parts); else if (!device_is_registered(&mtd->dev)) ret = add_mtd_device(mtd); else ret = 0; if (ret) goto out; /* * FIXME: some drivers unfortunately call this function more than once. * So we have to check if we've already assigned the reboot notifier. * * Generally, we can make multiple calls work for most cases, but it * does cause problems with parse_mtd_partitions() above (e.g., * cmdlineparts will register partitions more than once). */ WARN_ONCE(mtd->_reboot && mtd->reboot_notifier.notifier_call, "MTD already registered\n"); if (mtd->_reboot && !mtd->reboot_notifier.notifier_call) { mtd->reboot_notifier.notifier_call = mtd_reboot_notifier; register_reboot_notifier(&mtd->reboot_notifier); } out: if (ret) { nvmem_unregister(mtd->otp_user_nvmem); nvmem_unregister(mtd->otp_factory_nvmem); } if (ret && device_is_registered(&mtd->dev)) { err = del_mtd_device(mtd); if (err) pr_err("Error when deleting MTD device (%d)\n", err); } return ret; } EXPORT_SYMBOL_GPL(mtd_device_parse_register); /** * mtd_device_unregister - unregister an existing MTD device. * * @master: the MTD device to unregister. This will unregister both the master * and any partitions if registered. */ int mtd_device_unregister(struct mtd_info *master) { int err; if (master->_reboot) { unregister_reboot_notifier(&master->reboot_notifier); memset(&master->reboot_notifier, 0, sizeof(master->reboot_notifier)); } nvmem_unregister(master->otp_user_nvmem); nvmem_unregister(master->otp_factory_nvmem); err = del_mtd_partitions(master); if (err) return err; if (!device_is_registered(&master->dev)) return 0; return del_mtd_device(master); } EXPORT_SYMBOL_GPL(mtd_device_unregister); /** * register_mtd_user - register a 'user' of MTD devices. * @new: pointer to notifier info structure * * Registers a pair of callbacks function to be called upon addition * or removal of MTD devices. Causes the 'add' callback to be immediately * invoked for each MTD device currently present in the system. */ void register_mtd_user (struct mtd_notifier *new) { struct mtd_info *mtd; mutex_lock(&mtd_table_mutex); list_add(&new->list, &mtd_notifiers); __module_get(THIS_MODULE); mtd_for_each_device(mtd) new->add(mtd); mutex_unlock(&mtd_table_mutex); } EXPORT_SYMBOL_GPL(register_mtd_user); /** * unregister_mtd_user - unregister a 'user' of MTD devices. * @old: pointer to notifier info structure * * Removes a callback function pair from the list of 'users' to be * notified upon addition or removal of MTD devices. Causes the * 'remove' callback to be immediately invoked for each MTD device * currently present in the system. */ int unregister_mtd_user (struct mtd_notifier *old) { struct mtd_info *mtd; mutex_lock(&mtd_table_mutex); module_put(THIS_MODULE); mtd_for_each_device(mtd) old->remove(mtd); list_del(&old->list); mutex_unlock(&mtd_table_mutex); return 0; } EXPORT_SYMBOL_GPL(unregister_mtd_user); /** * get_mtd_device - obtain a validated handle for an MTD device * @mtd: last known address of the required MTD device * @num: internal device number of the required MTD device * * Given a number and NULL address, return the num'th entry in the device * table, if any. Given an address and num == -1, search the device table * for a device with that address and return if it's still present. Given * both, return the num'th driver only if its address matches. Return * error code if not. */ struct mtd_info *get_mtd_device(struct mtd_info *mtd, int num) { struct mtd_info *ret = NULL, *other; int err = -ENODEV; mutex_lock(&mtd_table_mutex); if (num == -1) { mtd_for_each_device(other) { if (other == mtd) { ret = mtd; break; } } } else if (num >= 0) { ret = idr_find(&mtd_idr, num); if (mtd && mtd != ret) ret = NULL; } if (!ret) { ret = ERR_PTR(err); goto out; } err = __get_mtd_device(ret); if (err) ret = ERR_PTR(err); out: mutex_unlock(&mtd_table_mutex); return ret; } EXPORT_SYMBOL_GPL(get_mtd_device); int __get_mtd_device(struct mtd_info *mtd) { struct mtd_info *master = mtd_get_master(mtd); int err; if (master->_get_device) { err = master->_get_device(mtd); if (err) return err; } if (!try_module_get(master->owner)) { if (master->_put_device) master->_put_device(master); return -ENODEV; } while (mtd) { if (mtd != master) kref_get(&mtd->refcnt); mtd = mtd->parent; } if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) kref_get(&master->refcnt); return 0; } EXPORT_SYMBOL_GPL(__get_mtd_device); /** * of_get_mtd_device_by_node - obtain an MTD device associated with a given node * * @np: device tree node */ struct mtd_info *of_get_mtd_device_by_node(struct device_node *np) { struct mtd_info *mtd = NULL; struct mtd_info *tmp; int err; mutex_lock(&mtd_table_mutex); err = -EPROBE_DEFER; mtd_for_each_device(tmp) { if (mtd_get_of_node(tmp) == np) { mtd = tmp; err = __get_mtd_device(mtd); break; } } mutex_unlock(&mtd_table_mutex); return err ? ERR_PTR(err) : mtd; } EXPORT_SYMBOL_GPL(of_get_mtd_device_by_node); /** * get_mtd_device_nm - obtain a validated handle for an MTD device by * device name * @name: MTD device name to open * * This function returns MTD device description structure in case of * success and an error code in case of failure. */ struct mtd_info *get_mtd_device_nm(const char *name) { int err = -ENODEV; struct mtd_info *mtd = NULL, *other; mutex_lock(&mtd_table_mutex); mtd_for_each_device(other) { if (!strcmp(name, other->name)) { mtd = other; break; } } if (!mtd) goto out_unlock; err = __get_mtd_device(mtd); if (err) goto out_unlock; mutex_unlock(&mtd_table_mutex); return mtd; out_unlock: mutex_unlock(&mtd_table_mutex); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(get_mtd_device_nm); void put_mtd_device(struct mtd_info *mtd) { mutex_lock(&mtd_table_mutex); __put_mtd_device(mtd); mutex_unlock(&mtd_table_mutex); } EXPORT_SYMBOL_GPL(put_mtd_device); void __put_mtd_device(struct mtd_info *mtd) { struct mtd_info *master = mtd_get_master(mtd); while (mtd) { /* kref_put() can relese mtd, so keep a reference mtd->parent */ struct mtd_info *parent = mtd->parent; if (mtd != master) kref_put(&mtd->refcnt, mtd_device_release); mtd = parent; } if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) kref_put(&master->refcnt, mtd_device_release); module_put(master->owner); /* must be the last as master can be freed in the _put_device */ if (master->_put_device) master->_put_device(master); } EXPORT_SYMBOL_GPL(__put_mtd_device); /* * Erase is an synchronous operation. Device drivers are epected to return a * negative error code if the operation failed and update instr->fail_addr * to point the portion that was not properly erased. */ int mtd_erase(struct mtd_info *mtd, struct erase_info *instr) { struct mtd_info *master = mtd_get_master(mtd); u64 mst_ofs = mtd_get_master_ofs(mtd, 0); struct erase_info adjinstr; int ret; instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN; adjinstr = *instr; if (!mtd->erasesize || !master->_erase) return -ENOTSUPP; if (instr->addr >= mtd->size || instr->len > mtd->size - instr->addr) return -EINVAL; if (!(mtd->flags & MTD_WRITEABLE)) return -EROFS; if (!instr->len) return 0; ledtrig_mtd_activity(); if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) { adjinstr.addr = (loff_t)mtd_div_by_eb(instr->addr, mtd) * master->erasesize; adjinstr.len = ((u64)mtd_div_by_eb(instr->addr + instr->len, mtd) * master->erasesize) - adjinstr.addr; } adjinstr.addr += mst_ofs; ret = master->_erase(master, &adjinstr); if (adjinstr.fail_addr != MTD_FAIL_ADDR_UNKNOWN) { instr->fail_addr = adjinstr.fail_addr - mst_ofs; if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) { instr->fail_addr = mtd_div_by_eb(instr->fail_addr, master); instr->fail_addr *= mtd->erasesize; } } return ret; } EXPORT_SYMBOL_GPL(mtd_erase); ALLOW_ERROR_INJECTION(mtd_erase, ERRNO); /* * This stuff for eXecute-In-Place. phys is optional and may be set to NULL. */ int mtd_point(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, void **virt, resource_size_t *phys) { struct mtd_info *master = mtd_get_master(mtd); *retlen = 0; *virt = NULL; if (phys) *phys = 0; if (!master->_point) return -EOPNOTSUPP; if (from < 0 || from >= mtd->size || len > mtd->size - from) return -EINVAL; if (!len) return 0; from = mtd_get_master_ofs(mtd, from); return master->_point(master, from, len, retlen, virt, phys); } EXPORT_SYMBOL_GPL(mtd_point); /* We probably shouldn't allow XIP if the unpoint isn't a NULL */ int mtd_unpoint(struct mtd_info *mtd, loff_t from, size_t len) { struct mtd_info *master = mtd_get_master(mtd); if (!master->_unpoint) return -EOPNOTSUPP; if (from < 0 || from >= mtd->size || len > mtd->size - from) return -EINVAL; if (!len) return 0; return master->_unpoint(master, mtd_get_master_ofs(mtd, from), len); } EXPORT_SYMBOL_GPL(mtd_unpoint); /* * Allow NOMMU mmap() to directly map the device (if not NULL) * - return the address to which the offset maps * - return -ENOSYS to indicate refusal to do the mapping */ unsigned long mtd_get_unmapped_area(struct mtd_info *mtd, unsigned long len, unsigned long offset, unsigned long flags) { size_t retlen; void *virt; int ret; ret = mtd_point(mtd, offset, len, &retlen, &virt, NULL); if (ret) return ret; if (retlen != len) { mtd_unpoint(mtd, offset, retlen); return -ENOSYS; } return (unsigned long)virt; } EXPORT_SYMBOL_GPL(mtd_get_unmapped_area); static void mtd_update_ecc_stats(struct mtd_info *mtd, struct mtd_info *master, const struct mtd_ecc_stats *old_stats) { struct mtd_ecc_stats diff; if (master == mtd) return; diff = master->ecc_stats; diff.failed -= old_stats->failed; diff.corrected -= old_stats->corrected; while (mtd->parent) { mtd->ecc_stats.failed += diff.failed; mtd->ecc_stats.corrected += diff.corrected; mtd = mtd->parent; } } int mtd_read(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct mtd_oob_ops ops = { .len = len, .datbuf = buf, }; int ret; ret = mtd_read_oob(mtd, from, &ops); *retlen = ops.retlen; WARN_ON_ONCE(*retlen != len && mtd_is_bitflip_or_eccerr(ret)); return ret; } EXPORT_SYMBOL_GPL(mtd_read); ALLOW_ERROR_INJECTION(mtd_read, ERRNO); int mtd_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf) { struct mtd_oob_ops ops = { .len = len, .datbuf = (u8 *)buf, }; int ret; ret = mtd_write_oob(mtd, to, &ops); *retlen = ops.retlen; return ret; } EXPORT_SYMBOL_GPL(mtd_write); ALLOW_ERROR_INJECTION(mtd_write, ERRNO); /* * In blackbox flight recorder like scenarios we want to make successful writes * in interrupt context. panic_write() is only intended to be called when its * known the kernel is about to panic and we need the write to succeed. Since * the kernel is not going to be running for much longer, this function can * break locks and delay to ensure the write succeeds (but not sleep). */ int mtd_panic_write(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf) { struct mtd_info *master = mtd_get_master(mtd); *retlen = 0; if (!master->_panic_write) return -EOPNOTSUPP; if (to < 0 || to >= mtd->size || len > mtd->size - to) return -EINVAL; if (!(mtd->flags & MTD_WRITEABLE)) return -EROFS; if (!len) return 0; if (!master->oops_panic_write) master->oops_panic_write = true; return master->_panic_write(master, mtd_get_master_ofs(mtd, to), len, retlen, buf); } EXPORT_SYMBOL_GPL(mtd_panic_write); static int mtd_check_oob_ops(struct mtd_info *mtd, loff_t offs, struct mtd_oob_ops *ops) { /* * Some users are setting ->datbuf or ->oobbuf to NULL, but are leaving * ->len or ->ooblen uninitialized. Force ->len and ->ooblen to 0 in * this case. */ if (!ops->datbuf) ops->len = 0; if (!ops->oobbuf) ops->ooblen = 0; if (offs < 0 || offs + ops->len > mtd->size) return -EINVAL; if (ops->ooblen) { size_t maxooblen; if (ops->ooboffs >= mtd_oobavail(mtd, ops)) return -EINVAL; maxooblen = ((size_t)(mtd_div_by_ws(mtd->size, mtd) - mtd_div_by_ws(offs, mtd)) * mtd_oobavail(mtd, ops)) - ops->ooboffs; if (ops->ooblen > maxooblen) return -EINVAL; } return 0; } static int mtd_read_oob_std(struct mtd_info *mtd, loff_t from, struct mtd_oob_ops *ops) { struct mtd_info *master = mtd_get_master(mtd); int ret; from = mtd_get_master_ofs(mtd, from); if (master->_read_oob) ret = master->_read_oob(master, from, ops); else ret = master->_read(master, from, ops->len, &ops->retlen, ops->datbuf); return ret; } static int mtd_write_oob_std(struct mtd_info *mtd, loff_t to, struct mtd_oob_ops *ops) { struct mtd_info *master = mtd_get_master(mtd); int ret; to = mtd_get_master_ofs(mtd, to); if (master->_write_oob) ret = master->_write_oob(master, to, ops); else ret = master->_write(master, to, ops->len, &ops->retlen, ops->datbuf); return ret; } static int mtd_io_emulated_slc(struct mtd_info *mtd, loff_t start, bool read, struct mtd_oob_ops *ops) { struct mtd_info *master = mtd_get_master(mtd); int ngroups = mtd_pairing_groups(master); int npairs = mtd_wunit_per_eb(master) / ngroups; struct mtd_oob_ops adjops = *ops; unsigned int wunit, oobavail; struct mtd_pairing_info info; int max_bitflips = 0; u32 ebofs, pageofs; loff_t base, pos; ebofs = mtd_mod_by_eb(start, mtd); base = (loff_t)mtd_div_by_eb(start, mtd) * master->erasesize; info.group = 0; info.pair = mtd_div_by_ws(ebofs, mtd); pageofs = mtd_mod_by_ws(ebofs, mtd); oobavail = mtd_oobavail(mtd, ops); while (ops->retlen < ops->len || ops->oobretlen < ops->ooblen) { int ret; if (info.pair >= npairs) { info.pair = 0; base += master->erasesize; } wunit = mtd_pairing_info_to_wunit(master, &info); pos = mtd_wunit_to_offset(mtd, base, wunit); adjops.len = ops->len - ops->retlen; if (adjops.len > mtd->writesize - pageofs) adjops.len = mtd->writesize - pageofs; adjops.ooblen = ops->ooblen - ops->oobretlen; if (adjops.ooblen > oobavail - adjops.ooboffs) adjops.ooblen = oobavail - adjops.ooboffs; if (read) { ret = mtd_read_oob_std(mtd, pos + pageofs, &adjops); if (ret > 0) max_bitflips = max(max_bitflips, ret); } else { ret = mtd_write_oob_std(mtd, pos + pageofs, &adjops); } if (ret < 0) return ret; max_bitflips = max(max_bitflips, ret); ops->retlen += adjops.retlen; ops->oobretlen += adjops.oobretlen; adjops.datbuf += adjops.retlen; adjops.oobbuf += adjops.oobretlen; adjops.ooboffs = 0; pageofs = 0; info.pair++; } return max_bitflips; } int mtd_read_oob(struct mtd_info *mtd, loff_t from, struct mtd_oob_ops *ops) { struct mtd_info *master = mtd_get_master(mtd); struct mtd_ecc_stats old_stats = master->ecc_stats; int ret_code; ops->retlen = ops->oobretlen = 0; ret_code = mtd_check_oob_ops(mtd, from, ops); if (ret_code) return ret_code; ledtrig_mtd_activity(); /* Check the validity of a potential fallback on mtd->_read */ if (!master->_read_oob && (!master->_read || ops->oobbuf)) return -EOPNOTSUPP; if (ops->stats) memset(ops->stats, 0, sizeof(*ops->stats)); if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) ret_code = mtd_io_emulated_slc(mtd, from, true, ops); else ret_code = mtd_read_oob_std(mtd, from, ops); mtd_update_ecc_stats(mtd, master, &old_stats); /* * In cases where ops->datbuf != NULL, mtd->_read_oob() has semantics * similar to mtd->_read(), returning a non-negative integer * representing max bitflips. In other cases, mtd->_read_oob() may * return -EUCLEAN. In all cases, perform similar logic to mtd_read(). */ if (unlikely(ret_code < 0)) return ret_code; if (mtd->ecc_strength == 0) return 0; /* device lacks ecc */ if (ops->stats) ops->stats->max_bitflips = ret_code; return ret_code >= mtd->bitflip_threshold ? -EUCLEAN : 0; } EXPORT_SYMBOL_GPL(mtd_read_oob); int mtd_write_oob(struct mtd_info *mtd, loff_t to, struct mtd_oob_ops *ops) { struct mtd_info *master = mtd_get_master(mtd); int ret; ops->retlen = ops->oobretlen = 0; if (!(mtd->flags & MTD_WRITEABLE)) return -EROFS; ret = mtd_check_oob_ops(mtd, to, ops); if (ret) return ret; ledtrig_mtd_activity(); /* Check the validity of a potential fallback on mtd->_write */ if (!master->_write_oob && (!master->_write || ops->oobbuf)) return -EOPNOTSUPP; if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) return mtd_io_emulated_slc(mtd, to, false, ops); return mtd_write_oob_std(mtd, to, ops); } EXPORT_SYMBOL_GPL(mtd_write_oob); /** * mtd_ooblayout_ecc - Get the OOB region definition of a specific ECC section * @mtd: MTD device structure * @section: ECC section. Depending on the layout you may have all the ECC * bytes stored in a single contiguous section, or one section * per ECC chunk (and sometime several sections for a single ECC * ECC chunk) * @oobecc: OOB region struct filled with the appropriate ECC position * information * * This function returns ECC section information in the OOB area. If you want * to get all the ECC bytes information, then you should call * mtd_ooblayout_ecc(mtd, section++, oobecc) until it returns -ERANGE. * * Returns zero on success, a negative error code otherwise. */ int mtd_ooblayout_ecc(struct mtd_info *mtd, int section, struct mtd_oob_region *oobecc) { struct mtd_info *master = mtd_get_master(mtd); memset(oobecc, 0, sizeof(*oobecc)); if (!master || section < 0) return -EINVAL; if (!master->ooblayout || !master->ooblayout->ecc) return -ENOTSUPP; return master->ooblayout->ecc(master, section, oobecc); } EXPORT_SYMBOL_GPL(mtd_ooblayout_ecc); /** * mtd_ooblayout_free - Get the OOB region definition of a specific free * section * @mtd: MTD device structure * @section: Free section you are interested in. Depending on the layout * you may have all the free bytes stored in a single contiguous * section, or one section per ECC chunk plus an extra section * for the remaining bytes (or other funky layout). * @oobfree: OOB region struct filled with the appropriate free position * information * * This function returns free bytes position in the OOB area. If you want * to get all the free bytes information, then you should call * mtd_ooblayout_free(mtd, section++, oobfree) until it returns -ERANGE. * * Returns zero on success, a negative error code otherwise. */ int mtd_ooblayout_free(struct mtd_info *mtd, int section, struct mtd_oob_region *oobfree) { struct mtd_info *master = mtd_get_master(mtd); memset(oobfree, 0, sizeof(*oobfree)); if (!master || section < 0) return -EINVAL; if (!master->ooblayout || !master->ooblayout->free) return -ENOTSUPP; return master->ooblayout->free(master, section, oobfree); } EXPORT_SYMBOL_GPL(mtd_ooblayout_free); /** * mtd_ooblayout_find_region - Find the region attached to a specific byte * @mtd: mtd info structure * @byte: the byte we are searching for * @sectionp: pointer where the section id will be stored * @oobregion: used to retrieve the ECC position * @iter: iterator function. Should be either mtd_ooblayout_free or * mtd_ooblayout_ecc depending on the region type you're searching for * * This function returns the section id and oobregion information of a * specific byte. For example, say you want to know where the 4th ECC byte is * stored, you'll use: * * mtd_ooblayout_find_region(mtd, 3, §ion, &oobregion, mtd_ooblayout_ecc); * * Returns zero on success, a negative error code otherwise. */ static int mtd_ooblayout_find_region(struct mtd_info *mtd, int byte, int *sectionp, struct mtd_oob_region *oobregion, int (*iter)(struct mtd_info *, int section, struct mtd_oob_region *oobregion)) { int pos = 0, ret, section = 0; memset(oobregion, 0, sizeof(*oobregion)); while (1) { ret = iter(mtd, section, oobregion); if (ret) return ret; if (pos + oobregion->length > byte) break; pos += oobregion->length; section++; } /* * Adjust region info to make it start at the beginning at the * 'start' ECC byte. */ oobregion->offset += byte - pos; oobregion->length -= byte - pos; *sectionp = section; return 0; } /** * mtd_ooblayout_find_eccregion - Find the ECC region attached to a specific * ECC byte * @mtd: mtd info structure * @eccbyte: the byte we are searching for * @section: pointer where the section id will be stored * @oobregion: OOB region information * * Works like mtd_ooblayout_find_region() except it searches for a specific ECC * byte. * * Returns zero on success, a negative error code otherwise. */ int mtd_ooblayout_find_eccregion(struct mtd_info *mtd, int eccbyte, int *section, struct mtd_oob_region *oobregion) { return mtd_ooblayout_find_region(mtd, eccbyte, section, oobregion, mtd_ooblayout_ecc); } EXPORT_SYMBOL_GPL(mtd_ooblayout_find_eccregion); /** * mtd_ooblayout_get_bytes - Extract OOB bytes from the oob buffer * @mtd: mtd info structure * @buf: destination buffer to store OOB bytes * @oobbuf: OOB buffer * @start: first byte to retrieve * @nbytes: number of bytes to retrieve * @iter: section iterator * * Extract bytes attached to a specific category (ECC or free) * from the OOB buffer and copy them into buf. * * Returns zero on success, a negative error code otherwise. */ static int mtd_ooblayout_get_bytes(struct mtd_info *mtd, u8 *buf, const u8 *oobbuf, int start, int nbytes, int (*iter)(struct mtd_info *, int section, struct mtd_oob_region *oobregion)) { struct mtd_oob_region oobregion; int section, ret; ret = mtd_ooblayout_find_region(mtd, start, §ion, &oobregion, iter); while (!ret) { int cnt; cnt = min_t(int, nbytes, oobregion.length); memcpy(buf, oobbuf + oobregion.offset, cnt); buf += cnt; nbytes -= cnt; if (!nbytes) break; ret = iter(mtd, ++section, &oobregion); } return ret; } /** * mtd_ooblayout_set_bytes - put OOB bytes into the oob buffer * @mtd: mtd info structure * @buf: source buffer to get OOB bytes from * @oobbuf: OOB buffer * @start: first OOB byte to set * @nbytes: number of OOB bytes to set * @iter: section iterator * * Fill the OOB buffer with data provided in buf. The category (ECC or free) * is selected by passing the appropriate iterator. * * Returns zero on success, a negative error code otherwise. */ static int mtd_ooblayout_set_bytes(struct mtd_info *mtd, const u8 *buf, u8 *oobbuf, int start, int nbytes, int (*iter)(struct mtd_info *, int section, struct mtd_oob_region *oobregion)) { struct mtd_oob_region oobregion; int section, ret; ret = mtd_ooblayout_find_region(mtd, start, §ion, &oobregion, iter); while (!ret) { int cnt; cnt = min_t(int, nbytes, oobregion.length); memcpy(oobbuf + oobregion.offset, buf, cnt); buf += cnt; nbytes -= cnt; if (!nbytes) break; ret = iter(mtd, ++section, &oobregion); } return ret; } /** * mtd_ooblayout_count_bytes - count the number of bytes in a OOB category * @mtd: mtd info structure * @iter: category iterator * * Count the number of bytes in a given category. * * Returns a positive value on success, a negative error code otherwise. */ static int mtd_ooblayout_count_bytes(struct mtd_info *mtd, int (*iter)(struct mtd_info *, int section, struct mtd_oob_region *oobregion)) { struct mtd_oob_region oobregion; int section = 0, ret, nbytes = 0; while (1) { ret = iter(mtd, section++, &oobregion); if (ret) { if (ret == -ERANGE) ret = nbytes; break; } nbytes += oobregion.length; } return ret; } /** * mtd_ooblayout_get_eccbytes - extract ECC bytes from the oob buffer * @mtd: mtd info structure * @eccbuf: destination buffer to store ECC bytes * @oobbuf: OOB buffer * @start: first ECC byte to retrieve * @nbytes: number of ECC bytes to retrieve * * Works like mtd_ooblayout_get_bytes(), except it acts on ECC bytes. * * Returns zero on success, a negative error code otherwise. */ int mtd_ooblayout_get_eccbytes(struct mtd_info *mtd, u8 *eccbuf, const u8 *oobbuf, int start, int nbytes) { return mtd_ooblayout_get_bytes(mtd, eccbuf, oobbuf, start, nbytes, mtd_ooblayout_ecc); } EXPORT_SYMBOL_GPL(mtd_ooblayout_get_eccbytes); /** * mtd_ooblayout_set_eccbytes - set ECC bytes into the oob buffer * @mtd: mtd info structure * @eccbuf: source buffer to get ECC bytes from * @oobbuf: OOB buffer * @start: first ECC byte to set * @nbytes: number of ECC bytes to set * * Works like mtd_ooblayout_set_bytes(), except it acts on ECC bytes. * * Returns zero on success, a negative error code otherwise. */ int mtd_ooblayout_set_eccbytes(struct mtd_info *mtd, const u8 *eccbuf, u8 *oobbuf, int start, int nbytes) { return mtd_ooblayout_set_bytes(mtd, eccbuf, oobbuf, start, nbytes, mtd_ooblayout_ecc); } EXPORT_SYMBOL_GPL(mtd_ooblayout_set_eccbytes); /** * mtd_ooblayout_get_databytes - extract data bytes from the oob buffer * @mtd: mtd info structure * @databuf: destination buffer to store ECC bytes * @oobbuf: OOB buffer * @start: first ECC byte to retrieve * @nbytes: number of ECC bytes to retrieve * * Works like mtd_ooblayout_get_bytes(), except it acts on free bytes. * * Returns zero on success, a negative error code otherwise. */ int mtd_ooblayout_get_databytes(struct mtd_info *mtd, u8 *databuf, const u8 *oobbuf, int start, int nbytes) { return mtd_ooblayout_get_bytes(mtd, databuf, oobbuf, start, nbytes, mtd_ooblayout_free); } EXPORT_SYMBOL_GPL(mtd_ooblayout_get_databytes); /** * mtd_ooblayout_set_databytes - set data bytes into the oob buffer * @mtd: mtd info structure * @databuf: source buffer to get data bytes from * @oobbuf: OOB buffer * @start: first ECC byte to set * @nbytes: number of ECC bytes to set * * Works like mtd_ooblayout_set_bytes(), except it acts on free bytes. * * Returns zero on success, a negative error code otherwise. */ int mtd_ooblayout_set_databytes(struct mtd_info *mtd, const u8 *databuf, u8 *oobbuf, int start, int nbytes) { return mtd_ooblayout_set_bytes(mtd, databuf, oobbuf, start, nbytes, mtd_ooblayout_free); } EXPORT_SYMBOL_GPL(mtd_ooblayout_set_databytes); /** * mtd_ooblayout_count_freebytes - count the number of free bytes in OOB * @mtd: mtd info structure * * Works like mtd_ooblayout_count_bytes(), except it count free bytes. * * Returns zero on success, a negative error code otherwise. */ int mtd_ooblayout_count_freebytes(struct mtd_info *mtd) { return mtd_ooblayout_count_bytes(mtd, mtd_ooblayout_free); } EXPORT_SYMBOL_GPL(mtd_ooblayout_count_freebytes); /** * mtd_ooblayout_count_eccbytes - count the number of ECC bytes in OOB * @mtd: mtd info structure * * Works like mtd_ooblayout_count_bytes(), except it count ECC bytes. * * Returns zero on success, a negative error code otherwise. */ int mtd_ooblayout_count_eccbytes(struct mtd_info *mtd) { return mtd_ooblayout_count_bytes(mtd, mtd_ooblayout_ecc); } EXPORT_SYMBOL_GPL(mtd_ooblayout_count_eccbytes); /* * Method to access the protection register area, present in some flash * devices. The user data is one time programmable but the factory data is read * only. */ int mtd_get_fact_prot_info(struct mtd_info *mtd, size_t len, size_t *retlen, struct otp_info *buf) { struct mtd_info *master = mtd_get_master(mtd); if (!master->_get_fact_prot_info) return -EOPNOTSUPP; if (!len) return 0; return master->_get_fact_prot_info(master, len, retlen, buf); } EXPORT_SYMBOL_GPL(mtd_get_fact_prot_info); int mtd_read_fact_prot_reg(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct mtd_info *master = mtd_get_master(mtd); *retlen = 0; if (!master->_read_fact_prot_reg) return -EOPNOTSUPP; if (!len) return 0; return master->_read_fact_prot_reg(master, from, len, retlen, buf); } EXPORT_SYMBOL_GPL(mtd_read_fact_prot_reg); int mtd_get_user_prot_info(struct mtd_info *mtd, size_t len, size_t *retlen, struct otp_info *buf) { struct mtd_info *master = mtd_get_master(mtd); if (!master->_get_user_prot_info) return -EOPNOTSUPP; if (!len) return 0; return master->_get_user_prot_info(master, len, retlen, buf); } EXPORT_SYMBOL_GPL(mtd_get_user_prot_info); int mtd_read_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf) { struct mtd_info *master = mtd_get_master(mtd); *retlen = 0; if (!master->_read_user_prot_reg) return -EOPNOTSUPP; if (!len) return 0; return master->_read_user_prot_reg(master, from, len, retlen, buf); } EXPORT_SYMBOL_GPL(mtd_read_user_prot_reg); int mtd_write_user_prot_reg(struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf) { struct mtd_info *master = mtd_get_master(mtd); int ret; *retlen = 0; if (!master->_write_user_prot_reg) return -EOPNOTSUPP; if (!len) return 0; ret = master->_write_user_prot_reg(master, to, len, retlen, buf); if (ret) return ret; /* * If no data could be written at all, we are out of memory and * must return -ENOSPC. */ return (*retlen) ? 0 : -ENOSPC; } EXPORT_SYMBOL_GPL(mtd_write_user_prot_reg); int mtd_lock_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len) { struct mtd_info *master = mtd_get_master(mtd); if (!master->_lock_user_prot_reg) return -EOPNOTSUPP; if (!len) return 0; return master->_lock_user_prot_reg(master, from, len); } EXPORT_SYMBOL_GPL(mtd_lock_user_prot_reg); int mtd_erase_user_prot_reg(struct mtd_info *mtd, loff_t from, size_t len) { struct mtd_info *master = mtd_get_master(mtd); if (!master->_erase_user_prot_reg) return -EOPNOTSUPP; if (!len) return 0; return master->_erase_user_prot_reg(master, from, len); } EXPORT_SYMBOL_GPL(mtd_erase_user_prot_reg); /* Chip-supported device locking */ int mtd_lock(struct mtd_info *mtd, loff_t ofs, uint64_t len) { struct mtd_info *master = mtd_get_master(mtd); if (!master->_lock) return -EOPNOTSUPP; if (ofs < 0 || ofs >= mtd->size || len > mtd->size - ofs) return -EINVAL; if (!len) return 0; if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) { ofs = (loff_t)mtd_div_by_eb(ofs, mtd) * master->erasesize; len = (u64)mtd_div_by_eb(len, mtd) * master->erasesize; } return master->_lock(master, mtd_get_master_ofs(mtd, ofs), len); } EXPORT_SYMBOL_GPL(mtd_lock); int mtd_unlock(struct mtd_info *mtd, loff_t ofs, uint64_t len) { struct mtd_info *master = mtd_get_master(mtd); if (!master->_unlock) return -EOPNOTSUPP; if (ofs < 0 || ofs >= mtd->size || len > mtd->size - ofs) return -EINVAL; if (!len) return 0; if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) { ofs = (loff_t)mtd_div_by_eb(ofs, mtd) * master->erasesize; len = (u64)mtd_div_by_eb(len, mtd) * master->erasesize; } return master->_unlock(master, mtd_get_master_ofs(mtd, ofs), len); } EXPORT_SYMBOL_GPL(mtd_unlock); int mtd_is_locked(struct mtd_info *mtd, loff_t ofs, uint64_t len) { struct mtd_info *master = mtd_get_master(mtd); if (!master->_is_locked) return -EOPNOTSUPP; if (ofs < 0 || ofs >= mtd->size || len > mtd->size - ofs) return -EINVAL; if (!len) return 0; if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) { ofs = (loff_t)mtd_div_by_eb(ofs, mtd) * master->erasesize; len = (u64)mtd_div_by_eb(len, mtd) * master->erasesize; } return master->_is_locked(master, mtd_get_master_ofs(mtd, ofs), len); } EXPORT_SYMBOL_GPL(mtd_is_locked); int mtd_block_isreserved(struct mtd_info *mtd, loff_t ofs) { struct mtd_info *master = mtd_get_master(mtd); if (ofs < 0 || ofs >= mtd->size) return -EINVAL; if (!master->_block_isreserved) return 0; if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) ofs = (loff_t)mtd_div_by_eb(ofs, mtd) * master->erasesize; return master->_block_isreserved(master, mtd_get_master_ofs(mtd, ofs)); } EXPORT_SYMBOL_GPL(mtd_block_isreserved); int mtd_block_isbad(struct mtd_info *mtd, loff_t ofs) { struct mtd_info *master = mtd_get_master(mtd); if (ofs < 0 || ofs >= mtd->size) return -EINVAL; if (!master->_block_isbad) return 0; if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) ofs = (loff_t)mtd_div_by_eb(ofs, mtd) * master->erasesize; return master->_block_isbad(master, mtd_get_master_ofs(mtd, ofs)); } EXPORT_SYMBOL_GPL(mtd_block_isbad); int mtd_block_markbad(struct mtd_info *mtd, loff_t ofs) { struct mtd_info *master = mtd_get_master(mtd); int ret; if (!master->_block_markbad) return -EOPNOTSUPP; if (ofs < 0 || ofs >= mtd->size) return -EINVAL; if (!(mtd->flags & MTD_WRITEABLE)) return -EROFS; if (mtd->flags & MTD_SLC_ON_MLC_EMULATION) ofs = (loff_t)mtd_div_by_eb(ofs, mtd) * master->erasesize; ret = master->_block_markbad(master, mtd_get_master_ofs(mtd, ofs)); if (ret) return ret; while (mtd->parent) { mtd->ecc_stats.badblocks++; mtd = mtd->parent; } return 0; } EXPORT_SYMBOL_GPL(mtd_block_markbad); ALLOW_ERROR_INJECTION(mtd_block_markbad, ERRNO); /* * default_mtd_writev - the default writev method * @mtd: mtd device description object pointer * @vecs: the vectors to write * @count: count of vectors in @vecs * @to: the MTD device offset to write to * @retlen: on exit contains the count of bytes written to the MTD device. * * This function returns zero in case of success and a negative error code in * case of failure. */ static int default_mtd_writev(struct mtd_info *mtd, const struct kvec *vecs, unsigned long count, loff_t to, size_t *retlen) { unsigned long i; size_t totlen = 0, thislen; int ret = 0; for (i = 0; i < count; i++) { if (!vecs[i].iov_len) continue; ret = mtd_write(mtd, to, vecs[i].iov_len, &thislen, vecs[i].iov_base); totlen += thislen; if (ret || thislen != vecs[i].iov_len) break; to += vecs[i].iov_len; } *retlen = totlen; return ret; } /* * mtd_writev - the vector-based MTD write method * @mtd: mtd device description object pointer * @vecs: the vectors to write * @count: count of vectors in @vecs * @to: the MTD device offset to write to * @retlen: on exit contains the count of bytes written to the MTD device. * * This function returns zero in case of success and a negative error code in * case of failure. */ int mtd_writev(struct mtd_info *mtd, const struct kvec *vecs, unsigned long count, loff_t to, size_t *retlen) { struct mtd_info *master = mtd_get_master(mtd); *retlen = 0; if (!(mtd->flags & MTD_WRITEABLE)) return -EROFS; if (!master->_writev) return default_mtd_writev(mtd, vecs, count, to, retlen); return master->_writev(master, vecs, count, mtd_get_master_ofs(mtd, to), retlen); } EXPORT_SYMBOL_GPL(mtd_writev); /** * mtd_kmalloc_up_to - allocate a contiguous buffer up to the specified size * @mtd: mtd device description object pointer * @size: a pointer to the ideal or maximum size of the allocation, points * to the actual allocation size on success. * * This routine attempts to allocate a contiguous kernel buffer up to * the specified size, backing off the size of the request exponentially * until the request succeeds or until the allocation size falls below * the system page size. This attempts to make sure it does not adversely * impact system performance, so when allocating more than one page, we * ask the memory allocator to avoid re-trying, swapping, writing back * or performing I/O. * * Note, this function also makes sure that the allocated buffer is aligned to * the MTD device's min. I/O unit, i.e. the "mtd->writesize" value. * * This is called, for example by mtd_{read,write} and jffs2_scan_medium, * to handle smaller (i.e. degraded) buffer allocations under low- or * fragmented-memory situations where such reduced allocations, from a * requested ideal, are allowed. * * Returns a pointer to the allocated buffer on success; otherwise, NULL. */ void *mtd_kmalloc_up_to(const struct mtd_info *mtd, size_t *size) { gfp_t flags = __GFP_NOWARN | __GFP_DIRECT_RECLAIM | __GFP_NORETRY; size_t min_alloc = max_t(size_t, mtd->writesize, PAGE_SIZE); void *kbuf; *size = min_t(size_t, *size, KMALLOC_MAX_SIZE); while (*size > min_alloc) { kbuf = kmalloc(*size, flags); if (kbuf) return kbuf; *size >>= 1; *size = ALIGN(*size, mtd->writesize); } /* * For the last resort allocation allow 'kmalloc()' to do all sorts of * things (write-back, dropping caches, etc) by using GFP_KERNEL. */ return kmalloc(*size, GFP_KERNEL); } EXPORT_SYMBOL_GPL(mtd_kmalloc_up_to); #ifdef CONFIG_PROC_FS /*====================================================================*/ /* Support for /proc/mtd */ static int mtd_proc_show(struct seq_file *m, void *v) { struct mtd_info *mtd; seq_puts(m, "dev: size erasesize name\n"); mutex_lock(&mtd_table_mutex); mtd_for_each_device(mtd) { seq_printf(m, "mtd%d: %8.8llx %8.8x \"%s\"\n", mtd->index, (unsigned long long)mtd->size, mtd->erasesize, mtd->name); } mutex_unlock(&mtd_table_mutex); return 0; } #endif /* CONFIG_PROC_FS */ /*====================================================================*/ /* Init code */ static struct backing_dev_info * __init mtd_bdi_init(const char *name) { struct backing_dev_info *bdi; int ret; bdi = bdi_alloc(NUMA_NO_NODE); if (!bdi) return ERR_PTR(-ENOMEM); bdi->ra_pages = 0; bdi->io_pages = 0; /* * We put '-0' suffix to the name to get the same name format as we * used to get. Since this is called only once, we get a unique name. */ ret = bdi_register(bdi, "%.28s-0", name); if (ret) bdi_put(bdi); return ret ? ERR_PTR(ret) : bdi; } static struct proc_dir_entry *proc_mtd; static int __init init_mtd(void) { int ret; ret = class_register(&mtd_class); if (ret) goto err_reg; mtd_bdi = mtd_bdi_init("mtd"); if (IS_ERR(mtd_bdi)) { ret = PTR_ERR(mtd_bdi); goto err_bdi; } proc_mtd = proc_create_single("mtd", 0, NULL, mtd_proc_show); ret = init_mtdchar(); if (ret) goto out_procfs; dfs_dir_mtd = debugfs_create_dir("mtd", NULL); debugfs_create_bool("expert_analysis_mode", 0600, dfs_dir_mtd, &mtd_expert_analysis_mode); return 0; out_procfs: if (proc_mtd) remove_proc_entry("mtd", NULL); bdi_unregister(mtd_bdi); bdi_put(mtd_bdi); err_bdi: class_unregister(&mtd_class); err_reg: pr_err("Error registering mtd class or bdi: %d\n", ret); return ret; } static void __exit cleanup_mtd(void) { debugfs_remove_recursive(dfs_dir_mtd); cleanup_mtdchar(); if (proc_mtd) remove_proc_entry("mtd", NULL); class_unregister(&mtd_class); bdi_unregister(mtd_bdi); bdi_put(mtd_bdi); idr_destroy(&mtd_idr); } module_init(init_mtd); module_exit(cleanup_mtd); MODULE_LICENSE("GPL"); MODULE_AUTHOR("David Woodhouse <dwmw2@infradead.org>"); MODULE_DESCRIPTION("Core MTD registration and access routines"); |
| 2 145 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc. * All Rights Reserved. */ #ifndef __XFS_RTBITMAP_H__ #define __XFS_RTBITMAP_H__ #include "xfs_rtgroup.h" struct xfs_rtalloc_args { struct xfs_rtgroup *rtg; struct xfs_mount *mp; struct xfs_trans *tp; struct xfs_buf *rbmbp; /* bitmap block buffer */ struct xfs_buf *sumbp; /* summary block buffer */ xfs_fileoff_t rbmoff; /* bitmap block number */ xfs_fileoff_t sumoff; /* summary block number */ }; static inline xfs_rtblock_t xfs_rtx_to_rtb( struct xfs_rtgroup *rtg, xfs_rtxnum_t rtx) { struct xfs_mount *mp = rtg_mount(rtg); xfs_rtblock_t start = xfs_group_start_fsb(rtg_group(rtg)); if (mp->m_rtxblklog >= 0) return start + (rtx << mp->m_rtxblklog); return start + (rtx * mp->m_sb.sb_rextsize); } /* Convert an rgbno into an rt extent number. */ static inline xfs_rtxnum_t xfs_rgbno_to_rtx( struct xfs_mount *mp, xfs_rgblock_t rgbno) { if (likely(mp->m_rtxblklog >= 0)) return rgbno >> mp->m_rtxblklog; return rgbno / mp->m_sb.sb_rextsize; } static inline uint64_t xfs_rtbxlen_to_blen( struct xfs_mount *mp, xfs_rtbxlen_t rtbxlen) { if (mp->m_rtxblklog >= 0) return rtbxlen << mp->m_rtxblklog; return rtbxlen * mp->m_sb.sb_rextsize; } static inline xfs_extlen_t xfs_rtxlen_to_extlen( struct xfs_mount *mp, xfs_rtxlen_t rtxlen) { if (mp->m_rtxblklog >= 0) return rtxlen << mp->m_rtxblklog; return rtxlen * mp->m_sb.sb_rextsize; } /* Compute the misalignment between an extent length and a realtime extent .*/ static inline unsigned int xfs_extlen_to_rtxmod( struct xfs_mount *mp, xfs_extlen_t len) { if (mp->m_rtxblklog >= 0) return len & mp->m_rtxblkmask; return len % mp->m_sb.sb_rextsize; } static inline xfs_rtxlen_t xfs_extlen_to_rtxlen( struct xfs_mount *mp, xfs_extlen_t len) { if (mp->m_rtxblklog >= 0) return len >> mp->m_rtxblklog; return len / mp->m_sb.sb_rextsize; } /* Convert an rt block count into an rt extent count. */ static inline xfs_rtbxlen_t xfs_blen_to_rtbxlen( struct xfs_mount *mp, uint64_t blen) { if (likely(mp->m_rtxblklog >= 0)) return blen >> mp->m_rtxblklog; return div_u64(blen, mp->m_sb.sb_rextsize); } /* Return the offset of a file block length within an rt extent. */ static inline xfs_extlen_t xfs_blen_to_rtxoff( struct xfs_mount *mp, xfs_filblks_t blen) { if (likely(mp->m_rtxblklog >= 0)) return blen & mp->m_rtxblkmask; return do_div(blen, mp->m_sb.sb_rextsize); } /* Round this block count up to the nearest rt extent size. */ static inline xfs_filblks_t xfs_blen_roundup_rtx( struct xfs_mount *mp, xfs_filblks_t blen) { return roundup_64(blen, mp->m_sb.sb_rextsize); } /* Convert an rt block number into an rt extent number. */ static inline xfs_rtxnum_t xfs_rtb_to_rtx( struct xfs_mount *mp, xfs_rtblock_t rtbno) { /* open-coded 64-bit masking operation */ rtbno &= mp->m_groups[XG_TYPE_RTG].blkmask; if (likely(mp->m_rtxblklog >= 0)) return rtbno >> mp->m_rtxblklog; return div_u64(rtbno, mp->m_sb.sb_rextsize); } /* Return the offset of a rtgroup block number within an rt extent. */ static inline xfs_extlen_t xfs_rgbno_to_rtxoff( struct xfs_mount *mp, xfs_rgblock_t rgbno) { return rgbno % mp->m_sb.sb_rextsize; } /* Return the offset of an rt block number within an rt extent. */ static inline xfs_extlen_t xfs_rtb_to_rtxoff( struct xfs_mount *mp, xfs_rtblock_t rtbno) { /* open-coded 64-bit masking operation */ rtbno &= mp->m_groups[XG_TYPE_RTG].blkmask; if (likely(mp->m_rtxblklog >= 0)) return rtbno & mp->m_rtxblkmask; return do_div(rtbno, mp->m_sb.sb_rextsize); } /* Round this file block offset up to the nearest rt extent size. */ static inline xfs_rtblock_t xfs_fileoff_roundup_rtx( struct xfs_mount *mp, xfs_fileoff_t off) { return roundup_64(off, mp->m_sb.sb_rextsize); } /* Round this file block offset down to the nearest rt extent size. */ static inline xfs_rtblock_t xfs_fileoff_rounddown_rtx( struct xfs_mount *mp, xfs_fileoff_t off) { return rounddown_64(off, mp->m_sb.sb_rextsize); } /* Convert an rt extent number to a file block offset in the rt bitmap file. */ static inline xfs_fileoff_t xfs_rtx_to_rbmblock( struct xfs_mount *mp, xfs_rtxnum_t rtx) { if (xfs_has_rtgroups(mp)) return div_u64(rtx, mp->m_rtx_per_rbmblock); return rtx >> mp->m_blkbit_log; } /* Convert an rt extent number to a word offset within an rt bitmap block. */ static inline unsigned int xfs_rtx_to_rbmword( struct xfs_mount *mp, xfs_rtxnum_t rtx) { if (xfs_has_rtgroups(mp)) { unsigned int mod; div_u64_rem(rtx >> XFS_NBWORDLOG, mp->m_blockwsize, &mod); return mod; } return (rtx >> XFS_NBWORDLOG) & (mp->m_blockwsize - 1); } /* Convert a file block offset in the rt bitmap file to an rt extent number. */ static inline xfs_rtxnum_t xfs_rbmblock_to_rtx( struct xfs_mount *mp, xfs_fileoff_t rbmoff) { if (xfs_has_rtgroups(mp)) return rbmoff * mp->m_rtx_per_rbmblock; return rbmoff << mp->m_blkbit_log; } /* Return a pointer to a bitmap word within a rt bitmap block. */ static inline union xfs_rtword_raw * xfs_rbmblock_wordptr( struct xfs_rtalloc_args *args, unsigned int index) { struct xfs_mount *mp = args->mp; union xfs_rtword_raw *words; struct xfs_rtbuf_blkinfo *hdr = args->rbmbp->b_addr; if (xfs_has_rtgroups(mp)) words = (union xfs_rtword_raw *)(hdr + 1); else words = args->rbmbp->b_addr; return words + index; } /* Convert an ondisk bitmap word to its incore representation. */ static inline xfs_rtword_t xfs_rtbitmap_getword( struct xfs_rtalloc_args *args, unsigned int index) { union xfs_rtword_raw *word = xfs_rbmblock_wordptr(args, index); if (xfs_has_rtgroups(args->mp)) return be32_to_cpu(word->rtg); return word->old; } /* Set an ondisk bitmap word from an incore representation. */ static inline void xfs_rtbitmap_setword( struct xfs_rtalloc_args *args, unsigned int index, xfs_rtword_t value) { union xfs_rtword_raw *word = xfs_rbmblock_wordptr(args, index); if (xfs_has_rtgroups(args->mp)) word->rtg = cpu_to_be32(value); else word->old = value; } /* * Convert a rt extent length and rt bitmap block number to a xfs_suminfo_t * offset within the rt summary file. */ static inline xfs_rtsumoff_t xfs_rtsumoffs( struct xfs_mount *mp, int log2_len, xfs_fileoff_t rbmoff) { return log2_len * mp->m_sb.sb_rbmblocks + rbmoff; } /* * Convert an xfs_suminfo_t offset to a file block offset within the rt summary * file. */ static inline xfs_fileoff_t xfs_rtsumoffs_to_block( struct xfs_mount *mp, xfs_rtsumoff_t rsumoff) { if (xfs_has_rtgroups(mp)) return rsumoff / mp->m_blockwsize; return XFS_B_TO_FSBT(mp, rsumoff * sizeof(xfs_suminfo_t)); } /* * Convert an xfs_suminfo_t offset to an info word offset within an rt summary * block. */ static inline unsigned int xfs_rtsumoffs_to_infoword( struct xfs_mount *mp, xfs_rtsumoff_t rsumoff) { unsigned int mask = mp->m_blockmask >> XFS_SUMINFOLOG; if (xfs_has_rtgroups(mp)) return rsumoff % mp->m_blockwsize; return rsumoff & mask; } /* Return a pointer to a summary info word within a rt summary block. */ static inline union xfs_suminfo_raw * xfs_rsumblock_infoptr( struct xfs_rtalloc_args *args, unsigned int index) { union xfs_suminfo_raw *info; struct xfs_rtbuf_blkinfo *hdr = args->sumbp->b_addr; if (xfs_has_rtgroups(args->mp)) info = (union xfs_suminfo_raw *)(hdr + 1); else info = args->sumbp->b_addr; return info + index; } /* Get the current value of a summary counter. */ static inline xfs_suminfo_t xfs_suminfo_get( struct xfs_rtalloc_args *args, unsigned int index) { union xfs_suminfo_raw *info = xfs_rsumblock_infoptr(args, index); if (xfs_has_rtgroups(args->mp)) return be32_to_cpu(info->rtg); return info->old; } /* Add to the current value of a summary counter and return the new value. */ static inline xfs_suminfo_t xfs_suminfo_add( struct xfs_rtalloc_args *args, unsigned int index, int delta) { union xfs_suminfo_raw *info = xfs_rsumblock_infoptr(args, index); if (xfs_has_rtgroups(args->mp)) { be32_add_cpu(&info->rtg, delta); return be32_to_cpu(info->rtg); } info->old += delta; return info->old; } static inline const struct xfs_buf_ops * xfs_rtblock_ops( struct xfs_mount *mp, enum xfs_rtg_inodes type) { if (xfs_has_rtgroups(mp)) { if (type == XFS_RTGI_SUMMARY) return &xfs_rtsummary_buf_ops; return &xfs_rtbitmap_buf_ops; } return &xfs_rtbuf_ops; } /* * Functions for walking free space rtextents in the realtime bitmap. */ struct xfs_rtalloc_rec { xfs_rtxnum_t ar_startext; xfs_rtbxlen_t ar_extcount; }; typedef int (*xfs_rtalloc_query_range_fn)( struct xfs_rtgroup *rtg, struct xfs_trans *tp, const struct xfs_rtalloc_rec *rec, void *priv); #ifdef CONFIG_XFS_RT void xfs_rtbuf_cache_relse(struct xfs_rtalloc_args *args); int xfs_rtbitmap_read_buf(struct xfs_rtalloc_args *args, xfs_fileoff_t block); int xfs_rtsummary_read_buf(struct xfs_rtalloc_args *args, xfs_fileoff_t block); int xfs_rtcheck_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start, xfs_rtxlen_t len, int val, xfs_rtxnum_t *new, int *stat); int xfs_rtfind_back(struct xfs_rtalloc_args *args, xfs_rtxnum_t start, xfs_rtxnum_t *rtblock); int xfs_rtfind_forw(struct xfs_rtalloc_args *args, xfs_rtxnum_t start, xfs_rtxnum_t limit, xfs_rtxnum_t *rtblock); int xfs_rtmodify_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start, xfs_rtxlen_t len, int val); int xfs_rtget_summary(struct xfs_rtalloc_args *args, int log, xfs_fileoff_t bbno, xfs_suminfo_t *sum); int xfs_rtmodify_summary(struct xfs_rtalloc_args *args, int log, xfs_fileoff_t bbno, int delta); int xfs_rtfree_range(struct xfs_rtalloc_args *args, xfs_rtxnum_t start, xfs_rtxlen_t len); int xfs_rtalloc_query_range(struct xfs_rtgroup *rtg, struct xfs_trans *tp, xfs_rtxnum_t start, xfs_rtxnum_t end, xfs_rtalloc_query_range_fn fn, void *priv); int xfs_rtalloc_query_all(struct xfs_rtgroup *rtg, struct xfs_trans *tp, xfs_rtalloc_query_range_fn fn, void *priv); int xfs_rtalloc_extent_is_free(struct xfs_rtgroup *rtg, struct xfs_trans *tp, xfs_rtxnum_t start, xfs_rtxlen_t len, bool *is_free); int xfs_rtfree_extent(struct xfs_trans *tp, struct xfs_rtgroup *rtg, xfs_rtxnum_t start, xfs_rtxlen_t len); /* Same as above, but in units of rt blocks. */ int xfs_rtfree_blocks(struct xfs_trans *tp, struct xfs_rtgroup *rtg, xfs_fsblock_t rtbno, xfs_filblks_t rtlen); xfs_rtxnum_t xfs_rtbitmap_rtx_per_rbmblock(struct xfs_mount *mp); xfs_filblks_t xfs_rtbitmap_blockcount(struct xfs_mount *mp); xfs_filblks_t xfs_rtbitmap_blockcount_len(struct xfs_mount *mp, xfs_rtbxlen_t rtextents); xfs_filblks_t xfs_rtsummary_blockcount(struct xfs_mount *mp, unsigned int *rsumlevels); int xfs_rtfile_initialize_blocks(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type, xfs_fileoff_t offset_fsb, xfs_fileoff_t end_fsb, void *data); int xfs_rtbitmap_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, struct xfs_trans *tp, bool init); int xfs_rtsummary_create(struct xfs_rtgroup *rtg, struct xfs_inode *ip, struct xfs_trans *tp, bool init); #else /* CONFIG_XFS_RT */ # define xfs_rtfree_extent(t,b,l) (-ENOSYS) static inline int xfs_rtfree_blocks(struct xfs_trans *tp, struct xfs_rtgroup *rtg, xfs_fsblock_t rtbno, xfs_filblks_t rtlen) { return -ENOSYS; } # define xfs_rtalloc_query_range(m,t,l,h,f,p) (-ENOSYS) # define xfs_rtalloc_query_all(m,t,f,p) (-ENOSYS) # define xfs_rtbitmap_read_buf(a,b) (-ENOSYS) # define xfs_rtsummary_read_buf(a,b) (-ENOSYS) # define xfs_rtbuf_cache_relse(a) (0) # define xfs_rtalloc_extent_is_free(m,t,s,l,i) (-ENOSYS) static inline xfs_filblks_t xfs_rtbitmap_blockcount_len(struct xfs_mount *mp, xfs_rtbxlen_t rtextents) { /* shut up gcc */ return 0; } #endif /* CONFIG_XFS_RT */ #endif /* __XFS_RTBITMAP_H__ */ |
| 353 142 148 167 89 158 126 127 117 123 53 83 83 53 53 83 150 65 140 28 68 21 33 20 16 21 12 12 130 1 20 107 78 3 12 15 126 4 1 5 32 32 32 139 97 126 138 139 139 139 139 161 161 140 140 158 54 116 116 115 116 116 51 51 51 51 51 2 2 2 2 2 2 121 83 53 121 3 2 1 2 120 66 7 179 118 11 66 120 119 120 111 10 2 17 113 106 23 37 20 20 30 29 17 17 23 8 51 107 97 97 1 1 1 277 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/err.h> #include <linux/slab.h> #include <linux/spinlock.h> #include "messages.h" #include "ctree.h" #include "extent_map.h" #include "compression.h" #include "btrfs_inode.h" #include "disk-io.h" static struct kmem_cache *extent_map_cache; int __init btrfs_extent_map_init(void) { extent_map_cache = kmem_cache_create("btrfs_extent_map", sizeof(struct extent_map), 0, 0, NULL); if (!extent_map_cache) return -ENOMEM; return 0; } void __cold btrfs_extent_map_exit(void) { kmem_cache_destroy(extent_map_cache); } /* * Initialize the extent tree @tree. Should be called for each new inode or * other user of the extent_map interface. */ void btrfs_extent_map_tree_init(struct extent_map_tree *tree) { tree->root = RB_ROOT; INIT_LIST_HEAD(&tree->modified_extents); rwlock_init(&tree->lock); } /* * Allocate a new extent_map structure. The new structure is returned with a * reference count of one and needs to be freed using free_extent_map() */ struct extent_map *btrfs_alloc_extent_map(void) { struct extent_map *em; em = kmem_cache_zalloc(extent_map_cache, GFP_NOFS); if (!em) return NULL; RB_CLEAR_NODE(&em->rb_node); refcount_set(&em->refs, 1); INIT_LIST_HEAD(&em->list); return em; } /* * Drop the reference out on @em by one and free the structure if the reference * count hits zero. */ void btrfs_free_extent_map(struct extent_map *em) { if (!em) return; if (refcount_dec_and_test(&em->refs)) { WARN_ON(btrfs_extent_map_in_tree(em)); WARN_ON(!list_empty(&em->list)); kmem_cache_free(extent_map_cache, em); } } /* Do the math around the end of an extent, handling wrapping. */ static u64 range_end(u64 start, u64 len) { if (start + len < start) return (u64)-1; return start + len; } static void remove_em(struct btrfs_inode *inode, struct extent_map *em) { struct btrfs_fs_info *fs_info = inode->root->fs_info; rb_erase(&em->rb_node, &inode->extent_tree.root); RB_CLEAR_NODE(&em->rb_node); if (!btrfs_is_testing(fs_info) && btrfs_is_fstree(btrfs_root_id(inode->root))) percpu_counter_dec(&fs_info->evictable_extent_maps); } static int tree_insert(struct rb_root *root, struct extent_map *em) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct extent_map *entry = NULL; struct rb_node *orig_parent = NULL; u64 end = range_end(em->start, em->len); while (*p) { parent = *p; entry = rb_entry(parent, struct extent_map, rb_node); if (em->start < entry->start) p = &(*p)->rb_left; else if (em->start >= btrfs_extent_map_end(entry)) p = &(*p)->rb_right; else return -EEXIST; } orig_parent = parent; while (parent && em->start >= btrfs_extent_map_end(entry)) { parent = rb_next(parent); entry = rb_entry(parent, struct extent_map, rb_node); } if (parent) if (end > entry->start && em->start < btrfs_extent_map_end(entry)) return -EEXIST; parent = orig_parent; entry = rb_entry(parent, struct extent_map, rb_node); while (parent && em->start < entry->start) { parent = rb_prev(parent); entry = rb_entry(parent, struct extent_map, rb_node); } if (parent) if (end > entry->start && em->start < btrfs_extent_map_end(entry)) return -EEXIST; rb_link_node(&em->rb_node, orig_parent, p); rb_insert_color(&em->rb_node, root); return 0; } /* * Search through the tree for an extent_map with a given offset. If it can't * be found, try to find some neighboring extents */ static struct rb_node *tree_search(struct rb_root *root, u64 offset, struct rb_node **prev_or_next_ret) { struct rb_node *n = root->rb_node; struct rb_node *prev = NULL; struct rb_node *orig_prev = NULL; struct extent_map *entry; struct extent_map *prev_entry = NULL; ASSERT(prev_or_next_ret); while (n) { entry = rb_entry(n, struct extent_map, rb_node); prev = n; prev_entry = entry; if (offset < entry->start) n = n->rb_left; else if (offset >= btrfs_extent_map_end(entry)) n = n->rb_right; else return n; } orig_prev = prev; while (prev && offset >= btrfs_extent_map_end(prev_entry)) { prev = rb_next(prev); prev_entry = rb_entry(prev, struct extent_map, rb_node); } /* * Previous extent map found, return as in this case the caller does not * care about the next one. */ if (prev) { *prev_or_next_ret = prev; return NULL; } prev = orig_prev; prev_entry = rb_entry(prev, struct extent_map, rb_node); while (prev && offset < prev_entry->start) { prev = rb_prev(prev); prev_entry = rb_entry(prev, struct extent_map, rb_node); } *prev_or_next_ret = prev; return NULL; } static inline u64 extent_map_block_len(const struct extent_map *em) { if (btrfs_extent_map_is_compressed(em)) return em->disk_num_bytes; return em->len; } static inline u64 extent_map_block_end(const struct extent_map *em) { const u64 block_start = btrfs_extent_map_block_start(em); const u64 block_end = block_start + extent_map_block_len(em); if (block_end < block_start) return (u64)-1; return block_end; } static bool can_merge_extent_map(const struct extent_map *em) { if (em->flags & EXTENT_FLAG_PINNED) return false; /* Don't merge compressed extents, we need to know their actual size. */ if (btrfs_extent_map_is_compressed(em)) return false; if (em->flags & EXTENT_FLAG_LOGGING) return false; /* * We don't want to merge stuff that hasn't been written to the log yet * since it may not reflect exactly what is on disk, and that would be * bad. */ if (!list_empty(&em->list)) return false; return true; } /* Check to see if two extent_map structs are adjacent and safe to merge. */ static bool mergeable_maps(const struct extent_map *prev, const struct extent_map *next) { if (btrfs_extent_map_end(prev) != next->start) return false; /* * The merged flag is not an on-disk flag, it just indicates we had the * extent maps of 2 (or more) adjacent extents merged, so factor it out. */ if ((prev->flags & ~EXTENT_FLAG_MERGED) != (next->flags & ~EXTENT_FLAG_MERGED)) return false; if (next->disk_bytenr < EXTENT_MAP_LAST_BYTE - 1) return btrfs_extent_map_block_start(next) == extent_map_block_end(prev); /* HOLES and INLINE extents. */ return next->disk_bytenr == prev->disk_bytenr; } /* * Handle the on-disk data extents merge for @prev and @next. * * @prev: left extent to merge * @next: right extent to merge * @merged: the extent we will not discard after the merge; updated with new values * * After this, one of the two extents is the new merged extent and the other is * removed from the tree and likely freed. Note that @merged is one of @prev/@next * so there is const/non-const aliasing occurring here. * * Only touches disk_bytenr/disk_num_bytes/offset/ram_bytes. * For now only uncompressed regular extent can be merged. */ static void merge_ondisk_extents(const struct extent_map *prev, const struct extent_map *next, struct extent_map *merged) { u64 new_disk_bytenr; u64 new_disk_num_bytes; u64 new_offset; /* @prev and @next should not be compressed. */ ASSERT(!btrfs_extent_map_is_compressed(prev)); ASSERT(!btrfs_extent_map_is_compressed(next)); /* * There are two different cases where @prev and @next can be merged. * * 1) They are referring to the same data extent: * * |<----- data extent A ----->| * |<- prev ->|<- next ->| * * 2) They are referring to different data extents but still adjacent: * * |<-- data extent A -->|<-- data extent B -->| * |<- prev ->|<- next ->| * * The calculation here always merges the data extents first, then updates * @offset using the new data extents. * * For case 1), the merged data extent would be the same. * For case 2), we just merge the two data extents into one. */ new_disk_bytenr = min(prev->disk_bytenr, next->disk_bytenr); new_disk_num_bytes = max(prev->disk_bytenr + prev->disk_num_bytes, next->disk_bytenr + next->disk_num_bytes) - new_disk_bytenr; new_offset = prev->disk_bytenr + prev->offset - new_disk_bytenr; merged->disk_bytenr = new_disk_bytenr; merged->disk_num_bytes = new_disk_num_bytes; merged->ram_bytes = new_disk_num_bytes; merged->offset = new_offset; } static void dump_extent_map(struct btrfs_fs_info *fs_info, const char *prefix, struct extent_map *em) { if (!IS_ENABLED(CONFIG_BTRFS_DEBUG)) return; btrfs_crit(fs_info, "%s, start=%llu len=%llu disk_bytenr=%llu disk_num_bytes=%llu ram_bytes=%llu offset=%llu flags=0x%x", prefix, em->start, em->len, em->disk_bytenr, em->disk_num_bytes, em->ram_bytes, em->offset, em->flags); ASSERT(0); } /* Internal sanity checks for btrfs debug builds. */ static void validate_extent_map(struct btrfs_fs_info *fs_info, struct extent_map *em) { if (!IS_ENABLED(CONFIG_BTRFS_DEBUG)) return; if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE) { if (em->disk_num_bytes == 0) dump_extent_map(fs_info, "zero disk_num_bytes", em); if (em->offset + em->len > em->ram_bytes) dump_extent_map(fs_info, "ram_bytes too small", em); if (em->offset + em->len > em->disk_num_bytes && !btrfs_extent_map_is_compressed(em)) dump_extent_map(fs_info, "disk_num_bytes too small", em); if (!btrfs_extent_map_is_compressed(em) && em->ram_bytes != em->disk_num_bytes) dump_extent_map(fs_info, "ram_bytes mismatch with disk_num_bytes for non-compressed em", em); } else if (em->offset) { dump_extent_map(fs_info, "non-zero offset for hole/inline", em); } } static void try_merge_map(struct btrfs_inode *inode, struct extent_map *em) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_map *merge = NULL; struct rb_node *rb; /* * We can't modify an extent map that is in the tree and that is being * used by another task, as it can cause that other task to see it in * inconsistent state during the merging. We always have 1 reference for * the tree and 1 for this task (which is unpinning the extent map or * clearing the logging flag), so anything > 2 means it's being used by * other tasks too. */ if (refcount_read(&em->refs) > 2) return; if (!can_merge_extent_map(em)) return; if (em->start != 0) { rb = rb_prev(&em->rb_node); merge = rb_entry_safe(rb, struct extent_map, rb_node); if (rb && can_merge_extent_map(merge) && mergeable_maps(merge, em)) { em->start = merge->start; em->len += merge->len; em->generation = max(em->generation, merge->generation); if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE) merge_ondisk_extents(merge, em, em); em->flags |= EXTENT_FLAG_MERGED; validate_extent_map(fs_info, em); remove_em(inode, merge); btrfs_free_extent_map(merge); } } rb = rb_next(&em->rb_node); merge = rb_entry_safe(rb, struct extent_map, rb_node); if (rb && can_merge_extent_map(merge) && mergeable_maps(em, merge)) { em->len += merge->len; if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE) merge_ondisk_extents(em, merge, em); validate_extent_map(fs_info, em); em->generation = max(em->generation, merge->generation); em->flags |= EXTENT_FLAG_MERGED; remove_em(inode, merge); btrfs_free_extent_map(merge); } } /* * Unpin an extent from the cache. * * @inode: the inode from which we are unpinning an extent range * @start: logical offset in the file * @len: length of the extent * @gen: generation that this extent has been modified in * * Called after an extent has been written to disk properly. Set the generation * to the generation that actually added the file item to the inode so we know * we need to sync this extent when we call fsync(). * * Returns: 0 on success * -ENOENT when the extent is not found in the tree * -EUCLEAN if the found extent does not match the expected start */ int btrfs_unpin_extent_cache(struct btrfs_inode *inode, u64 start, u64 len, u64 gen) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_map_tree *tree = &inode->extent_tree; int ret = 0; struct extent_map *em; write_lock(&tree->lock); em = btrfs_lookup_extent_mapping(tree, start, len); if (WARN_ON(!em)) { btrfs_warn(fs_info, "no extent map found for inode %llu (root %lld) when unpinning extent range [%llu, %llu), generation %llu", btrfs_ino(inode), btrfs_root_id(inode->root), start, start + len, gen); ret = -ENOENT; goto out; } if (WARN_ON(em->start != start)) { btrfs_warn(fs_info, "found extent map for inode %llu (root %lld) with unexpected start offset %llu when unpinning extent range [%llu, %llu), generation %llu", btrfs_ino(inode), btrfs_root_id(inode->root), em->start, start, start + len, gen); ret = -EUCLEAN; goto out; } em->generation = gen; em->flags &= ~EXTENT_FLAG_PINNED; try_merge_map(inode, em); out: write_unlock(&tree->lock); btrfs_free_extent_map(em); return ret; } void btrfs_clear_em_logging(struct btrfs_inode *inode, struct extent_map *em) { lockdep_assert_held_write(&inode->extent_tree.lock); em->flags &= ~EXTENT_FLAG_LOGGING; if (btrfs_extent_map_in_tree(em)) try_merge_map(inode, em); } static inline void setup_extent_mapping(struct btrfs_inode *inode, struct extent_map *em, int modified) { refcount_inc(&em->refs); ASSERT(list_empty(&em->list)); if (modified) list_add(&em->list, &inode->extent_tree.modified_extents); else try_merge_map(inode, em); } /* * Add a new extent map to an inode's extent map tree. * * @inode: the target inode * @em: map to insert * @modified: indicate whether the given @em should be added to the * modified list, which indicates the extent needs to be logged * * Insert @em into the @inode's extent map tree or perform a simple * forward/backward merge with existing mappings. The extent_map struct passed * in will be inserted into the tree directly, with an additional reference * taken, or a reference dropped if the merge attempt was successful. */ static int add_extent_mapping(struct btrfs_inode *inode, struct extent_map *em, int modified) { struct extent_map_tree *tree = &inode->extent_tree; struct btrfs_root *root = inode->root; struct btrfs_fs_info *fs_info = root->fs_info; int ret; lockdep_assert_held_write(&tree->lock); validate_extent_map(fs_info, em); ret = tree_insert(&tree->root, em); if (ret) return ret; setup_extent_mapping(inode, em, modified); if (!btrfs_is_testing(fs_info) && btrfs_is_fstree(btrfs_root_id(root))) percpu_counter_inc(&fs_info->evictable_extent_maps); return 0; } static struct extent_map *lookup_extent_mapping(struct extent_map_tree *tree, u64 start, u64 len, int strict) { struct extent_map *em; struct rb_node *rb_node; struct rb_node *prev_or_next = NULL; u64 end = range_end(start, len); rb_node = tree_search(&tree->root, start, &prev_or_next); if (!rb_node) { if (prev_or_next) rb_node = prev_or_next; else return NULL; } em = rb_entry(rb_node, struct extent_map, rb_node); if (strict && !(end > em->start && start < btrfs_extent_map_end(em))) return NULL; refcount_inc(&em->refs); return em; } /* * Lookup extent_map that intersects @start + @len range. * * @tree: tree to lookup in * @start: byte offset to start the search * @len: length of the lookup range * * Find and return the first extent_map struct in @tree that intersects the * [start, len] range. There may be additional objects in the tree that * intersect, so check the object returned carefully to make sure that no * additional lookups are needed. */ struct extent_map *btrfs_lookup_extent_mapping(struct extent_map_tree *tree, u64 start, u64 len) { return lookup_extent_mapping(tree, start, len, 1); } /* * Find a nearby extent map intersecting @start + @len (not an exact search). * * @tree: tree to lookup in * @start: byte offset to start the search * @len: length of the lookup range * * Find and return the first extent_map struct in @tree that intersects the * [start, len] range. * * If one can't be found, any nearby extent may be returned */ struct extent_map *btrfs_search_extent_mapping(struct extent_map_tree *tree, u64 start, u64 len) { return lookup_extent_mapping(tree, start, len, 0); } /* * Remove an extent_map from its inode's extent tree. * * @inode: the inode the extent map belongs to * @em: extent map being removed * * Remove @em from the extent tree of @inode. No reference counts are dropped, * and no checks are done to see if the range is in use. */ void btrfs_remove_extent_mapping(struct btrfs_inode *inode, struct extent_map *em) { struct extent_map_tree *tree = &inode->extent_tree; lockdep_assert_held_write(&tree->lock); WARN_ON(em->flags & EXTENT_FLAG_PINNED); if (!(em->flags & EXTENT_FLAG_LOGGING)) list_del_init(&em->list); remove_em(inode, em); } static void replace_extent_mapping(struct btrfs_inode *inode, struct extent_map *cur, struct extent_map *new, int modified) { struct btrfs_fs_info *fs_info = inode->root->fs_info; struct extent_map_tree *tree = &inode->extent_tree; lockdep_assert_held_write(&tree->lock); validate_extent_map(fs_info, new); WARN_ON(cur->flags & EXTENT_FLAG_PINNED); ASSERT(btrfs_extent_map_in_tree(cur)); if (!(cur->flags & EXTENT_FLAG_LOGGING)) list_del_init(&cur->list); rb_replace_node(&cur->rb_node, &new->rb_node, &tree->root); RB_CLEAR_NODE(&cur->rb_node); setup_extent_mapping(inode, new, modified); } static struct extent_map *next_extent_map(const struct extent_map *em) { struct rb_node *next; next = rb_next(&em->rb_node); if (!next) return NULL; return container_of(next, struct extent_map, rb_node); } static struct extent_map *prev_extent_map(struct extent_map *em) { struct rb_node *prev; prev = rb_prev(&em->rb_node); if (!prev) return NULL; return container_of(prev, struct extent_map, rb_node); } /* * Helper for btrfs_get_extent. Given an existing extent in the tree, * the existing extent is the nearest extent to map_start, * and an extent that you want to insert, deal with overlap and insert * the best fitted new extent into the tree. */ static noinline int merge_extent_mapping(struct btrfs_inode *inode, struct extent_map *existing, struct extent_map *em, u64 map_start) { struct extent_map *prev; struct extent_map *next; u64 start; u64 end; u64 start_diff; if (map_start < em->start || map_start >= btrfs_extent_map_end(em)) return -EINVAL; if (existing->start > map_start) { next = existing; prev = prev_extent_map(next); } else { prev = existing; next = next_extent_map(prev); } start = prev ? btrfs_extent_map_end(prev) : em->start; start = max_t(u64, start, em->start); end = next ? next->start : btrfs_extent_map_end(em); end = min_t(u64, end, btrfs_extent_map_end(em)); start_diff = start - em->start; em->start = start; em->len = end - start; if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE) em->offset += start_diff; return add_extent_mapping(inode, em, 0); } /* * Add extent mapping into an inode's extent map tree. * * @inode: target inode * @em_in: extent we are inserting * @start: start of the logical range btrfs_get_extent() is requesting * @len: length of the logical range btrfs_get_extent() is requesting * * Note that @em_in's range may be different from [start, start+len), * but they must be overlapped. * * Insert @em_in into the inode's extent map tree. In case there is an * overlapping range, handle the -EEXIST by either: * a) Returning the existing extent in @em_in if @start is within the * existing em. * b) Merge the existing extent with @em_in passed in. * * Return 0 on success, otherwise -EEXIST. * */ int btrfs_add_extent_mapping(struct btrfs_inode *inode, struct extent_map **em_in, u64 start, u64 len) { int ret; struct extent_map *em = *em_in; struct btrfs_fs_info *fs_info = inode->root->fs_info; /* * Tree-checker should have rejected any inline extent with non-zero * file offset. Here just do a sanity check. */ if (em->disk_bytenr == EXTENT_MAP_INLINE) ASSERT(em->start == 0); ret = add_extent_mapping(inode, em, 0); /* it is possible that someone inserted the extent into the tree * while we had the lock dropped. It is also possible that * an overlapping map exists in the tree */ if (ret == -EEXIST) { struct extent_map *existing; existing = btrfs_search_extent_mapping(&inode->extent_tree, start, len); trace_btrfs_handle_em_exist(fs_info, existing, em, start, len); /* * existing will always be non-NULL, since there must be * extent causing the -EEXIST. */ if (start >= existing->start && start < btrfs_extent_map_end(existing)) { btrfs_free_extent_map(em); *em_in = existing; ret = 0; } else { u64 orig_start = em->start; u64 orig_len = em->len; /* * The existing extent map is the one nearest to * the [start, start + len) range which overlaps */ ret = merge_extent_mapping(inode, existing, em, start); if (WARN_ON(ret)) { btrfs_free_extent_map(em); *em_in = NULL; btrfs_warn(fs_info, "extent map merge error existing [%llu, %llu) with em [%llu, %llu) start %llu", existing->start, btrfs_extent_map_end(existing), orig_start, orig_start + orig_len, start); } btrfs_free_extent_map(existing); } } ASSERT(ret == 0 || ret == -EEXIST); return ret; } /* * Drop all extent maps from a tree in the fastest possible way, rescheduling * if needed. This avoids searching the tree, from the root down to the first * extent map, before each deletion. */ static void drop_all_extent_maps_fast(struct btrfs_inode *inode) { struct extent_map_tree *tree = &inode->extent_tree; struct rb_node *node; write_lock(&tree->lock); node = rb_first(&tree->root); while (node) { struct extent_map *em; struct rb_node *next = rb_next(node); em = rb_entry(node, struct extent_map, rb_node); em->flags &= ~(EXTENT_FLAG_PINNED | EXTENT_FLAG_LOGGING); btrfs_remove_extent_mapping(inode, em); btrfs_free_extent_map(em); if (cond_resched_rwlock_write(&tree->lock)) node = rb_first(&tree->root); else node = next; } write_unlock(&tree->lock); } /* * Drop all extent maps in a given range. * * @inode: The target inode. * @start: Start offset of the range. * @end: End offset of the range (inclusive value). * @skip_pinned: Indicate if pinned extent maps should be ignored or not. * * This drops all the extent maps that intersect the given range [@start, @end]. * Extent maps that partially overlap the range and extend behind or beyond it, * are split. * The caller should have locked an appropriate file range in the inode's io * tree before calling this function. */ void btrfs_drop_extent_map_range(struct btrfs_inode *inode, u64 start, u64 end, bool skip_pinned) { struct extent_map *split; struct extent_map *split2; struct extent_map *em; struct extent_map_tree *em_tree = &inode->extent_tree; u64 len = end - start + 1; WARN_ON(end < start); if (end == (u64)-1) { if (start == 0 && !skip_pinned) { drop_all_extent_maps_fast(inode); return; } len = (u64)-1; } else { /* Make end offset exclusive for use in the loop below. */ end++; } /* * It's ok if we fail to allocate the extent maps, see the comment near * the bottom of the loop below. We only need two spare extent maps in * the worst case, where the first extent map that intersects our range * starts before the range and the last extent map that intersects our * range ends after our range (and they might be the same extent map), * because we need to split those two extent maps at the boundaries. */ split = btrfs_alloc_extent_map(); split2 = btrfs_alloc_extent_map(); write_lock(&em_tree->lock); em = btrfs_lookup_extent_mapping(em_tree, start, len); while (em) { /* extent_map_end() returns exclusive value (last byte + 1). */ const u64 em_end = btrfs_extent_map_end(em); struct extent_map *next_em = NULL; u64 gen; unsigned long flags; bool modified; if (em_end < end) { next_em = next_extent_map(em); if (next_em) { if (next_em->start < end) refcount_inc(&next_em->refs); else next_em = NULL; } } if (skip_pinned && (em->flags & EXTENT_FLAG_PINNED)) { start = em_end; goto next; } flags = em->flags; /* * In case we split the extent map, we want to preserve the * EXTENT_FLAG_LOGGING flag on our extent map, but we don't want * it on the new extent maps. */ em->flags &= ~(EXTENT_FLAG_PINNED | EXTENT_FLAG_LOGGING); modified = !list_empty(&em->list); /* * The extent map does not cross our target range, so no need to * split it, we can remove it directly. */ if (em->start >= start && em_end <= end) goto remove_em; gen = em->generation; if (em->start < start) { if (!split) { split = split2; split2 = NULL; if (!split) goto remove_em; } split->start = em->start; split->len = start - em->start; if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE) { split->disk_bytenr = em->disk_bytenr; split->disk_num_bytes = em->disk_num_bytes; split->offset = em->offset; split->ram_bytes = em->ram_bytes; } else { split->disk_bytenr = em->disk_bytenr; split->disk_num_bytes = 0; split->offset = 0; split->ram_bytes = split->len; } split->generation = gen; split->flags = flags; replace_extent_mapping(inode, em, split, modified); btrfs_free_extent_map(split); split = split2; split2 = NULL; } if (em_end > end) { if (!split) { split = split2; split2 = NULL; if (!split) goto remove_em; } split->start = end; split->len = em_end - end; split->disk_bytenr = em->disk_bytenr; split->flags = flags; split->generation = gen; if (em->disk_bytenr < EXTENT_MAP_LAST_BYTE) { split->disk_num_bytes = em->disk_num_bytes; split->offset = em->offset + end - em->start; split->ram_bytes = em->ram_bytes; } else { split->disk_num_bytes = 0; split->offset = 0; split->ram_bytes = split->len; } if (btrfs_extent_map_in_tree(em)) { replace_extent_mapping(inode, em, split, modified); } else { int ret; ret = add_extent_mapping(inode, split, modified); /* Logic error, shouldn't happen. */ ASSERT(ret == 0); if (WARN_ON(ret != 0) && modified) btrfs_set_inode_full_sync(inode); } btrfs_free_extent_map(split); split = NULL; } remove_em: if (btrfs_extent_map_in_tree(em)) { /* * If the extent map is still in the tree it means that * either of the following is true: * * 1) It fits entirely in our range (doesn't end beyond * it or starts before it); * * 2) It starts before our range and/or ends after our * range, and we were not able to allocate the extent * maps for split operations, @split and @split2. * * If we are at case 2) then we just remove the entire * extent map - this is fine since if anyone needs it to * access the subranges outside our range, will just * load it again from the subvolume tree's file extent * item. However if the extent map was in the list of * modified extents, then we must mark the inode for a * full fsync, otherwise a fast fsync will miss this * extent if it's new and needs to be logged. */ if ((em->start < start || em_end > end) && modified) { ASSERT(!split); btrfs_set_inode_full_sync(inode); } btrfs_remove_extent_mapping(inode, em); } /* * Once for the tree reference (we replaced or removed the * extent map from the tree). */ btrfs_free_extent_map(em); next: /* Once for us (for our lookup reference). */ btrfs_free_extent_map(em); em = next_em; } write_unlock(&em_tree->lock); btrfs_free_extent_map(split); btrfs_free_extent_map(split2); } /* * Replace a range in the inode's extent map tree with a new extent map. * * @inode: The target inode. * @new_em: The new extent map to add to the inode's extent map tree. * @modified: Indicate if the new extent map should be added to the list of * modified extents (for fast fsync tracking). * * Drops all the extent maps in the inode's extent map tree that intersect the * range of the new extent map and adds the new extent map to the tree. * The caller should have locked an appropriate file range in the inode's io * tree before calling this function. */ int btrfs_replace_extent_map_range(struct btrfs_inode *inode, struct extent_map *new_em, bool modified) { const u64 end = new_em->start + new_em->len - 1; struct extent_map_tree *tree = &inode->extent_tree; int ret; ASSERT(!btrfs_extent_map_in_tree(new_em)); /* * The caller has locked an appropriate file range in the inode's io * tree, but getting -EEXIST when adding the new extent map can still * happen in case there are extents that partially cover the range, and * this is due to two tasks operating on different parts of the extent. * See commit 18e83ac75bfe67 ("Btrfs: fix unexpected EEXIST from * btrfs_get_extent") for an example and details. */ do { btrfs_drop_extent_map_range(inode, new_em->start, end, false); write_lock(&tree->lock); ret = add_extent_mapping(inode, new_em, modified); write_unlock(&tree->lock); } while (ret == -EEXIST); return ret; } /* * Split off the first pre bytes from the extent_map at [start, start + len], * and set the block_start for it to new_logical. * * This function is used when an ordered_extent needs to be split. */ int btrfs_split_extent_map(struct btrfs_inode *inode, u64 start, u64 len, u64 pre, u64 new_logical) { struct extent_map_tree *em_tree = &inode->extent_tree; struct extent_map *em; struct extent_map *split_pre = NULL; struct extent_map *split_mid = NULL; int ret = 0; unsigned long flags; ASSERT(pre != 0); ASSERT(pre < len); split_pre = btrfs_alloc_extent_map(); if (!split_pre) return -ENOMEM; split_mid = btrfs_alloc_extent_map(); if (!split_mid) { ret = -ENOMEM; goto out_free_pre; } btrfs_lock_extent(&inode->io_tree, start, start + len - 1, NULL); write_lock(&em_tree->lock); em = btrfs_lookup_extent_mapping(em_tree, start, len); if (!em) { ret = -EIO; goto out_unlock; } ASSERT(em->len == len); ASSERT(!btrfs_extent_map_is_compressed(em)); ASSERT(em->disk_bytenr < EXTENT_MAP_LAST_BYTE); ASSERT(em->flags & EXTENT_FLAG_PINNED); ASSERT(!(em->flags & EXTENT_FLAG_LOGGING)); ASSERT(!list_empty(&em->list)); flags = em->flags; em->flags &= ~EXTENT_FLAG_PINNED; /* First, replace the em with a new extent_map starting from * em->start */ split_pre->start = em->start; split_pre->len = pre; split_pre->disk_bytenr = new_logical; split_pre->disk_num_bytes = split_pre->len; split_pre->offset = 0; split_pre->ram_bytes = split_pre->len; split_pre->flags = flags; split_pre->generation = em->generation; replace_extent_mapping(inode, em, split_pre, 1); /* * Now we only have an extent_map at: * [em->start, em->start + pre] */ /* Insert the middle extent_map. */ split_mid->start = em->start + pre; split_mid->len = em->len - pre; split_mid->disk_bytenr = btrfs_extent_map_block_start(em) + pre; split_mid->disk_num_bytes = split_mid->len; split_mid->offset = 0; split_mid->ram_bytes = split_mid->len; split_mid->flags = flags; split_mid->generation = em->generation; add_extent_mapping(inode, split_mid, 1); /* Once for us */ btrfs_free_extent_map(em); /* Once for the tree */ btrfs_free_extent_map(em); out_unlock: write_unlock(&em_tree->lock); btrfs_unlock_extent(&inode->io_tree, start, start + len - 1, NULL); btrfs_free_extent_map(split_mid); out_free_pre: btrfs_free_extent_map(split_pre); return ret; } struct btrfs_em_shrink_ctx { long nr_to_scan; long scanned; }; static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_ctx *ctx) { struct btrfs_fs_info *fs_info = inode->root->fs_info; const u64 cur_fs_gen = btrfs_get_fs_generation(fs_info); struct extent_map_tree *tree = &inode->extent_tree; long nr_dropped = 0; struct rb_node *node; lockdep_assert_held_write(&tree->lock); /* * Take the mmap lock so that we serialize with the inode logging phase * of fsync because we may need to set the full sync flag on the inode, * in case we have to remove extent maps in the tree's list of modified * extents. If we set the full sync flag in the inode while an fsync is * in progress, we may risk missing new extents because before the flag * is set, fsync decides to only wait for writeback to complete and then * during inode logging it sees the flag set and uses the subvolume tree * to find new extents, which may not be there yet because ordered * extents haven't completed yet. * * We also do a try lock because we don't want to block for too long and * we are holding the extent map tree's lock in write mode. */ if (!down_read_trylock(&inode->i_mmap_lock)) return 0; node = rb_first(&tree->root); while (node) { struct rb_node *next = rb_next(node); struct extent_map *em; em = rb_entry(node, struct extent_map, rb_node); ctx->scanned++; if (em->flags & EXTENT_FLAG_PINNED) goto next; /* * If the inode is in the list of modified extents (new) and its * generation is the same (or is greater than) the current fs * generation, it means it was not yet persisted so we have to * set the full sync flag so that the next fsync will not miss * it. */ if (!list_empty(&em->list) && em->generation >= cur_fs_gen) btrfs_set_inode_full_sync(inode); btrfs_remove_extent_mapping(inode, em); trace_btrfs_extent_map_shrinker_remove_em(inode, em); /* Drop the reference for the tree. */ btrfs_free_extent_map(em); nr_dropped++; next: if (ctx->scanned >= ctx->nr_to_scan) break; /* * Stop if we need to reschedule or there's contention on the * lock. This is to avoid slowing other tasks trying to take the * lock. */ if (need_resched() || rwlock_needbreak(&tree->lock) || btrfs_fs_closing(fs_info)) break; node = next; } up_read(&inode->i_mmap_lock); return nr_dropped; } static struct btrfs_inode *find_first_inode_to_shrink(struct btrfs_root *root, u64 min_ino) { struct btrfs_inode *inode; unsigned long from = min_ino; xa_lock(&root->inodes); while (true) { struct extent_map_tree *tree; inode = xa_find(&root->inodes, &from, ULONG_MAX, XA_PRESENT); if (!inode) break; tree = &inode->extent_tree; /* * We want to be fast so if the lock is busy we don't want to * spend time waiting for it (some task is about to do IO for * the inode). */ if (!write_trylock(&tree->lock)) goto next; /* * Skip inode if it doesn't have loaded extent maps, so we avoid * getting a reference and doing an iput later. This includes * cases like files that were opened for things like stat(2), or * files with all extent maps previously released through the * release folio callback (btrfs_release_folio()) or released in * a previous run, or directories which never have extent maps. */ if (RB_EMPTY_ROOT(&tree->root)) { write_unlock(&tree->lock); goto next; } if (igrab(&inode->vfs_inode)) break; write_unlock(&tree->lock); next: from = btrfs_ino(inode) + 1; cond_resched_lock(&root->inodes.xa_lock); } xa_unlock(&root->inodes); return inode; } static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx *ctx) { struct btrfs_fs_info *fs_info = root->fs_info; struct btrfs_inode *inode; long nr_dropped = 0; u64 min_ino = fs_info->em_shrinker_last_ino + 1; inode = find_first_inode_to_shrink(root, min_ino); while (inode) { nr_dropped += btrfs_scan_inode(inode, ctx); write_unlock(&inode->extent_tree.lock); min_ino = btrfs_ino(inode) + 1; fs_info->em_shrinker_last_ino = btrfs_ino(inode); iput(&inode->vfs_inode); if (ctx->scanned >= ctx->nr_to_scan || btrfs_fs_closing(fs_info)) break; cond_resched(); inode = find_first_inode_to_shrink(root, min_ino); } if (inode) { /* * There are still inodes in this root or we happened to process * the last one and reached the scan limit. In either case set * the current root to this one, so we'll resume from the next * inode if there is one or we will find out this was the last * one and move to the next root. */ fs_info->em_shrinker_last_root = btrfs_root_id(root); } else { /* * No more inodes in this root, set extent_map_shrinker_last_ino to 0 so * that when processing the next root we start from its first inode. */ fs_info->em_shrinker_last_ino = 0; fs_info->em_shrinker_last_root = btrfs_root_id(root) + 1; } return nr_dropped; } static void btrfs_extent_map_shrinker_worker(struct work_struct *work) { struct btrfs_fs_info *fs_info; struct btrfs_em_shrink_ctx ctx; u64 start_root_id; u64 next_root_id; bool cycled = false; long nr_dropped = 0; fs_info = container_of(work, struct btrfs_fs_info, em_shrinker_work); ctx.scanned = 0; ctx.nr_to_scan = atomic64_read(&fs_info->em_shrinker_nr_to_scan); start_root_id = fs_info->em_shrinker_last_root; next_root_id = fs_info->em_shrinker_last_root; if (trace_btrfs_extent_map_shrinker_scan_enter_enabled()) { s64 nr = percpu_counter_sum_positive(&fs_info->evictable_extent_maps); trace_btrfs_extent_map_shrinker_scan_enter(fs_info, nr); } while (ctx.scanned < ctx.nr_to_scan && !btrfs_fs_closing(fs_info)) { struct btrfs_root *root; unsigned long count; cond_resched(); spin_lock(&fs_info->fs_roots_radix_lock); count = radix_tree_gang_lookup(&fs_info->fs_roots_radix, (void **)&root, (unsigned long)next_root_id, 1); if (count == 0) { spin_unlock(&fs_info->fs_roots_radix_lock); if (start_root_id > 0 && !cycled) { next_root_id = 0; fs_info->em_shrinker_last_root = 0; fs_info->em_shrinker_last_ino = 0; cycled = true; continue; } break; } next_root_id = btrfs_root_id(root) + 1; root = btrfs_grab_root(root); spin_unlock(&fs_info->fs_roots_radix_lock); if (!root) continue; if (btrfs_is_fstree(btrfs_root_id(root))) nr_dropped += btrfs_scan_root(root, &ctx); btrfs_put_root(root); } if (trace_btrfs_extent_map_shrinker_scan_exit_enabled()) { s64 nr = percpu_counter_sum_positive(&fs_info->evictable_extent_maps); trace_btrfs_extent_map_shrinker_scan_exit(fs_info, nr_dropped, nr); } atomic64_set(&fs_info->em_shrinker_nr_to_scan, 0); } void btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan) { /* * Do nothing if the shrinker is already running. In case of high memory * pressure we can have a lot of tasks calling us and all passing the * same nr_to_scan value, but in reality we may need only to free * nr_to_scan extent maps (or less). In case we need to free more than * that, we will be called again by the fs shrinker, so no worries about * not doing enough work to reclaim memory from extent maps. * We can also be repeatedly called with the same nr_to_scan value * simply because the shrinker runs asynchronously and multiple calls * to this function are made before the shrinker does enough progress. * * That's why we set the atomic counter to nr_to_scan only if its * current value is zero, instead of incrementing the counter by * nr_to_scan. */ if (atomic64_cmpxchg(&fs_info->em_shrinker_nr_to_scan, 0, nr_to_scan) != 0) return; queue_work(system_unbound_wq, &fs_info->em_shrinker_work); } void btrfs_init_extent_map_shrinker_work(struct btrfs_fs_info *fs_info) { atomic64_set(&fs_info->em_shrinker_nr_to_scan, 0); INIT_WORK(&fs_info->em_shrinker_work, btrfs_extent_map_shrinker_worker); } |
| 25 12 12 1 11 13 13 23 12 24 27 26 28 14 1 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | // SPDX-License-Identifier: GPL-2.0 #include <linux/file.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/utime.h> #include <linux/syscalls.h> #include <linux/uaccess.h> #include <linux/compat.h> #include <asm/unistd.h> #include <linux/filelock.h> static bool nsec_valid(long nsec) { if (nsec == UTIME_OMIT || nsec == UTIME_NOW) return true; return nsec >= 0 && nsec <= 999999999; } int vfs_utimes(const struct path *path, struct timespec64 *times) { int error; struct iattr newattrs; struct inode *inode = path->dentry->d_inode; struct inode *delegated_inode = NULL; if (times) { if (!nsec_valid(times[0].tv_nsec) || !nsec_valid(times[1].tv_nsec)) return -EINVAL; if (times[0].tv_nsec == UTIME_NOW && times[1].tv_nsec == UTIME_NOW) times = NULL; } error = mnt_want_write(path->mnt); if (error) goto out; newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME; if (times) { if (times[0].tv_nsec == UTIME_OMIT) newattrs.ia_valid &= ~ATTR_ATIME; else if (times[0].tv_nsec != UTIME_NOW) { newattrs.ia_atime = times[0]; newattrs.ia_valid |= ATTR_ATIME_SET; } if (times[1].tv_nsec == UTIME_OMIT) newattrs.ia_valid &= ~ATTR_MTIME; else if (times[1].tv_nsec != UTIME_NOW) { newattrs.ia_mtime = times[1]; newattrs.ia_valid |= ATTR_MTIME_SET; } /* * Tell setattr_prepare(), that this is an explicit time * update, even if neither ATTR_ATIME_SET nor ATTR_MTIME_SET * were used. */ newattrs.ia_valid |= ATTR_TIMES_SET; } else { newattrs.ia_valid |= ATTR_TOUCH; } retry_deleg: inode_lock(inode); error = notify_change(mnt_idmap(path->mnt), path->dentry, &newattrs, &delegated_inode); inode_unlock(inode); if (delegated_inode) { error = break_deleg_wait(&delegated_inode); if (!error) goto retry_deleg; } mnt_drop_write(path->mnt); out: return error; } static int do_utimes_path(int dfd, const char __user *filename, struct timespec64 *times, int flags) { struct path path; int lookup_flags = 0, error; if (flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) return -EINVAL; if (!(flags & AT_SYMLINK_NOFOLLOW)) lookup_flags |= LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) lookup_flags |= LOOKUP_EMPTY; retry: error = user_path_at(dfd, filename, lookup_flags, &path); if (error) return error; error = vfs_utimes(&path, times); path_put(&path); if (retry_estale(error, lookup_flags)) { lookup_flags |= LOOKUP_REVAL; goto retry; } return error; } static int do_utimes_fd(int fd, struct timespec64 *times, int flags) { if (flags) return -EINVAL; CLASS(fd, f)(fd); if (fd_empty(f)) return -EBADF; return vfs_utimes(&fd_file(f)->f_path, times); } /* * do_utimes - change times on filename or file descriptor * @dfd: open file descriptor, -1 or AT_FDCWD * @filename: path name or NULL * @times: new times or NULL * @flags: zero or more flags (only AT_SYMLINK_NOFOLLOW for the moment) * * If filename is NULL and dfd refers to an open file, then operate on * the file. Otherwise look up filename, possibly using dfd as a * starting point. * * If times==NULL, set access and modification to current time, * must be owner or have write permission. * Else, update from *times, must be owner or super user. */ long do_utimes(int dfd, const char __user *filename, struct timespec64 *times, int flags) { if (filename == NULL && dfd != AT_FDCWD) return do_utimes_fd(dfd, times, flags); return do_utimes_path(dfd, filename, times, flags); } SYSCALL_DEFINE4(utimensat, int, dfd, const char __user *, filename, struct __kernel_timespec __user *, utimes, int, flags) { struct timespec64 tstimes[2]; if (utimes) { if ((get_timespec64(&tstimes[0], &utimes[0]) || get_timespec64(&tstimes[1], &utimes[1]))) return -EFAULT; /* Nothing to do, we must not even check the path. */ if (tstimes[0].tv_nsec == UTIME_OMIT && tstimes[1].tv_nsec == UTIME_OMIT) return 0; } return do_utimes(dfd, filename, utimes ? tstimes : NULL, flags); } #ifdef __ARCH_WANT_SYS_UTIME /* * futimesat(), utimes() and utime() are older versions of utimensat() * that are provided for compatibility with traditional C libraries. * On modern architectures, we always use libc wrappers around * utimensat() instead. */ static long do_futimesat(int dfd, const char __user *filename, struct __kernel_old_timeval __user *utimes) { struct __kernel_old_timeval times[2]; struct timespec64 tstimes[2]; if (utimes) { if (copy_from_user(×, utimes, sizeof(times))) return -EFAULT; /* This test is needed to catch all invalid values. If we would test only in do_utimes we would miss those invalid values truncated by the multiplication with 1000. Note that we also catch UTIME_{NOW,OMIT} here which are only valid for utimensat. */ if (times[0].tv_usec >= 1000000 || times[0].tv_usec < 0 || times[1].tv_usec >= 1000000 || times[1].tv_usec < 0) return -EINVAL; tstimes[0].tv_sec = times[0].tv_sec; tstimes[0].tv_nsec = 1000 * times[0].tv_usec; tstimes[1].tv_sec = times[1].tv_sec; tstimes[1].tv_nsec = 1000 * times[1].tv_usec; } return do_utimes(dfd, filename, utimes ? tstimes : NULL, 0); } SYSCALL_DEFINE3(futimesat, int, dfd, const char __user *, filename, struct __kernel_old_timeval __user *, utimes) { return do_futimesat(dfd, filename, utimes); } SYSCALL_DEFINE2(utimes, char __user *, filename, struct __kernel_old_timeval __user *, utimes) { return do_futimesat(AT_FDCWD, filename, utimes); } SYSCALL_DEFINE2(utime, char __user *, filename, struct utimbuf __user *, times) { struct timespec64 tv[2]; if (times) { if (get_user(tv[0].tv_sec, ×->actime) || get_user(tv[1].tv_sec, ×->modtime)) return -EFAULT; tv[0].tv_nsec = 0; tv[1].tv_nsec = 0; } return do_utimes(AT_FDCWD, filename, times ? tv : NULL, 0); } #endif #ifdef CONFIG_COMPAT_32BIT_TIME /* * Not all architectures have sys_utime, so implement this in terms * of sys_utimes. */ #ifdef __ARCH_WANT_SYS_UTIME32 SYSCALL_DEFINE2(utime32, const char __user *, filename, struct old_utimbuf32 __user *, t) { struct timespec64 tv[2]; if (t) { if (get_user(tv[0].tv_sec, &t->actime) || get_user(tv[1].tv_sec, &t->modtime)) return -EFAULT; tv[0].tv_nsec = 0; tv[1].tv_nsec = 0; } return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0); } #endif SYSCALL_DEFINE4(utimensat_time32, unsigned int, dfd, const char __user *, filename, struct old_timespec32 __user *, t, int, flags) { struct timespec64 tv[2]; if (t) { if (get_old_timespec32(&tv[0], &t[0]) || get_old_timespec32(&tv[1], &t[1])) return -EFAULT; if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT) return 0; } return do_utimes(dfd, filename, t ? tv : NULL, flags); } #ifdef __ARCH_WANT_SYS_UTIME32 static long do_compat_futimesat(unsigned int dfd, const char __user *filename, struct old_timeval32 __user *t) { struct timespec64 tv[2]; if (t) { if (get_user(tv[0].tv_sec, &t[0].tv_sec) || get_user(tv[0].tv_nsec, &t[0].tv_usec) || get_user(tv[1].tv_sec, &t[1].tv_sec) || get_user(tv[1].tv_nsec, &t[1].tv_usec)) return -EFAULT; if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 || tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0) return -EINVAL; tv[0].tv_nsec *= 1000; tv[1].tv_nsec *= 1000; } return do_utimes(dfd, filename, t ? tv : NULL, 0); } SYSCALL_DEFINE3(futimesat_time32, unsigned int, dfd, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(dfd, filename, t); } SYSCALL_DEFINE2(utimes_time32, const char __user *, filename, struct old_timeval32 __user *, t) { return do_compat_futimesat(AT_FDCWD, filename, t); } #endif #endif |
| 936 933 3 934 940 937 941 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/extable.h> #include <linux/uaccess.h> #include <linux/sched/debug.h> #include <linux/bitfield.h> #include <xen/xen.h> #include <asm/fpu/api.h> #include <asm/fred.h> #include <asm/sev.h> #include <asm/traps.h> #include <asm/kdebug.h> #include <asm/insn-eval.h> #include <asm/sgx.h> static inline unsigned long *pt_regs_nr(struct pt_regs *regs, int nr) { int reg_offset = pt_regs_offset(regs, nr); static unsigned long __dummy; if (WARN_ON_ONCE(reg_offset < 0)) return &__dummy; return (unsigned long *)((unsigned long)regs + reg_offset); } static inline unsigned long ex_fixup_addr(const struct exception_table_entry *x) { return (unsigned long)&x->fixup + x->fixup; } static bool ex_handler_default(const struct exception_table_entry *e, struct pt_regs *regs) { if (e->data & EX_FLAG_CLEAR_AX) regs->ax = 0; if (e->data & EX_FLAG_CLEAR_DX) regs->dx = 0; regs->ip = ex_fixup_addr(e); return true; } /* * This is the *very* rare case where we do a "load_unaligned_zeropad()" * and it's a page crosser into a non-existent page. * * This happens when we optimistically load a pathname a word-at-a-time * and the name is less than the full word and the next page is not * mapped. Typically that only happens for CONFIG_DEBUG_PAGEALLOC. * * NOTE! The faulting address is always a 'mov mem,reg' type instruction * of size 'long', and the exception fixup must always point to right * after the instruction. */ static bool ex_handler_zeropad(const struct exception_table_entry *e, struct pt_regs *regs, unsigned long fault_addr) { struct insn insn; const unsigned long mask = sizeof(long) - 1; unsigned long offset, addr, next_ip, len; unsigned long *reg; next_ip = ex_fixup_addr(e); len = next_ip - regs->ip; if (len > MAX_INSN_SIZE) return false; if (insn_decode(&insn, (void *) regs->ip, len, INSN_MODE_KERN)) return false; if (insn.length != len) return false; if (insn.opcode.bytes[0] != 0x8b) return false; if (insn.opnd_bytes != sizeof(long)) return false; addr = (unsigned long) insn_get_addr_ref(&insn, regs); if (addr == ~0ul) return false; offset = addr & mask; addr = addr & ~mask; if (fault_addr != addr + sizeof(long)) return false; reg = insn_get_modrm_reg_ptr(&insn, regs); if (!reg) return false; *reg = *(unsigned long *)addr >> (offset * 8); return ex_handler_default(e, regs); } static bool ex_handler_fault(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { regs->ax = trapnr; return ex_handler_default(fixup, regs); } static bool ex_handler_sgx(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr) { regs->ax = trapnr | SGX_ENCLS_FAULT_FLAG; return ex_handler_default(fixup, regs); } /* * Handler for when we fail to restore a task's FPU state. We should never get * here because the FPU state of a task using the FPU (struct fpu::fpstate) * should always be valid. However, past bugs have allowed userspace to set * reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn(). * These caused XRSTOR to fail when switching to the task, leaking the FPU * registers of the task previously executing on the CPU. Mitigate this class * of vulnerability by restoring from the initial state (essentially, zeroing * out all the FPU registers) if we can't restore from the task's FPU state. */ static bool ex_handler_fprestore(const struct exception_table_entry *fixup, struct pt_regs *regs) { WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.", (void *)instruction_pointer(regs)); fpu_reset_from_exception_fixup(); return ex_handler_default(fixup, regs); } /* * On x86-64, we end up being imprecise with 'access_ok()', and allow * non-canonical user addresses to make the range comparisons simpler, * and to not have to worry about LAM being enabled. * * In fact, we allow up to one page of "slop" at the sign boundary, * which means that we can do access_ok() by just checking the sign * of the pointer for the common case of having a small access size. */ static bool gp_fault_address_ok(unsigned long fault_address) { #ifdef CONFIG_X86_64 /* Is it in the "user space" part of the non-canonical space? */ if (valid_user_address(fault_address)) return true; /* .. or just above it? */ fault_address -= PAGE_SIZE; if (valid_user_address(fault_address)) return true; #endif return false; } static bool ex_handler_uaccess(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long fault_address) { WARN_ONCE(trapnr == X86_TRAP_GP && !gp_fault_address_ok(fault_address), "General protection fault in user access. Non-canonical address?"); return ex_handler_default(fixup, regs); } static bool ex_handler_msr(const struct exception_table_entry *fixup, struct pt_regs *regs, bool wrmsr, bool safe, int reg) { if (__ONCE_LITE_IF(!safe && wrmsr)) { pr_warn("unchecked MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax, regs->ip, (void *)regs->ip); show_stack_regs(regs); } if (__ONCE_LITE_IF(!safe && !wrmsr)) { pr_warn("unchecked MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", (unsigned int)regs->cx, regs->ip, (void *)regs->ip); show_stack_regs(regs); } if (!wrmsr) { /* Pretend that the read succeeded and returned 0. */ regs->ax = 0; regs->dx = 0; } if (safe) *pt_regs_nr(regs, reg) = -EIO; return ex_handler_default(fixup, regs); } static bool ex_handler_clear_fs(const struct exception_table_entry *fixup, struct pt_regs *regs) { if (static_cpu_has(X86_BUG_NULL_SEG)) asm volatile ("mov %0, %%fs" : : "rm" (__USER_DS)); asm volatile ("mov %0, %%fs" : : "rm" (0)); return ex_handler_default(fixup, regs); } static bool ex_handler_imm_reg(const struct exception_table_entry *fixup, struct pt_regs *regs, int reg, int imm) { *pt_regs_nr(regs, reg) = (long)imm; return ex_handler_default(fixup, regs); } static bool ex_handler_ucopy_len(const struct exception_table_entry *fixup, struct pt_regs *regs, int trapnr, unsigned long fault_address, int reg, int imm) { regs->cx = imm * regs->cx + *pt_regs_nr(regs, reg); return ex_handler_uaccess(fixup, regs, trapnr, fault_address); } #ifdef CONFIG_X86_FRED static bool ex_handler_eretu(const struct exception_table_entry *fixup, struct pt_regs *regs, unsigned long error_code) { struct pt_regs *uregs = (struct pt_regs *)(regs->sp - offsetof(struct pt_regs, orig_ax)); unsigned short ss = uregs->ss; unsigned short cs = uregs->cs; /* * Move the NMI bit from the invalid stack frame, which caused ERETU * to fault, to the fault handler's stack frame, thus to unblock NMI * with the fault handler's ERETS instruction ASAP if NMI is blocked. */ regs->fred_ss.nmi = uregs->fred_ss.nmi; /* * Sync event information to uregs, i.e., the ERETU return frame, but * is it safe to write to the ERETU return frame which is just above * current event stack frame? * * The RSP used by FRED to push a stack frame is not the value in %rsp, * it is calculated from %rsp with the following 2 steps: * 1) RSP = %rsp - (IA32_FRED_CONFIG & 0x1c0) // Reserve N*64 bytes * 2) RSP = RSP & ~0x3f // Align to a 64-byte cache line * when an event delivery doesn't trigger a stack level change. * * Here is an example with N*64 (N=1) bytes reserved: * * 64-byte cache line ==> ______________ * |___Reserved___| * |__Event_data__| * |_____SS_______| * |_____RSP______| * |_____FLAGS____| * |_____CS_______| * |_____IP_______| * 64-byte cache line ==> |__Error_code__| <== ERETU return frame * |______________| * |______________| * |______________| * |______________| * |______________| * |______________| * |______________| * 64-byte cache line ==> |______________| <== RSP after step 1) and 2) * |___Reserved___| * |__Event_data__| * |_____SS_______| * |_____RSP______| * |_____FLAGS____| * |_____CS_______| * |_____IP_______| * 64-byte cache line ==> |__Error_code__| <== ERETS return frame * * Thus a new FRED stack frame will always be pushed below a previous * FRED stack frame ((N*64) bytes may be reserved between), and it is * safe to write to a previous FRED stack frame as they never overlap. */ fred_info(uregs)->edata = fred_event_data(regs); uregs->ssx = regs->ssx; uregs->fred_ss.ss = ss; /* The NMI bit was moved away above */ uregs->fred_ss.nmi = 0; uregs->csx = regs->csx; uregs->fred_cs.sl = 0; uregs->fred_cs.wfe = 0; uregs->cs = cs; uregs->orig_ax = error_code; return ex_handler_default(fixup, regs); } #endif int ex_get_fixup_type(unsigned long ip) { const struct exception_table_entry *e = search_exception_tables(ip); return e ? FIELD_GET(EX_DATA_TYPE_MASK, e->data) : EX_TYPE_NONE; } int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, unsigned long fault_addr) { const struct exception_table_entry *e; int type, reg, imm; #ifdef CONFIG_PNPBIOS if (unlikely(SEGMENT_IS_PNP_CODE(regs->cs))) { extern u32 pnp_bios_fault_eip, pnp_bios_fault_esp; extern u32 pnp_bios_is_utter_crap; pnp_bios_is_utter_crap = 1; printk(KERN_CRIT "PNPBIOS fault.. attempting recovery.\n"); __asm__ volatile( "movl %0, %%esp\n\t" "jmp *%1\n\t" : : "g" (pnp_bios_fault_esp), "g" (pnp_bios_fault_eip)); panic("do_trap: can't hit this"); } #endif e = search_exception_tables(regs->ip); if (!e) return 0; type = FIELD_GET(EX_DATA_TYPE_MASK, e->data); reg = FIELD_GET(EX_DATA_REG_MASK, e->data); imm = FIELD_GET(EX_DATA_IMM_MASK, e->data); switch (type) { case EX_TYPE_DEFAULT: case EX_TYPE_DEFAULT_MCE_SAFE: return ex_handler_default(e, regs); case EX_TYPE_FAULT: case EX_TYPE_FAULT_MCE_SAFE: return ex_handler_fault(e, regs, trapnr); case EX_TYPE_UACCESS: return ex_handler_uaccess(e, regs, trapnr, fault_addr); case EX_TYPE_CLEAR_FS: return ex_handler_clear_fs(e, regs); case EX_TYPE_FPU_RESTORE: return ex_handler_fprestore(e, regs); case EX_TYPE_BPF: return ex_handler_bpf(e, regs); case EX_TYPE_WRMSR: return ex_handler_msr(e, regs, true, false, reg); case EX_TYPE_RDMSR: return ex_handler_msr(e, regs, false, false, reg); case EX_TYPE_WRMSR_SAFE: return ex_handler_msr(e, regs, true, true, reg); case EX_TYPE_RDMSR_SAFE: return ex_handler_msr(e, regs, false, true, reg); case EX_TYPE_WRMSR_IN_MCE: ex_handler_msr_mce(regs, true); break; case EX_TYPE_RDMSR_IN_MCE: ex_handler_msr_mce(regs, false); break; case EX_TYPE_POP_REG: regs->sp += sizeof(long); fallthrough; case EX_TYPE_IMM_REG: return ex_handler_imm_reg(e, regs, reg, imm); case EX_TYPE_FAULT_SGX: return ex_handler_sgx(e, regs, trapnr); case EX_TYPE_UCOPY_LEN: return ex_handler_ucopy_len(e, regs, trapnr, fault_addr, reg, imm); case EX_TYPE_ZEROPAD: return ex_handler_zeropad(e, regs, fault_addr); #ifdef CONFIG_X86_FRED case EX_TYPE_ERETU: return ex_handler_eretu(e, regs, error_code); #endif } BUG(); } extern unsigned int early_recursion_flag; /* Restricted version used during very early boot */ void __init early_fixup_exception(struct pt_regs *regs, int trapnr) { /* Ignore early NMIs. */ if (trapnr == X86_TRAP_NMI) return; if (early_recursion_flag > 2) goto halt_loop; /* * Old CPUs leave the high bits of CS on the stack * undefined. I'm not sure which CPUs do this, but at least * the 486 DX works this way. * Xen pv domains are not using the default __KERNEL_CS. */ if (!xen_pv_domain() && regs->cs != __KERNEL_CS) goto fail; /* * The full exception fixup machinery is available as soon as * the early IDT is loaded. This means that it is the * responsibility of extable users to either function correctly * when handlers are invoked early or to simply avoid causing * exceptions before they're ready to handle them. * * This is better than filtering which handlers can be used, * because refusing to call a handler here is guaranteed to * result in a hard-to-debug panic. * * Keep in mind that not all vectors actually get here. Early * page faults, for example, are special. */ if (fixup_exception(regs, trapnr, regs->orig_ax, 0)) return; if (trapnr == X86_TRAP_UD) { if (report_bug(regs->ip, regs) == BUG_TRAP_TYPE_WARN) { /* Skip the ud2. */ regs->ip += LEN_UD2; return; } /* * If this was a BUG and report_bug returns or if this * was just a normal #UD, we want to continue onward and * crash. */ } fail: early_printk("PANIC: early exception 0x%02x IP %lx:%lx error %lx cr2 0x%lx\n", (unsigned)trapnr, (unsigned long)regs->cs, regs->ip, regs->orig_ax, read_cr2()); show_regs(regs); halt_loop: while (true) halt(); } |
| 8 100 95 3 8 67 8 167 70 3 167 14 73 31 3 74 1 87 4 1 87 9 86 26 3 2 26 26 62 3 7 60 2 3 2 62 3 60 62 62 3 2 5 7 1 2 5 7 5 2 2 5 7 59 203 6 153 49 3 2 1 200 14 66 13 2 35 3 13 48 30 18 37 1 6 30 30 6 198 56 190 136 1 117 117 6 111 7 108 5 8 103 30 91 91 201 201 143 111 110 6 1 5 5 31 1 12 18 1 18 15 4 2 11 11 8 1 7 3 4 1 3 18 1 2 1 1 1 2 8 4 1 1 6 2 8 8 1 17 1 4 8 1 18 9 16 1 9 7 3 32 1 31 7 21 2 7 14 16 1 4 14 7 11 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2012-2013 Samsung Electronics Co., Ltd. */ #include <linux/iversion.h> #include <linux/namei.h> #include <linux/slab.h> #include <linux/buffer_head.h> #include <linux/nls.h> #include "exfat_raw.h" #include "exfat_fs.h" static inline unsigned long exfat_d_version(struct dentry *dentry) { return (unsigned long) dentry->d_fsdata; } static inline void exfat_d_version_set(struct dentry *dentry, unsigned long version) { dentry->d_fsdata = (void *) version; } /* * If new entry was created in the parent, it could create the 8.3 alias (the * shortname of logname). So, the parent may have the negative-dentry which * matches the created 8.3 alias. * * If it happened, the negative dentry isn't actually negative anymore. So, * drop it. */ static int exfat_d_revalidate(struct inode *dir, const struct qstr *name, struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; /* * This is not negative dentry. Always valid. * * Note, rename() to existing directory entry will have ->d_inode, and * will use existing name which isn't specified name by user. * * We may be able to drop this positive dentry here. But dropping * positive dentry isn't good idea. So it's unsupported like * rename("filename", "FILENAME") for now. */ if (d_really_is_positive(dentry)) return 1; /* * Drop the negative dentry, in order to make sure to use the case * sensitive name which is specified by user if this is for creation. */ if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; return inode_eq_iversion(dir, exfat_d_version(dentry)); } /* returns the length of a struct qstr, ignoring trailing dots if necessary */ static unsigned int exfat_striptail_len(unsigned int len, const char *name, bool keep_last_dots) { if (!keep_last_dots) { while (len && name[len - 1] == '.') len--; } return len; } /* * Compute the hash for the exfat name corresponding to the dentry. If the name * is invalid, we leave the hash code unchanged so that the existing dentry can * be used. The exfat fs routines will return ENOENT or EINVAL as appropriate. */ static int exfat_d_hash(const struct dentry *dentry, struct qstr *qstr) { struct super_block *sb = dentry->d_sb; struct nls_table *t = EXFAT_SB(sb)->nls_io; const unsigned char *name = qstr->name; unsigned int len = exfat_striptail_len(qstr->len, qstr->name, EXFAT_SB(sb)->options.keep_last_dots); unsigned long hash = init_name_hash(dentry); int i, charlen; wchar_t c; for (i = 0; i < len; i += charlen) { charlen = t->char2uni(&name[i], len - i, &c); if (charlen < 0) return charlen; hash = partial_name_hash(exfat_toupper(sb, c), hash); } qstr->hash = end_name_hash(hash); return 0; } static int exfat_d_cmp(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { struct super_block *sb = dentry->d_sb; struct nls_table *t = EXFAT_SB(sb)->nls_io; unsigned int alen = exfat_striptail_len(name->len, name->name, EXFAT_SB(sb)->options.keep_last_dots); unsigned int blen = exfat_striptail_len(len, str, EXFAT_SB(sb)->options.keep_last_dots); wchar_t c1, c2; int charlen, i; if (alen != blen) return 1; for (i = 0; i < len; i += charlen) { charlen = t->char2uni(&name->name[i], alen - i, &c1); if (charlen < 0) return 1; if (charlen != t->char2uni(&str[i], blen - i, &c2)) return 1; if (exfat_toupper(sb, c1) != exfat_toupper(sb, c2)) return 1; } return 0; } const struct dentry_operations exfat_dentry_ops = { .d_revalidate = exfat_d_revalidate, .d_hash = exfat_d_hash, .d_compare = exfat_d_cmp, }; static int exfat_utf8_d_hash(const struct dentry *dentry, struct qstr *qstr) { struct super_block *sb = dentry->d_sb; const unsigned char *name = qstr->name; unsigned int len = exfat_striptail_len(qstr->len, qstr->name, EXFAT_SB(sb)->options.keep_last_dots); unsigned long hash = init_name_hash(dentry); int i, charlen; unicode_t u; for (i = 0; i < len; i += charlen) { charlen = utf8_to_utf32(&name[i], len - i, &u); if (charlen < 0) return charlen; /* * exfat_toupper() works only for code points up to the U+FFFF. */ hash = partial_name_hash(u <= 0xFFFF ? exfat_toupper(sb, u) : u, hash); } qstr->hash = end_name_hash(hash); return 0; } static int exfat_utf8_d_cmp(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { struct super_block *sb = dentry->d_sb; unsigned int alen = exfat_striptail_len(name->len, name->name, EXFAT_SB(sb)->options.keep_last_dots); unsigned int blen = exfat_striptail_len(len, str, EXFAT_SB(sb)->options.keep_last_dots); unicode_t u_a, u_b; int charlen, i; if (alen != blen) return 1; for (i = 0; i < alen; i += charlen) { charlen = utf8_to_utf32(&name->name[i], alen - i, &u_a); if (charlen < 0) return 1; if (charlen != utf8_to_utf32(&str[i], blen - i, &u_b)) return 1; if (u_a <= 0xFFFF && u_b <= 0xFFFF) { if (exfat_toupper(sb, u_a) != exfat_toupper(sb, u_b)) return 1; } else { if (u_a != u_b) return 1; } } return 0; } const struct dentry_operations exfat_utf8_dentry_ops = { .d_revalidate = exfat_d_revalidate, .d_hash = exfat_utf8_d_hash, .d_compare = exfat_utf8_d_cmp, }; /* search EMPTY CONTINUOUS "num_entries" entries */ static int exfat_search_empty_slot(struct super_block *sb, struct exfat_hint_femp *hint_femp, struct exfat_chain *p_dir, int num_entries, struct exfat_entry_set_cache *es) { int i, dentry, ret; int dentries_per_clu; struct exfat_chain clu; struct exfat_sb_info *sbi = EXFAT_SB(sb); int total_entries = EXFAT_CLU_TO_DEN(p_dir->size, sbi); dentries_per_clu = sbi->dentries_per_clu; if (hint_femp->eidx != EXFAT_HINT_NONE) { dentry = hint_femp->eidx; /* * If hint_femp->count is enough, it is needed to check if * there are actual empty entries. * Otherwise, and if "dentry + hint_famp->count" is also equal * to "p_dir->size * dentries_per_clu", it means ENOSPC. */ if (dentry + hint_femp->count == total_entries && num_entries > hint_femp->count) return -ENOSPC; hint_femp->eidx = EXFAT_HINT_NONE; exfat_chain_dup(&clu, &hint_femp->cur); } else { exfat_chain_dup(&clu, p_dir); dentry = 0; } while (dentry + num_entries <= total_entries && clu.dir != EXFAT_EOF_CLUSTER) { i = dentry & (dentries_per_clu - 1); ret = exfat_get_empty_dentry_set(es, sb, &clu, i, num_entries); if (ret < 0) return ret; else if (ret == 0) return dentry; dentry += ret; i += ret; while (i >= dentries_per_clu) { if (clu.flags == ALLOC_NO_FAT_CHAIN) { if (--clu.size > 0) clu.dir++; else clu.dir = EXFAT_EOF_CLUSTER; } else { if (exfat_get_next_cluster(sb, &clu.dir)) return -EIO; } i -= dentries_per_clu; } } hint_femp->eidx = dentry; hint_femp->count = 0; if (dentry == total_entries || clu.dir == EXFAT_EOF_CLUSTER) exfat_chain_set(&hint_femp->cur, EXFAT_EOF_CLUSTER, 0, clu.flags); else hint_femp->cur = clu; return -ENOSPC; } static int exfat_check_max_dentries(struct inode *inode) { if (EXFAT_B_TO_DEN(i_size_read(inode)) >= MAX_EXFAT_DENTRIES) { /* * exFAT spec allows a dir to grow up to 8388608(256MB) * dentries */ return -ENOSPC; } return 0; } /* * Find an empty directory entry set. * * If there isn't any empty slot, expand cluster chain. * * in: * inode: inode of the parent directory * num_entries: specifies how many dentries in the empty directory entry set * * out: * p_dir: the cluster where the empty directory entry set is located * es: The found empty directory entry set * * return: * the directory entry index in p_dir is returned on succeeds * -error code is returned on failure */ static int exfat_find_empty_entry(struct inode *inode, struct exfat_chain *p_dir, int num_entries, struct exfat_entry_set_cache *es) { int dentry; unsigned int ret, last_clu; loff_t size = 0; struct exfat_chain clu; struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); struct exfat_hint_femp hint_femp; hint_femp.eidx = EXFAT_HINT_NONE; if (ei->hint_femp.eidx != EXFAT_HINT_NONE) { hint_femp = ei->hint_femp; ei->hint_femp.eidx = EXFAT_HINT_NONE; } exfat_chain_set(p_dir, ei->start_clu, EXFAT_B_TO_CLU(i_size_read(inode), sbi), ei->flags); while ((dentry = exfat_search_empty_slot(sb, &hint_femp, p_dir, num_entries, es)) < 0) { if (dentry != -ENOSPC) return dentry; if (exfat_check_max_dentries(inode)) return -ENOSPC; /* * Allocate new cluster to this directory */ if (ei->start_clu != EXFAT_EOF_CLUSTER) { /* we trust p_dir->size regardless of FAT type */ if (exfat_find_last_cluster(sb, p_dir, &last_clu)) return -EIO; exfat_chain_set(&clu, last_clu + 1, 0, p_dir->flags); } else { /* This directory is empty */ exfat_chain_set(&clu, EXFAT_EOF_CLUSTER, 0, ALLOC_NO_FAT_CHAIN); } /* allocate a cluster */ ret = exfat_alloc_cluster(inode, 1, &clu, IS_DIRSYNC(inode)); if (ret) return ret; if (exfat_zeroed_cluster(inode, clu.dir)) return -EIO; if (ei->start_clu == EXFAT_EOF_CLUSTER) { ei->start_clu = clu.dir; p_dir->dir = clu.dir; hint_femp.eidx = 0; } /* append to the FAT chain */ if (clu.flags != p_dir->flags) { /* no-fat-chain bit is disabled, * so fat-chain should be synced with alloc-bitmap */ exfat_chain_cont_cluster(sb, p_dir->dir, p_dir->size); p_dir->flags = ALLOC_FAT_CHAIN; hint_femp.cur.flags = ALLOC_FAT_CHAIN; } if (clu.flags == ALLOC_FAT_CHAIN) if (exfat_ent_set(sb, last_clu, clu.dir)) return -EIO; if (hint_femp.cur.dir == EXFAT_EOF_CLUSTER) exfat_chain_set(&hint_femp.cur, clu.dir, 0, clu.flags); hint_femp.count += sbi->dentries_per_clu; hint_femp.cur.size++; p_dir->size++; size = EXFAT_CLU_TO_B(p_dir->size, sbi); /* directory inode should be updated in here */ i_size_write(inode, size); ei->valid_size += sbi->cluster_size; ei->flags = p_dir->flags; inode->i_blocks += sbi->cluster_size >> 9; } p_dir->dir = exfat_sector_to_cluster(sbi, es->bh[0]->b_blocknr); p_dir->size -= dentry / sbi->dentries_per_clu; return dentry & (sbi->dentries_per_clu - 1); } /* * Name Resolution Functions : * Zero if it was successful; otherwise nonzero. */ static int __exfat_resolve_path(struct inode *inode, const unsigned char *path, struct exfat_uni_name *p_uniname, int lookup) { int namelen; int lossy = NLS_NAME_NO_LOSSY; struct super_block *sb = inode->i_sb; int pathlen = strlen(path); /* * get the length of the pathname excluding * trailing periods, if any. */ namelen = exfat_striptail_len(pathlen, path, false); if (EXFAT_SB(sb)->options.keep_last_dots) { /* * Do not allow the creation of files with names * ending with period(s). */ if (!lookup && (namelen < pathlen)) return -EINVAL; namelen = pathlen; } if (!namelen) return -ENOENT; if (pathlen > (MAX_NAME_LENGTH * MAX_CHARSET_SIZE)) return -ENAMETOOLONG; /* * strip all leading spaces : * "MS windows 7" supports leading spaces. * So we should skip this preprocessing for compatibility. */ /* file name conversion : * If lookup case, we allow bad-name for compatibility. */ namelen = exfat_nls_to_utf16(sb, path, namelen, p_uniname, &lossy); if (namelen < 0) return namelen; /* return error value */ if ((lossy && !lookup) || !namelen) return (lossy & NLS_NAME_OVERLEN) ? -ENAMETOOLONG : -EINVAL; return 0; } static inline int exfat_resolve_path(struct inode *inode, const unsigned char *path, struct exfat_uni_name *uni) { return __exfat_resolve_path(inode, path, uni, 0); } static inline int exfat_resolve_path_for_lookup(struct inode *inode, const unsigned char *path, struct exfat_uni_name *uni) { return __exfat_resolve_path(inode, path, uni, 1); } static inline loff_t exfat_make_i_pos(struct exfat_dir_entry *info) { return ((loff_t) info->dir.dir << 32) | (info->entry & 0xffffffff); } static int exfat_add_entry(struct inode *inode, const char *path, unsigned int type, struct exfat_dir_entry *info) { int ret, dentry, num_entries; struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_uni_name uniname; struct exfat_chain clu; struct timespec64 ts = current_time(inode); struct exfat_entry_set_cache es; int clu_size = 0; unsigned int start_clu = EXFAT_FREE_CLUSTER; ret = exfat_resolve_path(inode, path, &uniname); if (ret) goto out; num_entries = exfat_calc_num_entries(&uniname); if (num_entries < 0) { ret = num_entries; goto out; } /* exfat_find_empty_entry must be called before alloc_cluster() */ dentry = exfat_find_empty_entry(inode, &info->dir, num_entries, &es); if (dentry < 0) { ret = dentry; /* -EIO or -ENOSPC */ goto out; } if (type == TYPE_DIR && !sbi->options.zero_size_dir) { ret = exfat_alloc_new_dir(inode, &clu); if (ret) { exfat_put_dentry_set(&es, false); goto out; } start_clu = clu.dir; clu_size = sbi->cluster_size; } /* update the directory entry */ /* fill the dos name directory entry information of the created file. * the first cluster is not determined yet. (0) */ exfat_init_dir_entry(&es, type, start_clu, clu_size, &ts); exfat_init_ext_entry(&es, num_entries, &uniname); ret = exfat_put_dentry_set(&es, IS_DIRSYNC(inode)); if (ret) goto out; info->entry = dentry; info->flags = ALLOC_NO_FAT_CHAIN; info->type = type; if (type == TYPE_FILE) { info->attr = EXFAT_ATTR_ARCHIVE; info->start_clu = EXFAT_EOF_CLUSTER; info->size = 0; info->num_subdirs = 0; } else { info->attr = EXFAT_ATTR_SUBDIR; if (sbi->options.zero_size_dir) info->start_clu = EXFAT_EOF_CLUSTER; else info->start_clu = start_clu; info->size = clu_size; info->num_subdirs = EXFAT_MIN_SUBDIR; } info->valid_size = info->size; memset(&info->crtime, 0, sizeof(info->crtime)); memset(&info->mtime, 0, sizeof(info->mtime)); memset(&info->atime, 0, sizeof(info->atime)); out: return ret; } static int exfat_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode; struct exfat_dir_entry info; loff_t i_pos; int err; loff_t size = i_size_read(dir); if (unlikely(exfat_forced_shutdown(sb))) return -EIO; mutex_lock(&EXFAT_SB(sb)->s_lock); exfat_set_volume_dirty(sb); err = exfat_add_entry(dir, dentry->d_name.name, TYPE_FILE, &info); if (err) goto unlock; inode_inc_iversion(dir); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); if (IS_DIRSYNC(dir) && size != i_size_read(dir)) exfat_sync_inode(dir); else mark_inode_dirty(dir); i_pos = exfat_make_i_pos(&info); inode = exfat_build_inode(sb, &info, i_pos); err = PTR_ERR_OR_ZERO(inode); if (err) goto unlock; inode_inc_iversion(inode); EXFAT_I(inode)->i_crtime = simple_inode_init_ts(inode); exfat_truncate_inode_atime(inode); /* timestamp is already written, so mark_inode_dirty() is unneeded. */ d_instantiate(dentry, inode); unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); return err; } /* lookup a file */ static int exfat_find(struct inode *dir, struct qstr *qname, struct exfat_dir_entry *info) { int ret, dentry, count; struct exfat_chain cdir; struct exfat_uni_name uni_name; struct super_block *sb = dir->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(dir); struct exfat_dentry *ep, *ep2; struct exfat_entry_set_cache es; /* for optimized dir & entry to prevent long traverse of cluster chain */ struct exfat_hint hint_opt; if (qname->len == 0) return -ENOENT; /* check the validity of directory name in the given pathname */ ret = exfat_resolve_path_for_lookup(dir, qname->name, &uni_name); if (ret) return ret; exfat_chain_set(&cdir, ei->start_clu, EXFAT_B_TO_CLU(i_size_read(dir), sbi), ei->flags); /* check the validation of hint_stat and initialize it if required */ if (ei->version != (inode_peek_iversion_raw(dir) & 0xffffffff)) { ei->hint_stat.clu = cdir.dir; ei->hint_stat.eidx = 0; ei->version = (inode_peek_iversion_raw(dir) & 0xffffffff); ei->hint_femp.eidx = EXFAT_HINT_NONE; } /* search the file name for directories */ dentry = exfat_find_dir_entry(sb, ei, &cdir, &uni_name, &hint_opt); if (dentry < 0) return dentry; /* -error value */ /* adjust cdir to the optimized value */ cdir.dir = hint_opt.clu; if (cdir.flags & ALLOC_NO_FAT_CHAIN) cdir.size -= dentry / sbi->dentries_per_clu; dentry = hint_opt.eidx; info->dir = cdir; info->entry = dentry; info->num_subdirs = 0; if (exfat_get_dentry_set(&es, sb, &cdir, dentry, ES_2_ENTRIES)) return -EIO; ep = exfat_get_dentry_cached(&es, ES_IDX_FILE); ep2 = exfat_get_dentry_cached(&es, ES_IDX_STREAM); info->type = exfat_get_entry_type(ep); info->attr = le16_to_cpu(ep->dentry.file.attr); info->size = le64_to_cpu(ep2->dentry.stream.valid_size); info->valid_size = le64_to_cpu(ep2->dentry.stream.valid_size); info->size = le64_to_cpu(ep2->dentry.stream.size); if (unlikely(EXFAT_B_TO_CLU_ROUND_UP(info->size, sbi) > sbi->used_clusters)) { exfat_fs_error(sb, "data size is invalid(%lld)", info->size); return -EIO; } info->start_clu = le32_to_cpu(ep2->dentry.stream.start_clu); if (!is_valid_cluster(sbi, info->start_clu) && info->size) { exfat_warn(sb, "start_clu is invalid cluster(0x%x)", info->start_clu); info->size = 0; info->valid_size = 0; } if (info->valid_size > info->size) { exfat_warn(sb, "valid_size(%lld) is greater than size(%lld)", info->valid_size, info->size); info->valid_size = info->size; } if (info->size == 0) { info->flags = ALLOC_NO_FAT_CHAIN; info->start_clu = EXFAT_EOF_CLUSTER; } else info->flags = ep2->dentry.stream.flags; exfat_get_entry_time(sbi, &info->crtime, ep->dentry.file.create_tz, ep->dentry.file.create_time, ep->dentry.file.create_date, ep->dentry.file.create_time_cs); exfat_get_entry_time(sbi, &info->mtime, ep->dentry.file.modify_tz, ep->dentry.file.modify_time, ep->dentry.file.modify_date, ep->dentry.file.modify_time_cs); exfat_get_entry_time(sbi, &info->atime, ep->dentry.file.access_tz, ep->dentry.file.access_time, ep->dentry.file.access_date, 0); exfat_put_dentry_set(&es, false); if (ei->start_clu == EXFAT_FREE_CLUSTER) { exfat_fs_error(sb, "non-zero size file starts with zero cluster (size : %llu, p_dir : %u, entry : 0x%08x)", i_size_read(dir), ei->dir.dir, ei->entry); return -EIO; } if (info->type == TYPE_DIR) { exfat_chain_set(&cdir, info->start_clu, EXFAT_B_TO_CLU(info->size, sbi), info->flags); count = exfat_count_dir_entries(sb, &cdir); if (count < 0) return -EIO; info->num_subdirs = count + EXFAT_MIN_SUBDIR; } return 0; } static int exfat_d_anon_disconn(struct dentry *dentry) { return IS_ROOT(dentry) && (dentry->d_flags & DCACHE_DISCONNECTED); } static struct dentry *exfat_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct super_block *sb = dir->i_sb; struct inode *inode; struct dentry *alias; struct exfat_dir_entry info; int err; loff_t i_pos; mode_t i_mode; mutex_lock(&EXFAT_SB(sb)->s_lock); err = exfat_find(dir, &dentry->d_name, &info); if (err) { if (err == -ENOENT) { inode = NULL; goto out; } goto unlock; } i_pos = exfat_make_i_pos(&info); inode = exfat_build_inode(sb, &info, i_pos); err = PTR_ERR_OR_ZERO(inode); if (err) goto unlock; i_mode = inode->i_mode; alias = d_find_alias(inode); /* * Checking "alias->d_parent == dentry->d_parent" to make sure * FS is not corrupted (especially double linked dir). */ if (alias && alias->d_parent == dentry->d_parent && !exfat_d_anon_disconn(alias)) { /* * Unhashed alias is able to exist because of revalidate() * called by lookup_fast. You can easily make this status * by calling create and lookup concurrently * In such case, we reuse an alias instead of new dentry */ if (d_unhashed(alias)) { WARN_ON(alias->d_name.hash_len != dentry->d_name.hash_len); exfat_info(sb, "rehashed a dentry(%p) in read lookup", alias); d_drop(dentry); d_rehash(alias); } else if (!S_ISDIR(i_mode)) { /* * This inode has non anonymous-DCACHE_DISCONNECTED * dentry. This means, the user did ->lookup() by an * another name (longname vs 8.3 alias of it) in past. * * Switch to new one for reason of locality if possible. */ d_move(alias, dentry); } iput(inode); mutex_unlock(&EXFAT_SB(sb)->s_lock); return alias; } dput(alias); out: mutex_unlock(&EXFAT_SB(sb)->s_lock); if (!inode) exfat_d_version_set(dentry, inode_query_iversion(dir)); return d_splice_alias(inode, dentry); unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); return ERR_PTR(err); } /* remove an entry, BUT don't truncate */ static int exfat_unlink(struct inode *dir, struct dentry *dentry) { struct super_block *sb = dir->i_sb; struct inode *inode = dentry->d_inode; struct exfat_inode_info *ei = EXFAT_I(inode); struct exfat_entry_set_cache es; int err = 0; if (unlikely(exfat_forced_shutdown(sb))) return -EIO; mutex_lock(&EXFAT_SB(sb)->s_lock); if (ei->dir.dir == DIR_DELETED) { exfat_err(sb, "abnormal access to deleted dentry"); err = -ENOENT; goto unlock; } err = exfat_get_dentry_set_by_ei(&es, sb, ei); if (err) { err = -EIO; goto unlock; } exfat_set_volume_dirty(sb); /* update the directory entry */ exfat_remove_entries(inode, &es, ES_IDX_FILE); err = exfat_put_dentry_set(&es, IS_DIRSYNC(inode)); if (err) goto unlock; /* This doesn't modify ei */ ei->dir.dir = DIR_DELETED; inode_inc_iversion(dir); simple_inode_init_ts(dir); exfat_truncate_inode_atime(dir); mark_inode_dirty(dir); clear_nlink(inode); simple_inode_init_ts(inode); exfat_truncate_inode_atime(inode); exfat_unhash_inode(inode); exfat_d_version_set(dentry, inode_query_iversion(dir)); unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); return err; } static struct dentry *exfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode; struct exfat_dir_entry info; loff_t i_pos; int err; loff_t size = i_size_read(dir); if (unlikely(exfat_forced_shutdown(sb))) return ERR_PTR(-EIO); mutex_lock(&EXFAT_SB(sb)->s_lock); exfat_set_volume_dirty(sb); err = exfat_add_entry(dir, dentry->d_name.name, TYPE_DIR, &info); if (err) goto unlock; inode_inc_iversion(dir); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); if (IS_DIRSYNC(dir) && size != i_size_read(dir)) exfat_sync_inode(dir); else mark_inode_dirty(dir); inc_nlink(dir); i_pos = exfat_make_i_pos(&info); inode = exfat_build_inode(sb, &info, i_pos); err = PTR_ERR_OR_ZERO(inode); if (err) goto unlock; inode_inc_iversion(inode); EXFAT_I(inode)->i_crtime = simple_inode_init_ts(inode); exfat_truncate_inode_atime(inode); /* timestamp is already written, so mark_inode_dirty() is unneeded. */ d_instantiate(dentry, inode); unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); return ERR_PTR(err); } static int exfat_check_dir_empty(struct super_block *sb, struct exfat_chain *p_dir) { int i, dentries_per_clu; unsigned int type; unsigned int clu_count = 0; struct exfat_chain clu; struct exfat_dentry *ep; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct buffer_head *bh; dentries_per_clu = sbi->dentries_per_clu; if (p_dir->dir == EXFAT_EOF_CLUSTER) return 0; exfat_chain_dup(&clu, p_dir); while (clu.dir != EXFAT_EOF_CLUSTER) { for (i = 0; i < dentries_per_clu; i++) { ep = exfat_get_dentry(sb, &clu, i, &bh); if (!ep) return -EIO; type = exfat_get_entry_type(ep); brelse(bh); if (type == TYPE_UNUSED) return 0; if (type != TYPE_FILE && type != TYPE_DIR) continue; return -ENOTEMPTY; } if (clu.flags == ALLOC_NO_FAT_CHAIN) { if (--clu.size > 0) clu.dir++; else clu.dir = EXFAT_EOF_CLUSTER; } else { if (exfat_get_next_cluster(sb, &(clu.dir))) return -EIO; /* break if the cluster chain includes a loop */ if (unlikely(++clu_count > EXFAT_DATA_CLUSTER_COUNT(sbi))) break; } } return 0; } static int exfat_rmdir(struct inode *dir, struct dentry *dentry) { struct inode *inode = dentry->d_inode; struct exfat_chain clu_to_free; struct super_block *sb = inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); struct exfat_inode_info *ei = EXFAT_I(inode); struct exfat_entry_set_cache es; int err; if (unlikely(exfat_forced_shutdown(sb))) return -EIO; mutex_lock(&EXFAT_SB(inode->i_sb)->s_lock); if (ei->dir.dir == DIR_DELETED) { exfat_err(sb, "abnormal access to deleted dentry"); err = -ENOENT; goto unlock; } exfat_chain_set(&clu_to_free, ei->start_clu, EXFAT_B_TO_CLU_ROUND_UP(i_size_read(inode), sbi), ei->flags); err = exfat_check_dir_empty(sb, &clu_to_free); if (err) { if (err == -EIO) exfat_err(sb, "failed to exfat_check_dir_empty : err(%d)", err); goto unlock; } err = exfat_get_dentry_set_by_ei(&es, sb, ei); if (err) { err = -EIO; goto unlock; } exfat_set_volume_dirty(sb); exfat_remove_entries(inode, &es, ES_IDX_FILE); err = exfat_put_dentry_set(&es, IS_DIRSYNC(dir)); if (err) goto unlock; ei->dir.dir = DIR_DELETED; inode_inc_iversion(dir); simple_inode_init_ts(dir); exfat_truncate_inode_atime(dir); if (IS_DIRSYNC(dir)) exfat_sync_inode(dir); else mark_inode_dirty(dir); drop_nlink(dir); clear_nlink(inode); simple_inode_init_ts(inode); exfat_truncate_inode_atime(inode); exfat_unhash_inode(inode); exfat_d_version_set(dentry, inode_query_iversion(dir)); unlock: mutex_unlock(&EXFAT_SB(inode->i_sb)->s_lock); return err; } static int exfat_rename_file(struct inode *parent_inode, struct exfat_uni_name *p_uniname, struct exfat_inode_info *ei) { int ret, num_new_entries; struct exfat_dentry *epold, *epnew; struct super_block *sb = parent_inode->i_sb; struct exfat_entry_set_cache old_es, new_es; int sync = IS_DIRSYNC(parent_inode); if (unlikely(exfat_forced_shutdown(sb))) return -EIO; num_new_entries = exfat_calc_num_entries(p_uniname); if (num_new_entries < 0) return num_new_entries; ret = exfat_get_dentry_set_by_ei(&old_es, sb, ei); if (ret) { ret = -EIO; return ret; } epold = exfat_get_dentry_cached(&old_es, ES_IDX_FILE); if (old_es.num_entries < num_new_entries) { int newentry; struct exfat_chain dir; newentry = exfat_find_empty_entry(parent_inode, &dir, num_new_entries, &new_es); if (newentry < 0) { ret = newentry; /* -EIO or -ENOSPC */ goto put_old_es; } epnew = exfat_get_dentry_cached(&new_es, ES_IDX_FILE); *epnew = *epold; if (exfat_get_entry_type(epnew) == TYPE_FILE) { epnew->dentry.file.attr |= cpu_to_le16(EXFAT_ATTR_ARCHIVE); ei->attr |= EXFAT_ATTR_ARCHIVE; } epold = exfat_get_dentry_cached(&old_es, ES_IDX_STREAM); epnew = exfat_get_dentry_cached(&new_es, ES_IDX_STREAM); *epnew = *epold; exfat_init_ext_entry(&new_es, num_new_entries, p_uniname); ret = exfat_put_dentry_set(&new_es, sync); if (ret) goto put_old_es; exfat_remove_entries(parent_inode, &old_es, ES_IDX_FILE); ei->dir = dir; ei->entry = newentry; } else { if (exfat_get_entry_type(epold) == TYPE_FILE) { epold->dentry.file.attr |= cpu_to_le16(EXFAT_ATTR_ARCHIVE); ei->attr |= EXFAT_ATTR_ARCHIVE; } exfat_remove_entries(parent_inode, &old_es, ES_IDX_FIRST_FILENAME + 1); exfat_init_ext_entry(&old_es, num_new_entries, p_uniname); } return exfat_put_dentry_set(&old_es, sync); put_old_es: exfat_put_dentry_set(&old_es, false); return ret; } static int exfat_move_file(struct inode *parent_inode, struct exfat_uni_name *p_uniname, struct exfat_inode_info *ei) { int ret, newentry, num_new_entries; struct exfat_dentry *epmov, *epnew; struct exfat_entry_set_cache mov_es, new_es; struct exfat_chain newdir; num_new_entries = exfat_calc_num_entries(p_uniname); if (num_new_entries < 0) return num_new_entries; ret = exfat_get_dentry_set_by_ei(&mov_es, parent_inode->i_sb, ei); if (ret) return -EIO; newentry = exfat_find_empty_entry(parent_inode, &newdir, num_new_entries, &new_es); if (newentry < 0) { ret = newentry; /* -EIO or -ENOSPC */ goto put_mov_es; } epmov = exfat_get_dentry_cached(&mov_es, ES_IDX_FILE); epnew = exfat_get_dentry_cached(&new_es, ES_IDX_FILE); *epnew = *epmov; if (exfat_get_entry_type(epnew) == TYPE_FILE) { epnew->dentry.file.attr |= cpu_to_le16(EXFAT_ATTR_ARCHIVE); ei->attr |= EXFAT_ATTR_ARCHIVE; } epmov = exfat_get_dentry_cached(&mov_es, ES_IDX_STREAM); epnew = exfat_get_dentry_cached(&new_es, ES_IDX_STREAM); *epnew = *epmov; exfat_init_ext_entry(&new_es, num_new_entries, p_uniname); exfat_remove_entries(parent_inode, &mov_es, ES_IDX_FILE); ei->dir = newdir; ei->entry = newentry; ret = exfat_put_dentry_set(&new_es, IS_DIRSYNC(parent_inode)); if (ret) goto put_mov_es; return exfat_put_dentry_set(&mov_es, IS_DIRSYNC(parent_inode)); put_mov_es: exfat_put_dentry_set(&mov_es, false); return ret; } /* rename or move a old file into a new file */ static int __exfat_rename(struct inode *old_parent_inode, struct exfat_inode_info *ei, struct inode *new_parent_inode, struct dentry *new_dentry) { int ret; struct exfat_uni_name uni_name; struct super_block *sb = old_parent_inode->i_sb; struct exfat_sb_info *sbi = EXFAT_SB(sb); const unsigned char *new_path = new_dentry->d_name.name; struct inode *new_inode = new_dentry->d_inode; struct exfat_inode_info *new_ei = NULL; /* check the validity of pointer parameters */ if (new_path == NULL || strlen(new_path) == 0) return -EINVAL; if (ei->dir.dir == DIR_DELETED) { exfat_err(sb, "abnormal access to deleted source dentry"); return -ENOENT; } /* check whether new dir is existing directory and empty */ if (new_inode) { ret = -EIO; new_ei = EXFAT_I(new_inode); if (new_ei->dir.dir == DIR_DELETED) { exfat_err(sb, "abnormal access to deleted target dentry"); goto out; } /* if new_inode exists, update ei */ if (S_ISDIR(new_inode->i_mode)) { struct exfat_chain new_clu; new_clu.dir = new_ei->start_clu; new_clu.size = EXFAT_B_TO_CLU_ROUND_UP(i_size_read(new_inode), sbi); new_clu.flags = new_ei->flags; ret = exfat_check_dir_empty(sb, &new_clu); if (ret) goto out; } } /* check the validity of directory name in the given new pathname */ ret = exfat_resolve_path(new_parent_inode, new_path, &uni_name); if (ret) goto out; exfat_set_volume_dirty(sb); if (new_parent_inode == old_parent_inode) ret = exfat_rename_file(new_parent_inode, &uni_name, ei); else ret = exfat_move_file(new_parent_inode, &uni_name, ei); if (!ret && new_inode) { struct exfat_entry_set_cache es; /* delete entries of new_dir */ ret = exfat_get_dentry_set_by_ei(&es, sb, new_ei); if (ret) { ret = -EIO; goto del_out; } exfat_remove_entries(new_inode, &es, ES_IDX_FILE); ret = exfat_put_dentry_set(&es, IS_DIRSYNC(new_inode)); if (ret) goto del_out; /* Free the clusters if new_inode is a dir(as if exfat_rmdir) */ if (S_ISDIR(new_inode->i_mode) && new_ei->start_clu != EXFAT_EOF_CLUSTER) { /* new_ei, new_clu_to_free */ struct exfat_chain new_clu_to_free; exfat_chain_set(&new_clu_to_free, new_ei->start_clu, EXFAT_B_TO_CLU_ROUND_UP(i_size_read(new_inode), sbi), new_ei->flags); if (exfat_free_cluster(new_inode, &new_clu_to_free)) { /* just set I/O error only */ ret = -EIO; } i_size_write(new_inode, 0); new_ei->valid_size = 0; new_ei->start_clu = EXFAT_EOF_CLUSTER; new_ei->flags = ALLOC_NO_FAT_CHAIN; } del_out: /* Update new_inode ei * Prevent syncing removed new_inode * (new_ei is already initialized above code ("if (new_inode)") */ new_ei->dir.dir = DIR_DELETED; } out: return ret; } static int exfat_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode, *new_inode; struct super_block *sb = old_dir->i_sb; loff_t i_pos; int err; loff_t size = i_size_read(new_dir); /* * The VFS already checks for existence, so for local filesystems * the RENAME_NOREPLACE implementation is equivalent to plain rename. * Don't support any other flags */ if (flags & ~RENAME_NOREPLACE) return -EINVAL; mutex_lock(&EXFAT_SB(sb)->s_lock); old_inode = old_dentry->d_inode; new_inode = new_dentry->d_inode; err = __exfat_rename(old_dir, EXFAT_I(old_inode), new_dir, new_dentry); if (err) goto unlock; inode_inc_iversion(new_dir); simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry); EXFAT_I(new_dir)->i_crtime = current_time(new_dir); exfat_truncate_inode_atime(new_dir); if (IS_DIRSYNC(new_dir) && size != i_size_read(new_dir)) exfat_sync_inode(new_dir); else mark_inode_dirty(new_dir); i_pos = ((loff_t)EXFAT_I(old_inode)->dir.dir << 32) | (EXFAT_I(old_inode)->entry & 0xffffffff); exfat_unhash_inode(old_inode); exfat_hash_inode(old_inode, i_pos); if (IS_DIRSYNC(new_dir)) exfat_sync_inode(old_inode); else mark_inode_dirty(old_inode); if (S_ISDIR(old_inode->i_mode) && old_dir != new_dir) { drop_nlink(old_dir); if (!new_inode) inc_nlink(new_dir); } inode_inc_iversion(old_dir); if (new_dir != old_dir) mark_inode_dirty(old_dir); if (new_inode) { exfat_unhash_inode(new_inode); /* skip drop_nlink if new_inode already has been dropped */ if (new_inode->i_nlink) { drop_nlink(new_inode); if (S_ISDIR(new_inode->i_mode)) drop_nlink(new_inode); } else { exfat_warn(sb, "abnormal access to an inode dropped"); WARN_ON(new_inode->i_nlink == 0); } EXFAT_I(new_inode)->i_crtime = current_time(new_inode); } unlock: mutex_unlock(&EXFAT_SB(sb)->s_lock); return err; } const struct inode_operations exfat_dir_inode_operations = { .create = exfat_create, .lookup = exfat_lookup, .unlink = exfat_unlink, .mkdir = exfat_mkdir, .rmdir = exfat_rmdir, .rename = exfat_rename, .setattr = exfat_setattr, .getattr = exfat_getattr, }; |
| 467 1 1 597 12 12 12 11 11 9 284 597 12 12 12 12 773 1160 37 773 12 12 12 12 82 84 34 33 9 9 9 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 12 11 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/fork.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * 'fork.c' contains the help-routines for the 'fork' system call * (see also entry.S and others). * Fork is rather simple, once you get the hang of it, but the memory * management can be a bitch. See 'mm/memory.c': 'copy_page_range()' */ #include <linux/anon_inodes.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/user.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/sched/ext.h> #include <linux/seq_file.h> #include <linux/rtmutex.h> #include <linux/init.h> #include <linux/unistd.h> #include <linux/module.h> #include <linux/vmalloc.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/mempolicy.h> #include <linux/sem.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/kmsan.h> #include <linux/binfmts.h> #include <linux/mman.h> #include <linux/mmu_notifier.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/mm_inline.h> #include <linux/memblock.h> #include <linux/nsproxy.h> #include <linux/capability.h> #include <linux/cpu.h> #include <linux/cgroup.h> #include <linux/security.h> #include <linux/hugetlb.h> #include <linux/seccomp.h> #include <linux/swap.h> #include <linux/syscalls.h> #include <linux/syscall_user_dispatch.h> #include <linux/jiffies.h> #include <linux/futex.h> #include <linux/compat.h> #include <linux/kthread.h> #include <linux/task_io_accounting_ops.h> #include <linux/rcupdate.h> #include <linux/ptrace.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/memcontrol.h> #include <linux/ftrace.h> #include <linux/proc_fs.h> #include <linux/profile.h> #include <linux/rmap.h> #include <linux/ksm.h> #include <linux/acct.h> #include <linux/userfaultfd_k.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/freezer.h> #include <linux/delayacct.h> #include <linux/taskstats_kern.h> #include <linux/tty.h> #include <linux/fs_struct.h> #include <linux/magic.h> #include <linux/perf_event.h> #include <linux/posix-timers.h> #include <linux/user-return-notifier.h> #include <linux/oom.h> #include <linux/khugepaged.h> #include <linux/signalfd.h> #include <linux/uprobes.h> #include <linux/aio.h> #include <linux/compiler.h> #include <linux/sysctl.h> #include <linux/kcov.h> #include <linux/livepatch.h> #include <linux/thread_info.h> #include <linux/kstack_erase.h> #include <linux/kasan.h> #include <linux/scs.h> #include <linux/io_uring.h> #include <linux/bpf.h> #include <linux/stackprotector.h> #include <linux/user_events.h> #include <linux/iommu.h> #include <linux/rseq.h> #include <uapi/linux/pidfd.h> #include <linux/pidfs.h> #include <linux/tick.h> #include <linux/unwind_deferred.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> /* For dup_mmap(). */ #include "../mm/internal.h" #include <trace/events/sched.h> #define CREATE_TRACE_POINTS #include <trace/events/task.h> #include <kunit/visibility.h> /* * Minimum number of threads to boot the kernel */ #define MIN_THREADS 20 /* * Maximum number of threads */ #define MAX_THREADS FUTEX_TID_MASK /* * Protected counters by write_lock_irq(&tasklist_lock) */ unsigned long total_forks; /* Handle normal Linux uptimes. */ int nr_threads; /* The idle threads do not count.. */ static int max_threads; /* tunable limit on nr_threads */ #define NAMED_ARRAY_INDEX(x) [x] = __stringify(x) static const char * const resident_page_types[] = { NAMED_ARRAY_INDEX(MM_FILEPAGES), NAMED_ARRAY_INDEX(MM_ANONPAGES), NAMED_ARRAY_INDEX(MM_SWAPENTS), NAMED_ARRAY_INDEX(MM_SHMEMPAGES), }; DEFINE_PER_CPU(unsigned long, process_counts) = 0; __cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */ #ifdef CONFIG_PROVE_RCU int lockdep_tasklist_lock_is_held(void) { return lockdep_is_held(&tasklist_lock); } EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held); #endif /* #ifdef CONFIG_PROVE_RCU */ int nr_processes(void) { int cpu; int total = 0; for_each_possible_cpu(cpu) total += per_cpu(process_counts, cpu); return total; } void __weak arch_release_task_struct(struct task_struct *tsk) { } static struct kmem_cache *task_struct_cachep; static inline struct task_struct *alloc_task_struct_node(int node) { return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node); } static inline void free_task_struct(struct task_struct *tsk) { kmem_cache_free(task_struct_cachep, tsk); } #ifdef CONFIG_VMAP_STACK /* * vmalloc() is a bit slow, and calling vfree() enough times will force a TLB * flush. Try to minimize the number of calls by caching stacks. */ #define NR_CACHED_STACKS 2 static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]); /* * Allocated stacks are cached and later reused by new threads, so memcg * accounting is performed by the code assigning/releasing stacks to tasks. * We need a zeroed memory without __GFP_ACCOUNT. */ #define GFP_VMAP_STACK (GFP_KERNEL | __GFP_ZERO) struct vm_stack { struct rcu_head rcu; struct vm_struct *stack_vm_area; }; static bool try_release_thread_stack_to_cache(struct vm_struct *vm_area) { unsigned int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *tmp = NULL; if (this_cpu_try_cmpxchg(cached_stacks[i], &tmp, vm_area)) return true; } return false; } static void thread_stack_free_rcu(struct rcu_head *rh) { struct vm_stack *vm_stack = container_of(rh, struct vm_stack, rcu); struct vm_struct *vm_area = vm_stack->stack_vm_area; if (try_release_thread_stack_to_cache(vm_stack->stack_vm_area)) return; vfree(vm_area->addr); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct vm_stack *vm_stack = tsk->stack; vm_stack->stack_vm_area = tsk->stack_vm_area; call_rcu(&vm_stack->rcu, thread_stack_free_rcu); } static int free_vm_stack_cache(unsigned int cpu) { struct vm_struct **cached_vm_stack_areas = per_cpu_ptr(cached_stacks, cpu); int i; for (i = 0; i < NR_CACHED_STACKS; i++) { struct vm_struct *vm_area = cached_vm_stack_areas[i]; if (!vm_area) continue; vfree(vm_area->addr); cached_vm_stack_areas[i] = NULL; } return 0; } static int memcg_charge_kernel_stack(struct vm_struct *vm_area) { int i; int ret; int nr_charged = 0; BUG_ON(vm_area->nr_pages != THREAD_SIZE / PAGE_SIZE); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { ret = memcg_kmem_charge_page(vm_area->pages[i], GFP_KERNEL, 0); if (ret) goto err; nr_charged++; } return 0; err: for (i = 0; i < nr_charged; i++) memcg_kmem_uncharge_page(vm_area->pages[i], 0); return ret; } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct vm_struct *vm_area; void *stack; int i; for (i = 0; i < NR_CACHED_STACKS; i++) { vm_area = this_cpu_xchg(cached_stacks[i], NULL); if (!vm_area) continue; /* Reset stack metadata. */ kasan_unpoison_range(vm_area->addr, THREAD_SIZE); stack = kasan_reset_tag(vm_area->addr); /* Clear stale pointers from reused stack. */ memset(stack, 0, THREAD_SIZE); if (memcg_charge_kernel_stack(vm_area)) { vfree(vm_area->addr); return -ENOMEM; } tsk->stack_vm_area = vm_area; tsk->stack = stack; return 0; } stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, GFP_VMAP_STACK, node, __builtin_return_address(0)); if (!stack) return -ENOMEM; vm_area = find_vm_area(stack); if (memcg_charge_kernel_stack(vm_area)) { vfree(stack); return -ENOMEM; } /* * We can't call find_vm_area() in interrupt context, and * free_thread_stack() can be called in interrupt context, * so cache the vm_struct. */ tsk->stack_vm_area = vm_area; stack = kasan_reset_tag(stack); tsk->stack = stack; return 0; } static void free_thread_stack(struct task_struct *tsk) { if (!try_release_thread_stack_to_cache(tsk->stack_vm_area)) thread_stack_delayed_free(tsk); tsk->stack = NULL; tsk->stack_vm_area = NULL; } #else /* !CONFIG_VMAP_STACK */ /* * Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a * kmemcache based allocator. */ #if THREAD_SIZE >= PAGE_SIZE static void thread_stack_free_rcu(struct rcu_head *rh) { __free_pages(virt_to_page(rh), THREAD_SIZE_ORDER); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { struct page *page = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); if (likely(page)) { tsk->stack = kasan_reset_tag(page_address(page)); return 0; } return -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } #else /* !(THREAD_SIZE >= PAGE_SIZE) */ static struct kmem_cache *thread_stack_cache; static void thread_stack_free_rcu(struct rcu_head *rh) { kmem_cache_free(thread_stack_cache, rh); } static void thread_stack_delayed_free(struct task_struct *tsk) { struct rcu_head *rh = tsk->stack; call_rcu(rh, thread_stack_free_rcu); } static int alloc_thread_stack_node(struct task_struct *tsk, int node) { unsigned long *stack; stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node); stack = kasan_reset_tag(stack); tsk->stack = stack; return stack ? 0 : -ENOMEM; } static void free_thread_stack(struct task_struct *tsk) { thread_stack_delayed_free(tsk); tsk->stack = NULL; } void thread_stack_cache_init(void) { thread_stack_cache = kmem_cache_create_usercopy("thread_stack", THREAD_SIZE, THREAD_SIZE, 0, 0, THREAD_SIZE, NULL); BUG_ON(thread_stack_cache == NULL); } #endif /* THREAD_SIZE >= PAGE_SIZE */ #endif /* CONFIG_VMAP_STACK */ /* SLAB cache for signal_struct structures (tsk->signal) */ static struct kmem_cache *signal_cachep; /* SLAB cache for sighand_struct structures (tsk->sighand) */ struct kmem_cache *sighand_cachep; /* SLAB cache for files_struct structures (tsk->files) */ struct kmem_cache *files_cachep; /* SLAB cache for fs_struct structures (tsk->fs) */ struct kmem_cache *fs_cachep; /* SLAB cache for mm_struct structures (tsk->mm) */ static struct kmem_cache *mm_cachep; static void account_kernel_stack(struct task_struct *tsk, int account) { if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm_area = task_stack_vm_area(tsk); int i; for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) mod_lruvec_page_state(vm_area->pages[i], NR_KERNEL_STACK_KB, account * (PAGE_SIZE / 1024)); } else { void *stack = task_stack_page(tsk); /* All stack pages are in the same node. */ mod_lruvec_kmem_state(stack, NR_KERNEL_STACK_KB, account * (THREAD_SIZE / 1024)); } } void exit_task_stack_account(struct task_struct *tsk) { account_kernel_stack(tsk, -1); if (IS_ENABLED(CONFIG_VMAP_STACK)) { struct vm_struct *vm_area; int i; vm_area = task_stack_vm_area(tsk); for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) memcg_kmem_uncharge_page(vm_area->pages[i], 0); } } static void release_task_stack(struct task_struct *tsk) { if (WARN_ON(READ_ONCE(tsk->__state) != TASK_DEAD)) return; /* Better to leak the stack than to free prematurely */ free_thread_stack(tsk); } #ifdef CONFIG_THREAD_INFO_IN_TASK void put_task_stack(struct task_struct *tsk) { if (refcount_dec_and_test(&tsk->stack_refcount)) release_task_stack(tsk); } #endif void free_task(struct task_struct *tsk) { #ifdef CONFIG_SECCOMP WARN_ON_ONCE(tsk->seccomp.filter); #endif release_user_cpus_ptr(tsk); scs_release(tsk); #ifndef CONFIG_THREAD_INFO_IN_TASK /* * The task is finally done with both the stack and thread_info, * so free both. */ release_task_stack(tsk); #else /* * If the task had a separate stack allocation, it should be gone * by now. */ WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0); #endif rt_mutex_debug_task_free(tsk); ftrace_graph_exit_task(tsk); arch_release_task_struct(tsk); if (tsk->flags & PF_KTHREAD) free_kthread_struct(tsk); bpf_task_storage_free(tsk); free_task_struct(tsk); } EXPORT_SYMBOL(free_task); void dup_mm_exe_file(struct mm_struct *mm, struct mm_struct *oldmm) { struct file *exe_file; exe_file = get_mm_exe_file(oldmm); RCU_INIT_POINTER(mm->exe_file, exe_file); /* * We depend on the oldmm having properly denied write access to the * exe_file already. */ if (exe_file && exe_file_deny_write_access(exe_file)) pr_warn_once("exe_file_deny_write_access() failed in %s\n", __func__); } #ifdef CONFIG_MMU static inline int mm_alloc_pgd(struct mm_struct *mm) { mm->pgd = pgd_alloc(mm); if (unlikely(!mm->pgd)) return -ENOMEM; return 0; } static inline void mm_free_pgd(struct mm_struct *mm) { pgd_free(mm, mm->pgd); } #else #define mm_alloc_pgd(mm) (0) #define mm_free_pgd(mm) #endif /* CONFIG_MMU */ #ifdef CONFIG_MM_ID static DEFINE_IDA(mm_ida); static inline int mm_alloc_id(struct mm_struct *mm) { int ret; ret = ida_alloc_range(&mm_ida, MM_ID_MIN, MM_ID_MAX, GFP_KERNEL); if (ret < 0) return ret; mm->mm_id = ret; return 0; } static inline void mm_free_id(struct mm_struct *mm) { const mm_id_t id = mm->mm_id; mm->mm_id = MM_ID_DUMMY; if (id == MM_ID_DUMMY) return; if (WARN_ON_ONCE(id < MM_ID_MIN || id > MM_ID_MAX)) return; ida_free(&mm_ida, id); } #else /* !CONFIG_MM_ID */ static inline int mm_alloc_id(struct mm_struct *mm) { return 0; } static inline void mm_free_id(struct mm_struct *mm) {} #endif /* CONFIG_MM_ID */ static void check_mm(struct mm_struct *mm) { int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS, "Please make sure 'struct resident_page_types[]' is updated as well"); for (i = 0; i < NR_MM_COUNTERS; i++) { long x = percpu_counter_sum(&mm->rss_stat[i]); if (unlikely(x)) { pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld Comm:%s Pid:%d\n", mm, resident_page_types[i], x, current->comm, task_pid_nr(current)); } } if (mm_pgtables_bytes(mm)) pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n", mm_pgtables_bytes(mm)); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) VM_BUG_ON_MM(mm->pmd_huge_pte, mm); #endif } #define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL)) #define free_mm(mm) (kmem_cache_free(mm_cachep, (mm))) static void do_check_lazy_tlb(void *arg) { struct mm_struct *mm = arg; WARN_ON_ONCE(current->active_mm == mm); } static void do_shoot_lazy_tlb(void *arg) { struct mm_struct *mm = arg; if (current->active_mm == mm) { WARN_ON_ONCE(current->mm); current->active_mm = &init_mm; switch_mm(mm, &init_mm, current); } } static void cleanup_lazy_tlbs(struct mm_struct *mm) { if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { /* * In this case, lazy tlb mms are refounted and would not reach * __mmdrop until all CPUs have switched away and mmdrop()ed. */ return; } /* * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it * requires lazy mm users to switch to another mm when the refcount * drops to zero, before the mm is freed. This requires IPIs here to * switch kernel threads to init_mm. * * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm * switch with the final userspace teardown TLB flush which leaves the * mm lazy on this CPU but no others, reducing the need for additional * IPIs here. There are cases where a final IPI is still required here, * such as the final mmdrop being performed on a different CPU than the * one exiting, or kernel threads using the mm when userspace exits. * * IPI overheads have not found to be expensive, but they could be * reduced in a number of possible ways, for example (roughly * increasing order of complexity): * - The last lazy reference created by exit_mm() could instead switch * to init_mm, however it's probable this will run on the same CPU * immediately afterwards, so this may not reduce IPIs much. * - A batch of mms requiring IPIs could be gathered and freed at once. * - CPUs store active_mm where it can be remotely checked without a * lock, to filter out false-positives in the cpumask. * - After mm_users or mm_count reaches zero, switching away from the * mm could clear mm_cpumask to reduce some IPIs, perhaps together * with some batching or delaying of the final IPIs. * - A delayed freeing and RCU-like quiescing sequence based on mm * switching to avoid IPIs completely. */ on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1); if (IS_ENABLED(CONFIG_DEBUG_VM_SHOOT_LAZIES)) on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); } /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by * mmput. Free the page directory and the mm. */ void __mmdrop(struct mm_struct *mm) { BUG_ON(mm == &init_mm); WARN_ON_ONCE(mm == current->mm); /* Ensure no CPUs are using this as their lazy tlb mm */ cleanup_lazy_tlbs(mm); WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); mm_free_id(mm); destroy_context(mm); mmu_notifier_subscriptions_destroy(mm); check_mm(mm); put_user_ns(mm->user_ns); mm_pasid_drop(mm); mm_destroy_cid(mm); percpu_counter_destroy_many(mm->rss_stat, NR_MM_COUNTERS); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); static void mmdrop_async_fn(struct work_struct *work) { struct mm_struct *mm; mm = container_of(work, struct mm_struct, async_put_work); __mmdrop(mm); } static void mmdrop_async(struct mm_struct *mm) { if (unlikely(atomic_dec_and_test(&mm->mm_count))) { INIT_WORK(&mm->async_put_work, mmdrop_async_fn); schedule_work(&mm->async_put_work); } } static inline void free_signal_struct(struct signal_struct *sig) { taskstats_tgid_free(sig); sched_autogroup_exit(sig); /* * __mmdrop is not safe to call from softirq context on x86 due to * pgd_dtor so postpone it to the async context */ if (sig->oom_mm) mmdrop_async(sig->oom_mm); kmem_cache_free(signal_cachep, sig); } static inline void put_signal_struct(struct signal_struct *sig) { if (refcount_dec_and_test(&sig->sigcnt)) free_signal_struct(sig); } void __put_task_struct(struct task_struct *tsk) { WARN_ON(!tsk->exit_state); WARN_ON(refcount_read(&tsk->usage)); WARN_ON(tsk == current); unwind_task_free(tsk); sched_ext_free(tsk); io_uring_free(tsk); cgroup_free(tsk); task_numa_free(tsk, true); security_task_free(tsk); exit_creds(tsk); delayacct_tsk_free(tsk); put_signal_struct(tsk->signal); sched_core_free(tsk); free_task(tsk); } EXPORT_SYMBOL_GPL(__put_task_struct); void __put_task_struct_rcu_cb(struct rcu_head *rhp) { struct task_struct *task = container_of(rhp, struct task_struct, rcu); __put_task_struct(task); } EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb); void __init __weak arch_task_cache_init(void) { } /* * set_max_threads */ static void __init set_max_threads(unsigned int max_threads_suggested) { u64 threads; unsigned long nr_pages = memblock_estimated_nr_free_pages(); /* * The number of threads shall be limited such that the thread * structures may only consume a small part of the available memory. */ if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64) threads = MAX_THREADS; else threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE, (u64) THREAD_SIZE * 8UL); if (threads > max_threads_suggested) threads = max_threads_suggested; max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS); } #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT /* Initialized by the architecture: */ int arch_task_struct_size __read_mostly; #endif static void __init task_struct_whitelist(unsigned long *offset, unsigned long *size) { /* Fetch thread_struct whitelist for the architecture. */ arch_thread_struct_whitelist(offset, size); /* * Handle zero-sized whitelist or empty thread_struct, otherwise * adjust offset to position of thread_struct in task_struct. */ if (unlikely(*size == 0)) *offset = 0; else *offset += offsetof(struct task_struct, thread); } void __init fork_init(void) { int i; #ifndef ARCH_MIN_TASKALIGN #define ARCH_MIN_TASKALIGN 0 #endif int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN); unsigned long useroffset, usersize; /* create a slab on which task_structs can be allocated */ task_struct_whitelist(&useroffset, &usersize); task_struct_cachep = kmem_cache_create_usercopy("task_struct", arch_task_struct_size, align, SLAB_PANIC|SLAB_ACCOUNT, useroffset, usersize, NULL); /* do the arch specific task caches init */ arch_task_cache_init(); set_max_threads(MAX_THREADS); init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2; init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2; init_task.signal->rlim[RLIMIT_SIGPENDING] = init_task.signal->rlim[RLIMIT_NPROC]; for (i = 0; i < UCOUNT_COUNTS; i++) init_user_ns.ucount_max[i] = max_threads/2; set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_NPROC, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MSGQUEUE, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_SIGPENDING, RLIM_INFINITY); set_userns_rlimit_max(&init_user_ns, UCOUNT_RLIMIT_MEMLOCK, RLIM_INFINITY); #ifdef CONFIG_VMAP_STACK cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache", NULL, free_vm_stack_cache); #endif scs_init(); lockdep_init_task(&init_task); uprobes_init(); } int __weak arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) { *dst = *src; return 0; } void set_task_stack_end_magic(struct task_struct *tsk) { unsigned long *stackend; stackend = end_of_stack(tsk); *stackend = STACK_END_MAGIC; /* for overflow detection */ } static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; int err; if (node == NUMA_NO_NODE) node = tsk_fork_get_node(orig); tsk = alloc_task_struct_node(node); if (!tsk) return NULL; err = arch_dup_task_struct(tsk, orig); if (err) goto free_tsk; err = alloc_thread_stack_node(tsk, node); if (err) goto free_tsk; #ifdef CONFIG_THREAD_INFO_IN_TASK refcount_set(&tsk->stack_refcount, 1); #endif account_kernel_stack(tsk, 1); err = scs_prepare(tsk, node); if (err) goto free_stack; #ifdef CONFIG_SECCOMP /* * We must handle setting up seccomp filters once we're under * the sighand lock in case orig has changed between now and * then. Until then, filter must be NULL to avoid messing up * the usage counts on the error path calling free_task. */ tsk->seccomp.filter = NULL; #endif setup_thread_stack(tsk, orig); clear_user_return_notifier(tsk); clear_tsk_need_resched(tsk); set_task_stack_end_magic(tsk); clear_syscall_work_syscall_user_dispatch(tsk); #ifdef CONFIG_STACKPROTECTOR tsk->stack_canary = get_random_canary(); #endif if (orig->cpus_ptr == &orig->cpus_mask) tsk->cpus_ptr = &tsk->cpus_mask; dup_user_cpus_ptr(tsk, orig, node); /* * One for the user space visible state that goes away when reaped. * One for the scheduler. */ refcount_set(&tsk->rcu_users, 2); /* One for the rcu users */ refcount_set(&tsk->usage, 1); #ifdef CONFIG_BLK_DEV_IO_TRACE tsk->btrace_seq = 0; #endif tsk->splice_pipe = NULL; tsk->task_frag.page = NULL; tsk->wake_q.next = NULL; tsk->worker_private = NULL; kcov_task_init(tsk); kmsan_task_create(tsk); kmap_local_fork(tsk); #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif #ifdef CONFIG_BLK_CGROUP tsk->throttle_disk = NULL; tsk->use_memdelay = 0; #endif #ifdef CONFIG_ARCH_HAS_CPU_PASID tsk->pasid_activated = 0; #endif #ifdef CONFIG_MEMCG tsk->active_memcg = NULL; #endif #ifdef CONFIG_X86_BUS_LOCK_DETECT tsk->reported_split_lock = 0; #endif #ifdef CONFIG_SCHED_MM_CID tsk->mm_cid = -1; tsk->last_mm_cid = -1; tsk->mm_cid_active = 0; tsk->migrate_from_cpu = -1; #endif return tsk; free_stack: exit_task_stack_account(tsk); free_thread_stack(tsk); free_tsk: free_task_struct(tsk); return NULL; } __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock); static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT; static int __init coredump_filter_setup(char *s) { default_dump_filter = (simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) & MMF_DUMP_FILTER_MASK; return 1; } __setup("coredump_filter=", coredump_filter_setup); #include <linux/init_task.h> static void mm_init_aio(struct mm_struct *mm) { #ifdef CONFIG_AIO spin_lock_init(&mm->ioctx_lock); mm->ioctx_table = NULL; #endif } static __always_inline void mm_clear_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG if (mm->owner == p) WRITE_ONCE(mm->owner, NULL); #endif } static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) { #ifdef CONFIG_MEMCG mm->owner = p; #endif } static void mm_init_uprobes_state(struct mm_struct *mm) { #ifdef CONFIG_UPROBES mm->uprobes_state.xol_area = NULL; #endif } static void mmap_init_lock(struct mm_struct *mm) { init_rwsem(&mm->mmap_lock); mm_lock_seqcount_init(mm); #ifdef CONFIG_PER_VMA_LOCK rcuwait_init(&mm->vma_writer_wait); #endif } static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, struct user_namespace *user_ns) { mt_init_flags(&mm->mm_mt, MM_MT_FLAGS); mt_set_external_lock(&mm->mm_mt, &mm->mmap_lock); atomic_set(&mm->mm_users, 1); atomic_set(&mm->mm_count, 1); seqcount_init(&mm->write_protect_seq); mmap_init_lock(mm); INIT_LIST_HEAD(&mm->mmlist); mm_pgtables_bytes_init(mm); mm->map_count = 0; mm->locked_vm = 0; atomic64_set(&mm->pinned_vm, 0); memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); mm_init_aio(mm); mm_init_owner(mm, p); mm_pasid_init(mm); RCU_INIT_POINTER(mm->exe_file, NULL); mmu_notifier_subscriptions_init(mm); init_tlb_flush_pending(mm); #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS) mm->pmd_huge_pte = NULL; #endif mm_init_uprobes_state(mm); hugetlb_count_init(mm); if (current->mm) { mm->flags = mmf_init_flags(current->mm->flags); mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK; } else { mm->flags = default_dump_filter; mm->def_flags = 0; } if (futex_mm_init(mm)) goto fail_mm_init; if (mm_alloc_pgd(mm)) goto fail_nopgd; if (mm_alloc_id(mm)) goto fail_noid; if (init_new_context(p, mm)) goto fail_nocontext; if (mm_alloc_cid(mm, p)) goto fail_cid; if (percpu_counter_init_many(mm->rss_stat, 0, GFP_KERNEL_ACCOUNT, NR_MM_COUNTERS)) goto fail_pcpu; mm->user_ns = get_user_ns(user_ns); lru_gen_init_mm(mm); return mm; fail_pcpu: mm_destroy_cid(mm); fail_cid: destroy_context(mm); fail_nocontext: mm_free_id(mm); fail_noid: mm_free_pgd(mm); fail_nopgd: futex_hash_free(mm); fail_mm_init: free_mm(mm); return NULL; } /* * Allocate and initialize an mm_struct. */ struct mm_struct *mm_alloc(void) { struct mm_struct *mm; mm = allocate_mm(); if (!mm) return NULL; memset(mm, 0, sizeof(*mm)); return mm_init(mm, current, current_user_ns()); } EXPORT_SYMBOL_IF_KUNIT(mm_alloc); static inline void __mmput(struct mm_struct *mm) { VM_BUG_ON(atomic_read(&mm->mm_users)); uprobe_clear_state(mm); exit_aio(mm); ksm_exit(mm); khugepaged_exit(mm); /* must run before exit_mmap */ exit_mmap(mm); mm_put_huge_zero_folio(mm); set_mm_exe_file(mm, NULL); if (!list_empty(&mm->mmlist)) { spin_lock(&mmlist_lock); list_del(&mm->mmlist); spin_unlock(&mmlist_lock); } if (mm->binfmt) module_put(mm->binfmt->module); lru_gen_del_mm(mm); futex_hash_free(mm); mmdrop(mm); } /* * Decrement the use count and release all resources for an mm. */ void mmput(struct mm_struct *mm) { might_sleep(); if (atomic_dec_and_test(&mm->mm_users)) __mmput(mm); } EXPORT_SYMBOL_GPL(mmput); #if defined(CONFIG_MMU) || defined(CONFIG_FUTEX_PRIVATE_HASH) static void mmput_async_fn(struct work_struct *work) { struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work); __mmput(mm); } void mmput_async(struct mm_struct *mm) { if (atomic_dec_and_test(&mm->mm_users)) { INIT_WORK(&mm->async_put_work, mmput_async_fn); schedule_work(&mm->async_put_work); } } EXPORT_SYMBOL_GPL(mmput_async); #endif /** * set_mm_exe_file - change a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main users are mmput() and sys_execve(). Callers prevent concurrent * invocations: in mmput() nobody alive left, in execve it happens before * the new mm is made visible to anyone. * * Can only fail if new_exe_file != NULL. */ int set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct file *old_exe_file; /* * It is safe to dereference the exe_file without RCU as * this function is only called if nobody else can access * this mm -- see comment above for justification. */ old_exe_file = rcu_dereference_raw(mm->exe_file); if (new_exe_file) { /* * We expect the caller (i.e., sys_execve) to already denied * write access, so this is unlikely to fail. */ if (unlikely(exe_file_deny_write_access(new_exe_file))) return -EACCES; get_file(new_exe_file); } rcu_assign_pointer(mm->exe_file, new_exe_file); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * replace_mm_exe_file - replace a reference to the mm's executable file * @mm: The mm to change. * @new_exe_file: The new file to use. * * This changes mm's executable file (shown as symlink /proc/[pid]/exe). * * Main user is sys_prctl(PR_SET_MM_MAP/EXE_FILE). */ int replace_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file) { struct vm_area_struct *vma; struct file *old_exe_file; int ret = 0; /* Forbid mm->exe_file change if old file still mapped. */ old_exe_file = get_mm_exe_file(mm); if (old_exe_file) { VMA_ITERATOR(vmi, mm, 0); mmap_read_lock(mm); for_each_vma(vmi, vma) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &old_exe_file->f_path)) { ret = -EBUSY; break; } } mmap_read_unlock(mm); fput(old_exe_file); if (ret) return ret; } ret = exe_file_deny_write_access(new_exe_file); if (ret) return -EACCES; get_file(new_exe_file); /* set the new file */ mmap_write_lock(mm); old_exe_file = rcu_dereference_raw(mm->exe_file); rcu_assign_pointer(mm->exe_file, new_exe_file); mmap_write_unlock(mm); if (old_exe_file) { exe_file_allow_write_access(old_exe_file); fput(old_exe_file); } return 0; } /** * get_mm_exe_file - acquire a reference to the mm's executable file * @mm: The mm of interest. * * Returns %NULL if mm has no associated executable file. * User must release file via fput(). */ struct file *get_mm_exe_file(struct mm_struct *mm) { struct file *exe_file; rcu_read_lock(); exe_file = get_file_rcu(&mm->exe_file); rcu_read_unlock(); return exe_file; } /** * get_task_exe_file - acquire a reference to the task's executable file * @task: The task. * * Returns %NULL if task's mm (if any) has no associated executable file or * this is a kernel thread with borrowed mm (see the comment above get_task_mm). * User must release file via fput(). */ struct file *get_task_exe_file(struct task_struct *task) { struct file *exe_file = NULL; struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) exe_file = get_mm_exe_file(mm); task_unlock(task); return exe_file; } /** * get_task_mm - acquire a reference to the task's mm * @task: The task. * * Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning * this kernel workthread has transiently adopted a user mm with use_mm, * to do its AIO) is not set and if so returns a reference to it, after * bumping up the use count. User must release the mm via mmput() * after use. Typically used by /proc and ptrace. */ struct mm_struct *get_task_mm(struct task_struct *task) { struct mm_struct *mm; if (task->flags & PF_KTHREAD) return NULL; task_lock(task); mm = task->mm; if (mm) mmget(mm); task_unlock(task); return mm; } EXPORT_SYMBOL_GPL(get_task_mm); static bool may_access_mm(struct mm_struct *mm, struct task_struct *task, unsigned int mode) { if (mm == current->mm) return true; if (ptrace_may_access(task, mode)) return true; if ((mode & PTRACE_MODE_READ) && perfmon_capable()) return true; return false; } struct mm_struct *mm_access(struct task_struct *task, unsigned int mode) { struct mm_struct *mm; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return ERR_PTR(err); mm = get_task_mm(task); if (!mm) { mm = ERR_PTR(-ESRCH); } else if (!may_access_mm(mm, task, mode)) { mmput(mm); mm = ERR_PTR(-EACCES); } up_read(&task->signal->exec_update_lock); return mm; } static void complete_vfork_done(struct task_struct *tsk) { struct completion *vfork; task_lock(tsk); vfork = tsk->vfork_done; if (likely(vfork)) { tsk->vfork_done = NULL; complete(vfork); } task_unlock(tsk); } static int wait_for_vfork_done(struct task_struct *child, struct completion *vfork) { unsigned int state = TASK_KILLABLE|TASK_FREEZABLE; int killed; cgroup_enter_frozen(); killed = wait_for_completion_state(vfork, state); cgroup_leave_frozen(false); if (killed) { task_lock(child); child->vfork_done = NULL; task_unlock(child); } put_task_struct(child); return killed; } /* Please note the differences between mmput and mm_release. * mmput is called whenever we stop holding onto a mm_struct, * error success whatever. * * mm_release is called after a mm_struct has been removed * from the current process. * * This difference is important for error handling, when we * only half set up a mm_struct for a new process and need to restore * the old one. Because we mmput the new mm_struct before * restoring the old one. . . * Eric Biederman 10 January 1998 */ static void mm_release(struct task_struct *tsk, struct mm_struct *mm) { uprobe_free_utask(tsk); /* Get rid of any cached register state */ deactivate_mm(tsk, mm); /* * Signal userspace if we're not exiting with a core dump * because we want to leave the value intact for debugging * purposes. */ if (tsk->clear_child_tid) { if (atomic_read(&mm->mm_users) > 1) { /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ put_user(0, tsk->clear_child_tid); do_futex(tsk->clear_child_tid, FUTEX_WAKE, 1, NULL, NULL, 0, 0); } tsk->clear_child_tid = NULL; } /* * All done, finally we can wake up parent and return this mm to him. * Also kthread_stop() uses this completion for synchronization. */ if (tsk->vfork_done) complete_vfork_done(tsk); } void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exit_release(tsk); mm_release(tsk, mm); } void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm) { futex_exec_release(tsk); mm_release(tsk, mm); } /** * dup_mm() - duplicates an existing mm structure * @tsk: the task_struct with which the new mm will be associated. * @oldmm: the mm to duplicate. * * Allocates a new mm structure and duplicates the provided @oldmm structure * content into it. * * Return: the duplicated mm or NULL on failure. */ static struct mm_struct *dup_mm(struct task_struct *tsk, struct mm_struct *oldmm) { struct mm_struct *mm; int err; mm = allocate_mm(); if (!mm) goto fail_nomem; memcpy(mm, oldmm, sizeof(*mm)); if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; uprobe_start_dup_mmap(); err = dup_mmap(mm, oldmm); if (err) goto free_pt; uprobe_end_dup_mmap(); mm->hiwater_rss = get_mm_rss(mm); mm->hiwater_vm = mm->total_vm; if (mm->binfmt && !try_module_get(mm->binfmt->module)) goto free_pt; return mm; free_pt: /* don't put binfmt in mmput, we haven't got module yet */ mm->binfmt = NULL; mm_init_owner(mm, NULL); mmput(mm); if (err) uprobe_end_dup_mmap(); fail_nomem: return NULL; } static int copy_mm(unsigned long clone_flags, struct task_struct *tsk) { struct mm_struct *mm, *oldmm; tsk->min_flt = tsk->maj_flt = 0; tsk->nvcsw = tsk->nivcsw = 0; #ifdef CONFIG_DETECT_HUNG_TASK tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw; tsk->last_switch_time = 0; #endif tsk->mm = NULL; tsk->active_mm = NULL; /* * Are we cloning a kernel thread? * * We need to steal a active VM for that.. */ oldmm = current->mm; if (!oldmm) return 0; if (clone_flags & CLONE_VM) { mmget(oldmm); mm = oldmm; } else { mm = dup_mm(tsk, current->mm); if (!mm) return -ENOMEM; } tsk->mm = mm; tsk->active_mm = mm; sched_mm_cid_fork(tsk); return 0; } static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) { struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ read_seqlock_excl(&fs->seq); /* "users" and "in_exec" locked for check_unsafe_exec() */ if (fs->in_exec) { read_sequnlock_excl(&fs->seq); return -EAGAIN; } fs->users++; read_sequnlock_excl(&fs->seq); return 0; } tsk->fs = copy_fs_struct(fs); if (!tsk->fs) return -ENOMEM; return 0; } static int copy_files(unsigned long clone_flags, struct task_struct *tsk, int no_files) { struct files_struct *oldf, *newf; /* * A background process may not have any files ... */ oldf = current->files; if (!oldf) return 0; if (no_files) { tsk->files = NULL; return 0; } if (clone_flags & CLONE_FILES) { atomic_inc(&oldf->count); return 0; } newf = dup_fd(oldf, NULL); if (IS_ERR(newf)) return PTR_ERR(newf); tsk->files = newf; return 0; } static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk) { struct sighand_struct *sig; if (clone_flags & CLONE_SIGHAND) { refcount_inc(¤t->sighand->count); return 0; } sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); RCU_INIT_POINTER(tsk->sighand, sig); if (!sig) return -ENOMEM; refcount_set(&sig->count, 1); spin_lock_irq(¤t->sighand->siglock); memcpy(sig->action, current->sighand->action, sizeof(sig->action)); spin_unlock_irq(¤t->sighand->siglock); /* Reset all signal handler not set to SIG_IGN to SIG_DFL. */ if (clone_flags & CLONE_CLEAR_SIGHAND) flush_signal_handlers(tsk, 0); return 0; } void __cleanup_sighand(struct sighand_struct *sighand) { if (refcount_dec_and_test(&sighand->count)) { signalfd_cleanup(sighand); /* * sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it * without an RCU grace period, see __lock_task_sighand(). */ kmem_cache_free(sighand_cachep, sighand); } } /* * Initialize POSIX timer handling for a thread group. */ static void posix_cpu_timers_init_group(struct signal_struct *sig) { struct posix_cputimers *pct = &sig->posix_cputimers; unsigned long cpu_limit; cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); posix_cputimers_group_init(pct, cpu_limit); } static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; if (clone_flags & CLONE_THREAD) return 0; sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; if (!sig) return -ENOMEM; sig->nr_threads = 1; sig->quick_threads = 1; atomic_set(&sig->live, 1); refcount_set(&sig->sigcnt, 1); /* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */ sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node); tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head); init_waitqueue_head(&sig->wait_chldexit); sig->curr_target = tsk; init_sigpending(&sig->shared_pending); INIT_HLIST_HEAD(&sig->multiprocess); seqlock_init(&sig->stats_lock); prev_cputime_init(&sig->prev_cputime); #ifdef CONFIG_POSIX_TIMERS INIT_HLIST_HEAD(&sig->posix_timers); INIT_HLIST_HEAD(&sig->ignored_posix_timers); hrtimer_setup(&sig->real_timer, it_real_fn, CLOCK_MONOTONIC, HRTIMER_MODE_REL); #endif task_lock(current->group_leader); memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim); task_unlock(current->group_leader); posix_cpu_timers_init_group(sig); tty_audit_fork(sig); sched_autogroup_fork(sig); sig->oom_score_adj = current->signal->oom_score_adj; sig->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_init(&sig->cred_guard_mutex); init_rwsem(&sig->exec_update_lock); return 0; } static void copy_seccomp(struct task_struct *p) { #ifdef CONFIG_SECCOMP /* * Must be called with sighand->lock held, which is common to * all threads in the group. Holding cred_guard_mutex is not * needed because this new task is not yet running and cannot * be racing exec. */ assert_spin_locked(¤t->sighand->siglock); /* Ref-count the new filter user, and assign it. */ get_seccomp_filter(current); p->seccomp = current->seccomp; /* * Explicitly enable no_new_privs here in case it got set * between the task_struct being duplicated and holding the * sighand lock. The seccomp state and nnp must be in sync. */ if (task_no_new_privs(current)) task_set_no_new_privs(p); /* * If the parent gained a seccomp mode after copying thread * flags and between before we held the sighand lock, we have * to manually enable the seccomp thread flag here. */ if (p->seccomp.mode != SECCOMP_MODE_DISABLED) set_task_syscall_work(p, SECCOMP); #endif } SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) { current->clear_child_tid = tidptr; return task_pid_vnr(current); } static void rt_mutex_init_task(struct task_struct *p) { raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES p->pi_waiters = RB_ROOT_CACHED; p->pi_top_task = NULL; p->pi_blocked_on = NULL; #endif } static inline void init_task_pid_links(struct task_struct *task) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) INIT_HLIST_NODE(&task->pid_links[type]); } static inline void init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid) { if (type == PIDTYPE_PID) task->thread_pid = pid; else task->signal->pids[type] = pid; } static inline void rcu_copy_process(struct task_struct *p) { #ifdef CONFIG_PREEMPT_RCU p->rcu_read_lock_nesting = 0; p->rcu_read_unlock_special.s = 0; p->rcu_blocked_node = NULL; INIT_LIST_HEAD(&p->rcu_node_entry); #endif /* #ifdef CONFIG_PREEMPT_RCU */ #ifdef CONFIG_TASKS_RCU p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; INIT_LIST_HEAD(&p->rcu_tasks_exit_list); #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; p->trc_reader_special.s = 0; INIT_LIST_HEAD(&p->trc_holdout_list); INIT_LIST_HEAD(&p->trc_blkd_node); #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } /** * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd * @flags: flags of the new @pidfd * @ret_file: return the new pidfs file * * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * * The helper verifies that @pid is still in use, without PIDFD_THREAD the * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in * order to install the pidfd into its file descriptor table or they must use * put_unused_fd() and fput() on the returned pidfd and pidfd file * respectively. * * This function is useful when a pidfd must already be reserved but there * might still be points of failure afterwards and the caller wants to ensure * that no pidfd is leaked into its file descriptor table. * * Return: On success, a reserved pidfd is returned from the function and a new * pidfd file is returned in the last argument to the function. On * error, a negative error code is returned from the function and the * last argument remains unchanged. */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file) { struct file *pidfs_file; /* * PIDFD_STALE is only allowed to be passed if the caller knows * that @pid is already registered in pidfs and thus * PIDFD_INFO_EXIT information is guaranteed to be available. */ if (!(flags & PIDFD_STALE)) { /* * While holding the pidfd waitqueue lock removing the * task linkage for the thread-group leader pid * (PIDTYPE_TGID) isn't possible. Thus, if there's still * task linkage for PIDTYPE_PID not having thread-group * leader linkage for the pid means it wasn't a * thread-group leader in the first place. */ guard(spinlock_irq)(&pid->wait_pidfd.lock); /* Task has already been reaped. */ if (!pid_has_task(pid, PIDTYPE_PID)) return -ESRCH; /* * If this struct pid isn't used as a thread-group * leader but the caller requested to create a * thread-group leader pidfd then report ENOENT. */ if (!(flags & PIDFD_THREAD) && !pid_has_task(pid, PIDTYPE_TGID)) return -ENOENT; } CLASS(get_unused_fd, pidfd)(O_CLOEXEC); if (pidfd < 0) return pidfd; pidfs_file = pidfs_alloc_file(pid, flags | O_RDWR); if (IS_ERR(pidfs_file)) return PTR_ERR(pidfs_file); *ret_file = pidfs_file; return take_fd(pidfd); } static void __delayed_free_task(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); free_task(tsk); } static __always_inline void delayed_free_task(struct task_struct *tsk) { if (IS_ENABLED(CONFIG_MEMCG)) call_rcu(&tsk->rcu, __delayed_free_task); else free_task(tsk); } static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk) { /* Skip if kernel thread */ if (!tsk->mm) return; /* Skip if spawning a thread or using vfork */ if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM) return; /* We need to synchronize with __set_oom_adj */ mutex_lock(&oom_adj_mutex); set_bit(MMF_MULTIPROCESS, &tsk->mm->flags); /* Update the values in case they were changed after copy_signal */ tsk->signal->oom_score_adj = current->signal->oom_score_adj; tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min; mutex_unlock(&oom_adj_mutex); } #ifdef CONFIG_RV static void rv_task_fork(struct task_struct *p) { memset(&p->rv, 0, sizeof(p->rv)); } #else #define rv_task_fork(p) do {} while (0) #endif static bool need_futex_hash_allocate_default(u64 clone_flags) { if ((clone_flags & (CLONE_THREAD | CLONE_VM)) != (CLONE_THREAD | CLONE_VM)) return false; return true; } /* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ __latent_entropy struct task_struct *copy_process( struct pid *pid, int trace, int node, struct kernel_clone_args *args) { int pidfd = -1, retval; struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. */ if (clone_flags & CLONE_DETACHED) return ERR_PTR(-EINVAL); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->user_worker) { /* * Mark us a user worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } if (args->io_thread) p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_delayacct; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; #ifdef CONFIG_LOCKDEP lockdep_init_task(p); #endif p->blocked_on = NULL; /* not blocked yet */ #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif #ifdef CONFIG_BPF_SYSCALL RCU_INIT_POINTER(p->bpf_storage, NULL); p->bpf_ctx = NULL; #endif unwind_task_init(p); /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_sched_cancel_fork; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p, args->no_files); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; /* * Note that no task has been attached to @pid yet indicate * that via CLONE_PIDFD. */ retval = pidfd_prepare(pid, flags | PIDFD_STALE, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif #ifdef CONFIG_RETHOOK p->rethooks.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ retval = sched_cgroup_fork(p, args); if (retval) goto bad_fork_cancel_cgroup; /* * Allocate a default futex hash for the user process once the first * thread spawns. */ if (need_futex_hash_allocate_default(clone_flags)) { retval = futex_hash_allocate_default(); if (retval) goto bad_fork_core_free; /* * If we fail beyond this point we don't free the allocated * futex hash map. We assume that another thread will be created * and makes use of it. The hash map will be freed once the main * thread terminates. */ } /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rv_task_fork(p); rseq_fork(p, clone_flags); /* Don't start children in a dying pid namespace */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_core_free; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) { ns_of_pid(pid)->child_reaper = p; p->signal->flags |= SIGNAL_UNKILLABLE; } p->signal->shared_pending.signal = delayed.signal; p->signal->tty = tty_kref_get(current->signal->tty); /* * Inherit has_child_subreaper flag under the same * tasklist_lock with adding child to the process tree * for propagate_has_child_subreaper optimization. */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); attach_pid(p, PIDTYPE_PGID); attach_pid(p, PIDTYPE_SID); __this_cpu_inc(process_counts); } else { current->signal->nr_threads++; current->signal->quick_threads++; atomic_inc(¤t->signal->live); refcount_inc(¤t->signal->sigcnt); task_join_group_stop(p); list_add_tail_rcu(&p->thread_node, &p->signal->thread_head); } attach_pid(p, PIDTYPE_PID); nr_threads++; } total_forks++; hlist_del_init(&delayed.node); spin_unlock(¤t->sighand->siglock); syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); if (pidfile) fd_install(pidfd, pidfile); proc_fork_connector(p); sched_post_fork(p); cgroup_post_fork(p, args); perf_event_fork(p); trace_task_newtask(p, clone_flags); uprobe_copy_process(p, clone_flags); user_events_fork(p, clone_flags); copy_oom_score_adj(clone_flags, p); return p; bad_fork_core_free: sched_core_free(p); spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); bad_fork_cancel_cgroup: cgroup_cancel_fork(p, args); bad_fork_put_pidfd: if (clone_flags & CLONE_PIDFD) { fput(pidfile); put_unused_fd(pidfd); } bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_thread: exit_thread(p); bad_fork_cleanup_io: if (p->io_context) exit_io_context(p); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) { mm_clear_owner(p->mm, p); mmput(p->mm); } bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) free_signal_struct(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_perf: perf_event_free_task(p); bad_fork_sched_cancel_fork: sched_cancel_fork(p); bad_fork_cleanup_policy: lockdep_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); #endif bad_fork_cleanup_delayacct: delayacct_tsk_free(p); bad_fork_cleanup_count: dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); exit_creds(p); bad_fork_free: WRITE_ONCE(p->__state, TASK_DEAD); exit_task_stack_account(p); put_task_stack(p); delayed_free_task(p); fork_out: spin_lock_irq(¤t->sighand->siglock); hlist_del_init(&delayed.node); spin_unlock_irq(¤t->sighand->siglock); return ERR_PTR(retval); } static inline void init_idle_pids(struct task_struct *idle) { enum pid_type type; for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) { INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */ init_task_pid(idle, type, &init_struct_pid); } } static int idle_dummy(void *dummy) { /* This function is never called */ return 0; } struct task_struct * __init fork_idle(int cpu) { struct task_struct *task; struct kernel_clone_args args = { .flags = CLONE_VM, .fn = &idle_dummy, .fn_arg = NULL, .kthread = 1, .idle = 1, }; task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args); if (!IS_ERR(task)) { init_idle_pids(task); init_idle(task, cpu); } return task; } /* * This is like kernel_clone(), but shaved down and tailored to just * creating io_uring workers. It returns a created task, or an error pointer. * The returned task is inactive, and the caller must fire it up through * wake_up_new_task(p). All signals are blocked in the created task. */ struct task_struct *create_io_thread(int (*fn)(void *), void *arg, int node) { unsigned long flags = CLONE_FS|CLONE_FILES|CLONE_SIGHAND|CLONE_THREAD| CLONE_IO; struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .io_thread = 1, .user_worker = 1, }; return copy_process(NULL, 0, node, &args); } /* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. * * args->exit_signal is expected to be checked for sanity by the caller. */ pid_t kernel_clone(struct kernel_clone_args *args) { u64 clone_flags = args->flags; struct completion vfork; struct pid *pid; struct task_struct *p; int trace = 0; pid_t nr; /* * For legacy clone() calls, CLONE_PIDFD uses the parent_tid argument * to return the pidfd. Hence, CLONE_PIDFD and CLONE_PARENT_SETTID are * mutually exclusive. With clone3() CLONE_PIDFD has grown a separate * field in struct clone_args and it still doesn't make sense to have * them both point at the same memory location. Performing this check * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ if ((clone_flags & CLONE_PIDFD) && (clone_flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; /* * Determine whether and which event to report to ptracer. When * called from kernel_thread or CLONE_UNTRACED is explicitly * requested, no event is reported; otherwise, report if the event * for the type of forking is enabled. */ if (!(clone_flags & CLONE_UNTRACED)) { if (clone_flags & CLONE_VFORK) trace = PTRACE_EVENT_VFORK; else if (args->exit_signal != SIGCHLD) trace = PTRACE_EVENT_CLONE; else trace = PTRACE_EVENT_FORK; if (likely(!ptrace_event_enabled(current, trace))) trace = 0; } p = copy_process(NULL, trace, NUMA_NO_NODE, args); add_latent_entropy(); if (IS_ERR(p)) return PTR_ERR(p); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ trace_sched_process_fork(current, p); pid = get_task_pid(p, PIDTYPE_PID); nr = pid_vnr(pid); if (clone_flags & CLONE_PARENT_SETTID) put_user(nr, args->parent_tid); if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); get_task_struct(p); } if (IS_ENABLED(CONFIG_LRU_GEN_WALKS_MMU) && !(clone_flags & CLONE_VM)) { /* lock the task to synchronize with memcg migration */ task_lock(p); lru_gen_add_mm(p->mm); task_unlock(p); } wake_up_new_task(p); /* forking complete and child started to run, tell ptracer */ if (unlikely(trace)) ptrace_event_pid(trace, pid); if (clone_flags & CLONE_VFORK) { if (!wait_for_vfork_done(p, &vfork)) ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid); } put_pid(pid); return nr; } /* * Create a kernel thread. */ pid_t kernel_thread(int (*fn)(void *), void *arg, const char *name, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, .name = name, .kthread = 1, }; return kernel_clone(&args); } /* * Create a user mode thread. */ pid_t user_mode_thread(int (*fn)(void *), void *arg, unsigned long flags) { struct kernel_clone_args args = { .flags = ((lower_32_bits(flags) | CLONE_VM | CLONE_UNTRACED) & ~CSIGNAL), .exit_signal = (lower_32_bits(flags) & CSIGNAL), .fn = fn, .fn_arg = arg, }; return kernel_clone(&args); } #ifdef __ARCH_WANT_SYS_FORK SYSCALL_DEFINE0(fork) { #ifdef CONFIG_MMU struct kernel_clone_args args = { .exit_signal = SIGCHLD, }; return kernel_clone(&args); #else /* can not support in nommu mode */ return -EINVAL; #endif } #endif #ifdef __ARCH_WANT_SYS_VFORK SYSCALL_DEFINE0(vfork) { struct kernel_clone_args args = { .flags = CLONE_VFORK | CLONE_VM, .exit_signal = SIGCHLD, }; return kernel_clone(&args); } #endif #ifdef __ARCH_WANT_SYS_CLONE #ifdef CONFIG_CLONE_BACKWARDS SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, unsigned long, tls, int __user *, child_tidptr) #elif defined(CONFIG_CLONE_BACKWARDS2) SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #elif defined(CONFIG_CLONE_BACKWARDS3) SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp, int, stack_size, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #else SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp, int __user *, parent_tidptr, int __user *, child_tidptr, unsigned long, tls) #endif { struct kernel_clone_args args = { .flags = (lower_32_bits(clone_flags) & ~CSIGNAL), .pidfd = parent_tidptr, .child_tid = child_tidptr, .parent_tid = parent_tidptr, .exit_signal = (lower_32_bits(clone_flags) & CSIGNAL), .stack = newsp, .tls = tls, }; return kernel_clone(&args); } #endif static noinline int copy_clone_args_from_user(struct kernel_clone_args *kargs, struct clone_args __user *uargs, size_t usize) { int err; struct clone_args args; pid_t *kset_tid = kargs->set_tid; BUILD_BUG_ON(offsetofend(struct clone_args, tls) != CLONE_ARGS_SIZE_VER0); BUILD_BUG_ON(offsetofend(struct clone_args, set_tid_size) != CLONE_ARGS_SIZE_VER1); BUILD_BUG_ON(offsetofend(struct clone_args, cgroup) != CLONE_ARGS_SIZE_VER2); BUILD_BUG_ON(sizeof(struct clone_args) != CLONE_ARGS_SIZE_VER2); if (unlikely(usize > PAGE_SIZE)) return -E2BIG; if (unlikely(usize < CLONE_ARGS_SIZE_VER0)) return -EINVAL; err = copy_struct_from_user(&args, sizeof(args), uargs, usize); if (err) return err; if (unlikely(args.set_tid_size > MAX_PID_NS_LEVEL)) return -EINVAL; if (unlikely(!args.set_tid && args.set_tid_size > 0)) return -EINVAL; if (unlikely(args.set_tid && args.set_tid_size == 0)) return -EINVAL; /* * Verify that higher 32bits of exit_signal are unset and that * it is a valid signal */ if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) || !valid_signal(args.exit_signal))) return -EINVAL; if ((args.flags & CLONE_INTO_CGROUP) && (args.cgroup > INT_MAX || usize < CLONE_ARGS_SIZE_VER2)) return -EINVAL; *kargs = (struct kernel_clone_args){ .flags = args.flags, .pidfd = u64_to_user_ptr(args.pidfd), .child_tid = u64_to_user_ptr(args.child_tid), .parent_tid = u64_to_user_ptr(args.parent_tid), .exit_signal = args.exit_signal, .stack = args.stack, .stack_size = args.stack_size, .tls = args.tls, .set_tid_size = args.set_tid_size, .cgroup = args.cgroup, }; if (args.set_tid && copy_from_user(kset_tid, u64_to_user_ptr(args.set_tid), (kargs->set_tid_size * sizeof(pid_t)))) return -EFAULT; kargs->set_tid = kset_tid; return 0; } /** * clone3_stack_valid - check and prepare stack * @kargs: kernel clone args * * Verify that the stack arguments userspace gave us are sane. * In addition, set the stack direction for userspace since it's easy for us to * determine. */ static inline bool clone3_stack_valid(struct kernel_clone_args *kargs) { if (kargs->stack == 0) { if (kargs->stack_size > 0) return false; } else { if (kargs->stack_size == 0) return false; if (!access_ok((void __user *)kargs->stack, kargs->stack_size)) return false; #if !defined(CONFIG_STACK_GROWSUP) kargs->stack += kargs->stack_size; #endif } return true; } static bool clone3_args_valid(struct kernel_clone_args *kargs) { /* Verify that no unknown flags are passed along. */ if (kargs->flags & ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP)) return false; /* * - make the CLONE_DETACHED bit reusable for clone3 * - make the CSIGNAL bits reusable for clone3 */ if (kargs->flags & (CLONE_DETACHED | (CSIGNAL & (~CLONE_NEWTIME)))) return false; if ((kargs->flags & (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) == (CLONE_SIGHAND | CLONE_CLEAR_SIGHAND)) return false; if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) && kargs->exit_signal) return false; if (!clone3_stack_valid(kargs)) return false; return true; } /** * sys_clone3 - create a new process with specific properties * @uargs: argument structure * @size: size of @uargs * * clone3() is the extensible successor to clone()/clone2(). * It takes a struct as argument that is versioned by its size. * * Return: On success, a positive PID for the child process. * On error, a negative errno number. */ SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size) { int err; struct kernel_clone_args kargs; pid_t set_tid[MAX_PID_NS_LEVEL]; #ifdef __ARCH_BROKEN_SYS_CLONE3 #warning clone3() entry point is missing, please fix return -ENOSYS; #endif kargs.set_tid = set_tid; err = copy_clone_args_from_user(&kargs, uargs, size); if (err) return err; if (!clone3_args_valid(&kargs)) return -EINVAL; return kernel_clone(&kargs); } void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data) { struct task_struct *leader, *parent, *child; int res; read_lock(&tasklist_lock); leader = top = top->group_leader; down: for_each_thread(leader, parent) { list_for_each_entry(child, &parent->children, sibling) { res = visitor(child, data); if (res) { if (res < 0) goto out; leader = child; goto down; } up: ; } } if (leader != top) { child = leader; parent = child->real_parent; leader = parent->group_leader; goto up; } out: read_unlock(&tasklist_lock); } #ifndef ARCH_MIN_MMSTRUCT_ALIGN #define ARCH_MIN_MMSTRUCT_ALIGN 0 #endif static void sighand_ctor(void *data) { struct sighand_struct *sighand = data; spin_lock_init(&sighand->siglock); init_waitqueue_head(&sighand->signalfd_wqh); } void __init mm_cache_init(void) { unsigned int mm_size; /* * The mm_cpumask is located at the end of mm_struct, and is * dynamically sized based on the maximum CPU number this system * can have, taking hotplug into account (nr_cpu_ids). */ mm_size = sizeof(struct mm_struct) + cpumask_size() + mm_cid_size(); mm_cachep = kmem_cache_create_usercopy("mm_struct", mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), sizeof_field(struct mm_struct, saved_auxv), NULL); } void __init proc_caches_init(void) { sighand_cachep = kmem_cache_create("sighand_cache", sizeof(struct sighand_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU| SLAB_ACCOUNT, sighand_ctor); signal_cachep = kmem_cache_create("signal_cache", sizeof(struct signal_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); files_cachep = kmem_cache_create("files_cache", sizeof(struct files_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); fs_cachep = kmem_cache_create("fs_cache", sizeof(struct fs_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); mmap_init(); nsproxy_cache_init(); } /* * Check constraints on flags passed to the unshare system call. */ static int check_unshare_flags(unsigned long unshare_flags) { if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET| CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP| CLONE_NEWTIME)) return -EINVAL; /* * Not implemented, but pretend it works if there is nothing * to unshare. Note that unsharing the address space or the * signal handlers also need to unshare the signal queues (aka * CLONE_THREAD). */ if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) { if (!thread_group_empty(current)) return -EINVAL; } if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) { if (refcount_read(¤t->sighand->count) > 1) return -EINVAL; } if (unshare_flags & CLONE_VM) { if (!current_is_single_threaded()) return -EINVAL; } return 0; } /* * Unshare the filesystem structure if it is being shared */ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp) { struct fs_struct *fs = current->fs; if (!(unshare_flags & CLONE_FS) || !fs) return 0; /* don't need lock here; in the worst case we'll do useless copy */ if (fs->users == 1) return 0; *new_fsp = copy_fs_struct(fs); if (!*new_fsp) return -ENOMEM; return 0; } /* * Unshare file descriptor table if it is being shared */ static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp) { struct files_struct *fd = current->files; if ((unshare_flags & CLONE_FILES) && (fd && atomic_read(&fd->count) > 1)) { fd = dup_fd(fd, NULL); if (IS_ERR(fd)) return PTR_ERR(fd); *new_fdp = fd; } return 0; } /* * unshare allows a process to 'unshare' part of the process * context which was originally shared using clone. copy_* * functions used by kernel_clone() cannot be used here directly * because they modify an inactive task_struct that is being * constructed. Here we are modifying the current, active, * task_struct. */ int ksys_unshare(unsigned long unshare_flags) { struct fs_struct *fs, *new_fs = NULL; struct files_struct *new_fd = NULL; struct cred *new_cred = NULL; struct nsproxy *new_nsproxy = NULL; int do_sysvsem = 0; int err; /* * If unsharing a user namespace must also unshare the thread group * and unshare the filesystem root and working directories. */ if (unshare_flags & CLONE_NEWUSER) unshare_flags |= CLONE_THREAD | CLONE_FS; /* * If unsharing vm, must also unshare signal handlers. */ if (unshare_flags & CLONE_VM) unshare_flags |= CLONE_SIGHAND; /* * If unsharing a signal handlers, must also unshare the signal queues. */ if (unshare_flags & CLONE_SIGHAND) unshare_flags |= CLONE_THREAD; /* * If unsharing namespace, must also unshare filesystem information. */ if (unshare_flags & CLONE_NEWNS) unshare_flags |= CLONE_FS; err = check_unshare_flags(unshare_flags); if (err) goto bad_unshare_out; /* * CLONE_NEWIPC must also detach from the undolist: after switching * to a new ipc namespace, the semaphore arrays from the old * namespace are unreachable. */ if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM)) do_sysvsem = 1; err = unshare_fs(unshare_flags, &new_fs); if (err) goto bad_unshare_out; err = unshare_fd(unshare_flags, &new_fd); if (err) goto bad_unshare_cleanup_fs; err = unshare_userns(unshare_flags, &new_cred); if (err) goto bad_unshare_cleanup_fd; err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy, new_cred, new_fs); if (err) goto bad_unshare_cleanup_cred; if (new_cred) { err = set_cred_ucounts(new_cred); if (err) goto bad_unshare_cleanup_cred; } if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) { if (do_sysvsem) { /* * CLONE_SYSVSEM is equivalent to sys_exit(). */ exit_sem(current); } if (unshare_flags & CLONE_NEWIPC) { /* Orphan segments in old ns (see sem above). */ exit_shm(current); shm_init_task(current); } if (new_nsproxy) switch_task_namespaces(current, new_nsproxy); task_lock(current); if (new_fs) { fs = current->fs; read_seqlock_excl(&fs->seq); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; read_sequnlock_excl(&fs->seq); } if (new_fd) swap(current->files, new_fd); task_unlock(current); if (new_cred) { /* Install the new user namespace */ commit_creds(new_cred); new_cred = NULL; } } perf_event_namespaces(current); bad_unshare_cleanup_cred: if (new_cred) put_cred(new_cred); bad_unshare_cleanup_fd: if (new_fd) put_files_struct(new_fd); bad_unshare_cleanup_fs: if (new_fs) free_fs_struct(new_fs); bad_unshare_out: return err; } SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) { return ksys_unshare(unshare_flags); } /* * Helper to unshare the files of the current task. * We don't want to expose copy_files internals to * the exec layer of the kernel. */ int unshare_files(void) { struct task_struct *task = current; struct files_struct *old, *copy = NULL; int error; error = unshare_fd(CLONE_FILES, ©); if (error || !copy) return error; old = task->files; task_lock(task); task->files = copy; task_unlock(task); put_files_struct(old); return 0; } static int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int ret; int threads = max_threads; int min = 1; int max = MAX_THREADS; t = *table; t.data = &threads; t.extra1 = &min; t.extra2 = &max; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || !write) return ret; max_threads = threads; return 0; } static const struct ctl_table fork_sysctl_table[] = { { .procname = "threads-max", .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = sysctl_max_threads, }, }; static int __init init_fork_sysctl(void) { register_sysctl_init("kernel", fork_sysctl_table); return 0; } subsys_initcall(init_fork_sysctl); |
| 107 96 96 1 103 2 135 15 112 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _BCACHEFS_H #define _BCACHEFS_H /* * SOME HIGH LEVEL CODE DOCUMENTATION: * * Bcache mostly works with cache sets, cache devices, and backing devices. * * Support for multiple cache devices hasn't quite been finished off yet, but * it's about 95% plumbed through. A cache set and its cache devices is sort of * like a md raid array and its component devices. Most of the code doesn't care * about individual cache devices, the main abstraction is the cache set. * * Multiple cache devices is intended to give us the ability to mirror dirty * cached data and metadata, without mirroring clean cached data. * * Backing devices are different, in that they have a lifetime independent of a * cache set. When you register a newly formatted backing device it'll come up * in passthrough mode, and then you can attach and detach a backing device from * a cache set at runtime - while it's mounted and in use. Detaching implicitly * invalidates any cached data for that backing device. * * A cache set can have multiple (many) backing devices attached to it. * * There's also flash only volumes - this is the reason for the distinction * between struct cached_dev and struct bcache_device. A flash only volume * works much like a bcache device that has a backing device, except the * "cached" data is always dirty. The end result is that we get thin * provisioning with very little additional code. * * Flash only volumes work but they're not production ready because the moving * garbage collector needs more work. More on that later. * * BUCKETS/ALLOCATION: * * Bcache is primarily designed for caching, which means that in normal * operation all of our available space will be allocated. Thus, we need an * efficient way of deleting things from the cache so we can write new things to * it. * * To do this, we first divide the cache device up into buckets. A bucket is the * unit of allocation; they're typically around 1 mb - anywhere from 128k to 2M+ * works efficiently. * * Each bucket has a 16 bit priority, and an 8 bit generation associated with * it. The gens and priorities for all the buckets are stored contiguously and * packed on disk (in a linked list of buckets - aside from the superblock, all * of bcache's metadata is stored in buckets). * * The priority is used to implement an LRU. We reset a bucket's priority when * we allocate it or on cache it, and every so often we decrement the priority * of each bucket. It could be used to implement something more sophisticated, * if anyone ever gets around to it. * * The generation is used for invalidating buckets. Each pointer also has an 8 * bit generation embedded in it; for a pointer to be considered valid, its gen * must match the gen of the bucket it points into. Thus, to reuse a bucket all * we have to do is increment its gen (and write its new gen to disk; we batch * this up). * * Bcache is entirely COW - we never write twice to a bucket, even buckets that * contain metadata (including btree nodes). * * THE BTREE: * * Bcache is in large part design around the btree. * * At a high level, the btree is just an index of key -> ptr tuples. * * Keys represent extents, and thus have a size field. Keys also have a variable * number of pointers attached to them (potentially zero, which is handy for * invalidating the cache). * * The key itself is an inode:offset pair. The inode number corresponds to a * backing device or a flash only volume. The offset is the ending offset of the * extent within the inode - not the starting offset; this makes lookups * slightly more convenient. * * Pointers contain the cache device id, the offset on that device, and an 8 bit * generation number. More on the gen later. * * Index lookups are not fully abstracted - cache lookups in particular are * still somewhat mixed in with the btree code, but things are headed in that * direction. * * Updates are fairly well abstracted, though. There are two different ways of * updating the btree; insert and replace. * * BTREE_INSERT will just take a list of keys and insert them into the btree - * overwriting (possibly only partially) any extents they overlap with. This is * used to update the index after a write. * * BTREE_REPLACE is really cmpxchg(); it inserts a key into the btree iff it is * overwriting a key that matches another given key. This is used for inserting * data into the cache after a cache miss, and for background writeback, and for * the moving garbage collector. * * There is no "delete" operation; deleting things from the index is * accomplished by either by invalidating pointers (by incrementing a bucket's * gen) or by inserting a key with 0 pointers - which will overwrite anything * previously present at that location in the index. * * This means that there are always stale/invalid keys in the btree. They're * filtered out by the code that iterates through a btree node, and removed when * a btree node is rewritten. * * BTREE NODES: * * Our unit of allocation is a bucket, and we can't arbitrarily allocate and * free smaller than a bucket - so, that's how big our btree nodes are. * * (If buckets are really big we'll only use part of the bucket for a btree node * - no less than 1/4th - but a bucket still contains no more than a single * btree node. I'd actually like to change this, but for now we rely on the * bucket's gen for deleting btree nodes when we rewrite/split a node.) * * Anyways, btree nodes are big - big enough to be inefficient with a textbook * btree implementation. * * The way this is solved is that btree nodes are internally log structured; we * can append new keys to an existing btree node without rewriting it. This * means each set of keys we write is sorted, but the node is not. * * We maintain this log structure in memory - keeping 1Mb of keys sorted would * be expensive, and we have to distinguish between the keys we have written and * the keys we haven't. So to do a lookup in a btree node, we have to search * each sorted set. But we do merge written sets together lazily, so the cost of * these extra searches is quite low (normally most of the keys in a btree node * will be in one big set, and then there'll be one or two sets that are much * smaller). * * This log structure makes bcache's btree more of a hybrid between a * conventional btree and a compacting data structure, with some of the * advantages of both. * * GARBAGE COLLECTION: * * We can't just invalidate any bucket - it might contain dirty data or * metadata. If it once contained dirty data, other writes might overwrite it * later, leaving no valid pointers into that bucket in the index. * * Thus, the primary purpose of garbage collection is to find buckets to reuse. * It also counts how much valid data it each bucket currently contains, so that * allocation can reuse buckets sooner when they've been mostly overwritten. * * It also does some things that are really internal to the btree * implementation. If a btree node contains pointers that are stale by more than * some threshold, it rewrites the btree node to avoid the bucket's generation * wrapping around. It also merges adjacent btree nodes if they're empty enough. * * THE JOURNAL: * * Bcache's journal is not necessary for consistency; we always strictly * order metadata writes so that the btree and everything else is consistent on * disk in the event of an unclean shutdown, and in fact bcache had writeback * caching (with recovery from unclean shutdown) before journalling was * implemented. * * Rather, the journal is purely a performance optimization; we can't complete a * write until we've updated the index on disk, otherwise the cache would be * inconsistent in the event of an unclean shutdown. This means that without the * journal, on random write workloads we constantly have to update all the leaf * nodes in the btree, and those writes will be mostly empty (appending at most * a few keys each) - highly inefficient in terms of amount of metadata writes, * and it puts more strain on the various btree resorting/compacting code. * * The journal is just a log of keys we've inserted; on startup we just reinsert * all the keys in the open journal entries. That means that when we're updating * a node in the btree, we can wait until a 4k block of keys fills up before * writing them out. * * For simplicity, we only journal updates to leaf nodes; updates to parent * nodes are rare enough (since our leaf nodes are huge) that it wasn't worth * the complexity to deal with journalling them (in particular, journal replay) * - updates to non leaf nodes just happen synchronously (see btree_split()). */ #undef pr_fmt #ifdef __KERNEL__ #define pr_fmt(fmt) "bcachefs: %s() " fmt "\n", __func__ #else #define pr_fmt(fmt) "%s() " fmt "\n", __func__ #endif #ifdef CONFIG_BCACHEFS_DEBUG #define ENUMERATED_REF_DEBUG #endif #ifndef dynamic_fault #define dynamic_fault(...) 0 #endif #define race_fault(...) dynamic_fault("bcachefs:race") #include <linux/backing-dev-defs.h> #include <linux/bug.h> #include <linux/bio.h> #include <linux/closure.h> #include <linux/kobject.h> #include <linux/list.h> #include <linux/math64.h> #include <linux/mutex.h> #include <linux/percpu-refcount.h> #include <linux/percpu-rwsem.h> #include <linux/refcount.h> #include <linux/rhashtable.h> #include <linux/rwsem.h> #include <linux/semaphore.h> #include <linux/seqlock.h> #include <linux/shrinker.h> #include <linux/srcu.h> #include <linux/types.h> #include <linux/workqueue.h> #include <linux/zstd.h> #include <linux/unicode.h> #include "bcachefs_format.h" #include "btree_journal_iter_types.h" #include "disk_accounting_types.h" #include "errcode.h" #include "fast_list.h" #include "fifo.h" #include "nocow_locking_types.h" #include "opts.h" #include "sb-errors_types.h" #include "seqmutex.h" #include "snapshot_types.h" #include "time_stats.h" #include "util.h" #include "alloc_types.h" #include "async_objs_types.h" #include "btree_gc_types.h" #include "btree_types.h" #include "btree_node_scan_types.h" #include "btree_write_buffer_types.h" #include "buckets_types.h" #include "buckets_waiting_for_journal_types.h" #include "clock_types.h" #include "disk_groups_types.h" #include "ec_types.h" #include "enumerated_ref_types.h" #include "journal_types.h" #include "keylist_types.h" #include "quota_types.h" #include "rebalance_types.h" #include "recovery_passes_types.h" #include "replicas_types.h" #include "sb-members_types.h" #include "subvolume_types.h" #include "super_types.h" #include "thread_with_file_types.h" #include "trace.h" #define count_event(_c, _name) this_cpu_inc((_c)->counters[BCH_COUNTER_##_name]) #define trace_and_count(_c, _name, ...) \ do { \ count_event(_c, _name); \ trace_##_name(__VA_ARGS__); \ } while (0) #define bch2_fs_init_fault(name) \ dynamic_fault("bcachefs:bch_fs_init:" name) #define bch2_meta_read_fault(name) \ dynamic_fault("bcachefs:meta:read:" name) #define bch2_meta_write_fault(name) \ dynamic_fault("bcachefs:meta:write:" name) #ifdef __KERNEL__ #define BCACHEFS_LOG_PREFIX #endif #ifdef BCACHEFS_LOG_PREFIX #define bch2_log_msg(_c, fmt) "bcachefs (%s): " fmt, ((_c)->name) #define bch2_fmt_dev(_ca, fmt) "bcachefs (%s): " fmt "\n", ((_ca)->name) #define bch2_fmt_dev_offset(_ca, _offset, fmt) "bcachefs (%s sector %llu): " fmt "\n", ((_ca)->name), (_offset) #define bch2_fmt_inum(_c, _inum, fmt) "bcachefs (%s inum %llu): " fmt "\n", ((_c)->name), (_inum) #define bch2_fmt_inum_offset(_c, _inum, _offset, fmt) \ "bcachefs (%s inum %llu offset %llu): " fmt "\n", ((_c)->name), (_inum), (_offset) #else #define bch2_log_msg(_c, fmt) fmt #define bch2_fmt_dev(_ca, fmt) "%s: " fmt "\n", ((_ca)->name) #define bch2_fmt_dev_offset(_ca, _offset, fmt) "%s sector %llu: " fmt "\n", ((_ca)->name), (_offset) #define bch2_fmt_inum(_c, _inum, fmt) "inum %llu: " fmt "\n", (_inum) #define bch2_fmt_inum_offset(_c, _inum, _offset, fmt) \ "inum %llu offset %llu: " fmt "\n", (_inum), (_offset) #endif #define bch2_fmt(_c, fmt) bch2_log_msg(_c, fmt "\n") void bch2_print_str(struct bch_fs *, const char *, const char *); __printf(2, 3) void bch2_print_opts(struct bch_opts *, const char *, ...); __printf(2, 3) void __bch2_print(struct bch_fs *c, const char *fmt, ...); #define maybe_dev_to_fs(_c) _Generic((_c), \ struct bch_dev *: ((struct bch_dev *) (_c))->fs, \ struct bch_fs *: (_c)) #define bch2_print(_c, ...) __bch2_print(maybe_dev_to_fs(_c), __VA_ARGS__) #define bch2_print_ratelimited(_c, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ \ if (__ratelimit(&_rs)) \ bch2_print(_c, __VA_ARGS__); \ } while (0) #define bch2_print_str_ratelimited(_c, ...) \ do { \ static DEFINE_RATELIMIT_STATE(_rs, \ DEFAULT_RATELIMIT_INTERVAL, \ DEFAULT_RATELIMIT_BURST); \ \ if (__ratelimit(&_rs)) \ bch2_print_str(_c, __VA_ARGS__); \ } while (0) #define bch_info(c, fmt, ...) \ bch2_print(c, KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_info_ratelimited(c, fmt, ...) \ bch2_print_ratelimited(c, KERN_INFO bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_notice(c, fmt, ...) \ bch2_print(c, KERN_NOTICE bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_warn(c, fmt, ...) \ bch2_print(c, KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_warn_ratelimited(c, fmt, ...) \ bch2_print_ratelimited(c, KERN_WARNING bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_err(c, fmt, ...) \ bch2_print(c, KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_err_dev(ca, fmt, ...) \ bch2_print(c, KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__) #define bch_err_dev_offset(ca, _offset, fmt, ...) \ bch2_print(c, KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__) #define bch_err_inum(c, _inum, fmt, ...) \ bch2_print(c, KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__) #define bch_err_inum_offset(c, _inum, _offset, fmt, ...) \ bch2_print(c, KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__) #define bch_err_ratelimited(c, fmt, ...) \ bch2_print_ratelimited(c, KERN_ERR bch2_fmt(c, fmt), ##__VA_ARGS__) #define bch_err_dev_ratelimited(ca, fmt, ...) \ bch2_print_ratelimited(ca, KERN_ERR bch2_fmt_dev(ca, fmt), ##__VA_ARGS__) #define bch_err_dev_offset_ratelimited(ca, _offset, fmt, ...) \ bch2_print_ratelimited(ca, KERN_ERR bch2_fmt_dev_offset(ca, _offset, fmt), ##__VA_ARGS__) #define bch_err_inum_ratelimited(c, _inum, fmt, ...) \ bch2_print_ratelimited(c, KERN_ERR bch2_fmt_inum(c, _inum, fmt), ##__VA_ARGS__) #define bch_err_inum_offset_ratelimited(c, _inum, _offset, fmt, ...) \ bch2_print_ratelimited(c, KERN_ERR bch2_fmt_inum_offset(c, _inum, _offset, fmt), ##__VA_ARGS__) static inline bool should_print_err(int err) { return err && !bch2_err_matches(err, BCH_ERR_transaction_restart); } #define bch_err_fn(_c, _ret) \ do { \ if (should_print_err(_ret)) \ bch_err(_c, "%s(): error %s", __func__, bch2_err_str(_ret));\ } while (0) #define bch_err_fn_ratelimited(_c, _ret) \ do { \ if (should_print_err(_ret)) \ bch_err_ratelimited(_c, "%s(): error %s", __func__, bch2_err_str(_ret));\ } while (0) #define bch_err_msg(_c, _ret, _msg, ...) \ do { \ if (should_print_err(_ret)) \ bch_err(_c, "%s(): error " _msg " %s", __func__, \ ##__VA_ARGS__, bch2_err_str(_ret)); \ } while (0) #define bch_verbose(c, fmt, ...) \ do { \ if ((c)->opts.verbose) \ bch_info(c, fmt, ##__VA_ARGS__); \ } while (0) #define bch_verbose_ratelimited(c, fmt, ...) \ do { \ if ((c)->opts.verbose) \ bch_info_ratelimited(c, fmt, ##__VA_ARGS__); \ } while (0) #define pr_verbose_init(opts, fmt, ...) \ do { \ if (opt_get(opts, verbose)) \ pr_info(fmt, ##__VA_ARGS__); \ } while (0) static inline int __bch2_err_trace(struct bch_fs *c, int err) { trace_error_throw(c, err, _THIS_IP_); return err; } #define bch_err_throw(_c, _err) __bch2_err_trace(_c, -BCH_ERR_##_err) /* Parameters that are useful for debugging, but should always be compiled in: */ #define BCH_DEBUG_PARAMS_ALWAYS() \ BCH_DEBUG_PARAM(key_merging_disabled, \ "Disables merging of extents") \ BCH_DEBUG_PARAM(btree_node_merging_disabled, \ "Disables merging of btree nodes") \ BCH_DEBUG_PARAM(btree_gc_always_rewrite, \ "Causes mark and sweep to compact and rewrite every " \ "btree node it traverses") \ BCH_DEBUG_PARAM(btree_gc_rewrite_disabled, \ "Disables rewriting of btree nodes during mark and sweep")\ BCH_DEBUG_PARAM(btree_shrinker_disabled, \ "Disables the shrinker callback for the btree node cache")\ BCH_DEBUG_PARAM(verify_btree_ondisk, \ "Reread btree nodes at various points to verify the " \ "mergesort in the read path against modifications " \ "done in memory") \ BCH_DEBUG_PARAM(verify_all_btree_replicas, \ "When reading btree nodes, read all replicas and " \ "compare them") \ BCH_DEBUG_PARAM(backpointers_no_use_write_buffer, \ "Don't use the write buffer for backpointers, enabling "\ "extra runtime checks") \ BCH_DEBUG_PARAM(debug_check_btree_locking, \ "Enable additional asserts for btree locking") \ BCH_DEBUG_PARAM(debug_check_iterators, \ "Enables extra verification for btree iterators") \ BCH_DEBUG_PARAM(debug_check_bset_lookups, \ "Enables extra verification for bset lookups") \ BCH_DEBUG_PARAM(debug_check_btree_accounting, \ "Verify btree accounting for keys within a node") \ BCH_DEBUG_PARAM(debug_check_bkey_unpack, \ "Enables extra verification for bkey unpack") /* Parameters that should only be compiled in debug mode: */ #define BCH_DEBUG_PARAMS_DEBUG() \ BCH_DEBUG_PARAM(journal_seq_verify, \ "Store the journal sequence number in the version " \ "number of every btree key, and verify that btree " \ "update ordering is preserved during recovery") \ BCH_DEBUG_PARAM(inject_invalid_keys, \ "Store the journal sequence number in the version " \ "number of every btree key, and verify that btree " \ "update ordering is preserved during recovery") \ BCH_DEBUG_PARAM(test_alloc_startup, \ "Force allocator startup to use the slowpath where it" \ "can't find enough free buckets without invalidating" \ "cached data") \ BCH_DEBUG_PARAM(force_reconstruct_read, \ "Force reads to use the reconstruct path, when reading" \ "from erasure coded extents") \ BCH_DEBUG_PARAM(test_restart_gc, \ "Test restarting mark and sweep gc when bucket gens change") #define BCH_DEBUG_PARAMS_ALL() BCH_DEBUG_PARAMS_ALWAYS() BCH_DEBUG_PARAMS_DEBUG() #ifdef CONFIG_BCACHEFS_DEBUG #define BCH_DEBUG_PARAMS() BCH_DEBUG_PARAMS_ALL() #else #define BCH_DEBUG_PARAMS() BCH_DEBUG_PARAMS_ALWAYS() #endif #define BCH_DEBUG_PARAM(name, description) extern struct static_key_false bch2_##name; BCH_DEBUG_PARAMS_ALL() #undef BCH_DEBUG_PARAM #define BCH_TIME_STATS() \ x(btree_node_mem_alloc) \ x(btree_node_split) \ x(btree_node_compact) \ x(btree_node_merge) \ x(btree_node_sort) \ x(btree_node_get) \ x(btree_node_read) \ x(btree_node_read_done) \ x(btree_node_write) \ x(btree_interior_update_foreground) \ x(btree_interior_update_total) \ x(btree_gc) \ x(data_write) \ x(data_write_to_submit) \ x(data_write_to_queue) \ x(data_write_to_btree_update) \ x(data_write_btree_update) \ x(data_read) \ x(data_promote) \ x(journal_flush_write) \ x(journal_noflush_write) \ x(journal_flush_seq) \ x(blocked_journal_low_on_space) \ x(blocked_journal_low_on_pin) \ x(blocked_journal_max_in_flight) \ x(blocked_journal_max_open) \ x(blocked_key_cache_flush) \ x(blocked_allocate) \ x(blocked_allocate_open_bucket) \ x(blocked_write_buffer_full) \ x(nocow_lock_contended) enum bch_time_stats { #define x(name) BCH_TIME_##name, BCH_TIME_STATS() #undef x BCH_TIME_STAT_NR }; /* Number of nodes btree coalesce will try to coalesce at once */ #define GC_MERGE_NODES 4U /* Maximum number of nodes we might need to allocate atomically: */ #define BTREE_RESERVE_MAX (BTREE_MAX_DEPTH + (BTREE_MAX_DEPTH - 1)) /* Size of the freelist we allocate btree nodes from: */ #define BTREE_NODE_RESERVE (BTREE_RESERVE_MAX * 4) #define BTREE_NODE_OPEN_BUCKET_RESERVE (BTREE_RESERVE_MAX * BCH_REPLICAS_MAX) struct btree; struct io_count { u64 sectors[2][BCH_DATA_NR]; }; struct discard_in_flight { bool in_progress:1; u64 bucket:63; }; #define BCH_DEV_READ_REFS() \ x(bch2_online_devs) \ x(trans_mark_dev_sbs) \ x(read_fua_test) \ x(sb_field_resize) \ x(write_super) \ x(journal_read) \ x(fs_journal_alloc) \ x(fs_resize_on_mount) \ x(btree_node_read) \ x(btree_node_read_all_replicas) \ x(btree_node_scrub) \ x(btree_node_write) \ x(btree_node_scan) \ x(btree_verify_replicas) \ x(btree_node_ondisk_to_text) \ x(io_read) \ x(check_extent_checksums) \ x(ec_block) enum bch_dev_read_ref { #define x(n) BCH_DEV_READ_REF_##n, BCH_DEV_READ_REFS() #undef x BCH_DEV_READ_REF_NR, }; #define BCH_DEV_WRITE_REFS() \ x(journal_write) \ x(journal_do_discards) \ x(dev_do_discards) \ x(discard_one_bucket_fast) \ x(do_invalidates) \ x(nocow_flush) \ x(io_write) \ x(ec_block) \ x(ec_bucket_zero) enum bch_dev_write_ref { #define x(n) BCH_DEV_WRITE_REF_##n, BCH_DEV_WRITE_REFS() #undef x BCH_DEV_WRITE_REF_NR, }; struct bucket_bitmap { unsigned long *buckets; u64 nr; struct mutex lock; }; struct bch_dev { struct kobject kobj; #ifdef CONFIG_BCACHEFS_DEBUG atomic_long_t ref; bool dying; unsigned long last_put; #else struct percpu_ref ref; #endif struct completion ref_completion; struct enumerated_ref io_ref[2]; struct bch_fs *fs; u8 dev_idx; /* * Cached version of this device's member info from superblock * Committed by bch2_write_super() -> bch_fs_mi_update() */ struct bch_member_cpu mi; atomic64_t errors[BCH_MEMBER_ERROR_NR]; unsigned long write_errors_start; __uuid_t uuid; char name[BDEVNAME_SIZE]; struct bch_sb_handle disk_sb; struct bch_sb *sb_read_scratch; int sb_write_error; dev_t dev; atomic_t flush_seq; struct bch_devs_mask self; /* * Buckets: * Per-bucket arrays are protected by either rcu_read_lock or * state_lock, for device resize. */ GENRADIX(struct bucket) buckets_gc; struct bucket_gens __rcu *bucket_gens; u8 *oldest_gen; unsigned long *buckets_nouse; struct bucket_bitmap bucket_backpointer_mismatch; struct bucket_bitmap bucket_backpointer_empty; struct bch_dev_usage_full __percpu *usage; /* Allocator: */ u64 alloc_cursor[3]; unsigned nr_open_buckets; unsigned nr_partial_buckets; unsigned nr_btree_reserve; struct work_struct invalidate_work; struct work_struct discard_work; struct mutex discard_buckets_in_flight_lock; DARRAY(struct discard_in_flight) discard_buckets_in_flight; struct work_struct discard_fast_work; atomic64_t rebalance_work; struct journal_device journal; u64 prev_journal_sector; struct work_struct io_error_work; /* The rest of this all shows up in sysfs */ atomic64_t cur_latency[2]; struct bch2_time_stats_quantiles io_latency[2]; #define CONGESTED_MAX 1024 atomic_t congested; u64 congested_last; struct io_count __percpu *io_done; }; /* * initial_gc_unfixed * error * topology error */ #define BCH_FS_FLAGS() \ x(new_fs) \ x(started) \ x(clean_recovery) \ x(btree_running) \ x(accounting_replay_done) \ x(may_go_rw) \ x(rw) \ x(rw_init_done) \ x(was_rw) \ x(stopping) \ x(emergency_ro) \ x(going_ro) \ x(write_disable_complete) \ x(clean_shutdown) \ x(in_recovery) \ x(in_fsck) \ x(initial_gc_unfixed) \ x(need_delete_dead_snapshots) \ x(error) \ x(topology_error) \ x(errors_fixed) \ x(errors_not_fixed) \ x(no_invalid_checks) \ x(discard_mount_opt_set) \ enum bch_fs_flags { #define x(n) BCH_FS_##n, BCH_FS_FLAGS() #undef x }; struct btree_debug { unsigned id; }; #define BCH_TRANSACTIONS_NR 128 struct btree_transaction_stats { struct bch2_time_stats duration; struct bch2_time_stats lock_hold_times; struct mutex lock; unsigned nr_max_paths; unsigned max_mem; #ifdef CONFIG_BCACHEFS_TRANS_KMALLOC_TRACE darray_trans_kmalloc_trace trans_kmalloc_trace; #endif char *max_paths_text; }; struct bch_fs_pcpu { u64 sectors_available; }; struct journal_seq_blacklist_table { size_t nr; struct journal_seq_blacklist_table_entry { u64 start; u64 end; bool dirty; } entries[]; }; struct btree_trans_buf { struct btree_trans *trans; }; #define BCH_WRITE_REFS() \ x(journal) \ x(trans) \ x(write) \ x(promote) \ x(node_rewrite) \ x(stripe_create) \ x(stripe_delete) \ x(reflink) \ x(fallocate) \ x(fsync) \ x(dio_write) \ x(discard) \ x(discard_fast) \ x(check_discard_freespace_key) \ x(invalidate) \ x(delete_dead_snapshots) \ x(gc_gens) \ x(snapshot_delete_pagecache) \ x(sysfs) \ x(btree_write_buffer) \ x(btree_node_scrub) \ x(async_recovery_passes) \ x(ioctl_data) enum bch_write_ref { #define x(n) BCH_WRITE_REF_##n, BCH_WRITE_REFS() #undef x BCH_WRITE_REF_NR, }; #define BCH_FS_DEFAULT_UTF8_ENCODING UNICODE_AGE(12, 1, 0) struct bch_fs { struct closure cl; struct list_head list; struct kobject kobj; struct kobject counters_kobj; struct kobject internal; struct kobject opts_dir; struct kobject time_stats; unsigned long flags; int minor; struct device *chardev; struct super_block *vfs_sb; dev_t dev; char name[40]; struct stdio_redirect *stdio; struct task_struct *stdio_filter; /* ro/rw, add/remove/resize devices: */ struct rw_semaphore state_lock; /* Counts outstanding writes, for clean transition to read-only */ struct enumerated_ref writes; /* * Certain operations are only allowed in single threaded mode, during * recovery, and we want to assert that this is the case: */ struct task_struct *recovery_task; /* * Analagous to c->writes, for asynchronous ops that don't necessarily * need fs to be read-write */ refcount_t ro_ref; wait_queue_head_t ro_ref_wait; struct work_struct read_only_work; struct bch_dev __rcu *devs[BCH_SB_MEMBERS_MAX]; struct bch_accounting_mem accounting; struct bch_replicas_cpu replicas; struct bch_replicas_cpu replicas_gc; struct mutex replicas_gc_lock; struct journal_entry_res btree_root_journal_res; struct journal_entry_res clock_journal_res; struct bch_disk_groups_cpu __rcu *disk_groups; struct bch_opts opts; /* Updated by bch2_sb_update():*/ struct { __uuid_t uuid; __uuid_t user_uuid; u16 version; u16 version_incompat; u16 version_incompat_allowed; u16 version_min; u16 version_upgrade_complete; u8 nr_devices; u8 clean; bool multi_device; /* true if we've ever had more than one device */ u8 encryption_type; u64 time_base_lo; u32 time_base_hi; unsigned time_units_per_sec; unsigned nsec_per_time_unit; u64 features; u64 compat; u64 recovery_passes_required; unsigned long errors_silent[BITS_TO_LONGS(BCH_FSCK_ERR_MAX)]; u64 btrees_lost_data; } sb; DARRAY(enum bcachefs_metadata_version) incompat_versions_requested; struct unicode_map *cf_encoding; struct bch_sb_handle disk_sb; unsigned short block_bits; /* ilog2(block_size) */ u16 btree_foreground_merge_threshold; struct closure sb_write; struct mutex sb_lock; /* snapshot.c: */ struct snapshot_table __rcu *snapshots; struct mutex snapshot_table_lock; struct rw_semaphore snapshot_create_lock; struct snapshot_delete snapshot_delete; struct work_struct snapshot_wait_for_pagecache_and_delete_work; snapshot_id_list snapshots_unlinked; struct mutex snapshots_unlinked_lock; /* BTREE CACHE */ struct bio_set btree_bio; struct workqueue_struct *btree_read_complete_wq; struct workqueue_struct *btree_write_submit_wq; struct btree_root btree_roots_known[BTREE_ID_NR]; DARRAY(struct btree_root) btree_roots_extra; struct mutex btree_root_lock; struct btree_cache btree_cache; /* * Cache of allocated btree nodes - if we allocate a btree node and * don't use it, if we free it that space can't be reused until going * _all_ the way through the allocator (which exposes us to a livelock * when allocating btree reserves fail halfway through) - instead, we * can stick them here: */ struct btree_alloc btree_reserve_cache[BTREE_NODE_RESERVE * 2]; unsigned btree_reserve_cache_nr; struct mutex btree_reserve_cache_lock; mempool_t btree_interior_update_pool; struct list_head btree_interior_update_list; struct list_head btree_interior_updates_unwritten; struct mutex btree_interior_update_lock; struct closure_waitlist btree_interior_update_wait; struct workqueue_struct *btree_interior_update_worker; struct work_struct btree_interior_update_work; struct workqueue_struct *btree_node_rewrite_worker; struct list_head btree_node_rewrites; struct list_head btree_node_rewrites_pending; spinlock_t btree_node_rewrites_lock; struct closure_waitlist btree_node_rewrites_wait; /* btree_io.c: */ spinlock_t btree_write_error_lock; struct btree_write_stats { atomic64_t nr; atomic64_t bytes; } btree_write_stats[BTREE_WRITE_TYPE_NR]; /* btree_iter.c: */ struct seqmutex btree_trans_lock; struct list_head btree_trans_list; mempool_t btree_trans_pool; mempool_t btree_trans_mem_pool; struct btree_trans_buf __percpu *btree_trans_bufs; struct srcu_struct btree_trans_barrier; bool btree_trans_barrier_initialized; struct btree_key_cache btree_key_cache; unsigned btree_key_cache_btrees; struct btree_write_buffer btree_write_buffer; struct workqueue_struct *btree_update_wq; struct workqueue_struct *btree_write_complete_wq; /* copygc needs its own workqueue for index updates.. */ struct workqueue_struct *copygc_wq; /* * Use a dedicated wq for write ref holder tasks. Required to avoid * dependency problems with other wq tasks that can block on ref * draining, such as read-only transition. */ struct workqueue_struct *write_ref_wq; /* ALLOCATION */ struct bch_devs_mask online_devs; struct bch_devs_mask rw_devs[BCH_DATA_NR]; unsigned long rw_devs_change_count; u64 capacity; /* sectors */ u64 reserved; /* sectors */ /* * When capacity _decreases_ (due to a disk being removed), we * increment capacity_gen - this invalidates outstanding reservations * and forces them to be revalidated */ u32 capacity_gen; unsigned bucket_size_max; atomic64_t sectors_available; struct mutex sectors_available_lock; struct bch_fs_pcpu __percpu *pcpu; struct percpu_rw_semaphore mark_lock; seqcount_t usage_lock; struct bch_fs_usage_base __percpu *usage; u64 __percpu *online_reserved; unsigned long allocator_last_stuck; struct io_clock io_clock[2]; /* JOURNAL SEQ BLACKLIST */ struct journal_seq_blacklist_table * journal_seq_blacklist_table; /* ALLOCATOR */ spinlock_t freelist_lock; struct closure_waitlist freelist_wait; open_bucket_idx_t open_buckets_freelist; open_bucket_idx_t open_buckets_nr_free; struct closure_waitlist open_buckets_wait; struct open_bucket open_buckets[OPEN_BUCKETS_COUNT]; open_bucket_idx_t open_buckets_hash[OPEN_BUCKETS_COUNT]; open_bucket_idx_t open_buckets_partial[OPEN_BUCKETS_COUNT]; open_bucket_idx_t open_buckets_partial_nr; struct write_point btree_write_point; struct write_point rebalance_write_point; struct write_point write_points[WRITE_POINT_MAX]; struct hlist_head write_points_hash[WRITE_POINT_HASH_NR]; struct mutex write_points_hash_lock; unsigned write_points_nr; struct buckets_waiting_for_journal buckets_waiting_for_journal; /* GARBAGE COLLECTION */ struct work_struct gc_gens_work; unsigned long gc_count; enum btree_id gc_gens_btree; struct bpos gc_gens_pos; /* * Tracks GC's progress - everything in the range [ZERO_KEY..gc_cur_pos] * has been marked by GC. * * gc_cur_phase is a superset of btree_ids (BTREE_ID_extents etc.) * * Protected by gc_pos_lock. Only written to by GC thread, so GC thread * can read without a lock. */ seqcount_t gc_pos_lock; struct gc_pos gc_pos; /* * The allocation code needs gc_mark in struct bucket to be correct, but * it's not while a gc is in progress. */ struct rw_semaphore gc_lock; struct mutex gc_gens_lock; /* IO PATH */ struct semaphore io_in_flight; struct bio_set bio_read; struct bio_set bio_read_split; struct bio_set bio_write; struct bio_set replica_set; struct mutex bio_bounce_pages_lock; mempool_t bio_bounce_pages; struct bucket_nocow_lock_table nocow_locks; struct rhashtable promote_table; #ifdef CONFIG_BCACHEFS_ASYNC_OBJECT_LISTS struct async_obj_list async_objs[BCH_ASYNC_OBJ_NR]; #endif mempool_t compression_bounce[2]; mempool_t compress_workspace[BCH_COMPRESSION_OPT_NR]; size_t zstd_workspace_size; struct bch_key chacha20_key; bool chacha20_key_set; atomic64_t key_version; mempool_t large_bkey_pool; /* MOVE.C */ struct list_head moving_context_list; struct mutex moving_context_lock; /* REBALANCE */ struct bch_fs_rebalance rebalance; /* COPYGC */ struct task_struct *copygc_thread; struct write_point copygc_write_point; s64 copygc_wait_at; s64 copygc_wait; bool copygc_running; wait_queue_head_t copygc_running_wq; /* STRIPES: */ GENRADIX(struct gc_stripe) gc_stripes; struct hlist_head ec_stripes_new[32]; spinlock_t ec_stripes_new_lock; /* ERASURE CODING */ struct list_head ec_stripe_head_list; struct mutex ec_stripe_head_lock; struct list_head ec_stripe_new_list; struct mutex ec_stripe_new_lock; wait_queue_head_t ec_stripe_new_wait; struct work_struct ec_stripe_create_work; u64 ec_stripe_hint; struct work_struct ec_stripe_delete_work; struct bio_set ec_bioset; /* REFLINK */ reflink_gc_table reflink_gc_table; size_t reflink_gc_nr; /* fs.c */ struct list_head vfs_inodes_list; struct mutex vfs_inodes_lock; struct rhashtable vfs_inodes_table; struct rhltable vfs_inodes_by_inum_table; /* VFS IO PATH - fs-io.c */ struct bio_set writepage_bioset; struct bio_set dio_write_bioset; struct bio_set dio_read_bioset; struct bio_set nocow_flush_bioset; /* QUOTAS */ struct bch_memquota_type quotas[QTYP_NR]; /* RECOVERY */ u64 journal_replay_seq_start; u64 journal_replay_seq_end; struct bch_fs_recovery recovery; /* DEBUG JUNK */ struct dentry *fs_debug_dir; struct dentry *btree_debug_dir; struct dentry *async_obj_dir; struct btree_debug btree_debug[BTREE_ID_NR]; struct btree *verify_data; struct btree_node *verify_ondisk; struct mutex verify_lock; /* * A btree node on disk could have too many bsets for an iterator to fit * on the stack - have to dynamically allocate them */ mempool_t fill_iter; mempool_t btree_bounce_pool; struct journal journal; GENRADIX(struct journal_replay *) journal_entries; u64 journal_entries_base_seq; struct journal_keys journal_keys; struct list_head journal_iters; struct find_btree_nodes found_btree_nodes; u64 last_bucket_seq_cleanup; u64 counters_on_mount[BCH_COUNTER_NR]; u64 __percpu *counters; struct bch2_time_stats times[BCH_TIME_STAT_NR]; struct btree_transaction_stats btree_transaction_stats[BCH_TRANSACTIONS_NR]; /* ERRORS */ struct list_head fsck_error_msgs; struct mutex fsck_error_msgs_lock; bool fsck_alloc_msgs_err; bch_sb_errors_cpu fsck_error_counts; struct mutex fsck_error_counts_lock; }; extern struct wait_queue_head bch2_read_only_wait; static inline bool bch2_ro_ref_tryget(struct bch_fs *c) { if (test_bit(BCH_FS_stopping, &c->flags)) return false; return refcount_inc_not_zero(&c->ro_ref); } static inline void bch2_ro_ref_put(struct bch_fs *c) { if (refcount_dec_and_test(&c->ro_ref)) wake_up(&c->ro_ref_wait); } static inline void bch2_set_ra_pages(struct bch_fs *c, unsigned ra_pages) { #ifndef NO_BCACHEFS_FS if (c->vfs_sb) c->vfs_sb->s_bdi->ra_pages = ra_pages; #endif } static inline unsigned bucket_bytes(const struct bch_dev *ca) { return ca->mi.bucket_size << 9; } static inline unsigned block_bytes(const struct bch_fs *c) { return c->opts.block_size; } static inline unsigned block_sectors(const struct bch_fs *c) { return c->opts.block_size >> 9; } static inline bool btree_id_cached(const struct bch_fs *c, enum btree_id btree) { return c->btree_key_cache_btrees & (1U << btree); } static inline struct timespec64 bch2_time_to_timespec(const struct bch_fs *c, s64 time) { struct timespec64 t; s64 sec; s32 rem; time += c->sb.time_base_lo; sec = div_s64_rem(time, c->sb.time_units_per_sec, &rem); set_normalized_timespec64(&t, sec, rem * (s64)c->sb.nsec_per_time_unit); return t; } static inline s64 timespec_to_bch2_time(const struct bch_fs *c, struct timespec64 ts) { return (ts.tv_sec * c->sb.time_units_per_sec + (int) ts.tv_nsec / c->sb.nsec_per_time_unit) - c->sb.time_base_lo; } static inline s64 bch2_current_time(const struct bch_fs *c) { struct timespec64 now; ktime_get_coarse_real_ts64(&now); return timespec_to_bch2_time(c, now); } static inline u64 bch2_current_io_time(const struct bch_fs *c, int rw) { return max(1ULL, (u64) atomic64_read(&c->io_clock[rw].now) & LRU_TIME_MAX); } static inline struct stdio_redirect *bch2_fs_stdio_redirect(struct bch_fs *c) { struct stdio_redirect *stdio = c->stdio; if (c->stdio_filter && c->stdio_filter != current) stdio = NULL; return stdio; } static inline unsigned metadata_replicas_required(struct bch_fs *c) { return min(c->opts.metadata_replicas, c->opts.metadata_replicas_required); } static inline unsigned data_replicas_required(struct bch_fs *c) { return min(c->opts.data_replicas, c->opts.data_replicas_required); } #define BKEY_PADDED_ONSTACK(key, pad) \ struct { struct bkey_i key; __u64 key ## _pad[pad]; } /* * This is needed because discard is both a filesystem option and a device * option, and mount options are supposed to apply to that mount and not be * persisted, i.e. if it's set as a mount option we can't propagate it to the * device. */ static inline bool bch2_discard_opt_enabled(struct bch_fs *c, struct bch_dev *ca) { return test_bit(BCH_FS_discard_mount_opt_set, &c->flags) ? c->opts.discard : ca->mi.discard; } static inline bool bch2_fs_casefold_enabled(struct bch_fs *c) { #ifdef CONFIG_UNICODE return !c->opts.casefold_disabled; #else return false; #endif } #endif /* _BCACHEFS_H */ |
| 3 3 2 2 2 1 1 2 1 1 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 | // SPDX-License-Identifier: GPL-2.0-or-later /* * dlmfs.c * * Code which implements the kernel side of a minimal userspace * interface to our DLM. This file handles the virtual file system * used for communication with userspace. Credit should go to ramfs, * which was a template for the fs side of this module. * * Copyright (C) 2003, 2004 Oracle. All rights reserved. */ /* Simple VFS hooks based on: */ /* * Resizable simple ram filesystem for Linux. * * Copyright (C) 2000 Linus Torvalds. * 2000 Transmeta Corp. */ #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/pagemap.h> #include <linux/types.h> #include <linux/slab.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/string.h> #include <linux/backing-dev.h> #include <linux/poll.h> #include <linux/uaccess.h> #include "../stackglue.h" #include "userdlm.h" #define MLOG_MASK_PREFIX ML_DLMFS #include "../cluster/masklog.h" static const struct super_operations dlmfs_ops; static const struct file_operations dlmfs_file_operations; static const struct inode_operations dlmfs_dir_inode_operations; static const struct inode_operations dlmfs_root_inode_operations; static const struct inode_operations dlmfs_file_inode_operations; static struct kmem_cache *dlmfs_inode_cache; struct workqueue_struct *user_dlm_worker; /* * These are the ABI capabilities of dlmfs. * * Over time, dlmfs has added some features that were not part of the * initial ABI. Unfortunately, some of these features are not detectable * via standard usage. For example, Linux's default poll always returns * EPOLLIN, so there is no way for a caller of poll(2) to know when dlmfs * added poll support. Instead, we provide this list of new capabilities. * * Capabilities is a read-only attribute. We do it as a module parameter * so we can discover it whether dlmfs is built in, loaded, or even not * loaded. * * The ABI features are local to this machine's dlmfs mount. This is * distinct from the locking protocol, which is concerned with inter-node * interaction. * * Capabilities: * - bast : EPOLLIN against the file descriptor of a held lock * signifies a bast fired on the lock. */ #define DLMFS_CAPABILITIES "bast stackglue" static int param_set_dlmfs_capabilities(const char *val, const struct kernel_param *kp) { printk(KERN_ERR "%s: readonly parameter\n", kp->name); return -EINVAL; } static int param_get_dlmfs_capabilities(char *buffer, const struct kernel_param *kp) { return sysfs_emit(buffer, DLMFS_CAPABILITIES); } module_param_call(capabilities, param_set_dlmfs_capabilities, param_get_dlmfs_capabilities, NULL, 0444); MODULE_PARM_DESC(capabilities, DLMFS_CAPABILITIES); /* * decodes a set of open flags into a valid lock level and a set of flags. * returns < 0 if we have invalid flags * flags which mean something to us: * O_RDONLY -> PRMODE level * O_WRONLY -> EXMODE level * * O_NONBLOCK -> NOQUEUE */ static int dlmfs_decode_open_flags(int open_flags, int *level, int *flags) { if (open_flags & (O_WRONLY|O_RDWR)) *level = DLM_LOCK_EX; else *level = DLM_LOCK_PR; *flags = 0; if (open_flags & O_NONBLOCK) *flags |= DLM_LKF_NOQUEUE; return 0; } static int dlmfs_file_open(struct inode *inode, struct file *file) { int status, level, flags; struct dlmfs_filp_private *fp = NULL; struct dlmfs_inode_private *ip; if (S_ISDIR(inode->i_mode)) BUG(); mlog(0, "open called on inode %lu, flags 0x%x\n", inode->i_ino, file->f_flags); status = dlmfs_decode_open_flags(file->f_flags, &level, &flags); if (status < 0) goto bail; /* We don't want to honor O_APPEND at read/write time as it * doesn't make sense for LVB writes. */ file->f_flags &= ~O_APPEND; fp = kmalloc(sizeof(*fp), GFP_NOFS); if (!fp) { status = -ENOMEM; goto bail; } fp->fp_lock_level = level; ip = DLMFS_I(inode); status = user_dlm_cluster_lock(&ip->ip_lockres, level, flags); if (status < 0) { /* this is a strange error to return here but I want * to be able userspace to be able to distinguish a * valid lock request from one that simply couldn't be * granted. */ if (flags & DLM_LKF_NOQUEUE && status == -EAGAIN) status = -ETXTBSY; kfree(fp); goto bail; } file->private_data = fp; bail: return status; } static int dlmfs_file_release(struct inode *inode, struct file *file) { int level; struct dlmfs_inode_private *ip = DLMFS_I(inode); struct dlmfs_filp_private *fp = file->private_data; if (S_ISDIR(inode->i_mode)) BUG(); mlog(0, "close called on inode %lu\n", inode->i_ino); if (fp) { level = fp->fp_lock_level; if (level != DLM_LOCK_IV) user_dlm_cluster_unlock(&ip->ip_lockres, level); kfree(fp); file->private_data = NULL; } return 0; } /* * We do ->setattr() just to override size changes. Our size is the size * of the LVB and nothing else. */ static int dlmfs_file_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { int error; struct inode *inode = d_inode(dentry); attr->ia_valid &= ~ATTR_SIZE; error = setattr_prepare(&nop_mnt_idmap, dentry, attr); if (error) return error; setattr_copy(&nop_mnt_idmap, inode, attr); mark_inode_dirty(inode); return 0; } static __poll_t dlmfs_file_poll(struct file *file, poll_table *wait) { __poll_t event = 0; struct inode *inode = file_inode(file); struct dlmfs_inode_private *ip = DLMFS_I(inode); poll_wait(file, &ip->ip_lockres.l_event, wait); spin_lock(&ip->ip_lockres.l_lock); if (ip->ip_lockres.l_flags & USER_LOCK_BLOCKED) event = EPOLLIN | EPOLLRDNORM; spin_unlock(&ip->ip_lockres.l_lock); return event; } static ssize_t dlmfs_file_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { char lvb[DLM_LVB_LEN]; if (!user_dlm_read_lvb(file_inode(file), lvb)) return 0; return simple_read_from_buffer(buf, count, ppos, lvb, sizeof(lvb)); } static ssize_t dlmfs_file_write(struct file *filp, const char __user *buf, size_t count, loff_t *ppos) { char lvb_buf[DLM_LVB_LEN]; int bytes_left; struct inode *inode = file_inode(filp); mlog(0, "inode %lu, count = %zu, *ppos = %llu\n", inode->i_ino, count, *ppos); if (*ppos >= DLM_LVB_LEN) return -ENOSPC; /* don't write past the lvb */ if (count > DLM_LVB_LEN - *ppos) count = DLM_LVB_LEN - *ppos; if (!count) return 0; bytes_left = copy_from_user(lvb_buf, buf, count); count -= bytes_left; if (count) user_dlm_write_lvb(inode, lvb_buf, count); *ppos = *ppos + count; mlog(0, "wrote %zu bytes\n", count); return count; } static void dlmfs_init_once(void *foo) { struct dlmfs_inode_private *ip = (struct dlmfs_inode_private *) foo; ip->ip_conn = NULL; ip->ip_parent = NULL; inode_init_once(&ip->ip_vfs_inode); } static struct inode *dlmfs_alloc_inode(struct super_block *sb) { struct dlmfs_inode_private *ip; ip = alloc_inode_sb(sb, dlmfs_inode_cache, GFP_NOFS); if (!ip) return NULL; return &ip->ip_vfs_inode; } static void dlmfs_free_inode(struct inode *inode) { kmem_cache_free(dlmfs_inode_cache, DLMFS_I(inode)); } static void dlmfs_evict_inode(struct inode *inode) { int status; struct dlmfs_inode_private *ip; struct user_lock_res *lockres; int teardown; clear_inode(inode); mlog(0, "inode %lu\n", inode->i_ino); ip = DLMFS_I(inode); lockres = &ip->ip_lockres; if (S_ISREG(inode->i_mode)) { spin_lock(&lockres->l_lock); teardown = !!(lockres->l_flags & USER_LOCK_IN_TEARDOWN); spin_unlock(&lockres->l_lock); if (!teardown) { status = user_dlm_destroy_lock(lockres); if (status < 0) mlog_errno(status); } iput(ip->ip_parent); goto clear_fields; } mlog(0, "we're a directory, ip->ip_conn = 0x%p\n", ip->ip_conn); /* we must be a directory. If required, lets unregister the * dlm context now. */ if (ip->ip_conn) user_dlm_unregister(ip->ip_conn); clear_fields: ip->ip_parent = NULL; ip->ip_conn = NULL; } static struct inode *dlmfs_get_root_inode(struct super_block *sb) { struct inode *inode = new_inode(sb); umode_t mode = S_IFDIR | 0755; if (inode) { inode->i_ino = get_next_ino(); inode_init_owner(&nop_mnt_idmap, inode, NULL, mode); simple_inode_init_ts(inode); inc_nlink(inode); inode->i_fop = &simple_dir_operations; inode->i_op = &dlmfs_root_inode_operations; } return inode; } static struct inode *dlmfs_get_inode(struct inode *parent, struct dentry *dentry, umode_t mode) { struct super_block *sb = parent->i_sb; struct inode * inode = new_inode(sb); struct dlmfs_inode_private *ip; if (!inode) return NULL; inode->i_ino = get_next_ino(); inode_init_owner(&nop_mnt_idmap, inode, parent, mode); simple_inode_init_ts(inode); ip = DLMFS_I(inode); ip->ip_conn = DLMFS_I(parent)->ip_conn; switch (mode & S_IFMT) { default: /* for now we don't support anything other than * directories and regular files. */ BUG(); break; case S_IFREG: inode->i_op = &dlmfs_file_inode_operations; inode->i_fop = &dlmfs_file_operations; i_size_write(inode, DLM_LVB_LEN); user_dlm_lock_res_init(&ip->ip_lockres, dentry); /* released at clear_inode time, this insures that we * get to drop the dlm reference on each lock *before* * we call the unregister code for releasing parent * directories. */ ip->ip_parent = igrab(parent); BUG_ON(!ip->ip_parent); break; case S_IFDIR: inode->i_op = &dlmfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == * 2 (for "." entry) */ inc_nlink(inode); break; } return inode; } /* * File creation. Allocate an inode, and we're done.. */ /* SMP-safe */ static struct dentry *dlmfs_mkdir(struct mnt_idmap * idmap, struct inode * dir, struct dentry * dentry, umode_t mode) { int status; struct inode *inode = NULL; const struct qstr *domain = &dentry->d_name; struct dlmfs_inode_private *ip; struct ocfs2_cluster_connection *conn; mlog(0, "mkdir %.*s\n", domain->len, domain->name); /* verify that we have a proper domain */ if (domain->len >= GROUP_NAME_MAX) { status = -EINVAL; mlog(ML_ERROR, "invalid domain name for directory.\n"); goto bail; } inode = dlmfs_get_inode(dir, dentry, mode | S_IFDIR); if (!inode) { status = -ENOMEM; mlog_errno(status); goto bail; } ip = DLMFS_I(inode); conn = user_dlm_register(domain); if (IS_ERR(conn)) { status = PTR_ERR(conn); mlog(ML_ERROR, "Error %d could not register domain \"%.*s\"\n", status, domain->len, domain->name); goto bail; } ip->ip_conn = conn; inc_nlink(dir); d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ status = 0; bail: if (status < 0) iput(inode); return ERR_PTR(status); } static int dlmfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { int status = 0; struct inode *inode; const struct qstr *name = &dentry->d_name; mlog(0, "create %.*s\n", name->len, name->name); /* verify name is valid and doesn't contain any dlm reserved * characters */ if (name->len >= USER_DLM_LOCK_ID_MAX_LEN || name->name[0] == '$') { status = -EINVAL; mlog(ML_ERROR, "invalid lock name, %.*s\n", name->len, name->name); goto bail; } inode = dlmfs_get_inode(dir, dentry, mode | S_IFREG); if (!inode) { status = -ENOMEM; mlog_errno(status); goto bail; } d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ bail: return status; } static int dlmfs_unlink(struct inode *dir, struct dentry *dentry) { int status; struct inode *inode = d_inode(dentry); mlog(0, "unlink inode %lu\n", inode->i_ino); /* if there are no current holders, or none that are waiting * to acquire a lock, this basically destroys our lockres. */ status = user_dlm_destroy_lock(&DLMFS_I(inode)->ip_lockres); if (status < 0) { mlog(ML_ERROR, "unlink %pd, error %d from destroy\n", dentry, status); goto bail; } status = simple_unlink(dir, dentry); bail: return status; } static int dlmfs_fill_super(struct super_block *sb, struct fs_context *fc) { sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = DLMFS_MAGIC; sb->s_op = &dlmfs_ops; sb->s_root = d_make_root(dlmfs_get_root_inode(sb)); if (!sb->s_root) return -ENOMEM; return 0; } static const struct file_operations dlmfs_file_operations = { .open = dlmfs_file_open, .release = dlmfs_file_release, .poll = dlmfs_file_poll, .read = dlmfs_file_read, .write = dlmfs_file_write, .llseek = default_llseek, }; static const struct inode_operations dlmfs_dir_inode_operations = { .create = dlmfs_create, .lookup = simple_lookup, .unlink = dlmfs_unlink, }; /* this way we can restrict mkdir to only the toplevel of the fs. */ static const struct inode_operations dlmfs_root_inode_operations = { .lookup = simple_lookup, .mkdir = dlmfs_mkdir, .rmdir = simple_rmdir, }; static const struct super_operations dlmfs_ops = { .statfs = simple_statfs, .alloc_inode = dlmfs_alloc_inode, .free_inode = dlmfs_free_inode, .evict_inode = dlmfs_evict_inode, .drop_inode = generic_delete_inode, }; static const struct inode_operations dlmfs_file_inode_operations = { .getattr = simple_getattr, .setattr = dlmfs_file_setattr, }; static int dlmfs_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, dlmfs_fill_super); } static const struct fs_context_operations dlmfs_context_ops = { .get_tree = dlmfs_get_tree, }; static int dlmfs_init_fs_context(struct fs_context *fc) { fc->ops = &dlmfs_context_ops; return 0; } static struct file_system_type dlmfs_fs_type = { .owner = THIS_MODULE, .name = "ocfs2_dlmfs", .kill_sb = kill_litter_super, .init_fs_context = dlmfs_init_fs_context, }; MODULE_ALIAS_FS("ocfs2_dlmfs"); static int __init init_dlmfs_fs(void) { int status; int cleanup_inode = 0, cleanup_worker = 0; dlmfs_inode_cache = kmem_cache_create("dlmfs_inode_cache", sizeof(struct dlmfs_inode_private), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), dlmfs_init_once); if (!dlmfs_inode_cache) { status = -ENOMEM; goto bail; } cleanup_inode = 1; user_dlm_worker = alloc_workqueue("user_dlm", WQ_MEM_RECLAIM, 0); if (!user_dlm_worker) { status = -ENOMEM; goto bail; } cleanup_worker = 1; user_dlm_set_locking_protocol(); status = register_filesystem(&dlmfs_fs_type); bail: if (status) { if (cleanup_inode) kmem_cache_destroy(dlmfs_inode_cache); if (cleanup_worker) destroy_workqueue(user_dlm_worker); } else printk("OCFS2 User DLM kernel interface loaded\n"); return status; } static void __exit exit_dlmfs_fs(void) { unregister_filesystem(&dlmfs_fs_type); destroy_workqueue(user_dlm_worker); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(dlmfs_inode_cache); } MODULE_AUTHOR("Oracle"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("OCFS2 DLM-Filesystem"); module_init(init_dlmfs_fs) module_exit(exit_dlmfs_fs) |
| 2 2 2 13 2 11 9 12 12 7 8 10 8 3 3 2 12 12 1 7 2 1 2 11 1 1 1 8 13 13 13 1 12 4 2 2 8 1 6 1 7 22 7 15 18 7 7 1 6 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 | /* Block- or MTD-based romfs * * Copyright © 2007 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * Derived from: ROMFS file system, Linux implementation * * Copyright © 1997-1999 Janos Farkas <chexum@shadow.banki.hu> * * Using parts of the minix filesystem * Copyright © 1991, 1992 Linus Torvalds * * and parts of the affs filesystem additionally * Copyright © 1993 Ray Burr * Copyright © 1996 Hans-Joachim Widmaier * * Changes * Changed for 2.1.19 modules * Jan 1997 Initial release * Jun 1997 2.1.43+ changes * Proper page locking in read_folio * Changed to work with 2.1.45+ fs * Jul 1997 Fixed follow_link * 2.1.47 * lookup shouldn't return -ENOENT * from Horst von Brand: * fail on wrong checksum * double unlock_super was possible * correct namelen for statfs * spotted by Bill Hawes: * readlink shouldn't iput() * Jun 1998 2.1.106 from Avery Pennarun: glibc scandir() * exposed a problem in readdir * 2.1.107 code-freeze spellchecker run * Aug 1998 2.1.118+ VFS changes * Sep 1998 2.1.122 another VFS change (follow_link) * Apr 1999 2.2.7 no more EBADF checking in * lookup/readdir, use ERR_PTR * Jun 1999 2.3.6 d_alloc_root use changed * 2.3.9 clean up usage of ENOENT/negative * dentries in lookup * clean up page flags setting * (error, uptodate, locking) in * in read_folio * use init_special_inode for * fifos/sockets (and streamline) in * read_inode, fix _ops table order * Aug 1999 2.3.16 __initfunc() => __init change * Oct 1999 2.3.24 page->owner hack obsoleted * Nov 1999 2.3.27 2.3.25+ page->offset => index change * * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public Licence * as published by the Free Software Foundation; either version * 2 of the Licence, or (at your option) any later version. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/string.h> #include <linux/fs.h> #include <linux/time.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/blkdev.h> #include <linux/fs_context.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/statfs.h> #include <linux/mtd/super.h> #include <linux/ctype.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/uaccess.h> #include <linux/major.h> #include "internal.h" static struct kmem_cache *romfs_inode_cachep; static const umode_t romfs_modemap[8] = { 0, /* hard link */ S_IFDIR | 0644, /* directory */ S_IFREG | 0644, /* regular file */ S_IFLNK | 0777, /* symlink */ S_IFBLK | 0600, /* blockdev */ S_IFCHR | 0600, /* chardev */ S_IFSOCK | 0644, /* socket */ S_IFIFO | 0644 /* FIFO */ }; static const unsigned char romfs_dtype_table[] = { DT_UNKNOWN, DT_DIR, DT_REG, DT_LNK, DT_BLK, DT_CHR, DT_SOCK, DT_FIFO }; static struct inode *romfs_iget(struct super_block *sb, unsigned long pos); /* * read a page worth of data from the image */ static int romfs_read_folio(struct file *file, struct folio *folio) { struct inode *inode = folio->mapping->host; loff_t offset, size; unsigned long fillsize, pos; void *buf; int ret; buf = kmap_local_folio(folio, 0); offset = folio_pos(folio); size = i_size_read(inode); fillsize = 0; ret = 0; if (offset < size) { size -= offset; fillsize = size > PAGE_SIZE ? PAGE_SIZE : size; pos = ROMFS_I(inode)->i_dataoffset + offset; ret = romfs_dev_read(inode->i_sb, pos, buf, fillsize); if (ret < 0) { fillsize = 0; ret = -EIO; } } buf = folio_zero_tail(folio, fillsize, buf + fillsize); kunmap_local(buf); folio_end_read(folio, ret == 0); return ret; } static const struct address_space_operations romfs_aops = { .read_folio = romfs_read_folio }; /* * read the entries from a directory */ static int romfs_readdir(struct file *file, struct dir_context *ctx) { struct inode *i = file_inode(file); struct romfs_inode ri; unsigned long offset, maxoff; int j, ino, nextfh; char fsname[ROMFS_MAXFN]; /* XXX dynamic? */ int ret; maxoff = romfs_maxsize(i->i_sb); offset = ctx->pos; if (!offset) { offset = i->i_ino & ROMFH_MASK; ret = romfs_dev_read(i->i_sb, offset, &ri, ROMFH_SIZE); if (ret < 0) goto out; offset = be32_to_cpu(ri.spec) & ROMFH_MASK; } /* Not really failsafe, but we are read-only... */ for (;;) { if (!offset || offset >= maxoff) { offset = maxoff; ctx->pos = offset; goto out; } ctx->pos = offset; /* Fetch inode info */ ret = romfs_dev_read(i->i_sb, offset, &ri, ROMFH_SIZE); if (ret < 0) goto out; j = romfs_dev_strnlen(i->i_sb, offset + ROMFH_SIZE, sizeof(fsname) - 1); if (j < 0) goto out; ret = romfs_dev_read(i->i_sb, offset + ROMFH_SIZE, fsname, j); if (ret < 0) goto out; fsname[j] = '\0'; ino = offset; nextfh = be32_to_cpu(ri.next); if ((nextfh & ROMFH_TYPE) == ROMFH_HRD) ino = be32_to_cpu(ri.spec); if (!dir_emit(ctx, fsname, j, ino, romfs_dtype_table[nextfh & ROMFH_TYPE])) goto out; offset = nextfh & ROMFH_MASK; } out: return 0; } /* * look up an entry in a directory */ static struct dentry *romfs_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { unsigned long offset, maxoff; struct inode *inode = NULL; struct romfs_inode ri; const char *name; /* got from dentry */ int len, ret; offset = dir->i_ino & ROMFH_MASK; ret = romfs_dev_read(dir->i_sb, offset, &ri, ROMFH_SIZE); if (ret < 0) goto error; /* search all the file entries in the list starting from the one * pointed to by the directory's special data */ maxoff = romfs_maxsize(dir->i_sb); offset = be32_to_cpu(ri.spec) & ROMFH_MASK; name = dentry->d_name.name; len = dentry->d_name.len; for (;;) { if (!offset || offset >= maxoff) break; ret = romfs_dev_read(dir->i_sb, offset, &ri, sizeof(ri)); if (ret < 0) goto error; /* try to match the first 16 bytes of name */ ret = romfs_dev_strcmp(dir->i_sb, offset + ROMFH_SIZE, name, len); if (ret < 0) goto error; if (ret == 1) { /* Hard link handling */ if ((be32_to_cpu(ri.next) & ROMFH_TYPE) == ROMFH_HRD) offset = be32_to_cpu(ri.spec) & ROMFH_MASK; inode = romfs_iget(dir->i_sb, offset); break; } /* next entry */ offset = be32_to_cpu(ri.next) & ROMFH_MASK; } return d_splice_alias(inode, dentry); error: return ERR_PTR(ret); } static const struct file_operations romfs_dir_operations = { .read = generic_read_dir, .iterate_shared = romfs_readdir, .llseek = generic_file_llseek, }; static const struct inode_operations romfs_dir_inode_operations = { .lookup = romfs_lookup, }; /* * get a romfs inode based on its position in the image (which doubles as the * inode number) */ static struct inode *romfs_iget(struct super_block *sb, unsigned long pos) { struct romfs_inode_info *inode; struct romfs_inode ri; struct inode *i; unsigned long nlen; unsigned nextfh; int ret; umode_t mode; /* we might have to traverse a chain of "hard link" file entries to get * to the actual file */ for (;;) { ret = romfs_dev_read(sb, pos, &ri, sizeof(ri)); if (ret < 0) goto error; /* XXX: do romfs_checksum here too (with name) */ nextfh = be32_to_cpu(ri.next); if ((nextfh & ROMFH_TYPE) != ROMFH_HRD) break; pos = be32_to_cpu(ri.spec) & ROMFH_MASK; } /* determine the length of the filename */ nlen = romfs_dev_strnlen(sb, pos + ROMFH_SIZE, ROMFS_MAXFN); if (IS_ERR_VALUE(nlen)) goto eio; /* get an inode for this image position */ i = iget_locked(sb, pos); if (!i) return ERR_PTR(-ENOMEM); if (!(i->i_state & I_NEW)) return i; /* precalculate the data offset */ inode = ROMFS_I(i); inode->i_metasize = (ROMFH_SIZE + nlen + 1 + ROMFH_PAD) & ROMFH_MASK; inode->i_dataoffset = pos + inode->i_metasize; set_nlink(i, 1); /* Hard to decide.. */ i->i_size = be32_to_cpu(ri.size); inode_set_mtime_to_ts(i, inode_set_atime_to_ts(i, inode_set_ctime(i, 0, 0))); /* set up mode and ops */ mode = romfs_modemap[nextfh & ROMFH_TYPE]; switch (nextfh & ROMFH_TYPE) { case ROMFH_DIR: i->i_size = ROMFS_I(i)->i_metasize; i->i_op = &romfs_dir_inode_operations; i->i_fop = &romfs_dir_operations; if (nextfh & ROMFH_EXEC) mode |= S_IXUGO; break; case ROMFH_REG: i->i_fop = &romfs_ro_fops; i->i_data.a_ops = &romfs_aops; if (nextfh & ROMFH_EXEC) mode |= S_IXUGO; break; case ROMFH_SYM: i->i_op = &page_symlink_inode_operations; inode_nohighmem(i); i->i_data.a_ops = &romfs_aops; mode |= S_IRWXUGO; break; default: /* depending on MBZ for sock/fifos */ nextfh = be32_to_cpu(ri.spec); init_special_inode(i, mode, MKDEV(nextfh >> 16, nextfh & 0xffff)); break; } i->i_mode = mode; i->i_blocks = (i->i_size + 511) >> 9; unlock_new_inode(i); return i; eio: ret = -EIO; error: pr_err("read error for inode 0x%lx\n", pos); return ERR_PTR(ret); } /* * allocate a new inode */ static struct inode *romfs_alloc_inode(struct super_block *sb) { struct romfs_inode_info *inode; inode = alloc_inode_sb(sb, romfs_inode_cachep, GFP_KERNEL); return inode ? &inode->vfs_inode : NULL; } /* * return a spent inode to the slab cache */ static void romfs_free_inode(struct inode *inode) { kmem_cache_free(romfs_inode_cachep, ROMFS_I(inode)); } /* * get filesystem statistics */ static int romfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct super_block *sb = dentry->d_sb; u64 id = 0; /* When calling huge_encode_dev(), * use sb->s_bdev->bd_dev when, * - CONFIG_ROMFS_ON_BLOCK defined * use sb->s_dev when, * - CONFIG_ROMFS_ON_BLOCK undefined and * - CONFIG_ROMFS_ON_MTD defined * leave id as 0 when, * - CONFIG_ROMFS_ON_BLOCK undefined and * - CONFIG_ROMFS_ON_MTD undefined */ if (sb->s_bdev) id = huge_encode_dev(sb->s_bdev->bd_dev); else if (sb->s_dev) id = huge_encode_dev(sb->s_dev); buf->f_type = ROMFS_MAGIC; buf->f_namelen = ROMFS_MAXFN; buf->f_bsize = ROMBSIZE; buf->f_bfree = buf->f_bavail = buf->f_ffree; buf->f_blocks = (romfs_maxsize(dentry->d_sb) + ROMBSIZE - 1) >> ROMBSBITS; buf->f_fsid = u64_to_fsid(id); return 0; } /* * remounting must involve read-only */ static int romfs_reconfigure(struct fs_context *fc) { sync_filesystem(fc->root->d_sb); fc->sb_flags |= SB_RDONLY; return 0; } static const struct super_operations romfs_super_ops = { .alloc_inode = romfs_alloc_inode, .free_inode = romfs_free_inode, .statfs = romfs_statfs, }; /* * checksum check on part of a romfs filesystem */ static __u32 romfs_checksum(const void *data, int size) { const __be32 *ptr = data; __u32 sum; sum = 0; size >>= 2; while (size > 0) { sum += be32_to_cpu(*ptr++); size--; } return sum; } /* * fill in the superblock */ static int romfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct romfs_super_block *rsb; struct inode *root; unsigned long pos, img_size; const char *storage; size_t len; int ret; #ifdef CONFIG_BLOCK if (!sb->s_mtd) { sb_set_blocksize(sb, ROMBSIZE); } else { sb->s_blocksize = ROMBSIZE; sb->s_blocksize_bits = blksize_bits(ROMBSIZE); } #endif sb->s_maxbytes = 0xFFFFFFFF; sb->s_magic = ROMFS_MAGIC; sb->s_flags |= SB_RDONLY | SB_NOATIME; sb->s_time_min = 0; sb->s_time_max = 0; sb->s_op = &romfs_super_ops; #ifdef CONFIG_ROMFS_ON_MTD /* Use same dev ID from the underlying mtdblock device */ if (sb->s_mtd) sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, sb->s_mtd->index); #endif /* read the image superblock and check it */ rsb = kmalloc(512, GFP_KERNEL); if (!rsb) return -ENOMEM; sb->s_fs_info = (void *) 512; ret = romfs_dev_read(sb, 0, rsb, 512); if (ret < 0) goto error_rsb; img_size = be32_to_cpu(rsb->size); if (sb->s_mtd && img_size > sb->s_mtd->size) goto error_rsb_inval; sb->s_fs_info = (void *) img_size; if (rsb->word0 != ROMSB_WORD0 || rsb->word1 != ROMSB_WORD1 || img_size < ROMFH_SIZE) { if (!(fc->sb_flags & SB_SILENT)) errorf(fc, "VFS: Can't find a romfs filesystem on dev %s.\n", sb->s_id); goto error_rsb_inval; } if (romfs_checksum(rsb, min_t(size_t, img_size, 512))) { pr_err("bad initial checksum on dev %s.\n", sb->s_id); goto error_rsb_inval; } storage = sb->s_mtd ? "MTD" : "the block layer"; len = strnlen(rsb->name, ROMFS_MAXFN); if (!(fc->sb_flags & SB_SILENT)) pr_notice("Mounting image '%*.*s' through %s\n", (unsigned) len, (unsigned) len, rsb->name, storage); kfree(rsb); rsb = NULL; /* find the root directory */ pos = (ROMFH_SIZE + len + 1 + ROMFH_PAD) & ROMFH_MASK; root = romfs_iget(sb, pos); if (IS_ERR(root)) return PTR_ERR(root); sb->s_root = d_make_root(root); if (!sb->s_root) return -ENOMEM; return 0; error_rsb_inval: ret = -EINVAL; error_rsb: kfree(rsb); return ret; } /* * get a superblock for mounting */ static int romfs_get_tree(struct fs_context *fc) { int ret = -EINVAL; #ifdef CONFIG_ROMFS_ON_MTD ret = get_tree_mtd(fc, romfs_fill_super); #endif #ifdef CONFIG_ROMFS_ON_BLOCK if (ret == -EINVAL) ret = get_tree_bdev(fc, romfs_fill_super); #endif return ret; } static const struct fs_context_operations romfs_context_ops = { .get_tree = romfs_get_tree, .reconfigure = romfs_reconfigure, }; /* * Set up the filesystem mount context. */ static int romfs_init_fs_context(struct fs_context *fc) { fc->ops = &romfs_context_ops; return 0; } /* * destroy a romfs superblock in the appropriate manner */ static void romfs_kill_sb(struct super_block *sb) { generic_shutdown_super(sb); #ifdef CONFIG_ROMFS_ON_MTD if (sb->s_mtd) { put_mtd_device(sb->s_mtd); sb->s_mtd = NULL; } #endif #ifdef CONFIG_ROMFS_ON_BLOCK if (sb->s_bdev) { sync_blockdev(sb->s_bdev); bdev_fput(sb->s_bdev_file); } #endif } static struct file_system_type romfs_fs_type = { .owner = THIS_MODULE, .name = "romfs", .init_fs_context = romfs_init_fs_context, .kill_sb = romfs_kill_sb, .fs_flags = FS_REQUIRES_DEV, }; MODULE_ALIAS_FS("romfs"); /* * inode storage initialiser */ static void romfs_i_init_once(void *_inode) { struct romfs_inode_info *inode = _inode; inode_init_once(&inode->vfs_inode); } /* * romfs module initialisation */ static int __init init_romfs_fs(void) { int ret; pr_info("ROMFS MTD (C) 2007 Red Hat, Inc.\n"); romfs_inode_cachep = kmem_cache_create("romfs_i", sizeof(struct romfs_inode_info), 0, SLAB_RECLAIM_ACCOUNT | SLAB_ACCOUNT, romfs_i_init_once); if (!romfs_inode_cachep) { pr_err("Failed to initialise inode cache\n"); return -ENOMEM; } ret = register_filesystem(&romfs_fs_type); if (ret) { pr_err("Failed to register filesystem\n"); goto error_register; } return 0; error_register: kmem_cache_destroy(romfs_inode_cachep); return ret; } /* * romfs module removal */ static void __exit exit_romfs_fs(void) { unregister_filesystem(&romfs_fs_type); /* * Make sure all delayed rcu free inodes are flushed before we * destroy cache. */ rcu_barrier(); kmem_cache_destroy(romfs_inode_cachep); } module_init(init_romfs_fs); module_exit(exit_romfs_fs); MODULE_DESCRIPTION("Direct-MTD Capable RomFS"); MODULE_AUTHOR("Red Hat, Inc."); MODULE_LICENSE("GPL"); /* Actually dual-licensed, but it doesn't matter for */ |
| 4218 4222 4228 4225 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * internal.h - printk internal definitions */ #include <linux/console.h> #include <linux/percpu.h> #include <linux/types.h> #if defined(CONFIG_PRINTK) && defined(CONFIG_SYSCTL) struct ctl_table; void __init printk_sysctl_init(void); int devkmsg_sysctl_set_loglvl(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); #else #define printk_sysctl_init() do { } while (0) #endif #define con_printk(lvl, con, fmt, ...) \ printk(lvl pr_fmt("%s%sconsole [%s%d] " fmt), \ (con->flags & CON_NBCON) ? "" : "legacy ", \ (con->flags & CON_BOOT) ? "boot" : "", \ con->name, con->index, ##__VA_ARGS__) /* * Identify if legacy printing is forced in a dedicated kthread. If * true, all printing via console lock occurs within a dedicated * legacy printer thread. The only exception is on panic, after the * nbcon consoles have had their chance to print the panic messages * first. */ #ifdef CONFIG_PREEMPT_RT # define force_legacy_kthread() (true) #else # define force_legacy_kthread() (false) #endif #ifdef CONFIG_PRINTK #ifdef CONFIG_PRINTK_CALLER #define PRINTK_PREFIX_MAX 48 #else #define PRINTK_PREFIX_MAX 32 #endif /* * the maximum size of a formatted record (i.e. with prefix added * per line and dropped messages or in extended message format) */ #define PRINTK_MESSAGE_MAX 2048 /* the maximum size allowed to be reserved for a record */ #define PRINTKRB_RECORD_MAX 1024 /* Flags for a single printk record. */ enum printk_info_flags { /* always show on console, ignore console_loglevel */ LOG_FORCE_CON = 1, LOG_NEWLINE = 2, /* text ended with a newline */ LOG_CONT = 8, /* text is a fragment of a continuation line */ }; struct printk_ringbuffer; struct dev_printk_info; extern struct printk_ringbuffer *prb; extern bool printk_kthreads_running; extern bool printk_kthreads_ready; extern bool debug_non_panic_cpus; __printf(4, 0) int vprintk_store(int facility, int level, const struct dev_printk_info *dev_info, const char *fmt, va_list args); __printf(1, 0) int vprintk_default(const char *fmt, va_list args); void __printk_safe_enter(void); void __printk_safe_exit(void); bool printk_percpu_data_ready(void); #define printk_safe_enter_irqsave(flags) \ do { \ local_irq_save(flags); \ __printk_safe_enter(); \ } while (0) #define printk_safe_exit_irqrestore(flags) \ do { \ __printk_safe_exit(); \ local_irq_restore(flags); \ } while (0) void defer_console_output(void); bool is_printk_legacy_deferred(void); bool is_printk_force_console(void); u16 printk_parse_prefix(const char *text, int *level, enum printk_info_flags *flags); void console_lock_spinning_enable(void); int console_lock_spinning_disable_and_check(int cookie); u64 nbcon_seq_read(struct console *con); void nbcon_seq_force(struct console *con, u64 seq); bool nbcon_alloc(struct console *con); void nbcon_free(struct console *con); enum nbcon_prio nbcon_get_default_prio(void); void nbcon_atomic_flush_pending(void); bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, int cookie, bool use_atomic); bool nbcon_kthread_create(struct console *con); void nbcon_kthread_stop(struct console *con); void nbcon_kthreads_wake(void); /* * Check if the given console is currently capable and allowed to print * records. Note that this function does not consider the current context, * which can also play a role in deciding if @con can be used to print * records. */ static inline bool console_is_usable(struct console *con, short flags, bool use_atomic) { if (!(flags & CON_ENABLED)) return false; if ((flags & CON_SUSPENDED)) return false; if (flags & CON_NBCON) { /* The write_atomic() callback is optional. */ if (use_atomic && !con->write_atomic) return false; /* * For the !use_atomic case, @printk_kthreads_running is not * checked because the write_thread() callback is also used * via the legacy loop when the printer threads are not * available. */ } else { if (!con->write) return false; } /* * Console drivers may assume that per-cpu resources have been * allocated. So unless they're explicitly marked as being able to * cope (CON_ANYTIME) don't call them until this CPU is officially up. */ if (!cpu_online(raw_smp_processor_id()) && !(flags & CON_ANYTIME)) return false; return true; } /** * nbcon_kthread_wake - Wake up a console printing thread * @con: Console to operate on */ static inline void nbcon_kthread_wake(struct console *con) { /* * Guarantee any new records can be seen by tasks preparing to wait * before this context checks if the rcuwait is empty. * * The full memory barrier in rcuwait_wake_up() pairs with the full * memory barrier within set_current_state() of * ___rcuwait_wait_event(), which is called after prepare_to_rcuwait() * adds the waiter but before it has checked the wait condition. * * This pairs with nbcon_kthread_func:A. */ rcuwait_wake_up(&con->rcuwait); /* LMM(nbcon_kthread_wake:A) */ } #else #define PRINTK_PREFIX_MAX 0 #define PRINTK_MESSAGE_MAX 0 #define PRINTKRB_RECORD_MAX 0 #define printk_kthreads_running (false) #define printk_kthreads_ready (false) /* * In !PRINTK builds we still export console_sem * semaphore and some of console functions (console_unlock()/etc.), so * printk-safe must preserve the existing local IRQ guarantees. */ #define printk_safe_enter_irqsave(flags) local_irq_save(flags) #define printk_safe_exit_irqrestore(flags) local_irq_restore(flags) static inline bool printk_percpu_data_ready(void) { return false; } static inline void defer_console_output(void) { } static inline bool is_printk_legacy_deferred(void) { return false; } static inline u64 nbcon_seq_read(struct console *con) { return 0; } static inline void nbcon_seq_force(struct console *con, u64 seq) { } static inline bool nbcon_alloc(struct console *con) { return false; } static inline void nbcon_free(struct console *con) { } static inline enum nbcon_prio nbcon_get_default_prio(void) { return NBCON_PRIO_NONE; } static inline void nbcon_atomic_flush_pending(void) { } static inline bool nbcon_legacy_emit_next_record(struct console *con, bool *handover, int cookie, bool use_atomic) { return false; } static inline void nbcon_kthread_wake(struct console *con) { } static inline void nbcon_kthreads_wake(void) { } static inline bool console_is_usable(struct console *con, short flags, bool use_atomic) { return false; } #endif /* CONFIG_PRINTK */ extern bool have_boot_console; extern bool have_nbcon_console; extern bool have_legacy_console; extern bool legacy_allow_panic_sync; /** * struct console_flush_type - Define available console flush methods * @nbcon_atomic: Flush directly using nbcon_atomic() callback * @nbcon_offload: Offload flush to printer thread * @legacy_direct: Call the legacy loop in this context * @legacy_offload: Offload the legacy loop into IRQ or legacy thread * * Note that the legacy loop also flushes the nbcon consoles. */ struct console_flush_type { bool nbcon_atomic; bool nbcon_offload; bool legacy_direct; bool legacy_offload; }; /* * Identify which console flushing methods should be used in the context of * the caller. */ static inline void printk_get_console_flush_type(struct console_flush_type *ft) { memset(ft, 0, sizeof(*ft)); switch (nbcon_get_default_prio()) { case NBCON_PRIO_NORMAL: if (have_nbcon_console && !have_boot_console) { if (printk_kthreads_running) ft->nbcon_offload = true; else ft->nbcon_atomic = true; } /* Legacy consoles are flushed directly when possible. */ if (have_legacy_console || have_boot_console) { if (!is_printk_legacy_deferred()) ft->legacy_direct = true; else ft->legacy_offload = true; } break; case NBCON_PRIO_EMERGENCY: if (have_nbcon_console && !have_boot_console) ft->nbcon_atomic = true; /* Legacy consoles are flushed directly when possible. */ if (have_legacy_console || have_boot_console) { if (!is_printk_legacy_deferred()) ft->legacy_direct = true; else ft->legacy_offload = true; } break; case NBCON_PRIO_PANIC: /* * In panic, the nbcon consoles will directly print. But * only allowed if there are no boot consoles. */ if (have_nbcon_console && !have_boot_console) ft->nbcon_atomic = true; if (have_legacy_console || have_boot_console) { /* * This is the same decision as NBCON_PRIO_NORMAL * except that offloading never occurs in panic. * * Note that console_flush_on_panic() will flush * legacy consoles anyway, even if unsafe. */ if (!is_printk_legacy_deferred()) ft->legacy_direct = true; /* * In panic, if nbcon atomic printing occurs, * the legacy consoles must remain silent until * explicitly allowed. */ if (ft->nbcon_atomic && !legacy_allow_panic_sync) ft->legacy_direct = false; } break; default: WARN_ON_ONCE(1); break; } } extern struct printk_buffers printk_shared_pbufs; /** * struct printk_buffers - Buffers to read/format/output printk messages. * @outbuf: After formatting, contains text to output. * @scratchbuf: Used as temporary ringbuffer reading and string-print space. */ struct printk_buffers { char outbuf[PRINTK_MESSAGE_MAX]; char scratchbuf[PRINTKRB_RECORD_MAX]; }; /** * struct printk_message - Container for a prepared printk message. * @pbufs: printk buffers used to prepare the message. * @outbuf_len: The length of prepared text in @pbufs->outbuf to output. This * does not count the terminator. A value of 0 means there is * nothing to output and this record should be skipped. * @seq: The sequence number of the record used for @pbufs->outbuf. * @dropped: The number of dropped records from reading @seq. */ struct printk_message { struct printk_buffers *pbufs; unsigned int outbuf_len; u64 seq; unsigned long dropped; }; bool other_cpu_in_panic(void); bool printk_get_next_message(struct printk_message *pmsg, u64 seq, bool is_extended, bool may_supress); #ifdef CONFIG_PRINTK void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped); void console_prepend_replay(struct printk_message *pmsg); #endif #ifdef CONFIG_SMP bool is_printk_cpu_sync_owner(void); #else static inline bool is_printk_cpu_sync_owner(void) { return false; } #endif |
| 212 211 211 211 10 200 10 10 1 1 15 1 6 8 2 5 29 29 27 17 6 3 3 135 134 2 33 25 1 2 5 4 4 4 3 2 1 4 1 1 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/crypto/hooks.c * * Encryption hooks for higher-level filesystem operations. */ #include <linux/export.h> #include "fscrypt_private.h" /** * fscrypt_file_open() - prepare to open a possibly-encrypted regular file * @inode: the inode being opened * @filp: the struct file being set up * * Currently, an encrypted regular file can only be opened if its encryption key * is available; access to the raw encrypted contents is not supported. * Therefore, we first set up the inode's encryption key (if not already done) * and return an error if it's unavailable. * * We also verify that if the parent directory (from the path via which the file * is being opened) is encrypted, then the inode being opened uses the same * encryption policy. This is needed as part of the enforcement that all files * in an encrypted directory tree use the same encryption policy, as a * protection against certain types of offline attacks. Note that this check is * needed even when opening an *unencrypted* file, since it's forbidden to have * an unencrypted file in an encrypted directory. * * Return: 0 on success, -ENOKEY if the key is missing, or another -errno code */ int fscrypt_file_open(struct inode *inode, struct file *filp) { int err; struct dentry *dentry, *dentry_parent; struct inode *inode_parent; err = fscrypt_require_key(inode); if (err) return err; dentry = file_dentry(filp); /* * Getting a reference to the parent dentry is needed for the actual * encryption policy comparison, but it's expensive on multi-core * systems. Since this function runs on unencrypted files too, start * with a lightweight RCU-mode check for the parent directory being * unencrypted (in which case it's fine for the child to be either * unencrypted, or encrypted with any policy). Only continue on to the * full policy check if the parent directory is actually encrypted. */ rcu_read_lock(); dentry_parent = READ_ONCE(dentry->d_parent); inode_parent = d_inode_rcu(dentry_parent); if (inode_parent != NULL && !IS_ENCRYPTED(inode_parent)) { rcu_read_unlock(); return 0; } rcu_read_unlock(); dentry_parent = dget_parent(dentry); if (!fscrypt_has_permitted_context(d_inode(dentry_parent), inode)) { fscrypt_warn(inode, "Inconsistent encryption context (parent directory: %lu)", d_inode(dentry_parent)->i_ino); err = -EPERM; } dput(dentry_parent); return err; } EXPORT_SYMBOL_GPL(fscrypt_file_open); int __fscrypt_prepare_link(struct inode *inode, struct inode *dir, struct dentry *dentry) { if (fscrypt_is_nokey_name(dentry)) return -ENOKEY; /* * We don't need to separately check that the directory inode's key is * available, as it's implied by the dentry not being a no-key name. */ if (!fscrypt_has_permitted_context(dir, inode)) return -EXDEV; return 0; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_link); int __fscrypt_prepare_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { if (fscrypt_is_nokey_name(old_dentry) || fscrypt_is_nokey_name(new_dentry)) return -ENOKEY; /* * We don't need to separately check that the directory inodes' keys are * available, as it's implied by the dentries not being no-key names. */ if (old_dir != new_dir) { if (IS_ENCRYPTED(new_dir) && !fscrypt_has_permitted_context(new_dir, d_inode(old_dentry))) return -EXDEV; if ((flags & RENAME_EXCHANGE) && IS_ENCRYPTED(old_dir) && !fscrypt_has_permitted_context(old_dir, d_inode(new_dentry))) return -EXDEV; } return 0; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_rename); int __fscrypt_prepare_lookup(struct inode *dir, struct dentry *dentry, struct fscrypt_name *fname) { int err = fscrypt_setup_filename(dir, &dentry->d_name, 1, fname); if (err && err != -ENOENT) return err; fscrypt_prepare_dentry(dentry, fname->is_nokey_name); return err; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_lookup); /** * fscrypt_prepare_lookup_partial() - prepare lookup without filename setup * @dir: the encrypted directory being searched * @dentry: the dentry being looked up in @dir * * This function should be used by the ->lookup and ->atomic_open methods of * filesystems that handle filename encryption and no-key name encoding * themselves and thus can't use fscrypt_prepare_lookup(). Like * fscrypt_prepare_lookup(), this will try to set up the directory's encryption * key and will set DCACHE_NOKEY_NAME on the dentry if the key is unavailable. * However, this function doesn't set up a struct fscrypt_name for the filename. * * Return: 0 on success; -errno on error. Note that the encryption key being * unavailable is not considered an error. It is also not an error if * the encryption policy is unsupported by this kernel; that is treated * like the key being unavailable, so that files can still be deleted. */ int fscrypt_prepare_lookup_partial(struct inode *dir, struct dentry *dentry) { int err = fscrypt_get_encryption_info(dir, true); bool is_nokey_name = (!err && !fscrypt_has_encryption_key(dir)); fscrypt_prepare_dentry(dentry, is_nokey_name); return err; } EXPORT_SYMBOL_GPL(fscrypt_prepare_lookup_partial); int __fscrypt_prepare_readdir(struct inode *dir) { return fscrypt_get_encryption_info(dir, true); } EXPORT_SYMBOL_GPL(__fscrypt_prepare_readdir); int __fscrypt_prepare_setattr(struct dentry *dentry, struct iattr *attr) { if (attr->ia_valid & ATTR_SIZE) return fscrypt_require_key(d_inode(dentry)); return 0; } EXPORT_SYMBOL_GPL(__fscrypt_prepare_setattr); /** * fscrypt_prepare_setflags() - prepare to change flags with FS_IOC_SETFLAGS * @inode: the inode on which flags are being changed * @oldflags: the old flags * @flags: the new flags * * The caller should be holding i_rwsem for write. * * Return: 0 on success; -errno if the flags change isn't allowed or if * another error occurs. */ int fscrypt_prepare_setflags(struct inode *inode, unsigned int oldflags, unsigned int flags) { struct fscrypt_inode_info *ci; struct fscrypt_master_key *mk; int err; /* * When the CASEFOLD flag is set on an encrypted directory, we must * derive the secret key needed for the dirhash. This is only possible * if the directory uses a v2 encryption policy. */ if (IS_ENCRYPTED(inode) && (flags & ~oldflags & FS_CASEFOLD_FL)) { err = fscrypt_require_key(inode); if (err) return err; ci = inode->i_crypt_info; if (ci->ci_policy.version != FSCRYPT_POLICY_V2) return -EINVAL; mk = ci->ci_master_key; down_read(&mk->mk_sem); if (mk->mk_present) err = fscrypt_derive_dirhash_key(ci, mk); else err = -ENOKEY; up_read(&mk->mk_sem); return err; } return 0; } /** * fscrypt_prepare_symlink() - prepare to create a possibly-encrypted symlink * @dir: directory in which the symlink is being created * @target: plaintext symlink target * @len: length of @target excluding null terminator * @max_len: space the filesystem has available to store the symlink target * @disk_link: (out) the on-disk symlink target being prepared * * This function computes the size the symlink target will require on-disk, * stores it in @disk_link->len, and validates it against @max_len. An * encrypted symlink may be longer than the original. * * Additionally, @disk_link->name is set to @target if the symlink will be * unencrypted, but left NULL if the symlink will be encrypted. For encrypted * symlinks, the filesystem must call fscrypt_encrypt_symlink() to create the * on-disk target later. (The reason for the two-step process is that some * filesystems need to know the size of the symlink target before creating the * inode, e.g. to determine whether it will be a "fast" or "slow" symlink.) * * Return: 0 on success, -ENAMETOOLONG if the symlink target is too long, * -ENOKEY if the encryption key is missing, or another -errno code if a problem * occurred while setting up the encryption key. */ int fscrypt_prepare_symlink(struct inode *dir, const char *target, unsigned int len, unsigned int max_len, struct fscrypt_str *disk_link) { const union fscrypt_policy *policy; /* * To calculate the size of the encrypted symlink target we need to know * the amount of NUL padding, which is determined by the flags set in * the encryption policy which will be inherited from the directory. */ policy = fscrypt_policy_to_inherit(dir); if (policy == NULL) { /* Not encrypted */ disk_link->name = (unsigned char *)target; disk_link->len = len + 1; if (disk_link->len > max_len) return -ENAMETOOLONG; return 0; } if (IS_ERR(policy)) return PTR_ERR(policy); /* * Calculate the size of the encrypted symlink and verify it won't * exceed max_len. Note that for historical reasons, encrypted symlink * targets are prefixed with the ciphertext length, despite this * actually being redundant with i_size. This decreases by 2 bytes the * longest symlink target we can accept. * * We could recover 1 byte by not counting a null terminator, but * counting it (even though it is meaningless for ciphertext) is simpler * for now since filesystems will assume it is there and subtract it. */ if (!__fscrypt_fname_encrypted_size(policy, len, max_len - sizeof(struct fscrypt_symlink_data) - 1, &disk_link->len)) return -ENAMETOOLONG; disk_link->len += sizeof(struct fscrypt_symlink_data) + 1; disk_link->name = NULL; return 0; } EXPORT_SYMBOL_GPL(fscrypt_prepare_symlink); int __fscrypt_encrypt_symlink(struct inode *inode, const char *target, unsigned int len, struct fscrypt_str *disk_link) { int err; struct qstr iname = QSTR_INIT(target, len); struct fscrypt_symlink_data *sd; unsigned int ciphertext_len; /* * fscrypt_prepare_new_inode() should have already set up the new * symlink inode's encryption key. We don't wait until now to do it, * since we may be in a filesystem transaction now. */ if (WARN_ON_ONCE(!fscrypt_has_encryption_key(inode))) return -ENOKEY; if (disk_link->name) { /* filesystem-provided buffer */ sd = (struct fscrypt_symlink_data *)disk_link->name; } else { sd = kmalloc(disk_link->len, GFP_NOFS); if (!sd) return -ENOMEM; } ciphertext_len = disk_link->len - sizeof(*sd) - 1; sd->len = cpu_to_le16(ciphertext_len); err = fscrypt_fname_encrypt(inode, &iname, sd->encrypted_path, ciphertext_len); if (err) goto err_free_sd; /* * Null-terminating the ciphertext doesn't make sense, but we still * count the null terminator in the length, so we might as well * initialize it just in case the filesystem writes it out. */ sd->encrypted_path[ciphertext_len] = '\0'; /* Cache the plaintext symlink target for later use by get_link() */ err = -ENOMEM; inode->i_link = kmemdup(target, len + 1, GFP_NOFS); if (!inode->i_link) goto err_free_sd; if (!disk_link->name) disk_link->name = (unsigned char *)sd; return 0; err_free_sd: if (!disk_link->name) kfree(sd); return err; } EXPORT_SYMBOL_GPL(__fscrypt_encrypt_symlink); /** * fscrypt_get_symlink() - get the target of an encrypted symlink * @inode: the symlink inode * @caddr: the on-disk contents of the symlink * @max_size: size of @caddr buffer * @done: if successful, will be set up to free the returned target if needed * * If the symlink's encryption key is available, we decrypt its target. * Otherwise, we encode its target for presentation. * * This may sleep, so the filesystem must have dropped out of RCU mode already. * * Return: the presentable symlink target or an ERR_PTR() */ const char *fscrypt_get_symlink(struct inode *inode, const void *caddr, unsigned int max_size, struct delayed_call *done) { const struct fscrypt_symlink_data *sd; struct fscrypt_str cstr, pstr; bool has_key; int err; /* This is for encrypted symlinks only */ if (WARN_ON_ONCE(!IS_ENCRYPTED(inode))) return ERR_PTR(-EINVAL); /* If the decrypted target is already cached, just return it. */ pstr.name = READ_ONCE(inode->i_link); if (pstr.name) return pstr.name; /* * Try to set up the symlink's encryption key, but we can continue * regardless of whether the key is available or not. */ err = fscrypt_get_encryption_info(inode, false); if (err) return ERR_PTR(err); has_key = fscrypt_has_encryption_key(inode); /* * For historical reasons, encrypted symlink targets are prefixed with * the ciphertext length, even though this is redundant with i_size. */ if (max_size < sizeof(*sd) + 1) return ERR_PTR(-EUCLEAN); sd = caddr; cstr.name = (unsigned char *)sd->encrypted_path; cstr.len = le16_to_cpu(sd->len); if (cstr.len == 0) return ERR_PTR(-EUCLEAN); if (cstr.len + sizeof(*sd) > max_size) return ERR_PTR(-EUCLEAN); err = fscrypt_fname_alloc_buffer(cstr.len, &pstr); if (err) return ERR_PTR(err); err = fscrypt_fname_disk_to_usr(inode, 0, 0, &cstr, &pstr); if (err) goto err_kfree; err = -EUCLEAN; if (pstr.name[0] == '\0') goto err_kfree; pstr.name[pstr.len] = '\0'; /* * Cache decrypted symlink targets in i_link for later use. Don't cache * symlink targets encoded without the key, since those become outdated * once the key is added. This pairs with the READ_ONCE() above and in * the VFS path lookup code. */ if (!has_key || cmpxchg_release(&inode->i_link, NULL, pstr.name) != NULL) set_delayed_call(done, kfree_link, pstr.name); return pstr.name; err_kfree: kfree(pstr.name); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(fscrypt_get_symlink); /** * fscrypt_symlink_getattr() - set the correct st_size for encrypted symlinks * @path: the path for the encrypted symlink being queried * @stat: the struct being filled with the symlink's attributes * * Override st_size of encrypted symlinks to be the length of the decrypted * symlink target (or the no-key encoded symlink target, if the key is * unavailable) rather than the length of the encrypted symlink target. This is * necessary for st_size to match the symlink target that userspace actually * sees. POSIX requires this, and some userspace programs depend on it. * * This requires reading the symlink target from disk if needed, setting up the * inode's encryption key if possible, and then decrypting or encoding the * symlink target. This makes lstat() more heavyweight than is normally the * case. However, decrypted symlink targets will be cached in ->i_link, so * usually the symlink won't have to be read and decrypted again later if/when * it is actually followed, readlink() is called, or lstat() is called again. * * Return: 0 on success, -errno on failure */ int fscrypt_symlink_getattr(const struct path *path, struct kstat *stat) { struct dentry *dentry = path->dentry; struct inode *inode = d_inode(dentry); const char *link; DEFINE_DELAYED_CALL(done); /* * To get the symlink target that userspace will see (whether it's the * decrypted target or the no-key encoded target), we can just get it in * the same way the VFS does during path resolution and readlink(). */ link = READ_ONCE(inode->i_link); if (!link) { link = inode->i_op->get_link(dentry, inode, &done); if (IS_ERR(link)) return PTR_ERR(link); } stat->size = strlen(link); do_delayed_call(&done); return 0; } EXPORT_SYMBOL_GPL(fscrypt_symlink_getattr); |
| 122 169 161 20 116 170 169 96 168 112 5 114 1 167 166 3 5 114 77 4 11 11 11 11 11 11 11 11 106 106 44 105 103 102 66 5 92 53 15 4 11 42 83 100 3 32 9 42 79 22 13 23 107 107 55 2 53 37 3 34 7 1 6 8 1 7 46 2 1 3 40 4 7 7 5 2 3 1 1 1 1 1 15 1 13 1 14 21 1 1 3 3 3 3 3 16 19 19 19 16 6 2 1 1 16 8 16 18 15 3 7 3 4 30 4 7 4 3 7 8 8 2 25 1 9 15 1 22 11 11 20 2 15 3 4 3 3 3 1 1 4 2 9 1 8 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * namei.c * * PURPOSE * Inode name handling routines for the OSTA-UDF(tm) filesystem. * * COPYRIGHT * (C) 1998-2004 Ben Fennema * (C) 1999-2000 Stelias Computing Inc * * HISTORY * * 12/12/98 blf Created. Split out the lookup code from dir.c * 04/19/99 blf link, mknod, symlink support */ #include "udfdecl.h" #include "udf_i.h" #include "udf_sb.h" #include <linux/string.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/crc-itu-t.h> #include <linux/exportfs.h> #include <linux/iversion.h> static inline int udf_match(int len1, const unsigned char *name1, int len2, const unsigned char *name2) { if (len1 != len2) return 0; return !memcmp(name1, name2, len1); } /** * udf_fiiter_find_entry - find entry in given directory. * * @dir: directory inode to search in * @child: qstr of the name * @iter: iter to use for searching * * This function searches in the directory @dir for a file name @child. When * found, @iter points to the position in the directory with given entry. * * Returns 0 on success, < 0 on error (including -ENOENT). */ static int udf_fiiter_find_entry(struct inode *dir, const struct qstr *child, struct udf_fileident_iter *iter) { int flen; unsigned char *fname = NULL; struct super_block *sb = dir->i_sb; int isdotdot = child->len == 2 && child->name[0] == '.' && child->name[1] == '.'; int ret; fname = kmalloc(UDF_NAME_LEN, GFP_KERNEL); if (!fname) return -ENOMEM; for (ret = udf_fiiter_init(iter, dir, 0); !ret && iter->pos < dir->i_size; ret = udf_fiiter_advance(iter)) { if (iter->fi.fileCharacteristics & FID_FILE_CHAR_DELETED) { if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNDELETE)) continue; } if (iter->fi.fileCharacteristics & FID_FILE_CHAR_HIDDEN) { if (!UDF_QUERY_FLAG(sb, UDF_FLAG_UNHIDE)) continue; } if ((iter->fi.fileCharacteristics & FID_FILE_CHAR_PARENT) && isdotdot) goto out_ok; if (!iter->fi.lengthFileIdent) continue; flen = udf_get_filename(sb, iter->name, iter->fi.lengthFileIdent, fname, UDF_NAME_LEN); if (flen < 0) { ret = flen; goto out_err; } if (udf_match(flen, fname, child->len, child->name)) goto out_ok; } if (!ret) ret = -ENOENT; out_err: udf_fiiter_release(iter); out_ok: kfree(fname); return ret; } static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { struct inode *inode = NULL; struct udf_fileident_iter iter; int err; if (dentry->d_name.len > UDF_NAME_LEN) return ERR_PTR(-ENAMETOOLONG); err = udf_fiiter_find_entry(dir, &dentry->d_name, &iter); if (err < 0 && err != -ENOENT) return ERR_PTR(err); if (err == 0) { struct kernel_lb_addr loc; loc = lelb_to_cpu(iter.fi.icb.extLocation); udf_fiiter_release(&iter); inode = udf_iget(dir->i_sb, &loc); } return d_splice_alias(inode, dentry); } static int udf_expand_dir_adinicb(struct inode *inode, udf_pblk_t *block) { udf_pblk_t newblock; struct buffer_head *dbh = NULL; struct kernel_lb_addr eloc; struct extent_position epos; uint8_t alloctype; struct udf_inode_info *iinfo = UDF_I(inode); struct udf_fileident_iter iter; uint8_t *impuse; int ret; if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_USE_SHORT_AD)) alloctype = ICBTAG_FLAG_AD_SHORT; else alloctype = ICBTAG_FLAG_AD_LONG; if (!inode->i_size) { iinfo->i_alloc_type = alloctype; mark_inode_dirty(inode); return 0; } /* alloc block, and copy data to it */ *block = udf_new_block(inode->i_sb, inode, iinfo->i_location.partitionReferenceNum, iinfo->i_location.logicalBlockNum, &ret); if (!(*block)) return ret; newblock = udf_get_pblock(inode->i_sb, *block, iinfo->i_location.partitionReferenceNum, 0); if (newblock == 0xffffffff) return -EFSCORRUPTED; dbh = sb_getblk(inode->i_sb, newblock); if (!dbh) return -ENOMEM; lock_buffer(dbh); memcpy(dbh->b_data, iinfo->i_data, inode->i_size); memset(dbh->b_data + inode->i_size, 0, inode->i_sb->s_blocksize - inode->i_size); set_buffer_uptodate(dbh); unlock_buffer(dbh); /* Drop inline data, add block instead */ iinfo->i_alloc_type = alloctype; memset(iinfo->i_data + iinfo->i_lenEAttr, 0, iinfo->i_lenAlloc); iinfo->i_lenAlloc = 0; eloc.logicalBlockNum = *block; eloc.partitionReferenceNum = iinfo->i_location.partitionReferenceNum; iinfo->i_lenExtents = inode->i_size; epos.bh = NULL; epos.block = iinfo->i_location; epos.offset = udf_file_entry_alloc_offset(inode); ret = udf_add_aext(inode, &epos, &eloc, inode->i_size, 0); brelse(epos.bh); if (ret < 0) { brelse(dbh); udf_free_blocks(inode->i_sb, inode, &eloc, 0, 1); return ret; } mark_inode_dirty(inode); /* Now fixup tags in moved directory entries */ for (ret = udf_fiiter_init(&iter, inode, 0); !ret && iter.pos < inode->i_size; ret = udf_fiiter_advance(&iter)) { iter.fi.descTag.tagLocation = cpu_to_le32(*block); if (iter.fi.lengthOfImpUse != cpu_to_le16(0)) impuse = dbh->b_data + iter.pos + sizeof(struct fileIdentDesc); else impuse = NULL; udf_fiiter_write_fi(&iter, impuse); } brelse(dbh); /* * We don't expect the iteration to fail as the directory has been * already verified to be correct */ WARN_ON_ONCE(ret); udf_fiiter_release(&iter); return 0; } static int udf_fiiter_add_entry(struct inode *dir, struct dentry *dentry, struct udf_fileident_iter *iter) { struct udf_inode_info *dinfo = UDF_I(dir); int nfidlen, namelen = 0; int ret; int off, blksize = 1 << dir->i_blkbits; udf_pblk_t block; char name[UDF_NAME_LEN_CS0]; if (dentry) { namelen = udf_put_filename(dir->i_sb, dentry->d_name.name, dentry->d_name.len, name, UDF_NAME_LEN_CS0); if (!namelen) return -ENAMETOOLONG; } nfidlen = ALIGN(sizeof(struct fileIdentDesc) + namelen, UDF_NAME_PAD); for (ret = udf_fiiter_init(iter, dir, 0); !ret && iter->pos < dir->i_size; ret = udf_fiiter_advance(iter)) { if (iter->fi.fileCharacteristics & FID_FILE_CHAR_DELETED) { if (udf_dir_entry_len(&iter->fi) == nfidlen) { iter->fi.descTag.tagSerialNum = cpu_to_le16(1); iter->fi.fileVersionNum = cpu_to_le16(1); iter->fi.fileCharacteristics = 0; iter->fi.lengthFileIdent = namelen; iter->fi.lengthOfImpUse = cpu_to_le16(0); memcpy(iter->namebuf, name, namelen); iter->name = iter->namebuf; return 0; } } } if (ret) { udf_fiiter_release(iter); return ret; } if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB && blksize - udf_ext0_offset(dir) - iter->pos < nfidlen) { udf_fiiter_release(iter); ret = udf_expand_dir_adinicb(dir, &block); if (ret) return ret; ret = udf_fiiter_init(iter, dir, dir->i_size); if (ret < 0) return ret; } /* Get blocknumber to use for entry tag */ if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { block = dinfo->i_location.logicalBlockNum; } else { block = iter->eloc.logicalBlockNum + ((iter->elen - 1) >> dir->i_blkbits); } off = iter->pos & (blksize - 1); if (!off) off = blksize; /* Entry fits into current block? */ if (blksize - udf_ext0_offset(dir) - off >= nfidlen) goto store_fi; ret = udf_fiiter_append_blk(iter); if (ret) { udf_fiiter_release(iter); return ret; } /* Entry will be completely in the new block? Update tag location... */ if (!(iter->pos & (blksize - 1))) block = iter->eloc.logicalBlockNum + ((iter->elen - 1) >> dir->i_blkbits); store_fi: memset(&iter->fi, 0, sizeof(struct fileIdentDesc)); if (UDF_SB(dir->i_sb)->s_udfrev >= 0x0200) udf_new_tag((char *)(&iter->fi), TAG_IDENT_FID, 3, 1, block, sizeof(struct tag)); else udf_new_tag((char *)(&iter->fi), TAG_IDENT_FID, 2, 1, block, sizeof(struct tag)); iter->fi.fileVersionNum = cpu_to_le16(1); iter->fi.lengthFileIdent = namelen; iter->fi.lengthOfImpUse = cpu_to_le16(0); memcpy(iter->namebuf, name, namelen); iter->name = iter->namebuf; dir->i_size += nfidlen; if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) { dinfo->i_lenAlloc += nfidlen; } else { /* Truncate last extent to proper size */ udf_fiiter_update_elen(iter, iter->elen - (dinfo->i_lenExtents - dir->i_size)); } mark_inode_dirty(dir); return 0; } static void udf_fiiter_delete_entry(struct udf_fileident_iter *iter) { iter->fi.fileCharacteristics |= FID_FILE_CHAR_DELETED; if (UDF_QUERY_FLAG(iter->dir->i_sb, UDF_FLAG_STRICT)) memset(&iter->fi.icb, 0x00, sizeof(struct long_ad)); udf_fiiter_write_fi(iter, NULL); } static void udf_add_fid_counter(struct super_block *sb, bool dir, int val) { struct logicalVolIntegrityDescImpUse *lvidiu = udf_sb_lvidiu(sb); if (!lvidiu) return; mutex_lock(&UDF_SB(sb)->s_alloc_mutex); if (dir) le32_add_cpu(&lvidiu->numDirs, val); else le32_add_cpu(&lvidiu->numFiles, val); udf_updated_lvid(sb); mutex_unlock(&UDF_SB(sb)->s_alloc_mutex); } static int udf_add_nondir(struct dentry *dentry, struct inode *inode) { struct udf_inode_info *iinfo = UDF_I(inode); struct inode *dir = d_inode(dentry->d_parent); struct udf_fileident_iter iter; int err; err = udf_fiiter_add_entry(dir, dentry, &iter); if (err) { inode_dec_link_count(inode); discard_new_inode(inode); return err; } iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); iter.fi.icb.extLocation = cpu_to_lelb(iinfo->i_location); *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(iinfo->i_unique & 0x00000000FFFFFFFFUL); udf_fiiter_write_fi(&iter, NULL); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); udf_fiiter_release(&iter); udf_add_fid_counter(dir->i_sb, false, 1); d_instantiate_new(dentry, inode); return 0; } static int udf_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct inode *inode = udf_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_data.a_ops = &udf_aops; inode->i_op = &udf_file_inode_operations; inode->i_fop = &udf_file_operations; mark_inode_dirty(inode); return udf_add_nondir(dentry, inode); } static int udf_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode = udf_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_data.a_ops = &udf_aops; inode->i_op = &udf_file_inode_operations; inode->i_fop = &udf_file_operations; mark_inode_dirty(inode); d_tmpfile(file, inode); unlock_new_inode(inode); return finish_open_simple(file, 0); } static int udf_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct inode *inode; if (!old_valid_dev(rdev)) return -EINVAL; inode = udf_new_inode(dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); init_special_inode(inode, mode, rdev); return udf_add_nondir(dentry, inode); } static struct dentry *udf_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; struct udf_fileident_iter iter; int err; struct udf_inode_info *dinfo = UDF_I(dir); struct udf_inode_info *iinfo; inode = udf_new_inode(dir, S_IFDIR | mode); if (IS_ERR(inode)) return ERR_CAST(inode); iinfo = UDF_I(inode); inode->i_op = &udf_dir_inode_operations; inode->i_fop = &udf_dir_operations; err = udf_fiiter_add_entry(inode, NULL, &iter); if (err) { clear_nlink(inode); discard_new_inode(inode); return ERR_PTR(err); } set_nlink(inode, 2); iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); iter.fi.icb.extLocation = cpu_to_lelb(dinfo->i_location); *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(dinfo->i_unique & 0x00000000FFFFFFFFUL); iter.fi.fileCharacteristics = FID_FILE_CHAR_DIRECTORY | FID_FILE_CHAR_PARENT; udf_fiiter_write_fi(&iter, NULL); udf_fiiter_release(&iter); mark_inode_dirty(inode); err = udf_fiiter_add_entry(dir, dentry, &iter); if (err) { clear_nlink(inode); discard_new_inode(inode); return ERR_PTR(err); } iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); iter.fi.icb.extLocation = cpu_to_lelb(iinfo->i_location); *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(iinfo->i_unique & 0x00000000FFFFFFFFUL); iter.fi.fileCharacteristics |= FID_FILE_CHAR_DIRECTORY; udf_fiiter_write_fi(&iter, NULL); udf_fiiter_release(&iter); udf_add_fid_counter(dir->i_sb, true, 1); inc_nlink(dir); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); d_instantiate_new(dentry, inode); return NULL; } static int empty_dir(struct inode *dir) { struct udf_fileident_iter iter; int ret; for (ret = udf_fiiter_init(&iter, dir, 0); !ret && iter.pos < dir->i_size; ret = udf_fiiter_advance(&iter)) { if (iter.fi.lengthFileIdent && !(iter.fi.fileCharacteristics & FID_FILE_CHAR_DELETED)) { udf_fiiter_release(&iter); return 0; } } udf_fiiter_release(&iter); return 1; } static int udf_rmdir(struct inode *dir, struct dentry *dentry) { int ret; struct inode *inode = d_inode(dentry); struct udf_fileident_iter iter; struct kernel_lb_addr tloc; ret = udf_fiiter_find_entry(dir, &dentry->d_name, &iter); if (ret) goto out; ret = -EFSCORRUPTED; tloc = lelb_to_cpu(iter.fi.icb.extLocation); if (udf_get_lb_pblock(dir->i_sb, &tloc, 0) != inode->i_ino) goto end_rmdir; ret = -ENOTEMPTY; if (!empty_dir(inode)) goto end_rmdir; udf_fiiter_delete_entry(&iter); if (inode->i_nlink != 2) udf_warn(inode->i_sb, "empty directory has nlink != 2 (%u)\n", inode->i_nlink); clear_nlink(inode); inode->i_size = 0; if (dir->i_nlink >= 3) inode_dec_link_count(dir); else udf_warn(inode->i_sb, "parent dir link count too low (%u)\n", dir->i_nlink); udf_add_fid_counter(dir->i_sb, true, -1); inode_set_mtime_to_ts(dir, inode_set_ctime_to_ts(dir, inode_set_ctime_current(inode))); mark_inode_dirty(dir); ret = 0; end_rmdir: udf_fiiter_release(&iter); out: return ret; } static int udf_unlink(struct inode *dir, struct dentry *dentry) { int ret; struct inode *inode = d_inode(dentry); struct udf_fileident_iter iter; struct kernel_lb_addr tloc; ret = udf_fiiter_find_entry(dir, &dentry->d_name, &iter); if (ret) goto out; ret = -EFSCORRUPTED; tloc = lelb_to_cpu(iter.fi.icb.extLocation); if (udf_get_lb_pblock(dir->i_sb, &tloc, 0) != inode->i_ino) goto end_unlink; if (!inode->i_nlink) { udf_debug("Deleting nonexistent file (%lu), %u\n", inode->i_ino, inode->i_nlink); set_nlink(inode, 1); } udf_fiiter_delete_entry(&iter); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); inode_dec_link_count(inode); udf_add_fid_counter(dir->i_sb, false, -1); inode_set_ctime_to_ts(inode, inode_get_ctime(dir)); ret = 0; end_unlink: udf_fiiter_release(&iter); out: return ret; } static int udf_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { struct inode *inode; struct pathComponent *pc; const char *compstart; struct extent_position epos = {}; int eoffset, elen = 0; uint8_t *ea; int err; udf_pblk_t block; unsigned char *name = NULL; int namelen; struct udf_inode_info *iinfo; struct super_block *sb = dir->i_sb; name = kmalloc(UDF_NAME_LEN_CS0, GFP_KERNEL); if (!name) { err = -ENOMEM; goto out; } inode = udf_new_inode(dir, S_IFLNK | 0777); if (IS_ERR(inode)) { err = PTR_ERR(inode); goto out; } iinfo = UDF_I(inode); down_write(&iinfo->i_data_sem); inode->i_data.a_ops = &udf_symlink_aops; inode->i_op = &udf_symlink_inode_operations; inode_nohighmem(inode); if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) { struct kernel_lb_addr eloc; uint32_t bsize; block = udf_new_block(sb, inode, iinfo->i_location.partitionReferenceNum, iinfo->i_location.logicalBlockNum, &err); if (!block) goto out_no_entry; epos.block = iinfo->i_location; epos.offset = udf_file_entry_alloc_offset(inode); epos.bh = NULL; eloc.logicalBlockNum = block; eloc.partitionReferenceNum = iinfo->i_location.partitionReferenceNum; bsize = sb->s_blocksize; iinfo->i_lenExtents = bsize; err = udf_add_aext(inode, &epos, &eloc, bsize, 0); brelse(epos.bh); if (err < 0) { udf_free_blocks(sb, inode, &eloc, 0, 1); goto out_no_entry; } block = udf_get_pblock(sb, block, iinfo->i_location.partitionReferenceNum, 0); epos.bh = sb_getblk(sb, block); if (unlikely(!epos.bh)) { err = -ENOMEM; udf_free_blocks(sb, inode, &eloc, 0, 1); goto out_no_entry; } lock_buffer(epos.bh); memset(epos.bh->b_data, 0x00, bsize); set_buffer_uptodate(epos.bh); unlock_buffer(epos.bh); mark_buffer_dirty_inode(epos.bh, inode); ea = epos.bh->b_data + udf_ext0_offset(inode); } else ea = iinfo->i_data + iinfo->i_lenEAttr; eoffset = sb->s_blocksize - udf_ext0_offset(inode); pc = (struct pathComponent *)ea; if (*symname == '/') { do { symname++; } while (*symname == '/'); pc->componentType = 1; pc->lengthComponentIdent = 0; pc->componentFileVersionNum = 0; elen += sizeof(struct pathComponent); } err = -ENAMETOOLONG; while (*symname) { if (elen + sizeof(struct pathComponent) > eoffset) goto out_no_entry; pc = (struct pathComponent *)(ea + elen); compstart = symname; do { symname++; } while (*symname && *symname != '/'); pc->componentType = 5; pc->lengthComponentIdent = 0; pc->componentFileVersionNum = 0; if (compstart[0] == '.') { if ((symname - compstart) == 1) pc->componentType = 4; else if ((symname - compstart) == 2 && compstart[1] == '.') pc->componentType = 3; } if (pc->componentType == 5) { namelen = udf_put_filename(sb, compstart, symname - compstart, name, UDF_NAME_LEN_CS0); if (!namelen) goto out_no_entry; if (elen + sizeof(struct pathComponent) + namelen > eoffset) goto out_no_entry; else pc->lengthComponentIdent = namelen; memcpy(pc->componentIdent, name, namelen); } elen += sizeof(struct pathComponent) + pc->lengthComponentIdent; if (*symname) { do { symname++; } while (*symname == '/'); } } brelse(epos.bh); inode->i_size = elen; if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) iinfo->i_lenAlloc = inode->i_size; else udf_truncate_tail_extent(inode); mark_inode_dirty(inode); up_write(&iinfo->i_data_sem); err = udf_add_nondir(dentry, inode); out: kfree(name); return err; out_no_entry: up_write(&iinfo->i_data_sem); inode_dec_link_count(inode); discard_new_inode(inode); goto out; } static int udf_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = d_inode(old_dentry); struct udf_fileident_iter iter; int err; err = udf_fiiter_add_entry(dir, dentry, &iter); if (err) return err; iter.fi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize); iter.fi.icb.extLocation = cpu_to_lelb(UDF_I(inode)->i_location); if (UDF_SB(inode->i_sb)->s_lvid_bh) { *(__le32 *)((struct allocDescImpUse *)iter.fi.icb.impUse)->impUse = cpu_to_le32(lvid_get_unique_id(inode->i_sb)); } udf_fiiter_write_fi(&iter, NULL); udf_fiiter_release(&iter); inc_nlink(inode); udf_add_fid_counter(dir->i_sb, false, 1); inode_set_ctime_current(inode); mark_inode_dirty(inode); inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); mark_inode_dirty(dir); ihold(inode); d_instantiate(dentry, inode); return 0; } /* Anybody can rename anything with this: the permission checks are left to the * higher-level routines. */ static int udf_rename(struct mnt_idmap *idmap, struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags) { struct inode *old_inode = d_inode(old_dentry); struct inode *new_inode = d_inode(new_dentry); struct udf_fileident_iter oiter, niter, diriter; bool has_diriter = false, is_dir = false; int retval; struct kernel_lb_addr tloc; if (flags & ~RENAME_NOREPLACE) return -EINVAL; retval = udf_fiiter_find_entry(old_dir, &old_dentry->d_name, &oiter); if (retval) return retval; tloc = lelb_to_cpu(oiter.fi.icb.extLocation); if (udf_get_lb_pblock(old_dir->i_sb, &tloc, 0) != old_inode->i_ino) { retval = -ENOENT; goto out_oiter; } if (S_ISDIR(old_inode->i_mode)) { if (new_inode) { retval = -ENOTEMPTY; if (!empty_dir(new_inode)) goto out_oiter; retval = -EFSCORRUPTED; if (new_inode->i_nlink != 2) goto out_oiter; } retval = -EFSCORRUPTED; if (old_dir->i_nlink < 3) goto out_oiter; is_dir = true; } else if (new_inode) { retval = -EFSCORRUPTED; if (new_inode->i_nlink < 1) goto out_oiter; } if (is_dir && old_dir != new_dir) { retval = udf_fiiter_find_entry(old_inode, &dotdot_name, &diriter); if (retval == -ENOENT) { udf_err(old_inode->i_sb, "directory (ino %lu) has no '..' entry\n", old_inode->i_ino); retval = -EFSCORRUPTED; } if (retval) goto out_oiter; has_diriter = true; tloc = lelb_to_cpu(diriter.fi.icb.extLocation); if (udf_get_lb_pblock(old_inode->i_sb, &tloc, 0) != old_dir->i_ino) { retval = -EFSCORRUPTED; udf_err(old_inode->i_sb, "directory (ino %lu) has parent entry pointing to another inode (%lu != %u)\n", old_inode->i_ino, old_dir->i_ino, udf_get_lb_pblock(old_inode->i_sb, &tloc, 0)); goto out_oiter; } } retval = udf_fiiter_find_entry(new_dir, &new_dentry->d_name, &niter); if (retval && retval != -ENOENT) goto out_oiter; /* Entry found but not passed by VFS? */ if (!retval && !new_inode) { retval = -EFSCORRUPTED; udf_fiiter_release(&niter); goto out_oiter; } /* Entry not found? Need to add one... */ if (retval) { udf_fiiter_release(&niter); retval = udf_fiiter_add_entry(new_dir, new_dentry, &niter); if (retval) goto out_oiter; } /* * Like most other Unix systems, set the ctime for inodes on a * rename. */ inode_set_ctime_current(old_inode); mark_inode_dirty(old_inode); /* * ok, that's it */ niter.fi.fileVersionNum = oiter.fi.fileVersionNum; niter.fi.fileCharacteristics = oiter.fi.fileCharacteristics; memcpy(&(niter.fi.icb), &(oiter.fi.icb), sizeof(oiter.fi.icb)); udf_fiiter_write_fi(&niter, NULL); udf_fiiter_release(&niter); /* * The old entry may have moved due to new entry allocation. Find it * again. */ udf_fiiter_release(&oiter); retval = udf_fiiter_find_entry(old_dir, &old_dentry->d_name, &oiter); if (retval) { udf_err(old_dir->i_sb, "failed to find renamed entry again in directory (ino %lu)\n", old_dir->i_ino); } else { udf_fiiter_delete_entry(&oiter); udf_fiiter_release(&oiter); } if (new_inode) { inode_set_ctime_current(new_inode); inode_dec_link_count(new_inode); udf_add_fid_counter(old_dir->i_sb, S_ISDIR(new_inode->i_mode), -1); } inode_set_mtime_to_ts(old_dir, inode_set_ctime_current(old_dir)); inode_set_mtime_to_ts(new_dir, inode_set_ctime_current(new_dir)); mark_inode_dirty(old_dir); mark_inode_dirty(new_dir); if (has_diriter) { diriter.fi.icb.extLocation = cpu_to_lelb(UDF_I(new_dir)->i_location); udf_fiiter_write_fi(&diriter, NULL); udf_fiiter_release(&diriter); } if (is_dir) { inode_dec_link_count(old_dir); if (new_inode) inode_dec_link_count(new_inode); else { inc_nlink(new_dir); mark_inode_dirty(new_dir); } } return 0; out_oiter: if (has_diriter) udf_fiiter_release(&diriter); udf_fiiter_release(&oiter); return retval; } static struct dentry *udf_get_parent(struct dentry *child) { struct kernel_lb_addr tloc; struct udf_fileident_iter iter; int err; err = udf_fiiter_find_entry(d_inode(child), &dotdot_name, &iter); if (err) return ERR_PTR(err); tloc = lelb_to_cpu(iter.fi.icb.extLocation); udf_fiiter_release(&iter); return d_obtain_alias(udf_iget(child->d_sb, &tloc)); } static struct dentry *udf_nfs_get_inode(struct super_block *sb, u32 block, u16 partref, __u32 generation) { struct inode *inode; struct kernel_lb_addr loc; if (block == 0) return ERR_PTR(-ESTALE); loc.logicalBlockNum = block; loc.partitionReferenceNum = partref; inode = udf_iget(sb, &loc); if (IS_ERR(inode)) return ERR_CAST(inode); if (generation && inode->i_generation != generation) { iput(inode); return ERR_PTR(-ESTALE); } return d_obtain_alias(inode); } static struct dentry *udf_fh_to_dentry(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { if (fh_len < 3 || (fh_type != FILEID_UDF_WITH_PARENT && fh_type != FILEID_UDF_WITHOUT_PARENT)) return NULL; return udf_nfs_get_inode(sb, fid->udf.block, fid->udf.partref, fid->udf.generation); } static struct dentry *udf_fh_to_parent(struct super_block *sb, struct fid *fid, int fh_len, int fh_type) { if (fh_len < 5 || fh_type != FILEID_UDF_WITH_PARENT) return NULL; return udf_nfs_get_inode(sb, fid->udf.parent_block, fid->udf.parent_partref, fid->udf.parent_generation); } static int udf_encode_fh(struct inode *inode, __u32 *fh, int *lenp, struct inode *parent) { int len = *lenp; struct kernel_lb_addr location = UDF_I(inode)->i_location; struct fid *fid = (struct fid *)fh; int type = FILEID_UDF_WITHOUT_PARENT; if (parent && (len < 5)) { *lenp = 5; return FILEID_INVALID; } else if (len < 3) { *lenp = 3; return FILEID_INVALID; } *lenp = 3; fid->udf.block = location.logicalBlockNum; fid->udf.partref = location.partitionReferenceNum; fid->udf.parent_partref = 0; fid->udf.generation = inode->i_generation; if (parent) { location = UDF_I(parent)->i_location; fid->udf.parent_block = location.logicalBlockNum; fid->udf.parent_partref = location.partitionReferenceNum; fid->udf.parent_generation = inode->i_generation; *lenp = 5; type = FILEID_UDF_WITH_PARENT; } return type; } const struct export_operations udf_export_ops = { .encode_fh = udf_encode_fh, .fh_to_dentry = udf_fh_to_dentry, .fh_to_parent = udf_fh_to_parent, .get_parent = udf_get_parent, }; const struct inode_operations udf_dir_inode_operations = { .lookup = udf_lookup, .create = udf_create, .link = udf_link, .unlink = udf_unlink, .symlink = udf_symlink, .mkdir = udf_mkdir, .rmdir = udf_rmdir, .mknod = udf_mknod, .rename = udf_rename, .tmpfile = udf_tmpfile, }; |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Architecture specific (i386/x86_64) functions for kexec based crash dumps. * * Created by: Hariprasad Nellitheertha (hari@in.ibm.com) * * Copyright (C) IBM Corporation, 2004. All rights reserved. * Copyright (C) Red Hat Inc., 2014. All rights reserved. * Authors: * Vivek Goyal <vgoyal@redhat.com> * */ #define pr_fmt(fmt) "kexec: " fmt #include <linux/types.h> #include <linux/kernel.h> #include <linux/smp.h> #include <linux/reboot.h> #include <linux/kexec.h> #include <linux/delay.h> #include <linux/elf.h> #include <linux/elfcore.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/memblock.h> #include <asm/bootparam.h> #include <asm/processor.h> #include <asm/hardirq.h> #include <asm/nmi.h> #include <asm/hw_irq.h> #include <asm/apic.h> #include <asm/e820/types.h> #include <asm/io_apic.h> #include <asm/hpet.h> #include <linux/kdebug.h> #include <asm/cpu.h> #include <asm/reboot.h> #include <asm/intel_pt.h> #include <asm/crash.h> #include <asm/cmdline.h> #include <asm/sev.h> /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { struct boot_params *params; /* Type of memory */ unsigned int type; }; #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC) static void kdump_nmi_callback(int cpu, struct pt_regs *regs) { crash_save_cpu(regs, cpu); /* * Disable Intel PT to stop its logging */ cpu_emergency_stop_pt(); kdump_sev_callback(); disable_local_APIC(); } void kdump_nmi_shootdown_cpus(void) { nmi_shootdown_cpus(kdump_nmi_callback); disable_local_APIC(); } /* Override the weak function in kernel/panic.c */ void crash_smp_send_stop(void) { static int cpus_stopped; if (cpus_stopped) return; if (smp_ops.crash_stop_other_cpus) smp_ops.crash_stop_other_cpus(); else smp_send_stop(); cpus_stopped = 1; } #else void crash_smp_send_stop(void) { /* There are no cpus to shootdown */ } #endif void native_machine_crash_shutdown(struct pt_regs *regs) { /* This function is only called after the system * has panicked or is otherwise in a critical state. * The minimum amount of code to allow a kexec'd kernel * to run successfully needs to happen here. * * In practice this means shooting down the other cpus in * an SMP system. */ /* The kernel is broken so disable interrupts */ local_irq_disable(); crash_smp_send_stop(); cpu_emergency_disable_virtualization(); /* * Disable Intel PT to stop its logging */ cpu_emergency_stop_pt(); #ifdef CONFIG_X86_IO_APIC /* Prevent crash_kexec() from deadlocking on ioapic_lock. */ ioapic_zap_locks(); clear_IO_APIC(); #endif lapic_shutdown(); restore_boot_irq_mode(); #ifdef CONFIG_HPET_TIMER hpet_disable(); #endif /* * Non-crash kexec calls enc_kexec_begin() while scheduling is still * active. This allows the callback to wait until all in-flight * shared<->private conversions are complete. In a crash scenario, * enc_kexec_begin() gets called after all but one CPU have been shut * down and interrupts have been disabled. This allows the callback to * detect a race with the conversion and report it. */ x86_platform.guest.enc_kexec_begin(); x86_platform.guest.enc_kexec_finish(); crash_save_cpu(regs, smp_processor_id()); } #if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_HOTPLUG) static int get_nr_ram_ranges_callback(struct resource *res, void *arg) { unsigned int *nr_ranges = arg; (*nr_ranges)++; return 0; } /* Gather all the required information to prepare elf headers for ram regions */ static struct crash_mem *fill_up_crash_elf_data(void) { unsigned int nr_ranges = 0; struct crash_mem *cmem; walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); if (!nr_ranges) return NULL; /* * Exclusion of crash region, crashk_low_res and/or crashk_cma_ranges * may cause range splits. So add extra slots here. */ nr_ranges += 2 + crashk_cma_cnt; cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); if (!cmem) return NULL; cmem->max_nr_ranges = nr_ranges; cmem->nr_ranges = 0; return cmem; } /* * Look for any unwanted ranges between mstart, mend and remove them. This * might lead to split and split ranges are put in cmem->ranges[] array */ static int elf_header_exclude_ranges(struct crash_mem *cmem) { int ret = 0; int i; /* Exclude the low 1M because it is always reserved */ ret = crash_exclude_mem_range(cmem, 0, SZ_1M - 1); if (ret) return ret; /* Exclude crashkernel region */ ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); if (ret) return ret; if (crashk_low_res.end) ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end); if (ret) return ret; for (i = 0; i < crashk_cma_cnt; ++i) { ret = crash_exclude_mem_range(cmem, crashk_cma_ranges[i].start, crashk_cma_ranges[i].end); if (ret) return ret; } return 0; } static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) { struct crash_mem *cmem = arg; cmem->ranges[cmem->nr_ranges].start = res->start; cmem->ranges[cmem->nr_ranges].end = res->end; cmem->nr_ranges++; return 0; } /* Prepare elf headers. Return addr and size */ static int prepare_elf_headers(void **addr, unsigned long *sz, unsigned long *nr_mem_ranges) { struct crash_mem *cmem; int ret; cmem = fill_up_crash_elf_data(); if (!cmem) return -ENOMEM; ret = walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); if (ret) goto out; /* Exclude unwanted mem ranges */ ret = elf_header_exclude_ranges(cmem); if (ret) goto out; /* Return the computed number of memory ranges, for hotplug usage */ *nr_mem_ranges = cmem->nr_ranges; /* By default prepare 64bit headers */ ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); out: vfree(cmem); return ret; } #endif #ifdef CONFIG_KEXEC_FILE static int add_e820_entry(struct boot_params *params, struct e820_entry *entry) { unsigned int nr_e820_entries; nr_e820_entries = params->e820_entries; if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE) return 1; memcpy(¶ms->e820_table[nr_e820_entries], entry, sizeof(struct e820_entry)); params->e820_entries++; return 0; } static int memmap_entry_callback(struct resource *res, void *arg) { struct crash_memmap_data *cmd = arg; struct boot_params *params = cmd->params; struct e820_entry ei; ei.addr = res->start; ei.size = resource_size(res); ei.type = cmd->type; add_e820_entry(params, &ei); return 0; } static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem, unsigned long long mstart, unsigned long long mend) { unsigned long start, end; int ret; cmem->ranges[0].start = mstart; cmem->ranges[0].end = mend; cmem->nr_ranges = 1; /* Exclude elf header region */ start = image->elf_load_addr; end = start + image->elf_headers_sz - 1; ret = crash_exclude_mem_range(cmem, start, end); if (ret) return ret; /* Exclude dm crypt keys region */ if (image->dm_crypt_keys_addr) { start = image->dm_crypt_keys_addr; end = start + image->dm_crypt_keys_sz - 1; return crash_exclude_mem_range(cmem, start, end); } return ret; } /* Prepare memory map for crash dump kernel */ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) { unsigned int nr_ranges = 0; int i, ret = 0; unsigned long flags; struct e820_entry ei; struct crash_memmap_data cmd; struct crash_mem *cmem; /* * Using random kexec_buf for passing dm crypt keys may cause a range * split. So use two slots here. */ nr_ranges = 2; cmem = vzalloc(struct_size(cmem, ranges, nr_ranges)); if (!cmem) return -ENOMEM; cmem->max_nr_ranges = nr_ranges; cmem->nr_ranges = 0; memset(&cmd, 0, sizeof(struct crash_memmap_data)); cmd.params = params; /* Add the low 1M */ cmd.type = E820_TYPE_RAM; flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; walk_iomem_res_desc(IORES_DESC_NONE, flags, 0, (1<<20)-1, &cmd, memmap_entry_callback); /* Add ACPI tables */ cmd.type = E820_TYPE_ACPI; flags = IORESOURCE_MEM | IORESOURCE_BUSY; walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd, memmap_entry_callback); /* Add ACPI Non-volatile Storage */ cmd.type = E820_TYPE_NVS; walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd, memmap_entry_callback); /* Add e820 reserved ranges */ cmd.type = E820_TYPE_RESERVED; flags = IORESOURCE_MEM; walk_iomem_res_desc(IORES_DESC_RESERVED, flags, 0, -1, &cmd, memmap_entry_callback); /* Add crashk_low_res region */ if (crashk_low_res.end) { ei.addr = crashk_low_res.start; ei.size = resource_size(&crashk_low_res); ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } /* Exclude some ranges from crashk_res and add rest to memmap */ ret = memmap_exclude_ranges(image, cmem, crashk_res.start, crashk_res.end); if (ret) goto out; for (i = 0; i < cmem->nr_ranges; i++) { ei.size = cmem->ranges[i].end - cmem->ranges[i].start + 1; /* If entry is less than a page, skip it */ if (ei.size < PAGE_SIZE) continue; ei.addr = cmem->ranges[i].start; ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } for (i = 0; i < crashk_cma_cnt; ++i) { ei.addr = crashk_cma_ranges[i].start; ei.size = crashk_cma_ranges[i].end - crashk_cma_ranges[i].start + 1; ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } out: vfree(cmem); return ret; } int crash_load_segments(struct kimage *image) { int ret; unsigned long pnum = 0; struct kexec_buf kbuf = { .image = image, .buf_min = 0, .buf_max = ULONG_MAX, .top_down = false }; /* Prepare elf headers and add a segment */ ret = prepare_elf_headers(&kbuf.buffer, &kbuf.bufsz, &pnum); if (ret) return ret; image->elf_headers = kbuf.buffer; image->elf_headers_sz = kbuf.bufsz; kbuf.memsz = kbuf.bufsz; #ifdef CONFIG_CRASH_HOTPLUG /* * The elfcorehdr segment size accounts for VMCOREINFO, kernel_map, * maximum CPUs and maximum memory ranges. */ if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) pnum = 2 + CONFIG_NR_CPUS_DEFAULT + CONFIG_CRASH_MAX_MEMORY_RANGES; else pnum += 2 + CONFIG_NR_CPUS_DEFAULT; if (pnum < (unsigned long)PN_XNUM) { kbuf.memsz = pnum * sizeof(Elf64_Phdr); kbuf.memsz += sizeof(Elf64_Ehdr); image->elfcorehdr_index = image->nr_segments; /* Mark as usable to crash kernel, else crash kernel fails on boot */ image->elf_headers_sz = kbuf.memsz; } else { pr_err("number of Phdrs %lu exceeds max\n", pnum); } #endif kbuf.buf_align = ELF_CORE_HEADER_ALIGN; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) return ret; image->elf_load_addr = kbuf.mem; kexec_dprintk("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", image->elf_load_addr, kbuf.bufsz, kbuf.memsz); return ret; } #endif /* CONFIG_KEXEC_FILE */ #ifdef CONFIG_CRASH_HOTPLUG #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags) { #ifdef CONFIG_KEXEC_FILE if (image->file_mode) return 1; #endif /* * Initially, crash hotplug support for kexec_load was added * with the KEXEC_UPDATE_ELFCOREHDR flag. Later, this * functionality was expanded to accommodate multiple kexec * segment updates, leading to the introduction of the * KEXEC_CRASH_HOTPLUG_SUPPORT kexec flag bit. Consequently, * when the kexec tool sends either of these flags, it indicates * that the required kexec segment (elfcorehdr) is excluded from * the SHA calculation. */ return (kexec_flags & KEXEC_UPDATE_ELFCOREHDR || kexec_flags & KEXEC_CRASH_HOTPLUG_SUPPORT); } unsigned int arch_crash_get_elfcorehdr_size(void) { unsigned int sz; /* kernel_map, VMCOREINFO and maximum CPUs */ sz = 2 + CONFIG_NR_CPUS_DEFAULT; if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) sz += CONFIG_CRASH_MAX_MEMORY_RANGES; sz *= sizeof(Elf64_Phdr); return sz; } /** * arch_crash_handle_hotplug_event() - Handle hotplug elfcorehdr changes * @image: a pointer to kexec_crash_image * @arg: struct memory_notify handler for memory hotplug case and * NULL for CPU hotplug case. * * Prepare the new elfcorehdr and replace the existing elfcorehdr. */ void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { void *elfbuf = NULL, *old_elfcorehdr; unsigned long nr_mem_ranges; unsigned long mem, memsz; unsigned long elfsz = 0; /* * As crash_prepare_elf64_headers() has already described all * possible CPUs, there is no need to update the elfcorehdr * for additional CPU changes. */ if ((image->file_mode || image->elfcorehdr_updated) && ((image->hp_action == KEXEC_CRASH_HP_ADD_CPU) || (image->hp_action == KEXEC_CRASH_HP_REMOVE_CPU))) return; /* * Create the new elfcorehdr reflecting the changes to CPU and/or * memory resources. */ if (prepare_elf_headers(&elfbuf, &elfsz, &nr_mem_ranges)) { pr_err("unable to create new elfcorehdr"); goto out; } /* * Obtain address and size of the elfcorehdr segment, and * check it against the new elfcorehdr buffer. */ mem = image->segment[image->elfcorehdr_index].mem; memsz = image->segment[image->elfcorehdr_index].memsz; if (elfsz > memsz) { pr_err("update elfcorehdr elfsz %lu > memsz %lu", elfsz, memsz); goto out; } /* * Copy new elfcorehdr over the old elfcorehdr at destination. */ old_elfcorehdr = kmap_local_page(pfn_to_page(mem >> PAGE_SHIFT)); if (!old_elfcorehdr) { pr_err("mapping elfcorehdr segment failed\n"); goto out; } /* * Temporarily invalidate the crash image while the * elfcorehdr is updated. */ xchg(&kexec_crash_image, NULL); memcpy_flushcache(old_elfcorehdr, elfbuf, elfsz); xchg(&kexec_crash_image, image); kunmap_local(old_elfcorehdr); pr_debug("updated elfcorehdr\n"); out: vfree(elfbuf); } #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 1 1 1 1 1 1 1 4 4 4 4 4 4 4 4 2 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 3 4 4 5 5 5 5 5 5 2 5 5 5 5 5 5 5 5 5 5 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: Internet Group Management Protocol [IGMP] * * This code implements the IGMP protocol as defined in RFC1112. There has * been a further revision of this protocol since which is now supported. * * If you have trouble with this module be careful what gcc you have used, * the older version didn't come out right using gcc 2.5.8, the newer one * seems to fall out with gcc 2.6.2. * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * Alan Cox : Added lots of __inline__ to optimise * the memory usage of all the tiny little * functions. * Alan Cox : Dumped the header building experiment. * Alan Cox : Minor tweaks ready for multicast routing * and extended IGMP protocol. * Alan Cox : Removed a load of inline directives. Gcc 2.5.8 * writes utterly bogus code otherwise (sigh) * fixed IGMP loopback to behave in the manner * desired by mrouted, fixed the fact it has been * broken since 1.3.6 and cleaned up a few minor * points. * * Chih-Jen Chang : Tried to revise IGMP to Version 2 * Tsu-Sheng Tsao E-mail: chihjenc@scf.usc.edu and tsusheng@scf.usc.edu * The enhancements are mainly based on Steve Deering's * ipmulti-3.5 source code. * Chih-Jen Chang : Added the igmp_get_mrouter_info and * Tsu-Sheng Tsao igmp_set_mrouter_info to keep track of * the mrouted version on that device. * Chih-Jen Chang : Added the max_resp_time parameter to * Tsu-Sheng Tsao igmp_heard_query(). Using this parameter * to identify the multicast router version * and do what the IGMP version 2 specified. * Chih-Jen Chang : Added a timer to revert to IGMP V2 router * Tsu-Sheng Tsao if the specified time expired. * Alan Cox : Stop IGMP from 0.0.0.0 being accepted. * Alan Cox : Use GFP_ATOMIC in the right places. * Christian Daudt : igmp timer wasn't set for local group * memberships but was being deleted, * which caused a "del_timer() called * from %p with timer not initialized\n" * message (960131). * Christian Daudt : removed del_timer from * igmp_timer_expire function (960205). * Christian Daudt : igmp_heard_report now only calls * igmp_timer_expire if tm->running is * true (960216). * Malcolm Beattie : ttl comparison wrong in igmp_rcv made * igmp_heard_query never trigger. Expiry * miscalculation fixed in igmp_heard_query * and random() made to return unsigned to * prevent negative expiry times. * Alexey Kuznetsov: Wrong group leaving behaviour, backport * fix from pending 2.1.x patches. * Alan Cox: Forget to enable FDDI support earlier. * Alexey Kuznetsov: Fixed leaving groups on device down. * Alexey Kuznetsov: Accordance to igmp-v2-06 draft. * David L Stevens: IGMPv3 support, with help from * Vinay Kulkarni */ #include <linux/module.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include "igmp_internal.h" #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> #include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/addrconf.h> #include <net/arp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/sock.h> #include <net/checksum.h> #include <net/inet_common.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> #endif #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ #define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) #define IGMP_INITIAL_REPORT_DELAY (1) /* IGMP_INITIAL_REPORT_DELAY is not from IGMP specs! * IGMP specs require to report membership immediately after * joining a group, but we delay the first report by a * small interval. It seems more natural and still does not * contradict to specs provided this delay is small enough. */ #define IGMP_V1_SEEN(in_dev) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ (IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) static int unsolicited_report_interval(struct in_device *in_dev) { int interval_ms, interval_jiffies; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV2_UNSOLICITED_REPORT_INTERVAL); else /* v3 */ interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV3_UNSOLICITED_REPORT_INTERVAL); interval_jiffies = msecs_to_jiffies(interval_ms); /* _timer functions can't handle a delay of 0 jiffies so ensure * we always return a positive value. */ if (interval_jiffies <= 0) interval_jiffies = 1; return interval_jiffies; } static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp); static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); #endif static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); static void ip_ma_put(struct ip_mc_list *im) { if (refcount_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); kfree_rcu(im, rcu); } } #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rcu_dereference(pmc->next_rcu)) #define for_each_pmc_rtnl(in_dev, pmc) \ for (pmc = rtnl_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { next = psf->sf_next; kfree(psf); psf = next; } } #ifdef CONFIG_IP_MULTICAST /* * Timer management */ static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (timer_delete(&im->timer)) refcount_dec(&im->refcnt); im->tm_running = 0; im->reporter = 0; im->unsolicit_count = 0; spin_unlock_bh(&im->lock); } /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { int tv = get_random_u32_below(max_delay); im->tm_running = 1; if (refcount_inc_not_zero(&im->refcnt)) { if (mod_timer(&im->timer, jiffies + tv + 2)) ip_ma_put(im); } } static void igmp_gq_start_timer(struct in_device *in_dev) { int tv = get_random_u32_below(in_dev->mr_maxdelay); unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && time_after_eq(exp, (in_dev->mr_gq_timer).expires)) return; in_dev->mr_gq_running = 1; if (!mod_timer(&in_dev->mr_gq_timer, exp)) in_dev_hold(in_dev); } static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { int tv = get_random_u32_below(delay); if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); } static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) { spin_lock_bh(&im->lock); im->unsolicit_count = 0; if (timer_delete(&im->timer)) { if ((long)(im->timer.expires-jiffies) < max_delay) { add_timer(&im->timer); im->tm_running = 1; spin_unlock_bh(&im->lock); return; } refcount_dec(&im->refcnt); } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); } /* * Send an IGMP report. */ #define IGMP_SIZE (sizeof(struct igmphdr)+sizeof(struct iphdr)+4) static int is_in(struct ip_mc_list *pmc, struct ip_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return 0; if (!(pmc->gsquery && !psf->sf_gsresp)) { if (pmc->sfmode == MCAST_INCLUDE) return 1; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == IGMPV3_MODE_IS_INCLUDE; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return 0; case IGMPV3_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return 0; return psf->sf_count[MCAST_INCLUDE] != 0; case IGMPV3_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return 0; if (pmc->sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return 0; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case IGMPV3_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return 0; return (pmc->sfmode == MCAST_INCLUDE) ^ sdeleted; case IGMPV3_BLOCK_OLD_SOURCES: if (pmc->sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return 0; } static int igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct ip_sf_list *psf; int scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } /* source address selection per RFC 3376 section 4.2.13 */ static __be32 igmpv3_get_srcaddr(struct net_device *dev, const struct flowi4 *fl4) { struct in_device *in_dev = __in_dev_get_rcu(dev); const struct in_ifaddr *ifa; if (!in_dev) return htonl(INADDR_ANY); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (fl4->saddr == ifa->ifa_local) return fl4->saddr; } return htonl(INADDR_ANY); } static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; struct rtable *rt; struct iphdr *pip; struct igmpv3_report *pig; struct net *net = dev_net(dev); struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int size; size = min(mtu, IP_MAX_MTU); while (1) { skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); if (skb) break; size >>= 1; if (size < 256) return NULL; } skb->priority = TC_PRIO_CONTROL; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) { kfree_skb(skb); return NULL; } skb_dst_set(skb, &rt->dst); skb->dev = dev; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); pip->version = 4; pip->ihl = (sizeof(struct iphdr)+4)>>2; pip->tos = 0xc0; pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); rcu_read_unlock(); pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; ((u8 *)&pip[1])[3] = 0; skb->transport_header = skb->network_header + sizeof(struct iphdr) + 4; skb_put(skb, sizeof(*pig)); pig = igmpv3_report_hdr(skb); pig->type = IGMPV3_HOST_MEMBERSHIP_REPORT; pig->resv1 = 0; pig->csum = 0; pig->resv2 = 0; pig->ngrec = 0; return skb; } static int igmpv3_sendpack(struct sk_buff *skb) { struct igmphdr *pig = igmp_hdr(skb); const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb); pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); return ip_local_out(skb_dst_dev_net(skb), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) { return sizeof(struct igmpv3_grec) + 4*igmp_scount(pmc, type, gdel, sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; if (!skb) { skb = igmpv3_newpack(dev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->multiaddr; pih = igmpv3_report_hdr(skb); pih->ngrec = htons(ntohs(pih->ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct net_device *dev = pmc->interface->dev; struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV4_MIN_MTU) return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || type == IGMPV3_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->tomb : &pmc->sources; if (!*psf_list) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pih && pih->ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); } } first = 1; psf_prev = NULL; for (psf = *psf_list; psf; psf = psf_next) { __be32 *psrc; psf_next = psf->sf_next; if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; continue; } /* Based on RFC3376 5.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->crcount)) && (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(__be32) + first*sizeof(struct igmpv3_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *psf_list = psf->sf_next; kfree(psf); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) return skb; if (pmc->crcount || isquery) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct igmpv3_grec)) { igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->gsquery = 0; /* clear query state on report */ return skb; } static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; struct net *net = dev_net(in_dev->dev); int type; if (!pmc) { rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } if (!skb) return 0; return igmpv3_sendpack(skb); } /* * remove zero-count source records from a source filter list */ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = *ppsf; psf; psf = psf_next) { psf_next = psf->sf_next; if (psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *ppsf = psf->sf_next; kfree(psf); } else psf_prev = psf; } } static void kfree_pmc(struct ip_mc_list *pmc) { ip_sf_list_clear_all(pmc->sources); ip_sf_list_clear_all(pmc->tomb); kfree(pmc); } static void igmpv3_send_cr(struct in_device *in_dev) { struct ip_mc_list *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc_next) { pmc_next = pmc->next; if (pmc->sfmode == MCAST_INCLUDE) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0); skb = add_grec(skb, pmc, dtype, 1, 1); } if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) { type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0); } pmc->crcount--; if (pmc->crcount == 0) { igmpv3_clear_zeros(&pmc->tomb); igmpv3_clear_zeros(&pmc->sources); } } if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { if (pmc_prev) pmc_prev->next = pmc_next; else in_dev->mc_tomb = pmc_next; in_dev_put(pmc->interface); kfree_pmc(pmc); } else pmc_prev = pmc; } spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_ALLOW_NEW_SOURCES; } else { type = IGMPV3_ALLOW_NEW_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1); /* deleted sources */ /* filter mode changes */ if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) type = IGMPV3_CHANGE_TO_EXCLUDE; else type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); pmc->crcount--; } spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); if (!skb) return; (void) igmpv3_sendpack(skb); } static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, int type) { struct sk_buff *skb; struct iphdr *iph; struct igmphdr *ih; struct rtable *rt; struct net_device *dev = in_dev->dev; struct net *net = dev_net(dev); __be32 group = pmc ? pmc->multiaddr : 0; struct flowi4 fl4; __be32 dst; int hlen, tlen; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) dst = IGMP_ALL_ROUTER; else dst = group; rt = ip_route_output_ports(net, &fl4, NULL, dst, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) return -1; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); if (!skb) { ip_rt_put(rt); return -1; } skb->priority = TC_PRIO_CONTROL; skb_dst_set(skb, &rt->dst); skb_reserve(skb, hlen); skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); iph->version = 4; iph->ihl = (sizeof(struct iphdr)+4)>>2; iph->tos = 0xc0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; ip_select_ident(net, skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; ih = skb_put(skb, sizeof(struct igmphdr)); ih->type = type; ih->code = 0; ih->csum = 0; ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); return ip_local_out(net, skb->sk, skb); } static void igmp_gq_timer_expire(struct timer_list *t) { struct in_device *in_dev = timer_container_of(in_dev, t, mr_gq_timer); in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); in_dev_put(in_dev); } static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = timer_container_of(in_dev, t, mr_ifc_timer); u32 mr_ifc_count; igmpv3_send_cr(in_dev); restart: mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count); if (mr_ifc_count) { if (cmpxchg(&in_dev->mr_ifc_count, mr_ifc_count, mr_ifc_count - 1) != mr_ifc_count) goto restart; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv)); igmp_ifc_start_timer(in_dev, 1); } static void igmp_timer_expire(struct timer_list *t) { struct ip_mc_list *im = timer_container_of(im, t, timer); struct in_device *in_dev = im->interface; spin_lock(&im->lock); im->tm_running = 0; if (im->unsolicit_count && --im->unsolicit_count) igmp_start_timer(im, unsolicited_report_interval(in_dev)); im->reporter = 1; spin_unlock(&im->lock); if (IGMP_V1_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); else if (IGMP_V2_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); else igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); ip_ma_put(im); } /* mark EXCLUDE-mode sources */ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (srcs[i] == psf->sf_inaddr) { scount++; break; } } } pmc->gsquery = 0; if (scount == nsrcs) /* all sources excluded */ return 0; return 1; } static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; if (pmc->sfmode == MCAST_EXCLUDE) return igmp_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) if (srcs[i] == psf->sf_inaddr) { psf->sf_gsresp = 1; scount++; break; } } if (!scount) { pmc->gsquery = 0; return 0; } pmc->gsquery = 1; return 1; } /* return true if packet was dropped */ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; struct net *net = dev_net(in_dev->dev); /* Timers are only set for non-local groups */ if (group == IGMP_ALL_HOSTS) return false; if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } rcu_read_unlock(); return false; } /* return true if packet was dropped */ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, int len) { struct igmphdr *ih = igmp_hdr(skb); struct igmpv3_query *ih3 = igmpv3_query_hdr(skb); struct ip_mc_list *im; __be32 group = ih->group; int max_delay; int mark = 0; struct net *net = dev_net(in_dev->dev); if (len == 8) { if (ih->code == 0) { /* Alas, old v1 router presents here. */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; } /* cancel the interface change timer */ WRITE_ONCE(in_dev->mr_ifc_count, 0); if (timer_delete(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ igmpv3_clear_delrec(in_dev); } else if (len < 12) { return true; /* ignore bogus packet; freed by caller */ } else if (IGMP_V1_SEEN(in_dev)) { /* This is a v3 query with v1 queriers present */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; group = 0; } else if (IGMP_V2_SEEN(in_dev)) { /* this is a v3 query with v2 queriers present; * Interpretation of the max_delay code is problematic here. * A real v2 host would use ih_code directly, while v3 has a * different encoding. We use the v3 encoding as more likely * to be intended in a v3 query. */ max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return true; ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) { if (!pskb_may_pull(skb, sizeof(struct igmpv3_query) + ntohs(ih3->nsrcs)*sizeof(__be32))) return true; ih3 = igmpv3_query_hdr(skb); } max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ in_dev->mr_maxdelay = max_delay; /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently * received value was zero, use the default or statically * configured value. */ in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; /* RFC3376, 8.3. Query Response Interval: * The number of seconds represented by the [Query Response * Interval] must be less than the [Query Interval]. */ if (in_dev->mr_qri >= in_dev->mr_qi) in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; if (!group) { /* general query */ if (ih3->nsrcs) return true; /* no sources allowed */ igmp_gq_start_timer(in_dev); return false; } /* mark sources to include, if group & source-specific */ mark = ih3->nsrcs != 0; } /* * - Start the timers in all of our membership records * that the query applies to for the interface on * which the query arrived excl. those that belong * to a "local" group (224.0.0.X) * - For timers already running check if they need to * be reset. * - Use the igmp->igmp_code field as the maximum * delay possible */ rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) continue; if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) im->gsquery = im->gsquery && mark; else im->gsquery = mark; changed = !im->gsquery || igmp_marksources(im, ntohs(ih3->nsrcs), ih3->srcs); spin_unlock_bh(&im->lock); if (changed) igmp_mod_timer(im, max_delay); } rcu_read_unlock(); return false; } /* called in rcu_read_lock() section */ int igmp_rcv(struct sk_buff *skb) { /* This basically follows the spec line by line -- see RFC1112 */ struct igmphdr *ih; struct net_device *dev = skb->dev; struct in_device *in_dev; int len = skb->len; bool dropped = true; if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(dev_net(dev), IPCB(skb)->iif); if (!dev) goto drop; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto drop; if (!pskb_may_pull(skb, sizeof(struct igmphdr))) goto drop; if (skb_checksum_simple_validate(skb)) goto drop; ih = igmp_hdr(skb); switch (ih->type) { case IGMP_HOST_MEMBERSHIP_QUERY: dropped = igmp_heard_query(in_dev, skb, len); break; case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ if (rt_is_output_route(skb_rtable(skb))) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST) dropped = igmp_heard_report(in_dev, ih->group); break; case IGMP_PIM: #ifdef CONFIG_IP_PIMSM_V1 return pim_rcv_v1(skb); #endif case IGMPV3_HOST_MEMBERSHIP_REPORT: case IGMP_DVMRP: case IGMP_TRACE: case IGMP_HOST_LEAVE_MESSAGE: case IGMP_MTRACE: case IGMP_MTRACE_RESP: break; default: break; } drop: if (dropped) kfree_skb(skb); else consume_skb(skb); return 0; } #endif /* * Add a filter to a device */ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; /* Checking for IFF_MULTICAST here is WRONG-WRONG-WRONG. We will get multicast token leakage, when IFF_MULTICAST is changed. This check should be done in ndo_set_rx_mode routine. Something sort of: if (dev->mc_list && dev->flags&IFF_MULTICAST) { do it; } --ANK */ if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } /* * Remove a filter from a device */ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } #ifdef CONFIG_IP_MULTICAST /* * deleted ip_mc_list manipulation */ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp) { struct ip_mc_list *pmc; struct net *net = dev_net(in_dev->dev); /* this is an "ip_mc_list" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc(sizeof(*pmc), gfp); if (!pmc) return; spin_lock_init(&pmc->lock); spin_lock_bh(&im->lock); pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; pmc->tomb = im->tomb; pmc->sources = im->sources; im->tomb = im->sources = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = pmc->crcount; } spin_unlock_bh(&im->lock); spin_lock_bh(&in_dev->mc_tomb_lock); pmc->next = in_dev->mc_tomb; in_dev->mc_tomb = pmc; spin_unlock_bh(&in_dev->mc_tomb_lock); } /* * restore ip_mc_list deleted records */ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc, *pmc_prev; struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); __be32 multiaddr = im->multiaddr; spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc->next) { if (pmc->multiaddr == multiaddr) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) pmc_prev->next = pmc->next; else in_dev->mc_tomb = pmc->next; } spin_unlock_bh(&in_dev->mc_tomb_lock); spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { swap(im->tomb, pmc->tomb); swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } in_dev_put(pmc->interface); kfree_pmc(pmc); } spin_unlock_bh(&im->lock); } /* * flush ip_mc_list deleted records */ static void igmpv3_clear_delrec(struct in_device *in_dev) { struct ip_mc_list *pmc, *nextpmc; spin_lock_bh(&in_dev->mc_tomb_lock); pmc = in_dev->mc_tomb; in_dev->mc_tomb = NULL; spin_unlock_bh(&in_dev->mc_tomb_lock); for (; pmc; pmc = nextpmc) { nextpmc = pmc->next; ip_mc_clear_src(pmc); in_dev_put(pmc->interface); kfree_pmc(pmc); } /* clear dead sources, too */ rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } rcu_read_unlock(); } #endif static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); int reporter; #endif if (im->loaded) { im->loaded = 0; ip_mc_filter_del(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; igmp_stop_timer(im); if (!in_dev->dead) { if (IGMP_V1_SEEN(in_dev)) return; if (IGMP_V2_SEEN(in_dev)) { if (reporter) igmp_send_report(in_dev, im, IGMP_HOST_LEAVE_MESSAGE); return; } /* IGMPv3 */ igmpv3_add_delrec(in_dev, im, gfp); igmp_ifc_event(in_dev); } #endif } static void igmp_group_dropped(struct ip_mc_list *im) { __igmp_group_dropped(im, GFP_KERNEL); } static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); #endif if (im->loaded == 0) { im->loaded = 1; ip_mc_filter_add(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) return; im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); spin_unlock_bh(&im->lock); return; } /* else, v3 */ /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should * not send filter-mode change record as the mode should be from * IN() to IN(A). */ if (im->sfmode == MCAST_EXCLUDE) im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_event(in_dev); #endif } /* * Multicast list managers */ static u32 ip_mc_hash(const struct ip_mc_list *im) { return hash_32((__force u32)im->multiaddr, MC_HASH_SZ_LOG); } static void ip_mc_hash_add(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash; u32 hash; mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; rcu_assign_pointer(mc_hash[hash], im); return; } /* do not use a hash table for small number of items */ if (in_dev->mc_count < 4) return; mc_hash = kzalloc(sizeof(struct ip_mc_list *) << MC_HASH_SZ_LOG, GFP_KERNEL); if (!mc_hash) return; for_each_pmc_rtnl(in_dev, im) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; RCU_INIT_POINTER(mc_hash[hash], im); } rcu_assign_pointer(in_dev->mc_hash, mc_hash); } static void ip_mc_hash_remove(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash = rtnl_dereference(in_dev->mc_hash); struct ip_mc_list *aux; if (!mc_hash) return; mc_hash += ip_mc_hash(im); while ((aux = rtnl_dereference(*mc_hash)) != im) mc_hash = &aux->next_hash; *mc_hash = im->next_hash; } int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev, const struct ip_mc_list *im, struct inet_fill_args *args) { struct ifa_cacheinfo ci; struct ifaddrmsg *ifm; struct nlmsghdr *nlh; nlh = nlmsg_put(skb, args->portid, args->seq, args->event, sizeof(struct ifaddrmsg), args->flags); if (!nlh) return -EMSGSIZE; ifm = nlmsg_data(nlh); ifm->ifa_family = AF_INET; ifm->ifa_prefixlen = 32; ifm->ifa_flags = IFA_F_PERMANENT; ifm->ifa_scope = RT_SCOPE_UNIVERSE; ifm->ifa_index = dev->ifindex; ci.cstamp = (READ_ONCE(im->mca_cstamp) - INITIAL_JIFFIES) * 100UL / HZ; ci.tstamp = ci.cstamp; ci.ifa_prefered = INFINITY_LIFE_TIME; ci.ifa_valid = INFINITY_LIFE_TIME; if (nla_put_in_addr(skb, IFA_MULTICAST, im->multiaddr) < 0 || nla_put(skb, IFA_CACHEINFO, sizeof(ci), &ci) < 0) { nlmsg_cancel(skb, nlh); return -EMSGSIZE; } nlmsg_end(skb, nlh); return 0; } static void inet_ifmcaddr_notify(struct net_device *dev, const struct ip_mc_list *im, int event) { struct inet_fill_args fillargs = { .event = event, }; struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOMEM; skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) + nla_total_size(sizeof(__be32)) + nla_total_size(sizeof(struct ifa_cacheinfo)), GFP_KERNEL); if (!skb) goto error; err = inet_fill_ifmcaddr(skb, dev, im, &fillargs); if (err < 0) { WARN_ON_ONCE(err == -EMSGSIZE); nlmsg_free(skb); goto error; } rtnl_notify(skb, net, 0, RTNLGRP_IPV4_MCADDR, NULL, GFP_KERNEL); return; error: rtnl_set_sk_err(net, RTNLGRP_IPV4_MCADDR, err); } /* * A socket has joined a multicast group on device dev. */ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode, gfp_t gfp) { struct ip_mc_list __rcu **mc_hash; struct ip_mc_list *im; ASSERT_RTNL(); mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)addr, MC_HASH_SZ_LOG); for (im = rtnl_dereference(mc_hash[hash]); im; im = rtnl_dereference(im->next_hash)) { if (im->multiaddr == addr) break; } } else { for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) break; } } if (im) { im->users++; ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0); goto out; } im = kzalloc(sizeof(*im), gfp); if (!im) goto out; im->users = 1; im->interface = in_dev; in_dev_hold(in_dev); im->multiaddr = addr; im->mca_cstamp = jiffies; im->mca_tstamp = im->mca_cstamp; /* initial mode is (EX, empty) */ im->sfmode = mode; im->sfcount[mode] = 1; refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST timer_setup(&im->timer, igmp_timer_expire, 0); #endif im->next_rcu = in_dev->mc_list; in_dev->mc_count++; rcu_assign_pointer(in_dev->mc_list, im); ip_mc_hash_add(in_dev, im); #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); inet_ifmcaddr_notify(in_dev->dev, im, RTM_NEWMULTICAST); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: return; } void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { ____ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE, gfp); } EXPORT_SYMBOL(__ip_mc_inc_group); void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { __ip_mc_inc_group(in_dev, addr, GFP_KERNEL); } EXPORT_SYMBOL(ip_mc_inc_group); static int ip_mc_check_iphdr(struct sk_buff *skb) { const struct iphdr *iph; unsigned int len; unsigned int offset = skb_network_offset(skb) + sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (iph->version != 4 || ip_hdrlen(skb) < sizeof(*iph)) return -EINVAL; offset += ip_hdrlen(skb) - sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) return -EINVAL; len = skb_network_offset(skb) + ntohs(iph->tot_len); if (skb->len < len || len < offset) return -EINVAL; skb_set_transport_header(skb, offset); return 0; } static int ip_mc_check_igmp_reportv3(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb); len += sizeof(struct igmpv3_report); return ip_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ip_mc_check_igmp_query(struct sk_buff *skb) { unsigned int transport_len = ip_transport_len(skb); unsigned int len; /* IGMPv{1,2}? */ if (transport_len != sizeof(struct igmphdr)) { /* or IGMPv3? */ if (transport_len < sizeof(struct igmpv3_query)) return -EINVAL; len = skb_transport_offset(skb) + sizeof(struct igmpv3_query); if (!ip_mc_may_pull(skb, len)) return -EINVAL; } /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer * all-systems destination addresses (224.0.0.1) for general queries */ if (!igmp_hdr(skb)->group && ip_hdr(skb)->daddr != htonl(INADDR_ALLHOSTS_GROUP)) return -EINVAL; return 0; } static int ip_mc_check_igmp_msg(struct sk_buff *skb) { switch (igmp_hdr(skb)->type) { case IGMP_HOST_LEAVE_MESSAGE: case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: return 0; case IGMPV3_HOST_MEMBERSHIP_REPORT: return ip_mc_check_igmp_reportv3(skb); case IGMP_HOST_MEMBERSHIP_QUERY: return ip_mc_check_igmp_query(skb); default: return -ENOMSG; } } static __sum16 ip_mc_validate_checksum(struct sk_buff *skb) { return skb_checksum_simple_validate(skb); } static int ip_mc_check_igmp_csum(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr); unsigned int transport_len = ip_transport_len(skb); struct sk_buff *skb_chk; if (!ip_mc_may_pull(skb, len)) return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ip_mc_validate_checksum); if (!skb_chk) return -EINVAL; if (skb_chk != skb) kfree_skb(skb_chk); return 0; } /** * ip_mc_check_igmp - checks whether this is a sane IGMP packet * @skb: the skb to validate * * Checks whether an IPv4 packet is a valid IGMP packet. If so sets * skb transport header accordingly and returns zero. * * -EINVAL: A broken packet was detected, i.e. it violates some internet * standard * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. * -ENOMEM: A memory allocation failure happened. * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ int ip_mc_check_igmp(struct sk_buff *skb) { int ret = ip_mc_check_iphdr(skb); if (ret < 0) return ret; if (ip_hdr(skb)->protocol != IPPROTO_IGMP) return -ENOMSG; ret = ip_mc_check_igmp_csum(skb); if (ret < 0) return ret; return ip_mc_check_igmp_msg(skb); } EXPORT_SYMBOL(ip_mc_check_igmp); /* * Resend IGMP JOIN report; used by netdev notifier. */ static void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches * must be notified immediately */ if (IGMP_V1_SEEN(in_dev)) type = IGMP_HOST_MEMBERSHIP_REPORT; else if (IGMP_V2_SEEN(in_dev)) type = IGMPV2_HOST_MEMBERSHIP_REPORT; else type = IGMPV3_HOST_MEMBERSHIP_REPORT; igmp_send_report(in_dev, im, type); } #endif } /* * A socket has left a multicast group on device dev */ void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { struct ip_mc_list *i; struct ip_mc_list __rcu **ip; ASSERT_RTNL(); for (ip = &in_dev->mc_list; (i = rtnl_dereference(*ip)) != NULL; ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; __igmp_group_dropped(i, gfp); inet_ifmcaddr_notify(in_dev->dev, i, RTM_DELMULTICAST); ip_mc_clear_src(i); if (!in_dev->dead) ip_rt_multicast_event(in_dev); ip_ma_put(i); return; } break; } } } EXPORT_SYMBOL(__ip_mc_dec_group); /* Device changing type */ void ip_mc_unmap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST WRITE_ONCE(in_dev->mr_ifc_count, 0); if (timer_delete(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; if (timer_delete(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); #endif ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); } #ifdef CONFIG_IP_MULTICAST static void ip_mc_reset(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); in_dev->mr_qi = IGMP_QUERY_INTERVAL; in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv); } #else static void ip_mc_reset(struct in_device *in_dev) { } #endif void ip_mc_init_dev(struct in_device *in_dev) { ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0); timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0); #endif ip_mc_reset(in_dev); spin_lock_init(&in_dev->mc_tomb_lock); } /* Device going up */ void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_reset(in_dev); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* * Device is about to be destroyed: clean up. */ void ip_mc_destroy_dev(struct in_device *in_dev) { struct ip_mc_list *i; ASSERT_RTNL(); /* Deactivate timers */ ip_mc_down(in_dev); #ifdef CONFIG_IP_MULTICAST igmpv3_clear_delrec(in_dev); #endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; ip_mc_clear_src(i); ip_ma_put(i); } } /* RTNL is locked */ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct net_device *dev = NULL; struct in_device *idev = NULL; if (imr->imr_ifindex) { idev = inetdev_by_index(net, imr->imr_ifindex); return idev; } if (imr->imr_address.s_addr) { dev = __ip_dev_find(net, imr->imr_address.s_addr, false); if (!dev) return NULL; } if (!dev) { struct rtable *rt = ip_route_output(net, imr->imr_multiaddr.s_addr, 0, 0, 0, RT_SCOPE_UNIVERSE); if (!IS_ERR(rt)) { dev = rt->dst.dev; ip_rt_put(rt); } } if (dev) { imr->imr_ifindex = dev->ifindex; idev = __in_dev_get_rtnl(dev); } return idev; } /* * Join a socket to a group */ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; int rv = 0; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } psf->sf_count[sfmode]--; if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct in_device *in_dev = pmc->interface; struct net *net = dev_net(in_dev->dev); #endif /* no more filters for this source */ if (psf_prev) psf_prev->sf_next = psf->sf_next; else pmc->sources = psf->sf_next; #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; } else #endif kfree(psf); } return rv; } #ifndef CONFIG_IP_MULTICAST #define igmp_ifc_event(x) do { } while (0) #endif static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int changerec = 0; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif if (!delta) { err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; pmc->sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->sfmode == MCAST_EXCLUDE && pmc->sfcount[MCAST_EXCLUDE] == 0 && pmc->sfcount[MCAST_INCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); #endif /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { igmp_ifc_event(pmc->interface); #endif } out_unlock: spin_unlock_bh(&pmc->lock); return err; } /* * Add multicast single-source filter to the interface list */ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf) { psf = kzalloc(sizeof(*psf), GFP_ATOMIC); if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; if (psf_prev) { psf_prev->sf_next = psf; } else pmc->sources = psf; } psf->sf_count[sfmode]++; if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } return 0; } #ifdef CONFIG_IP_MULTICAST static void sf_markstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; for (psf = pmc->sources; psf; psf = psf->sf_next) if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } static int sf_setstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf, *dpsf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; int qrv = pmc->interface->mr_qrv; int new_in, rv; rv = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { if (prev) prev->sf_next = dpsf->sf_next; else pmc->tomb = dpsf->sf_next; kfree(dpsf); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) if (dpsf->sf_inaddr == psf->sf_inaddr) break; if (!dpsf) { dpsf = kmalloc(sizeof(*dpsf), GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ dpsf->sf_next = pmc->tomb; pmc->tomb = dpsf; } dpsf->sf_crcount = qrv; rv++; } } return rv; } #endif /* * Add multicast source filter list to the interface list */ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int isexclude; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) pmc->sfcount[sfmode]++; err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) pmc->sfcount[sfmode]--; for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(pmc->interface->dev); in_dev = pmc->interface; #endif /* filter mode change */ if (pmc->sfcount[MCAST_EXCLUDE]) pmc->sfmode = MCAST_EXCLUDE; else if (pmc->sfcount[MCAST_INCLUDE]) pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { igmp_ifc_event(in_dev); #endif } spin_unlock_bh(&pmc->lock); return err; } static void ip_mc_clear_src(struct ip_mc_list *pmc) { struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); tomb = pmc->tomb; pmc->tomb = NULL; sources = pmc->sources; pmc->sources = NULL; pmc->sfmode = MCAST_EXCLUDE; pmc->sfcount[MCAST_INCLUDE] = 0; pmc->sfcount[MCAST_EXCLUDE] = 1; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); ip_sf_list_clear_all(sources); } /* Join a multicast group */ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int ifindex; int count = 0; int err; ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRINUSE; ifindex = imr->imr_ifindex; for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; count++; } err = -ENOBUFS; if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL); err = 0; done: return err; } /* Join ASM (Any-Source Multicast) group */ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) { return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ip_mc_join_group); /* Join SSM (Source-Specific Multicast) group */ int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { return __ip_mc_join_group(sk, imr, mode); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (!psf) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); } err = ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, psf->sl_count, psf->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psf, sl_addr, psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); return err; } int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; u32 ifindex; int ret = -EADDRNOTAVAIL; ASSERT_RTNL(); in_dev = ip_mc_find_dev(net, imr); if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) { ret = -ENODEV; goto out; } ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = rtnl_dereference(*imlp)) != NULL; imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { if (iml->multi.imr_ifindex != ifindex) continue; } else if (imr->imr_address.s_addr && imr->imr_address.s_addr != iml->multi.imr_address.s_addr) continue; (void) ip_mc_leave_src(sk, iml, in_dev); *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } out: return ret; } EXPORT_SYMBOL(ip_mc_leave_group); int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex) { int err; struct ip_mreqn imr; __be32 addr = mreqs->imr_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); int leavegroup = 0; int i, j, rv; if (!ipv4_is_multicast(addr)) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (pmc->sflist) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 0, NULL, 0); ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip_sf_socklist *newpsl; int count = IP_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv == 0) /* address already there is an error */ goto done; for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = mreqs->imr_sourceaddr; psl->sl_count++; err = 0; /* update the interface list */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) { int err = 0; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); int leavegroup = 0; if (!ipv4_is_multicast(addr)) return -EINVAL; if (msf->imsf_fmode != MCAST_INCLUDE && msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (msf->imsf_fmode == MCAST_INCLUDE && msf->imsf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (msf->imsf_numsrc) { newpsl = sock_kmalloc(sk, struct_size(newpsl, sl_addr, msf->imsf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = msf->imsf_numsrc; memcpy(newpsl->sl_addr, msf->imsf_slist_flex, flex_array_size(msf, imsf_slist_flex, msf->imsf_numsrc)); err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { sock_kfree_s(sk, newpsl, struct_size(newpsl, sl_addr, newpsl->sl_max)); goto done; } } else { newpsl = NULL; (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ atomic_sub(struct_size(psl, sl_addr, psl->sl_max), &sk->sk_omem_alloc); } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, sockptr_t optval, sockptr_t optlen) { int err, len, count, copycount, msf_size; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = 0; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); if (!psl) { count = 0; } else { count = psl->sl_count; } copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc; len = flex_array_size(psl, sl_addr, copycount); msf->imsf_numsrc = count; msf_size = IP_MSFILTER_SIZE(copycount); if (copy_to_sockptr(optlen, &msf_size, sizeof(int)) || copy_to_sockptr(optval, msf, IP_MSFILTER_SIZE(0))) { return -EFAULT; } if (len && copy_to_sockptr_offset(optval, offsetof(struct ip_msfilter, imsf_slist_flex), psl->sl_addr, len)) return -EFAULT; return 0; done: return err; } int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, sockptr_t optval, size_t ss_offset) { int i, count, copycount; struct sockaddr_in *psin; __be32 addr; struct ip_mc_socklist *pmc; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; ASSERT_RTNL(); psin = (struct sockaddr_in *)&gsf->gf_group; if (psin->sin_family != AF_INET) return -EINVAL; addr = psin->sin_addr.s_addr; if (!ipv4_is_multicast(addr)) return -EINVAL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; } if (!pmc) /* must have a prior join */ return -EADDRNOTAVAIL; gsf->gf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; for (i = 0; i < copycount; i++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; memset(&ss, 0, sizeof(ss)); psin->sin_family = AF_INET; psin->sin_addr.s_addr = psl->sl_addr[i]; if (copy_to_sockptr_offset(optval, ss_offset, &ss, sizeof(ss))) return -EFAULT; ss_offset += sizeof(ss); } return 0; } /* * check if a multicast source filter allows delivery for a given <src,dst,intf> */ int ip_mc_sf_allow(const struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif, int sdif) { const struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *pmc; struct ip_sf_socklist *psl; int i; int ret; ret = 1; if (!ipv4_is_multicast(loc_addr)) goto out; rcu_read_lock(); for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && (pmc->multi.imr_ifindex == dif || (sdif && pmc->multi.imr_ifindex == sdif))) break; } ret = inet_test_bit(MC_ALL, sk); if (!pmc) goto unlock; psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; for (i = 0; i < psl->sl_count; i++) { if (psl->sl_addr[i] == rmt_addr) break; } ret = 0; if (pmc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) goto unlock; if (pmc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) goto unlock; ret = 1; unlock: rcu_read_unlock(); out: return ret; } /* * A socket is closing. */ void ip_mc_drop_socket(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct net *net = sock_net(sk); if (!inet->mc_list) return; rtnl_lock(); while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); } rtnl_unlock(); } /* called with rcu_read_lock() */ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u8 proto) { struct ip_mc_list *im; struct ip_mc_list __rcu **mc_hash; struct ip_sf_list *psf; int rv = 0; mc_hash = rcu_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)mc_addr, MC_HASH_SZ_LOG); for (im = rcu_dereference(mc_hash[hash]); im != NULL; im = rcu_dereference(im->next_hash)) { if (im->multiaddr == mc_addr) break; } } else { for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } } if (im && proto == IPPROTO_IGMP) { rv = 1; } else if (im) { if (src_addr) { spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; } if (psf) rv = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } return rv; } #if defined(CONFIG_PROC_FS) struct igmp_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *in_dev; }; #define igmp_mc_seq_private(seq) ((struct igmp_mc_iter_state *)(seq)->private) static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_mc_list *im = NULL; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } } return im; } static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); im = rcu_dereference(im->next_rcu); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; break; } state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; im = rcu_dereference(state->in_dev->mc_list); } return im; } static struct ip_mc_list *igmp_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ip_mc_list *im = igmp_mc_get_first(seq); if (im) while (pos && (im = igmp_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mc_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_mc_list *im; if (v == SEQ_START_TOKEN) im = igmp_mc_get_first(seq); else im = igmp_mc_get_next(seq, v); ++*pos; return im; } static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mc_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Idx\tDevice : Count Querier\tGroup Users Timer\tReporter\n"); else { struct ip_mc_list *im = v; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); char *querier; long delta; #ifdef CONFIG_IP_MULTICAST querier = IGMP_V1_SEEN(state->in_dev) ? "V1" : IGMP_V2_SEEN(state->in_dev) ? "V2" : "V3"; #else querier = "NONE"; #endif if (rcu_access_pointer(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } delta = im->timer.expires - jiffies; seq_printf(seq, "\t\t\t\t%08X %5d %d:%08lX\t\t%d\n", im->multiaddr, im->users, im->tm_running, im->tm_running ? jiffies_delta_to_clock_t(delta) : 0, im->reporter); } return 0; } static const struct seq_operations igmp_mc_seq_ops = { .start = igmp_mc_seq_start, .next = igmp_mc_seq_next, .stop = igmp_mc_seq_stop, .show = igmp_mc_seq_show, }; struct igmp_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *idev; struct ip_mc_list *im; }; #define igmp_mcf_seq_private(seq) ((struct igmp_mcf_iter_state *)(seq)->private) static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_sf_list *psf = NULL; struct ip_mc_list *im = NULL; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *idev; idev = __in_dev_get_rcu(state->dev); if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); psf = im->sources; if (likely(psf)) { state->im = im; state->idev = idev; break; } spin_unlock_bh(&im->lock); } } return psf; } static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_list *psf) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); psf = psf->sf_next; while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } spin_lock_bh(&state->im->lock); psf = state->im->sources; } out: return psf; } static struct ip_sf_list *igmp_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip_sf_list *psf = igmp_mcf_get_first(seq); if (psf) while (pos && (psf = igmp_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp_mcf_get_first(seq); else psf = igmp_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (likely(state->im)) { spin_unlock_bh(&state->im->lock); state->im = NULL; } state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mcf_seq_show(struct seq_file *seq, void *v) { struct ip_sf_list *psf = v; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device MCA SRC INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s 0x%08x " "0x%08x %6lu %6lu\n", state->dev->ifindex, state->dev->name, ntohl(state->im->multiaddr), ntohl(psf->sf_inaddr), psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } static const struct seq_operations igmp_mcf_seq_ops = { .start = igmp_mcf_seq_start, .next = igmp_mcf_seq_next, .stop = igmp_mcf_seq_stop, .show = igmp_mcf_seq_show, }; static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; int err; pde = proc_create_net("igmp", 0444, net->proc_net, &igmp_mc_seq_ops, sizeof(struct igmp_mc_iter_state)); if (!pde) goto out_igmp; pde = proc_create_net("mcfilter", 0444, net->proc_net, &igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state)); if (!pde) goto out_mcfilter; err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET, SOCK_DGRAM, 0, net); if (err < 0) { pr_err("Failed to initialize the IGMP autojoin socket (err %d)\n", err); goto out_sock; } return 0; out_sock: remove_proc_entry("mcfilter", net->proc_net); out_mcfilter: remove_proc_entry("igmp", net->proc_net); out_igmp: return -ENOMEM; } static void __net_exit igmp_net_exit(struct net *net) { remove_proc_entry("mcfilter", net->proc_net); remove_proc_entry("igmp", net->proc_net); inet_ctl_sock_destroy(net->ipv4.mc_autojoin_sk); } static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, }; #endif static int igmp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev; switch (event) { case NETDEV_RESEND_IGMP: in_dev = __in_dev_get_rtnl(dev); if (in_dev) ip_mc_rejoin_groups(in_dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp_notifier = { .notifier_call = igmp_netdev_event, }; int __init igmp_mc_init(void) { #if defined(CONFIG_PROC_FS) int err; err = register_pernet_subsys(&igmp_net_ops); if (err) return err; err = register_netdevice_notifier(&igmp_notifier); if (err) goto reg_notif_fail; return 0; reg_notif_fail: unregister_pernet_subsys(&igmp_net_ops); return err; #else return register_netdevice_notifier(&igmp_notifier); #endif } |
| 19 26 10 21 32 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * NILFS block mapping. * * Copyright (C) 2006-2008 Nippon Telegraph and Telephone Corporation. * * Written by Koji Sato. */ #ifndef _NILFS_BMAP_H #define _NILFS_BMAP_H #include <linux/types.h> #include <linux/fs.h> #include <linux/buffer_head.h> #include <linux/nilfs2_ondisk.h> /* nilfs_binfo, nilfs_inode, etc */ #include "alloc.h" #include "dat.h" #define NILFS_BMAP_INVALID_PTR 0 #define nilfs_bmap_keydiff_abs(diff) ((diff) < 0 ? -(diff) : (diff)) struct nilfs_bmap; /** * union nilfs_bmap_ptr_req - request for bmap ptr * @bpr_ptr: bmap pointer * @bpr_req: request for persistent allocator */ union nilfs_bmap_ptr_req { __u64 bpr_ptr; struct nilfs_palloc_req bpr_req; }; /** * struct nilfs_bmap_stats - bmap statistics * @bs_nblocks: number of blocks created or deleted */ struct nilfs_bmap_stats { unsigned int bs_nblocks; }; /** * struct nilfs_bmap_operations - bmap operation table * @bop_lookup: single block search operation * @bop_lookup_contig: consecutive block search operation * @bop_insert: block insertion operation * @bop_delete: block delete operation * @bop_clear: block mapping resource release operation * @bop_propagate: operation to propagate dirty state towards the * mapping root * @bop_lookup_dirty_buffers: operation to collect dirty block buffers * @bop_assign: disk block address assignment operation * @bop_mark: operation to mark in-use blocks as dirty for * relocation by GC * @bop_seek_key: find valid block key operation * @bop_last_key: find last valid block key operation */ struct nilfs_bmap_operations { int (*bop_lookup)(const struct nilfs_bmap *, __u64, int, __u64 *); int (*bop_lookup_contig)(const struct nilfs_bmap *, __u64, __u64 *, unsigned int); int (*bop_insert)(struct nilfs_bmap *, __u64, __u64); int (*bop_delete)(struct nilfs_bmap *, __u64); void (*bop_clear)(struct nilfs_bmap *); int (*bop_propagate)(struct nilfs_bmap *, struct buffer_head *); void (*bop_lookup_dirty_buffers)(struct nilfs_bmap *, struct list_head *); int (*bop_assign)(struct nilfs_bmap *, struct buffer_head **, sector_t, union nilfs_binfo *); int (*bop_mark)(struct nilfs_bmap *, __u64, int); int (*bop_seek_key)(const struct nilfs_bmap *, __u64, __u64 *); int (*bop_last_key)(const struct nilfs_bmap *, __u64 *); /* private: internal use only */ int (*bop_check_insert)(const struct nilfs_bmap *, __u64); int (*bop_check_delete)(struct nilfs_bmap *, __u64); int (*bop_gather_data)(struct nilfs_bmap *, __u64 *, __u64 *, int); }; #define NILFS_BMAP_SIZE (NILFS_INODE_BMAP_SIZE * sizeof(__le64)) #define NILFS_BMAP_KEY_BIT BITS_PER_LONG #define NILFS_BMAP_NEW_PTR_INIT (1UL << (BITS_PER_LONG - 1)) static inline int nilfs_bmap_is_new_ptr(unsigned long ptr) { return !!(ptr & NILFS_BMAP_NEW_PTR_INIT); } /** * struct nilfs_bmap - bmap structure * @b_u: raw data * @b_sem: semaphore * @b_inode: owner of bmap * @b_ops: bmap operation table * @b_last_allocated_key: last allocated key for data block * @b_last_allocated_ptr: last allocated ptr for data block * @b_ptr_type: pointer type * @b_state: state * @b_nchildren_per_block: maximum number of child nodes for non-root nodes */ struct nilfs_bmap { union { __u8 u_flags; __le64 u_data[NILFS_BMAP_SIZE / sizeof(__le64)]; } b_u; struct rw_semaphore b_sem; struct inode *b_inode; const struct nilfs_bmap_operations *b_ops; __u64 b_last_allocated_key; __u64 b_last_allocated_ptr; int b_ptr_type; int b_state; __u16 b_nchildren_per_block; }; /* pointer type */ #define NILFS_BMAP_PTR_P 0 /* physical block number (i.e. LBN) */ #define NILFS_BMAP_PTR_VS 1 /* * virtual block number (single * version) */ #define NILFS_BMAP_PTR_VM 2 /* * virtual block number (has multiple * versions) */ #define NILFS_BMAP_PTR_U (-1) /* never perform pointer operations */ #define NILFS_BMAP_USE_VBN(bmap) ((bmap)->b_ptr_type > 0) /* state */ #define NILFS_BMAP_DIRTY 0x00000001 /** * struct nilfs_bmap_store - shadow copy of bmap state * @data: cached raw block mapping of on-disk inode * @last_allocated_key: cached value of last allocated key for data block * @last_allocated_ptr: cached value of last allocated ptr for data block * @state: cached value of state field of bmap structure */ struct nilfs_bmap_store { __le64 data[NILFS_BMAP_SIZE / sizeof(__le64)]; __u64 last_allocated_key; __u64 last_allocated_ptr; int state; }; int nilfs_bmap_test_and_clear_dirty(struct nilfs_bmap *); int nilfs_bmap_read(struct nilfs_bmap *, struct nilfs_inode *); void nilfs_bmap_write(struct nilfs_bmap *, struct nilfs_inode *); int nilfs_bmap_lookup_contig(struct nilfs_bmap *, __u64, __u64 *, unsigned int); int nilfs_bmap_insert(struct nilfs_bmap *bmap, __u64 key, unsigned long rec); int nilfs_bmap_delete(struct nilfs_bmap *bmap, __u64 key); int nilfs_bmap_seek_key(struct nilfs_bmap *bmap, __u64 start, __u64 *keyp); int nilfs_bmap_last_key(struct nilfs_bmap *bmap, __u64 *keyp); int nilfs_bmap_truncate(struct nilfs_bmap *bmap, __u64 key); void nilfs_bmap_clear(struct nilfs_bmap *); int nilfs_bmap_propagate(struct nilfs_bmap *, struct buffer_head *); void nilfs_bmap_lookup_dirty_buffers(struct nilfs_bmap *, struct list_head *); int nilfs_bmap_assign(struct nilfs_bmap *, struct buffer_head **, unsigned long, union nilfs_binfo *); int nilfs_bmap_lookup_at_level(struct nilfs_bmap *, __u64, int, __u64 *); int nilfs_bmap_mark(struct nilfs_bmap *, __u64, int); void nilfs_bmap_init_gc(struct nilfs_bmap *); void nilfs_bmap_save(const struct nilfs_bmap *, struct nilfs_bmap_store *); void nilfs_bmap_restore(struct nilfs_bmap *, const struct nilfs_bmap_store *); static inline int nilfs_bmap_lookup(struct nilfs_bmap *bmap, __u64 key, __u64 *ptr) { return nilfs_bmap_lookup_at_level(bmap, key, 1, ptr); } /* * Internal use only */ struct inode *nilfs_bmap_get_dat(const struct nilfs_bmap *); static inline int nilfs_bmap_prepare_alloc_ptr(struct nilfs_bmap *bmap, union nilfs_bmap_ptr_req *req, struct inode *dat) { if (dat) return nilfs_dat_prepare_alloc(dat, &req->bpr_req); /* ignore target ptr */ req->bpr_ptr = bmap->b_last_allocated_ptr++; return 0; } static inline void nilfs_bmap_commit_alloc_ptr(struct nilfs_bmap *bmap, union nilfs_bmap_ptr_req *req, struct inode *dat) { if (dat) nilfs_dat_commit_alloc(dat, &req->bpr_req); } static inline void nilfs_bmap_abort_alloc_ptr(struct nilfs_bmap *bmap, union nilfs_bmap_ptr_req *req, struct inode *dat) { if (dat) nilfs_dat_abort_alloc(dat, &req->bpr_req); else bmap->b_last_allocated_ptr--; } static inline int nilfs_bmap_prepare_end_ptr(struct nilfs_bmap *bmap, union nilfs_bmap_ptr_req *req, struct inode *dat) { return dat ? nilfs_dat_prepare_end(dat, &req->bpr_req) : 0; } static inline void nilfs_bmap_commit_end_ptr(struct nilfs_bmap *bmap, union nilfs_bmap_ptr_req *req, struct inode *dat) { if (dat) nilfs_dat_commit_end(dat, &req->bpr_req, bmap->b_ptr_type == NILFS_BMAP_PTR_VS); } static inline void nilfs_bmap_abort_end_ptr(struct nilfs_bmap *bmap, union nilfs_bmap_ptr_req *req, struct inode *dat) { if (dat) nilfs_dat_abort_end(dat, &req->bpr_req); } static inline void nilfs_bmap_set_target_v(struct nilfs_bmap *bmap, __u64 key, __u64 ptr) { bmap->b_last_allocated_key = key; bmap->b_last_allocated_ptr = ptr; } __u64 nilfs_bmap_data_get_key(const struct nilfs_bmap *, const struct buffer_head *); __u64 nilfs_bmap_find_target_seq(const struct nilfs_bmap *, __u64); __u64 nilfs_bmap_find_target_in_group(const struct nilfs_bmap *); /* Assume that bmap semaphore is locked. */ static inline int nilfs_bmap_dirty(const struct nilfs_bmap *bmap) { return !!(bmap->b_state & NILFS_BMAP_DIRTY); } /* Assume that bmap semaphore is locked. */ static inline void nilfs_bmap_set_dirty(struct nilfs_bmap *bmap) { bmap->b_state |= NILFS_BMAP_DIRTY; } /* Assume that bmap semaphore is locked. */ static inline void nilfs_bmap_clear_dirty(struct nilfs_bmap *bmap) { bmap->b_state &= ~NILFS_BMAP_DIRTY; } #define NILFS_BMAP_LARGE 0x1 #define NILFS_BMAP_SMALL_LOW NILFS_DIRECT_KEY_MIN #define NILFS_BMAP_SMALL_HIGH NILFS_DIRECT_KEY_MAX #define NILFS_BMAP_LARGE_LOW NILFS_BTREE_ROOT_NCHILDREN_MAX #define NILFS_BMAP_LARGE_HIGH NILFS_BTREE_KEY_MAX #endif /* _NILFS_BMAP_H */ |
| 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_TTY_DRIVER_H #define _LINUX_TTY_DRIVER_H #include <linux/export.h> #include <linux/fs.h> #include <linux/kref.h> #include <linux/list.h> #include <linux/cdev.h> #include <linux/uaccess.h> #include <linux/termios.h> #include <linux/seq_file.h> struct tty_struct; struct tty_driver; struct serial_icounter_struct; struct serial_struct; /** * enum tty_driver_flag -- TTY Driver Flags * * These are flags passed to tty_alloc_driver(). * * @TTY_DRIVER_INSTALLED: * Whether this driver was succesfully installed. This is a tty internal * flag. Do not touch. * * @TTY_DRIVER_RESET_TERMIOS: * Requests the tty layer to reset the termios setting when the last * process has closed the device. Used for PTYs, in particular. * * @TTY_DRIVER_REAL_RAW: * Indicates that the driver will guarantee not to set any special * character handling flags if this is set for the tty: * * ``(IGNBRK || (!BRKINT && !PARMRK)) && (IGNPAR || !INPCK)`` * * That is, if there is no reason for the driver to * send notifications of parity and break characters up to the line * driver, it won't do so. This allows the line driver to optimize for * this case if this flag is set. (Note that there is also a promise, if * the above case is true, not to signal overruns, either.) * * @TTY_DRIVER_DYNAMIC_DEV: * The individual tty devices need to be registered with a call to * tty_register_device() when the device is found in the system and * unregistered with a call to tty_unregister_device() so the devices will * be show up properly in sysfs. If not set, all &tty_driver.num entries * will be created by the tty core in sysfs when tty_register_driver() is * called. This is to be used by drivers that have tty devices that can * appear and disappear while the main tty driver is registered with the * tty core. * * @TTY_DRIVER_DEVPTS_MEM: * Don't use the standard arrays (&tty_driver.ttys and * &tty_driver.termios), instead use dynamic memory keyed through the * devpts filesystem. This is only applicable to the PTY driver. * * @TTY_DRIVER_HARDWARE_BREAK: * Hardware handles break signals. Pass the requested timeout to the * &tty_operations.break_ctl instead of using a simple on/off interface. * * @TTY_DRIVER_DYNAMIC_ALLOC: * Do not allocate structures which are needed per line for this driver * (&tty_driver.ports) as it would waste memory. The driver will take * care. This is only applicable to the PTY driver. * * @TTY_DRIVER_UNNUMBERED_NODE: * Do not create numbered ``/dev`` nodes. For example, create * ``/dev/ttyprintk`` and not ``/dev/ttyprintk0``. Applicable only when a * driver for a single tty device is being allocated. */ enum tty_driver_flag { TTY_DRIVER_INSTALLED = BIT(0), TTY_DRIVER_RESET_TERMIOS = BIT(1), TTY_DRIVER_REAL_RAW = BIT(2), TTY_DRIVER_DYNAMIC_DEV = BIT(3), TTY_DRIVER_DEVPTS_MEM = BIT(4), TTY_DRIVER_HARDWARE_BREAK = BIT(5), TTY_DRIVER_DYNAMIC_ALLOC = BIT(6), TTY_DRIVER_UNNUMBERED_NODE = BIT(7), }; enum tty_driver_type { TTY_DRIVER_TYPE_SYSTEM, TTY_DRIVER_TYPE_CONSOLE, TTY_DRIVER_TYPE_SERIAL, TTY_DRIVER_TYPE_PTY, TTY_DRIVER_TYPE_SCC, TTY_DRIVER_TYPE_SYSCONS, }; enum tty_driver_subtype { SYSTEM_TYPE_TTY = 1, SYSTEM_TYPE_CONSOLE, SYSTEM_TYPE_SYSCONS, SYSTEM_TYPE_SYSPTMX, PTY_TYPE_MASTER = 1, PTY_TYPE_SLAVE, SERIAL_TYPE_NORMAL = 1, }; /** * struct tty_operations -- interface between driver and tty * * @lookup: ``struct tty_struct *()(struct tty_driver *self, struct file *, * int idx)`` * * Return the tty device corresponding to @idx, %NULL if there is not * one currently in use and an %ERR_PTR value on error. Called under * %tty_mutex (for now!) * * Optional method. Default behaviour is to use the @self->ttys array. * * @install: ``int ()(struct tty_driver *self, struct tty_struct *tty)`` * * Install a new @tty into the @self's internal tables. Used in * conjunction with @lookup and @remove methods. * * Optional method. Default behaviour is to use the @self->ttys array. * * @remove: ``void ()(struct tty_driver *self, struct tty_struct *tty)`` * * Remove a closed @tty from the @self's internal tables. Used in * conjunction with @lookup and @remove methods. * * Optional method. Default behaviour is to use the @self->ttys array. * * @open: ``int ()(struct tty_struct *tty, struct file *)`` * * This routine is called when a particular @tty device is opened. This * routine is mandatory; if this routine is not filled in, the attempted * open will fail with %ENODEV. * * Required method. Called with tty lock held. May sleep. * * @close: ``void ()(struct tty_struct *tty, struct file *)`` * * This routine is called when a particular @tty device is closed. At the * point of return from this call the driver must make no further ldisc * calls of any kind. * * Remark: called even if the corresponding @open() failed. * * Required method. Called with tty lock held. May sleep. * * @shutdown: ``void ()(struct tty_struct *tty)`` * * This routine is called under the tty lock when a particular @tty device * is closed for the last time. It executes before the @tty resources * are freed so may execute while another function holds a @tty kref. * * @cleanup: ``void ()(struct tty_struct *tty)`` * * This routine is called asynchronously when a particular @tty device * is closed for the last time freeing up the resources. This is * actually the second part of shutdown for routines that might sleep. * * @write: ``ssize_t ()(struct tty_struct *tty, const u8 *buf, size_t count)`` * * This routine is called by the kernel to write a series (@count) of * characters (@buf) to the @tty device. The characters may come from * user space or kernel space. This routine will return the * number of characters actually accepted for writing. * * May occur in parallel in special cases. Because this includes panic * paths drivers generally shouldn't try and do clever locking here. * * Optional: Required for writable devices. May not sleep. * * @put_char: ``int ()(struct tty_struct *tty, u8 ch)`` * * This routine is called by the kernel to write a single character @ch to * the @tty device. If the kernel uses this routine, it must call the * @flush_chars() routine (if defined) when it is done stuffing characters * into the driver. If there is no room in the queue, the character is * ignored. * * Optional: Kernel will use the @write method if not provided. Do not * call this function directly, call tty_put_char(). * * @flush_chars: ``void ()(struct tty_struct *tty)`` * * This routine is called by the kernel after it has written a * series of characters to the tty device using @put_char(). * * Optional. Do not call this function directly, call * tty_driver_flush_chars(). * * @write_room: ``unsigned int ()(struct tty_struct *tty)`` * * This routine returns the numbers of characters the @tty driver * will accept for queuing to be written. This number is subject * to change as output buffers get emptied, or if the output flow * control is acted. * * The ldisc is responsible for being intelligent about multi-threading of * write_room/write calls * * Required if @write method is provided else not needed. Do not call this * function directly, call tty_write_room() * * @chars_in_buffer: ``unsigned int ()(struct tty_struct *tty)`` * * This routine returns the number of characters in the device private * output queue. Used in tty_wait_until_sent() and for poll() * implementation. * * Optional: if not provided, it is assumed there is no queue on the * device. Do not call this function directly, call tty_chars_in_buffer(). * * @ioctl: ``int ()(struct tty_struct *tty, unsigned int cmd, * unsigned long arg)`` * * This routine allows the @tty driver to implement device-specific * ioctls. If the ioctl number passed in @cmd is not recognized by the * driver, it should return %ENOIOCTLCMD. * * Optional. * * @compat_ioctl: ``long ()(struct tty_struct *tty, unsigned int cmd, * unsigned long arg)`` * * Implement ioctl processing for 32 bit process on 64 bit system. * * Optional. * * @set_termios: ``void ()(struct tty_struct *tty, const struct ktermios *old)`` * * This routine allows the @tty driver to be notified when device's * termios settings have changed. New settings are in @tty->termios. * Previous settings are passed in the @old argument. * * The API is defined such that the driver should return the actual modes * selected. This means that the driver is responsible for modifying any * bits in @tty->termios it cannot fulfill to indicate the actual modes * being used. * * Optional. Called under the @tty->termios_rwsem. May sleep. * * @ldisc_ok: ``int ()(struct tty_struct *tty, int ldisc)`` * * This routine allows the @tty driver to decide if it can deal * with a particular @ldisc. * * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. * * @set_ldisc: ``void ()(struct tty_struct *tty)`` * * This routine allows the @tty driver to be notified when the device's * line discipline is being changed. At the point this is done the * discipline is not yet usable. * * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. * * @throttle: ``void ()(struct tty_struct *tty)`` * * This routine notifies the @tty driver that input buffers for the line * discipline are close to full, and it should somehow signal that no more * characters should be sent to the @tty. * * Serialization including with @unthrottle() is the job of the ldisc * layer. * * Optional: Always invoke via tty_throttle_safe(). Called under the * @tty->termios_rwsem. * * @unthrottle: ``void ()(struct tty_struct *tty)`` * * This routine notifies the @tty driver that it should signal that * characters can now be sent to the @tty without fear of overrunning the * input buffers of the line disciplines. * * Optional. Always invoke via tty_unthrottle(). Called under the * @tty->termios_rwsem. * * @stop: ``void ()(struct tty_struct *tty)`` * * This routine notifies the @tty driver that it should stop outputting * characters to the tty device. * * Called with @tty->flow.lock held. Serialized with @start() method. * * Optional. Always invoke via stop_tty(). * * @start: ``void ()(struct tty_struct *tty)`` * * This routine notifies the @tty driver that it resumed sending * characters to the @tty device. * * Called with @tty->flow.lock held. Serialized with stop() method. * * Optional. Always invoke via start_tty(). * * @hangup: ``void ()(struct tty_struct *tty)`` * * This routine notifies the @tty driver that it should hang up the @tty * device. * * Optional. Called with tty lock held. * * @break_ctl: ``int ()(struct tty_struct *tty, int state)`` * * This optional routine requests the @tty driver to turn on or off BREAK * status on the RS-232 port. If @state is -1, then the BREAK status * should be turned on; if @state is 0, then BREAK should be turned off. * * If this routine is implemented, the high-level tty driver will handle * the following ioctls: %TCSBRK, %TCSBRKP, %TIOCSBRK, %TIOCCBRK. * * If the driver sets %TTY_DRIVER_HARDWARE_BREAK in tty_alloc_driver(), * then the interface will also be called with actual times and the * hardware is expected to do the delay work itself. 0 and -1 are still * used for on/off. * * Optional: Required for %TCSBRK/%BRKP/etc. handling. May sleep. * * @flush_buffer: ``void ()(struct tty_struct *tty)`` * * This routine discards device private output buffer. Invoked on close, * hangup, to implement %TCOFLUSH ioctl and similar. * * Optional: if not provided, it is assumed there is no queue on the * device. Do not call this function directly, call * tty_driver_flush_buffer(). * * @wait_until_sent: ``void ()(struct tty_struct *tty, int timeout)`` * * This routine waits until the device has written out all of the * characters in its transmitter FIFO. Or until @timeout (in jiffies) is * reached. * * Optional: If not provided, the device is assumed to have no FIFO. * Usually correct to invoke via tty_wait_until_sent(). May sleep. * * @send_xchar: ``void ()(struct tty_struct *tty, u8 ch)`` * * This routine is used to send a high-priority XON/XOFF character (@ch) * to the @tty device. * * Optional: If not provided, then the @write method is called under * the @tty->atomic_write_lock to keep it serialized with the ldisc. * * @tiocmget: ``int ()(struct tty_struct *tty)`` * * This routine is used to obtain the modem status bits from the @tty * driver. * * Optional: If not provided, then %ENOTTY is returned from the %TIOCMGET * ioctl. Do not call this function directly, call tty_tiocmget(). * * @tiocmset: ``int ()(struct tty_struct *tty, * unsigned int set, unsigned int clear)`` * * This routine is used to set the modem status bits to the @tty driver. * First, @clear bits should be cleared, then @set bits set. * * Optional: If not provided, then %ENOTTY is returned from the %TIOCMSET * ioctl. Do not call this function directly, call tty_tiocmset(). * * @resize: ``int ()(struct tty_struct *tty, struct winsize *ws)`` * * Called when a termios request is issued which changes the requested * terminal geometry to @ws. * * Optional: the default action is to update the termios structure * without error. This is usually the correct behaviour. Drivers should * not force errors here if they are not resizable objects (e.g. a serial * line). See tty_do_resize() if you need to wrap the standard method * in your own logic -- the usual case. * * @get_icount: ``int ()(struct tty_struct *tty, * struct serial_icounter *icount)`` * * Called when the @tty device receives a %TIOCGICOUNT ioctl. Passed a * kernel structure @icount to complete. * * Optional: called only if provided, otherwise %ENOTTY will be returned. * * @get_serial: ``int ()(struct tty_struct *tty, struct serial_struct *p)`` * * Called when the @tty device receives a %TIOCGSERIAL ioctl. Passed a * kernel structure @p (&struct serial_struct) to complete. * * Optional: called only if provided, otherwise %ENOTTY will be returned. * Do not call this function directly, call tty_tiocgserial(). * * @set_serial: ``int ()(struct tty_struct *tty, struct serial_struct *p)`` * * Called when the @tty device receives a %TIOCSSERIAL ioctl. Passed a * kernel structure @p (&struct serial_struct) to set the values from. * * Optional: called only if provided, otherwise %ENOTTY will be returned. * Do not call this function directly, call tty_tiocsserial(). * * @show_fdinfo: ``void ()(struct tty_struct *tty, struct seq_file *m)`` * * Called when the @tty device file descriptor receives a fdinfo request * from VFS (to show in /proc/<pid>/fdinfo/). @m should be filled with * information. * * Optional: called only if provided, otherwise nothing is written to @m. * Do not call this function directly, call tty_show_fdinfo(). * * @poll_init: ``int ()(struct tty_driver *driver, int line, char *options)`` * * kgdboc support (Documentation/process/debugging/kgdb.rst). This routine is * called to initialize the HW for later use by calling @poll_get_char or * @poll_put_char. * * Optional: called only if provided, otherwise skipped as a non-polling * driver. * * @poll_get_char: ``int ()(struct tty_driver *driver, int line)`` * * kgdboc support (see @poll_init). @driver should read a character from a * tty identified by @line and return it. * * Optional: called only if @poll_init provided. * * @poll_put_char: ``void ()(struct tty_driver *driver, int line, char ch)`` * * kgdboc support (see @poll_init). @driver should write character @ch to * a tty identified by @line. * * Optional: called only if @poll_init provided. * * @proc_show: ``int ()(struct seq_file *m, void *driver)`` * * Driver @driver (cast to &struct tty_driver) can show additional info in * /proc/tty/driver/<driver_name>. It is enough to fill in the information * into @m. * * Optional: called only if provided, otherwise no /proc entry created. * * This structure defines the interface between the low-level tty driver and * the tty routines. These routines can be defined. Unless noted otherwise, * they are optional, and can be filled in with a %NULL pointer. */ struct tty_operations { struct tty_struct * (*lookup)(struct tty_driver *driver, struct file *filp, int idx); int (*install)(struct tty_driver *driver, struct tty_struct *tty); void (*remove)(struct tty_driver *driver, struct tty_struct *tty); int (*open)(struct tty_struct * tty, struct file * filp); void (*close)(struct tty_struct * tty, struct file * filp); void (*shutdown)(struct tty_struct *tty); void (*cleanup)(struct tty_struct *tty); ssize_t (*write)(struct tty_struct *tty, const u8 *buf, size_t count); int (*put_char)(struct tty_struct *tty, u8 ch); void (*flush_chars)(struct tty_struct *tty); unsigned int (*write_room)(struct tty_struct *tty); unsigned int (*chars_in_buffer)(struct tty_struct *tty); int (*ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); long (*compat_ioctl)(struct tty_struct *tty, unsigned int cmd, unsigned long arg); void (*set_termios)(struct tty_struct *tty, const struct ktermios *old); void (*throttle)(struct tty_struct * tty); void (*unthrottle)(struct tty_struct * tty); void (*stop)(struct tty_struct *tty); void (*start)(struct tty_struct *tty); void (*hangup)(struct tty_struct *tty); int (*break_ctl)(struct tty_struct *tty, int state); void (*flush_buffer)(struct tty_struct *tty); int (*ldisc_ok)(struct tty_struct *tty, int ldisc); void (*set_ldisc)(struct tty_struct *tty); void (*wait_until_sent)(struct tty_struct *tty, int timeout); void (*send_xchar)(struct tty_struct *tty, u8 ch); int (*tiocmget)(struct tty_struct *tty); int (*tiocmset)(struct tty_struct *tty, unsigned int set, unsigned int clear); int (*resize)(struct tty_struct *tty, struct winsize *ws); int (*get_icount)(struct tty_struct *tty, struct serial_icounter_struct *icount); int (*get_serial)(struct tty_struct *tty, struct serial_struct *p); int (*set_serial)(struct tty_struct *tty, struct serial_struct *p); void (*show_fdinfo)(struct tty_struct *tty, struct seq_file *m); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct tty_driver *driver, int line, char *options); int (*poll_get_char)(struct tty_driver *driver, int line); void (*poll_put_char)(struct tty_driver *driver, int line, char ch); #endif int (*proc_show)(struct seq_file *m, void *driver); } __randomize_layout; /** * struct tty_driver -- driver for TTY devices * * @kref: reference counting. Reaching zero frees all the internals and the * driver. * @cdevs: allocated/registered character /dev devices * @owner: modules owning this driver. Used drivers cannot be rmmod'ed. * Automatically set by tty_alloc_driver(). * @driver_name: name of the driver used in /proc/tty * @name: used for constructing /dev node name * @name_base: used as a number base for constructing /dev node name * @major: major /dev device number (zero for autoassignment) * @minor_start: the first minor /dev device number * @num: number of devices allocated * @type: type of tty driver (enum tty_driver_type) * @subtype: subtype of tty driver (enum tty_driver_subtype) * @init_termios: termios to set to each tty initially (e.g. %tty_std_termios) * @flags: tty driver flags (%TTY_DRIVER_) * @proc_entry: proc fs entry, used internally * @other: driver of the linked tty; only used for the PTY driver * @ttys: array of active &struct tty_struct, set by tty_standard_install() * @ports: array of &struct tty_port; can be set during initialization by * tty_port_link_device() and similar * @termios: storage for termios at each TTY close for the next open * @driver_state: pointer to driver's arbitrary data * @ops: driver hooks for TTYs. Set them using tty_set_operations(). Use &struct * tty_port helpers in them as much as possible. * @tty_drivers: used internally to link tty_drivers together * * The usual handling of &struct tty_driver is to allocate it by * tty_alloc_driver(), set up all the necessary members, and register it by * tty_register_driver(). At last, the driver is torn down by calling * tty_unregister_driver() followed by tty_driver_kref_put(). * * The fields required to be set before calling tty_register_driver() include * @driver_name, @name, @type, @subtype, @init_termios, and @ops. */ struct tty_driver { struct kref kref; struct cdev **cdevs; struct module *owner; const char *driver_name; const char *name; int name_base; int major; int minor_start; unsigned int num; enum tty_driver_type type; enum tty_driver_subtype subtype; struct ktermios init_termios; unsigned long flags; struct proc_dir_entry *proc_entry; struct tty_driver *other; /* * Pointer to the tty data structures */ struct tty_struct **ttys; struct tty_port **ports; struct ktermios **termios; void *driver_state; /* * Driver methods */ const struct tty_operations *ops; struct list_head tty_drivers; } __randomize_layout; extern struct list_head tty_drivers; struct tty_driver *__tty_alloc_driver(unsigned int lines, struct module *owner, unsigned long flags); struct tty_driver *tty_find_polling_driver(char *name, int *line); void tty_driver_kref_put(struct tty_driver *driver); /** * tty_alloc_driver - allocate tty driver * @lines: count of lines this driver can handle at most * @flags: some of enum tty_driver_flag, will be set in driver->flags * * Returns: struct tty_driver or a PTR-encoded error (use IS_ERR() and friends). */ #define tty_alloc_driver(lines, flags) \ __tty_alloc_driver(lines, THIS_MODULE, flags) static inline struct tty_driver *tty_driver_kref_get(struct tty_driver *d) { kref_get(&d->kref); return d; } static inline void tty_set_operations(struct tty_driver *driver, const struct tty_operations *op) { driver->ops = op; } int tty_register_driver(struct tty_driver *driver); void tty_unregister_driver(struct tty_driver *driver); struct device *tty_register_device(struct tty_driver *driver, unsigned index, struct device *dev); struct device *tty_register_device_attr(struct tty_driver *driver, unsigned index, struct device *device, void *drvdata, const struct attribute_group **attr_grp); void tty_unregister_device(struct tty_driver *driver, unsigned index); #ifdef CONFIG_PROC_FS void proc_tty_register_driver(struct tty_driver *); void proc_tty_unregister_driver(struct tty_driver *); #else static inline void proc_tty_register_driver(struct tty_driver *d) {} static inline void proc_tty_unregister_driver(struct tty_driver *d) {} #endif #endif /* #ifdef _LINUX_TTY_DRIVER_H */ |
| 3764 3035 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM pagemap #if !defined(_TRACE_PAGEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_PAGEMAP_H #include <linux/tracepoint.h> #include <linux/mm.h> #define PAGEMAP_MAPPED 0x0001u #define PAGEMAP_ANONYMOUS 0x0002u #define PAGEMAP_FILE 0x0004u #define PAGEMAP_SWAPCACHE 0x0008u #define PAGEMAP_SWAPBACKED 0x0010u #define PAGEMAP_MAPPEDDISK 0x0020u #define PAGEMAP_BUFFERS 0x0040u #define trace_pagemap_flags(folio) ( \ (folio_test_anon(folio) ? PAGEMAP_ANONYMOUS : PAGEMAP_FILE) | \ (folio_mapped(folio) ? PAGEMAP_MAPPED : 0) | \ (folio_test_swapcache(folio) ? PAGEMAP_SWAPCACHE : 0) | \ (folio_test_swapbacked(folio) ? PAGEMAP_SWAPBACKED : 0) | \ (folio_test_mappedtodisk(folio) ? PAGEMAP_MAPPEDDISK : 0) | \ (folio_test_private(folio) ? PAGEMAP_BUFFERS : 0) \ ) TRACE_EVENT(mm_lru_insertion, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) __field(enum lru_list, lru ) __field(unsigned long, flags ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); __entry->lru = folio_lru_list(folio); __entry->flags = trace_pagemap_flags(folio); ), /* Flag format is based on page-types.c formatting for pagemap */ TP_printk("folio=%p pfn=0x%lx lru=%d flags=%s%s%s%s%s%s", __entry->folio, __entry->pfn, __entry->lru, __entry->flags & PAGEMAP_MAPPED ? "M" : " ", __entry->flags & PAGEMAP_ANONYMOUS ? "a" : "f", __entry->flags & PAGEMAP_SWAPCACHE ? "s" : " ", __entry->flags & PAGEMAP_SWAPBACKED ? "b" : " ", __entry->flags & PAGEMAP_MAPPEDDISK ? "d" : " ", __entry->flags & PAGEMAP_BUFFERS ? "B" : " ") ); TRACE_EVENT(mm_lru_activate, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(struct folio *, folio ) __field(unsigned long, pfn ) ), TP_fast_assign( __entry->folio = folio; __entry->pfn = folio_pfn(folio); ), TP_printk("folio=%p pfn=0x%lx", __entry->folio, __entry->pfn) ); #endif /* _TRACE_PAGEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 3930 3925 4412 4412 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BACKING_DEV_DEFS_H #define __LINUX_BACKING_DEV_DEFS_H #include <linux/list.h> #include <linux/radix-tree.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/percpu_counter.h> #include <linux/percpu-refcount.h> #include <linux/flex_proportions.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/kref.h> #include <linux/refcount.h> struct page; struct device; struct dentry; /* * Bits in bdi_writeback.state */ enum wb_state { WB_registered, /* bdi_register() was done */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ WB_start_all, /* nr_pages == 0 (all) work pending */ }; enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, WB_DIRTIED, WB_WRITTEN, NR_WB_STAT_ITEMS }; #define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) /* * why some writeback work was initiated */ enum wb_reason { WB_REASON_BACKGROUND, WB_REASON_VMSCAN, WB_REASON_SYNC, WB_REASON_PERIODIC, WB_REASON_LAPTOP_TIMER, WB_REASON_FS_FREE_SPACE, /* * There is no bdi forker thread any more and works are done * by emergency worker, however, this is TPs userland visible * and we'll be exposing exactly the same information, * so it has a mismatch name. */ WB_REASON_FORKER_THREAD, WB_REASON_FOREIGN_FLUSH, WB_REASON_MAX, }; struct wb_completion { atomic_t cnt; wait_queue_head_t *waitq; }; #define __WB_COMPLETION_INIT(_waitq) \ (struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) } /* * If one wants to wait for one or more wb_writeback_works, each work's * ->done should be set to a wb_completion defined using the following * macro. Once all work items are issued with wb_queue_work(), the caller * can wait for the completion of all using wb_wait_for_completion(). Work * items which are waited upon aren't freed automatically on completion. */ #define WB_COMPLETION_INIT(bdi) __WB_COMPLETION_INIT(&(bdi)->wb_waitq) #define DEFINE_WB_COMPLETION(cmpl, bdi) \ struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) /* * Each wb (bdi_writeback) can perform writeback operations, is measured * and throttled, independently. Without cgroup writeback, each bdi * (bdi_writeback) is served by its embedded bdi->wb. * * On the default hierarchy, blkcg implicitly enables memcg. This allows * using memcg's page ownership for attributing writeback IOs, and every * memcg - blkcg combination can be served by its own wb by assigning a * dedicated wb to each memcg, which enables isolation across different * cgroups and propagation of IO back pressure down from the IO layer upto * the tasks which are generating the dirty pages to be written back. * * A cgroup wb is indexed on its bdi by the ID of the associated memcg, * refcounted with the number of inodes attached to it, and pins the memcg * and the corresponding blkcg. As the corresponding blkcg for a memcg may * change as blkcg is disabled and enabled higher up in the hierarchy, a wb * is tested for blkcg after lookup and removed from index on mismatch so * that a new wb for the combination can be created. * * Each bdi_writeback that is not embedded into the backing_dev_info must hold * a reference to the parent backing_dev_info. See cgwb_create() for details. */ struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ unsigned long state; /* Always use atomic bitops on this */ unsigned long last_old_flush; /* last old data flush */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ atomic_t writeback_inodes; /* number of inodes under writeback */ struct percpu_counter stat[NR_WB_STAT_ITEMS]; unsigned long bw_time_stamp; /* last time write bw is updated */ unsigned long dirtied_stamp; unsigned long written_stamp; /* pages written at bw_time_stamp */ unsigned long write_bandwidth; /* the estimated write bandwidth */ unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */ /* * The base dirty throttle rate, re-calculated on every 200ms. * All the bdi tasks' dirty rate will be curbed under it. * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit * in small steps and is much more smooth/stable than the latter. */ unsigned long dirty_ratelimit; unsigned long balanced_dirty_ratelimit; struct fprop_local_percpu completions; int dirty_exceeded; enum wb_reason start_all_reason; spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ struct delayed_work bw_dwork; /* work item used for bandwidth estimate */ struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK struct percpu_ref refcnt; /* used only for !root wb's */ struct fprop_local_percpu memcg_completions; struct cgroup_subsys_state *memcg_css; /* the associated memcg */ struct cgroup_subsys_state *blkcg_css; /* and blkcg */ struct list_head memcg_node; /* anchored at memcg->cgwb_list */ struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ struct list_head b_attached; /* attached inodes, protected by list_lock */ struct list_head offline_node; /* anchored at offline_cgwbs */ union { struct work_struct release_work; struct rcu_head rcu; }; #endif }; struct backing_dev_info { u64 id; struct rb_node rb_node; /* keyed by ->id */ struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; /* * Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are * any dirty wbs, which is depended upon by bdi_has_dirty(). */ atomic_long_t tot_write_bandwidth; /* * Jiffies when last process was dirty throttled on this bdi. Used by * blk-wbt. */ unsigned long last_bdp_sleep; struct bdi_writeback wb; /* the root writeback info for this bdi */ struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #endif wait_queue_head_t wb_waitq; struct device *dev; char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; #endif }; struct wb_lock_cookie { bool locked; unsigned long flags; }; #ifdef CONFIG_CGROUP_WRITEBACK /** * wb_tryget - try to increment a wb's refcount * @wb: bdi_writeback to get */ static inline bool wb_tryget(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) return percpu_ref_tryget(&wb->refcnt); return true; } /** * wb_get - increment a wb's refcount * @wb: bdi_writeback to get */ static inline void wb_get(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) percpu_ref_get(&wb->refcnt); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put * @nr: number of references to put */ static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { if (WARN_ON_ONCE(!wb->bdi)) { /* * A driver bug might cause a file to be removed before bdi was * initialized. */ return; } if (wb != &wb->bdi->wb) percpu_ref_put_many(&wb->refcnt, nr); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put */ static inline void wb_put(struct bdi_writeback *wb) { wb_put_many(wb, 1); } /** * wb_dying - is a wb dying? * @wb: bdi_writeback of interest * * Returns whether @wb is unlinked and being drained. */ static inline bool wb_dying(struct bdi_writeback *wb) { return percpu_ref_is_dying(&wb->refcnt); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool wb_tryget(struct bdi_writeback *wb) { return true; } static inline void wb_get(struct bdi_writeback *wb) { } static inline void wb_put(struct bdi_writeback *wb) { } static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr) { } static inline bool wb_dying(struct bdi_writeback *wb) { return false; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* __LINUX_BACKING_DEV_DEFS_H */ |
| 3501 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 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 _ASM_X86_PAGE_64_H #define _ASM_X86_PAGE_64_H #include <asm/page_64_types.h> #ifndef __ASSEMBLER__ #include <asm/cpufeatures.h> #include <asm/alternative.h> #include <linux/kmsan-checks.h> /* duplicated to the one in bootmem.h */ extern unsigned long max_pfn; extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; extern unsigned long direct_map_physmem_end; static __always_inline unsigned long __phys_addr_nodebug(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ x = y + ((x > y) ? phys_base : (__START_KERNEL_map - PAGE_OFFSET)); return x; } #ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); extern unsigned long __phys_addr_symbol(unsigned long); #else #define __phys_addr(x) __phys_addr_nodebug(x) #define __phys_addr_symbol(x) \ ((unsigned long)(x) - __START_KERNEL_map + phys_base) #endif #define __phys_reloc_hide(x) (x) void clear_page_orig(void *page); void clear_page_rep(void *page); void clear_page_erms(void *page); static inline void clear_page(void *page) { /* * Clean up KMSAN metadata for the page being cleared. The assembly call * below clobbers @page, so we perform unpoisoning before it. */ kmsan_unpoison_memory(page, PAGE_SIZE); alternative_call_2(clear_page_orig, clear_page_rep, X86_FEATURE_REP_GOOD, clear_page_erms, X86_FEATURE_ERMS, "=D" (page), "D" (page), "cc", "memory", "rax", "rcx"); } void copy_page(void *to, void *from); KCFI_REFERENCE(copy_page); /* * User space process size. This is the first address outside the user range. * There are a few constraints that determine this: * * On Intel CPUs, if a SYSCALL instruction is at the highest canonical * address, then that syscall will enter the kernel with a * non-canonical return address, and SYSRET will explode dangerously. * We avoid this particular problem by preventing anything * from being mapped at the maximum canonical address. * * On AMD CPUs in the Ryzen family, there's a nasty bug in which the * CPUs malfunction if they execute code from the highest canonical page. * They'll speculate right off the end of the canonical space, and * bad things happen. This is worked around in the same way as the * Intel problem. * * With page table isolation enabled, we map the LDT in ... [stay tuned] */ static __always_inline unsigned long task_size_max(void) { unsigned long ret; alternative_io("movq %[small],%0","movq %[large],%0", X86_FEATURE_LA57, "=r" (ret), [small] "i" ((1ul << 47)-PAGE_SIZE), [large] "i" ((1ul << 56)-PAGE_SIZE)); return ret; } #endif /* !__ASSEMBLER__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION # define __HAVE_ARCH_GATE_AREA 1 #endif #endif /* _ASM_X86_PAGE_64_H */ |
| 196 2582 1894 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM maple_tree #if !defined(_TRACE_MM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_MM_H #include <linux/tracepoint.h> struct ma_state; TRACE_EVENT(ma_op, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_read, TP_PROTO(const char *fn, struct ma_state *mas), TP_ARGS(fn, mas), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->node = mas->node; ), TP_printk("%s\tNode: %p (%lu %lu) range: %lu-%lu", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last ) ) TRACE_EVENT(ma_write, TP_PROTO(const char *fn, struct ma_state *mas, unsigned long piv, void *val), TP_ARGS(fn, mas, piv, val), TP_STRUCT__entry( __field(const char *, fn) __field(unsigned long, min) __field(unsigned long, max) __field(unsigned long, index) __field(unsigned long, last) __field(unsigned long, piv) __field(void *, val) __field(void *, node) ), TP_fast_assign( __entry->fn = fn; __entry->min = mas->min; __entry->max = mas->max; __entry->index = mas->index; __entry->last = mas->last; __entry->piv = piv; __entry->val = val; __entry->node = mas->node; ), TP_printk("%s\tNode %p (%lu %lu) range:%lu-%lu piv (%lu) val %p", __entry->fn, (void *) __entry->node, (unsigned long) __entry->min, (unsigned long) __entry->max, (unsigned long) __entry->index, (unsigned long) __entry->last, (unsigned long) __entry->piv, (void *) __entry->val ) ) #endif /* _TRACE_MM_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2 2 2 2 2 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 | /* * Copyright (c) 2006-2009 Red Hat Inc. * Copyright (c) 2006-2008 Intel Corporation * Copyright (c) 2007 Dave Airlie <airlied@linux.ie> * * DRM framebuffer helper functions * * Permission to use, copy, modify, distribute, and sell this software and its * documentation for any purpose is hereby granted without fee, provided that * the above copyright notice appear in all copies and that both that copyright * notice and this permission notice appear in supporting documentation, and * that the name of the copyright holders not be used in advertising or * publicity pertaining to distribution of the software without specific, * written prior permission. The copyright holders make no representations * about the suitability of this software for any purpose. It is provided "as * is" without express or implied warranty. * * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS SOFTWARE, * INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO * EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT OR * CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, * DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER * TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE * OF THIS SOFTWARE. * * Authors: * Dave Airlie <airlied@linux.ie> * Jesse Barnes <jesse.barnes@intel.com> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/console.h> #include <linux/export.h> #include <linux/pci.h> #include <linux/sysrq.h> #include <linux/vga_switcheroo.h> #include <drm/drm_atomic.h> #include <drm/drm_drv.h> #include <drm/drm_fb_helper.h> #include <drm/drm_fourcc.h> #include <drm/drm_framebuffer.h> #include <drm/drm_modeset_helper_vtables.h> #include <drm/drm_print.h> #include <drm/drm_vblank.h> #include "drm_internal.h" #include "drm_crtc_internal.h" static bool drm_fbdev_emulation = true; module_param_named(fbdev_emulation, drm_fbdev_emulation, bool, 0600); MODULE_PARM_DESC(fbdev_emulation, "Enable legacy fbdev emulation [default=true]"); static int drm_fbdev_overalloc = CONFIG_DRM_FBDEV_OVERALLOC; module_param(drm_fbdev_overalloc, int, 0444); MODULE_PARM_DESC(drm_fbdev_overalloc, "Overallocation of the fbdev buffer (%) [default=" __MODULE_STRING(CONFIG_DRM_FBDEV_OVERALLOC) "]"); /* * In order to keep user-space compatibility, we want in certain use-cases * to keep leaking the fbdev physical address to the user-space program * handling the fbdev buffer. * * This is a bad habit, essentially kept to support closed-source OpenGL * drivers that should really be moved into open-source upstream projects * instead of using legacy physical addresses in user space to communicate * with other out-of-tree kernel modules. * * This module_param *should* be removed as soon as possible and be * considered as a broken and legacy behaviour from a modern fbdev device. */ static bool drm_leak_fbdev_smem; #if IS_ENABLED(CONFIG_DRM_FBDEV_LEAK_PHYS_SMEM) module_param_unsafe(drm_leak_fbdev_smem, bool, 0600); MODULE_PARM_DESC(drm_leak_fbdev_smem, "Allow unsafe leaking fbdev physical smem address [default=false]"); #endif static LIST_HEAD(kernel_fb_helper_list); static DEFINE_MUTEX(kernel_fb_helper_lock); /** * DOC: fbdev helpers * * The fb helper functions are useful to provide an fbdev on top of a drm kernel * mode setting driver. They can be used mostly independently from the crtc * helper functions used by many drivers to implement the kernel mode setting * interfaces. Drivers that use one of the shared memory managers, TTM, SHMEM, * DMA, should instead use the corresponding fbdev emulation. * * For suspend/resume consider using drm_mode_config_helper_suspend() and * drm_mode_config_helper_resume() which takes care of fbdev as well. * * All other functions exported by the fb helper library can be used to * implement the fbdev driver interface by the driver. * * It is possible, though perhaps somewhat tricky, to implement race-free * hotplug detection using the fbdev helpers. The drm_fb_helper_prepare() * helper must be called first to initialize the minimum required to make * hotplug detection work. Drivers also need to make sure to properly set up * the &drm_mode_config.funcs member. After calling drm_kms_helper_poll_init() * it is safe to enable interrupts and start processing hotplug events. At the * same time, drivers should initialize all modeset objects such as CRTCs, * encoders and connectors. To finish up the fbdev helper initialization, the * drm_fb_helper_init() function is called. To probe for all attached displays * and set up an initial configuration using the detected hardware, drivers * should call drm_fb_helper_initial_config(). * * If &drm_framebuffer_funcs.dirty is set, the * drm_fb_helper_{cfb,sys}_{write,fillrect,copyarea,imageblit} functions will * accumulate changes and schedule &drm_fb_helper.dirty_work to run right * away. This worker then calls the dirty() function ensuring that it will * always run in process context since the fb_*() function could be running in * atomic context. If drm_fb_helper_deferred_io() is used as the deferred_io * callback it will also schedule dirty_work with the damage collected from the * mmap page writes. */ static void drm_fb_helper_restore_lut_atomic(struct drm_crtc *crtc) { uint16_t *r_base, *g_base, *b_base; if (crtc->funcs->gamma_set == NULL) return; r_base = crtc->gamma_store; g_base = r_base + crtc->gamma_size; b_base = g_base + crtc->gamma_size; crtc->funcs->gamma_set(crtc, r_base, g_base, b_base, crtc->gamma_size, NULL); } /** * drm_fb_helper_debug_enter - implementation for &fb_ops.fb_debug_enter * @info: fbdev registered by the helper */ int drm_fb_helper_debug_enter(struct fb_info *info) { struct drm_fb_helper *helper = info->par; const struct drm_crtc_helper_funcs *funcs; struct drm_mode_set *mode_set; list_for_each_entry(helper, &kernel_fb_helper_list, kernel_fb_list) { mutex_lock(&helper->client.modeset_mutex); drm_client_for_each_modeset(mode_set, &helper->client) { if (!mode_set->crtc->enabled) continue; funcs = mode_set->crtc->helper_private; if (funcs->mode_set_base_atomic == NULL) continue; if (drm_drv_uses_atomic_modeset(mode_set->crtc->dev)) continue; funcs->mode_set_base_atomic(mode_set->crtc, mode_set->fb, mode_set->x, mode_set->y, ENTER_ATOMIC_MODE_SET); } mutex_unlock(&helper->client.modeset_mutex); } return 0; } EXPORT_SYMBOL(drm_fb_helper_debug_enter); /** * drm_fb_helper_debug_leave - implementation for &fb_ops.fb_debug_leave * @info: fbdev registered by the helper */ int drm_fb_helper_debug_leave(struct fb_info *info) { struct drm_fb_helper *helper = info->par; struct drm_client_dev *client = &helper->client; struct drm_device *dev = helper->dev; struct drm_crtc *crtc; const struct drm_crtc_helper_funcs *funcs; struct drm_mode_set *mode_set; struct drm_framebuffer *fb; mutex_lock(&client->modeset_mutex); drm_client_for_each_modeset(mode_set, client) { crtc = mode_set->crtc; if (drm_drv_uses_atomic_modeset(crtc->dev)) continue; funcs = crtc->helper_private; fb = crtc->primary->fb; if (!crtc->enabled) continue; if (!fb) { drm_err(dev, "no fb to restore?\n"); continue; } if (funcs->mode_set_base_atomic == NULL) continue; drm_fb_helper_restore_lut_atomic(mode_set->crtc); funcs->mode_set_base_atomic(mode_set->crtc, fb, crtc->x, crtc->y, LEAVE_ATOMIC_MODE_SET); } mutex_unlock(&client->modeset_mutex); return 0; } EXPORT_SYMBOL(drm_fb_helper_debug_leave); static int __drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper, bool force) { bool do_delayed; int ret; if (!drm_fbdev_emulation || !fb_helper) return -ENODEV; if (READ_ONCE(fb_helper->deferred_setup)) return 0; mutex_lock(&fb_helper->lock); if (force) { /* * Yes this is the _locked version which expects the master lock * to be held. But for forced restores we're intentionally * racing here, see drm_fb_helper_set_par(). */ ret = drm_client_modeset_commit_locked(&fb_helper->client); } else { ret = drm_client_modeset_commit(&fb_helper->client); } do_delayed = fb_helper->delayed_hotplug; if (do_delayed) fb_helper->delayed_hotplug = false; mutex_unlock(&fb_helper->lock); if (do_delayed) drm_fb_helper_hotplug_event(fb_helper); if (fb_helper->funcs->fb_restore) fb_helper->funcs->fb_restore(fb_helper); return ret; } /** * drm_fb_helper_restore_fbdev_mode_unlocked - restore fbdev configuration * @fb_helper: driver-allocated fbdev helper, can be NULL * * This helper should be called from fbdev emulation's &drm_client_funcs.restore * callback. It ensures that the user isn't greeted with a black screen when the * userspace compositor releases the display device. * * Returns: * 0 on success, or a negative errno code otherwise. */ int drm_fb_helper_restore_fbdev_mode_unlocked(struct drm_fb_helper *fb_helper) { return __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, false); } EXPORT_SYMBOL(drm_fb_helper_restore_fbdev_mode_unlocked); #ifdef CONFIG_MAGIC_SYSRQ /* emergency restore, don't bother with error reporting */ static void drm_fb_helper_restore_work_fn(struct work_struct *ignored) { struct drm_fb_helper *helper; mutex_lock(&kernel_fb_helper_lock); list_for_each_entry(helper, &kernel_fb_helper_list, kernel_fb_list) { struct drm_device *dev = helper->dev; if (dev->switch_power_state == DRM_SWITCH_POWER_OFF) continue; mutex_lock(&helper->lock); drm_client_modeset_commit_locked(&helper->client); mutex_unlock(&helper->lock); } mutex_unlock(&kernel_fb_helper_lock); } static DECLARE_WORK(drm_fb_helper_restore_work, drm_fb_helper_restore_work_fn); static void drm_fb_helper_sysrq(u8 dummy1) { schedule_work(&drm_fb_helper_restore_work); } static const struct sysrq_key_op sysrq_drm_fb_helper_restore_op = { .handler = drm_fb_helper_sysrq, .help_msg = "force-fb(v)", .action_msg = "Restore framebuffer console", }; #else static const struct sysrq_key_op sysrq_drm_fb_helper_restore_op = { }; #endif static void drm_fb_helper_dpms(struct fb_info *info, int dpms_mode) { struct drm_fb_helper *fb_helper = info->par; mutex_lock(&fb_helper->lock); drm_client_modeset_dpms(&fb_helper->client, dpms_mode); mutex_unlock(&fb_helper->lock); } /** * drm_fb_helper_blank - implementation for &fb_ops.fb_blank * @blank: desired blanking state * @info: fbdev registered by the helper */ int drm_fb_helper_blank(int blank, struct fb_info *info) { if (oops_in_progress) return -EBUSY; switch (blank) { /* Display: On; HSync: On, VSync: On */ case FB_BLANK_UNBLANK: drm_fb_helper_dpms(info, DRM_MODE_DPMS_ON); break; /* Display: Off; HSync: On, VSync: On */ case FB_BLANK_NORMAL: drm_fb_helper_dpms(info, DRM_MODE_DPMS_STANDBY); break; /* Display: Off; HSync: Off, VSync: On */ case FB_BLANK_HSYNC_SUSPEND: drm_fb_helper_dpms(info, DRM_MODE_DPMS_STANDBY); break; /* Display: Off; HSync: On, VSync: Off */ case FB_BLANK_VSYNC_SUSPEND: drm_fb_helper_dpms(info, DRM_MODE_DPMS_SUSPEND); break; /* Display: Off; HSync: Off, VSync: Off */ case FB_BLANK_POWERDOWN: drm_fb_helper_dpms(info, DRM_MODE_DPMS_OFF); break; } return 0; } EXPORT_SYMBOL(drm_fb_helper_blank); static void drm_fb_helper_resume_worker(struct work_struct *work) { struct drm_fb_helper *helper = container_of(work, struct drm_fb_helper, resume_work); console_lock(); fb_set_suspend(helper->info, 0); console_unlock(); } static void drm_fb_helper_fb_dirty(struct drm_fb_helper *helper) { struct drm_device *dev = helper->dev; struct drm_clip_rect *clip = &helper->damage_clip; struct drm_clip_rect clip_copy; unsigned long flags; int ret; if (drm_WARN_ON_ONCE(dev, !helper->funcs->fb_dirty)) return; spin_lock_irqsave(&helper->damage_lock, flags); clip_copy = *clip; clip->x1 = clip->y1 = ~0; clip->x2 = clip->y2 = 0; spin_unlock_irqrestore(&helper->damage_lock, flags); ret = helper->funcs->fb_dirty(helper, &clip_copy); if (ret) goto err; return; err: /* * Restore damage clip rectangle on errors. The next run * of the damage worker will perform the update. */ spin_lock_irqsave(&helper->damage_lock, flags); clip->x1 = min_t(u32, clip->x1, clip_copy.x1); clip->y1 = min_t(u32, clip->y1, clip_copy.y1); clip->x2 = max_t(u32, clip->x2, clip_copy.x2); clip->y2 = max_t(u32, clip->y2, clip_copy.y2); spin_unlock_irqrestore(&helper->damage_lock, flags); } static void drm_fb_helper_damage_work(struct work_struct *work) { struct drm_fb_helper *helper = container_of(work, struct drm_fb_helper, damage_work); drm_fb_helper_fb_dirty(helper); } /** * drm_fb_helper_prepare - setup a drm_fb_helper structure * @dev: DRM device * @helper: driver-allocated fbdev helper structure to set up * @preferred_bpp: Preferred bits per pixel for the device. * @funcs: pointer to structure of functions associate with this helper * * Sets up the bare minimum to make the framebuffer helper usable. This is * useful to implement race-free initialization of the polling helpers. */ void drm_fb_helper_prepare(struct drm_device *dev, struct drm_fb_helper *helper, unsigned int preferred_bpp, const struct drm_fb_helper_funcs *funcs) { /* * Pick a preferred bpp of 32 if no value has been given. This * will select XRGB8888 for the framebuffer formats. All drivers * have to support XRGB8888 for backwards compatibility with legacy * userspace, so it's the safe choice here. * * TODO: Replace struct drm_mode_config.preferred_depth and this * bpp value with a preferred format that is given as struct * drm_format_info. Then derive all other values from the * format. */ if (!preferred_bpp) preferred_bpp = 32; INIT_LIST_HEAD(&helper->kernel_fb_list); spin_lock_init(&helper->damage_lock); INIT_WORK(&helper->resume_work, drm_fb_helper_resume_worker); INIT_WORK(&helper->damage_work, drm_fb_helper_damage_work); helper->damage_clip.x1 = helper->damage_clip.y1 = ~0; mutex_init(&helper->lock); helper->funcs = funcs; helper->dev = dev; helper->preferred_bpp = preferred_bpp; } EXPORT_SYMBOL(drm_fb_helper_prepare); /** * drm_fb_helper_unprepare - clean up a drm_fb_helper structure * @fb_helper: driver-allocated fbdev helper structure to set up * * Cleans up the framebuffer helper. Inverse of drm_fb_helper_prepare(). */ void drm_fb_helper_unprepare(struct drm_fb_helper *fb_helper) { mutex_destroy(&fb_helper->lock); } EXPORT_SYMBOL(drm_fb_helper_unprepare); /** * drm_fb_helper_init - initialize a &struct drm_fb_helper * @dev: drm device * @fb_helper: driver-allocated fbdev helper structure to initialize * * This allocates the structures for the fbdev helper with the given limits. * Note that this won't yet touch the hardware (through the driver interfaces) * nor register the fbdev. This is only done in drm_fb_helper_initial_config() * to allow driver writes more control over the exact init sequence. * * Drivers must call drm_fb_helper_prepare() before calling this function. * * RETURNS: * Zero if everything went ok, nonzero otherwise. */ int drm_fb_helper_init(struct drm_device *dev, struct drm_fb_helper *fb_helper) { int ret; /* * If this is not the generic fbdev client, initialize a drm_client * without callbacks so we can use the modesets. */ if (!fb_helper->client.funcs) { ret = drm_client_init(dev, &fb_helper->client, "drm_fb_helper", NULL); if (ret) return ret; } dev->fb_helper = fb_helper; return 0; } EXPORT_SYMBOL(drm_fb_helper_init); /** * drm_fb_helper_alloc_info - allocate fb_info and some of its members * @fb_helper: driver-allocated fbdev helper * * A helper to alloc fb_info and the member cmap. Called by the driver * within the struct &drm_driver.fbdev_probe callback function. Drivers do * not need to release the allocated fb_info structure themselves, this is * automatically done when calling drm_fb_helper_fini(). * * RETURNS: * fb_info pointer if things went okay, pointer containing error code * otherwise */ struct fb_info *drm_fb_helper_alloc_info(struct drm_fb_helper *fb_helper) { struct device *dev = fb_helper->dev->dev; struct fb_info *info; int ret; info = framebuffer_alloc(0, dev); if (!info) return ERR_PTR(-ENOMEM); if (!drm_leak_fbdev_smem) info->flags |= FBINFO_HIDE_SMEM_START; ret = fb_alloc_cmap(&info->cmap, 256, 0); if (ret) goto err_release; fb_helper->info = info; info->skip_vt_switch = true; info->skip_panic = drm_panic_is_enabled(fb_helper->dev); return info; err_release: framebuffer_release(info); return ERR_PTR(ret); } EXPORT_SYMBOL(drm_fb_helper_alloc_info); /** * drm_fb_helper_release_info - release fb_info and its members * @fb_helper: driver-allocated fbdev helper * * A helper to release fb_info and the member cmap. Drivers do not * need to release the allocated fb_info structure themselves, this is * automatically done when calling drm_fb_helper_fini(). */ void drm_fb_helper_release_info(struct drm_fb_helper *fb_helper) { struct fb_info *info = fb_helper->info; if (!info) return; fb_helper->info = NULL; if (info->cmap.len) fb_dealloc_cmap(&info->cmap); framebuffer_release(info); } EXPORT_SYMBOL(drm_fb_helper_release_info); /** * drm_fb_helper_unregister_info - unregister fb_info framebuffer device * @fb_helper: driver-allocated fbdev helper, must not be NULL * * A wrapper around unregister_framebuffer, to release the fb_info * framebuffer device. This must be called before releasing all resources for * @fb_helper by calling drm_fb_helper_fini(). */ void drm_fb_helper_unregister_info(struct drm_fb_helper *fb_helper) { struct fb_info *info = fb_helper->info; struct device *dev = info->device; if (dev_is_pci(dev)) vga_switcheroo_client_fb_set(to_pci_dev(dev), NULL); unregister_framebuffer(fb_helper->info); } EXPORT_SYMBOL(drm_fb_helper_unregister_info); /** * drm_fb_helper_fini - finialize a &struct drm_fb_helper * @fb_helper: driver-allocated fbdev helper, can be NULL * * This cleans up all remaining resources associated with @fb_helper. */ void drm_fb_helper_fini(struct drm_fb_helper *fb_helper) { if (!fb_helper) return; fb_helper->dev->fb_helper = NULL; if (!drm_fbdev_emulation) return; cancel_work_sync(&fb_helper->resume_work); cancel_work_sync(&fb_helper->damage_work); drm_fb_helper_release_info(fb_helper); mutex_lock(&kernel_fb_helper_lock); if (!list_empty(&fb_helper->kernel_fb_list)) { list_del(&fb_helper->kernel_fb_list); if (list_empty(&kernel_fb_helper_list)) unregister_sysrq_key('v', &sysrq_drm_fb_helper_restore_op); } mutex_unlock(&kernel_fb_helper_lock); if (!fb_helper->client.funcs) drm_client_release(&fb_helper->client); } EXPORT_SYMBOL(drm_fb_helper_fini); static void drm_fb_helper_add_damage_clip(struct drm_fb_helper *helper, u32 x, u32 y, u32 width, u32 height) { struct drm_clip_rect *clip = &helper->damage_clip; unsigned long flags; spin_lock_irqsave(&helper->damage_lock, flags); clip->x1 = min_t(u32, clip->x1, x); clip->y1 = min_t(u32, clip->y1, y); clip->x2 = max_t(u32, clip->x2, x + width); clip->y2 = max_t(u32, clip->y2, y + height); spin_unlock_irqrestore(&helper->damage_lock, flags); } static void drm_fb_helper_damage(struct drm_fb_helper *helper, u32 x, u32 y, u32 width, u32 height) { /* * This function may be invoked by panic() to flush the frame * buffer, where all CPUs except the panic CPU are stopped. * During the following schedule_work(), the panic CPU needs * the worker_pool lock, which might be held by a stopped CPU, * causing schedule_work() and panic() to block. Return early on * oops_in_progress to prevent this blocking. */ if (oops_in_progress) return; drm_fb_helper_add_damage_clip(helper, x, y, width, height); schedule_work(&helper->damage_work); } /* * Convert memory region into area of scanlines and pixels per * scanline. The parameters off and len must not reach beyond * the end of the framebuffer. */ static void drm_fb_helper_memory_range_to_clip(struct fb_info *info, off_t off, size_t len, struct drm_rect *clip) { u32 line_length = info->fix.line_length; u32 fb_height = info->var.yres; off_t end = off + len; u32 x1 = 0; u32 y1 = off / line_length; u32 x2 = info->var.xres; u32 y2 = DIV_ROUND_UP(end, line_length); /* Don't allow any of them beyond the bottom bound of display area */ if (y1 > fb_height) y1 = fb_height; if (y2 > fb_height) y2 = fb_height; if ((y2 - y1) == 1) { /* * We've only written to a single scanline. Try to reduce * the number of horizontal pixels that need an update. */ off_t bit_off = (off % line_length) * 8; off_t bit_end = (end % line_length) * 8; x1 = bit_off / info->var.bits_per_pixel; x2 = DIV_ROUND_UP(bit_end, info->var.bits_per_pixel); } drm_rect_init(clip, x1, y1, x2 - x1, y2 - y1); } /* Don't use in new code. */ void drm_fb_helper_damage_range(struct fb_info *info, off_t off, size_t len) { struct drm_fb_helper *fb_helper = info->par; struct drm_rect damage_area; drm_fb_helper_memory_range_to_clip(info, off, len, &damage_area); drm_fb_helper_damage(fb_helper, damage_area.x1, damage_area.y1, drm_rect_width(&damage_area), drm_rect_height(&damage_area)); } EXPORT_SYMBOL(drm_fb_helper_damage_range); /* Don't use in new code. */ void drm_fb_helper_damage_area(struct fb_info *info, u32 x, u32 y, u32 width, u32 height) { struct drm_fb_helper *fb_helper = info->par; drm_fb_helper_damage(fb_helper, x, y, width, height); } EXPORT_SYMBOL(drm_fb_helper_damage_area); #ifdef CONFIG_FB_DEFERRED_IO /** * drm_fb_helper_deferred_io() - fbdev deferred_io callback function * @info: fb_info struct pointer * @pagereflist: list of mmap framebuffer pages that have to be flushed * * This function is used as the &fb_deferred_io.deferred_io * callback function for flushing the fbdev mmap writes. */ void drm_fb_helper_deferred_io(struct fb_info *info, struct list_head *pagereflist) { struct drm_fb_helper *helper = info->par; unsigned long start, end, min_off, max_off, total_size; struct fb_deferred_io_pageref *pageref; struct drm_rect damage_area; min_off = ULONG_MAX; max_off = 0; list_for_each_entry(pageref, pagereflist, list) { start = pageref->offset; end = start + PAGE_SIZE; min_off = min(min_off, start); max_off = max(max_off, end); } /* * As we can only track pages, we might reach beyond the end * of the screen and account for non-existing scanlines. Hence, * keep the covered memory area within the screen buffer. */ if (info->screen_size) total_size = info->screen_size; else total_size = info->fix.smem_len; max_off = min(max_off, total_size); if (min_off < max_off) { drm_fb_helper_memory_range_to_clip(info, min_off, max_off - min_off, &damage_area); drm_fb_helper_damage(helper, damage_area.x1, damage_area.y1, drm_rect_width(&damage_area), drm_rect_height(&damage_area)); } } EXPORT_SYMBOL(drm_fb_helper_deferred_io); #endif /** * drm_fb_helper_set_suspend - wrapper around fb_set_suspend * @fb_helper: driver-allocated fbdev helper, can be NULL * @suspend: whether to suspend or resume * * A wrapper around fb_set_suspend implemented by fbdev core. * Use drm_fb_helper_set_suspend_unlocked() if you don't need to take * the lock yourself */ void drm_fb_helper_set_suspend(struct drm_fb_helper *fb_helper, bool suspend) { if (!fb_helper || !fb_helper->info) return; if (fb_helper->funcs->fb_set_suspend) fb_helper->funcs->fb_set_suspend(fb_helper, suspend); else fb_set_suspend(fb_helper->info, suspend); } EXPORT_SYMBOL(drm_fb_helper_set_suspend); /** * drm_fb_helper_set_suspend_unlocked - wrapper around fb_set_suspend that also * takes the console lock * @fb_helper: driver-allocated fbdev helper, can be NULL * @suspend: whether to suspend or resume * * A wrapper around fb_set_suspend() that takes the console lock. If the lock * isn't available on resume, a worker is tasked with waiting for the lock * to become available. The console lock can be pretty contented on resume * due to all the printk activity. * * This function can be called multiple times with the same state since * &fb_info.state is checked to see if fbdev is running or not before locking. * * Use drm_fb_helper_set_suspend() if you need to take the lock yourself. */ void drm_fb_helper_set_suspend_unlocked(struct drm_fb_helper *fb_helper, bool suspend) { if (!fb_helper || !fb_helper->info) return; /* make sure there's no pending/ongoing resume */ flush_work(&fb_helper->resume_work); if (suspend) { if (fb_helper->info->state != FBINFO_STATE_RUNNING) return; console_lock(); } else { if (fb_helper->info->state == FBINFO_STATE_RUNNING) return; if (!console_trylock()) { schedule_work(&fb_helper->resume_work); return; } } drm_fb_helper_set_suspend(fb_helper, suspend); console_unlock(); } EXPORT_SYMBOL(drm_fb_helper_set_suspend_unlocked); static int setcmap_pseudo_palette(struct fb_cmap *cmap, struct fb_info *info) { u32 *palette = (u32 *)info->pseudo_palette; int i; if (cmap->start + cmap->len > 16) return -EINVAL; for (i = 0; i < cmap->len; ++i) { u16 red = cmap->red[i]; u16 green = cmap->green[i]; u16 blue = cmap->blue[i]; u32 value; red >>= 16 - info->var.red.length; green >>= 16 - info->var.green.length; blue >>= 16 - info->var.blue.length; value = (red << info->var.red.offset) | (green << info->var.green.offset) | (blue << info->var.blue.offset); if (info->var.transp.length > 0) { u32 mask = (1 << info->var.transp.length) - 1; mask <<= info->var.transp.offset; value |= mask; } palette[cmap->start + i] = value; } return 0; } static int setcmap_legacy(struct fb_cmap *cmap, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_mode_set *modeset; struct drm_crtc *crtc; u16 *r, *g, *b; int ret = 0; drm_modeset_lock_all(fb_helper->dev); drm_client_for_each_modeset(modeset, &fb_helper->client) { crtc = modeset->crtc; if (!crtc->funcs->gamma_set || !crtc->gamma_size) { ret = -EINVAL; goto out; } if (cmap->start + cmap->len > crtc->gamma_size) { ret = -EINVAL; goto out; } r = crtc->gamma_store; g = r + crtc->gamma_size; b = g + crtc->gamma_size; memcpy(r + cmap->start, cmap->red, cmap->len * sizeof(*r)); memcpy(g + cmap->start, cmap->green, cmap->len * sizeof(*g)); memcpy(b + cmap->start, cmap->blue, cmap->len * sizeof(*b)); ret = crtc->funcs->gamma_set(crtc, r, g, b, crtc->gamma_size, NULL); if (ret) goto out; } out: drm_modeset_unlock_all(fb_helper->dev); return ret; } static struct drm_property_blob *setcmap_new_gamma_lut(struct drm_crtc *crtc, struct fb_cmap *cmap) { struct drm_device *dev = crtc->dev; struct drm_property_blob *gamma_lut; struct drm_color_lut *lut; int size = crtc->gamma_size; int i; if (!size || cmap->start + cmap->len > size) return ERR_PTR(-EINVAL); gamma_lut = drm_property_create_blob(dev, sizeof(*lut) * size, NULL); if (IS_ERR(gamma_lut)) return gamma_lut; lut = gamma_lut->data; if (cmap->start || cmap->len != size) { u16 *r = crtc->gamma_store; u16 *g = r + crtc->gamma_size; u16 *b = g + crtc->gamma_size; for (i = 0; i < cmap->start; i++) { lut[i].red = r[i]; lut[i].green = g[i]; lut[i].blue = b[i]; } for (i = cmap->start + cmap->len; i < size; i++) { lut[i].red = r[i]; lut[i].green = g[i]; lut[i].blue = b[i]; } } for (i = 0; i < cmap->len; i++) { lut[cmap->start + i].red = cmap->red[i]; lut[cmap->start + i].green = cmap->green[i]; lut[cmap->start + i].blue = cmap->blue[i]; } return gamma_lut; } static int setcmap_atomic(struct fb_cmap *cmap, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_device *dev = fb_helper->dev; struct drm_property_blob *gamma_lut = NULL; struct drm_modeset_acquire_ctx ctx; struct drm_crtc_state *crtc_state; struct drm_atomic_state *state; struct drm_mode_set *modeset; struct drm_crtc *crtc; u16 *r, *g, *b; bool replaced; int ret = 0; drm_modeset_acquire_init(&ctx, 0); state = drm_atomic_state_alloc(dev); if (!state) { ret = -ENOMEM; goto out_ctx; } state->acquire_ctx = &ctx; retry: drm_client_for_each_modeset(modeset, &fb_helper->client) { crtc = modeset->crtc; if (!gamma_lut) gamma_lut = setcmap_new_gamma_lut(crtc, cmap); if (IS_ERR(gamma_lut)) { ret = PTR_ERR(gamma_lut); gamma_lut = NULL; goto out_state; } crtc_state = drm_atomic_get_crtc_state(state, crtc); if (IS_ERR(crtc_state)) { ret = PTR_ERR(crtc_state); goto out_state; } /* * FIXME: This always uses gamma_lut. Some HW have only * degamma_lut, in which case we should reset gamma_lut and set * degamma_lut. See drm_crtc_legacy_gamma_set(). */ replaced = drm_property_replace_blob(&crtc_state->degamma_lut, NULL); replaced |= drm_property_replace_blob(&crtc_state->ctm, NULL); replaced |= drm_property_replace_blob(&crtc_state->gamma_lut, gamma_lut); crtc_state->color_mgmt_changed |= replaced; } ret = drm_atomic_commit(state); if (ret) goto out_state; drm_client_for_each_modeset(modeset, &fb_helper->client) { crtc = modeset->crtc; r = crtc->gamma_store; g = r + crtc->gamma_size; b = g + crtc->gamma_size; memcpy(r + cmap->start, cmap->red, cmap->len * sizeof(*r)); memcpy(g + cmap->start, cmap->green, cmap->len * sizeof(*g)); memcpy(b + cmap->start, cmap->blue, cmap->len * sizeof(*b)); } out_state: if (ret == -EDEADLK) goto backoff; drm_property_blob_put(gamma_lut); drm_atomic_state_put(state); out_ctx: drm_modeset_drop_locks(&ctx); drm_modeset_acquire_fini(&ctx); return ret; backoff: drm_atomic_state_clear(state); drm_modeset_backoff(&ctx); goto retry; } /** * drm_fb_helper_setcmap - implementation for &fb_ops.fb_setcmap * @cmap: cmap to set * @info: fbdev registered by the helper */ int drm_fb_helper_setcmap(struct fb_cmap *cmap, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_device *dev = fb_helper->dev; int ret; if (oops_in_progress) return -EBUSY; mutex_lock(&fb_helper->lock); if (!drm_master_internal_acquire(dev)) { ret = -EBUSY; goto unlock; } mutex_lock(&fb_helper->client.modeset_mutex); if (info->fix.visual == FB_VISUAL_TRUECOLOR) ret = setcmap_pseudo_palette(cmap, info); else if (drm_drv_uses_atomic_modeset(fb_helper->dev)) ret = setcmap_atomic(cmap, info); else ret = setcmap_legacy(cmap, info); mutex_unlock(&fb_helper->client.modeset_mutex); drm_master_internal_release(dev); unlock: mutex_unlock(&fb_helper->lock); return ret; } EXPORT_SYMBOL(drm_fb_helper_setcmap); /** * drm_fb_helper_ioctl - legacy ioctl implementation * @info: fbdev registered by the helper * @cmd: ioctl command * @arg: ioctl argument * * A helper to implement the standard fbdev ioctl. Only * FBIO_WAITFORVSYNC is implemented for now. */ int drm_fb_helper_ioctl(struct fb_info *info, unsigned int cmd, unsigned long arg) { struct drm_fb_helper *fb_helper = info->par; struct drm_device *dev = fb_helper->dev; struct drm_crtc *crtc; int ret = 0; mutex_lock(&fb_helper->lock); if (!drm_master_internal_acquire(dev)) { ret = -EBUSY; goto unlock; } switch (cmd) { case FBIO_WAITFORVSYNC: /* * Only consider the first CRTC. * * This ioctl is supposed to take the CRTC number as * an argument, but in fbdev times, what that number * was supposed to be was quite unclear, different * drivers were passing that argument differently * (some by reference, some by value), and most of the * userspace applications were just hardcoding 0 as an * argument. * * The first CRTC should be the integrated panel on * most drivers, so this is the best choice we can * make. If we're not smart enough here, one should * just consider switch the userspace to KMS. */ crtc = fb_helper->client.modesets[0].crtc; /* * Only wait for a vblank event if the CRTC is * enabled, otherwise just don't do anythintg, * not even report an error. */ ret = drm_crtc_vblank_get(crtc); if (!ret) { drm_crtc_wait_one_vblank(crtc); drm_crtc_vblank_put(crtc); } ret = 0; break; default: ret = -ENOTTY; } drm_master_internal_release(dev); unlock: mutex_unlock(&fb_helper->lock); return ret; } EXPORT_SYMBOL(drm_fb_helper_ioctl); static bool drm_fb_pixel_format_equal(const struct fb_var_screeninfo *var_1, const struct fb_var_screeninfo *var_2) { return var_1->bits_per_pixel == var_2->bits_per_pixel && var_1->grayscale == var_2->grayscale && var_1->red.offset == var_2->red.offset && var_1->red.length == var_2->red.length && var_1->red.msb_right == var_2->red.msb_right && var_1->green.offset == var_2->green.offset && var_1->green.length == var_2->green.length && var_1->green.msb_right == var_2->green.msb_right && var_1->blue.offset == var_2->blue.offset && var_1->blue.length == var_2->blue.length && var_1->blue.msb_right == var_2->blue.msb_right && var_1->transp.offset == var_2->transp.offset && var_1->transp.length == var_2->transp.length && var_1->transp.msb_right == var_2->transp.msb_right; } static void drm_fb_helper_fill_pixel_fmt(struct fb_var_screeninfo *var, const struct drm_format_info *format) { u8 depth = format->depth; if (format->is_color_indexed) { var->red.offset = 0; var->green.offset = 0; var->blue.offset = 0; var->red.length = depth; var->green.length = depth; var->blue.length = depth; var->transp.offset = 0; var->transp.length = 0; return; } switch (depth) { case 15: var->red.offset = 10; var->green.offset = 5; var->blue.offset = 0; var->red.length = 5; var->green.length = 5; var->blue.length = 5; var->transp.offset = 15; var->transp.length = 1; break; case 16: var->red.offset = 11; var->green.offset = 5; var->blue.offset = 0; var->red.length = 5; var->green.length = 6; var->blue.length = 5; var->transp.offset = 0; break; case 24: var->red.offset = 16; var->green.offset = 8; var->blue.offset = 0; var->red.length = 8; var->green.length = 8; var->blue.length = 8; var->transp.offset = 0; var->transp.length = 0; break; case 32: var->red.offset = 16; var->green.offset = 8; var->blue.offset = 0; var->red.length = 8; var->green.length = 8; var->blue.length = 8; var->transp.offset = 24; var->transp.length = 8; break; default: break; } } static void __fill_var(struct fb_var_screeninfo *var, struct fb_info *info, struct drm_framebuffer *fb) { int i; var->xres_virtual = fb->width; var->yres_virtual = fb->height; var->accel_flags = 0; var->bits_per_pixel = drm_format_info_bpp(fb->format, 0); var->height = info->var.height; var->width = info->var.width; var->left_margin = var->right_margin = 0; var->upper_margin = var->lower_margin = 0; var->hsync_len = var->vsync_len = 0; var->sync = var->vmode = 0; var->rotate = 0; var->colorspace = 0; for (i = 0; i < 4; i++) var->reserved[i] = 0; } /** * drm_fb_helper_check_var - implementation for &fb_ops.fb_check_var * @var: screeninfo to check * @info: fbdev registered by the helper */ int drm_fb_helper_check_var(struct fb_var_screeninfo *var, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_framebuffer *fb = fb_helper->fb; const struct drm_format_info *format = fb->format; struct drm_device *dev = fb_helper->dev; unsigned int bpp; if (in_dbg_master()) return -EINVAL; if (var->pixclock != 0) { drm_dbg_kms(dev, "fbdev emulation doesn't support changing the pixel clock, value of pixclock is ignored\n"); var->pixclock = 0; } switch (format->format) { case DRM_FORMAT_C1: case DRM_FORMAT_C2: case DRM_FORMAT_C4: /* supported format with sub-byte pixels */ break; default: if ((drm_format_info_block_width(format, 0) > 1) || (drm_format_info_block_height(format, 0) > 1)) return -EINVAL; break; } /* * Changes struct fb_var_screeninfo are currently not pushed back * to KMS, hence fail if different settings are requested. */ bpp = drm_format_info_bpp(format, 0); if (var->bits_per_pixel > bpp || var->xres > fb->width || var->yres > fb->height || var->xres_virtual > fb->width || var->yres_virtual > fb->height) { drm_dbg_kms(dev, "fb requested width/height/bpp can't fit in current fb " "request %dx%d-%d (virtual %dx%d) > %dx%d-%d\n", var->xres, var->yres, var->bits_per_pixel, var->xres_virtual, var->yres_virtual, fb->width, fb->height, bpp); return -EINVAL; } __fill_var(var, info, fb); /* * fb_pan_display() validates this, but fb_set_par() doesn't and just * falls over. Note that __fill_var above adjusts y/res_virtual. */ if (var->yoffset > var->yres_virtual - var->yres || var->xoffset > var->xres_virtual - var->xres) return -EINVAL; /* We neither support grayscale nor FOURCC (also stored in here). */ if (var->grayscale > 0) return -EINVAL; if (var->nonstd) return -EINVAL; /* * Workaround for SDL 1.2, which is known to be setting all pixel format * fields values to zero in some cases. We treat this situation as a * kind of "use some reasonable autodetected values". */ if (!var->red.offset && !var->green.offset && !var->blue.offset && !var->transp.offset && !var->red.length && !var->green.length && !var->blue.length && !var->transp.length && !var->red.msb_right && !var->green.msb_right && !var->blue.msb_right && !var->transp.msb_right) { drm_fb_helper_fill_pixel_fmt(var, format); } /* * drm fbdev emulation doesn't support changing the pixel format at all, * so reject all pixel format changing requests. */ if (!drm_fb_pixel_format_equal(var, &info->var)) { drm_dbg_kms(dev, "fbdev emulation doesn't support changing the pixel format\n"); return -EINVAL; } return 0; } EXPORT_SYMBOL(drm_fb_helper_check_var); /** * drm_fb_helper_set_par - implementation for &fb_ops.fb_set_par * @info: fbdev registered by the helper * * This will let fbcon do the mode init and is called at initialization time by * the fbdev core when registering the driver, and later on through the hotplug * callback. */ int drm_fb_helper_set_par(struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct fb_var_screeninfo *var = &info->var; bool force; if (oops_in_progress) return -EBUSY; /* * Normally we want to make sure that a kms master takes precedence over * fbdev, to avoid fbdev flickering and occasionally stealing the * display status. But Xorg first sets the vt back to text mode using * the KDSET IOCTL with KD_TEXT, and only after that drops the master * status when exiting. * * In the past this was caught by drm_fb_helper_lastclose(), but on * modern systems where logind always keeps a drm fd open to orchestrate * the vt switching, this doesn't work. * * To not break the userspace ABI we have this special case here, which * is only used for the above case. Everything else uses the normal * commit function, which ensures that we never steal the display from * an active drm master. */ force = var->activate & FB_ACTIVATE_KD_TEXT; __drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper, force); return 0; } EXPORT_SYMBOL(drm_fb_helper_set_par); static void pan_set(struct drm_fb_helper *fb_helper, int dx, int dy) { struct drm_mode_set *mode_set; mutex_lock(&fb_helper->client.modeset_mutex); drm_client_for_each_modeset(mode_set, &fb_helper->client) { mode_set->x += dx; mode_set->y += dy; } mutex_unlock(&fb_helper->client.modeset_mutex); } static int pan_display_atomic(struct fb_var_screeninfo *var, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; int ret, dx, dy; dx = var->xoffset - info->var.xoffset; dy = var->yoffset - info->var.yoffset; pan_set(fb_helper, dx, dy); ret = drm_client_modeset_commit_locked(&fb_helper->client); if (!ret) { info->var.xoffset = var->xoffset; info->var.yoffset = var->yoffset; } else pan_set(fb_helper, -dx, -dy); return ret; } static int pan_display_legacy(struct fb_var_screeninfo *var, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_client_dev *client = &fb_helper->client; struct drm_mode_set *modeset; int ret = 0; mutex_lock(&client->modeset_mutex); drm_modeset_lock_all(fb_helper->dev); drm_client_for_each_modeset(modeset, client) { modeset->x = var->xoffset; modeset->y = var->yoffset; if (modeset->num_connectors) { ret = drm_mode_set_config_internal(modeset); if (!ret) { info->var.xoffset = var->xoffset; info->var.yoffset = var->yoffset; } } } drm_modeset_unlock_all(fb_helper->dev); mutex_unlock(&client->modeset_mutex); return ret; } /** * drm_fb_helper_pan_display - implementation for &fb_ops.fb_pan_display * @var: updated screen information * @info: fbdev registered by the helper */ int drm_fb_helper_pan_display(struct fb_var_screeninfo *var, struct fb_info *info) { struct drm_fb_helper *fb_helper = info->par; struct drm_device *dev = fb_helper->dev; int ret; if (oops_in_progress) return -EBUSY; mutex_lock(&fb_helper->lock); if (!drm_master_internal_acquire(dev)) { ret = -EBUSY; goto unlock; } if (drm_drv_uses_atomic_modeset(dev)) ret = pan_display_atomic(var, info); else ret = pan_display_legacy(var, info); drm_master_internal_release(dev); unlock: mutex_unlock(&fb_helper->lock); return ret; } EXPORT_SYMBOL(drm_fb_helper_pan_display); static uint32_t drm_fb_helper_find_format(struct drm_fb_helper *fb_helper, const uint32_t *formats, size_t format_count, unsigned int color_mode) { struct drm_device *dev = fb_helper->dev; uint32_t format; size_t i; format = drm_driver_color_mode_format(dev, color_mode); if (!format) { drm_info(dev, "unsupported color mode of %d\n", color_mode); return DRM_FORMAT_INVALID; } for (i = 0; i < format_count; ++i) { if (formats[i] == format) return format; } drm_warn(dev, "format %p4cc not supported\n", &format); return DRM_FORMAT_INVALID; } static int __drm_fb_helper_find_sizes(struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes) { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; int crtc_count = 0; struct drm_connector_list_iter conn_iter; struct drm_connector *connector; struct drm_mode_set *mode_set; uint32_t surface_format = DRM_FORMAT_INVALID; const struct drm_format_info *info; memset(sizes, 0, sizeof(*sizes)); sizes->fb_width = (u32)-1; sizes->fb_height = (u32)-1; drm_client_for_each_modeset(mode_set, client) { struct drm_crtc *crtc = mode_set->crtc; struct drm_plane *plane = crtc->primary; drm_dbg_kms(dev, "test CRTC %u primary plane\n", drm_crtc_index(crtc)); drm_connector_list_iter_begin(fb_helper->dev, &conn_iter); drm_client_for_each_connector_iter(connector, &conn_iter) { struct drm_cmdline_mode *cmdline_mode = &connector->cmdline_mode; if (!cmdline_mode->bpp_specified) continue; surface_format = drm_fb_helper_find_format(fb_helper, plane->format_types, plane->format_count, cmdline_mode->bpp); if (surface_format != DRM_FORMAT_INVALID) break; /* found supported format */ } drm_connector_list_iter_end(&conn_iter); if (surface_format != DRM_FORMAT_INVALID) break; /* found supported format */ /* try preferred color mode */ surface_format = drm_fb_helper_find_format(fb_helper, plane->format_types, plane->format_count, fb_helper->preferred_bpp); if (surface_format != DRM_FORMAT_INVALID) break; /* found supported format */ } if (surface_format == DRM_FORMAT_INVALID) { /* * If none of the given color modes works, fall back * to XRGB8888. Drivers are expected to provide this * format for compatibility with legacy applications. */ drm_warn(dev, "No compatible format found\n"); surface_format = drm_driver_legacy_fb_format(dev, 32, 24); } info = drm_format_info(surface_format); sizes->surface_bpp = drm_format_info_bpp(info, 0); sizes->surface_depth = info->depth; /* first up get a count of crtcs now in use and new min/maxes width/heights */ crtc_count = 0; drm_client_for_each_modeset(mode_set, client) { struct drm_display_mode *desired_mode; int x, y, j; /* in case of tile group, are we the last tile vert or horiz? * If no tile group you are always the last one both vertically * and horizontally */ bool lastv = true, lasth = true; desired_mode = mode_set->mode; if (!desired_mode) continue; crtc_count++; x = mode_set->x; y = mode_set->y; sizes->surface_width = max_t(u32, desired_mode->hdisplay + x, sizes->surface_width); sizes->surface_height = max_t(u32, desired_mode->vdisplay + y, sizes->surface_height); for (j = 0; j < mode_set->num_connectors; j++) { struct drm_connector *connector = mode_set->connectors[j]; if (connector->has_tile && desired_mode->hdisplay == connector->tile_h_size && desired_mode->vdisplay == connector->tile_v_size) { lasth = (connector->tile_h_loc == (connector->num_h_tile - 1)); lastv = (connector->tile_v_loc == (connector->num_v_tile - 1)); /* cloning to multiple tiles is just crazy-talk, so: */ break; } } if (lasth) sizes->fb_width = min_t(u32, desired_mode->hdisplay + x, sizes->fb_width); if (lastv) sizes->fb_height = min_t(u32, desired_mode->vdisplay + y, sizes->fb_height); } if (crtc_count == 0 || sizes->fb_width == -1 || sizes->fb_height == -1) { drm_info(dev, "Cannot find any crtc or sizes\n"); return -EAGAIN; } return 0; } static int drm_fb_helper_find_sizes(struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes) { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; struct drm_mode_config *config = &dev->mode_config; int ret; mutex_lock(&client->modeset_mutex); ret = __drm_fb_helper_find_sizes(fb_helper, sizes); mutex_unlock(&client->modeset_mutex); if (ret) return ret; /* Handle our overallocation */ sizes->surface_height *= drm_fbdev_overalloc; sizes->surface_height /= 100; if (sizes->surface_height > config->max_height) { drm_dbg_kms(dev, "Fbdev over-allocation too large; clamping height to %d\n", config->max_height); sizes->surface_height = config->max_height; } return 0; } /* * Allocates the backing storage and sets up the fbdev info structure through * the ->fbdev_probe callback. */ static int drm_fb_helper_single_fb_probe(struct drm_fb_helper *fb_helper) { struct drm_client_dev *client = &fb_helper->client; struct drm_device *dev = fb_helper->dev; struct drm_fb_helper_surface_size sizes; struct fb_info *info; int ret; if (drm_WARN_ON(dev, !dev->driver->fbdev_probe)) return -EINVAL; ret = drm_fb_helper_find_sizes(fb_helper, &sizes); if (ret) { /* First time: disable all crtc's.. */ if (!fb_helper->deferred_setup) drm_client_modeset_commit(client); return ret; } /* push down into drivers */ ret = dev->driver->fbdev_probe(fb_helper, &sizes); if (ret < 0) return ret; strcpy(fb_helper->fb->comm, "[fbcon]"); info = fb_helper->info; /* Set the fb info for vgaswitcheroo clients. Does nothing otherwise. */ if (dev_is_pci(info->device)) vga_switcheroo_client_fb_set(to_pci_dev(info->device), info); return 0; } static void drm_fb_helper_fill_fix(struct fb_info *info, uint32_t pitch, bool is_color_indexed) { info->fix.type = FB_TYPE_PACKED_PIXELS; info->fix.visual = is_color_indexed ? FB_VISUAL_PSEUDOCOLOR : FB_VISUAL_TRUECOLOR; info->fix.mmio_start = 0; info->fix.mmio_len = 0; info->fix.type_aux = 0; info->fix.xpanstep = 1; /* doing it in hw */ info->fix.ypanstep = 1; /* doing it in hw */ info->fix.ywrapstep = 0; info->fix.accel = FB_ACCEL_NONE; info->fix.line_length = pitch; } static void drm_fb_helper_fill_var(struct fb_info *info, struct drm_fb_helper *fb_helper, uint32_t fb_width, uint32_t fb_height) { struct drm_framebuffer *fb = fb_helper->fb; const struct drm_format_info *format = fb->format; switch (format->format) { case DRM_FORMAT_C1: case DRM_FORMAT_C2: case DRM_FORMAT_C4: /* supported format with sub-byte pixels */ break; default: WARN_ON((drm_format_info_block_width(format, 0) > 1) || (drm_format_info_block_height(format, 0) > 1)); break; } info->pseudo_palette = fb_helper->pseudo_palette; info->var.xoffset = 0; info->var.yoffset = 0; __fill_var(&info->var, info, fb); info->var.activate = FB_ACTIVATE_NOW; drm_fb_helper_fill_pixel_fmt(&info->var, format); info->var.xres = fb_width; info->var.yres = fb_height; } /** * drm_fb_helper_fill_info - initializes fbdev information * @info: fbdev instance to set up * @fb_helper: fb helper instance to use as template * @sizes: describes fbdev size and scanout surface size * * Sets up the variable and fixed fbdev metainformation from the given fb helper * instance and the drm framebuffer allocated in &drm_fb_helper.fb. * * Drivers should call this (or their equivalent setup code) from their * &drm_driver.fbdev_probe callback after having allocated the fbdev * backing storage framebuffer. */ void drm_fb_helper_fill_info(struct fb_info *info, struct drm_fb_helper *fb_helper, struct drm_fb_helper_surface_size *sizes) { struct drm_framebuffer *fb = fb_helper->fb; drm_fb_helper_fill_fix(info, fb->pitches[0], fb->format->is_color_indexed); drm_fb_helper_fill_var(info, fb_helper, sizes->fb_width, sizes->fb_height); info->par = fb_helper; /* * The DRM drivers fbdev emulation device name can be confusing if the * driver name also has a "drm" suffix on it. Leading to names such as * "simpledrmdrmfb" in /proc/fb. Unfortunately, it's an uAPI and can't * be changed due user-space tools (e.g: pm-utils) matching against it. */ snprintf(info->fix.id, sizeof(info->fix.id), "%sdrmfb", fb_helper->dev->driver->name); } EXPORT_SYMBOL(drm_fb_helper_fill_info); /* * This is a continuation of drm_setup_crtcs() that sets up anything related * to the framebuffer. During initialization, drm_setup_crtcs() is called before * the framebuffer has been allocated (fb_helper->fb and fb_helper->info). * So, any setup that touches those fields needs to be done here instead of in * drm_setup_crtcs(). */ static void drm_setup_crtcs_fb(struct drm_fb_helper *fb_helper) { struct drm_client_dev *client = &fb_helper->client; struct drm_connector_list_iter conn_iter; struct fb_info *info = fb_helper->info; unsigned int rotation, sw_rotations = 0; struct drm_connector *connector; struct drm_mode_set *modeset; mutex_lock(&client->modeset_mutex); drm_client_for_each_modeset(modeset, client) { if (!modeset->num_connectors) continue; modeset->fb = fb_helper->fb; if (drm_client_rotation(modeset, &rotation)) /* Rotating in hardware, fbcon should not rotate */ sw_rotations |= DRM_MODE_ROTATE_0; else sw_rotations |= rotation; } mutex_unlock(&client->modeset_mutex); drm_connector_list_iter_begin(fb_helper->dev, &conn_iter); drm_client_for_each_connector_iter(connector, &conn_iter) { /* use first connected connector for the physical dimensions */ if (connector->status == connector_status_connected) { info->var.width = connector->display_info.width_mm; info->var.height = connector->display_info.height_mm; break; } } drm_connector_list_iter_end(&conn_iter); switch (sw_rotations) { case DRM_MODE_ROTATE_0: info->fbcon_rotate_hint = FB_ROTATE_UR; break; case DRM_MODE_ROTATE_90: info->fbcon_rotate_hint = FB_ROTATE_CCW; break; case DRM_MODE_ROTATE_180: info->fbcon_rotate_hint = FB_ROTATE_UD; break; case DRM_MODE_ROTATE_270: info->fbcon_rotate_hint = FB_ROTATE_CW; break; default: /* * Multiple bits are set / multiple rotations requested * fbcon cannot handle separate rotation settings per * output, so fallback to unrotated. */ info->fbcon_rotate_hint = FB_ROTATE_UR; } } /* Note: Drops fb_helper->lock before returning. */ static int __drm_fb_helper_initial_config_and_unlock(struct drm_fb_helper *fb_helper) { struct drm_device *dev = fb_helper->dev; struct fb_info *info; unsigned int width, height; int ret; width = dev->mode_config.max_width; height = dev->mode_config.max_height; drm_client_modeset_probe(&fb_helper->client, width, height); ret = drm_fb_helper_single_fb_probe(fb_helper); if (ret < 0) { if (ret == -EAGAIN) { fb_helper->deferred_setup = true; ret = 0; } mutex_unlock(&fb_helper->lock); return ret; } drm_setup_crtcs_fb(fb_helper); fb_helper->deferred_setup = false; info = fb_helper->info; info->var.pixclock = 0; /* Need to drop locks to avoid recursive deadlock in * register_framebuffer. This is ok because the only thing left to do is * register the fbdev emulation instance in kernel_fb_helper_list. */ mutex_unlock(&fb_helper->lock); ret = register_framebuffer(info); if (ret < 0) return ret; drm_info(dev, "fb%d: %s frame buffer device\n", info->node, info->fix.id); mutex_lock(&kernel_fb_helper_lock); if (list_empty(&kernel_fb_helper_list)) register_sysrq_key('v', &sysrq_drm_fb_helper_restore_op); list_add(&fb_helper->kernel_fb_list, &kernel_fb_helper_list); mutex_unlock(&kernel_fb_helper_lock); return 0; } /** * drm_fb_helper_initial_config - setup a sane initial connector configuration * @fb_helper: fb_helper device struct * * Scans the CRTCs and connectors and tries to put together an initial setup. * At the moment, this is a cloned configuration across all heads with * a new framebuffer object as the backing store. * * Note that this also registers the fbdev and so allows userspace to call into * the driver through the fbdev interfaces. * * This function will call down into the &drm_driver.fbdev_probe callback * to let the driver allocate and initialize the fbdev info structure and the * drm framebuffer used to back the fbdev. drm_fb_helper_fill_info() is provided * as a helper to setup simple default values for the fbdev info structure. * * HANG DEBUGGING: * * When you have fbcon support built-in or already loaded, this function will do * a full modeset to setup the fbdev console. Due to locking misdesign in the * VT/fbdev subsystem that entire modeset sequence has to be done while holding * console_lock. Until console_unlock is called no dmesg lines will be sent out * to consoles, not even serial console. This means when your driver crashes, * you will see absolutely nothing else but a system stuck in this function, * with no further output. Any kind of printk() you place within your own driver * or in the drm core modeset code will also never show up. * * Standard debug practice is to run the fbcon setup without taking the * console_lock as a hack, to be able to see backtraces and crashes on the * serial line. This can be done by setting the fb.lockless_register_fb=1 kernel * cmdline option. * * The other option is to just disable fbdev emulation since very likely the * first modeset from userspace will crash in the same way, and is even easier * to debug. This can be done by setting the drm_kms_helper.fbdev_emulation=0 * kernel cmdline option. * * RETURNS: * Zero if everything went ok, nonzero otherwise. */ int drm_fb_helper_initial_config(struct drm_fb_helper *fb_helper) { int ret; if (!drm_fbdev_emulation) return 0; mutex_lock(&fb_helper->lock); ret = __drm_fb_helper_initial_config_and_unlock(fb_helper); return ret; } EXPORT_SYMBOL(drm_fb_helper_initial_config); /** * drm_fb_helper_hotplug_event - respond to a hotplug notification by * probing all the outputs attached to the fb * @fb_helper: driver-allocated fbdev helper, can be NULL * * Scan the connectors attached to the fb_helper and try to put together a * setup after notification of a change in output configuration. * * Called at runtime, takes the mode config locks to be able to check/change the * modeset configuration. Must be run from process context (which usually means * either the output polling work or a work item launched from the driver's * hotplug interrupt). * * Note that drivers may call this even before calling * drm_fb_helper_initial_config but only after drm_fb_helper_init. This allows * for a race-free fbcon setup and will make sure that the fbdev emulation will * not miss any hotplug events. * * RETURNS: * 0 on success and a non-zero error code otherwise. */ int drm_fb_helper_hotplug_event(struct drm_fb_helper *fb_helper) { int err = 0; if (!drm_fbdev_emulation || !fb_helper) return 0; mutex_lock(&fb_helper->lock); if (fb_helper->deferred_setup) { err = __drm_fb_helper_initial_config_and_unlock(fb_helper); return err; } if (!fb_helper->fb || !drm_master_internal_acquire(fb_helper->dev)) { fb_helper->delayed_hotplug = true; mutex_unlock(&fb_helper->lock); return err; } drm_master_internal_release(fb_helper->dev); drm_dbg_kms(fb_helper->dev, "\n"); drm_client_modeset_probe(&fb_helper->client, fb_helper->fb->width, fb_helper->fb->height); drm_setup_crtcs_fb(fb_helper); mutex_unlock(&fb_helper->lock); drm_fb_helper_set_par(fb_helper->info); return 0; } EXPORT_SYMBOL(drm_fb_helper_hotplug_event); /** * drm_fb_helper_lastclose - DRM driver lastclose helper for fbdev emulation * @dev: DRM device * * This function is obsolete. Call drm_fb_helper_restore_fbdev_mode_unlocked() * instead. */ void drm_fb_helper_lastclose(struct drm_device *dev) { drm_fb_helper_restore_fbdev_mode_unlocked(dev->fb_helper); } EXPORT_SYMBOL(drm_fb_helper_lastclose); |
| 8 1 1 1 1 1 8 8 5 5 5 4 4 4 4 19 15 19 4 1 5 5 5 5 5 18 4 4 4 15 41 42 23 25 25 25 25 14 19 19 15 19 6 19 4 6 19 25 25 25 19 19 25 18 25 25 25 42 42 13 11 2 12 42 42 42 42 42 42 6 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 106 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2010 Kent Overstreet <kent.overstreet@gmail.com> * Copyright (C) 2014 Datera Inc. */ #include "bcachefs.h" #include "alloc_background.h" #include "alloc_foreground.h" #include "backpointers.h" #include "bkey_methods.h" #include "bkey_buf.h" #include "btree_journal_iter.h" #include "btree_key_cache.h" #include "btree_locking.h" #include "btree_node_scan.h" #include "btree_update_interior.h" #include "btree_io.h" #include "btree_gc.h" #include "buckets.h" #include "clock.h" #include "debug.h" #include "disk_accounting.h" #include "ec.h" #include "enumerated_ref.h" #include "error.h" #include "extents.h" #include "journal.h" #include "keylist.h" #include "move.h" #include "progress.h" #include "recovery_passes.h" #include "reflink.h" #include "recovery.h" #include "replicas.h" #include "super-io.h" #include "trace.h" #include <linux/slab.h> #include <linux/bitops.h> #include <linux/freezer.h> #include <linux/kthread.h> #include <linux/preempt.h> #include <linux/rcupdate.h> #include <linux/sched/task.h> #define DROP_THIS_NODE 10 #define DROP_PREV_NODE 11 #define DID_FILL_FROM_SCAN 12 /* * Returns true if it's a btree we can easily reconstruct, or otherwise won't * cause data loss if it's missing: */ static bool btree_id_important(enum btree_id btree) { if (btree_id_is_alloc(btree)) return false; switch (btree) { case BTREE_ID_quotas: case BTREE_ID_snapshot_trees: case BTREE_ID_logged_ops: case BTREE_ID_rebalance_work: case BTREE_ID_subvolume_children: return false; default: return true; } } static const char * const bch2_gc_phase_strs[] = { #define x(n) #n, GC_PHASES() #undef x NULL }; void bch2_gc_pos_to_text(struct printbuf *out, struct gc_pos *p) { prt_str(out, bch2_gc_phase_strs[p->phase]); prt_char(out, ' '); bch2_btree_id_level_to_text(out, p->btree, p->level); prt_char(out, ' '); bch2_bpos_to_text(out, p->pos); } static struct bkey_s unsafe_bkey_s_c_to_s(struct bkey_s_c k) { return (struct bkey_s) {{{ (struct bkey *) k.k, (struct bch_val *) k.v }}}; } static inline void __gc_pos_set(struct bch_fs *c, struct gc_pos new_pos) { preempt_disable(); write_seqcount_begin(&c->gc_pos_lock); c->gc_pos = new_pos; write_seqcount_end(&c->gc_pos_lock); preempt_enable(); } static inline void gc_pos_set(struct bch_fs *c, struct gc_pos new_pos) { BUG_ON(gc_pos_cmp(new_pos, c->gc_pos) < 0); __gc_pos_set(c, new_pos); } static void btree_ptr_to_v2(struct btree *b, struct bkey_i_btree_ptr_v2 *dst) { switch (b->key.k.type) { case KEY_TYPE_btree_ptr: { struct bkey_i_btree_ptr *src = bkey_i_to_btree_ptr(&b->key); dst->k.p = src->k.p; dst->v.mem_ptr = 0; dst->v.seq = b->data->keys.seq; dst->v.sectors_written = 0; dst->v.flags = 0; dst->v.min_key = b->data->min_key; set_bkey_val_bytes(&dst->k, sizeof(dst->v) + bkey_val_bytes(&src->k)); memcpy(dst->v.start, src->v.start, bkey_val_bytes(&src->k)); break; } case KEY_TYPE_btree_ptr_v2: bkey_copy(&dst->k_i, &b->key); break; default: BUG(); } } static int set_node_min(struct bch_fs *c, struct btree *b, struct bpos new_min) { struct bkey_i_btree_ptr_v2 *new; int ret; if (c->opts.verbose) { struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, " -> "); bch2_bpos_to_text(&buf, new_min); bch_info(c, "%s(): %s", __func__, buf.buf); printbuf_exit(&buf); } new = kmalloc_array(BKEY_BTREE_PTR_U64s_MAX, sizeof(u64), GFP_KERNEL); if (!new) return bch_err_throw(c, ENOMEM_gc_repair_key); btree_ptr_to_v2(b, new); b->data->min_key = new_min; new->v.min_key = new_min; SET_BTREE_PTR_RANGE_UPDATED(&new->v, true); ret = bch2_journal_key_insert_take(c, b->c.btree_id, b->c.level + 1, &new->k_i); if (ret) { kfree(new); return ret; } bch2_btree_node_drop_keys_outside_node(b); bkey_copy(&b->key, &new->k_i); return 0; } static int set_node_max(struct bch_fs *c, struct btree *b, struct bpos new_max) { struct bkey_i_btree_ptr_v2 *new; int ret; if (c->opts.verbose) { struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, " -> "); bch2_bpos_to_text(&buf, new_max); bch_info(c, "%s(): %s", __func__, buf.buf); printbuf_exit(&buf); } ret = bch2_journal_key_delete(c, b->c.btree_id, b->c.level + 1, b->key.k.p); if (ret) return ret; new = kmalloc_array(BKEY_BTREE_PTR_U64s_MAX, sizeof(u64), GFP_KERNEL); if (!new) return bch_err_throw(c, ENOMEM_gc_repair_key); btree_ptr_to_v2(b, new); b->data->max_key = new_max; new->k.p = new_max; SET_BTREE_PTR_RANGE_UPDATED(&new->v, true); ret = bch2_journal_key_insert_take(c, b->c.btree_id, b->c.level + 1, &new->k_i); if (ret) { kfree(new); return ret; } bch2_btree_node_drop_keys_outside_node(b); mutex_lock(&c->btree_cache.lock); __bch2_btree_node_hash_remove(&c->btree_cache, b); bkey_copy(&b->key, &new->k_i); ret = __bch2_btree_node_hash_insert(&c->btree_cache, b); BUG_ON(ret); mutex_unlock(&c->btree_cache.lock); return 0; } static int btree_check_node_boundaries(struct btree_trans *trans, struct btree *b, struct btree *prev, struct btree *cur, struct bpos *pulled_from_scan) { struct bch_fs *c = trans->c; struct bpos expected_start = !prev ? b->data->min_key : bpos_successor(prev->key.k.p); struct printbuf buf = PRINTBUF; int ret = 0; BUG_ON(b->key.k.type == KEY_TYPE_btree_ptr_v2 && !bpos_eq(bkey_i_to_btree_ptr_v2(&b->key)->v.min_key, b->data->min_key)); if (bpos_eq(expected_start, cur->data->min_key)) return 0; prt_printf(&buf, " at "); bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); prt_printf(&buf, ":\nparent: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); if (prev) { prt_printf(&buf, "\nprev: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&prev->key)); } prt_str(&buf, "\nnext: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&cur->key)); if (bpos_lt(expected_start, cur->data->min_key)) { /* gap */ if (b->c.level == 1 && bpos_lt(*pulled_from_scan, cur->data->min_key)) { ret = bch2_get_scanned_nodes(c, b->c.btree_id, 0, expected_start, bpos_predecessor(cur->data->min_key)); if (ret) goto err; *pulled_from_scan = cur->data->min_key; ret = DID_FILL_FROM_SCAN; } else { if (mustfix_fsck_err(trans, btree_node_topology_bad_min_key, "btree node with incorrect min_key%s", buf.buf)) ret = set_node_min(c, cur, expected_start); } } else { /* overlap */ if (prev && BTREE_NODE_SEQ(cur->data) > BTREE_NODE_SEQ(prev->data)) { /* cur overwrites prev */ if (bpos_ge(prev->data->min_key, cur->data->min_key)) { /* fully? */ if (mustfix_fsck_err(trans, btree_node_topology_overwritten_by_next_node, "btree node overwritten by next node%s", buf.buf)) ret = DROP_PREV_NODE; } else { if (mustfix_fsck_err(trans, btree_node_topology_bad_max_key, "btree node with incorrect max_key%s", buf.buf)) ret = set_node_max(c, prev, bpos_predecessor(cur->data->min_key)); } } else { if (bpos_ge(expected_start, cur->data->max_key)) { /* fully? */ if (mustfix_fsck_err(trans, btree_node_topology_overwritten_by_prev_node, "btree node overwritten by prev node%s", buf.buf)) ret = DROP_THIS_NODE; } else { if (mustfix_fsck_err(trans, btree_node_topology_bad_min_key, "btree node with incorrect min_key%s", buf.buf)) ret = set_node_min(c, cur, expected_start); } } } err: fsck_err: printbuf_exit(&buf); return ret; } static int btree_repair_node_end(struct btree_trans *trans, struct btree *b, struct btree *child, struct bpos *pulled_from_scan) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; int ret = 0; if (bpos_eq(child->key.k.p, b->key.k.p)) return 0; prt_printf(&buf, "\nat: "); bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); prt_printf(&buf, "\nparent: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); prt_str(&buf, "\nchild: "); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&child->key)); if (mustfix_fsck_err(trans, btree_node_topology_bad_max_key, "btree node with incorrect max_key%s", buf.buf)) { if (b->c.level == 1 && bpos_lt(*pulled_from_scan, b->key.k.p)) { ret = bch2_get_scanned_nodes(c, b->c.btree_id, 0, bpos_successor(child->key.k.p), b->key.k.p); if (ret) goto err; *pulled_from_scan = b->key.k.p; ret = DID_FILL_FROM_SCAN; } else { ret = set_node_max(c, child, b->key.k.p); } } err: fsck_err: printbuf_exit(&buf); return ret; } static int bch2_btree_repair_topology_recurse(struct btree_trans *trans, struct btree *b, struct bpos *pulled_from_scan) { struct bch_fs *c = trans->c; struct btree_and_journal_iter iter; struct bkey_s_c k; struct bkey_buf prev_k, cur_k; struct btree *prev = NULL, *cur = NULL; bool have_child, new_pass = false; struct printbuf buf = PRINTBUF; int ret = 0; if (!b->c.level) return 0; bch2_bkey_buf_init(&prev_k); bch2_bkey_buf_init(&cur_k); again: cur = prev = NULL; have_child = new_pass = false; bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); iter.prefetch = true; while ((k = bch2_btree_and_journal_iter_peek(&iter)).k) { BUG_ON(bpos_lt(k.k->p, b->data->min_key)); BUG_ON(bpos_gt(k.k->p, b->data->max_key)); bch2_btree_and_journal_iter_advance(&iter); bch2_bkey_buf_reassemble(&cur_k, c, k); cur = bch2_btree_node_get_noiter(trans, cur_k.k, b->c.btree_id, b->c.level - 1, false); ret = PTR_ERR_OR_ZERO(cur); printbuf_reset(&buf); bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level - 1); prt_char(&buf, ' '); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(cur_k.k)); if (bch2_err_matches(ret, EIO)) { bch2_btree_node_evict(trans, cur_k.k); cur = NULL; ret = bch2_journal_key_delete(c, b->c.btree_id, b->c.level, cur_k.k->k.p); if (ret) break; continue; } bch_err_msg(c, ret, "getting btree node"); if (ret) break; if (bch2_btree_node_is_stale(c, cur)) { bch_info(c, "btree node older than nodes found by scanning\n %s", buf.buf); six_unlock_read(&cur->c.lock); bch2_btree_node_evict(trans, cur_k.k); ret = bch2_journal_key_delete(c, b->c.btree_id, b->c.level, cur_k.k->k.p); cur = NULL; if (ret) break; continue; } ret = lockrestart_do(trans, btree_check_node_boundaries(trans, b, prev, cur, pulled_from_scan)); if (ret < 0) goto err; if (ret == DID_FILL_FROM_SCAN) { new_pass = true; ret = 0; } if (ret == DROP_THIS_NODE) { six_unlock_read(&cur->c.lock); bch2_btree_node_evict(trans, cur_k.k); ret = bch2_journal_key_delete(c, b->c.btree_id, b->c.level, cur_k.k->k.p); cur = NULL; if (ret) break; continue; } if (prev) six_unlock_read(&prev->c.lock); prev = NULL; if (ret == DROP_PREV_NODE) { bch_info(c, "dropped prev node"); bch2_btree_node_evict(trans, prev_k.k); ret = bch2_journal_key_delete(c, b->c.btree_id, b->c.level, prev_k.k->k.p); if (ret) break; bch2_btree_and_journal_iter_exit(&iter); goto again; } else if (ret) break; prev = cur; cur = NULL; bch2_bkey_buf_copy(&prev_k, c, cur_k.k); } if (!ret && !IS_ERR_OR_NULL(prev)) { BUG_ON(cur); ret = lockrestart_do(trans, btree_repair_node_end(trans, b, prev, pulled_from_scan)); if (ret == DID_FILL_FROM_SCAN) { new_pass = true; ret = 0; } } if (!IS_ERR_OR_NULL(prev)) six_unlock_read(&prev->c.lock); prev = NULL; if (!IS_ERR_OR_NULL(cur)) six_unlock_read(&cur->c.lock); cur = NULL; if (ret) goto err; bch2_btree_and_journal_iter_exit(&iter); if (new_pass) goto again; bch2_btree_and_journal_iter_init_node_iter(trans, &iter, b); iter.prefetch = true; while ((k = bch2_btree_and_journal_iter_peek(&iter)).k) { bch2_bkey_buf_reassemble(&cur_k, c, k); bch2_btree_and_journal_iter_advance(&iter); cur = bch2_btree_node_get_noiter(trans, cur_k.k, b->c.btree_id, b->c.level - 1, false); ret = PTR_ERR_OR_ZERO(cur); bch_err_msg(c, ret, "getting btree node"); if (ret) goto err; ret = bch2_btree_repair_topology_recurse(trans, cur, pulled_from_scan); six_unlock_read(&cur->c.lock); cur = NULL; if (ret == DROP_THIS_NODE) { bch2_btree_node_evict(trans, cur_k.k); ret = bch2_journal_key_delete(c, b->c.btree_id, b->c.level, cur_k.k->k.p); new_pass = true; } if (ret) goto err; have_child = true; } printbuf_reset(&buf); bch2_btree_id_level_to_text(&buf, b->c.btree_id, b->c.level); prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(&b->key)); /* * XXX: we're not passing the trans object here because we're not set up * to handle a transaction restart - this code needs to be rewritten * when we start doing online topology repair */ bch2_trans_unlock_long(trans); if (mustfix_fsck_err_on(!have_child, c, btree_node_topology_interior_node_empty, "empty interior btree node at %s", buf.buf)) ret = DROP_THIS_NODE; err: fsck_err: if (!IS_ERR_OR_NULL(prev)) six_unlock_read(&prev->c.lock); if (!IS_ERR_OR_NULL(cur)) six_unlock_read(&cur->c.lock); bch2_btree_and_journal_iter_exit(&iter); if (!ret && new_pass) goto again; BUG_ON(!ret && bch2_btree_node_check_topology(trans, b)); bch2_bkey_buf_exit(&prev_k, c); bch2_bkey_buf_exit(&cur_k, c); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } static int bch2_check_root(struct btree_trans *trans, enum btree_id btree, bool *reconstructed_root) { struct bch_fs *c = trans->c; struct btree_root *r = bch2_btree_id_root(c, btree); struct printbuf buf = PRINTBUF; int ret = 0; bch2_btree_id_to_text(&buf, btree); if (r->error) { bch_info(c, "btree root %s unreadable, must recover from scan", buf.buf); ret = bch2_btree_has_scanned_nodes(c, btree); if (ret < 0) goto err; if (!ret) { __fsck_err(trans, FSCK_CAN_FIX|(!btree_id_important(btree) ? FSCK_AUTOFIX : 0), btree_root_unreadable_and_scan_found_nothing, "no nodes found for btree %s, continue?", buf.buf); r->alive = false; r->error = 0; bch2_btree_root_alloc_fake_trans(trans, btree, 0); } else { r->alive = false; r->error = 0; bch2_btree_root_alloc_fake_trans(trans, btree, 1); bch2_shoot_down_journal_keys(c, btree, 1, BTREE_MAX_DEPTH, POS_MIN, SPOS_MAX); ret = bch2_get_scanned_nodes(c, btree, 0, POS_MIN, SPOS_MAX); if (ret) goto err; } *reconstructed_root = true; } err: fsck_err: printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } int bch2_check_topology(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); struct bpos pulled_from_scan = POS_MIN; int ret = 0; bch2_trans_srcu_unlock(trans); for (unsigned i = 0; i < btree_id_nr_alive(c) && !ret; i++) { bool reconstructed_root = false; recover: ret = lockrestart_do(trans, bch2_check_root(trans, i, &reconstructed_root)); if (ret) break; struct btree_root *r = bch2_btree_id_root(c, i); struct btree *b = r->b; btree_node_lock_nopath_nofail(trans, &b->c, SIX_LOCK_read); ret = bch2_btree_repair_topology_recurse(trans, b, &pulled_from_scan); six_unlock_read(&b->c.lock); if (ret == DROP_THIS_NODE) { mutex_lock(&c->btree_cache.lock); bch2_btree_node_hash_remove(&c->btree_cache, b); mutex_unlock(&c->btree_cache.lock); r->b = NULL; if (!reconstructed_root) { r->error = -EIO; goto recover; } struct printbuf buf = PRINTBUF; bch2_btree_id_to_text(&buf, i); bch_err(c, "empty btree root %s", buf.buf); printbuf_exit(&buf); bch2_btree_root_alloc_fake_trans(trans, i, 0); r->alive = false; ret = 0; } } bch2_trans_put(trans); return ret; } /* marking of btree keys/nodes: */ static int bch2_gc_mark_key(struct btree_trans *trans, enum btree_id btree_id, unsigned level, struct btree **prev, struct btree_iter *iter, struct bkey_s_c k, bool initial) { struct bch_fs *c = trans->c; if (iter) { struct btree_path *path = btree_iter_path(trans, iter); struct btree *b = path_l(path)->b; if (*prev != b) { int ret = bch2_btree_node_check_topology(trans, b); if (ret) return ret; } *prev = b; } struct bkey deleted = KEY(0, 0, 0); struct bkey_s_c old = (struct bkey_s_c) { &deleted, NULL }; struct printbuf buf = PRINTBUF; int ret = 0; deleted.p = k.k->p; if (initial) { BUG_ON(static_branch_unlikely(&bch2_journal_seq_verify) && k.k->bversion.lo > atomic64_read(&c->journal.seq)); if (fsck_err_on(btree_id != BTREE_ID_accounting && k.k->bversion.lo > atomic64_read(&c->key_version), trans, bkey_version_in_future, "key version number higher than recorded %llu\n%s", atomic64_read(&c->key_version), (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) atomic64_set(&c->key_version, k.k->bversion.lo); } if (mustfix_fsck_err_on(level && !bch2_dev_btree_bitmap_marked(c, k), trans, btree_bitmap_not_marked, "btree ptr not marked in member info btree allocated bitmap\n%s", (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { mutex_lock(&c->sb_lock); bch2_dev_btree_bitmap_mark(c, k); bch2_write_super(c); mutex_unlock(&c->sb_lock); } /* * We require a commit before key_trigger() because * key_trigger(BTREE_TRIGGER_GC) is not idempotant; we'll calculate the * wrong result if we run it multiple times. */ unsigned flags = !iter ? BTREE_TRIGGER_is_root : 0; ret = bch2_key_trigger(trans, btree_id, level, old, unsafe_bkey_s_c_to_s(k), BTREE_TRIGGER_check_repair|flags); if (ret) goto out; if (trans->nr_updates) { ret = bch2_trans_commit(trans, NULL, NULL, 0) ?: -BCH_ERR_transaction_restart_nested; goto out; } ret = bch2_key_trigger(trans, btree_id, level, old, unsafe_bkey_s_c_to_s(k), BTREE_TRIGGER_gc|BTREE_TRIGGER_insert|flags); out: fsck_err: printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } static int bch2_gc_btree(struct btree_trans *trans, struct progress_indicator_state *progress, enum btree_id btree, bool initial) { struct bch_fs *c = trans->c; unsigned target_depth = btree_node_type_has_triggers(__btree_node_type(0, btree)) ? 0 : 1; int ret = 0; /* We need to make sure every leaf node is readable before going RW */ if (initial) target_depth = 0; for (unsigned level = target_depth; level < BTREE_MAX_DEPTH; level++) { struct btree *prev = NULL; struct btree_iter iter; bch2_trans_node_iter_init(trans, &iter, btree, POS_MIN, 0, level, BTREE_ITER_prefetch); ret = for_each_btree_key_continue(trans, iter, 0, k, ({ bch2_progress_update_iter(trans, progress, &iter, "check_allocations"); gc_pos_set(c, gc_pos_btree(btree, level, k.k->p)); bch2_gc_mark_key(trans, btree, level, &prev, &iter, k, initial); })); if (ret) goto err; } /* root */ do { retry_root: bch2_trans_begin(trans); struct btree_iter iter; bch2_trans_node_iter_init(trans, &iter, btree, POS_MIN, 0, bch2_btree_id_root(c, btree)->b->c.level, 0); struct btree *b = bch2_btree_iter_peek_node(trans, &iter); ret = PTR_ERR_OR_ZERO(b); if (ret) goto err_root; if (b != btree_node_root(c, b)) { bch2_trans_iter_exit(trans, &iter); goto retry_root; } gc_pos_set(c, gc_pos_btree(btree, b->c.level + 1, SPOS_MAX)); struct bkey_s_c k = bkey_i_to_s_c(&b->key); ret = bch2_gc_mark_key(trans, btree, b->c.level + 1, NULL, NULL, k, initial); err_root: bch2_trans_iter_exit(trans, &iter); } while (bch2_err_matches(ret, BCH_ERR_transaction_restart)); err: bch_err_fn(c, ret); return ret; } static inline int btree_id_gc_phase_cmp(enum btree_id l, enum btree_id r) { return cmp_int(gc_btree_order(l), gc_btree_order(r)); } static int bch2_gc_btrees(struct bch_fs *c) { struct btree_trans *trans = bch2_trans_get(c); struct printbuf buf = PRINTBUF; int ret = 0; struct progress_indicator_state progress; bch2_progress_init(&progress, c, ~0ULL); enum btree_id ids[BTREE_ID_NR]; for (unsigned i = 0; i < BTREE_ID_NR; i++) ids[i] = i; bubble_sort(ids, BTREE_ID_NR, btree_id_gc_phase_cmp); for (unsigned i = 0; i < btree_id_nr_alive(c) && !ret; i++) { unsigned btree = i < BTREE_ID_NR ? ids[i] : i; if (IS_ERR_OR_NULL(bch2_btree_id_root(c, btree)->b)) continue; ret = bch2_gc_btree(trans, &progress, btree, true); } printbuf_exit(&buf); bch2_trans_put(trans); bch_err_fn(c, ret); return ret; } static int bch2_mark_superblocks(struct bch_fs *c) { gc_pos_set(c, gc_phase(GC_PHASE_sb)); return bch2_trans_mark_dev_sbs_flags(c, BTREE_TRIGGER_gc); } static void bch2_gc_free(struct bch_fs *c) { bch2_accounting_gc_free(c); genradix_free(&c->reflink_gc_table); genradix_free(&c->gc_stripes); for_each_member_device(c, ca) genradix_free(&ca->buckets_gc); } static int bch2_gc_start(struct bch_fs *c) { for_each_member_device(c, ca) { int ret = bch2_dev_usage_init(ca, true); if (ret) { bch2_dev_put(ca); return ret; } } return 0; } /* returns true if not equal */ static inline bool bch2_alloc_v4_cmp(struct bch_alloc_v4 l, struct bch_alloc_v4 r) { return l.gen != r.gen || l.oldest_gen != r.oldest_gen || l.data_type != r.data_type || l.dirty_sectors != r.dirty_sectors || l.stripe_sectors != r.stripe_sectors || l.cached_sectors != r.cached_sectors || l.stripe_redundancy != r.stripe_redundancy || l.stripe != r.stripe; } static int bch2_alloc_write_key(struct btree_trans *trans, struct btree_iter *iter, struct bch_dev *ca, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct bkey_i_alloc_v4 *a; struct bch_alloc_v4 old_gc, gc, old_convert, new; const struct bch_alloc_v4 *old; int ret; if (!bucket_valid(ca, k.k->p.offset)) return 0; old = bch2_alloc_to_v4(k, &old_convert); gc = new = *old; __bucket_m_to_alloc(&gc, *gc_bucket(ca, iter->pos.offset)); old_gc = gc; if ((old->data_type == BCH_DATA_sb || old->data_type == BCH_DATA_journal) && !bch2_dev_is_online(ca)) { gc.data_type = old->data_type; gc.dirty_sectors = old->dirty_sectors; } /* * gc.data_type doesn't yet include need_discard & need_gc_gen states - * fix that here: */ alloc_data_type_set(&gc, gc.data_type); if (gc.data_type != old_gc.data_type || gc.dirty_sectors != old_gc.dirty_sectors) { ret = bch2_alloc_key_to_dev_counters(trans, ca, &old_gc, &gc, BTREE_TRIGGER_gc); if (ret) return ret; /* * Ugly: alloc_key_to_dev_counters(..., BTREE_TRIGGER_gc) is not * safe w.r.t. transaction restarts, so fixup the gc_bucket so * we don't run it twice: */ struct bucket *gc_m = gc_bucket(ca, iter->pos.offset); gc_m->data_type = gc.data_type; gc_m->dirty_sectors = gc.dirty_sectors; } if (fsck_err_on(new.data_type != gc.data_type, trans, alloc_key_data_type_wrong, "bucket %llu:%llu gen %u has wrong data_type" ": got %s, should be %s", iter->pos.inode, iter->pos.offset, gc.gen, bch2_data_type_str(new.data_type), bch2_data_type_str(gc.data_type))) new.data_type = gc.data_type; #define copy_bucket_field(_errtype, _f) \ if (fsck_err_on(new._f != gc._f, \ trans, _errtype, \ "bucket %llu:%llu gen %u data type %s has wrong " #_f \ ": got %llu, should be %llu", \ iter->pos.inode, iter->pos.offset, \ gc.gen, \ bch2_data_type_str(gc.data_type), \ (u64) new._f, (u64) gc._f)) \ new._f = gc._f; \ copy_bucket_field(alloc_key_gen_wrong, gen); copy_bucket_field(alloc_key_dirty_sectors_wrong, dirty_sectors); copy_bucket_field(alloc_key_stripe_sectors_wrong, stripe_sectors); copy_bucket_field(alloc_key_cached_sectors_wrong, cached_sectors); copy_bucket_field(alloc_key_stripe_wrong, stripe); copy_bucket_field(alloc_key_stripe_redundancy_wrong, stripe_redundancy); #undef copy_bucket_field if (!bch2_alloc_v4_cmp(*old, new)) return 0; a = bch2_alloc_to_v4_mut(trans, k); ret = PTR_ERR_OR_ZERO(a); if (ret) return ret; a->v = new; /* * The trigger normally makes sure these are set, but we're not running * triggers: */ if (a->v.data_type == BCH_DATA_cached && !a->v.io_time[READ]) a->v.io_time[READ] = max_t(u64, 1, atomic64_read(&c->io_clock[READ].now)); ret = bch2_trans_update(trans, iter, &a->k_i, BTREE_TRIGGER_norun); fsck_err: return ret; } static int bch2_gc_alloc_done(struct bch_fs *c) { int ret = 0; for_each_member_device(c, ca) { ret = bch2_trans_run(c, for_each_btree_key_max_commit(trans, iter, BTREE_ID_alloc, POS(ca->dev_idx, ca->mi.first_bucket), POS(ca->dev_idx, ca->mi.nbuckets - 1), BTREE_ITER_slots|BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_alloc_write_key(trans, &iter, ca, k))); if (ret) { bch2_dev_put(ca); break; } } bch_err_fn(c, ret); return ret; } static int bch2_gc_alloc_start(struct bch_fs *c) { int ret = 0; for_each_member_device(c, ca) { ret = genradix_prealloc(&ca->buckets_gc, ca->mi.nbuckets, GFP_KERNEL); if (ret) { bch2_dev_put(ca); ret = bch_err_throw(c, ENOMEM_gc_alloc_start); break; } } bch_err_fn(c, ret); return ret; } static int bch2_gc_write_stripes_key(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; const struct bch_stripe *s; struct gc_stripe *m; bool bad = false; unsigned i; int ret = 0; if (k.k->type != KEY_TYPE_stripe) return 0; s = bkey_s_c_to_stripe(k).v; m = genradix_ptr(&c->gc_stripes, k.k->p.offset); for (i = 0; i < s->nr_blocks; i++) { u32 old = stripe_blockcount_get(s, i); u32 new = (m ? m->block_sectors[i] : 0); if (old != new) { prt_printf(&buf, "stripe block %u has wrong sector count: got %u, should be %u\n", i, old, new); bad = true; } } if (bad) bch2_bkey_val_to_text(&buf, c, k); if (fsck_err_on(bad, trans, stripe_sector_count_wrong, "%s", buf.buf)) { struct bkey_i_stripe *new; new = bch2_trans_kmalloc(trans, bkey_bytes(k.k)); ret = PTR_ERR_OR_ZERO(new); if (ret) return ret; bkey_reassemble(&new->k_i, k); for (i = 0; i < new->v.nr_blocks; i++) stripe_blockcount_set(&new->v, i, m ? m->block_sectors[i] : 0); ret = bch2_trans_update(trans, iter, &new->k_i, 0); } fsck_err: printbuf_exit(&buf); return ret; } static int bch2_gc_stripes_done(struct bch_fs *c) { return bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_stripes, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, bch2_gc_write_stripes_key(trans, &iter, k))); } /** * bch2_check_allocations - walk all references to buckets, and recompute them: * * @c: filesystem object * * Returns: 0 on success, or standard errcode on failure * * Order matters here: * - Concurrent GC relies on the fact that we have a total ordering for * everything that GC walks - see gc_will_visit_node(), * gc_will_visit_root() * * - also, references move around in the course of index updates and * various other crap: everything needs to agree on the ordering * references are allowed to move around in - e.g., we're allowed to * start with a reference owned by an open_bucket (the allocator) and * move it to the btree, but not the reverse. * * This is necessary to ensure that gc doesn't miss references that * move around - if references move backwards in the ordering GC * uses, GC could skip past them */ int bch2_check_allocations(struct bch_fs *c) { int ret; down_read(&c->state_lock); down_write(&c->gc_lock); bch2_btree_interior_updates_flush(c); ret = bch2_gc_accounting_start(c) ?: bch2_gc_start(c) ?: bch2_gc_alloc_start(c) ?: bch2_gc_reflink_start(c); if (ret) goto out; gc_pos_set(c, gc_phase(GC_PHASE_start)); ret = bch2_mark_superblocks(c); bch_err_msg(c, ret, "marking superblocks"); if (ret) goto out; ret = bch2_gc_btrees(c); if (ret) goto out; c->gc_count++; ret = bch2_gc_alloc_done(c) ?: bch2_gc_accounting_done(c) ?: bch2_gc_stripes_done(c) ?: bch2_gc_reflink_done(c); out: percpu_down_write(&c->mark_lock); /* Indicates that gc is no longer in progress: */ __gc_pos_set(c, gc_phase(GC_PHASE_not_running)); bch2_gc_free(c); percpu_up_write(&c->mark_lock); up_write(&c->gc_lock); up_read(&c->state_lock); /* * At startup, allocations can happen directly instead of via the * allocator thread - issue wakeup in case they blocked on gc_lock: */ closure_wake_up(&c->freelist_wait); if (!ret && !test_bit(BCH_FS_errors_not_fixed, &c->flags)) bch2_sb_members_clean_deleted(c); bch_err_fn(c, ret); return ret; } static int gc_btree_gens_key(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); if (unlikely(test_bit(BCH_FS_going_ro, &c->flags))) return -EROFS; bool too_stale = false; scoped_guard(rcu) { bkey_for_each_ptr(ptrs, ptr) { struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev); if (!ca) continue; too_stale |= dev_ptr_stale(ca, ptr) > 16; } if (!too_stale) bkey_for_each_ptr(ptrs, ptr) { struct bch_dev *ca = bch2_dev_rcu(c, ptr->dev); if (!ca) continue; u8 *gen = &ca->oldest_gen[PTR_BUCKET_NR(ca, ptr)]; if (gen_after(*gen, ptr->gen)) *gen = ptr->gen; } } if (too_stale) { struct bkey_i *u = bch2_bkey_make_mut(trans, iter, &k, 0); int ret = PTR_ERR_OR_ZERO(u); if (ret) return ret; bch2_extent_normalize(c, bkey_i_to_s(u)); } return 0; } static int bch2_alloc_write_oldest_gen(struct btree_trans *trans, struct bch_dev *ca, struct btree_iter *iter, struct bkey_s_c k) { struct bch_alloc_v4 a_convert; const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &a_convert); struct bkey_i_alloc_v4 *a_mut; int ret; if (a->oldest_gen == ca->oldest_gen[iter->pos.offset]) return 0; a_mut = bch2_alloc_to_v4_mut(trans, k); ret = PTR_ERR_OR_ZERO(a_mut); if (ret) return ret; a_mut->v.oldest_gen = ca->oldest_gen[iter->pos.offset]; return bch2_trans_update(trans, iter, &a_mut->k_i, 0); } int bch2_gc_gens(struct bch_fs *c) { u64 b, start_time = local_clock(); int ret; if (!mutex_trylock(&c->gc_gens_lock)) return 0; trace_and_count(c, gc_gens_start, c); /* * We have to use trylock here. Otherwise, we would * introduce a deadlock in the RO path - we take the * state lock at the start of going RO. */ if (!down_read_trylock(&c->state_lock)) { mutex_unlock(&c->gc_gens_lock); return 0; } for_each_member_device(c, ca) { struct bucket_gens *gens = bucket_gens(ca); BUG_ON(ca->oldest_gen); ca->oldest_gen = kvmalloc(gens->nbuckets, GFP_KERNEL); if (!ca->oldest_gen) { bch2_dev_put(ca); ret = bch_err_throw(c, ENOMEM_gc_gens); goto err; } for (b = gens->first_bucket; b < gens->nbuckets; b++) ca->oldest_gen[b] = gens->b[b]; } for (unsigned i = 0; i < BTREE_ID_NR; i++) if (btree_type_has_ptrs(i)) { c->gc_gens_btree = i; c->gc_gens_pos = POS_MIN; ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, i, POS_MIN, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, gc_btree_gens_key(trans, &iter, k))); if (ret) goto err; } struct bch_dev *ca = NULL; ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_alloc, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ ca = bch2_dev_iterate(c, ca, k.k->p.inode); if (!ca) { bch2_btree_iter_set_pos(trans, &iter, POS(k.k->p.inode + 1, 0)); continue; } bch2_alloc_write_oldest_gen(trans, ca, &iter, k); }))); bch2_dev_put(ca); if (ret) goto err; c->gc_gens_btree = 0; c->gc_gens_pos = POS_MIN; c->gc_count++; bch2_time_stats_update(&c->times[BCH_TIME_btree_gc], start_time); trace_and_count(c, gc_gens_end, c); err: for_each_member_device(c, ca) { kvfree(ca->oldest_gen); ca->oldest_gen = NULL; } up_read(&c->state_lock); mutex_unlock(&c->gc_gens_lock); if (!bch2_err_matches(ret, EROFS)) bch_err_fn(c, ret); return ret; } static void bch2_gc_gens_work(struct work_struct *work) { struct bch_fs *c = container_of(work, struct bch_fs, gc_gens_work); bch2_gc_gens(c); enumerated_ref_put(&c->writes, BCH_WRITE_REF_gc_gens); } void bch2_gc_gens_async(struct bch_fs *c) { if (enumerated_ref_tryget(&c->writes, BCH_WRITE_REF_gc_gens) && !queue_work(c->write_ref_wq, &c->gc_gens_work)) enumerated_ref_put(&c->writes, BCH_WRITE_REF_gc_gens); } void bch2_fs_btree_gc_init_early(struct bch_fs *c) { seqcount_init(&c->gc_pos_lock); INIT_WORK(&c->gc_gens_work, bch2_gc_gens_work); init_rwsem(&c->gc_lock); mutex_init(&c->gc_gens_lock); } |
| 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 | // SPDX-License-Identifier: GPL-2.0 #include "bcachefs.h" #include "bcachefs_ioctl.h" #include "bkey_buf.h" #include "btree_cache.h" #include "btree_update.h" #include "buckets.h" #include "darray.h" #include "dirent.h" #include "error.h" #include "fs.h" #include "fsck.h" #include "inode.h" #include "io_misc.h" #include "keylist.h" #include "namei.h" #include "recovery_passes.h" #include "snapshot.h" #include "super.h" #include "thread_with_file.h" #include "xattr.h" #include <linux/bsearch.h> #include <linux/dcache.h> /* struct qstr */ static int dirent_points_to_inode_nowarn(struct bch_fs *c, struct bkey_s_c_dirent d, struct bch_inode_unpacked *inode) { if (d.v->d_type == DT_SUBVOL ? le32_to_cpu(d.v->d_child_subvol) == inode->bi_subvol : le64_to_cpu(d.v->d_inum) == inode->bi_inum) return 0; return bch_err_throw(c, ENOENT_dirent_doesnt_match_inode); } static void dirent_inode_mismatch_msg(struct printbuf *out, struct bch_fs *c, struct bkey_s_c_dirent dirent, struct bch_inode_unpacked *inode) { prt_str(out, "inode points to dirent that does not point back:"); prt_newline(out); bch2_bkey_val_to_text(out, c, dirent.s_c); prt_newline(out); bch2_inode_unpacked_to_text(out, inode); } static int dirent_points_to_inode(struct bch_fs *c, struct bkey_s_c_dirent dirent, struct bch_inode_unpacked *inode) { int ret = dirent_points_to_inode_nowarn(c, dirent, inode); if (ret) { struct printbuf buf = PRINTBUF; dirent_inode_mismatch_msg(&buf, c, dirent, inode); bch_warn(c, "%s", buf.buf); printbuf_exit(&buf); } return ret; } /* * XXX: this is handling transaction restarts without returning * -BCH_ERR_transaction_restart_nested, this is not how we do things anymore: */ static s64 bch2_count_inode_sectors(struct btree_trans *trans, u64 inum, u32 snapshot) { u64 sectors = 0; int ret = for_each_btree_key_max(trans, iter, BTREE_ID_extents, SPOS(inum, 0, snapshot), POS(inum, U64_MAX), 0, k, ({ if (bkey_extent_is_allocation(k.k)) sectors += k.k->size; 0; })); return ret ?: sectors; } static s64 bch2_count_subdirs(struct btree_trans *trans, u64 inum, u32 snapshot) { u64 subdirs = 0; int ret = for_each_btree_key_max(trans, iter, BTREE_ID_dirents, SPOS(inum, 0, snapshot), POS(inum, U64_MAX), 0, k, ({ if (k.k->type == KEY_TYPE_dirent && bkey_s_c_to_dirent(k).v->d_type == DT_DIR) subdirs++; 0; })); return ret ?: subdirs; } static int subvol_lookup(struct btree_trans *trans, u32 subvol, u32 *snapshot, u64 *inum) { struct bch_subvolume s; int ret = bch2_subvolume_get(trans, subvol, false, &s); *snapshot = le32_to_cpu(s.snapshot); *inum = le64_to_cpu(s.inode); return ret; } static int lookup_dirent_in_snapshot(struct btree_trans *trans, struct bch_hash_info hash_info, subvol_inum dir, struct qstr *name, u64 *target, unsigned *type, u32 snapshot) { struct btree_iter iter; struct bkey_s_c k = bch2_hash_lookup_in_snapshot(trans, &iter, bch2_dirent_hash_desc, &hash_info, dir, name, 0, snapshot); int ret = bkey_err(k); if (ret) return ret; struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); *target = le64_to_cpu(d.v->d_inum); *type = d.v->d_type; bch2_trans_iter_exit(trans, &iter); return 0; } /* * Find any subvolume associated with a tree of snapshots * We can't rely on master_subvol - it might have been deleted. */ static int find_snapshot_tree_subvol(struct btree_trans *trans, u32 tree_id, u32 *subvol) { struct btree_iter iter; struct bkey_s_c k; int ret; for_each_btree_key_norestart(trans, iter, BTREE_ID_snapshots, POS_MIN, 0, k, ret) { if (k.k->type != KEY_TYPE_snapshot) continue; struct bkey_s_c_snapshot s = bkey_s_c_to_snapshot(k); if (le32_to_cpu(s.v->tree) != tree_id) continue; if (s.v->subvol) { *subvol = le32_to_cpu(s.v->subvol); goto found; } } ret = bch_err_throw(trans->c, ENOENT_no_snapshot_tree_subvol); found: bch2_trans_iter_exit(trans, &iter); return ret; } /* Get lost+found, create if it doesn't exist: */ static int lookup_lostfound(struct btree_trans *trans, u32 snapshot, struct bch_inode_unpacked *lostfound, u64 reattaching_inum) { struct bch_fs *c = trans->c; struct qstr lostfound_str = QSTR("lost+found"); struct btree_iter lostfound_iter = {}; u64 inum = 0; unsigned d_type = 0; int ret; struct bch_snapshot_tree st; ret = bch2_snapshot_tree_lookup(trans, bch2_snapshot_tree(c, snapshot), &st); if (ret) return ret; u32 subvolid; ret = find_snapshot_tree_subvol(trans, bch2_snapshot_tree(c, snapshot), &subvolid); bch_err_msg(c, ret, "finding subvol associated with snapshot tree %u", bch2_snapshot_tree(c, snapshot)); if (ret) return ret; struct bch_subvolume subvol; ret = bch2_subvolume_get(trans, subvolid, false, &subvol); bch_err_msg(c, ret, "looking up subvol %u for snapshot %u", subvolid, snapshot); if (ret) return ret; if (!subvol.inode) { struct btree_iter iter; struct bkey_i_subvolume *subvol = bch2_bkey_get_mut_typed(trans, &iter, BTREE_ID_subvolumes, POS(0, subvolid), 0, subvolume); ret = PTR_ERR_OR_ZERO(subvol); if (ret) return ret; subvol->v.inode = cpu_to_le64(reattaching_inum); bch2_trans_iter_exit(trans, &iter); } subvol_inum root_inum = { .subvol = subvolid, .inum = le64_to_cpu(subvol.inode) }; struct bch_inode_unpacked root_inode; struct bch_hash_info root_hash_info; ret = bch2_inode_find_by_inum_snapshot(trans, root_inum.inum, snapshot, &root_inode, 0); bch_err_msg(c, ret, "looking up root inode %llu for subvol %u", root_inum.inum, subvolid); if (ret) return ret; root_hash_info = bch2_hash_info_init(c, &root_inode); ret = lookup_dirent_in_snapshot(trans, root_hash_info, root_inum, &lostfound_str, &inum, &d_type, snapshot); if (bch2_err_matches(ret, ENOENT)) goto create_lostfound; bch_err_fn(c, ret); if (ret) return ret; if (d_type != DT_DIR) { bch_err(c, "error looking up lost+found: not a directory"); return bch_err_throw(c, ENOENT_not_directory); } /* * The bch2_check_dirents pass has already run, dangling dirents * shouldn't exist here: */ ret = bch2_inode_find_by_inum_snapshot(trans, inum, snapshot, lostfound, 0); bch_err_msg(c, ret, "looking up lost+found %llu:%u in (root inode %llu, snapshot root %u)", inum, snapshot, root_inum.inum, bch2_snapshot_root(c, snapshot)); return ret; create_lostfound: /* * we always create lost+found in the root snapshot; we don't want * different branches of the snapshot tree to have different lost+found */ snapshot = le32_to_cpu(st.root_snapshot); /* * XXX: we could have a nicer log message here if we had a nice way to * walk backpointers to print a path */ struct printbuf path = PRINTBUF; ret = bch2_inum_to_path(trans, root_inum, &path); if (ret) goto err; bch_notice(c, "creating %s/lost+found in subvol %llu snapshot %u", path.buf, root_inum.subvol, snapshot); printbuf_exit(&path); u64 now = bch2_current_time(c); u64 cpu = raw_smp_processor_id(); bch2_inode_init_early(c, lostfound); bch2_inode_init_late(c, lostfound, now, 0, 0, S_IFDIR|0700, 0, &root_inode); lostfound->bi_dir = root_inode.bi_inum; lostfound->bi_snapshot = le32_to_cpu(st.root_snapshot); root_inode.bi_nlink++; ret = bch2_inode_create(trans, &lostfound_iter, lostfound, snapshot, cpu); if (ret) goto err; bch2_btree_iter_set_snapshot(trans, &lostfound_iter, snapshot); ret = bch2_btree_iter_traverse(trans, &lostfound_iter); if (ret) goto err; ret = bch2_dirent_create_snapshot(trans, 0, root_inode.bi_inum, snapshot, &root_hash_info, mode_to_type(lostfound->bi_mode), &lostfound_str, lostfound->bi_inum, &lostfound->bi_dir_offset, BTREE_UPDATE_internal_snapshot_node| STR_HASH_must_create) ?: bch2_inode_write_flags(trans, &lostfound_iter, lostfound, BTREE_UPDATE_internal_snapshot_node); err: bch_err_msg(c, ret, "creating lost+found"); bch2_trans_iter_exit(trans, &lostfound_iter); return ret; } static inline bool inode_should_reattach(struct bch_inode_unpacked *inode) { if (inode->bi_inum == BCACHEFS_ROOT_INO && inode->bi_subvol == BCACHEFS_ROOT_SUBVOL) return false; /* * Subvolume roots are special: older versions of subvolume roots may be * disconnected, it's only the newest version that matters. * * We only keep a single dirent pointing to a subvolume root, i.e. * older versions of snapshots will not have a different dirent pointing * to the same subvolume root. * * This is because dirents that point to subvolumes are only visible in * the parent subvolume - versioning is not needed - and keeping them * around would break fsck, because when we're crossing subvolumes we * don't have a consistent snapshot ID to do check the inode <-> dirent * relationships. * * Thus, a subvolume root that's been renamed after a snapshot will have * a disconnected older version - that's expected. * * Note that taking a snapshot always updates the root inode (to update * the dirent backpointer), so a subvolume root inode with * BCH_INODE_has_child_snapshot is never visible. */ if (inode->bi_subvol && (inode->bi_flags & BCH_INODE_has_child_snapshot)) return false; return !bch2_inode_has_backpointer(inode) && !(inode->bi_flags & BCH_INODE_unlinked); } static int maybe_delete_dirent(struct btree_trans *trans, struct bpos d_pos, u32 snapshot) { struct btree_iter iter; struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_dirents, SPOS(d_pos.inode, d_pos.offset, snapshot), BTREE_ITER_intent| BTREE_ITER_with_updates); int ret = bkey_err(k); if (ret) return ret; if (bpos_eq(k.k->p, d_pos)) { /* * delet_at() doesn't work because the update path doesn't * internally use BTREE_ITER_with_updates yet */ struct bkey_i *k = bch2_trans_kmalloc(trans, sizeof(*k)); ret = PTR_ERR_OR_ZERO(k); if (ret) goto err; bkey_init(&k->k); k->k.type = KEY_TYPE_whiteout; k->k.p = iter.pos; ret = bch2_trans_update(trans, &iter, k, BTREE_UPDATE_internal_snapshot_node); } err: bch2_trans_iter_exit(trans, &iter); return ret; } static int reattach_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode) { struct bch_fs *c = trans->c; struct bch_inode_unpacked lostfound; char name_buf[20]; int ret; u32 dirent_snapshot = inode->bi_snapshot; if (inode->bi_subvol) { inode->bi_parent_subvol = BCACHEFS_ROOT_SUBVOL; struct btree_iter subvol_iter; struct bkey_i_subvolume *subvol = bch2_bkey_get_mut_typed(trans, &subvol_iter, BTREE_ID_subvolumes, POS(0, inode->bi_subvol), 0, subvolume); ret = PTR_ERR_OR_ZERO(subvol); if (ret) return ret; subvol->v.fs_path_parent = BCACHEFS_ROOT_SUBVOL; bch2_trans_iter_exit(trans, &subvol_iter); u64 root_inum; ret = subvol_lookup(trans, inode->bi_parent_subvol, &dirent_snapshot, &root_inum); if (ret) return ret; snprintf(name_buf, sizeof(name_buf), "subvol-%u", inode->bi_subvol); } else { snprintf(name_buf, sizeof(name_buf), "%llu", inode->bi_inum); } ret = lookup_lostfound(trans, dirent_snapshot, &lostfound, inode->bi_inum); if (ret) return ret; bch_verbose(c, "got lostfound inum %llu", lostfound.bi_inum); lostfound.bi_nlink += S_ISDIR(inode->bi_mode); /* ensure lost+found inode is also present in inode snapshot */ if (!inode->bi_subvol) { BUG_ON(!bch2_snapshot_is_ancestor(c, inode->bi_snapshot, lostfound.bi_snapshot)); lostfound.bi_snapshot = inode->bi_snapshot; } ret = __bch2_fsck_write_inode(trans, &lostfound); if (ret) return ret; struct bch_hash_info dir_hash = bch2_hash_info_init(c, &lostfound); struct qstr name = QSTR(name_buf); inode->bi_dir = lostfound.bi_inum; ret = bch2_dirent_create_snapshot(trans, inode->bi_parent_subvol, lostfound.bi_inum, dirent_snapshot, &dir_hash, inode_d_type(inode), &name, inode->bi_subvol ?: inode->bi_inum, &inode->bi_dir_offset, BTREE_UPDATE_internal_snapshot_node| STR_HASH_must_create); if (ret) { bch_err_msg(c, ret, "error creating dirent"); return ret; } ret = __bch2_fsck_write_inode(trans, inode); if (ret) return ret; { CLASS(printbuf, buf)(); ret = bch2_inum_snapshot_to_path(trans, inode->bi_inum, inode->bi_snapshot, NULL, &buf); if (ret) return ret; bch_info(c, "reattached at %s", buf.buf); } /* * Fix up inodes in child snapshots: if they should also be reattached * update the backpointer field, if they should not be we need to emit * whiteouts for the dirent we just created. */ if (!inode->bi_subvol && bch2_snapshot_is_leaf(c, inode->bi_snapshot) <= 0) { snapshot_id_list whiteouts_done; struct btree_iter iter; struct bkey_s_c k; darray_init(&whiteouts_done); for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inode->bi_inum, inode->bi_snapshot - 1), BTREE_ITER_all_snapshots|BTREE_ITER_intent, k, ret) { if (k.k->p.offset != inode->bi_inum) break; if (!bkey_is_inode(k.k) || !bch2_snapshot_is_ancestor(c, k.k->p.snapshot, inode->bi_snapshot) || snapshot_list_has_ancestor(c, &whiteouts_done, k.k->p.snapshot)) continue; struct bch_inode_unpacked child_inode; ret = bch2_inode_unpack(k, &child_inode); if (ret) break; if (!inode_should_reattach(&child_inode)) { ret = maybe_delete_dirent(trans, SPOS(lostfound.bi_inum, inode->bi_dir_offset, dirent_snapshot), k.k->p.snapshot); if (ret) break; ret = snapshot_list_add(c, &whiteouts_done, k.k->p.snapshot); if (ret) break; } else { iter.snapshot = k.k->p.snapshot; child_inode.bi_dir = inode->bi_dir; child_inode.bi_dir_offset = inode->bi_dir_offset; ret = bch2_inode_write_flags(trans, &iter, &child_inode, BTREE_UPDATE_internal_snapshot_node); if (ret) break; } } darray_exit(&whiteouts_done); bch2_trans_iter_exit(trans, &iter); } return ret; } static struct bkey_s_c_dirent dirent_get_by_pos(struct btree_trans *trans, struct btree_iter *iter, struct bpos pos) { return bch2_bkey_get_iter_typed(trans, iter, BTREE_ID_dirents, pos, 0, dirent); } static int remove_backpointer(struct btree_trans *trans, struct bch_inode_unpacked *inode) { if (!bch2_inode_has_backpointer(inode)) return 0; u32 snapshot = inode->bi_snapshot; if (inode->bi_parent_subvol) { int ret = bch2_subvolume_get_snapshot(trans, inode->bi_parent_subvol, &snapshot); if (ret) return ret; } struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c_dirent d = dirent_get_by_pos(trans, &iter, SPOS(inode->bi_dir, inode->bi_dir_offset, snapshot)); int ret = bkey_err(d) ?: dirent_points_to_inode(c, d, inode) ?: bch2_fsck_remove_dirent(trans, d.k->p); bch2_trans_iter_exit(trans, &iter); return ret; } static int reattach_subvol(struct btree_trans *trans, struct bkey_s_c_subvolume s) { struct bch_fs *c = trans->c; struct bch_inode_unpacked inode; int ret = bch2_inode_find_by_inum_trans(trans, (subvol_inum) { s.k->p.offset, le64_to_cpu(s.v->inode) }, &inode); if (ret) return ret; ret = remove_backpointer(trans, &inode); if (!bch2_err_matches(ret, ENOENT)) bch_err_msg(c, ret, "removing dirent"); if (ret) return ret; ret = reattach_inode(trans, &inode); bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum); return ret; } static int reconstruct_subvol(struct btree_trans *trans, u32 snapshotid, u32 subvolid, u64 inum) { struct bch_fs *c = trans->c; if (!bch2_snapshot_is_leaf(c, snapshotid)) { bch_err(c, "need to reconstruct subvol, but have interior node snapshot"); return bch_err_throw(c, fsck_repair_unimplemented); } /* * If inum isn't set, that means we're being called from check_dirents, * not check_inodes - the root of this subvolume doesn't exist or we * would have found it there: */ if (!inum) { struct btree_iter inode_iter = {}; struct bch_inode_unpacked new_inode; u64 cpu = raw_smp_processor_id(); bch2_inode_init_early(c, &new_inode); bch2_inode_init_late(c, &new_inode, bch2_current_time(c), 0, 0, S_IFDIR|0755, 0, NULL); new_inode.bi_subvol = subvolid; int ret = bch2_inode_create(trans, &inode_iter, &new_inode, snapshotid, cpu) ?: bch2_btree_iter_traverse(trans, &inode_iter) ?: bch2_inode_write(trans, &inode_iter, &new_inode); bch2_trans_iter_exit(trans, &inode_iter); if (ret) return ret; inum = new_inode.bi_inum; } bch_info(c, "reconstructing subvol %u with root inode %llu", subvolid, inum); struct bkey_i_subvolume *new_subvol = bch2_trans_kmalloc(trans, sizeof(*new_subvol)); int ret = PTR_ERR_OR_ZERO(new_subvol); if (ret) return ret; bkey_subvolume_init(&new_subvol->k_i); new_subvol->k.p.offset = subvolid; new_subvol->v.snapshot = cpu_to_le32(snapshotid); new_subvol->v.inode = cpu_to_le64(inum); ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &new_subvol->k_i, 0); if (ret) return ret; struct btree_iter iter; struct bkey_i_snapshot *s = bch2_bkey_get_mut_typed(trans, &iter, BTREE_ID_snapshots, POS(0, snapshotid), 0, snapshot); ret = PTR_ERR_OR_ZERO(s); bch_err_msg(c, ret, "getting snapshot %u", snapshotid); if (ret) return ret; u32 snapshot_tree = le32_to_cpu(s->v.tree); s->v.subvol = cpu_to_le32(subvolid); SET_BCH_SNAPSHOT_SUBVOL(&s->v, true); bch2_trans_iter_exit(trans, &iter); struct bkey_i_snapshot_tree *st = bch2_bkey_get_mut_typed(trans, &iter, BTREE_ID_snapshot_trees, POS(0, snapshot_tree), 0, snapshot_tree); ret = PTR_ERR_OR_ZERO(st); bch_err_msg(c, ret, "getting snapshot tree %u", snapshot_tree); if (ret) return ret; if (!st->v.master_subvol) st->v.master_subvol = cpu_to_le32(subvolid); bch2_trans_iter_exit(trans, &iter); return 0; } static int reconstruct_inode(struct btree_trans *trans, enum btree_id btree, u32 snapshot, u64 inum) { struct bch_fs *c = trans->c; unsigned i_mode = S_IFREG; u64 i_size = 0; switch (btree) { case BTREE_ID_extents: { struct btree_iter iter = {}; bch2_trans_iter_init(trans, &iter, BTREE_ID_extents, SPOS(inum, U64_MAX, snapshot), 0); struct bkey_s_c k = bch2_btree_iter_peek_prev_min(trans, &iter, POS(inum, 0)); bch2_trans_iter_exit(trans, &iter); int ret = bkey_err(k); if (ret) return ret; i_size = k.k->p.offset << 9; break; } case BTREE_ID_dirents: i_mode = S_IFDIR; break; case BTREE_ID_xattrs: break; default: BUG(); } struct bch_inode_unpacked new_inode; bch2_inode_init_early(c, &new_inode); bch2_inode_init_late(c, &new_inode, bch2_current_time(c), 0, 0, i_mode|0600, 0, NULL); new_inode.bi_size = i_size; new_inode.bi_inum = inum; new_inode.bi_snapshot = snapshot; return __bch2_fsck_write_inode(trans, &new_inode); } static inline void snapshots_seen_exit(struct snapshots_seen *s) { darray_exit(&s->ids); } static inline void snapshots_seen_init(struct snapshots_seen *s) { memset(s, 0, sizeof(*s)); } static int snapshots_seen_add_inorder(struct bch_fs *c, struct snapshots_seen *s, u32 id) { u32 *i; __darray_for_each(s->ids, i) { if (*i == id) return 0; if (*i > id) break; } int ret = darray_insert_item(&s->ids, i - s->ids.data, id); if (ret) bch_err(c, "error reallocating snapshots_seen table (size %zu)", s->ids.size); return ret; } static int snapshots_seen_update(struct bch_fs *c, struct snapshots_seen *s, enum btree_id btree_id, struct bpos pos) { if (!bkey_eq(s->pos, pos)) s->ids.nr = 0; s->pos = pos; return snapshot_list_add_nodup(c, &s->ids, pos.snapshot); } /** * key_visible_in_snapshot - returns true if @id is a descendent of @ancestor, * and @ancestor hasn't been overwritten in @seen * * @c: filesystem handle * @seen: list of snapshot ids already seen at current position * @id: descendent snapshot id * @ancestor: ancestor snapshot id * * Returns: whether key in @ancestor snapshot is visible in @id snapshot */ static bool key_visible_in_snapshot(struct bch_fs *c, struct snapshots_seen *seen, u32 id, u32 ancestor) { EBUG_ON(id > ancestor); if (id == ancestor) return true; if (!bch2_snapshot_is_ancestor(c, id, ancestor)) return false; /* * We know that @id is a descendant of @ancestor, we're checking if * we've seen a key that overwrote @ancestor - i.e. also a descendent of * @ascestor and with @id as a descendent. * * But we already know that we're scanning IDs between @id and @ancestor * numerically, since snapshot ID lists are kept sorted, so if we find * an id that's an ancestor of @id we're done: */ darray_for_each_reverse(seen->ids, i) if (*i != ancestor && bch2_snapshot_is_ancestor(c, id, *i)) return false; return true; } /** * ref_visible - given a key with snapshot id @src that points to a key with * snapshot id @dst, test whether there is some snapshot in which @dst is * visible. * * @c: filesystem handle * @s: list of snapshot IDs already seen at @src * @src: snapshot ID of src key * @dst: snapshot ID of dst key * Returns: true if there is some snapshot in which @dst is visible * * Assumes we're visiting @src keys in natural key order */ static bool ref_visible(struct bch_fs *c, struct snapshots_seen *s, u32 src, u32 dst) { return dst <= src ? key_visible_in_snapshot(c, s, dst, src) : bch2_snapshot_is_ancestor(c, src, dst); } static int ref_visible2(struct bch_fs *c, u32 src, struct snapshots_seen *src_seen, u32 dst, struct snapshots_seen *dst_seen) { if (dst > src) { swap(dst, src); swap(dst_seen, src_seen); } return key_visible_in_snapshot(c, src_seen, dst, src); } #define for_each_visible_inode(_c, _s, _w, _snapshot, _i) \ for (_i = (_w)->inodes.data; _i < (_w)->inodes.data + (_w)->inodes.nr && \ (_i)->inode.bi_snapshot <= (_snapshot); _i++) \ if (key_visible_in_snapshot(_c, _s, _i->inode.bi_snapshot, _snapshot)) struct inode_walker_entry { struct bch_inode_unpacked inode; bool whiteout; u64 count; u64 i_size; }; struct inode_walker { bool first_this_inode; bool have_inodes; bool recalculate_sums; struct bpos last_pos; DARRAY(struct inode_walker_entry) inodes; snapshot_id_list deletes; }; static void inode_walker_exit(struct inode_walker *w) { darray_exit(&w->inodes); darray_exit(&w->deletes); } static struct inode_walker inode_walker_init(void) { return (struct inode_walker) { 0, }; } static int add_inode(struct bch_fs *c, struct inode_walker *w, struct bkey_s_c inode) { int ret = darray_push(&w->inodes, ((struct inode_walker_entry) { .whiteout = !bkey_is_inode(inode.k), })); if (ret) return ret; struct inode_walker_entry *n = &darray_last(w->inodes); if (!n->whiteout) { return bch2_inode_unpack(inode, &n->inode); } else { n->inode.bi_inum = inode.k->p.offset; n->inode.bi_snapshot = inode.k->p.snapshot; return 0; } } static int get_inodes_all_snapshots(struct btree_trans *trans, struct inode_walker *w, u64 inum) { struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c k; int ret; /* * We no longer have inodes for w->last_pos; clear this to avoid * screwing up check_i_sectors/check_subdir_count if we take a * transaction restart here: */ w->have_inodes = false; w->recalculate_sums = false; w->inodes.nr = 0; for_each_btree_key_max_norestart(trans, iter, BTREE_ID_inodes, POS(0, inum), SPOS(0, inum, U32_MAX), BTREE_ITER_all_snapshots, k, ret) { ret = add_inode(c, w, k); if (ret) break; } bch2_trans_iter_exit(trans, &iter); if (ret) return ret; w->first_this_inode = true; w->have_inodes = true; return 0; } static int get_visible_inodes(struct btree_trans *trans, struct inode_walker *w, struct snapshots_seen *s, u64 inum) { struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c k; int ret; w->inodes.nr = 0; w->deletes.nr = 0; for_each_btree_key_reverse_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inum, s->pos.snapshot), BTREE_ITER_all_snapshots, k, ret) { if (k.k->p.offset != inum) break; if (!ref_visible(c, s, s->pos.snapshot, k.k->p.snapshot)) continue; if (snapshot_list_has_ancestor(c, &w->deletes, k.k->p.snapshot)) continue; ret = bkey_is_inode(k.k) ? add_inode(c, w, k) : snapshot_list_add(c, &w->deletes, k.k->p.snapshot); if (ret) break; } bch2_trans_iter_exit(trans, &iter); return ret; } static struct inode_walker_entry * lookup_inode_for_snapshot(struct btree_trans *trans, struct inode_walker *w, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct inode_walker_entry *i = darray_find_p(w->inodes, i, bch2_snapshot_is_ancestor(c, k.k->p.snapshot, i->inode.bi_snapshot)); if (!i) return NULL; struct printbuf buf = PRINTBUF; int ret = 0; if (fsck_err_on(k.k->p.snapshot != i->inode.bi_snapshot, trans, snapshot_key_missing_inode_snapshot, "have key for inode %llu:%u but have inode in ancestor snapshot %u\n" "unexpected because we should always update the inode when we update a key in that inode\n" "%s", w->last_pos.inode, k.k->p.snapshot, i->inode.bi_snapshot, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { if (!i->whiteout) { struct bch_inode_unpacked new = i->inode; new.bi_snapshot = k.k->p.snapshot; ret = __bch2_fsck_write_inode(trans, &new); } else { struct bkey_i whiteout; bkey_init(&whiteout.k); whiteout.k.type = KEY_TYPE_whiteout; whiteout.k.p = SPOS(0, i->inode.bi_inum, k.k->p.snapshot); ret = bch2_btree_insert_nonextent(trans, BTREE_ID_inodes, &whiteout, BTREE_UPDATE_internal_snapshot_node); } if (ret) goto fsck_err; ret = bch2_trans_commit(trans, NULL, NULL, 0); if (ret) goto fsck_err; struct inode_walker_entry new_entry = *i; new_entry.inode.bi_snapshot = k.k->p.snapshot; new_entry.count = 0; new_entry.i_size = 0; while (i > w->inodes.data && i[-1].inode.bi_snapshot > k.k->p.snapshot) --i; size_t pos = i - w->inodes.data; ret = darray_insert_item(&w->inodes, pos, new_entry); if (ret) goto fsck_err; ret = bch_err_throw(c, transaction_restart_nested); goto fsck_err; } printbuf_exit(&buf); return i; fsck_err: printbuf_exit(&buf); return ERR_PTR(ret); } static struct inode_walker_entry *walk_inode(struct btree_trans *trans, struct inode_walker *w, struct bkey_s_c k) { if (w->last_pos.inode != k.k->p.inode) { int ret = get_inodes_all_snapshots(trans, w, k.k->p.inode); if (ret) return ERR_PTR(ret); } w->last_pos = k.k->p; return lookup_inode_for_snapshot(trans, w, k); } /* * Prefer to delete the first one, since that will be the one at the wrong * offset: * return value: 0 -> delete k1, 1 -> delete k2 */ int bch2_fsck_update_backpointers(struct btree_trans *trans, struct snapshots_seen *s, const struct bch_hash_desc desc, struct bch_hash_info *hash_info, struct bkey_i *new) { if (new->k.type != KEY_TYPE_dirent) return 0; struct bkey_i_dirent *d = bkey_i_to_dirent(new); struct inode_walker target = inode_walker_init(); int ret = 0; if (d->v.d_type == DT_SUBVOL) { bch_err(trans->c, "%s does not support DT_SUBVOL", __func__); ret = -BCH_ERR_fsck_repair_unimplemented; } else { ret = get_visible_inodes(trans, &target, s, le64_to_cpu(d->v.d_inum)); if (ret) goto err; darray_for_each(target.inodes, i) { i->inode.bi_dir_offset = d->k.p.offset; ret = __bch2_fsck_write_inode(trans, &i->inode); if (ret) goto err; } } err: inode_walker_exit(&target); return ret; } static struct bkey_s_c_dirent inode_get_dirent(struct btree_trans *trans, struct btree_iter *iter, struct bch_inode_unpacked *inode, u32 *snapshot) { if (inode->bi_subvol) { u64 inum; int ret = subvol_lookup(trans, inode->bi_parent_subvol, snapshot, &inum); if (ret) return ((struct bkey_s_c_dirent) { .k = ERR_PTR(ret) }); } return dirent_get_by_pos(trans, iter, SPOS(inode->bi_dir, inode->bi_dir_offset, *snapshot)); } static int check_inode_deleted_list(struct btree_trans *trans, struct bpos p) { struct btree_iter iter; struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_deleted_inodes, p, 0); int ret = bkey_err(k) ?: k.k->type == KEY_TYPE_set; bch2_trans_iter_exit(trans, &iter); return ret; } static int check_inode_dirent_inode(struct btree_trans *trans, struct bch_inode_unpacked *inode, bool *write_inode) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; u32 inode_snapshot = inode->bi_snapshot; struct btree_iter dirent_iter = {}; struct bkey_s_c_dirent d = inode_get_dirent(trans, &dirent_iter, inode, &inode_snapshot); int ret = bkey_err(d); if (ret && !bch2_err_matches(ret, ENOENT)) return ret; if ((ret || dirent_points_to_inode_nowarn(c, d, inode)) && inode->bi_subvol && (inode->bi_flags & BCH_INODE_has_child_snapshot)) { /* Older version of a renamed subvolume root: we won't have a * correct dirent for it. That's expected, see * inode_should_reattach(). * * We don't clear the backpointer field when doing the rename * because there might be arbitrarily many versions in older * snapshots. */ inode->bi_dir = 0; inode->bi_dir_offset = 0; *write_inode = true; goto out; } if (fsck_err_on(ret, trans, inode_points_to_missing_dirent, "inode points to missing dirent\n%s", (bch2_inode_unpacked_to_text(&buf, inode), buf.buf)) || fsck_err_on(!ret && dirent_points_to_inode_nowarn(c, d, inode), trans, inode_points_to_wrong_dirent, "%s", (printbuf_reset(&buf), dirent_inode_mismatch_msg(&buf, c, d, inode), buf.buf))) { /* * We just clear the backpointer fields for now. If we find a * dirent that points to this inode in check_dirents(), we'll * update it then; then when we get to check_path() if the * backpointer is still 0 we'll reattach it. */ inode->bi_dir = 0; inode->bi_dir_offset = 0; *write_inode = true; } out: ret = 0; fsck_err: bch2_trans_iter_exit(trans, &dirent_iter); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } static int check_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct bch_inode_unpacked *snapshot_root, struct snapshots_seen *s) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; struct bch_inode_unpacked u; bool do_update = false; int ret; ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret < 0) goto err; if (ret) return 0; ret = snapshots_seen_update(c, s, iter->btree_id, k.k->p); if (ret) goto err; if (!bkey_is_inode(k.k)) return 0; ret = bch2_inode_unpack(k, &u); if (ret) goto err; if (snapshot_root->bi_inum != u.bi_inum) { ret = bch2_inode_find_snapshot_root(trans, u.bi_inum, snapshot_root); if (ret) goto err; } if (u.bi_hash_seed != snapshot_root->bi_hash_seed || INODE_STR_HASH(&u) != INODE_STR_HASH(snapshot_root)) { ret = bch2_repair_inode_hash_info(trans, snapshot_root); BUG_ON(ret == -BCH_ERR_fsck_repair_unimplemented); if (ret) goto err; } ret = bch2_check_inode_has_case_insensitive(trans, &u, &s->ids, &do_update); if (ret) goto err; if (bch2_inode_has_backpointer(&u)) { ret = check_inode_dirent_inode(trans, &u, &do_update); if (ret) goto err; } if (fsck_err_on(bch2_inode_has_backpointer(&u) && (u.bi_flags & BCH_INODE_unlinked), trans, inode_unlinked_but_has_dirent, "inode unlinked but has dirent\n%s", (printbuf_reset(&buf), bch2_inode_unpacked_to_text(&buf, &u), buf.buf))) { u.bi_flags &= ~BCH_INODE_unlinked; do_update = true; } if (S_ISDIR(u.bi_mode) && (u.bi_flags & BCH_INODE_unlinked)) { /* Check for this early so that check_unreachable_inode() will reattach it */ ret = bch2_empty_dir_snapshot(trans, k.k->p.offset, 0, k.k->p.snapshot); if (ret && ret != -BCH_ERR_ENOTEMPTY_dir_not_empty) goto err; fsck_err_on(ret, trans, inode_dir_unlinked_but_not_empty, "dir unlinked but not empty\n%s", (printbuf_reset(&buf), bch2_inode_unpacked_to_text(&buf, &u), buf.buf)); u.bi_flags &= ~BCH_INODE_unlinked; do_update = true; ret = 0; } if (fsck_err_on(S_ISDIR(u.bi_mode) && u.bi_size, trans, inode_dir_has_nonzero_i_size, "directory %llu:%u with nonzero i_size %lli", u.bi_inum, u.bi_snapshot, u.bi_size)) { u.bi_size = 0; do_update = true; } ret = bch2_inode_has_child_snapshots(trans, k.k->p); if (ret < 0) goto err; if (fsck_err_on(ret != !!(u.bi_flags & BCH_INODE_has_child_snapshot), trans, inode_has_child_snapshots_wrong, "inode has_child_snapshots flag wrong (should be %u)\n%s", ret, (printbuf_reset(&buf), bch2_inode_unpacked_to_text(&buf, &u), buf.buf))) { if (ret) u.bi_flags |= BCH_INODE_has_child_snapshot; else u.bi_flags &= ~BCH_INODE_has_child_snapshot; do_update = true; } ret = 0; if ((u.bi_flags & BCH_INODE_unlinked) && !(u.bi_flags & BCH_INODE_has_child_snapshot)) { if (!test_bit(BCH_FS_started, &c->flags)) { /* * If we're not in online fsck, don't delete unlinked * inodes, just make sure they're on the deleted list. * * They might be referred to by a logged operation - * i.e. we might have crashed in the middle of a * truncate on an unlinked but open file - so we want to * let the delete_dead_inodes kill it after resuming * logged ops. */ ret = check_inode_deleted_list(trans, k.k->p); if (ret < 0) goto err_noprint; fsck_err_on(!ret, trans, unlinked_inode_not_on_deleted_list, "inode %llu:%u unlinked, but not on deleted list", u.bi_inum, k.k->p.snapshot); ret = bch2_btree_bit_mod_buffered(trans, BTREE_ID_deleted_inodes, k.k->p, 1); if (ret) goto err; } else { ret = bch2_inode_or_descendents_is_open(trans, k.k->p); if (ret < 0) goto err; if (fsck_err_on(!ret, trans, inode_unlinked_and_not_open, "inode %llu:%u unlinked and not open", u.bi_inum, u.bi_snapshot)) { ret = bch2_inode_rm_snapshot(trans, u.bi_inum, iter->pos.snapshot); bch_err_msg(c, ret, "in fsck deleting inode"); goto err_noprint; } ret = 0; } } if (fsck_err_on(u.bi_parent_subvol && (u.bi_subvol == 0 || u.bi_subvol == BCACHEFS_ROOT_SUBVOL), trans, inode_bi_parent_nonzero, "inode %llu:%u has subvol %u but nonzero parent subvol %u", u.bi_inum, k.k->p.snapshot, u.bi_subvol, u.bi_parent_subvol)) { u.bi_parent_subvol = 0; do_update = true; } if (u.bi_subvol) { struct bch_subvolume s; ret = bch2_subvolume_get(trans, u.bi_subvol, false, &s); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; if (ret && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_subvolumes))) { ret = reconstruct_subvol(trans, k.k->p.snapshot, u.bi_subvol, u.bi_inum); goto do_update; } if (fsck_err_on(ret, trans, inode_bi_subvol_missing, "inode %llu:%u bi_subvol points to missing subvolume %u", u.bi_inum, k.k->p.snapshot, u.bi_subvol) || fsck_err_on(le64_to_cpu(s.inode) != u.bi_inum || !bch2_snapshot_is_ancestor(c, le32_to_cpu(s.snapshot), k.k->p.snapshot), trans, inode_bi_subvol_wrong, "inode %llu:%u points to subvol %u, but subvol points to %llu:%u", u.bi_inum, k.k->p.snapshot, u.bi_subvol, le64_to_cpu(s.inode), le32_to_cpu(s.snapshot))) { u.bi_subvol = 0; u.bi_parent_subvol = 0; do_update = true; } } if (fsck_err_on(u.bi_journal_seq > journal_cur_seq(&c->journal), trans, inode_journal_seq_in_future, "inode journal seq in future (currently at %llu)\n%s", journal_cur_seq(&c->journal), (printbuf_reset(&buf), bch2_inode_unpacked_to_text(&buf, &u), buf.buf))) { u.bi_journal_seq = journal_cur_seq(&c->journal); do_update = true; } do_update: if (do_update) { ret = __bch2_fsck_write_inode(trans, &u); bch_err_msg(c, ret, "in fsck updating inode"); if (ret) goto err_noprint; } err: fsck_err: bch_err_fn(c, ret); err_noprint: printbuf_exit(&buf); return ret; } int bch2_check_inodes(struct bch_fs *c) { struct bch_inode_unpacked snapshot_root = {}; struct snapshots_seen s; snapshots_seen_init(&s); int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_inode(trans, &iter, k, &snapshot_root, &s))); snapshots_seen_exit(&s); bch_err_fn(c, ret); return ret; } static int find_oldest_inode_needs_reattach(struct btree_trans *trans, struct bch_inode_unpacked *inode) { struct bch_fs *c = trans->c; struct btree_iter iter; struct bkey_s_c k; int ret = 0; /* * We look for inodes to reattach in natural key order, leaves first, * but we should do the reattach at the oldest version that needs to be * reattached: */ for_each_btree_key_norestart(trans, iter, BTREE_ID_inodes, SPOS(0, inode->bi_inum, inode->bi_snapshot + 1), BTREE_ITER_all_snapshots, k, ret) { if (k.k->p.offset != inode->bi_inum) break; if (!bch2_snapshot_is_ancestor(c, inode->bi_snapshot, k.k->p.snapshot)) continue; if (!bkey_is_inode(k.k)) break; struct bch_inode_unpacked parent_inode; ret = bch2_inode_unpack(k, &parent_inode); if (ret) break; if (!inode_should_reattach(&parent_inode)) break; *inode = parent_inode; } bch2_trans_iter_exit(trans, &iter); return ret; } static int check_unreachable_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct printbuf buf = PRINTBUF; int ret = 0; if (!bkey_is_inode(k.k)) return 0; struct bch_inode_unpacked inode; ret = bch2_inode_unpack(k, &inode); if (ret) return ret; if (!inode_should_reattach(&inode)) return 0; ret = find_oldest_inode_needs_reattach(trans, &inode); if (ret) return ret; if (fsck_err(trans, inode_unreachable, "unreachable inode:\n%s", (bch2_inode_unpacked_to_text(&buf, &inode), buf.buf))) ret = reattach_inode(trans, &inode); fsck_err: printbuf_exit(&buf); return ret; } /* * Reattach unreachable (but not unlinked) inodes * * Run after check_inodes() and check_dirents(), so we node that inode * backpointer fields point to valid dirents, and every inode that has a dirent * that points to it has its backpointer field set - so we're just looking for * non-unlinked inodes without backpointers: * * XXX: this is racy w.r.t. hardlink removal in online fsck */ int bch2_check_unreachable_inodes(struct bch_fs *c) { int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS_MIN, BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_unreachable_inode(trans, &iter, k))); bch_err_fn(c, ret); return ret; } static inline bool btree_matches_i_mode(enum btree_id btree, unsigned mode) { switch (btree) { case BTREE_ID_extents: return S_ISREG(mode) || S_ISLNK(mode); case BTREE_ID_dirents: return S_ISDIR(mode); case BTREE_ID_xattrs: return true; default: BUG(); } } static int check_key_has_inode(struct btree_trans *trans, struct btree_iter *iter, struct inode_walker *inode, struct inode_walker_entry *i, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; struct btree_iter iter2 = {}; int ret = PTR_ERR_OR_ZERO(i); if (ret) return ret; if (k.k->type == KEY_TYPE_whiteout) goto out; bool have_inode = i && !i->whiteout; if (!have_inode && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_inodes))) goto reconstruct; if (have_inode && btree_matches_i_mode(iter->btree_id, i->inode.bi_mode)) goto out; prt_printf(&buf, ", "); bool have_old_inode = false; darray_for_each(inode->inodes, i2) if (!i2->whiteout && bch2_snapshot_is_ancestor(c, k.k->p.snapshot, i2->inode.bi_snapshot) && btree_matches_i_mode(iter->btree_id, i2->inode.bi_mode)) { prt_printf(&buf, "but found good inode in older snapshot\n"); bch2_inode_unpacked_to_text(&buf, &i2->inode); prt_newline(&buf); have_old_inode = true; break; } struct bkey_s_c k2; unsigned nr_keys = 0; prt_printf(&buf, "found keys:\n"); for_each_btree_key_max_norestart(trans, iter2, iter->btree_id, SPOS(k.k->p.inode, 0, k.k->p.snapshot), POS(k.k->p.inode, U64_MAX), 0, k2, ret) { nr_keys++; if (nr_keys <= 10) { bch2_bkey_val_to_text(&buf, c, k2); prt_newline(&buf); } if (nr_keys >= 100) break; } if (ret) goto err; if (nr_keys > 100) prt_printf(&buf, "found > %u keys for this missing inode\n", nr_keys); else if (nr_keys > 10) prt_printf(&buf, "found %u keys for this missing inode\n", nr_keys); if (!have_inode) { if (fsck_err_on(!have_inode, trans, key_in_missing_inode, "key in missing inode%s", buf.buf)) { /* * Maybe a deletion that raced with data move, or something * weird like that? But if we know the inode was deleted, or * it's just a few keys, we can safely delete them. * * If it's many keys, we should probably recreate the inode */ if (have_old_inode || nr_keys <= 2) goto delete; else goto reconstruct; } } else { /* * not autofix, this one would be a giant wtf - bit error in the * inode corrupting i_mode? * * may want to try repairing inode instead of deleting */ if (fsck_err_on(!btree_matches_i_mode(iter->btree_id, i->inode.bi_mode), trans, key_in_wrong_inode_type, "key for wrong inode mode %o%s", i->inode.bi_mode, buf.buf)) goto delete; } out: err: fsck_err: bch2_trans_iter_exit(trans, &iter2); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; delete: /* * XXX: print out more info * count up extents for this inode, check if we have different inode in * an older snapshot version, perhaps decide if we want to reconstitute */ ret = bch2_btree_delete_at(trans, iter, BTREE_UPDATE_internal_snapshot_node); goto out; reconstruct: ret = reconstruct_inode(trans, iter->btree_id, k.k->p.snapshot, k.k->p.inode) ?: bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret) goto err; inode->last_pos.inode--; ret = bch_err_throw(c, transaction_restart_nested); goto out; } static int check_i_sectors_notnested(struct btree_trans *trans, struct inode_walker *w) { struct bch_fs *c = trans->c; int ret = 0; s64 count2; darray_for_each(w->inodes, i) { if (i->inode.bi_sectors == i->count) continue; count2 = bch2_count_inode_sectors(trans, w->last_pos.inode, i->inode.bi_snapshot); if (w->recalculate_sums) i->count = count2; if (i->count != count2) { bch_err_ratelimited(c, "fsck counted i_sectors wrong for inode %llu:%u: got %llu should be %llu", w->last_pos.inode, i->inode.bi_snapshot, i->count, count2); i->count = count2; } if (fsck_err_on(!(i->inode.bi_flags & BCH_INODE_i_sectors_dirty), trans, inode_i_sectors_wrong, "inode %llu:%u has incorrect i_sectors: got %llu, should be %llu", w->last_pos.inode, i->inode.bi_snapshot, i->inode.bi_sectors, i->count)) { i->inode.bi_sectors = i->count; ret = bch2_fsck_write_inode(trans, &i->inode); if (ret) break; } } fsck_err: bch_err_fn(c, ret); return ret; } static int check_i_sectors(struct btree_trans *trans, struct inode_walker *w) { u32 restart_count = trans->restart_count; return check_i_sectors_notnested(trans, w) ?: trans_was_restarted(trans, restart_count); } struct extent_end { u32 snapshot; u64 offset; struct snapshots_seen seen; }; struct extent_ends { struct bpos last_pos; DARRAY(struct extent_end) e; }; static void extent_ends_reset(struct extent_ends *extent_ends) { darray_for_each(extent_ends->e, i) snapshots_seen_exit(&i->seen); extent_ends->e.nr = 0; } static void extent_ends_exit(struct extent_ends *extent_ends) { extent_ends_reset(extent_ends); darray_exit(&extent_ends->e); } static void extent_ends_init(struct extent_ends *extent_ends) { memset(extent_ends, 0, sizeof(*extent_ends)); } static int extent_ends_at(struct bch_fs *c, struct extent_ends *extent_ends, struct snapshots_seen *seen, struct bkey_s_c k) { struct extent_end *i, n = (struct extent_end) { .offset = k.k->p.offset, .snapshot = k.k->p.snapshot, .seen = *seen, }; n.seen.ids.data = kmemdup(seen->ids.data, sizeof(seen->ids.data[0]) * seen->ids.size, GFP_KERNEL); if (!n.seen.ids.data) return bch_err_throw(c, ENOMEM_fsck_extent_ends_at); __darray_for_each(extent_ends->e, i) { if (i->snapshot == k.k->p.snapshot) { snapshots_seen_exit(&i->seen); *i = n; return 0; } if (i->snapshot >= k.k->p.snapshot) break; } return darray_insert_item(&extent_ends->e, i - extent_ends->e.data, n); } static int overlapping_extents_found(struct btree_trans *trans, enum btree_id btree, struct bpos pos1, struct snapshots_seen *pos1_seen, struct bkey pos2, bool *fixed, struct extent_end *extent_end) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; struct btree_iter iter1, iter2 = {}; struct bkey_s_c k1, k2; int ret; BUG_ON(bkey_le(pos1, bkey_start_pos(&pos2))); bch2_trans_iter_init(trans, &iter1, btree, pos1, BTREE_ITER_all_snapshots| BTREE_ITER_not_extents); k1 = bch2_btree_iter_peek_max(trans, &iter1, POS(pos1.inode, U64_MAX)); ret = bkey_err(k1); if (ret) goto err; prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, k1); if (!bpos_eq(pos1, k1.k->p)) { prt_str(&buf, "\nwanted\n "); bch2_bpos_to_text(&buf, pos1); prt_str(&buf, "\n"); bch2_bkey_to_text(&buf, &pos2); bch_err(c, "%s: error finding first overlapping extent when repairing, got%s", __func__, buf.buf); ret = bch_err_throw(c, internal_fsck_err); goto err; } bch2_trans_copy_iter(trans, &iter2, &iter1); while (1) { bch2_btree_iter_advance(trans, &iter2); k2 = bch2_btree_iter_peek_max(trans, &iter2, POS(pos1.inode, U64_MAX)); ret = bkey_err(k2); if (ret) goto err; if (bpos_ge(k2.k->p, pos2.p)) break; } prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, k2); if (bpos_gt(k2.k->p, pos2.p) || pos2.size != k2.k->size) { bch_err(c, "%s: error finding seconding overlapping extent when repairing%s", __func__, buf.buf); ret = bch_err_throw(c, internal_fsck_err); goto err; } prt_printf(&buf, "\noverwriting %s extent", pos1.snapshot >= pos2.p.snapshot ? "first" : "second"); if (fsck_err(trans, extent_overlapping, "overlapping extents%s", buf.buf)) { struct btree_iter *old_iter = &iter1; struct disk_reservation res = { 0 }; if (pos1.snapshot < pos2.p.snapshot) { old_iter = &iter2; swap(k1, k2); } trans->extra_disk_res += bch2_bkey_sectors_compressed(k2); ret = bch2_trans_update_extent_overwrite(trans, old_iter, BTREE_UPDATE_internal_snapshot_node, k1, k2) ?: bch2_trans_commit(trans, &res, NULL, BCH_TRANS_COMMIT_no_enospc); bch2_disk_reservation_put(c, &res); bch_info(c, "repair ret %s", bch2_err_str(ret)); if (ret) goto err; *fixed = true; if (pos1.snapshot == pos2.p.snapshot) { /* * We overwrote the first extent, and did the overwrite * in the same snapshot: */ extent_end->offset = bkey_start_offset(&pos2); } else if (pos1.snapshot > pos2.p.snapshot) { /* * We overwrote the first extent in pos2's snapshot: */ ret = snapshots_seen_add_inorder(c, pos1_seen, pos2.p.snapshot); } else { /* * We overwrote the second extent - restart * check_extent() from the top: */ ret = bch_err_throw(c, transaction_restart_nested); } } fsck_err: err: bch2_trans_iter_exit(trans, &iter2); bch2_trans_iter_exit(trans, &iter1); printbuf_exit(&buf); return ret; } static int check_overlapping_extents(struct btree_trans *trans, struct snapshots_seen *seen, struct extent_ends *extent_ends, struct bkey_s_c k, struct btree_iter *iter, bool *fixed) { struct bch_fs *c = trans->c; int ret = 0; /* transaction restart, running again */ if (bpos_eq(extent_ends->last_pos, k.k->p)) return 0; if (extent_ends->last_pos.inode != k.k->p.inode) extent_ends_reset(extent_ends); darray_for_each(extent_ends->e, i) { if (i->offset <= bkey_start_offset(k.k)) continue; if (!ref_visible2(c, k.k->p.snapshot, seen, i->snapshot, &i->seen)) continue; ret = overlapping_extents_found(trans, iter->btree_id, SPOS(iter->pos.inode, i->offset, i->snapshot), &i->seen, *k.k, fixed, i); if (ret) goto err; } extent_ends->last_pos = k.k->p; err: return ret; } static int check_extent_overbig(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct bkey_ptrs_c ptrs = bch2_bkey_ptrs_c(k); struct bch_extent_crc_unpacked crc; const union bch_extent_entry *i; unsigned encoded_extent_max_sectors = c->opts.encoded_extent_max >> 9; bkey_for_each_crc(k.k, ptrs, crc, i) if (crc_is_encoded(crc) && crc.uncompressed_size > encoded_extent_max_sectors) { struct printbuf buf = PRINTBUF; bch2_bkey_val_to_text(&buf, c, k); bch_err(c, "overbig encoded extent, please report this:\n %s", buf.buf); printbuf_exit(&buf); } return 0; } static int check_extent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct inode_walker *inode, struct snapshots_seen *s, struct extent_ends *extent_ends, struct disk_reservation *res) { struct bch_fs *c = trans->c; struct printbuf buf = PRINTBUF; int ret = 0; ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret) { ret = ret < 0 ? ret : 0; goto out; } if (inode->last_pos.inode != k.k->p.inode && inode->have_inodes) { ret = check_i_sectors(trans, inode); if (ret) goto err; } ret = snapshots_seen_update(c, s, iter->btree_id, k.k->p); if (ret) goto err; struct inode_walker_entry *extent_i = walk_inode(trans, inode, k); ret = PTR_ERR_OR_ZERO(extent_i); if (ret) goto err; ret = check_key_has_inode(trans, iter, inode, extent_i, k); if (ret) goto err; if (k.k->type != KEY_TYPE_whiteout) { ret = check_overlapping_extents(trans, s, extent_ends, k, iter, &inode->recalculate_sums); if (ret) goto err; /* * Check inodes in reverse order, from oldest snapshots to * newest, starting from the inode that matches this extent's * snapshot. If we didn't have one, iterate over all inodes: */ for (struct inode_walker_entry *i = extent_i ?: &darray_last(inode->inodes); inode->inodes.data && i >= inode->inodes.data; --i) { if (i->inode.bi_snapshot > k.k->p.snapshot || !key_visible_in_snapshot(c, s, i->inode.bi_snapshot, k.k->p.snapshot)) continue; u64 last_block = round_up(i->inode.bi_size, block_bytes(c)) >> 9; if (fsck_err_on(k.k->p.offset > last_block && !bkey_extent_is_reservation(k), trans, extent_past_end_of_inode, "extent type past end of inode %llu:%u, i_size %llu\n%s", i->inode.bi_inum, i->inode.bi_snapshot, i->inode.bi_size, (bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { ret = snapshots_seen_add_inorder(c, s, i->inode.bi_snapshot) ?: bch2_fpunch_snapshot(trans, SPOS(i->inode.bi_inum, last_block, i->inode.bi_snapshot), POS(i->inode.bi_inum, U64_MAX)); if (ret) goto err; iter->k.type = KEY_TYPE_whiteout; break; } } } ret = bch2_trans_commit(trans, res, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret) goto err; if (bkey_extent_is_allocation(k.k)) { for (struct inode_walker_entry *i = extent_i ?: &darray_last(inode->inodes); inode->inodes.data && i >= inode->inodes.data; --i) { if (i->whiteout || i->inode.bi_snapshot > k.k->p.snapshot || !key_visible_in_snapshot(c, s, i->inode.bi_snapshot, k.k->p.snapshot)) continue; i->count += k.k->size; } } if (k.k->type != KEY_TYPE_whiteout) { ret = extent_ends_at(c, extent_ends, s, k); if (ret) goto err; } out: err: fsck_err: printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } /* * Walk extents: verify that extents have a corresponding S_ISREG inode, and * that i_size an i_sectors are consistent */ int bch2_check_extents(struct bch_fs *c) { struct inode_walker w = inode_walker_init(); struct snapshots_seen s; struct extent_ends extent_ends; struct disk_reservation res = { 0 }; snapshots_seen_init(&s); extent_ends_init(&extent_ends); int ret = bch2_trans_run(c, for_each_btree_key(trans, iter, BTREE_ID_extents, POS(BCACHEFS_ROOT_INO, 0), BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, ({ bch2_disk_reservation_put(c, &res); check_extent(trans, &iter, k, &w, &s, &extent_ends, &res) ?: check_extent_overbig(trans, &iter, k); })) ?: check_i_sectors_notnested(trans, &w)); bch2_disk_reservation_put(c, &res); extent_ends_exit(&extent_ends); inode_walker_exit(&w); snapshots_seen_exit(&s); bch_err_fn(c, ret); return ret; } int bch2_check_indirect_extents(struct bch_fs *c) { struct disk_reservation res = { 0 }; int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_reflink, POS_MIN, BTREE_ITER_prefetch, k, &res, NULL, BCH_TRANS_COMMIT_no_enospc, ({ bch2_disk_reservation_put(c, &res); check_extent_overbig(trans, &iter, k); }))); bch2_disk_reservation_put(c, &res); bch_err_fn(c, ret); return ret; } static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_walker *w) { struct bch_fs *c = trans->c; int ret = 0; s64 count2; darray_for_each(w->inodes, i) { if (i->inode.bi_nlink == i->count) continue; count2 = bch2_count_subdirs(trans, w->last_pos.inode, i->inode.bi_snapshot); if (count2 < 0) return count2; if (i->count != count2) { bch_err_ratelimited(c, "fsck counted subdirectories wrong for inum %llu:%u: got %llu should be %llu", w->last_pos.inode, i->inode.bi_snapshot, i->count, count2); i->count = count2; if (i->inode.bi_nlink == i->count) continue; } if (i->inode.bi_nlink != i->count) { CLASS(printbuf, buf)(); lockrestart_do(trans, bch2_inum_snapshot_to_path(trans, w->last_pos.inode, i->inode.bi_snapshot, NULL, &buf)); if (fsck_err_on(i->inode.bi_nlink != i->count, trans, inode_dir_wrong_nlink, "directory with wrong i_nlink: got %u, should be %llu\n%s", i->inode.bi_nlink, i->count, buf.buf)) { i->inode.bi_nlink = i->count; ret = bch2_fsck_write_inode(trans, &i->inode); if (ret) break; } } } fsck_err: bch_err_fn(c, ret); return ret; } static int check_subdir_dirents_count(struct btree_trans *trans, struct inode_walker *w) { u32 restart_count = trans->restart_count; return check_subdir_count_notnested(trans, w) ?: trans_was_restarted(trans, restart_count); } /* find a subvolume that's a descendent of @snapshot: */ static int find_snapshot_subvol(struct btree_trans *trans, u32 snapshot, u32 *subvolid) { struct btree_iter iter; struct bkey_s_c k; int ret; for_each_btree_key_norestart(trans, iter, BTREE_ID_subvolumes, POS_MIN, 0, k, ret) { if (k.k->type != KEY_TYPE_subvolume) continue; struct bkey_s_c_subvolume s = bkey_s_c_to_subvolume(k); if (bch2_snapshot_is_ancestor(trans->c, le32_to_cpu(s.v->snapshot), snapshot)) { bch2_trans_iter_exit(trans, &iter); *subvolid = k.k->p.offset; goto found; } } if (!ret) ret = -ENOENT; found: bch2_trans_iter_exit(trans, &iter); return ret; } noinline_for_stack static int check_dirent_to_subvol(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c_dirent d) { struct bch_fs *c = trans->c; struct btree_iter subvol_iter = {}; struct bch_inode_unpacked subvol_root; u32 parent_subvol = le32_to_cpu(d.v->d_parent_subvol); u32 target_subvol = le32_to_cpu(d.v->d_child_subvol); u32 parent_snapshot; u32 new_parent_subvol = 0; u64 parent_inum; struct printbuf buf = PRINTBUF; int ret = 0; ret = subvol_lookup(trans, parent_subvol, &parent_snapshot, &parent_inum); if (ret && !bch2_err_matches(ret, ENOENT)) return ret; if (ret || (!ret && !bch2_snapshot_is_ancestor(c, parent_snapshot, d.k->p.snapshot))) { int ret2 = find_snapshot_subvol(trans, d.k->p.snapshot, &new_parent_subvol); if (ret2 && !bch2_err_matches(ret, ENOENT)) return ret2; } if (ret && !new_parent_subvol && (c->sb.btrees_lost_data & BIT_ULL(BTREE_ID_subvolumes))) { /* * Couldn't find a subvol for dirent's snapshot - but we lost * subvols, so we need to reconstruct: */ ret = reconstruct_subvol(trans, d.k->p.snapshot, parent_subvol, 0); if (ret) return ret; parent_snapshot = d.k->p.snapshot; } if (fsck_err_on(ret, trans, dirent_to_missing_parent_subvol, "dirent parent_subvol points to missing subvolume\n%s", (bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf)) || fsck_err_on(!ret && !bch2_snapshot_is_ancestor(c, parent_snapshot, d.k->p.snapshot), trans, dirent_not_visible_in_parent_subvol, "dirent not visible in parent_subvol (not an ancestor of subvol snap %u)\n%s", parent_snapshot, (bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf))) { if (!new_parent_subvol) { bch_err(c, "could not find a subvol for snapshot %u", d.k->p.snapshot); return bch_err_throw(c, fsck_repair_unimplemented); } struct bkey_i_dirent *new_dirent = bch2_bkey_make_mut_typed(trans, iter, &d.s_c, 0, dirent); ret = PTR_ERR_OR_ZERO(new_dirent); if (ret) goto err; new_dirent->v.d_parent_subvol = cpu_to_le32(new_parent_subvol); } struct bkey_s_c_subvolume s = bch2_bkey_get_iter_typed(trans, &subvol_iter, BTREE_ID_subvolumes, POS(0, target_subvol), 0, subvolume); ret = bkey_err(s.s_c); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; if (ret) { if (fsck_err(trans, dirent_to_missing_subvol, "dirent points to missing subvolume\n%s", (bch2_bkey_val_to_text(&buf, c, d.s_c), buf.buf))) return bch2_fsck_remove_dirent(trans, d.k->p); ret = 0; goto out; } if (le32_to_cpu(s.v->fs_path_parent) != parent_subvol) { printbuf_reset(&buf); prt_printf(&buf, "subvol with wrong fs_path_parent, should be be %u\n", parent_subvol); ret = bch2_inum_to_path(trans, (subvol_inum) { s.k->p.offset, le64_to_cpu(s.v->inode) }, &buf); if (ret) goto err; prt_newline(&buf); bch2_bkey_val_to_text(&buf, c, s.s_c); if (fsck_err(trans, subvol_fs_path_parent_wrong, "%s", buf.buf)) { struct bkey_i_subvolume *n = bch2_bkey_make_mut_typed(trans, &subvol_iter, &s.s_c, 0, subvolume); ret = PTR_ERR_OR_ZERO(n); if (ret) goto err; n->v.fs_path_parent = cpu_to_le32(parent_subvol); } } u64 target_inum = le64_to_cpu(s.v->inode); u32 target_snapshot = le32_to_cpu(s.v->snapshot); ret = bch2_inode_find_by_inum_snapshot(trans, target_inum, target_snapshot, &subvol_root, 0); if (ret && !bch2_err_matches(ret, ENOENT)) goto err; if (ret) { bch_err(c, "subvol %u points to missing inode root %llu", target_subvol, target_inum); ret = bch_err_throw(c, fsck_repair_unimplemented); goto err; } if (fsck_err_on(!ret && parent_subvol != subvol_root.bi_parent_subvol, trans, inode_bi_parent_wrong, "subvol root %llu has wrong bi_parent_subvol: got %u, should be %u", target_inum, subvol_root.bi_parent_subvol, parent_subvol)) { subvol_root.bi_parent_subvol = parent_subvol; subvol_root.bi_snapshot = le32_to_cpu(s.v->snapshot); ret = __bch2_fsck_write_inode(trans, &subvol_root); if (ret) goto err; } ret = bch2_check_dirent_target(trans, iter, d, &subvol_root, true); if (ret) goto err; out: err: fsck_err: bch2_trans_iter_exit(trans, &subvol_iter); printbuf_exit(&buf); return ret; } static int check_dirent(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct bch_hash_info *hash_info, struct inode_walker *dir, struct inode_walker *target, struct snapshots_seen *s, bool *need_second_pass) { struct bch_fs *c = trans->c; struct inode_walker_entry *i; struct printbuf buf = PRINTBUF; int ret = 0; ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret) { ret = ret < 0 ? ret : 0; goto out; } ret = snapshots_seen_update(c, s, iter->btree_id, k.k->p); if (ret) goto err; if (k.k->type == KEY_TYPE_whiteout) goto out; if (dir->last_pos.inode != k.k->p.inode && dir->have_inodes) { ret = check_subdir_dirents_count(trans, dir); if (ret) goto err; } i = walk_inode(trans, dir, k); ret = PTR_ERR_OR_ZERO(i); if (ret < 0) goto err; ret = check_key_has_inode(trans, iter, dir, i, k); if (ret) goto err; if (!i || i->whiteout) goto out; if (dir->first_this_inode) *hash_info = bch2_hash_info_init(c, &i->inode); dir->first_this_inode = false; hash_info->cf_encoding = bch2_inode_casefold(c, &i->inode) ? c->cf_encoding : NULL; ret = bch2_str_hash_check_key(trans, s, &bch2_dirent_hash_desc, hash_info, iter, k, need_second_pass); if (ret < 0) goto err; if (ret) { /* dirent has been deleted */ ret = 0; goto out; } if (k.k->type != KEY_TYPE_dirent) goto out; struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); /* check casefold */ if (fsck_err_on(d.v->d_casefold != !!hash_info->cf_encoding, trans, dirent_casefold_mismatch, "dirent casefold does not match dir casefold\n%s", (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { subvol_inum dir_inum = { .subvol = d.v->d_type == DT_SUBVOL ? le32_to_cpu(d.v->d_parent_subvol) : 0, }; u64 target = d.v->d_type == DT_SUBVOL ? le32_to_cpu(d.v->d_child_subvol) : le64_to_cpu(d.v->d_inum); struct qstr name = bch2_dirent_get_name(d); struct bkey_i_dirent *new_d = bch2_dirent_create_key(trans, hash_info, dir_inum, d.v->d_type, &name, NULL, target); ret = PTR_ERR_OR_ZERO(new_d); if (ret) goto out; new_d->k.p.inode = d.k->p.inode; new_d->k.p.snapshot = d.k->p.snapshot; struct btree_iter dup_iter = {}; ret = bch2_hash_delete_at(trans, bch2_dirent_hash_desc, hash_info, iter, BTREE_UPDATE_internal_snapshot_node) ?: bch2_str_hash_repair_key(trans, s, &bch2_dirent_hash_desc, hash_info, iter, bkey_i_to_s_c(&new_d->k_i), &dup_iter, bkey_s_c_null, need_second_pass); goto out; } if (d.v->d_type == DT_SUBVOL) { ret = check_dirent_to_subvol(trans, iter, d); if (ret) goto err; } else { ret = get_visible_inodes(trans, target, s, le64_to_cpu(d.v->d_inum)); if (ret) goto err; if (fsck_err_on(!target->inodes.nr, trans, dirent_to_missing_inode, "dirent points to missing inode:\n%s", (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { ret = bch2_fsck_remove_dirent(trans, d.k->p); if (ret) goto err; } darray_for_each(target->inodes, i) { ret = bch2_check_dirent_target(trans, iter, d, &i->inode, true); if (ret) goto err; } darray_for_each(target->deletes, i) if (fsck_err_on(!snapshot_list_has_id(&s->ids, *i), trans, dirent_to_overwritten_inode, "dirent points to inode overwritten in snapshot %u:\n%s", *i, (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, k), buf.buf))) { struct btree_iter delete_iter; bch2_trans_iter_init(trans, &delete_iter, BTREE_ID_dirents, SPOS(k.k->p.inode, k.k->p.offset, *i), BTREE_ITER_intent); ret = bch2_btree_iter_traverse(trans, &delete_iter) ?: bch2_hash_delete_at(trans, bch2_dirent_hash_desc, hash_info, &delete_iter, BTREE_UPDATE_internal_snapshot_node); bch2_trans_iter_exit(trans, &delete_iter); if (ret) goto err; } } ret = bch2_trans_commit(trans, NULL, NULL, BCH_TRANS_COMMIT_no_enospc); if (ret) goto err; for_each_visible_inode(c, s, dir, d.k->p.snapshot, i) { if (d.v->d_type == DT_DIR) i->count++; i->i_size += bkey_bytes(d.k); } out: err: fsck_err: printbuf_exit(&buf); return ret; } /* * Walk dirents: verify that they all have a corresponding S_ISDIR inode, * validate d_type */ int bch2_check_dirents(struct bch_fs *c) { struct inode_walker dir = inode_walker_init(); struct inode_walker target = inode_walker_init(); struct snapshots_seen s; struct bch_hash_info hash_info; bool need_second_pass = false, did_second_pass = false; int ret; snapshots_seen_init(&s); again: ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_dirents, POS(BCACHEFS_ROOT_INO, 0), BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_dirent(trans, &iter, k, &hash_info, &dir, &target, &s, &need_second_pass)) ?: check_subdir_count_notnested(trans, &dir)); if (!ret && need_second_pass && !did_second_pass) { bch_info(c, "check_dirents requires second pass"); swap(did_second_pass, need_second_pass); goto again; } if (!ret && need_second_pass) { bch_err(c, "dirents not repairing"); ret = -EINVAL; } snapshots_seen_exit(&s); inode_walker_exit(&dir); inode_walker_exit(&target); bch_err_fn(c, ret); return ret; } static int check_xattr(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct bch_hash_info *hash_info, struct inode_walker *inode) { struct bch_fs *c = trans->c; int ret = bch2_check_key_has_snapshot(trans, iter, k); if (ret < 0) return ret; if (ret) return 0; struct inode_walker_entry *i = walk_inode(trans, inode, k); ret = PTR_ERR_OR_ZERO(i); if (ret) return ret; ret = check_key_has_inode(trans, iter, inode, i, k); if (ret) return ret; if (!i || i->whiteout) return 0; if (inode->first_this_inode) *hash_info = bch2_hash_info_init(c, &i->inode); inode->first_this_inode = false; bool need_second_pass = false; return bch2_str_hash_check_key(trans, NULL, &bch2_xattr_hash_desc, hash_info, iter, k, &need_second_pass); } /* * Walk xattrs: verify that they all have a corresponding inode */ int bch2_check_xattrs(struct bch_fs *c) { struct inode_walker inode = inode_walker_init(); struct bch_hash_info hash_info; int ret = 0; ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_xattrs, POS(BCACHEFS_ROOT_INO, 0), BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_xattr(trans, &iter, k, &hash_info, &inode))); inode_walker_exit(&inode); bch_err_fn(c, ret); return ret; } static int check_root_trans(struct btree_trans *trans) { struct bch_fs *c = trans->c; struct bch_inode_unpacked root_inode; u32 snapshot; u64 inum; int ret; ret = subvol_lookup(trans, BCACHEFS_ROOT_SUBVOL, &snapshot, &inum); if (ret && !bch2_err_matches(ret, ENOENT)) return ret; if (mustfix_fsck_err_on(ret, trans, root_subvol_missing, "root subvol missing")) { struct bkey_i_subvolume *root_subvol = bch2_trans_kmalloc(trans, sizeof(*root_subvol)); ret = PTR_ERR_OR_ZERO(root_subvol); if (ret) goto err; snapshot = U32_MAX; inum = BCACHEFS_ROOT_INO; bkey_subvolume_init(&root_subvol->k_i); root_subvol->k.p.offset = BCACHEFS_ROOT_SUBVOL; root_subvol->v.flags = 0; root_subvol->v.snapshot = cpu_to_le32(snapshot); root_subvol->v.inode = cpu_to_le64(inum); ret = bch2_btree_insert_trans(trans, BTREE_ID_subvolumes, &root_subvol->k_i, 0); bch_err_msg(c, ret, "writing root subvol"); if (ret) goto err; } ret = bch2_inode_find_by_inum_snapshot(trans, BCACHEFS_ROOT_INO, snapshot, &root_inode, 0); if (ret && !bch2_err_matches(ret, ENOENT)) return ret; if (mustfix_fsck_err_on(ret, trans, root_dir_missing, "root directory missing") || mustfix_fsck_err_on(!S_ISDIR(root_inode.bi_mode), trans, root_inode_not_dir, "root inode not a directory")) { bch2_inode_init(c, &root_inode, 0, 0, S_IFDIR|0755, 0, NULL); root_inode.bi_inum = inum; root_inode.bi_snapshot = snapshot; ret = __bch2_fsck_write_inode(trans, &root_inode); bch_err_msg(c, ret, "writing root inode"); } err: fsck_err: return ret; } /* Get root directory, create if it doesn't exist: */ int bch2_check_root(struct bch_fs *c) { int ret = bch2_trans_commit_do(c, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_root_trans(trans)); bch_err_fn(c, ret); return ret; } static bool darray_u32_has(darray_u32 *d, u32 v) { darray_for_each(*d, i) if (*i == v) return true; return false; } static int check_subvol_path(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bch_fs *c = trans->c; struct btree_iter parent_iter = {}; darray_u32 subvol_path = {}; struct printbuf buf = PRINTBUF; int ret = 0; if (k.k->type != KEY_TYPE_subvolume) return 0; subvol_inum start = { .subvol = k.k->p.offset, .inum = le64_to_cpu(bkey_s_c_to_subvolume(k).v->inode), }; while (k.k->p.offset != BCACHEFS_ROOT_SUBVOL) { ret = darray_push(&subvol_path, k.k->p.offset); if (ret) goto err; struct bkey_s_c_subvolume s = bkey_s_c_to_subvolume(k); struct bch_inode_unpacked subvol_root; ret = bch2_inode_find_by_inum_trans(trans, (subvol_inum) { s.k->p.offset, le64_to_cpu(s.v->inode) }, &subvol_root); if (ret) break; u32 parent = le32_to_cpu(s.v->fs_path_parent); if (darray_u32_has(&subvol_path, parent)) { printbuf_reset(&buf); prt_printf(&buf, "subvolume loop: "); ret = bch2_inum_to_path(trans, start, &buf); if (ret) goto err; if (fsck_err(trans, subvol_loop, "%s", buf.buf)) ret = reattach_subvol(trans, s); break; } bch2_trans_iter_exit(trans, &parent_iter); bch2_trans_iter_init(trans, &parent_iter, BTREE_ID_subvolumes, POS(0, parent), 0); k = bch2_btree_iter_peek_slot(trans, &parent_iter); ret = bkey_err(k); if (ret) goto err; if (fsck_err_on(k.k->type != KEY_TYPE_subvolume, trans, subvol_unreachable, "unreachable subvolume %s", (printbuf_reset(&buf), bch2_bkey_val_to_text(&buf, c, s.s_c), buf.buf))) { ret = reattach_subvol(trans, s); break; } } fsck_err: err: printbuf_exit(&buf); darray_exit(&subvol_path); bch2_trans_iter_exit(trans, &parent_iter); return ret; } int bch2_check_subvolume_structure(struct bch_fs *c) { int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_subvolumes, POS_MIN, BTREE_ITER_prefetch, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_subvol_path(trans, &iter, k))); bch_err_fn(c, ret); return ret; } static int bch2_bi_depth_renumber_one(struct btree_trans *trans, u64 inum, u32 snapshot, u32 new_depth) { struct btree_iter iter; struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_inodes, SPOS(0, inum, snapshot), 0); struct bch_inode_unpacked inode; int ret = bkey_err(k) ?: !bkey_is_inode(k.k) ? -BCH_ERR_ENOENT_inode : bch2_inode_unpack(k, &inode); if (ret) goto err; if (inode.bi_depth != new_depth) { inode.bi_depth = new_depth; ret = __bch2_fsck_write_inode(trans, &inode) ?: bch2_trans_commit(trans, NULL, NULL, 0); } err: bch2_trans_iter_exit(trans, &iter); return ret; } static int bch2_bi_depth_renumber(struct btree_trans *trans, darray_u64 *path, u32 snapshot, u32 new_bi_depth) { u32 restart_count = trans->restart_count; int ret = 0; darray_for_each_reverse(*path, i) { ret = nested_lockrestart_do(trans, bch2_bi_depth_renumber_one(trans, *i, snapshot, new_bi_depth)); bch_err_fn(trans->c, ret); if (ret) break; new_bi_depth++; } return ret ?: trans_was_restarted(trans, restart_count); } static int check_path_loop(struct btree_trans *trans, struct bkey_s_c inode_k) { struct bch_fs *c = trans->c; struct btree_iter inode_iter = {}; darray_u64 path = {}; struct printbuf buf = PRINTBUF; u32 snapshot = inode_k.k->p.snapshot; bool redo_bi_depth = false; u32 min_bi_depth = U32_MAX; int ret = 0; struct bpos start = inode_k.k->p; struct bch_inode_unpacked inode; ret = bch2_inode_unpack(inode_k, &inode); if (ret) return ret; /* * If we're running full fsck, check_dirents() will have already ran, * and we shouldn't see any missing backpointers here - otherwise that's * handled separately, by check_unreachable_inodes */ while (!inode.bi_subvol && bch2_inode_has_backpointer(&inode)) { struct btree_iter dirent_iter; struct bkey_s_c_dirent d; d = dirent_get_by_pos(trans, &dirent_iter, SPOS(inode.bi_dir, inode.bi_dir_offset, snapshot)); ret = bkey_err(d.s_c); if (ret && !bch2_err_matches(ret, ENOENT)) goto out; if (!ret && (ret = dirent_points_to_inode(c, d, &inode))) bch2_trans_iter_exit(trans, &dirent_iter); if (bch2_err_matches(ret, ENOENT)) { printbuf_reset(&buf); bch2_bkey_val_to_text(&buf, c, inode_k); bch_err(c, "unreachable inode in check_directory_structure: %s\n%s", bch2_err_str(ret), buf.buf); goto out; } bch2_trans_iter_exit(trans, &dirent_iter); ret = darray_push(&path, inode.bi_inum); if (ret) return ret; bch2_trans_iter_exit(trans, &inode_iter); inode_k = bch2_bkey_get_iter(trans, &inode_iter, BTREE_ID_inodes, SPOS(0, inode.bi_dir, snapshot), 0); struct bch_inode_unpacked parent_inode; ret = bkey_err(inode_k) ?: !bkey_is_inode(inode_k.k) ? -BCH_ERR_ENOENT_inode : bch2_inode_unpack(inode_k, &parent_inode); if (ret) { /* Should have been caught in dirents pass */ bch_err_msg(c, ret, "error looking up parent directory"); goto out; } min_bi_depth = parent_inode.bi_depth; if (parent_inode.bi_depth < inode.bi_depth && min_bi_depth < U16_MAX) break; inode = parent_inode; redo_bi_depth = true; if (darray_find(path, inode.bi_inum)) { printbuf_reset(&buf); prt_printf(&buf, "directory structure loop in snapshot %u: ", snapshot); ret = bch2_inum_snapshot_to_path(trans, start.offset, start.snapshot, NULL, &buf); if (ret) goto out; if (c->opts.verbose) { prt_newline(&buf); darray_for_each(path, i) prt_printf(&buf, "%llu ", *i); } if (fsck_err(trans, dir_loop, "%s", buf.buf)) { ret = remove_backpointer(trans, &inode); bch_err_msg(c, ret, "removing dirent"); if (ret) goto out; ret = reattach_inode(trans, &inode); bch_err_msg(c, ret, "reattaching inode %llu", inode.bi_inum); } goto out; } } if (inode.bi_subvol) min_bi_depth = 0; if (redo_bi_depth) ret = bch2_bi_depth_renumber(trans, &path, snapshot, min_bi_depth); out: fsck_err: bch2_trans_iter_exit(trans, &inode_iter); darray_exit(&path); printbuf_exit(&buf); bch_err_fn(c, ret); return ret; } /* * Check for loops in the directory structure: all other connectivity issues * have been fixed by prior passes */ int bch2_check_directory_structure(struct bch_fs *c) { int ret = bch2_trans_run(c, for_each_btree_key_reverse_commit(trans, iter, BTREE_ID_inodes, POS_MIN, BTREE_ITER_intent| BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, ({ if (!S_ISDIR(bkey_inode_mode(k))) continue; if (bch2_inode_flags(k) & BCH_INODE_unlinked) continue; check_path_loop(trans, k); }))); bch_err_fn(c, ret); return ret; } struct nlink_table { size_t nr; size_t size; struct nlink { u64 inum; u32 snapshot; u32 count; } *d; }; static int add_nlink(struct bch_fs *c, struct nlink_table *t, u64 inum, u32 snapshot) { if (t->nr == t->size) { size_t new_size = max_t(size_t, 128UL, t->size * 2); void *d = kvmalloc_array(new_size, sizeof(t->d[0]), GFP_KERNEL); if (!d) { bch_err(c, "fsck: error allocating memory for nlink_table, size %zu", new_size); return bch_err_throw(c, ENOMEM_fsck_add_nlink); } if (t->d) memcpy(d, t->d, t->size * sizeof(t->d[0])); kvfree(t->d); t->d = d; t->size = new_size; } t->d[t->nr++] = (struct nlink) { .inum = inum, .snapshot = snapshot, }; return 0; } static int nlink_cmp(const void *_l, const void *_r) { const struct nlink *l = _l; const struct nlink *r = _r; return cmp_int(l->inum, r->inum); } static void inc_link(struct bch_fs *c, struct snapshots_seen *s, struct nlink_table *links, u64 range_start, u64 range_end, u64 inum, u32 snapshot) { struct nlink *link, key = { .inum = inum, .snapshot = U32_MAX, }; if (inum < range_start || inum >= range_end) return; link = __inline_bsearch(&key, links->d, links->nr, sizeof(links->d[0]), nlink_cmp); if (!link) return; while (link > links->d && link[0].inum == link[-1].inum) --link; for (; link < links->d + links->nr && link->inum == inum; link++) if (ref_visible(c, s, snapshot, link->snapshot)) { link->count++; if (link->snapshot >= snapshot) break; } } noinline_for_stack static int check_nlinks_find_hardlinks(struct bch_fs *c, struct nlink_table *t, u64 start, u64 *end) { int ret = bch2_trans_run(c, for_each_btree_key(trans, iter, BTREE_ID_inodes, POS(0, start), BTREE_ITER_intent| BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, ({ if (!bkey_is_inode(k.k)) continue; /* Should never fail, checked by bch2_inode_invalid: */ struct bch_inode_unpacked u; _ret3 = bch2_inode_unpack(k, &u); if (_ret3) break; /* * Backpointer and directory structure checks are sufficient for * directories, since they can't have hardlinks: */ if (S_ISDIR(u.bi_mode)) continue; /* * Previous passes ensured that bi_nlink is nonzero if * it had multiple hardlinks: */ if (!u.bi_nlink) continue; ret = add_nlink(c, t, k.k->p.offset, k.k->p.snapshot); if (ret) { *end = k.k->p.offset; ret = 0; break; } 0; }))); bch_err_fn(c, ret); return ret; } noinline_for_stack static int check_nlinks_walk_dirents(struct bch_fs *c, struct nlink_table *links, u64 range_start, u64 range_end) { struct snapshots_seen s; snapshots_seen_init(&s); int ret = bch2_trans_run(c, for_each_btree_key(trans, iter, BTREE_ID_dirents, POS_MIN, BTREE_ITER_intent| BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, ({ ret = snapshots_seen_update(c, &s, iter.btree_id, k.k->p); if (ret) break; if (k.k->type == KEY_TYPE_dirent) { struct bkey_s_c_dirent d = bkey_s_c_to_dirent(k); if (d.v->d_type != DT_DIR && d.v->d_type != DT_SUBVOL) inc_link(c, &s, links, range_start, range_end, le64_to_cpu(d.v->d_inum), d.k->p.snapshot); } 0; }))); snapshots_seen_exit(&s); bch_err_fn(c, ret); return ret; } static int check_nlinks_update_inode(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k, struct nlink_table *links, size_t *idx, u64 range_end) { struct bch_inode_unpacked u; struct nlink *link = &links->d[*idx]; int ret = 0; if (k.k->p.offset >= range_end) return 1; if (!bkey_is_inode(k.k)) return 0; ret = bch2_inode_unpack(k, &u); if (ret) return ret; if (S_ISDIR(u.bi_mode)) return 0; if (!u.bi_nlink) return 0; while ((cmp_int(link->inum, k.k->p.offset) ?: cmp_int(link->snapshot, k.k->p.snapshot)) < 0) { BUG_ON(*idx == links->nr); link = &links->d[++*idx]; } if (fsck_err_on(bch2_inode_nlink_get(&u) != link->count, trans, inode_wrong_nlink, "inode %llu type %s has wrong i_nlink (%u, should be %u)", u.bi_inum, bch2_d_types[mode_to_type(u.bi_mode)], bch2_inode_nlink_get(&u), link->count)) { bch2_inode_nlink_set(&u, link->count); ret = __bch2_fsck_write_inode(trans, &u); } fsck_err: return ret; } noinline_for_stack static int check_nlinks_update_hardlinks(struct bch_fs *c, struct nlink_table *links, u64 range_start, u64 range_end) { size_t idx = 0; int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_inodes, POS(0, range_start), BTREE_ITER_intent|BTREE_ITER_prefetch|BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, check_nlinks_update_inode(trans, &iter, k, links, &idx, range_end))); if (ret < 0) { bch_err(c, "error in fsck walking inodes: %s", bch2_err_str(ret)); return ret; } return 0; } int bch2_check_nlinks(struct bch_fs *c) { struct nlink_table links = { 0 }; u64 this_iter_range_start, next_iter_range_start = 0; int ret = 0; do { this_iter_range_start = next_iter_range_start; next_iter_range_start = U64_MAX; ret = check_nlinks_find_hardlinks(c, &links, this_iter_range_start, &next_iter_range_start); ret = check_nlinks_walk_dirents(c, &links, this_iter_range_start, next_iter_range_start); if (ret) break; ret = check_nlinks_update_hardlinks(c, &links, this_iter_range_start, next_iter_range_start); if (ret) break; links.nr = 0; } while (next_iter_range_start != U64_MAX); kvfree(links.d); bch_err_fn(c, ret); return ret; } static int fix_reflink_p_key(struct btree_trans *trans, struct btree_iter *iter, struct bkey_s_c k) { struct bkey_s_c_reflink_p p; struct bkey_i_reflink_p *u; if (k.k->type != KEY_TYPE_reflink_p) return 0; p = bkey_s_c_to_reflink_p(k); if (!p.v->front_pad && !p.v->back_pad) return 0; u = bch2_trans_kmalloc(trans, sizeof(*u)); int ret = PTR_ERR_OR_ZERO(u); if (ret) return ret; bkey_reassemble(&u->k_i, k); u->v.front_pad = 0; u->v.back_pad = 0; return bch2_trans_update(trans, iter, &u->k_i, BTREE_TRIGGER_norun); } int bch2_fix_reflink_p(struct bch_fs *c) { if (c->sb.version >= bcachefs_metadata_version_reflink_p_fix) return 0; int ret = bch2_trans_run(c, for_each_btree_key_commit(trans, iter, BTREE_ID_extents, POS_MIN, BTREE_ITER_intent|BTREE_ITER_prefetch| BTREE_ITER_all_snapshots, k, NULL, NULL, BCH_TRANS_COMMIT_no_enospc, fix_reflink_p_key(trans, &iter, k))); bch_err_fn(c, ret); return ret; } #ifndef NO_BCACHEFS_CHARDEV struct fsck_thread { struct thread_with_stdio thr; struct bch_fs *c; struct bch_opts opts; }; static void bch2_fsck_thread_exit(struct thread_with_stdio *_thr) { struct fsck_thread *thr = container_of(_thr, struct fsck_thread, thr); kfree(thr); } static int bch2_fsck_offline_thread_fn(struct thread_with_stdio *stdio) { struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); struct bch_fs *c = thr->c; int ret = PTR_ERR_OR_ZERO(c); if (ret) return ret; ret = bch2_fs_start(thr->c); if (ret) goto err; if (test_bit(BCH_FS_errors_fixed, &c->flags)) { bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: errors fixed\n", c->name); ret |= 1; } if (test_bit(BCH_FS_error, &c->flags)) { bch2_stdio_redirect_printf(&stdio->stdio, false, "%s: still has errors\n", c->name); ret |= 4; } err: bch2_fs_stop(c); return ret; } static const struct thread_with_stdio_ops bch2_offline_fsck_ops = { .exit = bch2_fsck_thread_exit, .fn = bch2_fsck_offline_thread_fn, }; long bch2_ioctl_fsck_offline(struct bch_ioctl_fsck_offline __user *user_arg) { struct bch_ioctl_fsck_offline arg; struct fsck_thread *thr = NULL; darray_const_str devs = {}; long ret = 0; if (copy_from_user(&arg, user_arg, sizeof(arg))) return -EFAULT; if (arg.flags) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; for (size_t i = 0; i < arg.nr_devs; i++) { u64 dev_u64; ret = copy_from_user_errcode(&dev_u64, &user_arg->devs[i], sizeof(u64)); if (ret) goto err; char *dev_str = strndup_user((char __user *)(unsigned long) dev_u64, PATH_MAX); ret = PTR_ERR_OR_ZERO(dev_str); if (ret) goto err; ret = darray_push(&devs, dev_str); if (ret) { kfree(dev_str); goto err; } } thr = kzalloc(sizeof(*thr), GFP_KERNEL); if (!thr) { ret = -ENOMEM; goto err; } thr->opts = bch2_opts_empty(); if (arg.opts) { char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); ret = PTR_ERR_OR_ZERO(optstr) ?: bch2_parse_mount_opts(NULL, &thr->opts, NULL, optstr, false); if (!IS_ERR(optstr)) kfree(optstr); if (ret) goto err; } opt_set(thr->opts, stdio, (u64)(unsigned long)&thr->thr.stdio); opt_set(thr->opts, read_only, 1); opt_set(thr->opts, ratelimit_errors, 0); /* We need request_key() to be called before we punt to kthread: */ opt_set(thr->opts, nostart, true); bch2_thread_with_stdio_init(&thr->thr, &bch2_offline_fsck_ops); thr->c = bch2_fs_open(&devs, &thr->opts); if (!IS_ERR(thr->c) && thr->c->opts.errors == BCH_ON_ERROR_panic) thr->c->opts.errors = BCH_ON_ERROR_ro; ret = __bch2_run_thread_with_stdio(&thr->thr); out: darray_for_each(devs, i) kfree(*i); darray_exit(&devs); return ret; err: if (thr) bch2_fsck_thread_exit(&thr->thr); pr_err("ret %s", bch2_err_str(ret)); goto out; } static int bch2_fsck_online_thread_fn(struct thread_with_stdio *stdio) { struct fsck_thread *thr = container_of(stdio, struct fsck_thread, thr); struct bch_fs *c = thr->c; c->stdio_filter = current; c->stdio = &thr->thr.stdio; /* * XXX: can we figure out a way to do this without mucking with c->opts? */ unsigned old_fix_errors = c->opts.fix_errors; if (opt_defined(thr->opts, fix_errors)) c->opts.fix_errors = thr->opts.fix_errors; else c->opts.fix_errors = FSCK_FIX_ask; c->opts.fsck = true; set_bit(BCH_FS_in_fsck, &c->flags); int ret = bch2_run_online_recovery_passes(c, ~0ULL); clear_bit(BCH_FS_in_fsck, &c->flags); bch_err_fn(c, ret); c->stdio = NULL; c->stdio_filter = NULL; c->opts.fix_errors = old_fix_errors; up(&c->recovery.run_lock); bch2_ro_ref_put(c); return ret; } static const struct thread_with_stdio_ops bch2_online_fsck_ops = { .exit = bch2_fsck_thread_exit, .fn = bch2_fsck_online_thread_fn, }; long bch2_ioctl_fsck_online(struct bch_fs *c, struct bch_ioctl_fsck_online arg) { struct fsck_thread *thr = NULL; long ret = 0; if (arg.flags) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!bch2_ro_ref_tryget(c)) return -EROFS; if (down_trylock(&c->recovery.run_lock)) { bch2_ro_ref_put(c); return -EAGAIN; } thr = kzalloc(sizeof(*thr), GFP_KERNEL); if (!thr) { ret = -ENOMEM; goto err; } thr->c = c; thr->opts = bch2_opts_empty(); if (arg.opts) { char *optstr = strndup_user((char __user *)(unsigned long) arg.opts, 1 << 16); ret = PTR_ERR_OR_ZERO(optstr) ?: bch2_parse_mount_opts(c, &thr->opts, NULL, optstr, false); if (!IS_ERR(optstr)) kfree(optstr); if (ret) goto err; } ret = bch2_run_thread_with_stdio(&thr->thr, &bch2_online_fsck_ops); err: if (ret < 0) { bch_err_fn(c, ret); if (thr) bch2_fsck_thread_exit(&thr->thr); up(&c->recovery.run_lock); bch2_ro_ref_put(c); } return ret; } #endif /* NO_BCACHEFS_CHARDEV */ |
| 1 4 3 1 4 5 6 6 6 5 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * 9P Client * * Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com> * Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/errno.h> #include <linux/fs.h> #include <linux/poll.h> #include <linux/idr.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/uaccess.h> #include <linux/uio.h> #include <linux/netfs.h> #include <net/9p/9p.h> #include <linux/parser.h> #include <linux/seq_file.h> #include <net/9p/client.h> #include <net/9p/transport.h> #include "protocol.h" #define CREATE_TRACE_POINTS #include <trace/events/9p.h> /* DEFAULT MSIZE = 32 pages worth of payload + P9_HDRSZ + * room for write (16 extra) or read (11 extra) operands. */ #define DEFAULT_MSIZE ((128 * 1024) + P9_IOHDRSZ) /* Client Option Parsing (code inspired by NFS code) * - a little lazy - parse all client options */ enum { Opt_msize, Opt_trans, Opt_legacy, Opt_version, Opt_err, }; static const match_table_t tokens = { {Opt_msize, "msize=%u"}, {Opt_legacy, "noextend"}, {Opt_trans, "trans=%s"}, {Opt_version, "version=%s"}, {Opt_err, NULL}, }; inline int p9_is_proto_dotl(struct p9_client *clnt) { return clnt->proto_version == p9_proto_2000L; } EXPORT_SYMBOL(p9_is_proto_dotl); inline int p9_is_proto_dotu(struct p9_client *clnt) { return clnt->proto_version == p9_proto_2000u; } EXPORT_SYMBOL(p9_is_proto_dotu); int p9_show_client_options(struct seq_file *m, struct p9_client *clnt) { if (clnt->msize != DEFAULT_MSIZE) seq_printf(m, ",msize=%u", clnt->msize); seq_printf(m, ",trans=%s", clnt->trans_mod->name); switch (clnt->proto_version) { case p9_proto_legacy: seq_puts(m, ",noextend"); break; case p9_proto_2000u: seq_puts(m, ",version=9p2000.u"); break; case p9_proto_2000L: /* Default */ break; } if (clnt->trans_mod->show_options) return clnt->trans_mod->show_options(m, clnt); return 0; } EXPORT_SYMBOL(p9_show_client_options); /* Some error codes are taken directly from the server replies, * make sure they are valid. */ static int safe_errno(int err) { if (err > 0 || err < -MAX_ERRNO) { p9_debug(P9_DEBUG_ERROR, "Invalid error code %d\n", err); return -EPROTO; } return err; } /* Interpret mount option for protocol version */ static int get_protocol_version(char *s) { int version = -EINVAL; if (!strcmp(s, "9p2000")) { version = p9_proto_legacy; p9_debug(P9_DEBUG_9P, "Protocol version: Legacy\n"); } else if (!strcmp(s, "9p2000.u")) { version = p9_proto_2000u; p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.u\n"); } else if (!strcmp(s, "9p2000.L")) { version = p9_proto_2000L; p9_debug(P9_DEBUG_9P, "Protocol version: 9P2000.L\n"); } else { pr_info("Unknown protocol version %s\n", s); } return version; } /** * parse_opts - parse mount options into client structure * @opts: options string passed from mount * @clnt: existing v9fs client information * * Return 0 upon success, -ERRNO upon failure */ static int parse_opts(char *opts, struct p9_client *clnt) { char *options, *tmp_options; char *p; substring_t args[MAX_OPT_ARGS]; int option; char *s; int ret = 0; clnt->proto_version = p9_proto_2000L; clnt->msize = DEFAULT_MSIZE; if (!opts) return 0; tmp_options = kstrdup(opts, GFP_KERNEL); if (!tmp_options) return -ENOMEM; options = tmp_options; while ((p = strsep(&options, ",")) != NULL) { int token, r; if (!*p) continue; token = match_token(p, tokens, args); switch (token) { case Opt_msize: r = match_int(&args[0], &option); if (r < 0) { p9_debug(P9_DEBUG_ERROR, "integer field, but no integer?\n"); ret = r; continue; } if (option < 4096) { p9_debug(P9_DEBUG_ERROR, "msize should be at least 4k\n"); ret = -EINVAL; continue; } clnt->msize = option; break; case Opt_trans: s = match_strdup(&args[0]); if (!s) { ret = -ENOMEM; p9_debug(P9_DEBUG_ERROR, "problem allocating copy of trans arg\n"); goto free_and_return; } v9fs_put_trans(clnt->trans_mod); clnt->trans_mod = v9fs_get_trans_by_name(s); if (!clnt->trans_mod) { pr_info("Could not find request transport: %s\n", s); ret = -EINVAL; } kfree(s); break; case Opt_legacy: |